High and low voltage power distribution cabinet operation monitoring system based on data analysis

Abstract

The invention discloses a high and low voltage power distribution cabinet operation monitoring system based on data analysis, and relates to the technical field of power distribution cabinet operation monitoring, the system comprises an operation monitoring platform, the operation monitoring platform is in communication connection with a data acquisition module, a fault risk analysis module, a fault risk diagnosis module, a fault positioning module and a monitoring early warning module, the modules are in electric signal connection; the data acquisition module is used for collecting and preprocessing power distribution equipment data of the high-low voltage power distribution cabinet. According to the invention, through integration of the data acquisition module, the fault risk analysis module, the diagnosis module and the positioning module, comprehensive monitoring of the operation state of the high-low voltage power distribution cabinet is realized, a fault risk diagnosis model is established by using a deep learning algorithm, and potential fault risks are accurately identified in combination with real-time data and historical cases, so that the accuracy and timeliness of early warning are significantly improved, and the working efficiency of the high-low voltage power distribution cabinet is improved. And operation and maintenance personnel can intervene in advance according to the early warning information and take preventive measures, thereby effectively avoiding faults and ensuring stable operation of the power system.

Description

Technical Field

[0001] The present invention relates to the technical field of power distribution cabinet operation monitoring, and in particular to a high and low voltage power distribution cabinet operation monitoring system based on data analysis. Background Art

[0002] With the acceleration of urbanization and the improvement of industrialization, the scale of power systems is getting larger and larger, and the types and quantities of equipment are also increasing. As key equipment in the power system, the stability of the operating status of high and low voltage distribution cabinets is directly related to the safety and reliable operation of the entire power system. Therefore, it is particularly important to effectively monitor the operation of high and low voltage distribution cabinets.

[0003] For example, Chinese patent publication number: CN119209919A is a high and low voltage distribution cabinet operation monitoring system based on data analysis, including an electrical component status monitoring module, a moving part lubrication judgment module, a distribution cabinet cleaning analysis module, a distribution cabinet inspection and early warning module and a remote control terminal.

[0004] In the prior art, through the cooperation between various modules, the high and low voltage distribution cabinets are comprehensively monitored and accurately analyzed and warned, so as to solve the problem that the high and low voltage distribution cabinets cannot be inspected in time. However, during the operation, the operating environment and load conditions of the distribution cabinet will change, which will cause certain errors in the diagnosis of fault risks, resulting in the inability to timely identify minor abnormal changes, affecting the insufficient accuracy of the diagnosis. Therefore, how to accurately diagnose the fault risks based on the operating environment and load conditions of the distribution cabinet and ensure the accuracy of the execution of operation and maintenance measures is the problem to be solved by the present invention. To this end, a high and low voltage distribution cabinet operation monitoring system based on data analysis is proposed. Summary of the invention

[0005] The object of the present invention is to provide a high and low voltage distribution cabinet operation monitoring system based on data analysis to solve the problems raised in the above background technology.

[0006] In order to solve the above technical problems, the technical solution adopted by the present invention is: A high and low voltage power distribution cabinet operation monitoring system based on data analysis, comprising an operation monitoring platform, wherein the operation monitoring platform is communicatively connected with a data acquisition module, a fault risk analysis module, a fault risk diagnosis module, a fault location module and a monitoring and early warning module, wherein electrical signals are connected between the modules; The data acquisition module is used to collect and pre-process the distribution equipment data of the high and low voltage distribution cabinets, wherein the distribution equipment data includes equipment status data, operating environment data and load data; The fault risk analysis module is used to extract features related to fault risk diagnosis by combining the preprocessed distribution equipment data, obtain a diagnostic feature sequence, and analyze the risk trend of distribution equipment data in each dimension; The fault risk diagnosis module is used to establish a fault risk diagnosis model based on the feature data of the diagnostic feature sequence and the deep learning algorithm, obtain a fault risk score, diagnose the fault risk of the distribution cabinet, and timely discover the potential fault risk of the distribution cabinet, and provide early warning information for operation and maintenance personnel; The fault location module is used to locate abnormal features based on the fault risk diagnosis results, assist operation and maintenance personnel in troubleshooting problems, and optimize equipment maintenance strategies; The monitoring and early warning module is used to combine the fault risk diagnosis and fault location results to determine the specific risk level of the fault, generate and issue corresponding early warning information, and notify the operation and maintenance personnel to handle it.

[0007] A further improvement of the technical solution of the present invention is that the data acquisition module specifically includes: The original distribution equipment data including equipment status data, operating environment data and load data are collected through various sensors of high and low voltage distribution cabinets. The sensors collect the original distribution equipment data at preset fixed time intervals and store them in the form of time series. For equipment status data, voltage, current and equipment operation record data are collected. For operating environment data, ambient temperature, ambient humidity and ambient vibration acceleration data are collected. For load data, load rate, power factor deviation, load fluctuation frequency, peak load duration and three-phase load imbalance data are collected. Among them, the sensors include voltage sensors, current sensors, vibration sensors, temperature sensors, humidity sensors, load sensors, power factor meters, etc., which are respectively used to monitor the key parameters of the equipment such as voltage, current, temperature, humidity, vibration acceleration, etc.; Perform data cleaning and standardization preprocessing operations on the collected raw distribution equipment data; Integrate the pre-processed distribution equipment data and store it in the data warehouse. Use structured storage to organize the data into tables to facilitate subsequent query and analysis.

