CN115600136A - A method, system and medium for fault diagnosis of high voltage bushing based on multi-sensor - Google Patents

Abstract

The invention discloses a multi-sensor-based high-voltage bushing fault diagnosis method, system and medium to obtain first data information, the first data information is the collected signal data of each sensor in the high-voltage bushing; A data information is preprocessed to obtain the second data information; the feature data information of the second data information is extracted by using an optimized BP neural network model, and the feature data information includes feature data on several different sensors; using D-S evidence Theoretical algorithm, calculate the weight value of different fault types under the same characteristic data, and obtain several weight values; divide the weight values according to different fault types, and judge the occurrence of the monitoring system according to the weight value under the same fault type fault; the beneficial effect of the present invention is that it can improve the accuracy of judging the fault type of the high-voltage bushing and reduce the efficiency of judging the fault of the high-voltage bushing.

Description

A method, system and medium for fault diagnosis of high voltage bushing based on multi-sensor

technical field

The invention relates to the technical field of bushing fault judgment, in particular to a multi-sensor-based high-voltage bushing fault diagnosis method, system and medium.

Background technique

High-voltage bushings are key components of transformers, current transformers and other equipment in power systems. In recent years, a variety of online monitoring devices have been developed for high-voltage bushings, using different sensors to monitor the state of the bushing. Different sensors have been developed for bushing temperature, pressure, partial discharge, insulation, hydrogen content, etc. The temperature, pressure, UHF, HFCT, dielectric loss, capacitance, hydrogen content and other signals of the casing can be collected or calculated through different sensors.

Due to the complexity of the bushing structure, when the bushing is running, there are multiple structural movements inside and different state quantities. Therefore, when using different sensors for online monitoring and fault diagnosis of the bushing, the fault and state quantities are very different. It may not be a one-to-one correspondence. A certain fault may correspond to multiple state quantities, and a certain state quantity may also be caused by multiple faults.

However, in the existing technology, when diagnosing casing faults, it is usually judged by the data information of a single sensor. When using the information of a single sensor for judgment, the collected information may be vague or contradictory. , reducing the accuracy of judging the type of fault that occurs in the high voltage bushing, and increasing the efficiency of judging the fault of the high voltage bushing.

In view of this, this application is proposed.

Contents of the invention

The technical problem to be solved by the present invention is that in the prior art, the failure of the high-voltage bushing is judged by collecting the information data of a single sensor, and the information collected may be vague or contradictory, which will reduce the ability to judge the type of failure of the high-voltage bushing. Accuracy increases the efficiency of high-voltage bushing fault judgment. The purpose is to provide a multi-sensor-based high-voltage bushing fault diagnosis method, system and medium, which can improve the accuracy of the judgment of high-voltage bushing fault types and reduce Efficiency in judging high voltage bushing faults.

The present invention realizes through following technical scheme:

A method for diagnosing faults of high-voltage bushings based on multiple sensors, the method steps comprising:

Acquiring first data information, where the first data information is the collected signal data of each sensor in the high-voltage bushing;

Preprocessing the first data information to obtain second data information;

Using an optimized BP neural network model to extract feature data information of the second data information, the feature data information includes feature data on several different sensors;

Using the D-S evidence theory algorithm, calculate the weight values of different fault types under the same characteristic data, and obtain several weight values;

The several weight values are divided according to different fault types, and the faults in the monitoring system are judged according to the magnitude of the weight values under the same fault type.

In the traditional fault judgment of the high-voltage bushing online monitoring system, it is usually used to collect and analyze the information data of a single sensor to realize the fault diagnosis of the high-voltage bushing online monitoring system. However, when this method is used, sometimes the information data collected by a single sensor is vague and inaccurate or the collected data information is contradictory, which reduces the accuracy of the judgment of the fault type of the high-voltage bushing and increases the accuracy of the fault type. Efficiency of high-voltage bushing fault judgment; the present invention provides a multi-sensor-based high-voltage bushing fault diagnosis method, by collecting and merging various sensor information data, and adopting BP neural network in combination with D-S evidence theory algorithm, the data The information is processed to judge the fault of the online monitoring system, which can improve the accuracy of the judgment of the fault type of the high-voltage bushing and reduce the efficiency of the fault judgment of the high-voltage bushing.

Preferably, the preprocessing is to perform denoising or deinterference processing on the first data information.

