阅读说明：本技术 一种基于脑电波分析的施工安全监测方法和装置 (Construction safety monitoring method and device based on brain wave analysis ) 是由 刘妍 李燕姚 姚福义 佟文晶 于 2020-05-06 设计创作，主要内容包括：本公开提供一种基于脑电波分析的施工安全监测方法和装置,所述方法包括：采集施工人员的脑电波信号；根据所述脑电波信号,用预设的稀疏表示分类器进行分类,根据分类结果得到所述施工人员的疲劳程度；根据所述疲劳程度构建安全监测模型；将获取的危险处理信息输入所述安全监测模型,得到施工安全信息；根据所述施工安全信息判断所述施工人员是否存在施工安全隐患。本公开提供的方法和装置中,通过对施工人员的脑电波信号判断施工人员的疲劳程度,进而建立能够体现施工人员疲劳程度的安全监测模型,并利用所述模型监测施工人员是否存在安全隐患,利用脑电波技术对人的行为进行安全监管,极大程度可以避免安全事故的发生。(The present disclosure provides a construction safety monitoring method and apparatus based on brain wave analysis, the method comprising: collecting brain wave signals of constructors; classifying by using a preset sparse representation classifier according to the brain wave signals, and obtaining the fatigue degree of the constructors according to a classification result; constructing a safety monitoring model according to the fatigue degree; inputting the acquired danger processing information into the safety monitoring model to obtain construction safety information; and judging whether the construction personnel have construction potential safety hazards or not according to the construction safety information. According to the method and the device, the fatigue degree of the constructors is judged through the brain wave signals of the constructors, then a safety monitoring model capable of reflecting the fatigue degree of the constructors is established, whether the constructors have potential safety hazards or not is monitored through the model, safety supervision is conducted on the behaviors of the constructors through the brain wave technology, and safety accidents can be avoided to the maximum degree.)

1. A construction safety monitoring method based on brain wave analysis is characterized by comprising the following steps:

collecting brain wave signals of constructors;

classifying by using a preset sparse representation classifier according to the brain wave signals, and obtaining the fatigue degree of the constructors according to a classification result;

constructing a safety monitoring model according to the fatigue degree;

inputting the acquired danger processing information into the safety monitoring model to obtain construction safety information;

and judging whether the construction personnel have construction potential safety hazards or not according to the construction safety information.

2. The method as claimed in claim 1, further comprising, after the collecting of the brain wave signals of the constructor:

performing segmentation processing on the brain wave signals to obtain a plurality of wave band brain wave signals;

carrying out Fourier transform on the brain wave signals of the plurality of wave bands and calculating corresponding power spectral density;

and respectively calculating the energy characteristic values of the brain wave signals of the multiple wave bands according to the frequency distribution and the power spectral density of the brain wave signals.

3. The method according to claim 2, wherein the energy characteristic values of the plurality of band brain wave signals are calculated using the following relation:

wherein E is_αEnergy characteristic value of α wave band brain wave signal_βEnergy characteristic value of β wave band brain wave signal_θEnergy characteristic values of brain wave signals in theta wave bands; eEnergy characteristic values of wave band brain wave signals; freq is frequency in Hz; p is a radical of_freqIs the power spectral density of brain waves in the frequency freq band.

4. The method as claimed in claim 2, wherein the classifying with a preset sparse representation classifier according to the brain wave signal, and obtaining the fatigue degree of the constructor according to the classification result, comprises:

acquiring electroencephalogram characteristic matrixes corresponding to different fatigue degrees in advance to form training samples, and training by using the training samples to obtain the sparse representation classifier;

and classifying by using the sparse representation classifier according to the energy characteristic values of the brain wave signals with the multiple wave bands, and obtaining the fatigue degree of the constructors according to the classification result.

5. The method according to any one of claims 1 to 4, wherein the building of the safety monitoring model according to the fatigue level is in particular:

wherein, t_nReaction time for hazardous conditions, R_nFor correct handling of dangerous situations, F_nThe fatigue degree, a, b, and c are the correlation coefficients of the response time and safety, respectively.

6. The method according to any one of claims 1 to 4, wherein the inputting the acquired danger handling information into the safety monitoring model to obtain construction safety information comprises:

acquiring actual dangerous condition reaction time;

acquiring the correct processing rate of the actual dangerous condition;

and inputting the obtained actual dangerous condition reaction time and the actual dangerous condition correct processing rate into the safety monitoring model to obtain the construction safety information.