[0008] A further improvement of the technical solution of the present invention is that: the fault risk analysis module includes a feature extraction unit, an abnormal feature marking unit and a risk trend unit; The feature extraction unit is used to perform feature analysis on the preprocessed distribution equipment data, and extract feature sub-indicators related to fault risk diagnosis from the equipment status data, operating environment data and load data respectively; The abnormal feature marking unit is used to determine the normal value of each feature sub-indicator in combination with historical data, and distinguish and mark the abnormal features to obtain a diagnostic feature sequence; The risk trend unit is used to analyze the characteristic sub-indicators in the diagnostic characteristic sequence, calculate the equipment risk trend value, the environmental risk trend value and the load risk trend value respectively, and clarify the risk trend of the distribution equipment data in each dimension.

[0009] A further improvement of the technical solution of the present invention is that the feature extraction unit specifically includes: Extract the pre-processed distribution equipment data, perform feature analysis on the equipment status data, operating environment data and load data, and extract features related to fault risk diagnosis, including equipment features, environment features and load features; Perform feature analysis on the equipment status data, extract equipment features, and determine the sub-indicators contained in the equipment features, which are voltage deviation, current peak, and equipment operating time; Perform feature analysis on the operating environment data, extract environmental features, and determine the sub-indicators contained in the environmental features, namely, environmental temperature, environmental humidity, and environmental vibration intensity; The load data is analyzed to extract the load characteristics, and the sub-indicators contained in the load characteristics are determined, which are load rate, power factor deviation, load fluctuation frequency, peak load duration and three-phase load imbalance.

[0010] A further improvement of the technical solution of the present invention is that the abnormal feature marking unit specifically includes: Based on the output of the feature extraction unit, the historical data covering different time periods and different operating conditions are collected for the equipment features, environmental features and load features extracted from the distribution equipment data. The historical data are integrated and classified according to the feature type to ensure the organization and accessibility of the data. Analyze the integrated and classified historical data, and combine with the operation monitoring requirements of high and low voltage distribution cabinets to determine the normal value of each characteristic sub-indicator as the abnormal judgment standard. In the analysis process, statistical methods are used to calculate the mean, standard deviation, and median statistics of each sub-indicator to determine the central trend and dispersion of the data. According to the calculated statistics, the normal value range is set, with the mean as the center and a certain multiple of the standard deviation as the upper and lower limits. The characteristic sub-indicator data of the power distribution equipment collected in real time are compared with the determined normal value range, and the characteristic sub-indicators of the power distribution equipment that deviate from the normal value range are marked as abnormal features. After the marking is completed, the marking results of all the characteristic sub-indicators of the power distribution equipment are arranged in chronological order to generate a diagnostic feature sequence, where the diagnostic feature sequence contains the marking information of normal and abnormal features and retains the chronological order of the features.

[0011] A further improvement of the technical solution of the present invention is that the risk trend unit specifically includes: Perform a preliminary time series analysis on the equipment status data, operating environment data, and load data in the diagnostic feature sequence. Calculate the change rate of each feature sub-indicator at intervals of adjacent unit time. Extract the change rate results by comparing the data at adjacent time points. The change rate reflects the trend of the feature sub-indicator deviating from the normal value range in a short period of time. For the equipment characteristic sub-indicators of the equipment status data, analyze the deviation of the voltage deviation, current peak value and equipment operation time per unit time compared with the normal value range, as well as the change rate of the analysis, and comprehensively analyze the equipment risk trend value of the high and low voltage distribution cabinets to analyze the change trend of the equipment status data; For the environmental characteristic sub-indicators of the operating environment data, analyze the deviation values ​​of the ambient temperature, ambient humidity, and ambient vibration intensity compared with the normal value range per unit time, as well as the change rate of the analysis, and comprehensively analyze to obtain the environmental risk trend value to evaluate the risk trend of the operating environment data; For the load characteristic sub-indicators of load data, analyze the deviation of load rate, power factor deviation, load fluctuation frequency, peak load duration and three-phase load imbalance compared with the normal value range, as well as the change rate of analysis, and obtain the load risk trend value through comprehensive analysis to clarify the load risk trend of high and low voltage distribution cabinets.

[0012] A further improvement of the technical solution of the present invention is that the fault risk diagnosis module specifically includes: Collect a large amount of historical distribution equipment data of high and low voltage distribution cabinets in advance, and extract features related to fault risk diagnosis from them. Then, combine the monitoring requirements of high and low voltage distribution cabinets with the abnormal features therein, analyze the fault risk score, integrate the abnormal features and fault risk score, and obtain the risk data set, which is divided into training set, validation set and test set in the ratio of 7:1.5:1.5. According to the fault risk diagnosis requirements of high and low voltage distribution cabinets, a deep learning algorithm based on the convolutional neural network model is selected as the basic architecture, including the input layer, convolution layer, pooling layer and output layer. A fault risk diagnosis model is established, and the convolutional neural network model is trained using the training set. The performance of the model is monitored using the validation set. The hyperparameters of the model are adjusted according to the validation results, and then the test set is input into the trained model to evaluate the performance of the model and obtain the fault risk diagnosis model. The real-time diagnostic feature sequence related data is input into the trained fault risk diagnosis model to perform fault risk diagnosis of high and low voltage distribution cabinets, and then output the fault risk score.

[0013] A further improvement of the technical solution of the present invention is that the calculation process of the fault risk score is: Extract equipment risk trend value, environmental risk trend value and load risk trend value, set the maximum allowable value for each risk trend value, divide each risk trend value by its corresponding maximum allowable value, and normalize each risk trend value, that is, convert it to a unified scale; According to the different influences of equipment, environment and load on failure risk, a weight coefficient is assigned to each normalized risk trend value. The weight coefficient reflects the relative importance of each factor in failure risk assessment, and the sum of all weight coefficients should be 1. The normalized risk trend value is multiplied by the corresponding weight coefficient, and the products are added to obtain the final fault risk score. When the fault risk score is close to 0, it indicates that the fault risk is low. As the fault risk score increases, it indicates that the fault risk is gradually increasing.