Preferably, the construction steps of the optimized BP neural network model are:

Acquiring historical data information, the historical data information is the signal data of each sensor failure in the high-voltage bushing and the corresponding failure type;

Perform denoising and de-interference processing on the historical data information to obtain sub-historical data information;

A BP neural network model is constructed, and the BP neural network model is trained through the sub-historical data information, and an error function of a standard neural network is used to perform optimization iterations to obtain an optimized BP neural network model.

Preferably, the specific steps of obtaining the weight value include:

In the characteristic data information, select any characteristic data, adopt the BPA decision-making method in the D-S evidence theory, calculate the conflict difference of the characteristic data under different fault types, and obtain several conflict differences;

Using a normalization method and combining the cosine theorem in trigonometric functions to process some of the conflict differences to obtain the corresponding weight value of the feature data;

Traverse feature data information to obtain several weight values.

Preferably, the failure type is an overheating failure or a discharge failure.

Preferably, the specific expression of the error function is:

E is the error function, d _k is the target output value, and o _k is the actual output value.

Preferably, the specific expression of the conflict difference is:

为冲突度，x_t为第t组焦元，

为冲突，x_ti为t组中的i焦元，x_tj为t组中的i焦元j焦元，m(x_ti)为可信度分配。

is the degree of conflict, x _t is the focal element of the tth group,

is the conflict, x _ti is i focal element in t group, x _tj is i focal element j in t group, and m(x _ti ) is reliability distribution.

Preferably, the specific expression of the weight value is:

为冲突差，H_t为指数运算值，β_t为权值，ω_t为权重值。

is the conflict difference, H _t is the exponential operation value, β _t is the weight value, and ω _t is the weight value.

The present invention also provides a high-voltage bushing fault diagnosis system based on multiple sensors, including a data acquisition module, a preprocessing module, a characteristic data extraction module, a weight value calculation module and a judgment module,

The data acquisition module is configured to acquire first data information, and the first data information is the collected signal data of each sensor in the high-voltage bushing;

The preprocessing module is configured to preprocess the first data information to obtain second data information;

The feature data extraction module is used to extract feature data information of the second data information by using an optimized BP neural network model, and the feature data information includes feature data on several different sensors;

The weight calculation module is used to adopt the D-S evidence theory algorithm to calculate the weight values of different fault types under the same characteristic data, and obtain several weight values;

The judging module is used to divide several weight values according to different fault types, and judge the faults in the monitoring system according to the magnitude of the weight values under the same fault type.

The present invention also provides a computer storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the above-mentioned fault diagnosis method is realized.

Compared with the prior art, the present invention has the following advantages and beneficial effects:

The embodiment of the present invention provides a multi-sensor-based high-voltage bushing fault diagnosis method, system, and medium. By collecting and merging various sensor information data, and using BP neural network combined with D-S evidence theory algorithm, the data information is analyzed. Processing to judge the fault of the online monitoring system can improve the accuracy of the judgment of the fault type of the high-voltage bushing and reduce the efficiency of the fault judgment of the high-voltage bushing.

Description of drawings

In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention. Therefore, it should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can also be obtained according to these drawings without creative work.

Fig. 1 is the high voltage bushing fault diagnosis model;

Figure 2 is a structural model of a parallel multi-source information fusion system;

Fig. 3 is a feedforward neural network structure;

Figure 4 shows the process of multi-source information fusion.

detailed description

In order to make the purpose, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the examples and accompanying drawings. As a limitation of the present invention.

In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention. It will be apparent, however, to one skilled in the art that these specific details need not be employed to practice the present invention. In other instances, well-known structures, circuits, materials or methods have not been described in detail in order not to obscure the present invention.

Throughout this specification, reference to "one embodiment," "an embodiment," "an example," or "example" means that a particular feature, structure, or characteristic described in connection with the embodiment or example is included in the present invention. In at least one embodiment. Thus, appearances of the phrases "one embodiment," "an embodiment," "an example," or "example" in various places throughout this specification are not necessarily all referring to the same embodiment or example. Furthermore, particular features, structures or characteristics may be combined in any suitable combination and/or subcombination in one or more embodiments or examples. Furthermore, those of ordinary skill in the art will appreciate that the drawings provided herein are for illustrative purposes and are not necessarily drawn to scale. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.