7. The method of claim 6, wherein said obtaining actual hazardous condition reaction time comprises:

acquiring time from occurrence of multiple dangerous conditions to occurrence of reaction within a preset time interval to obtain multiple original dangerous condition reaction times;

and obtaining the actual dangerous situation reaction time according to the plurality of original dangerous situation reaction times.

8. The method of claim 6, wherein said obtaining the correct handling rate of the actual dangerous condition comprises:

acquiring dangerous condition processing times and dangerous condition correct processing times within a preset time interval;

and obtaining the correct handling rate of the actual dangerous situation according to the dangerous situation handling times and the dangerous situation correct handling times.

9. The method according to any one of claims 1 to 4, wherein the determining whether the constructor has the construction safety hazard according to the construction safety information comprises:

if the construction safety information is less than or equal to a preset first threshold value, judging that the construction personnel has construction safety hidden danger; otherwise, judging that the construction personnel does not have construction potential safety hazards.

10. A construction safety monitoring device based on brain wave analysis is characterized by comprising:

the acquisition module is used for acquiring brain wave signals of constructors;

the analysis module is used for classifying by using a preset sparse representation classifier according to the brain wave signals and obtaining the fatigue degree of the constructors according to a classification result;

the model construction module is used for constructing a safety monitoring model according to the fatigue degree;

the processing module is used for inputting the acquired danger processing information into the safety monitoring model to obtain construction safety information;

and the judging module is used for judging whether the construction personnel have construction potential safety hazards or not according to the construction safety information.

Technical Field

The disclosure belongs to the technical field of construction safety monitoring, and particularly relates to a construction safety monitoring method based on brain wave analysis and a construction safety monitoring device based on brain wave analysis.

Background

Based on the existing literature search and the actual situation of a construction site, aiming at construction safety management, at present, most of the equipment of construction is improved or safely supervised, for example, aiming at a tower crane, the traditional construction safety monitoring technology comprises a black box technology, a hook positioning technology and the like, the equipment finally needs to be operated by people, and few researches take people as research objects, but the operation of people is very important for the safety of hoisting operation, and the safe operation needs that constructors have clear cognitive ability and quick reaction ability, so that the fatigue degree of the constructors, such as operators such as a tower crane and the like, needs to be monitored.

Disclosure of Invention

The present disclosure is directed to at least one of the technical problems of the prior art, and provides a construction safety monitoring method and a construction safety monitoring apparatus based on brain wave analysis.

In one aspect of the present disclosure, a construction safety monitoring method based on brain wave analysis is provided, including:

collecting brain wave signals of constructors;

classifying by using a preset sparse representation classifier according to the brain wave signals, and obtaining the fatigue degree of the constructors according to a classification result;

constructing a safety monitoring model according to the fatigue degree;

inputting the acquired danger processing information into the safety monitoring model to obtain construction safety information;

and judging whether the construction personnel have construction potential safety hazards or not according to the construction safety information.

Optionally, after acquiring brain wave signals of constructors, the method further includes:

performing segmentation processing on the brain wave signals to obtain a plurality of wave band brain wave signals;

carrying out Fourier transform on the brain wave signals of the plurality of wave bands and calculating corresponding power spectral density;

and respectively calculating the energy characteristic values of the brain wave signals of the multiple wave bands according to the frequency distribution and the power spectral density of the brain wave signals.

Optionally, the energy characteristic values of the brain wave signals of multiple wave bands are calculated by using the following relational expression:

wherein E is_αEnergy characteristic value of α wave band brain wave signal_βEnergy characteristic value of β wave band brain wave signal_θEnergy characteristic values of brain wave signals in theta wave bands; eEnergy characteristic values of wave band brain wave signals; freq is frequency in Hz; p is a radical of_freqIs the power spectral density of brain waves in the frequency freq band.

Optionally, the classifying the brain wave signal by using a preset sparse representation classifier, and obtaining the fatigue degree of the constructor according to a classification result includes:

acquiring electroencephalogram characteristic matrixes corresponding to different fatigue degrees in advance to form training samples, and training by using the training samples to obtain the sparse representation classifier;

and classifying by using the sparse representation classifier according to the energy characteristic values of the brain wave signals with the multiple wave bands, and obtaining the fatigue degree of the constructors according to the classification result.

