阅读说明：本技术 一种电力设备运行状态监测系统及方法 (Power equipment running state monitoring system and method ) 是由 景光良 李震 于政弘 苏锋 杜娟 于 2021-08-09 设计创作，主要内容包括：本发明提出的一种电力设备运行状态监测系统,包括：数据采集单元,安装在电力设备壳体上,用于采集电力设备运行过程中的声音信号；无线传输单元,用于将声音信号通过无线网络进行传输；云服务平台,用于接收无线网络传输的声音信号,将声音信号转换为音频数据,并提取音频数据的音频特征,应用预设分类算法识别音频特征,生成对应的分类结果；报警单元,用于根据分类结果确定电缆设备是否存在故障,若存在,显示分类结果对应的故障种类并进行报警。(The invention provides a power equipment running state monitoring system, which comprises: the data acquisition unit is arranged on the shell of the power equipment and is used for acquiring sound signals in the operation process of the power equipment; the wireless transmission unit is used for transmitting the sound signal through a wireless network; the cloud service platform is used for receiving the sound signals transmitted by the wireless network, converting the sound signals into audio data, extracting audio features of the audio data, identifying the audio features by applying a preset classification algorithm, and generating corresponding classification results; and the alarm unit is used for determining whether the cable equipment has faults according to the classification result, and if so, displaying the fault type corresponding to the classification result and giving an alarm.)

1. An electrical equipment operating condition monitoring system, comprising:

the data acquisition unit is arranged on the shell of the power equipment and is used for acquiring sound signals in the operation process of the power equipment;

the wireless transmission unit is used for transmitting the sound signal through a wireless network;

the cloud service platform is used for receiving the sound signals transmitted by the wireless network, converting the sound signals into audio data, extracting audio features of the audio data, identifying the audio features by applying a preset classification algorithm, and generating corresponding classification results;

and the alarm unit is used for determining whether the cable equipment has faults according to the classification result, and if so, displaying the fault type corresponding to the classification result and giving an alarm.

2. The power equipment operating condition monitoring system according to claim 1, wherein the data acquisition unit includes:

the first acquisition module is used for acquiring sound signals in the running process of the rotary power equipment;

and the second acquisition module is used for acquiring sound signals in the operation process of the non-rotating power equipment.

3. The power equipment operating condition monitoring system according to claim 2, wherein the rotating power equipment includes: the system comprises an induced draft fan, a generator, a wind turbine generator, a water turbine and a bearing; the non-rotating electrical device includes: boiler, circuit breaker, transformer, fuel cutter and governing valve.

4. The electrical equipment operating condition monitoring system according to claim 1, wherein the cloud service platform comprises:

the preprocessing unit is used for carrying out sound channel conversion and pre-emphasis conversion on the sound signals to generate corresponding audio data;

the segmentation unit is used for identifying whether the audio data comprises target audio data, if so, sending the audio data to the sound source separation unit, and if not, sending a collection signal to the data collection unit to control the data collection unit to collect the sound signal again;

a sound source separating unit for separating target audio data from the audio data;

the audio feature extraction unit is used for extracting feature data containing power equipment fault information from state data in the target audio data as audio features;

and the classification unit is used for calculating the audio features by using a fuzzy C-means clustering algorithm, determining a fuzzy classification matrix of the fault audio features corresponding to the audio features, obtaining the closeness of the clustering center of the fault audio features, and determining fault classification numbers according to the closeness.

5. The system for monitoring the operating state of the electrical equipment according to claim 4, wherein the fuzzy classification matrix and the clustering center of the fault audio features are generated through fault sound training, and specifically comprise:

carrying out 3-layer wavelet packet decomposition on the audio frequency characteristics of the power equipment with known faults, taking the sensitive frequency band energy of the wavelet packet as identification characteristic quantity, and carrying out fuzzy clustering on the identification characteristic quantity by utilizing a fuzzy C mean value clustering algorithm to obtain a fuzzy classification matrix and a clustering center of the audio frequency characteristics of the faults.

6. The electrical equipment operating condition monitoring system according to claim 4, wherein the alarm unit includes:

and the identification module is used for searching whether the classification unit exists in the preset fault classification list to determine the fault classification number, and if so, displaying the fault type corresponding to the fault classification number and giving an alarm.

