New energy motor control system based on anomaly diagnosis

Abstract

The invention discloses a new energy motor control system based on abnormality diagnosis, and belongs to the field of new energy automobiles. The new energy motor control system based on anomaly diagnosis comprises a data acquisition unit, a data analysis unit, an anomaly early warning unit and a visualization unit. The problem that the abnormity cannot be detected in time at present is solved, the operation data is collected in real time and preprocessed, then the preprocessed operation data is analyzed through the machine learning technology, possible abnormal conditions are found, if the abnormity is found, early warning information is generated, and an early warning notice is sent to management personnel, so that the safety of the management personnel is improved. According to the method, the new energy motor can be conveniently and timely controlled by a manager, meanwhile, feedback of an early warning notification of the manager is monitored to ensure that the manager timely responds to the early warning notification, and early warning information and data are visually displayed, so that the manager can be helped to more intuitively understand the operation condition of the new energy motor, and the operation efficiency of the new energy motor is improved. Therefore, stable and efficient operation of the new energy motor is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of new energy vehicles, and in particular to a new energy motor control system based on abnormality diagnosis. Background Art

[0002] Traditional motor control systems usually use simple speed control or position control to maintain stable operation of the motor, but this control method has some problems in practical applications. For example, when a motor fails, the traditional control system cannot detect the abnormality in time and take corresponding measures, which leads to unstable operation and reduced safety of the motor. Therefore, it does not meet the existing needs. In this regard, we propose a new energy motor control system based on abnormal diagnosis. Summary of the invention

[0003] The purpose of the present invention is to provide a new energy motor control system based on abnormal diagnosis. By collecting operating data in real time and performing preprocessing, the influence of sensor errors on the data can be eliminated or reduced. The preprocessed operating data is then analyzed through machine learning technology to find out possible abnormal conditions. If an abnormality is found, early warning information is generated and an early warning notification is sent to management personnel so that the management personnel can control the new energy motor in time. At the same time, the management personnel are monitored to ensure that they respond to the early warning notification in time. The early warning information, the collected operating data and the analyzed abnormal data are visualized, which can help management personnel understand the operating status of the new energy motor more intuitively and solve the problems raised in the above-mentioned background technology.

[0004] To achieve the above object, the present invention provides the following technical solution: a new energy motor control system based on abnormality diagnosis, comprising: A data acquisition unit, for: Install sensors on new energy motors to collect and pre-process the operating data of new energy motors in real time, including speed, load and temperature data. Data analysis unit for: By mining a large amount of historical data, we can analyze the currently collected operating data and automatically detect abnormal conditions in new energy motors; Abnormal warning unit, used for: Generate early warning information for detected abnormal situations and send early warning notifications to management personnel at the same time, so that management personnel can adjust the new energy motor control strategy and optimize the operating status of the new energy motor based on the collected operating data and abnormal data; Visualization unit for: Displays the warning information generated by the abnormal warning unit, and visualizes the collected operation data and analyzed abnormal data. The visualization unit provides a display interface for managers, including the following functions: Data visualization function: Use line charts, bar charts and pie charts to visualize the collected operation data and analyzed abnormal data on the display interface; Early warning function: when early warning information appears, real-time prompts will be given on the display interface; Backup and recovery function: Back up the displayed data regularly and restore from the backup data when the data is damaged or lost.

[0005] Furthermore, the data acquisition unit includes: Collection strategy module, used to: Set the data collection cycle in advance, including the frequency and time of data collection; Data acquisition module for: Through the installed sensors and according to the set collection cycle, the data of the new energy motor during operation is collected in real time, and finally the operation data of the new energy motor is obtained; Data processing module for: After collecting the operating data of the new energy motor, the operating data is preprocessed, including format unification, denoising, and outlier and missing value processing.

[0006] Furthermore, the sensor comprises: Temperature sensor: used to collect temperature information during the operation of new energy motors and obtain temperature data; Speed ​​sensor: used to collect speed information during the operation of new energy motors and obtain speed data; Load sensor: used to collect load speed information during the operation of new energy motors and obtain load speed data.

