阅读说明：本技术 一种gil电接触状态监测信息融合与故障诊断方法、装置及系统 (GIL electric contact state monitoring information fusion and fault diagnosis method, device and system ) 是由 杨景刚 李洪涛 高山 赵科 陈少波 丁然 刘咏飞 杨騉 马径坦 刘媛 李玉杰 于 2021-06-28 设计创作，主要内容包括：本发明提供一种GIL电接触状态监测信息融合与故障诊断方法、装置及系统,所述方法包括以下步骤：获取不同电接触缺陷下GIL外壳的温升和振动图谱；在特征层对GIL外壳的发热和振动监测信息融合,获得内部触头状态的一致性描述；对不同缺陷下的GIL触头状态尚未一致性描述进行标记,利用深度学习神经网络进行分类训练,构建GIL电接触故障诊断方法和模型。本发明所提供的GIL电接触状态监测信息融合与故障诊断方法可实现对GIL设备发热和振动异构信息的融合,为GIL设备的电接触状态检修提供技术支持,实现对GIL触头接触故障智能诊断,对于提高GIL设备的智能化运维水平,保障设备的安全稳定运行具有重要意义。(The invention provides a method, a device and a system for monitoring information fusion and fault diagnosis of a GIL electric contact state, wherein the method comprises the following steps: acquiring temperature rise and vibration maps of the GIL shell under different electrical contact defects; fusing heating and vibration monitoring information of the GIL shell in the characteristic layer to obtain consistency description of the state of the internal contact; marking the inconsistency description of the contact states of the GIL under different defects, and performing classification training by using a deep learning neural network to construct a GIL electrical contact fault diagnosis method and a model. The GIL electric contact state monitoring information fusion and fault diagnosis method provided by the invention can realize fusion of heating and vibration heterogeneous information of the GIL equipment, provides technical support for electric contact state maintenance of the GIL equipment, realizes intelligent diagnosis of contact faults of the GIL contact, and has important significance for improving the intelligent operation and maintenance level of the GIL equipment and ensuring safe and stable operation of the equipment.)

1. A GIL electric contact state monitoring information fusion and fault diagnosis method is characterized by comprising the following steps:

s01: acquiring temperature rise and vibration maps of the GIL shell under different electrical contact defects;

s02: fusing heating and vibration monitoring information of the GIL shell in the characteristic layer to obtain consistency description of the state of the internal contact;

s03: marking the inconsistency description of the contact states of the GIL under different defects, and performing classification training by using a deep learning neural network to construct a GIL electrical contact fault diagnosis method and a model.

2. The GIL electrical contact state monitoring information fusion and fault diagnosis method according to claim 1, wherein the step S01 comprises:

different contact defects are simulated by adjusting the insertion depth, butt joint, angle and spring stiffness of the bus conductor and the contact;

collecting temperature and vibration data of a GIL shell under different contact defects;

preprocessing temperature and vibration data through maximum and minimum normalization;

segmenting the time sequence of the temperature and vibration data by a time sliding window method, and determining the sampling frequency of the data and the length of a time sliding window according to the precision requirement of field GIL state monitoring time;

and converting the one-dimensional time sequence data of the temperature and vibration heterogeneous information into a two-dimensional heat map by drawing a temperature-time heat map and a vibration-time heat map for the segmented grouped data.

3. The GIL electrical contact state monitoring information fusion and fault diagnosis method according to claim 1, wherein the step S02 comprises:

performing feature extraction on the temperature and vibration pattern of the GIL shell and modeling on the weight by adopting a machine learning method, wherein the machine learning method comprises an analytic hierarchy process, a multivariate correspondence analysis, a principal component analysis, a support vector machine and a BP neural network;

and fusing the GIL temperature and the vibration map by adopting a weighted fusion algorithm to obtain the consistency description of the electrical contact state of the GIL contact.

4. The GIL electrical contact state monitoring information fusion and fault diagnosis method according to claim 1, wherein the step S03 comprises:

constructing a GIL electric contact fault sample data set according to the fused information, wherein the data before and after fusion has consistency description corresponding to the state of the GIL contact, and the GIL electric contact fault sample data set is enlarged by using a data enhancement technology;

constructing a GIL electric contact fault diagnosis model by adopting a classical deep learning classification network, setting the optimal parameter setting of the model by a parameter optimization mode of grid search, and then training the model to obtain the contact state prediction results of the GIL contacts of different models;

and comparing the performances of different diagnosis models through a clustering analysis method, and constructing a GIL electric contact defect diagnosis method and model based on deep learning.

