SVM-based multi-parameter fusion switch storage battery state diagnosis method and system

Abstract

The invention discloses an SVM-based multi-parameter fusion switch storage battery state diagnosis method and system, and relates to the technical field of power line automation and Internet of Things technology combined intelligent monitoring, and the method comprises the steps: collecting multi-parameter data through a sensor, and carrying out the preprocessing of the multi-parameter data; extracting fault diagnosis features from the processed data, screening important features by using a Pearson's correlation coefficient, and dividing a data set into a training set and a test set; and combining the SVM with the BP neural network to form an SVM-BP model, and evaluating the state of the storage battery by training and optimizing weights and parameters. Intelligent operation and maintenance of the storage battery are achieved, passive storage battery maintenance work is converted into active storage battery maintenance work, the operation and maintenance level of the power distribution automation terminal equipment is improved, the operation and maintenance workload is greatly reduced, and the state of the backup power supply storage battery is also brought into daily operation management of the power distribution automation equipment; and operation and maintenance management can be carried out more timely and quickly.

Description

Technical Field

[0001] The present invention relates to the field of intelligent monitoring technology combined with power line automation and Internet of Things technology, and in particular to a multi-parameter fusion switch battery status diagnosis method and system based on SVM. Background Art

[0002] As the construction of distribution automation systems continues to expand and develop in depth, a large number of automated complete switchgear are used in distribution network production and operation, and continue to grow rapidly with the continuous construction of distribution networks. The backup power supply technology solution for automated complete switchgear is also an important technical problem that must be solved in the construction of distribution automation. The reasonable configuration of the backup power supply is not only related to the safe operation and power supply reliability of the distribution network, but also affects the construction cost of distribution automation and the operation and maintenance cost of the distribution automation system. This paper mainly analyzes and summarizes the technical requirements, operation and maintenance status and existing problems of the backup power supply battery of the automated complete switchgear. It is proposed to carry out the operation and maintenance management of the backup power supply battery of the automated complete switchgear from three aspects: management measures, technical means, and supervision management, so as to improve the operation and maintenance management level of the backup power supply of the automated complete switchgear, and support the improvement of the operation and maintenance quality and efficiency of the backup power supply of the automated complete switchgear.

[0003] The backup power supply system of the automated complete switch maintains the power distribution terminal to work continuously for a period of time when the line is out of power due to a fault or maintenance, so as to complete a series of tasks such as fault detection, information reporting, and opening and closing operations of the switch. In order to achieve switch status monitoring, analog quantity acquisition and fault judgment, fault isolation and power restoration in non-fault areas. Therefore, the backup power supply technology solution for automated complete switchgear is also an important technical problem that must be solved in the construction of distribution automation. The reasonable configuration of the backup power supply is not only related to the safe operation and power supply reliability of the distribution network, but also affects the construction cost of distribution automation and the operation and maintenance cost of the distribution automation system. The maintenance-free valve-controlled sealed lead-acid batteries currently used in large quantities are not completely maintenance-free. Only correct use and maintenance can have a longer life. In particular, the operating environment of intelligent equipment in the distribution network is harsh, the on-site influencing factors are complex, the battery discharge cycle is too much, the discharge depth is too large, and the continuous high temperature environment in the southern summer will lead to the deterioration of the operation of the lead-acid battery and the reduction of its service life. From the current operation and maintenance experience, there are mainly three types of problems:

[0004] (1) Battery life problems caused by harsh environments. At present, users require that the life of the backup power supply of intelligent distribution terminals is as long as possible, preferably 8 to 10 years, especially in outdoor ambient temperatures, it should still be able to maintain a relatively long life. The general nominal life of valve-regulated lead-acid batteries is about 6 years at 25°C, but in actual operation, performance degradation often occurs within less than 3 years. (2) Battery life problems caused by improper operation and maintenance. Through summarizing and analyzing a large number of distribution automation terminal equipment put into operation on site, it is found that a high proportion of the current distribution automation terminal backup power supply system has been damaged or the actual battery capacity has decreased due to improper operation and maintenance such as overcharging and overdischarging, resulting in poor battery operation and failure to play the role of backup power supply, posing a hidden danger to the normal operation of the system. (3) Capacity problems affected by the environment. The capacity of valve-regulated lead-acid batteries at -40°C is only about 30% of that at room temperature, and the utilization rate is sharply reduced. To deal with this situation, the idea of ​​derating design should be adopted in engineering design, and more than 3 times of redundant capacity should be used in the lead-acid battery capacity configuration to ensure the normal service life of lead-acid batteries in extremely high temperature climates. Summary of the invention