Optionally, the building of the safety monitoring model according to the fatigue degree specifically includes:

wherein, t_nReaction time for hazardous conditions, R_nFor correct handling of dangerous situations, F_nThe fatigue degree, a, b, and c are the correlation coefficients of the response time and safety, respectively.

Optionally, the step of inputting the acquired danger handling information into the safety monitoring model to obtain construction safety information includes:

acquiring actual dangerous condition reaction time;

acquiring the correct processing rate of the actual dangerous condition;

and inputting the obtained actual dangerous condition reaction time and the actual dangerous condition correct processing rate into the safety monitoring model to obtain the construction safety information.

Optionally, the obtaining of the actual reaction time of the dangerous situation includes:

acquiring time from occurrence of multiple dangerous conditions to occurrence of reaction within a preset time interval to obtain multiple original dangerous condition reaction times;

and obtaining the actual dangerous situation reaction time according to the plurality of original dangerous situation reaction times.

Optionally, the obtaining of the correct handling rate of the actual dangerous condition includes:

acquiring dangerous condition processing times and dangerous condition correct processing times within a preset time interval;

and obtaining the correct handling rate of the actual dangerous situation according to the dangerous situation handling times and the dangerous situation correct handling times.

Optionally, the determining whether the constructor has the potential safety hazard according to the construction safety information includes:

if the construction safety information is less than or equal to a preset first threshold value, judging that the construction personnel has construction safety hidden danger; otherwise, judging that the construction personnel does not have construction potential safety hazards.

In another aspect of the present disclosure, there is provided a construction safety monitoring apparatus based on brain wave analysis, including:

the acquisition module is used for acquiring brain wave signals of constructors;

the analysis module is used for classifying by using a preset sparse representation classifier according to the brain wave signals and obtaining the fatigue degree of the constructors according to a classification result;

the model construction module is used for constructing a safety monitoring model according to the fatigue degree;

the processing module is used for inputting the acquired danger processing information into the safety monitoring model to obtain construction safety information;

and the judging module is used for judging whether the construction personnel have construction potential safety hazards or not according to the construction safety information.

In the construction safety monitoring method based on brain wave analysis and the construction safety monitoring device based on brain wave analysis, the fatigue degree of constructors is judged through brain wave signals of the constructors, then a safety monitoring model capable of reflecting the fatigue degree of the constructors is established, whether the constructors have potential safety hazards is monitored through the model, safety supervision is carried out on behaviors of people through brain wave technology, and safety accidents can be avoided to the maximum extent.

Drawings

Fig. 1 is a block diagram schematically illustrating the components of an electronic device according to a first embodiment of the present disclosure;

fig. 2 is a schematic flow chart of a construction safety monitoring method based on electroencephalogram analysis according to a second embodiment of the present disclosure;

fig. 3 is a schematic structural diagram of a construction safety monitoring device based on electroencephalogram analysis according to a third embodiment of the present disclosure;

fig. 4 is a schematic diagram illustrating a processing flow of brain wave signals according to a second embodiment of the present disclosure.

Detailed Description

For a better understanding of the technical aspects of the present disclosure, reference is made to the following detailed description taken in conjunction with the accompanying drawings.

First, an example electronic device for implementing a construction safety monitoring method based on brain wave analysis and a construction safety monitoring apparatus based on brain wave analysis of the embodiments of the present disclosure is described with reference to fig. 1.

As shown in FIG. 1, electronic device 200 includes one or more processors 210, one or more memory devices 220, one or more input devices 230, one or more output devices 240, and the like, interconnected by a bus system 250 and/or other form of connection mechanism. It should be noted that the components and structures of the electronic device shown in fig. 1 are exemplary only, and not limiting, and the electronic device may have other components and structures as desired.

The processor 210 may be a Central Processing Unit (CPU) or other form of processing unit having data processing capabilities and/or instruction execution capabilities, and may control other components in the electronic device 200 to perform desired functions.

Storage 220 may include one or more computer program products that may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. The volatile memory may include, for example, Random Access Memory (RAM), cache memory (cache), and/or the like. The non-volatile memory may include, for example, Read Only Memory (ROM), hard disk, flash memory, etc. On which one or more computer program instructions may be stored that a processor may execute to implement the client functionality (implemented by the processor) in the embodiments of the disclosure described below and/or other desired functionality. Various applications and various data, such as various data used and/or generated by the applications, may also be stored in the computer-readable storage medium.