7. A method for monitoring the running state of electric equipment is characterized by comprising the following steps:

s1: collecting sound signals in the operation process of the power equipment;

s2: transmitting the sound signal through a wireless network;

s3: receiving a sound signal transmitted by a wireless network, converting the sound signal into audio data, extracting audio features of the audio data, identifying the audio features by applying a preset classification algorithm, and generating a corresponding classification result;

s4: and determining whether the cable equipment has faults according to the classification result, and if so, displaying the fault type corresponding to the classification result and giving an alarm.

8. The power equipment operation state monitoring method according to claim 7, wherein the step S3 includes:

s31: carrying out sound channel conversion and pre-emphasis conversion on the sound signals to generate corresponding audio data;

s32: identifying whether the audio data comprises target audio data, if so, sending the audio data to a sound source separation unit, otherwise, sending a collection signal to a data collection unit, and controlling the data collection unit to collect the sound signal again;

s33: separating target audio data from the audio data;

s34: extracting characteristic data containing power equipment fault information from state data in the target audio data to serve as audio characteristics;

s35: and calculating audio features by using a fuzzy C-means clustering algorithm, determining a fuzzy classification matrix of the fault audio features corresponding to the audio features, obtaining the closeness of the clustering center of the fault audio features, and determining fault classification numbers according to the closeness.

9. The method for monitoring the operating state of the electrical equipment according to claim 8, wherein the step S4 specifically includes:

and searching whether a classification unit exists in a preset fault classification list to determine a fault classification number, and if so, displaying a fault type corresponding to the fault classification number and giving an alarm.

Technical Field

The invention relates to the technical field of power equipment monitoring, in particular to a system and a method for monitoring the running state of power equipment.

Background

The power equipment is used as a basic unit for operating the power system, and the operating state of the power equipment influences the safety and stability of a power grid. Currently, the following two methods are mainly adopted for monitoring the operating state of the power equipment:

1. the mode of manual inspection and periodic maintenance is adopted, a large amount of manpower is consumed in the mode, the manual inspection real-time performance is poor, and the hidden danger of equipment is not easy to find in time. In addition, once regular maintenance is performed, the equipment needs to be shut down, which affects the continuity and stability of the operation of the power equipment.

2. All kinds of sensors of installation on power equipment and build intelligent monitoring system through the network and realize automatic monitoring, this kind of mode need install a large amount of sensors and carry out data acquisition, and the sensor needs carry out electrical connection with power equipment in addition, can influence power equipment's steady operation to a certain extent. Moreover, the investment is huge in the early stage, and the equipment monitoring cost is increased.

Disclosure of Invention

Aiming at the problems in the prior art, the invention aims to provide a system and a method for monitoring the running state of power equipment.

In order to achieve the purpose, the invention is realized by the following technical scheme:

an electrical equipment operating condition monitoring system comprising:

the data acquisition unit is arranged on the shell of the power equipment and is used for acquiring sound signals in the operation process of the power equipment; the data acquisition unit adopts a directional sound pickup or a vibration sensor, so that noise generated in the operation process of the power equipment is effectively directionally acquired;

the wireless transmission unit is used for transmitting the sound signal through a wireless network;

the cloud service platform is used for receiving the sound signals transmitted by the wireless network, converting the sound signals into audio data, extracting audio features of the audio data, identifying the audio features by applying a preset classification algorithm, and generating corresponding classification results;

and the alarm unit is used for determining whether the cable equipment has faults according to the classification result, and if so, displaying the fault type corresponding to the classification result and giving an alarm.

Further, the data acquisition unit includes:

the first acquisition module is used for acquiring sound signals in the running process of the rotary power equipment;

and the second acquisition module is used for acquiring sound signals in the operation process of the non-rotating power equipment. The sound signal adds different signal identifications according to different acquisition modules.

Further, the rotating electric device includes: the system comprises an induced draft fan, a generator, a wind turbine generator, a water turbine and a bearing; the non-rotating electrical device includes: boiler, circuit breaker, transformer, fuel cutter and governing valve.

Further, the cloud service platform comprises:

the preprocessing unit is used for carrying out sound channel conversion and pre-emphasis conversion on the sound signals to generate corresponding audio data;

the segmentation unit is used for identifying whether the audio data comprises target audio data, if so, sending the audio data to the sound source separation unit, and if not, sending a collection signal to the data collection unit to control the data collection unit to collect the sound signal again;

a sound source separating unit for separating target audio data from the audio data;

the audio feature extraction unit is used for extracting feature data containing power equipment fault information from state data in the target audio data as audio features; the purpose of audio characteristic extraction is to extract characteristic data carrying fault information, such as frequency spectrum, energy spectrum, power spectrum, amplitude value and the like, from the state signal;

and the classification unit is used for calculating the audio features by using a fuzzy C-means clustering algorithm, determining a fuzzy classification matrix of the fault audio features corresponding to the audio features, obtaining the closeness of the clustering center of the fault audio features, and determining fault classification numbers according to the closeness.