In the description of the present invention, the terms "front", "rear", "left", "right", "upper", "lower", "vertical", "horizontal", "higher", "lower", "inner ", "outside" and other indicated orientations or positional relationships are based on the orientations or positional relationships shown in the drawings, which are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the referred device or element must have a specific Orientation, construction and operation in a particular orientation, therefore, should not be construed as limiting the scope of the invention.

Embodiment one

In the traditional fault judgment of the high-voltage bushing online monitoring system, it is usually used to collect and analyze the information data of a single sensor to realize the fault diagnosis of the high-voltage bushing online monitoring system. However, when this method is used, sometimes the information data collected by a single sensor is vague and inaccurate or the collected data information is contradictory, which reduces the accuracy of the judgment of the fault type of the high-voltage bushing and increases the accuracy of the fault type. Efficiency of high voltage bushing fault judgment.

This embodiment discloses a multi-sensor-based high-voltage bushing fault diagnosis method. By collecting and merging various sensor information data, and using BP neural network combined with D-S evidence theory algorithm, the data information is processed to judge the online fault. The faults of the monitoring system can improve the accuracy of judging the fault type of the high-voltage bushing and reduce the efficiency of judging the fault of the high-voltage bushing. The schematic diagram of the specific diagnostic method in this embodiment is shown in Figures 1 to 4, and the method steps include:

S1: Obtain first data information, where the first data information is the collected signal data of each sensor in the high-voltage bushing;

In step S1, the high-voltage bushing is an outlet device that leads the high-voltage wire inside the transformer to the outside of the oil tank. It not only serves as the ground insulation of the lead wire, but also plays the role of fixing the lead wire. It is one of the important accessories of the transformer; therefore, in the transformer During operation, the casing usually needs to be monitored online, and it is monitored through various sensors installed. Therefore, in this embodiment, the acquired data of various sensors for online monitoring of the casing will be Data fusion can increase the accuracy of fault type judgment.

S2: Perform preprocessing on the first data information to obtain second data information; the preprocessing is to perform denoising or deinterference processing on the first data information.

In step S2, there may be certain noise or interference information in the collected first data information, and the noise and interference information need to be removed by filtering.

S3: Using an optimized BP neural network model to extract feature data information of the second data information, where the feature data information includes feature data on several different sensors;

The construction steps of the optimized BP neural network model are:

Obtain historical data information, the historical data information is the signal data of each sensor failure in the high-voltage bushing and the corresponding fault type; perform denoising and de-interference processing on the historical data information to obtain sub-historical data information; construct BP A neural network model, and train the BP neural network model through the sub-historical data information, and use the error function of the standard neural network to perform optimization iterations to obtain an optimized BP neural network model.

The BP neural network model is continuously optimized and iteratively updated through the collected historical data information, which can increase the accuracy of the model's processing of relevant data information.

The specific BP neural network model is:

The input layer, intermediate layer and output layer of the standard BP network have N _i i, N _j and N _k neurons respectively. The input of the jth neuron in the middle layer is:

In the formula, ω _ij is the weight of the i-th neuron in the input layer to the j-th neuron in the middle layer; o _i is the output of the i-th neuron in the input layer. The input of the kth neuron in the output layer is:

In the formula, ω _jk is the weight from the jth neuron in the middle layer to the kth neuron in the output layer; o _j is the output of the kth neuron in the middle layer.

The outputs of the input layer, middle layer and output layer are respectively:

o _i = net _j = x _i

θ _j and θ _k are the thresholds of the jth neuron in the middle layer and the kth neuron in the output layer, respectively. x _i is the signal collected by each sensor.

The training of the BP network adopts the γ learning law based on the gradient method, and its goal is to minimize the mean square error between the network output and the training samples. In the standard BP neural network, set the training sample as P, where the input vector is x1, x2...xp; the output vector is y1, y2...yp; the corresponding teacher value (sample) vector is t1, t2.. .tp; then the mean square error of the P sample is:

In the formula, tpk and ypk are the teacher value and the actual output value of the pth sample of the kth output neuron respectively.

At this time, the weight of the middle layer is adjusted as:

Δω _ij (n+1)=ηδ _jp o _jp +αΔw _ij (n)

At this time, the weight of the output layer is adjusted to:

Δω _jk (n+1)=ηδ _jp o _jp +αΔw _jk (n)

δ _kp ＝(t _kp -y _kp )f _k '(net _kp )

In the formula, η is the learning rate and α is the momentum factor.