[0005] In view of the above-mentioned existing problems, the present invention adopts active battery monitoring technology to implement precise battery maintenance, and has achieved good results. By upgrading and improving the battery monitoring technology, precise monitoring of the battery is implemented, including continuous monitoring of real-time operation data and performance status data, and then the battery capacity and internal resistance are verified and measured; according to the actual state of the battery, the automatic maintenance strategies such as charging, discharging, and activation are adjusted to avoid overcharging, over-discharging, and undercharging of the battery, so as to achieve the purpose of intelligent repair and optimized use of the battery, and realize precise maintenance of the battery to ensure endurance. By real-time monitoring of the battery status, verification and measurement of the battery capacity and internal resistance, and adjustment of automatic maintenance strategies such as charging, discharging, and activation according to the actual state of the battery, the intelligent operation and maintenance of the battery can be better realized.

[0006] In order to solve the above technical problems, a multi-parameter fusion switch battery status diagnosis method based on SVM is proposed, including:

[0007] Multi-parameter data is collected through sensors and pre-processed. Fault diagnosis features are extracted from the processed data, important features are screened using the Pearson correlation coefficient, and the data set is divided into a training set and a test set. SVM is combined with a BP neural network to form an SVM-BP model, and the battery status is evaluated by optimizing weights and parameters through training.

[0008] As a preferred solution of the multi-parameter fusion switch battery status diagnosis method based on SVM described in the present invention, wherein: the sensor collects multi-parameter data including collecting multi-parameter data of the device in normal operation and various fault states;

[0009] The multi-parameter data include ambient temperature, ambient humidity, battery surface temperature, operating current, operating voltage, and battery internal resistance;

[0010] The temperature of the surface of the automatic switch battery and the operating environment temperature of the automatic switch battery are detected by the temperature sensor;

[0011] Use humidity sensors to monitor the humidity of the operating environment;

[0012] The battery sensor is used to detect the real-time current data of the battery of the automated switch set.

[0013] As a preferred solution of the multi-parameter fusion switch battery status diagnosis method based on SVM of the present invention, wherein: the preprocessing includes cleaning and standardizing the collected data;

[0014] The continuity of data in time is judged by the time dimension. When the collected data is continuous in time, the data is preliminarily identified as valid data. The average value of the data in the current time range is calculated. According to the deviation between the value range of the data set and the average value, the data that obviously deviates from the average value is removed, that is, the invalid data and abnormal data are analyzed and identified;

[0015] At the same time, when the collected data is discontinuous in the time dimension, the data is deemed to be random data generated by the collection problem, the values ​​determined to be random data are cleared, and fixed value filling or statistical value filling is used, and the values ​​are further standardized and normalized.

[0016] As a preferred solution of the multi-parameter fusion switch battery status diagnosis method based on SVM of the present invention, wherein: the preprocessing also includes information redundant parameters and complementary parameters obtained by the system through the monitoring device;

[0017] The redundant parameters are multiple repeated information collected by multiple sensors from any multi-parameter data of the battery connector in different dimensions, and multiple sensors are used to collect physical quantity information;

[0018] The complementary parameters establish a correlation matrix between the battery temperature and the current flowing through the battery, a correlation matrix between the battery ambient temperature and the battery internal resistance, and a correlation matrix between the battery ambient humidity and the battery internal resistance. The confidence coefficient of the data is calculated through the correlation matrix data, and the confidence coefficient is merged into the data set as a complementary parameter of the acquisition parameter. The data set is divided into a training set and a test set. The training set is used to train the model, and the test set is used to evaluate the final effect of the model.