The input device 230 may be a device used by a user to input instructions and may include one or more of a keyboard, a mouse, a microphone, a touch screen, and the like.

The output device 240 may output various information (e.g., images or sounds) to an outside (e.g., a user), and may include one or more of a display, a speaker, and the like.

Next, a construction safety monitoring method based on brain wave analysis according to an embodiment of the present disclosure will be described with reference to fig. 2.

As shown in fig. 2, a construction safety monitoring method S100 based on brain wave analysis includes:

s110: and collecting brain wave signals of constructors.

Specifically, in the step, according to actual requirements, brain wave information of construction personnel is collected, for example, one or more of α brain waves, β brain waves, theta brain waves and gamma brain waves are collected.

Specifically, in this step, a specific device may be used to collect brain wave information, and for example, an emotv Epoc + wireless portable electroencephalograph monitor and a matched emoti pro software may be used as an electroencephalogram signal collecting device to collect electroencephalograms of a constructor in real time, and transmit the electroencephalograms to a PC terminal through a USB receiver for signal analysis. Besides, other devices can be used to acquire brain wave signals, which can be determined according to actual needs, and the embodiments of the present disclosure do not limit this.

S120: and classifying by using a preset sparse representation classifier according to the brain wave signals, and obtaining the fatigue degree of the constructors according to the classification result.

Specifically, in this step, the brain wave signal is input into a sparse representation classifier as a test sample, residual analysis is performed on the test sample in the sparse representation classifier to obtain a training sample corresponding to the test sample, and the fatigue degree of the test sample is obtained according to the corresponding training sample. The preset sparse representation classifier can be obtained through experience, and can also be specifically set according to different actual construction conditions, for example, the sparse representation classifier for classifying the fatigue degree of the hoisting tower crane is set by a needle.

S130: and constructing a safety monitoring model according to the fatigue degree.

Specifically, in this step, parameters of the safety monitoring model are set according to the fatigue degree, and different safety monitoring models with different fatigue degrees are obtained. The safety monitoring model may use a safety monitoring model in the prior art, for example, a construction safety model related to construction duration may be constructed, and may be determined according to actual needs, which is not limited by the embodiments of the present disclosure.

S140: and inputting the acquired danger processing information into the safety monitoring model to obtain construction safety information.

Specifically, in this step, the acquired danger handling information includes information related to handling operation of the construction danger by the constructor detected by the detection device at the construction site, and may be an operation image of the constructor or a motion image of the construction equipment detected by the imaging device installed at the construction site, or may be motion information of the constructor or motion information detected by the sensing device, and for example, an operation image of the tower crane to the tower crane or a motion image of the tower crane detected by the camera may be determined according to actual needs, which is not limited by the embodiment of the present disclosure.

Further, in this step, the acquired danger processing information is input into the safety monitoring model, and the safety monitoring model is solved to obtain the construction safety information.

S150: and judging whether the construction personnel have construction potential safety hazards or not according to the construction safety information.

Specifically, in this step, whether the constructor has a construction safety hazard is judged according to the construction safety information by a preset judgment method, and the preset judgment method may be determined according to actual needs, for example, a threshold judgment method may be used, which is not limited in the embodiment of the present disclosure. Further, in this step, if it is determined that there is a construction safety hazard, an alarm is given, specifically, an alarm device installed at a construction site, such as a horn, may be used for giving an alarm, and an alarm device worn by a constructor, such as a wearable alarm, may also be used for giving an alarm.

According to the construction safety monitoring method based on brain wave analysis, the fatigue degree of a constructor is judged by detecting brain wave signals of the constructor, a construction safety monitoring model is built according to the fatigue degree, whether the constructor has potential safety hazards or not is monitored through the safety monitoring model, the potential safety hazards are monitored by combining the working state of the constructor, the technical problems that the potential safety hazards can be judged only by comparing the operation correctness of the constructor or construction equipment and prejudgment cannot be realized in the traditional technology are solved, the safety monitoring capable of judging the potential safety hazards in advance is realized, and the accuracy of the safety monitoring is improved.

In order to improve the accuracy of obtaining the fatigue degree of the constructor according to the brain wave signals, the collected brain wave signals need to be processed as necessary, and meanwhile, the accuracy of classification of the preset sparse representation classifier needs to be ensured.