The concrete expression of described error function is:

E is the error function, d _k is the target output value, and o _k is the actual output value.

What the error function reflects is that d _k and ok _k are different "distance" scales between the two quantities. The purpose of BP network training is to make the actual output o _k as close as possible to the target output d _k , which is measured by the degree of proximity. Using this error function can effectively improve the problem of slow convergence speed when the BP neural network is trained, and improve the training speed of the BP neural network.

After using this error function, the weights of the middle layer of the neural network are adjusted to:

At this time, the weight of the output layer is adjusted to:

Among them, ω _ij is the weight from the i-th neuron in the input layer to the j-th neuron in the middle layer; ω _jk is the weight from the j-th neuron in the middle layer to the k-th neuron in the output layer; η is the learning rate adjustment factor . O _i is the output of the i-th neuron in the input layer. O _j is the output of the Kth neuron in the middle layer.

S4: Using the D-S evidence theory algorithm, calculate the weight values of different fault types under the same characteristic data, and obtain several weight values;

The specific steps for obtaining the weight value include:

In the characteristic data information, select any characteristic data, adopt the BPA decision-making method in the D-S evidence theory, calculate the conflict difference of the characteristic data under different fault types, and obtain several conflict differences; the fault type is an overheating fault or Discharge failure.

Using a normalization method and combining the cosine theorem in trigonometric functions to process some of the conflict differences to obtain the corresponding weight value of the feature data;

Traverse feature data information to obtain several weight values.

In this embodiment, a method for redistributing evidence BPA is proposed for the D-S evidence theory algorithm, which can effectively overcome the impact of evidence conflicts on information fusion, and reasonably use evidence reasoning to describe the degree of certainty and hesitation in judgment with numerical values Spend.

Define m as the BPA function on the recognition space θ, A and B are the focal elements on the recognition space, and use Eq. to redefine the BPA on the recognition space.

SetPm(A) represents the degree of support of the basic probability distribution for each subset.

The conflict degree Diff of the same target is expressed as:

Diff(A)＝|SetP _mi (A)-SetP _mj (A)|

In this embodiment, the algorithm of the D-S evidence theory is improved, and weights are re-assigned to the evidence according to the reliability of the evidence, so as to obtain better fusion results.

Let θ be the sample space, xi be the focal element in the sample space θ, i=1,2,...n, and there are N sets of evidence functions. Denote as mi={xt1, xt2, xt3...xti} where i=1, 2,...n, t=1, 2,...N. Use βi to represent weights, where i=1,2,3....N.

First, reassign the BPAs of the evidence separately.

Secondly, calculate the conflict difference of the same focal element under different evidences.

为冲突度，x_t为第t组焦元，

为冲突，x_ti为t组中的i焦元，x_tj为t组中的i焦元j焦元，m(x_ti)为可信度分配。

is the degree of conflict, x _t is the focal element of the tth group,

is the conflict, x _ti is i focal element in t group, x _tj is i focal element j in t group, and m(x _ti ) is reliability distribution.

Again, normalize the conflict difference.

为冲突差，H_t为指数运算值，β_t为权值，ω_t为权重值。satisfy,

is the conflict difference, H _t is the exponential operation value, β _t is the weight value, and ω _t is the weight value.

Then calculate the normalized value.

Weights can be expressed as:

Introduce the cosine theorem in trigonometric functions, fix the weight between [0,1], use the curve characteristics of the cosine function to assign weights, and the obtained weights are relatively smooth. which is:

In this way, the weight vector composed of the weight coefficients of each evidence is determined.

S5: Dividing several weight values according to different fault types, and judging the faults occurred in the monitoring system according to the magnitude of the weight values under the same fault type.

Combine BP neural network and D-S evidence theory to fuse eigenvalues and eigenvectors. Set the uncertainty factor fi as the training error of the BP neural network, and normalize the output as the basic probability value of each focus element. The calculation formula is:

In the formula: fi represents the failure mode, i=(0,1,2,3,4,5,6), and y(fi) represents the output result of the BP neural network.

其中，En为该样本的网络误差,tnj,ynj分别为別对应第j个神经元的期望值和实际值。

Among them, En is the network error of the sample, tnj, ynj are the expected value and actual value corresponding to the jth neuron respectively.