[0019] As a preferred solution of the multi-parameter fusion switch battery state diagnosis method based on SVM described in the present invention, wherein: the extraction of fault diagnosis features includes extracting an important feature set X' that is helpful for fault diagnosis from the preprocessed data through the Pearson correlation coefficient, including time domain features, frequency domain features, and time-frequency domain features, combining the selected important features with historical experience to construct an automated complete switch battery defect diagnosis model, and combining historical experience to assign weights to the extracted features to form a weighted feature set W i , the selected features and historical weights are integrated to form a comprehensive feature vector F, an automated complete switch battery defect diagnosis model is constructed, and the status is scored through the classification boundary obtained by the model:

[0020]

[0021] S(F′)=Classification(SVM new (F′)

[0022] Among them, SVM new (F) is the new support vector machine model, b is the bias term, C is the penalty parameter, M is the total number of training samples, ξ j is a slack variable, p is a hyperparameter adjusted based on historical experience, S(F') is a state scoring function, which represents the classification result of the feature vector F'; F' is the comprehensive feature vector of the sample to be classified, Classification represents the classification process, and SVM new (F') is the classification of feature vector F' using the newly constructed SVM model.

[0023] As a preferred solution of the multi-parameter fusion switch battery state diagnosis method based on SVM of the present invention, wherein: the extraction of fault diagnosis features also includes dividing the defects of the automated complete switch battery into three states of normal, alarm and fault by constructing the calculation results of the automated complete switch battery defect diagnosis model, and defining the score value range of different states by the result of S(F');

[0024] By comparing the Pearson correlation coefficient of the battery internal resistance of the batteries of adjacent data in the data set;

[0025] When the solved Pearson correlation coefficient is within the Pearson correlation coefficient threshold range, the battery internal resistance data corresponding to the extreme value of the Pearson correlation coefficient is recorded as the normal value range of the internal resistance parameter of the current battery pack, and the current data set is selected as the healthy state data set, corresponding to the normal state of the battery;

[0026] When the correlation coefficient is outside the Pearson correlation coefficient threshold range, the current value is recorded as the alarm value, and the current data set is marked as a suspected fault data set, and the corresponding battery status is in the alarm state. The data set with a correlation coefficient outside the Pearson correlation coefficient threshold range is further used to judge the corresponding battery working current. When the working current is lower than the preset threshold, the current value is recorded as the fault value, and the current data set is marked as a battery fault data set, and the corresponding battery status is in the fault state.

[0027] As a preferred solution of the multi-parameter fusion switch battery status diagnosis method based on SVM of the present invention, wherein: the SVM-BP model includes the weight parameters of the SVM model constructed by using the improved BP neural network to form the SVM-BP;

[0028] Through BP neural network training samples, the neural network model of the monitored object is trained to establish a model of the logical relationship between the input parameters of the measured object and the operating status of the measured object;

[0029] Determine the weights and thresholds of the BP neural network for optimization: the average value of the square of the difference between the actual monitoring value and the training sample data value is used as the objective function f(α) of the optimization algorithm:

[0030]

[0031] Among them, P i is the evaluation value output by the model, is the actual value, N is the number of training samples, n is the variable index, and α is the normalized value of the output result of the BP neural network;

[0032] Determine the objective function f(x) of the optimization algorithm for the SVM model:

[0033]

[0034] Among them, K(x n -x) is the kernel function, b is the bias term;

[0035] Initialize the network and provide the input data to the first hidden layer of the network. The data propagates forward in the network. The neurons in each layer calculate the weighted sum of their inputs and generate outputs through the activation function. The output is passed to the next layer. The last layer, the output layer, generates the prediction result f(α). Through multiple training network iterations, the current normalized value updates the α value, so that the SVM model gradually approaches the optimal solution.

[0036] The training set data is used to train and optimize the mathematical model, and the test set data is input into the mathematical model to test the mathematical model, and the effectiveness of the model is verified according to the output results;

[0037] BP neural network training is performed on the sampled data of different operating status types, such as normal, alarm and fault, and then passed to the SVM model for model fusion optimization. The accuracy of the model is judged by evaluating the output results, and the SVM-BP model is iteratively optimized to evaluate the operating status of the automated switch battery and reduce the probability of misjudgment and missed judgment.

[0038] The trained SVM-BP model is deployed to the real-time monitoring system to perform real-time monitoring and fault diagnosis of the equipment operation status, and real-time monitoring and operation status diagnosis of the battery intermediate connector.