Exemplarily, with reference to fig. 4, after step S110, the method further includes:

s111: and denoising the brain wave signal.

In order to reduce noise in the brain wave signal, reduce external interference of the brain wave signal, and improve accuracy of post-signal processing, it is necessary to perform denoising processing on the brain wave signal. Specifically, in the step, denoising processing is performed through filtering, filtering is performed by adopting a linear filter, and denoising processing of the electroencephalogram signal is performed by combining a wavelet threshold decomposition method. Of course, besides, those skilled in the art may select some other ways to perform denoising processing according to actual needs, which is not limited by the embodiments of the present disclosure.

S112: and carrying out segmentation processing on the brain wave signals to obtain a plurality of wave band brain wave signals.

Specifically, in the step, the brain wave signals are segmented according to preset frequency intervals to obtain brain wave signals with a plurality of wave bands, the preset frequency intervals can be equal intervals or unequal intervals, and can also be segmented according to specific frequency distribution according to actual needs, for example, the wave bands can be divided according to different frequencies of α, β, gamma and theta, and through the segmentation processing of the brain wave signals, the post-processing calculation amount is reduced, so that the brain waves of the target wave band can be acquired quickly.

S113: and carrying out Fourier transform on the brain wave signals of the plurality of wave bands and calculating corresponding power spectral density.

Specifically, in this step, the power spectral densities corresponding to the brain wave signals in multiple bands are calculated by the following relational expression:

wherein freq represents the frequency, i.e. in the band of frequencies freq, p_freq(n) is the power spectral density of brain waves in the frequency freq band, F_freq(n) is the original power of the band freq at sample point n,the power of a wave band freq after N Fourier transform at a sampling point is obtained, N is an electroencephalogram signal sampling point, and N is an electroencephalogram signal sampling frequency.

S114: and respectively calculating the energy characteristic values of the brain wave signals of the multiple wave bands according to the frequency distribution and the power spectral density of the brain wave signals.

Specifically, in this step, the energy characteristic values of the plurality of band brain wave signals are calculated using the following relational expression:

wherein freq is frequency and unit is Hz; p is a radical of_freqPower spectral density of brain waves in a band of frequency freq; e_αEnergy characteristic value of α wave band brain wave signal, i.e. energy characteristic value of brain wave signal with frequency of 8-13 Hz, E_βEnergy characteristic value of β wave band brain wave signal, i.e. the energy characteristic value of the brain wave signal with frequency of 14-30 Hz, E_θThe energy characteristic value of the theta-band brain wave signal is the energy characteristic value of the brain wave signal with the frequency of 4-7 Hz; eThe energy characteristic value of the wave band brain wave signal is the energy characteristic value of the brain wave signal with the frequency of 0.5-3 Hz.

Illustratively, step S120 includes:

s121: acquiring electroencephalogram characteristic matrixes corresponding to different fatigue degrees in advance to form training samples, and training by using the training samples to obtain the sparse representation classifier.

Specifically, in this step, an electroencephalogram feature matrix capable of representing five types of fatigue degrees is constructed according to the collected empirical data, and a corresponding feature matrix is constructed for the five types of fatigue degrees, and is a five energy feature value feature matrix, that is, five training samples corresponding to the five types of fatigue degrees, for example, in this embodiment, the five types of fatigue degrees may be 1, 3, 5, 7, and 9.

S122: and classifying by using the sparse representation classifier according to the energy characteristic values of the brain wave signals with the multiple wave bands, and obtaining the fatigue degree of the constructors according to the classification result.

Specifically, in this step, the energy eigenvalue of the brain wave signal is input into a sparse representation classifier as a test sample, the test sample and five training samples are respectively associated with the sparse representation classifier, residual analysis is performed on the test sample and the five training samples respectively, a training sample with the highest correlation with the test sample is obtained, and then the fatigue degrees corresponding to the test sample and the training sample are the same, so that a classification result is obtained, that is, the fatigue degree of the brain wave signal is obtained.

According to the construction safety monitoring method based on brain wave analysis, the accuracy of the brain wave signal is improved by performing preprocessing such as denoising on the brain wave signal; inputting the energy characteristic value as a test sample into a sparse representation classifier for residual analysis; the brain wave feature matrixes of multiple fatigue degrees are constructed, the classification result of the fatigue degrees is refined, and the accuracy of fatigue degree classification is improved through the method, so that the accuracy of safety monitoring is improved.