First, the input values of each sensor are processed by the BP neural network to obtain the mass function values confirmed by the corresponding different fault types, and then the D-S evidence theory rules are used to finally obtain the fusion result.

The specific implementation process:

Construct a BP diagnostic network, the number of neurons in the input layer of the BP network is 9 characteristic parameters, and the number of neurons in the output layer is the number of faults (representing different types of faults), that is, the output objective function F={f1, f2, f3, f4, f5 ,f6}, the expected output of the neural network is represented by [0,1], where 1 means that the fault exists, and 0 means that the fault does not exist. Table 1 shows the input samples of the neural network, which are the square root mean x1, standard deviation x2, temperature index x3, pressure index x4, oil level index x5, dielectric loss index x6, capacitance index x7, leakage current x8, angle difference x9 and other 9 characteristic parameters.

Table 1 Input samples of neural network

According to the measuring point data in Table 1, the BP neural network is firstly used for local diagnosis, and the input layer of the BP network is set to 6 nodes, the hidden layer is set to 17 nodes, and the output layer is set to 6 nodes, representing six kinds of For faults, use the training set to train the three-layer BP network, and then extract some samples from each fault sample for training. The training results are shown in Table 2:

Table 2 Training results of BP neural network

By using the present invention, the BP neural network is combined with the D-S evidence theory, and the fusion results of samples can be obtained by using the rules of the D-S evidence theory, as shown in Table 3.

Table 3 Fusion results of D-S evidence theory

By comparing Table 2 and Table 3, it can be seen that after information fusion and comprehensive diagnosis, the diagnostic accuracy is greatly improved. There are unsatisfactory results in each sample. If a single measurement point data is used for judgment, it is easy to make a misjudgment. However, the multi-sensor information fusion method is used to comprehensively consider multi-parameters and multi-variables. First, the BP neural network is used to perform feature layer Fusion, using D-S synthesis rules for decision-making fusion, the final results are still relatively ideal, all trust levels are above 0.95, thus proving the intelligent diagnosis method of casing faults by information fusion combining BP neural network and D-S evidence theory effectiveness.

This embodiment provides a fault diagnosis method for a high-voltage bushing online monitoring system. By collecting and merging various sensor information data, and using BP neural network combined with D-S evidence theory algorithm, the data information is processed to judge the online fault. The faults of the monitoring system can improve the accuracy of judging the fault type of the high-voltage bushing and reduce the efficiency of judging the fault of the high-voltage bushing.

Embodiment two

This embodiment discloses a high-voltage bushing fault diagnosis system based on multiple sensors. This embodiment is to realize the fault diagnosis method as in Embodiment 1, including a data acquisition module, a preprocessing module, a feature data extraction module, and a weight value Calculation module and judgment module,

The data acquisition module is configured to acquire first data information, and the first data information is the collected signal data of each sensor in the high-voltage bushing;

The preprocessing module is configured to preprocess the first data information to obtain second data information;

The feature data extraction module is used to extract feature data information of the second data information by using an optimized BP neural network model, and the feature data information includes feature data on several different sensors;

The weight calculation module is used to adopt the D-S evidence theory algorithm to calculate the weight values of different fault types under the same characteristic data, and obtain several weight values;

The judging module is used to divide several weight values according to different fault types, and judge the faults in the monitoring system according to the magnitude of the weight values under the same fault type.

Embodiment three

This embodiment discloses a computer storage medium, on which a computing program is stored. When the computer program is executed by a processor, the fault diagnosis method as described in the first embodiment is realized.

Those skilled in the art should understand that the embodiments of the present application may be provided as methods, systems, or computer program products. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

The present application is described with reference to flowcharts and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present application. It should be understood that each procedure and/or block in the flowchart and/or block diagram, and a combination of procedures and/or blocks in the flowchart and/or block diagram can be implemented by computer program issuing instructions. These computer programs may be provided to issue instructions to a general purpose computer, special purpose computer, embedded processor, or processor of other programmable data processing equipment to produce a machine such that the issued instructions executed by the processor of the computer or other programmable data processing equipment Produce means for realizing the functions specified in one or more procedures of the flowchart and/or one or more blocks of the block diagram.

These computer program issued instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing apparatus to operate in a specific manner such that the issued instructions stored in the computer readable memory produce an article of manufacture comprising the issued instruction means , the device for issuing instructions realizes the functions specified in one or more procedures of the flow chart and/or one or more blocks of the block diagram.