[0014] A further improvement of the technical solution of the present invention is that the fault location module specifically includes: Receive the fault risk score output by the fault risk diagnosis model, identify the feature categories with higher risk trend values, and analyze the risk trend values ​​of each category to determine the main risk sources, and then identify specific abnormal feature sub-indicators; Map the identified abnormal characteristic sub-indicators to the specific equipment components of the high and low voltage distribution cabinets. Through the structural and functional analysis of the equipment, determine the affected equipment components. Then, combined with the operation records and maintenance history of the high and low voltage distribution cabinets, further narrow the scope of the fault and improve the accuracy of positioning. A fault location report is generated based on the analysis results, which lists in detail the abnormal characteristic sub-indicators, related equipment components, fault risk scores, and maintenance recommendations, to assist operation and maintenance personnel in quickly troubleshooting problems and optimizing maintenance strategies.

[0015] A further improvement of the technical solution of the present invention is that the monitoring and early warning module specifically includes: Receive the fault risk score output by the fault risk diagnosis model and the fault location report generated by the fault location module in real time, and divide the fault risks of high and low voltage distribution cabinets into three levels according to the preset risk level classification standard, namely low risk level, medium risk level and high risk level. Then, combined with the historical fault case library, assign corresponding risk thresholds to each risk level to adapt to different operating conditions; According to the output fault risk score, the risk level is determined, and then the corresponding warning information is generated. The warning information alarm includes the fault risk score, risk level, affected equipment components, abnormal characteristic sub-indicators and maintenance suggestions; Through multi-channel communication mechanisms (SMS, email, SCADA system pop-up window), early warning information is pushed to the operation and maintenance personnel's terminal in real time. Differentiated notifications are made based on the operation and maintenance personnel's role permissions (on-duty engineer, regional supervisor), and the recipient's status (online / offline) is verified before release to ensure that the information is delivered, and push logs are recorded at the same time; Establish an early warning response tracking mechanism to monitor the progress of operation and maintenance personnel in handling early warning information (read, confirmed, and being processed) in real time, automatically associate fault location reports through the work order system, push maintenance suggestions and operation guides, and set automatic escalation rules for no response after timeout. That is, if the information is not processed for more than 1 hour, it will be escalated to the superior supervisor to ensure that the fault is handled in a timely manner.

[0016] Due to the adoption of the above technical solution, the present invention has the following technical advances compared with the prior art: 1. The present invention provides a high and low voltage distribution cabinet operation monitoring system based on data analysis. By integrating data acquisition, fault risk analysis, diagnosis and positioning modules, it realizes comprehensive monitoring of the operation status of high and low voltage distribution cabinets. It uses deep learning algorithms to establish a fault risk diagnosis model, combines real-time data with historical cases, and accurately identifies potential fault risks, which significantly improves the accuracy and timeliness of early warning. Operation and maintenance personnel can intervene in advance according to the early warning information and take preventive measures to effectively avoid faults and ensure the stable operation of the power system.