Further, a fuzzy classification matrix and a clustering center of fault audio features are generated through fault sound training, and the following method is specifically adopted:

carrying out 3-layer wavelet packet decomposition on the audio frequency characteristics of the power equipment with known faults, taking the sensitive frequency band energy of the wavelet packet as identification characteristic quantity, and carrying out fuzzy clustering on the identification characteristic quantity by utilizing a fuzzy C mean value clustering algorithm to obtain a fuzzy classification matrix and a clustering center of the audio frequency characteristics of the faults.

Further, the alarm unit includes:

and the identification module is used for searching whether the classification unit exists in the preset fault classification list to determine the fault classification number, and if so, displaying the fault type corresponding to the fault classification number and giving an alarm.

Correspondingly, the invention also discloses a method for monitoring the running state of the power equipment, which comprises the following steps:

s1: collecting sound signals in the operation process of the power equipment;

s2: transmitting the sound signal through a wireless network;

s3: receiving a sound signal transmitted by a wireless network, converting the sound signal into audio data, extracting audio features of the audio data, identifying the audio features by applying a preset classification algorithm, and generating a corresponding classification result;

s4: and determining whether the cable equipment has faults according to the classification result, and if so, displaying the fault type corresponding to the classification result and giving an alarm.

Further, step S3 includes:

s31: carrying out sound channel conversion and pre-emphasis conversion on the sound signals to generate corresponding audio data;

s32: identifying whether the audio data comprises target audio data, if so, sending the audio data to a sound source separation unit, otherwise, sending a collection signal to a data collection unit, and controlling the data collection unit to collect the sound signal again;

s33: separating target audio data from the audio data;

s34: extracting characteristic data containing power equipment fault information from state data in the target audio data to serve as audio characteristics;

s35: and calculating audio features by using a fuzzy C-means clustering algorithm, determining a fuzzy classification matrix of the fault audio features corresponding to the audio features, obtaining the closeness of the clustering center of the fault audio features, and determining fault classification numbers according to the closeness.

Further, step S4 specifically includes:

and searching whether a classification unit exists in a preset fault classification list to determine a fault classification number, and if so, displaying a fault type corresponding to the fault classification number and giving an alarm.

Compared with the prior art, the invention has the beneficial effects that: the invention provides a system and a method for monitoring the running state of electric power equipment. The invention adopts relatively single detection equipment or sensor, only carries out noise acquisition, does not need to be electrically connected with the power equipment, effectively ensures the stable operation of the power equipment, and reduces the equipment investment cost in the early stage.

In addition, the invention has the characteristics of convenient and flexible installation, simple and convenient test method and the like, and has better popularization prospect.

Therefore, compared with the prior art, the invention has prominent substantive features and remarkable progress, and the beneficial effects of the implementation are also obvious.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.

FIG. 1 is a system block diagram of the present invention.

FIG. 2 is a flow chart of the method of the present invention.

In the figure, 1 is a data acquisition unit, 2 is a wireless transmission unit, 3 is a cloud service platform, 4 is an alarm unit, 5 is a first acquisition module, 6 is a second acquisition module, 7 is an identification module, 11 is a preprocessing unit, 12 is a segmentation unit, 13 is a sound source separation unit, 14 is an audio feature extraction unit, and 15 is a classification unit.

Detailed Description

The following description of the embodiments of the present invention will be made with reference to the accompanying drawings.

The first embodiment is as follows:

as shown in fig. 1, the present embodiment provides an electrical equipment operating state monitoring system, including: the system comprises a data acquisition unit 1, a wireless transmission unit 2, a cloud service platform 3 and an alarm unit 4.

The data acquisition unit 1 is arranged on a shell of the power equipment and is used for acquiring sound signals in the operation process of the power equipment; the data acquisition unit 1 adopts a directional sound pickup or a vibration sensor, and effectively directionally acquires noise generated in the operation process of the power equipment.

The data acquisition unit 1 includes:

the first acquisition module 5 is used for acquiring sound signals in the operation process of the rotating electrical equipment.