These computer programs issue instructions that can also be loaded onto a computer or other programmable data processing device, causing a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process that is executed on the computer or other programmable device The issued instructions provide steps for implementing the functions specified in the flow chart or flow charts and/or block diagram block or block blocks.

The specific embodiments described above have further described the purpose, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above descriptions are only specific embodiments of the present invention and are not intended to limit the scope of the present invention. Protection scope, within the spirit and principles of the present invention, any modification, equivalent replacement, improvement, etc., shall be included in the protection scope of the present invention.

Claims (10)

1. A multisensor-based high-voltage bushing fault diagnosis method, characterized in that the method steps include: Acquiring first data information, where the first data information is the collected signal data of each sensor in the high-voltage bushing; Preprocessing the first data information to obtain second data information; Using an optimized BP neural network model to extract feature data information of the second data information, the feature data information includes feature data on several different sensors; Using the D-S evidence theory algorithm, calculate the weight values of different fault types under the same characteristic data, and obtain several weight values; The several weight values are divided according to different fault types, and the faults in the monitoring system are judged according to the magnitude of the weight values under the same fault type. 2. A multi-sensor-based high-voltage bushing fault diagnosis method according to claim 1, wherein the preprocessing is to perform denoising or deinterference processing on the first data information. 3. a kind of high voltage bushing fault diagnosis method based on multisensor according to claim 1, is characterized in that, the construction step of described optimization BP neural network model is: Acquiring historical data information, the historical data information is the signal data of each sensor failure in the high-voltage bushing and the corresponding failure type; Perform denoising and de-interference processing on the historical data information to obtain sub-historical data information; A BP neural network model is constructed, and the BP neural network model is trained through the sub-historical data information, and an error function of the improved neural network is used for optimization iteration to obtain an optimized BP neural network model. 4. A kind of high voltage bushing fault diagnosis method based on multi-sensor according to claim 1, is characterized in that, the concrete step that described weight value obtains comprises: In the characteristic data information, select any characteristic data, adopt the BPA decision-making method in the D-S evidence theory, calculate the conflict difference of the characteristic data under different fault types, and obtain several conflict differences; Using a normalization method and combining the cosine theorem in trigonometric functions to process some of the conflict differences to obtain the corresponding weight value of the feature data; Traverse feature data information to obtain several weight values. 5. A multi-sensor-based high-voltage bushing fault diagnosis method according to claim 4, characterized in that the fault type is an overheating fault or a discharge fault. 6. a kind of multi-sensor based high voltage bushing fault diagnosis method according to claim 3, is characterized in that, the concrete expression of described error function is:

E is the error function, d _k is the target output value, and o _k is the actual output value. 7. a kind of high voltage bushing fault diagnosis method based on multisensor according to claim 4, is characterized in that, the specific expression of described conflict difference is:

is the degree of conflict, x _t is the focal element of the tth group,

is the conflict, x _ti is i focal element in t group, x _tj is i focal element j in t group, and m(x _ti ) is reliability distribution. 8. A kind of high voltage bushing fault diagnosis method based on multi-sensor according to claim 7, is characterized in that, the specific expression of described weight value is:

α _xt is the conflict difference, H _t is the exponential operation value, β _t is the weight value, and ω _t is the weight value. 9. A multisensor-based high-voltage bushing fault diagnosis system, characterized in that, comprising a data acquisition module, a preprocessing module, a characteristic data extraction module, a weight value calculation module and a judgment module, The data acquisition module is configured to acquire first data information, where the first data information is the collected signal data of each sensor in the high-voltage bushing; The preprocessing module is configured to preprocess the first data information to obtain second data information; The feature data extraction module is used to extract feature data information of the second data information by using an optimized BP neural network model, and the feature data information includes feature data on several different sensors; The weight calculation module is used to adopt the D-S evidence theory algorithm to calculate the weight values of different fault types under the same characteristic data, and obtain several weight values; The judging module is used to divide several weight values according to different fault types, and judge the faults in the monitoring system according to the magnitude of the weight values under the same fault type. 10. A computer storage medium, on which a calculation program is stored, characterized in that, when the computer program is executed by a processor, the fault diagnosis method according to any one of claims 1-8 is realized.

Images