[0039] Another object of the present invention is to provide a multi-parameter fusion switch battery status diagnosis system based on SVM. The present invention aims to accurately monitor and diagnose the operating status of the switch battery, including normal, alarm and fault status; improve the accuracy and reliability of fault diagnosis by fusing multi-parameter data; use machine learning algorithms to reduce the probability of misjudgment and missed judgment, and realize automated and intelligent status monitoring; provide data support for the maintenance and management of the switch battery, extend the battery life, and ensure safe and stable operation of the equipment.

[0040] As a preferred solution of the multi-parameter fusion switch battery status diagnosis system based on SVM described in the present invention, it is characterized by comprising a data acquisition module, a data preprocessing module, a feature extraction module, a model training and optimization module and a status diagnosis module;

[0041] The data acquisition module collects multi-parameter data of the switch battery through various sensors, including ambient temperature, humidity, battery surface temperature, operating current, operating voltage, and battery internal resistance, and provides raw data to the data preprocessing module;

[0042] The data preprocessing module receives the raw data from the data acquisition module, cleans, standardizes and normalizes the collected data, and passes the processed data to the feature extraction module;

[0043] The feature extraction module receives data from the data preprocessing module, uses the Pearson correlation coefficient to filter out features corresponding to fault diagnosis from the preprocessed data, assigns weights to the features based on historical experience, and constructs a comprehensive feature vector to pass to the model training and optimization module;

[0044] The model training and optimization module receives the feature vector of the feature extraction module, combines the SVM and BP neural network, constructs the SVM-BP model for training and optimization, trains the model through the training set data, and uses the test set data to evaluate the model effect, and passes the result to the status diagnosis module;

[0045] The state diagnosis module uses the trained SVM-BP model to perform state scoring on the real-time monitoring data, classifies the battery state into normal, warning and fault, and outputs the diagnosis result.

[0046] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and is characterized in that when the processor executes the computer program, the steps of the multi-parameter fusion switch battery status diagnosis method based on SVM are implemented.

[0047] A computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of the multi-parameter fusion switch battery status diagnosis method based on SVM are implemented.

[0048] Beneficial effects of the present invention: The present invention can better realize intelligent operation and maintenance of batteries by real-time monitoring of battery status, verification and measurement of battery capacity and internal resistance, and adjusting automatic maintenance strategies such as charging, discharging, and activation according to the actual battery status. At the same time, with real-time monitoring of battery status, the monitoring status information of the battery can be sent to the distribution automation master station through the information point table of the distribution automation terminal through the communication channel. When the backup power battery status is found to be abnormal, the distribution automation master station is alarmed through remote signaling, and the operation and maintenance personnel are notified in time to diagnose and repair on site.

[0049] The battery maintenance work has been transformed from passive to active, which has improved the operation and maintenance level of distribution automation terminal equipment, greatly reduced the operation and maintenance workload, and included the status of backup power supply batteries in the daily operation management of distribution automation equipment, achieving more timely and rapid operation and maintenance management. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work, among which:

[0051] Figure 1 An overall flow chart of a multi-parameter fusion switch battery status diagnosis method based on SVM provided in one embodiment of the present invention.

[0052] Figure 2 A system solution module diagram of a multi-parameter fusion switch battery status diagnosis system based on SVM provided in one embodiment of the present invention. DETAILED DESCRIPTION

[0053] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0054] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0055] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it an embodiment that is mutually exclusive with other embodiments, either individually or selectively.

[0056] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0057] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0058] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0059] Example 1, reference Figure 1 , which is the first embodiment of the present invention, and provides a multi-parameter fusion switch battery status diagnosis method based on SVM, comprising:

[0060] The battery operation status of the automated switchgear is in an uncontrolled state. It is common that the battery is replaced once it shows a fault, insufficient battery life, and cannot meet the backup guarantee requirements. The operation and maintenance strategy is simple and extensive, which increases the operation and maintenance workload, wastes the investment cost of battery replacement, and also causes a waste of resources. It cannot fundamentally solve the operation and maintenance problems of the automated switchgear battery. At the same time, based on the real-time monitoring of the battery status of the automated switchgear, the monitoring status information of the battery can be sent to the distribution automation master station through the information point table of the distribution automation terminal through the communication channel. When the monitoring finds that the backup power battery status is abnormal, the remote signal is used to realize the alarm at the distribution automation master station, and the operation and maintenance personnel are notified in time for on-site diagnosis and repair. The battery maintenance work is transformed from passive to active, which improves the operation and maintenance level of the distribution automation terminal equipment, and greatly reduces the operation and maintenance workload. The status of the backup power battery is also included in the daily operation management of the distribution automation equipment, so as to achieve more timely and rapid operation and maintenance management.