[0017] 2. The present invention provides a high and low voltage distribution cabinet operation monitoring system based on data analysis, which can automatically generate a detailed fault location report, clearly point out the abnormal characteristic sub-indicators, affected equipment components and recommended maintenance measures, greatly simplifying the troubleshooting process of operation and maintenance personnel, reducing the time and errors of manual analysis. At the same time, through risk level classification, the operation and maintenance team can allocate resources more efficiently, give priority to high-risk faults, and ensure the continuous and reliable operation of key equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0019] Figure 1 It is a schematic diagram of the system function modules of the present invention; Figure 2 Schematic diagram of the work flow of the fault risk diagnosis module of the present invention. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. Embodiment 1, as Figure 1 , Figure 2 As shown, the present invention provides a high and low voltage distribution cabinet operation monitoring system based on data analysis, including an operation monitoring platform, the operation monitoring platform is communicatively connected with a data acquisition module, a fault risk analysis module, a fault risk diagnosis module, a fault location module and a monitoring and early warning module, wherein the electrical signals between the modules are connected; The data acquisition module is used to collect and pre-process the distribution equipment data of the high and low voltage distribution cabinets, wherein the distribution equipment data includes equipment status data, operating environment data and load data. The original distribution equipment data including equipment status data, operating environment data and load data are collected through various sensors of the high and low voltage distribution cabinets. The sensors collect the original distribution equipment data at preset fixed time intervals and store them in the form of time series. For the equipment status data, the voltage, current and equipment operation record data are collected. For the operating environment data, the ambient temperature, ambient humidity and ambient vibration acceleration data are collected. For the load data, the load rate, power factor deviation, load fluctuation frequency, peak load duration and three-phase load imbalance data are collected. The sensors include voltage sensors, current sensors, vibration sensors, temperature sensors, etc. Sensors, humidity sensors, load sensors, power factor meters, etc. are used to monitor the key parameters of the equipment, such as voltage, current, temperature, humidity, vibration acceleration, etc., and perform data cleaning and standardization preprocessing operations on the collected original distribution equipment data. Among them, filtering algorithms are used to remove noise, and interpolation or mean filling methods are used to process missing values. At the same time, historical data and statistical analysis methods are combined to identify and eliminate outliers to ensure that the cleaned data is more accurate and reliable. Then, the cleaned distribution equipment data is standardized, and data in different formats are converted into a unified format. Data in different dimensions are normalized to make them comparable. The preprocessed distribution equipment data is integrated and stored in the data warehouse. A structured storage method is used to organize the data into a table form to facilitate subsequent query and analysis. The fault risk analysis module is used to extract features related to fault risk diagnosis by combining the preprocessed distribution equipment data, obtain a diagnostic feature sequence, and analyze the risk trend of distribution equipment data in each dimension. The fault risk analysis module includes a feature extraction unit, an abnormal feature marking unit, and a risk trend unit; Among them, the feature extraction unit is used to perform feature analysis on the pre-processed distribution equipment data, and extract feature sub-indicators related to fault risk diagnosis in the equipment status data, operating environment data and load data respectively, extract the pre-processed distribution equipment data, perform feature analysis on the equipment status data, operating environment data and load data respectively, extract features related to fault risk diagnosis, including equipment characteristics, environmental characteristics and load characteristics, perform feature analysis on the equipment status data, extract equipment characteristics, and determine the sub-indicators included in the equipment characteristics, which are voltage deviation, current peak value and equipment operating time respectively. Among them, the voltage deviation reflects the degree of deviation between the actual operating voltage of the distribution equipment and the rated voltage. Excessive voltage deviation will cause the equipment to fail Normal operation affects the performance and life of the equipment, and even causes equipment failure. The voltage data of the equipment is collected in real time through the voltage sensor, and the actual voltage value collected is compared with the rated voltage value to calculate the voltage deviation. The current peak reflects the maximum current value passed by the equipment during operation, reflecting the load condition and electrical stress of the equipment. If the current peak often exceeds the rated current of the equipment, the equipment will heat up seriously, accelerate insulation aging, and increase the risk of equipment failure. The current sensor is used to continuously monitor the current changes of the equipment and record the maximum value of the current within a certain period of time, which is the current peak. The equipment operation time reflects the equipment usage time and accumulated workload. With the increase of operation time, the wear and aging of the equipment will gradually increase, and the failure will occur. The probability of failure will also increase accordingly. By monitoring the operating time of the equipment, the maintenance and inspection plan of the equipment can be reasonably arranged. By analyzing the operating record data of the equipment, the cumulative operating time of the equipment is counted, the operating environment data is feature analyzed, the environmental characteristics are extracted, and the sub-indicators contained in the environmental characteristics are determined, which are ambient temperature, ambient humidity and ambient vibration intensity. Among them, the ambient temperature has an important impact on the performance and life of the distribution equipment. Excessive temperature accelerates the insulation aging of the equipment, reduces the heat dissipation efficiency of the equipment, causes the temperature of the equipment to rise, and increases the risk of failure. Excessive low temperature may affect the normal operation of the equipment, such as solidifying the lubricating oil. The ambient temperature data is collected through the temperature sensor. Excessive ambient humidity will make the surface of the equipment damp, resulting in insulation failure. Performance is degraded, which is easy to cause leakage, short circuit and other faults. At the same time, excessive humidity may also promote the growth of mold and corrode equipment. Excessive humidity will generate static electricity and damage the electronic components of the equipment. Humidity sensors are used to monitor environmental humidity. Environmental vibration intensity reflects the vibration conditions of the environment in which the distribution equipment is located. Strong vibration may cause loose connections and damage to components of the equipment, affecting the normal operation of the equipment and increasing the possibility of failure. Vibration acceleration parameters are measured by vibration sensors, and environmental vibration intensity is evaluated. Load data is analyzed to extract load characteristics and determine the sub-indicators contained in the load characteristics, which are load rate, power factor deviation, load fluctuation frequency, peak load duration and three-phase load imbalance. Among them,The load rate refers to the ratio of the average load of the equipment within a certain period of time to the rated load, reflecting the utilization degree of the equipment load. If the load rate is too low, it means that the equipment is not fully utilized, resulting in a waste of resources. If the load rate is too high, the equipment will be in an overloaded state for a long time, accelerating equipment aging and increasing the risk of failure. The load data of the equipment is collected by the load sensor, and the total load within a certain period of time is counted and then divided by the product of the rated load and time in the time period to get the load rate. The power factor reflects the efficiency of the equipment in utilizing electric energy. If the power factor deviation is too large, it means that the equipment has a large reactive power loss problem, which will not only reduce the power supply efficiency of the power grid, but also may cause problems such as equipment heating and voltage fluctuations, affecting the normal operation of the equipment. The power factor of the equipment is measured by a power factor meter, and the measured value is compared with the standard power factor to calculate the power factor deviation. The load fluctuation frequency refers to the number of times the equipment load fluctuates per unit time. Frequent load fluctuations will cause the equipment to Unstable operation status increases the mechanical and