In order to ensure the accuracy of safety monitoring, in addition to improving the accuracy of detecting and classifying brain wave signals, the accuracy of a safety monitoring model constructed according to the fatigue degree of brain constructors needs to be ensured, and the process of constructing the safety monitoring model according to the fatigue degree of constructors and the process of performing safety monitoring according to the safety monitoring model will be further described below, but the embodiment of the disclosure is not limited thereto.

Illustratively, step S130 further includes:

the method for constructing the safety monitoring model according to the fatigue degree specifically comprises the following steps:

wherein, t_nReaction time for hazardous conditions, R_nFor correct handling of dangerous situations, F_nThe fatigue degree, a, b, and c are the correlation coefficients of the response time and safety, respectively.

Specifically, in this step, a safety monitoring model is constructed according to the dangerous condition reaction time, the dangerous correct handling rate and the fatigue degree as input parameters, and the output S of the safety monitoring model_nNamely the construction safety information. Wherein, degree of fatigue F_nThe fatigue level of the operator obtained from the electroencephalogram signal may be any one of 1, 3, 5, 7, and 9.

Specifically, in this step, the correlation coefficient a of the fatigue degree and the safety, the correlation coefficient b of the reaction time and the safety, and the correlation coefficient c of the correct processing rate and the safety may be set according to actual use conditions, and for example, the coefficient a may be set to 5, the coefficient b may be set to 0.14, and c may be set to 1.67.

Further, the safety monitoring model constructed according to the fatigue degree can be further improved, and specifically, the method comprises the following steps:

the improved model is based on the model, the first constant coefficient d and the second constant coefficient e are added, and the flexibility of the model in a specific use process is improved. Also, the first constant coefficient d and the second constant coefficient e may be set according to actual use conditions. For example, in the improved model, the coefficient a may be set to 7.592, the coefficient b may be set to 0.5, c may be set to 0.5, the first constant coefficient d may be set to 105.11, and the second constant coefficient e may be set to 120, but other coefficient values may be set by those skilled in the art according to actual needs, and the embodiment of the disclosure is not limited thereto.

The above describes a process of constructing a safety monitoring model, and the following describes a process of obtaining construction safety information according to danger handling information and a constructed safety monitoring model.

Illustratively, the construction safety information in step S140 includes actual dangerous situation reaction time and an actual dangerous situation correct processing rate, and step S140 further includes:

s141: and acquiring the actual dangerous situation reaction time.

Specifically, in this step, the actual dangerous situation response time is an actual response time of the construction worker facing the dangerous situation, and the acquiring of the actual dangerous situation response time may be a time from occurrence of the dangerous situation to start of operation of the construction worker facing the dangerous situation, or may be a time from occurrence of the dangerous situation to start of operation of the construction equipment.

Further, in this step, the actual hazardous situation reaction time may be obtained using a construction site installed device. For example, the image of the construction site may be detected by using the image capturing device, the time when the dangerous condition of the construction site occurs is detected, the time when the constructor starts to react and operate is detected, or the time when the construction equipment starts to perform the risk avoiding action is detected, and the actual dangerous condition reaction time is obtained by using the difference between the times.

Illustratively, step S141 further includes:

and acquiring the time from the occurrence of a plurality of dangerous conditions to the occurrence of reaction within a preset time interval to obtain a plurality of original dangerous condition reaction times. Specifically, in this step, the preset time interval is a time period set according to actual conditions, and may be 30 minutes as an example. The obtaining of the multiple original dangerous condition reaction times is to obtain the reaction times for all the dangerous conditions within the preset time interval, and for example, if 5 dangerous conditions occur within 30 minutes of the preset time interval, the obtained reaction times are to obtain the original dangerous condition reaction times for processing the 5 dangerous conditions.

And obtaining the actual dangerous situation reaction time according to the plurality of original dangerous situation reaction times. Specifically, in this step, the actual dangerous situation reaction time is obtained by averaging the plurality of original dangerous situation reaction times.

S142: and acquiring the correct processing rate of the actual dangerous condition.