[0061] S1: Collect multi-parameter data through sensors and pre-process the multi-parameter data.

[0062] Furthermore, multi-parameter data of the equipment under normal operation and various fault conditions are collected;

[0063] The multi-parameter data include ambient temperature, ambient humidity, battery surface temperature, operating current, operating voltage, and battery internal resistance;

[0064] The temperature of the surface of the automatic switch battery and the operating environment temperature of the automatic switch battery are detected by the temperature sensor;

[0065] Use humidity sensors to monitor the humidity of the operating environment;

[0066] The battery sensor is used to detect the real-time current data of the battery of the automated switch set.

[0067] It should be noted that the collected data were cleaned and standardized to improve data quality;

[0068] The continuity of data in time is judged by the time dimension. When the collected data is continuous in time, the data is preliminarily identified as valid data. The average value of the data in the current time range is calculated. According to the deviation between the value range of the data set and the average value, the data that obviously deviates from the average value is removed, that is, the invalid data and abnormal data are analyzed and identified;

[0069] At the same time, when the collected data is discontinuous in the time dimension, the data is deemed to be random data generated by the collection problem, the values ​​determined to be random data are cleared, and fixed value filling is used, that is, -9999 is used instead of missing values ​​or statistical values, that is, the average value of the data set is filled, and the values ​​are further standardized and normalized.

[0070] The system obtains information redundant parameters and complementary parameters through monitoring devices;

[0071] The redundant parameters are multiple repeated information collected by multiple sensors from any multi-parameter data of the battery connector in different dimensions, and multiple sensors are used to collect physical quantity information;

[0072] The complementary parameters establish a correlation matrix between the battery temperature and the current flowing through the battery, a correlation matrix between the battery ambient temperature and the battery internal resistance, and a correlation matrix between the battery ambient humidity and the battery internal resistance. The confidence coefficient of the data is calculated through the correlation matrix data, and the confidence coefficient is merged into the data set as a complementary parameter of the acquisition parameter. The data set is divided into a training set and a test set. The training set is used to train the model, and the test set is used to evaluate the final effect of the model.

[0073] S2: Extract fault diagnosis features from the processed data, use the Pearson correlation coefficient to screen important features, and divide the dataset into training and testing sets.

[0074] Furthermore, the important feature set X' that is helpful for fault diagnosis is extracted from the preprocessed data through the Pearson correlation coefficient, including time domain features, frequency domain features, and time-frequency domain features. The selected important features are combined with historical experience to construct an automated complete switch battery defect diagnosis model. Combined with historical experience, weights are assigned to the extracted features to form a weighted feature set W i :

[0075]

[0076] Among them, W i is the weight of the i-th feature, h i is with the feature x i The corresponding historical experience weight, x i is the i-th feature in the feature set, and I is the total number of features in the feature set;

[0077] The selected features and historical weights are integrated to form a comprehensive feature vector Construct an automated switch battery defect diagnosis model and use the classification boundaries obtained by the model to score the status:

[0078]

[0079] S(F′)=Classification(SVM new (F′)

[0080] Among them, SVM new (F) is the new support vector machine model, b is the bias term, C is the penalty parameter, M is the total number of training samples, ξ j is a slack variable, p is a hyperparameter adjusted based on historical experience, S(F') is a state scoring function, which represents the classification result of the feature vector F'; F' is the comprehensive feature vector of the sample to be classified, Classification represents the classification process, and SVM new (F') is the classification of feature vector F' using the newly constructed SVM model.