5. A GIL electric contact state monitoring information fusion and fault diagnosis device is characterized by comprising:

the data acquisition module is used for acquiring the temperature rise and vibration map of the GIL shell under different electrical contact defects;

the data fusion module is used for fusing heating and vibration monitoring information of the GIL shell in the characteristic layer to obtain consistency description of the state of the internal contact;

and the fault diagnosis module is used for marking the inconsistent description of the GIL contact states under different defects, performing classification training by using a deep learning neural network, and constructing a GIL electric contact fault diagnosis method and a model.

6. A GIL electrical contact state monitoring information fusion and fault diagnosis system, which is characterized by comprising: the system comprises a GIL shell to be tested, a temperature sensor, an acceleration sensor, a temperature rise data acquisition and processing unit, a vibration data acquisition and processing unit, a temperature rise/vibration data fusion unit and a fault diagnosis unit; the temperature sensor and the acceleration sensor are arranged on the GIL shell to be measured; the temperature rise data acquisition and processing unit and the vibration data acquisition and processing unit are respectively connected with the temperature sensor and the acceleration sensor; the temperature rise/vibration data fusion unit is connected with the temperature rise data acquisition and processing unit and the vibration data acquisition and processing unit; and the fault diagnosis unit is connected with the temperature rise/vibration data fusion unit.

Technical Field

The invention belongs to the technical field of power equipment, and particularly relates to a method, a device and a system for monitoring information fusion and fault diagnosis of GIL (general information acquisition) electrical contact state.

Background

A gas insulated transmission line (GIL) is high-voltage and high-current power transmission equipment which adopts SF6 gas or mixed gas of SF6 and N2 as an insulating medium, is coaxially arranged with a shell and a conductor and is placed in a pipeline. The GIL electric contact mostly adopts plug-in type structures such as interference-assembled plum blossom/watchband/helical spring, and the like, and in the operation process, the temperature of the electric contact part is raised to a conductor part due to the existence of contact resistance, and the heat generates a concentrated temperature rise area on the surface of the shell through the natural convection and heat radiation process of gas in the GIL, and meanwhile, the plug-in type structure generates mechanical vibration under the action of electromagnetic force generated by operation current and is transmitted to the shell through supporting structures such as insulators and the like. Once the contact system has insufficient butt joint depth, poor centering degree and other working conditions, hidden contact troubles are formed, and when the defects of poor butt joint of a moving contact and a fixed contact, loosening of a bolt and the like occur at an electric contact part, abnormal heating and vibration of the electric contact part can be caused and transmitted to the shell, so that the temperature rise and the vibration characteristic of the GIL shell can be used as the diagnosis basis of the electric contact defect.

At present, the resistance test of a loop before the operation of GIL equipment can only evaluate the whole contact state of the test loop, and because the GIL electric contact adopts a multi-contact parallel structure, the contact hidden trouble of a single contact or a contact is difficult to detect and discover; aiming at the electrical contact state diagnosis of the GIL in operation, only single temperature rise or vibration information detection can be carried out, and due to the facts that the temperature rise-vibration multi-scale multi-physical field coupling mechanism is not clear, the fault propagation process of the GIL temperature rise and vibration under the contact defect is not clear, an effective temperature rise/vibration combined detection technology is lacked, and accurate diagnosis of the electrical contact state inside the GIL is difficult to achieve.

Disclosure of Invention

The invention aims to overcome the defects in the prior art and provides a method, a device and a system for monitoring information fusion and fault diagnosis of a GIL (general information acquisition) electric contact state.

In a first aspect, the invention provides a method for monitoring information fusion and fault diagnosis of a GIL (general information acquisition) electric contact state, which comprises the following steps:

s01: acquiring the temperature rise and vibration pattern of the GIL shell under different electrical contact defects;

s02: fusing heating and vibration monitoring information of the GIL shell in the characteristic layer to obtain consistency description of the state of the internal contact;

s03: marking the inconsistency description of the contact states of the GIL under different defects, and performing classification training by using a deep learning neural network to construct a GIL electrical contact fault diagnosis method and a model.