electrical stress of the equipment, which can easily lead to equipment failure. Real-time monitoring and analysis of load data is carried out, and the number of load changes per unit time is counted, which is the load fluctuation frequency. Peak load duration refers to the operating time of the equipment under peak load status. Long-term peak load operation will cause the equipment to bear greater pressure and heat, accelerate the aging and damage of the equipment, and increase the probability of failure. By analyzing the load data, the peak load value of the equipment is determined, and then the operating time of the equipment under peak load status is counted. In a three-phase power supply system, the three-phase load imbalance reflects the degree of difference between the three-phase loads. The three-phase load imbalance will cause the rotating motor to vibrate more, heat up more, transformer loss to increase, efficiency to decrease, and may even cause equipment failure. The load currents of the three phases are measured separately, and the difference between the maximum phase current and the minimum phase current is calculated, and the ratio of the difference to the maximum phase current is calculated, which is the imbalance of the three-phase current; The abnormal feature marking unit is used to determine the normal value of each characteristic sub-indicator in combination with historical data, and distinguish and mark the abnormal features to obtain a diagnostic feature sequence. Based on the output of the feature extraction unit, the historical data covering different time periods and different operating conditions are collected for the equipment features, environmental features and load features extracted from the distribution equipment data, and the historical data are integrated and classified according to the feature type to ensure the organization and accessibility of the data. Among them, the historical data comprehensively reflects the operating status of the high and low voltage distribution cabinets under various conditions. The integrated and classified historical data is analyzed, and combined with the operation monitoring requirements of the high and low voltage distribution cabinets, the normal value of each characteristic sub-indicator is determined as the abnormal judgment mark. Accurate, wherein, during the analysis process, a statistical method is used to calculate the mean, standard deviation, and median statistics of each sub-indicator to determine the central tendency and dispersion of the data, and a normal value range is set based on the calculated statistics, with the mean as the center and a certain multiple of the standard deviation as the upper and lower limits, and the real-time collected distribution equipment characteristic sub-indicator data is compared with the determined normal value range, and the distribution equipment characteristic sub-indicator that deviates from the normal value range is marked as an abnormal feature. After the marking is completed, the marking results of all distribution equipment characteristic sub-indicators are arranged in chronological order to generate a diagnostic feature sequence, wherein the diagnostic feature sequence contains the marking information of normal and abnormal features, and retains the chronological order of the features; The risk trend unit is used to analyze the characteristic sub-indicators in the diagnostic feature sequence, calculate the equipment risk trend value, environmental risk trend value and load risk trend value respectively, clarify the risk trend of the distribution equipment data in each dimension, and conduct a preliminary analysis of the time series of the equipment status data, operating environment data and load data in the diagnostic feature sequence. The change rate of each characteristic sub-indicator is calculated with adjacent unit time intervals. By comparing the data at adjacent time points, the change rate results are extracted. The change rate reflects the trend of the characteristic sub-indicator deviating from the normal value range in a short period of time. For the equipment characteristic sub-indicators of the equipment status data, the deviation values ​​of the voltage deviation, current peak value and equipment operation time compared with the normal value range per unit time are analyzed. And the rate of change of analysis, comprehensive analysis to obtain the equipment risk trend value of high and low voltage distribution cabinets, analyze the change trend of equipment status data, for the environmental characteristic sub-indicators of the operating environment data, analyze the deviation values ​​of the ambient temperature, ambient humidity and ambient vibration intensity compared with the normal value range per unit time, and the rate of change of analysis, comprehensive analysis to obtain the environmental risk trend value, evaluate the risk trend of the operating environment data, for the load characteristic sub-indicators of the load data, analyze the deviation values ​​of the load rate, power factor deviation, load fluctuation frequency, peak load duration and three-phase load imbalance compared with the normal value range, and the rate of change of analysis, comprehensive analysis to obtain the load risk trend value, clarify the load risk trend of high and low voltage distribution cabinets; The expression of equipment risk trend value is: ; In the formula, is the equipment risk trend value, which indicates the comprehensive risk level of equipment status data. For the Deviation value of device characteristic sub-indicator ( , corresponding to voltage deviation, current peak and equipment operation time respectively), For the The normal value range of each device characteristic sub-indicator (usually mean ± 2 times standard deviation), For the The rate of change of each device characteristic sub-indicator per unit time, is the unit time interval, The value range is , when the deviation values ​​and change rates of all device characteristic sub-indicators are small, Close to 0, it means the device is in normal condition. When the deviation value or change rate of any device characteristic sub-indicator increases, Increase, indicating that the equipment status is deteriorating. When multiple equipment characteristic sub-indicators deviate from normal values ​​at the same time and the change rate is large, Rapid increase indicates that the equipment status has seriously deteriorated; The expression of environmental risk trend value is: ; In the formula, is the environmental risk trend value, which indicates the comprehensive risk level of the operating environment data. For the Deviation value of environmental characteristic sub-indicator ( , corresponding to ambient temperature, humidity and vibration intensity respectively), For the The normal value range of each environmental characteristic sub-indicator (usually mean ± 2 times standard deviation), For the The rate of change of each environmental characteristic sub-indicator per unit time, The value range is , when the deviation values ​​and change rates of all environmental characteristic sub-indicators are small, Close to 0, it means the environment is normal. When the deviation value or change rate of any environmental characteristic sub-indicator increases, Increase, indicating that the environmental status is deteriorating. When multiple environmental characteristic sub-indicators deviate from normal values ​​at the same time and the rate of change is large, Rapid increase indicates serious deterioration of environmental conditions; The expression of load risk trend value is: ; In the formula, is the load risk trend value, which indicates the comprehensive risk level of the load data. For the The deviation value of each load characteristic sub-indicator ( , corresponding to load rate, power factor deviation, load fluctuation frequency, peak load duration and three-phase load imbalance respectively). For the The normal value range of each load characteristic sub-indicator, For the The rate of change of each load characteristic sub-index per unit time, The value range is , when the deviation values ​​and change rates of all load characteristic sub-indicators are small, Close to 0, it means the load status is normal. When the deviation value or change rate of any load characteristic sub-indicator increases, Increase, indicating that the load state is deteriorating. When multiple load characteristic sub-indicators deviate from normal values ​​at the same time and the change rate is large, Rapid increase indicates that the load condition has seriously deteriorated; The fault risk diagnosis module is used to establish a fault risk diagnosis model based on the feature data of the diagnostic feature sequence and the deep learning algorithm, obtain the fault risk score, and diagnose the fault risk of the distribution cabinet. It can timely discover the potential fault risk of the distribution cabinet, provide early warning information to the operation and maintenance personnel, and reduce the probability of faults; The fault location module is used to locate abnormal features based on the fault risk diagnosis results, assist operation and maintenance personnel in troubleshooting problems, and optimize equipment maintenance strategies; The monitoring and early warning module is used to combine the fault risk diagnosis and fault location results to determine the specific risk level of the fault, generate and issue corresponding early warning information, and notify the operation and maintenance personnel to handle it, ensuring that the operation and maintenance personnel can understand the operating status of the distribution cabinet in a timely manner and take corresponding measures to deal with it to avoid the expansion of the fault.