[0081] It should be noted that the calculation results of the defect diagnosis model of the automatic complete switch battery are used to divide the defects of the automatic complete switch battery into three states: normal, alarm and fault. The score value range of different states is defined by the results of S(F');

[0082] By comparing the Pearson correlation coefficient of the battery internal resistance of the batteries of adjacent data in the data set;

[0083] When the solved Pearson correlation coefficient is within the Pearson correlation coefficient threshold range, the battery internal resistance data corresponding to the extreme value of the Pearson correlation coefficient is recorded as the normal value range of the internal resistance parameter of the current battery pack, and the current data set is selected as the healthy state data set, corresponding to the normal state of the battery;

[0084] When the correlation coefficient is outside the Pearson correlation coefficient threshold range, the current value is recorded as the alarm value, and the current data set is marked as a suspected fault data set, and the corresponding battery status is in the alarm state. The data set with a correlation coefficient outside the Pearson correlation coefficient threshold range is further used to judge the corresponding battery working current. When the working current is lower than the preset threshold, the current value is recorded as the fault value, and the current data set is marked as a battery fault data set, and the corresponding battery status is in the fault state.

[0085] S3: Combine SVM with BP neural network to form SVM-BP model, and evaluate the battery status by training and optimizing weights and parameters.

[0086] Furthermore, the weight parameters of the SVM model are constructed using the improved BP neural network to form SVM-BP;

[0087] Through BP neural network training samples, the neural network model of the monitored object is trained to establish a model of the logical relationship between the input parameters of the measured object and the operating status of the measured object;

[0088] Determine the weights and thresholds of the BP neural network for optimization: the average value of the square of the difference between the actual monitoring value and the training sample data value is used as the objective function f(α) of the optimization algorithm:

[0089]

[0090] Among them, P i is the evaluation value output by the model, is the actual value, N is the number of training samples, n is the variable index, and α is the normalized value of the output result of the BP neural network;

[0091] Determine the objective function f(x) of the optimization algorithm for the SVM model:

[0092]

[0093] Among them, K(x n -x) is the kernel function, b is the bias term;

[0094] Initialize the network and provide the input data to the first hidden layer of the network. The data propagates forward in the network. The neurons in each layer calculate the weighted sum of their inputs and generate outputs through the activation function. The output is passed to the next layer. The last layer, the output layer, generates the prediction result f(α). Through multiple training network iterations, the current normalized value updates the α value, so that the SVM model gradually approaches the optimal solution.

[0095] The training set data is used to train and optimize the mathematical model, and the test set data is input into the mathematical model to test the mathematical model, and the effectiveness of the model is verified according to the output results;

[0096] BP neural network training is performed on the sampled data of different operating status types, such as normal, alarm and fault, and then passed to the SVM model for model fusion optimization. The accuracy of the model can be judged by evaluating the output results, and the iterative optimization of the SVM-BP model can be further carried out to achieve a more comprehensive evaluation of the operating status of the automated switch battery and reduce the probability of misjudgment and missed judgment. Compared with the traditional single SVM parameter fault diagnosis method, the method combined with BP neural network multi-parameter fusion has better classification performance and generalization ability, and the process can further improve the accuracy and reliability of fault diagnosis.

[0097] The trained SVM-BP model is deployed to the real-time monitoring system to perform real-time monitoring and fault diagnosis of the equipment operation status, and real-time monitoring and operation status diagnosis of the battery intermediate connector.

[0098] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

[0099] Embodiment 2, the second embodiment of the present invention, is different from the first two embodiments in that:

[0100] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program codes.

[0101] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0102] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0103] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0104] Example 3, reference Figure 2 , which is the third embodiment of the present invention, and provides a multi-parameter fusion switch battery status diagnosis system based on SVM, including a data acquisition module 10, a data preprocessing module 20, a feature extraction module 30, a model training and optimization module 40 and a status diagnosis module 50;

[0105] The data acquisition module 10 collects multi-parameter data of the switch battery through various sensors, including ambient temperature, humidity, battery surface temperature, operating current, operating voltage, and battery internal resistance, and provides raw data to the data preprocessing module 20;

[0106] The data preprocessing module 20 receives the raw data from the data acquisition module, cleans, standardizes and normalizes the collected data, and passes the processed data to the feature extraction module 30;

[0107] The feature extraction module 30 receives the data from the data preprocessing module 20, uses the Pearson correlation coefficient to filter out features corresponding to fault diagnosis from the preprocessed data, assigns weights to the features based on historical experience, and constructs a comprehensive feature vector to pass to the model training and optimization module;

[0108] The model training and optimization module 40 receives the feature vector of the feature extraction module 30, combines the SVM and BP neural network, constructs the SVM-BP model for training and optimization, trains the model through the training set data, and uses the test set data to evaluate the model effect, and passes the result to the state diagnosis module 50;

[0109] The state diagnosis module 50 uses the trained SVM-BP model to perform state scoring on the real-time monitoring data, classifies the battery state into normal, warning and fault, and outputs the diagnosis result.