In a second aspect, the present invention further provides a GIL electrical contact state monitoring information fusion and fault diagnosis apparatus for implementing the above method, where the apparatus includes:

the data acquisition module is used for acquiring the temperature rise and vibration map of the GIL shell under different electrical contact defects;

the data fusion module is used for fusing heating and vibration monitoring information of the GIL shell in the characteristic layer to obtain consistency description of the state of the internal contact;

and the fault diagnosis module is used for marking the inconsistent description of the GIL contact states under different defects, performing classification training by using a deep learning neural network, and constructing a GIL electric contact fault diagnosis method and a model.

In a third aspect, the present invention further provides a GIL electrical contact state monitoring information fusion and fault system for implementing the above method, where the system includes: the system comprises a GIL shell to be tested, a temperature sensor, an acceleration sensor, a temperature rise data acquisition and processing unit, a vibration data acquisition and processing unit, a temperature rise/vibration data fusion unit and a fault diagnosis unit; the temperature sensor and the acceleration sensor are arranged on the GIL shell to be measured; the temperature rise data acquisition and processing unit and the vibration data acquisition and processing unit are respectively connected with the temperature sensor and the acceleration sensor; the temperature rise/vibration data fusion unit is connected with the temperature rise data acquisition and processing unit and the vibration data acquisition and processing unit; and the fault diagnosis unit is connected with the temperature rise/vibration data fusion unit.

Compared with the prior art, the invention has the beneficial effects that:

the method can realize the fusion of heating and vibration heterogeneous information of the GIL equipment, can deeply reveal the multiscale failure characteristics of GIL electric contact, provides technical support for electric contact state maintenance of the GIL equipment, realizes intelligent diagnosis of contact faults of the GIL contact, and has important significance for improving the intelligent operation and maintenance level of the GIL equipment and ensuring the safe and stable operation of the equipment.

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 some embodiments described in the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.

FIG. 1 is a flow chart of a GIL electrical contact state monitoring information fusion and fault diagnosis method provided by the present invention;

FIG. 2 is a schematic diagram of a GIL electrical contact state monitoring information fusion and fault diagnosis apparatus according to the present invention;

fig. 3 is a schematic diagram of a system for monitoring information fusion and fault diagnosis of a GIL electrical contact state according to the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments.

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.

As shown in fig. 1, a GIL electrical contact state monitoring information fusion and fault diagnosis method provided by an embodiment of the present invention includes the following steps:

s01: acquiring temperature rise and vibration maps of the GIL shell under different electrical contact defects;

as one example, different contact defects are simulated by adjusting conditions such as insertion depth, butt joint, angle and spring stiffness of the bus conductor and the contact; acquiring the temperature rise and vibration characteristics of the GIL shell under different contact defects by arranging temperature and acceleration sensors on the GIL shell; the temperature and vibration data of the GIL shell under different contact defects are acquired by connecting a data acquisition unit with a sensor; segmenting the time sequence of the temperature and vibration data by a time sliding window method, and determining the sampling frequency of the data and the length of a time sliding window according to the precision requirement of field GIL state monitoring time; the temperature rise and vibration map of the GIL shell is drawn by drawing a temperature-time heat map and an acceleration-time heat map which take time as an abscissa and temperature/vibration data of each sensor as a ordinate, so that one-dimensional time sequence data of temperature and vibration heterogeneous information is converted into a two-dimensional heat map.

S02: fusing heating and vibration monitoring information of the GIL shell in the characteristic layer to obtain consistency description of the state of the internal contact;

as one example, the characteristic vectors of the heating and vibration patterns of the GIL shell are respectively extracted by adopting machine learning methods such as an analytic hierarchy process, a multivariate correspondence analysis, a principal component analysis, a support vector machine and the like; and performing weighted fusion on the GIL temperature and vibration characteristic vectors through a weighted fusion algorithm to obtain the consistency description of the electrical contact state of the GIL contact.

S03: marking consistency description of the GIL contact state under different defects, and performing classification training by using a deep learning neural network to construct a GIL electric contact fault diagnosis method and a model.