[0021] Embodiment 2, as Figure 1 , Figure 2 As shown, based on Example 1, the present invention provides a technical solution: preferably, the fault risk diagnosis module specifically includes: A large amount of historical distribution equipment data of high and low voltage distribution cabinets is collected in advance, and features related to fault risk diagnosis are extracted from them. Then, the fault risk score is analyzed by combining the monitoring requirements of high and low voltage distribution cabinets with the abnormal features therein. The abnormal features and fault risk scores are integrated to obtain the risk data set, which is divided into training set, validation set and test set at a ratio of 7:1.5:1.5. According to the fault risk diagnosis requirements of high and low voltage distribution cabinets, a deep learning algorithm based on the convolutional neural network model is selected as the basic architecture, including input layer, convolution layer, pooling layer and output layer, to establish a fault risk diagnosis model, and the training set is used to train the convolutional neural network. The network model is trained, the prediction value is calculated through forward propagation, and the model parameters are adjusted through back propagation to make the prediction result of the model as close to the real label as possible. During the training process, the performance of the model is monitored by the validation set, and the hyperparameters of the model, including learning rate, batch size, etc., are adjusted according to the validation results. The model is continuously optimized to improve the accuracy and reliability of diagnosis. Then, the test set is input into the trained model to evaluate the performance of the model and obtain the fault risk diagnosis model. The real-time diagnostic feature sequence related data is input into the trained fault risk diagnosis model to perform fault risk diagnosis of high and low voltage distribution cabinets, and then the fault risk score is output; In addition, the failure risk score is calculated as follows: Extract the equipment risk trend value, environmental risk trend value and load risk trend value, and set the maximum allowable value for each risk trend value. Divide each risk trend value by its corresponding maximum allowable value, and normalize each risk trend value, that is, convert it to a unified scale. According to the different degrees of influence of equipment, environment and load on fault risk, assign a weight coefficient to each normalized risk trend value. The weight coefficient reflects the relative importance of each factor in fault risk assessment, and the sum of all weight coefficients should be 1. Multiply the normalized risk trend value with the corresponding weight coefficient, and add the products to obtain the final fault risk score. When the fault risk score is close to 0, it means that the fault risk is low. As the fault risk score increases, it means that the fault risk is gradually increasing. The expression of failure risk score is: ; In the formula, It is the fault risk score, which indicates the comprehensive fault risk level of high and low voltage distribution cabinets. is the equipment risk trend value, is the environmental risk trend value, is the load risk trend value, is the maximum allowable value of the equipment risk tendency value, is the maximum allowable value of the environmental risk trend value, is the maximum allowable value of the load risk trend value, is the weight coefficient of equipment risk, is the weight coefficient of environmental risk, is the weight coefficient of load risk, , The value range is , when all risk trend values ​​are small, Close to 0, it means the failure risk is low. When any risk trend value increases, Increases, indicating an increased risk of failure; The fault location module specifically includes: Receive the fault risk score output by the fault risk diagnosis model, identify feature categories with higher risk trend values, analyze the risk trend values ​​of each category, determine the main risk sources, and then identify specific abnormal feature sub-indicators. Map the identified abnormal feature sub-indicators to specific equipment components of high and low voltage distribution cabinets. Through the structure and function analysis of the equipment, determine the affected equipment components, and then combine the operation records and maintenance history of the high and low voltage distribution cabinets to further narrow the scope of the fault and improve the accuracy of positioning. Generate a fault location report based on the analysis results, listing in detail the abnormal feature sub-indicators, related equipment components, fault risk scores and maintenance suggestions, to assist operation and maintenance personnel to quickly troubleshoot problems and optimize maintenance strategies; The monitoring and early warning module specifically includes: The fault risk score output by the fault risk diagnosis model and the fault location report generated by the fault location module are received in real time. According to the preset risk level classification standard, the fault risks of high and low voltage distribution cabinets are divided into three levels, namely low risk level, medium risk level and high risk level. Then, combined with the historical fault case library, corresponding risk thresholds are assigned to each risk level to adapt to different operating conditions. According to the output fault risk score, the risk level is judged, and then the corresponding early warning information is generated. Among them, the early warning information alarm includes the fault risk score, risk level, affected equipment components, abnormal characteristic sub-indicators and maintenance suggestions, ensuring that the early warning information content is clear and comprehensive, and can provide clear guidance for operation and maintenance personnel. Set early warning information according to the risk level Priority of information is set to ensure that high-risk faults are handled first. Warning information is pushed to the operation and maintenance personnel's terminal in real time through multi-channel communication mechanisms (SMS, email, SCADA system pop-up windows). Differentiated notifications are made in combination with the operation and maintenance personnel's role permissions (on-duty engineers, regional supervisors), and the recipient's status (online / offline) is verified before release to ensure that the information is delivered. At the same time, push logs are recorded to support subsequent audits and traceability, and a warning response tracking mechanism is established to monitor the operation and maintenance personnel's processing progress of warning information in real time (read, confirmed, and being processed). The work order system automatically associates fault location reports, pushes maintenance suggestions and operation guides, and sets automatic escalation rules for timeout failures, that is, if the failure exceeds 1 hour, it will be escalated to the superior supervisor to ensure timely handling of faults. Multiple risk levels correspond to multiple risk thresholds one by one, and the corresponding relationship is as follows: Low risk level: ; A low score means that the equipment is in good operating condition, the risk of failure is low, the equipment, environment and load risk trend values ​​are all low, the equipment is in good operating condition, and regular maintenance is required to keep the equipment running normally. It has a low priority and can be notified via email or system pop-up window; Medium risk level: ; A medium score indicates that the equipment has a certain risk of failure, one or more risk trend values ​​are high, and it is necessary to strengthen monitoring and arrange preventive maintenance. It has a medium priority and can be notified via SMS and system pop-up windows; High risk level: A high score indicates that the equipment has a high risk of failure, and multiple risk trend values ​​are high. Immediate measures must be taken to arrange emergency repairs with high priority. Notifications will be sent via SMS, email, and system pop-up windows, and the incident will be escalated to the superior supervisor. in, Score the risk of failure, is the upper threshold of the low risk level and the lower threshold of the medium risk level, It is the upper threshold of medium risk level and the lower threshold of high risk level.