And the second acquisition module 6 is used for acquiring sound signals in the operation process of the non-rotating power equipment. The sound signal adds different signal identifications according to different acquisition modules.

Wherein, rotatory power equipment includes: the system comprises an induced draft fan, a generator, a wind turbine generator, a water turbine and a bearing; the non-rotating electrical device includes: boiler, circuit breaker, transformer, fuel cutter and governing valve.

And the wireless transmission unit 2 is used for transmitting the sound signal through a wireless network. The wireless transmission unit 2 adopts a 4G communication module and can be bound with the data acquisition unit 1.

The cloud service platform 3 is used for receiving the sound signals transmitted by the wireless network, converting the sound signals into audio data, extracting audio features of the audio data, identifying the audio features by applying a preset classification algorithm, and generating corresponding classification results.

The cloud service platform 3 specifically includes:

and the preprocessing unit 11 is configured to perform channel conversion and pre-emphasis conversion on the sound signal to generate corresponding audio data.

And the dividing unit 12 is configured to identify whether the audio data includes target audio data, send the audio data to the sound source separating unit 13 if the target audio data includes the target audio data, send a collection signal to the data collection unit 1 if the target audio data does not include the target audio data, and control the data collection unit to collect the sound signal again.

A sound source separating unit 13 for separating the target audio data from the audio data.

An audio feature extraction unit 14 configured to extract feature data including power equipment failure information from the status data in the target audio data as an audio feature; the purpose of audio feature extraction is to extract feature data carrying fault information, such as frequency spectrum, energy spectrum, power spectrum, amplitude, etc., from the status signal.

And the classification unit 15 is used for calculating the audio features by using a fuzzy C-means clustering algorithm, determining a fuzzy classification matrix of the fault audio features corresponding to the audio features, obtaining the closeness of the clustering center of the fault audio features, and determining fault classification numbers according to the closeness.

And the alarm unit 4 is used for determining whether the cable equipment has faults according to the classification result, and if so, displaying the fault type corresponding to the classification result and giving an alarm. And an identification module 7 is arranged in the alarm unit 4 and used for searching whether a classification unit exists in a preset fault classification list to determine a fault classification number, and if so, displaying a fault type corresponding to the fault classification number and giving an alarm.

Example two:

as shown in fig. 2, the present embodiment provides a method for monitoring an operating state of an electrical device, including the following steps:

s1: collecting sound signals in the operation process of the power equipment.

S2: the sound signal is transmitted over a wireless network.

S3: the method comprises the steps of receiving sound signals transmitted by a wireless network, converting the sound signals into audio data, extracting audio features of the audio data, identifying the audio features by applying a preset classification algorithm, and generating corresponding classification results.

Firstly, sound channel conversion and pre-emphasis conversion are carried out on a sound signal to generate corresponding audio data; and then, identifying whether the audio data comprises target audio data, if so, sending the audio data to a sound source separation unit, otherwise, sending a collection signal to a data collection unit, and controlling the data collection unit to collect the sound signal again. Next, separating target audio data from the audio data by using a sound source separation unit; feature data including power equipment failure information is extracted from the status data in the target audio data as audio features. And finally, calculating the audio features by using a fuzzy C-means clustering algorithm, determining a fuzzy classification matrix of the fault audio features corresponding to the audio features, obtaining the closeness of the clustering center of the fault audio features, and determining fault classification numbers according to the closeness.

S4: and determining whether the cable equipment has faults according to the classification result, and if so, displaying the fault type corresponding to the classification result and giving an alarm. Specifically, whether a classification unit exists in a preset fault classification list or not is searched to determine a fault classification number, and if yes, a fault type corresponding to the fault classification number is displayed and an alarm is given.

In the embodiments provided by the present invention, it should be understood that the disclosed system, system and method can be implemented in other ways. For example, the above-described system embodiments are merely illustrative, and for example, the division of the units is only one logical functional division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, systems or units, and may be in an electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional modules in the embodiments of the present invention may be integrated into one processing unit, or each module may exist alone physically, or two or more modules are integrated into one unit.

Similarly, each processing unit in the embodiments of the present invention may be integrated into one functional module, or each processing unit may exist physically, or two or more processing units are integrated into one functional module.

The invention is further described with reference to the accompanying drawings and specific embodiments. It should be understood that these examples are for illustrative purposes only and are not intended to limit the scope of the present invention. Further, it should be understood that various changes or modifications of the present invention may be made by those skilled in the art after reading the teaching of the present invention, and these equivalents also fall within the scope of the present application.