Specifically, in this step, the correct handling of the dangerous condition refers to that the constructor takes a correct reflection measure to avoid causing field loss when an emergency occurs, and the incorrect handling of the dangerous condition refers to that the constructor does not operate in violation during the construction operation. The actual dangerous condition correct processing rate is the probability of correct processing when the constructor faces the dangerous condition. Exemplarily, step S142 specifically includes:

and acquiring dangerous condition processing times and dangerous condition correct processing times within a preset time interval. The actual dangerous condition handling times are the times of handling by constructors in the face of dangerous conditions, can be the times of operation by the constructors and can also be the times of movement of construction equipment; the actual dangerous condition handling times are the times for the constructors to carry out correct handling when facing the dangerous condition, can be the times for the constructors to carry out correct operation, and can also be the times for the constructors to correctly move.

Specifically, in this step, the preset time interval is a time period set according to actual conditions, and may be 30 minutes as an example. The obtaining of the number of dangerous condition handling times and the number of dangerous condition correct handling times within the preset time interval is to obtain the number of handling times and the number of correct handling times for all dangerous conditions within the preset time interval, for example, if 5 dangerous conditions occur within 30 minutes of the preset time interval, and an operator handles 4 dangerous conditions, and correctly handles 1 dangerous condition, the number of dangerous condition handling times is to obtain 4 dangerous condition handling times and 1 dangerous condition correct handling times within 30 minutes.

Further, the actual dangerous situation handling times include times that the constructor does not handle when facing a dangerous situation, for example, if 5 dangerous situations occur within 30 minutes of a preset time interval, and the operator handles 4 times and correctly handles 1 time, the number of times of handling 5 dangerous situations and the number of times of correctly handling 1 dangerous situation within 30 minutes are obtained.

Further, in this step, the dangerous situation handling number and the dangerous situation correct handling number may be acquired using a device installed at a construction site. For example, an image of a construction site can be detected by using the camera device, an image of operation performed by a constructor in the face of a dangerous condition is detected, and the number of times of operation performed by the constructor and the number of times of correct operation performed by the constructor are obtained through image recognition and image analysis; or detecting the image of the movement of the construction equipment facing the dangerous condition by using the camera device, and obtaining the times of the movement of the construction equipment for avoiding the danger and the times of the correct movement of the construction equipment through image recognition and image analysis. Besides, the skilled person can select other ways, such as sensors, etc., to obtain the actual reaction time of the dangerous situation according to the actual needs, which is not limited by the embodiments of the present disclosure.

Obtaining the actual dangerous situation correct processing rate according to the dangerous situation processing times and the dangerous situation correct processing times, wherein the actual dangerous situation correct processing rate is specifically shown in the following relational expression:

besides, a person skilled in the art can select other methods according to actual needs to obtain the correct handling rate of the actual dangerous situation, which is not limited by the embodiments of the present disclosure.

S143: and inputting the obtained actual dangerous condition reaction time and the actual dangerous condition correct processing rate into the safety monitoring model to obtain the construction safety information.

Specifically, in this step, the actual dangerous situation reaction time and the actual dangerous situation right place to be obtainedThe physical rates are respectively taken as t_nAnd R_nInputting the safety monitoring model, and calculating to obtain construction safety information S_n。

The above description explains the process of obtaining the construction safety information according to the danger handling information and the constructed safety monitoring model, and further explains the process of judging whether the potential safety hazard exists according to the construction safety information.

Exemplarily, step S150 specifically includes:

if the construction safety information is less than or equal to a preset first threshold value, judging that the construction personnel has construction safety hidden danger; otherwise, judging that the construction personnel does not have construction potential safety hazards.

In this step, the preset first threshold is a statement set according to actual conditions, and may be set to 60 as an example.

According to the construction safety monitoring method based on brain wave analysis, the construction safety information is obtained according to the actual dangerous condition reaction time and the actual dangerous condition correct processing rate, whether potential safety hazards exist or not is judged according to the construction safety information, namely, the fatigue degree obtained through brain wave signals is removed, the specific operation conditions of construction personnel facing danger are gathered to monitor safety risks, and the accuracy and the reliability of safety monitoring are improved.

Next, a construction safety monitoring device 100 based on electroencephalogram analysis according to another embodiment of the present disclosure is described with reference to fig. 3, which can be applied to the construction safety monitoring method based on electroencephalogram analysis described above, and specific contents thereof can refer to the related descriptions above, and are not described herein again. The device comprises an acquisition module 110, an analysis module 120, a model construction module 130, a processing module 140 and a judgment module 150, specifically:

the acquisition module 110 is used for acquiring brain wave signals of constructors;

the analysis module 120 is configured to classify the brain wave signal by using a preset sparse representation classifier, and obtain the fatigue degree of the constructor according to a classification result;

a model construction module 130, configured to construct a safety monitoring model according to the fatigue degree;

the processing module 140 is configured to input the acquired danger processing information into the safety monitoring model to obtain construction safety information;

and the judging module 150 is used for judging whether the construction personnel have construction potential safety hazards according to the construction safety information.