[0022] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A high and low voltage distribution cabinet operation monitoring system based on data analysis, including an operation monitoring platform, characterized in that: The operation monitoring platform is communicatively connected with a data acquisition module, a fault risk analysis module, a fault risk diagnosis module, a fault location module and a monitoring and early warning module, wherein electrical signals are connected between the modules; The data acquisition module is used to collect and pre-process the distribution equipment data of the high and low voltage distribution cabinets, wherein the distribution equipment data includes equipment status data, operating environment data and load data; The fault risk analysis module is used to extract features related to fault risk diagnosis by combining the preprocessed distribution equipment data, obtain a diagnostic feature sequence, and analyze the risk trend of distribution equipment data in each dimension; The fault risk diagnosis module is used to establish a fault risk diagnosis model based on the feature data of the diagnostic feature sequence and the deep learning algorithm, obtain a fault risk score, and diagnose the fault risk of the distribution cabinet; The fault location module is used to locate abnormal features based on the fault risk diagnosis results, assist operation and maintenance personnel in troubleshooting problems, and optimize equipment maintenance strategies; The monitoring and early warning module is used to combine the fault risk diagnosis and fault location results, determine the specific risk level of the fault, and generate and issue corresponding early warning information.

2. The high and low voltage distribution cabinet operation monitoring system based on data analysis according to claim 1 is characterized in that: The data acquisition module specifically includes: The original distribution equipment data including equipment status data, operating environment data and load data are collected through various sensors of high and low voltage distribution cabinets. The sensors collect the original distribution equipment data at preset fixed time intervals and store them in the form of time series. For equipment status data, voltage, current and equipment operation record data are collected. For operating environment data, ambient temperature, ambient humidity and ambient vibration acceleration data are collected. For load data, load rate, power factor deviation, load fluctuation frequency, peak load duration and three-phase load imbalance data are collected. Perform data cleaning and standardization preprocessing operations on the collected raw distribution equipment data; Integrate the pre-processed distribution equipment data and store it in the data warehouse, using structured storage to organize the data into tabular form.

3. The high and low voltage distribution cabinet operation monitoring system based on data analysis according to claim 2 is characterized in that: The fault risk analysis module includes a feature extraction unit, an abnormal feature marking unit and a risk trend unit; The feature extraction unit is used to perform feature analysis on the preprocessed distribution equipment data, and extract feature sub-indicators related to fault risk diagnosis from the equipment status data, operating environment data and load data respectively; The abnormal feature marking unit is used to determine the normal value of each feature sub-indicator in combination with historical data, and distinguish and mark the abnormal features to obtain a diagnostic feature sequence; The risk trend unit is used to analyze the characteristic sub-indicators in the diagnostic characteristic sequence, calculate the equipment risk trend value, the environmental risk trend value and the load risk trend value respectively, and clarify the risk trend of the distribution equipment data in each dimension.

4. The high and low voltage distribution cabinet operation monitoring system based on data analysis according to claim 3 is characterized in that: The feature extraction unit specifically includes: Extract the pre-processed distribution equipment data, perform feature analysis on the equipment status data, operating environment data and load data, and extract features related to fault risk diagnosis, including equipment features, environment features and load features; Perform feature analysis on the equipment status data, extract equipment features, and determine the sub-indicators contained in the equipment features, which are voltage deviation, current peak, and equipment operating time; Perform feature analysis on the operating environment data, extract environmental features, and determine the sub-indicators contained in the environmental features, namely, environmental temperature, environmental humidity, and environmental vibration intensity; The load data is analyzed to extract the load characteristics, and the sub-indicators contained in the load characteristics are determined, which are load rate, power factor deviation, load fluctuation frequency, peak load duration and three-phase load imbalance.

5. The high and low voltage distribution cabinet operation monitoring system based on data analysis according to claim 3 is characterized in that: The abnormal feature marking unit specifically includes: Based on the output of the feature extraction unit, the historical data covering different time periods and different operating conditions are collected for the equipment features, environmental features and load features extracted from the distribution equipment data, and the historical data are integrated and classified according to the feature type; Analyze the integrated and classified historical data, and determine the normal value of each characteristic sub-indicator as the abnormality judgment standard in combination with the operation monitoring requirements of high and low voltage distribution cabinets; The characteristic sub-indicator data of the power distribution equipment collected in real time are compared with the determined normal value range, and the characteristic sub-indicators of the power distribution equipment that deviate from the normal value range are marked as abnormal characteristics. After the marking is completed, the marking results of all the characteristic sub-indicators of the power distribution equipment are arranged in chronological order to generate a diagnostic feature sequence.