As one embodiment, a GIL electrical contact fault sample data set is constructed according to the fused information, the data before and after fusion has consistency description corresponding to the state of the GIL contact, namely the state of the GIL contact before fusion is used for marking the state of the GIL contact after fusion, and the GIL electrical contact fault sample data set is expanded by using a data enhancement technology; constructing a GIL electric contact fault diagnosis model by adopting a classical deep learning classification network (AlexNet, VGG, GoogleNet and the like), setting the optimal parameter setting of the model by a parameter optimization mode of grid search, and then training the model to obtain the contact state prediction results of the GIL contacts of different models; and finally, comparing the performances of different diagnosis models by methods such as cluster analysis and AP curves, and providing a GIL electric contact fault diagnosis method based on deep learning on the basis.

As an embodiment, fig. 2 shows a schematic diagram of a GIL electrical contact state monitoring information fusion and fault diagnosis apparatus, which implements the GIL electrical contact state monitoring information fusion and fault diagnosis method, including:

the data acquisition module 210 is used for acquiring the temperature rise and vibration map of the GIL shell under different electrical contact defects;

the data fusion module 220 is used for fusing heating and vibration monitoring information of the GIL shell in the characteristic layer to obtain consistency description of the state of the internal contact;

and the fault diagnosis module 230 is used for marking the inconsistency description of the contact states of the GIL under different defects, performing classification training by using a deep learning neural network, and constructing a GIL electrical contact fault diagnosis method and model.

It should be understood that the device corresponds to the aforementioned GIL electrical contact state monitoring information fusion and fault diagnosis method embodiment, and can perform the steps involved in the aforementioned method embodiment, and the specific functions of the device can be referred to the above description, and the detailed description is appropriately omitted here to avoid redundancy. The device includes at least one software function that can be stored in memory in the form of software or firmware (firmware) or solidified in the Operating System (OS) of the device.

As an embodiment, fig. 3 shows a schematic diagram of a GIL electrical contact state monitoring information fusion and fault diagnosis system, which implements the GIL electrical contact state monitoring information fusion and fault diagnosis method, including: temperature sensors A-1 to A-4 and E-1; acceleration sensors B-1 to B-4; a GIL shell 1 to be tested; a temperature rise data acquisition and processing unit 2; a vibration data acquisition and processing unit 3; a temperature rise/vibration data fusion unit 4; and a fault diagnosis unit 5.

Wherein the temperature sensor and the acceleration sensor are arranged in the GIL housing; the temperature rise data acquisition and processing unit 2 and the vibration data acquisition and processing unit 3 are respectively connected with a temperature sensor and an acceleration sensor; the temperature rise/vibration data fusion unit is connected with the data acquisition and processing unit; the fault diagnosis unit 5 is connected with the temperature rise/vibration data fusion unit 4.

According to the theory of heat transfer and hydromechanics, when the contact of the GIL equipment is abnormal, the phenomena of temperature rise, vibration and the like occur on the surface of the shell, but the temperature rise and the vibration of the contact are reflected differently on different positions of the shell, so that a plurality of temperature sensors A-1-A-4 and acceleration sensors B-1-B-4 are required to be arranged on the shell to reflect the temperature information and the vibration information of the shell in an all-around manner, and a temperature sensor E-1 is arranged 2m away from the GIL shell to monitor the ambient temperature.

The temperature sensor and the acceleration sensor are connected with the data acquisition unit, and the time sequence data of the temperature and the acceleration are acquired through the data acquisition unit; preprocessing temperature and acceleration data through maximum and minimum normalization; the temperature and acceleration time sequence is segmented through a time sliding window method, and the data sampling frequency and the length of a time sliding window can be set according to the requirement of field GIL state monitoring time precision; and converting the one-dimensional time sequence data into a two-dimensional heat map by drawing a temperature-time heat map and an acceleration-time heat map for the segmented grouped data.

The data fusion unit is connected with the data acquisition unit, converts the high-dimensional temperature-time heat map and the acceleration-time heat map into low-dimensional feature vectors through feature extraction, fuses the feature vectors through a feature weighting fusion algorithm, and finally obtains GIL temperature rise/vibration fusion data. And the fault intelligent diagnosis unit is connected with the data fusion unit, and the trained fault diagnosis model is used for deducing the data after data fusion so as to realize GIL electric contact state judgment.

The above description is only a preferred embodiment of the present invention, and the scope of the present invention is not limited thereto, and any simple modifications or equivalent substitutions of the technical solutions that can be obviously obtained by those skilled in the art within the technical scope of the present invention are within the scope of the present invention.