[0110] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A multi-parameter fusion switch battery status diagnosis method based on SVM, characterized by: include, Collect multi-parameter data through sensors and pre-process the multi-parameter data; Extract fault diagnosis features from the processed data, use the Pearson correlation coefficient to screen important features, and divide the data set into training and test sets; The SVM is combined with the BP neural network to form an SVM-BP model, and the battery status is evaluated by optimizing the weights and parameters through training.

2. The multi-parameter fusion switch battery status diagnosis method based on SVM as claimed in claim 1 is characterized by: The sensor collects multi-parameter data including collecting multi-parameter data of the equipment in normal operation and various fault states; The multi-parameter data include ambient temperature, ambient humidity, battery surface temperature, operating current, operating voltage, and battery internal resistance; The temperature of the surface of the automatic switch battery and the operating environment temperature of the automatic switch battery are detected by the temperature sensor; Use humidity sensors to monitor the humidity of the operating environment; The battery sensor is used to detect the real-time current data of the battery of the automated switch set.

3. The multi-parameter fusion switch battery status diagnosis method based on SVM as claimed in claim 2 is characterized by: The preprocessing includes cleaning and standardizing the collected data; The continuity of data in time is judged by the time dimension. When the collected data is continuous in time, the data is preliminarily identified as valid data. The average value of the data in the current time range is calculated. According to the deviation between the value range of the data set and the average value, the data that obviously deviates from the average value is removed, that is, the invalid data and abnormal data are analyzed and identified; At the same time, when the collected data is discontinuous in the time dimension, the data is deemed to be random data generated by the collection problem, the values ​​determined to be random data are cleared, and fixed value filling or statistical value filling is used, and the values ​​are further standardized and normalized.

4. The multi-parameter fusion switch battery status diagnosis method based on SVM as claimed in claim 3 is characterized by: The preprocessing also includes information redundancy parameters and complementary parameters obtained by the system through the monitoring device; The redundant parameters are multiple repeated information collected by multiple sensors from any multi-parameter data of the battery connector in different dimensions, and multiple sensors are used to collect physical quantity information; The complementary parameters establish a correlation matrix between the battery temperature and the current flowing through the battery, a correlation matrix between the battery ambient temperature and the battery internal resistance, and a correlation matrix between the battery ambient humidity and the battery internal resistance. The confidence coefficient of the data is calculated through the correlation matrix data, and the confidence coefficient is merged into the data set as a complementary parameter of the acquisition parameter. The data set is divided into a training set and a test set. The training set is used to train the model, and the test set is used to evaluate the final effect of the model.

5. The multi-parameter fusion switch battery status diagnosis method based on SVM as claimed in claim 4 is characterized by: The fault diagnosis feature extraction includes extracting an important feature set X' that is helpful for fault diagnosis from the preprocessed data through the Pearson correlation coefficient, including time domain features, frequency domain features, and time-frequency domain features, combining the selected important features with historical experience to construct an automated complete switch battery defect diagnosis model, and combining historical experience to assign weights to the extracted features to form a weighted feature set W i , the selected features and historical weights are integrated to form a comprehensive feature vector F, an automated complete switch battery defect diagnosis model is constructed, and the status is scored through the classification boundary obtained by the model: Among them, SVM new (F) is the new support vector machine model, b is the bias term, C is the penalty parameter, M is the total number of training samples, ξ j is a slack variable, p is a hyperparameter adjusted based on historical experience, S(F') is a state scoring function, which represents the classification result of the feature vector F'; F' is the comprehensive feature vector of the sample to be classified, Classification represents the classification process, and SVM new (F') is the classification of feature vector F' using the newly constructed SVM model.