According to the construction safety monitoring device based on brain wave analysis, the fatigue degree of a constructor is judged by detecting brain wave signals of the constructor, a construction safety monitoring model is built according to the fatigue degree, whether the constructor has potential safety hazards or not is monitored through the safety monitoring model, the potential safety hazards are monitored by combining the working state of the constructor, the technical problems that the potential safety hazards can be judged only by comparing the operation correctness of the constructor or construction equipment and prejudgment cannot be realized in the traditional technology are solved, the safety monitoring capable of prejudging the potential safety hazards is realized, and the accuracy of the safety monitoring is improved.

Further, the device further comprises a brain wave processing module 111, configured to perform denoising processing on the brain wave signal; the electroencephalogram processing module is used for carrying out segmentation processing on the electroencephalogram signals to obtain a plurality of waveband electroencephalogram signals; the system comprises a plurality of wave band brain wave signals, a plurality of signal processing units and a power spectrum density calculation unit, wherein the signal processing units are used for carrying out Fourier transform on the plurality of wave band brain wave signals and calculating corresponding power spectrum density; the energy characteristic values of the brain wave signals of the multiple wave bands are respectively calculated according to the frequency distribution and the power spectral density of the brain wave signals.

Further, the analysis module 120 further includes a classifier construction sub-module and a classification sub-module.

The classifier construction submodule is used for acquiring electroencephalogram characteristic matrixes corresponding to different fatigue degrees in advance to form training samples, and training the training samples to obtain the sparse representation classifier; and the classification submodule is used for classifying by using the sparse representation classifier according to the energy characteristic values of the brain wave signals of the multiple wave bands, and obtaining the fatigue degree of the constructors according to the classification result.

Further, the processing module 140 further includes an obtaining sub-module and an operation sub-module.

The obtaining submodule is used for obtaining actual dangerous condition reaction time and obtaining the correct handling rate of the actual dangerous condition, specifically obtaining the time from the occurrence of a plurality of dangerous conditions to the occurrence of a reaction within a preset time interval to obtain a plurality of original dangerous condition reaction times, and obtaining the actual dangerous condition reaction time according to the plurality of original dangerous condition reaction times; and acquiring dangerous condition processing times and dangerous condition correct processing times within a preset time interval, and acquiring the actual dangerous condition correct processing rate according to the dangerous condition processing times and the dangerous condition correct processing times.

And the operation submodule is used for inputting the obtained actual dangerous condition reaction time and the actual dangerous condition correct processing rate into the safety monitoring model to obtain the construction safety information.

The construction safety monitoring device based on brain wave analysis can monitor safety risks by combining the correct processing rate according to fatigue degree, actual dangerous condition reaction time and actual dangerous condition, and improves the accuracy and reliability of safety monitoring.

Further, the embodiment further discloses an electronic device, including:

one or more processors;

a storage unit for storing one or more programs, which when executed by the one or more processors, enable the one or more processors to implement the construction safety monitoring method based on brain wave analysis as set forth above.

Further, a computer-readable storage medium is disclosed in the present embodiment, and a computer program is stored thereon, and when being executed by a processor, the computer program can implement the construction safety monitoring method based on brain wave analysis as described above.

The computer readable medium may be included in the apparatus, device, system, or may exist separately.

The computer readable storage medium may be any tangible medium that can contain or store a program, and may be an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, more specific examples of which include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, an optical fiber, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

The computer readable storage medium may also include a propagated data signal with computer readable program code embodied therein, for example, in a non-transitory form, such as in a carrier wave or in a carrier wave, wherein the carrier wave is any suitable carrier wave or carrier wave for carrying the program code.

It is to be understood that the above embodiments are merely exemplary embodiments that are employed to illustrate the principles of the present disclosure, and that the present disclosure is not limited thereto. It will be apparent to those skilled in the art that various changes and modifications can be made therein without departing from the spirit and scope of the disclosure, and these are to be considered as the scope of the disclosure.