6. The high and low voltage distribution cabinet operation monitoring system based on data analysis according to claim 4 is characterized in that: The risk trend unit specifically includes: Perform a preliminary time series analysis on the equipment status data, operating environment data, and load data in the diagnostic feature sequence, calculate the change rate of each feature sub-indicator with adjacent unit time intervals, and extract the change rate results by comparing the data at adjacent time points; For the equipment characteristic sub-indicators of the equipment status data, analyze the deviation of the voltage deviation, current peak value and equipment operation time per unit time compared with the normal value range, as well as the change rate of the analysis, and comprehensively analyze the equipment risk trend value of the high and low voltage distribution cabinets to analyze the change trend of the equipment status data; For the environmental characteristic sub-indicators of the operating environment data, analyze the deviation values ​​of the ambient temperature, ambient humidity, and ambient vibration intensity compared with the normal value range per unit time, as well as the change rate of the analysis, and comprehensively analyze to obtain the environmental risk trend value to evaluate the risk trend of the operating environment data; For the load characteristic sub-indicators of load data, analyze the deviation of load rate, power factor deviation, load fluctuation frequency, peak load duration and three-phase load imbalance compared with the normal value range, as well as the change rate of analysis, and obtain the load risk trend value through comprehensive analysis to clarify the load risk trend of high and low voltage distribution cabinets.

7. The high and low voltage distribution cabinet operation monitoring system based on data analysis according to claim 3 is characterized in that: The fault risk diagnosis module specifically includes: Collect historical distribution equipment data of high and low voltage distribution cabinets in advance, and extract features related to fault risk diagnosis from them. Then, combine the monitoring requirements of high and low voltage distribution cabinets with the abnormal features therein, analyze the fault risk score, integrate the abnormal features and fault risk score, obtain the risk data set, and divide it into training set, validation set and test set; According to the fault risk diagnosis requirements of high and low voltage distribution cabinets, a deep learning algorithm based on the convolutional neural network model is selected as the basic architecture to establish a fault risk diagnosis model. The convolutional neural network model is trained using the training set, and the performance of the model is monitored using the validation set. The hyperparameters of the model are adjusted according to the validation results, and then the test set is input into the trained model to evaluate the performance of the model and obtain the fault risk diagnosis model. The real-time diagnostic feature sequence related data is input into the trained fault risk diagnosis model to perform fault risk diagnosis of high and low voltage distribution cabinets, and then output the fault risk score.

8. The high and low voltage distribution cabinet operation monitoring system based on data analysis according to claim 7 is characterized in that: The calculation process of the fault risk score is: Extract equipment risk trend value, environmental risk trend value and load risk trend value, set the maximum allowable value for each risk trend value, divide each risk trend value by its corresponding maximum allowable value, and perform normalization on each risk trend value; According to the different impacts of equipment, environment and load on failure risk, a weight coefficient is assigned to each normalized risk trend value; The normalized risk trend value is multiplied by the corresponding weight coefficient, and the products are added to obtain the final fault risk score. When the fault risk score is close to 0, it indicates that the fault risk is low. As the fault risk score increases, it indicates that the fault risk is gradually increasing.

9. The high and low voltage distribution cabinet operation monitoring system based on data analysis according to claim 7 is characterized in that: The fault location module specifically includes: Receive the fault risk score output by the fault risk diagnosis model, identify the feature categories with higher risk trend values, and analyze the risk trend values ​​of each category to determine the main risk sources, and then identify specific abnormal feature sub-indicators; Map the identified abnormal characteristic sub-indicators to specific equipment components of the high and low voltage distribution cabinets. Through the structural and functional analysis of the equipment, determine the affected equipment components, and then combine the operation records and maintenance history of the high and low voltage distribution cabinets to further narrow the scope of the fault; A fault location report is generated based on the analysis results, which lists in detail the abnormal characteristic sub-indicators, related equipment components, fault risk scores, and maintenance recommendations, to assist operation and maintenance personnel in quickly troubleshooting problems and optimizing maintenance strategies.

10. The high and low voltage distribution cabinet operation monitoring system based on data analysis according to claim 9 is characterized in that: The monitoring and early warning module specifically includes: Receive the fault risk score output by the fault risk diagnosis model and the fault location report generated by the fault location module in real time, and divide the fault risks of high and low voltage distribution cabinets into three levels according to the preset risk level classification standard, namely low risk level, medium risk level and high risk level. Then, combined with the historical fault case library, assign corresponding risk thresholds to each risk level to adapt to different operating conditions; According to the output fault risk score, the risk level is determined, and then the corresponding warning information is generated. The warning information alarm includes the fault risk score, risk level, affected equipment components, abnormal characteristic sub-indicators and maintenance suggestions; Through the multi-channel communication mechanism, the early warning information is pushed to the operation and maintenance personnel's terminal in real time. Differentiated notifications are made according to the operation and maintenance personnel's role permissions. The status of the recipient is verified before release, and the push log is recorded at the same time. Establish an early warning response tracking mechanism to monitor the progress of operation and maintenance personnel in handling early warning information in real time, automatically associate fault location reports through the work order system, push maintenance suggestions and operation guides, and set automatic escalation rules for no response after timeout. That is, if no processing is carried out for more than 1 hour, it will be escalated to the superior supervisor.

Images