6. The multi-parameter fusion switch battery status diagnosis method based on SVM as claimed in claim 5, characterized in that: The extracting of fault diagnosis features also includes dividing the defects of the automated complete switch battery into three states: normal, warning, and fault by constructing the calculation results of the automated complete switch battery defect diagnosis model, and defining the score value ranges of different states by the results of S(F'); By comparing the Pearson correlation coefficient of the battery internal resistance of the batteries of adjacent data in the data set; When the solved Pearson correlation coefficient is within the Pearson correlation coefficient threshold range, the battery internal resistance data corresponding to the extreme value of the Pearson correlation coefficient is recorded as the normal value range of the internal resistance parameter of the current battery pack, and the current data set is selected as the healthy state data set, corresponding to the normal state of the battery; When the correlation coefficient is outside the Pearson correlation coefficient threshold range, the current value is recorded as the alarm value, and the current data set is marked as a suspected fault data set, and the corresponding battery status is in the alarm state. The data set with a correlation coefficient outside the Pearson correlation coefficient threshold range is further used to judge the corresponding battery working current. When the working current is lower than the preset threshold, the current value is recorded as the fault value, and the current data set is marked as a battery fault data set, and the corresponding battery status is in the fault state.

7. The multi-parameter fusion switch battery status diagnosis method based on SVM as claimed in claim 6 is characterized by: The SVM-BP model includes: using an improved BP neural network to construct the weight parameters of the SVM model to form the SVM-BP; Through BP neural network training samples, the neural network model of the monitored object is trained to establish a model of the logical relationship between the input parameters of the measured object and the operating status of the measured object; Determine the weights and thresholds of the BP neural network for optimization: the average of the squares of the differences between the actual detection values ​​and the training sample data values ​​is used as the objective function f(α) of the optimization algorithm: Among them, P i is the evaluation value output by the model, is the actual value, N is the number of training samples, n is the variable index, and α is the normalized value of the output result of the BP neural network; Determine the objective function f(x) of the optimization algorithm for the SVM model: Among them, K(x n -x) is the kernel function, b is the bias term; Initialize the network and provide the input data to the first hidden layer of the network. The data propagates forward in the network. The neurons in each layer calculate the weighted sum of their inputs and generate outputs through the activation function. The output is passed to the next layer. The last layer, the output layer, generates the prediction result f(α). Through multiple training network iterations, the current normalized value updates the α value, so that the SVM model gradually approaches the optimal solution. The training set data is used to train and optimize the mathematical model, and the test set data is input into the mathematical model to test the mathematical model, and the effectiveness of the model is verified according to the output results; BP neural network training is performed on the sampled data of different operating status types, such as normal, alarm and fault, and then passed to the SVM model for model fusion optimization. The accuracy of the model is judged by evaluating the output results, and the SVM-BP model is iteratively optimized to evaluate the operating status of the automated switch battery and reduce the probability of misjudgment and missed judgment. The trained SVM-BP model is deployed to the real-time monitoring system to perform real-time monitoring and fault diagnosis of the equipment operation status, and real-time monitoring and operation status diagnosis of the battery intermediate connector.

8. A system using the multi-parameter fusion switch battery status diagnosis method based on SVM as claimed in any one of claims 1 to 7, characterized in that: It includes data acquisition module, data preprocessing module, feature extraction module, model training and optimization module and status diagnosis module; The data acquisition module collects multi-parameter data of the switch battery through various sensors, including ambient temperature, humidity, battery surface temperature, operating current, operating voltage, and battery internal resistance, and provides raw data to the data preprocessing module; The data preprocessing module receives the raw data from the data acquisition module, cleans, standardizes and normalizes the collected data, and passes the processed data to the feature extraction module; The feature extraction module receives data from the data preprocessing module, uses the Pearson correlation coefficient to filter out features corresponding to fault diagnosis from the preprocessed data, assigns weights to the features based on historical experience, and constructs a comprehensive feature vector to pass to the model training and optimization module; The model training and optimization module receives the feature vector of the feature extraction module, combines the SVM and BP neural network, constructs the SVM-BP model for training and optimization, trains the model through the training set data, and uses the test set data to evaluate the model effect, and passes the result to the status diagnosis module; The state diagnosis module uses the trained SVM-BP model to perform state scoring on the real-time monitoring data, classifies the battery state into normal, warning and fault, and outputs the diagnosis result.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the multi-parameter fusion switch battery status diagnosis method based on SVM described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the multi-parameter fusion switching battery status diagnosis method based on SVM described in any one of claims 1 to 7 are implemented.

Images