[0007] Furthermore, the preprocessing includes: Format unification: used to unify the formats of raw data collected from different sensors into a standard format; De-noising: It is used to remove noise from running data by using linear filtering or Kalman filtering; Outlier and missing value processing: used to delete or replace outliers in the running data, and delete or use linear interpolation and polynomial interpolation to process missing values ​​in the running data; Among them, for outliers outside the normal range, the maximum or minimum value is used to replace them, and for outliers within the normal range, the average or median is used to replace them.

[0008] Furthermore, the data analysis unit comprises: Data collection module for: Collect historical data of new energy motors in the past time period and process the collected historical data, including cleaning, deduplication and normalization, including: Data cleaning: used to check and process errors, missing values ​​and outliers in historical data; Data deduplication: used to eliminate duplicate data in historical data; Data normalization: used to scale historical data so that it falls between 0 and 1; Feature extraction module for: Extract features of historical data such as speed, load, and temperature based on the characteristics of new energy motors; Model building modules for: Based on the collected historical data and extracted features, a machine learning algorithm is used to establish an abnormality diagnosis model, and the established model is trained and evaluated; Model application module for: The trained abnormal diagnosis model is used to analyze the currently collected operating data. When the predicted value of a data point differs from the normal range, it is determined that an abnormality exists in the new energy motor.

[0009] Furthermore, the model building module includes: Data partitioning module, used to: The collected historical data and extracted features are randomly divided into training sets and test sets, with a ratio of 8:2. Model training module, used to: The abnormal diagnosis model is trained using the training set. During the training process, the optimal hyperparameters are selected through cross-validation and grid search. Model evaluation module for: Use the test set to test and evaluate the anomaly diagnosis model, including accuracy, precision, recall, and F1 score. If the performance of the anomaly diagnosis model does not meet the requirements, return to the feature extraction module to re-extract features. Model optimization module for: According to the evaluation results of the model evaluation module, the abnormal diagnosis model is optimized, including modifying the algorithm, adjusting hyperparameters, and increasing training data.

[0010] Furthermore, the abnormal warning unit includes: Early warning notification module, used to: Generate warning information based on detected abnormal situations, and send warning notifications to managers via email or SMS; After receiving the early warning notification, the management personnel formulate corresponding solutions based on the collected operation data and abnormal data, such as replacing the faulty motor or modifying the operation parameters; The management personnel will adjust and control the new energy motor according to the formulated solution, and continuously monitor the operating status of the new energy motor after the adjustment is completed; Early warning monitoring module, used for: After sending the early warning notification, the response of the manager is monitored to determine whether the manager responds to the early warning notification in a timely manner.

[0011] Furthermore, the early warning monitoring module specifically performs the following process: Design monitoring strategy: set the monitoring start time in advance, and the start time is to start the early warning monitoring module within 10 seconds after the early warning notification is issued; Get feedback information: When managers receive warning notifications, they can send feedback on the warning notifications regularly; Check feedback time: monitor the feedback time of managers in real time, and judge whether managers respond to early warning notifications in a timely manner based on the length of feedback time; Abnormal warning processing: Based on the early warning monitoring results, warnings will be issued to managers who have given feedback for too long in a row and their superiors will be informed.

[0012] Furthermore, the new energy motor control system based on abnormal diagnosis, the visualization unit includes: The node determination module is used to: Acquire the data dimensions of the collected operation data, and create a multi-dimensional first visualization node according to the data dimensions of the operation data, and at the same time, construct a first warning sub-node and a second warning sub-node attached to the first visualization node of each data dimension; Obtain a data visualization function project, and create a multi-project second visualization node according to the data visualization function project; The visible area determination module is used to: Reading a target number of first visualization nodes and creating a first data visualization area of ​​the target number; Creating a second data visible area corresponding to the first data visible area according to the first warning sub-node, and creating a third data visible area corresponding to the first data visible area according to the second warning sub-node; Data filling module, used for: Acquire the association relationship between the first visualization node and the second visualization node, and determine the target visualization function item in each first data visual area according to the association relationship; Matching and mapping the running data in the first visualization node in the target visualization function project, and completing the first data filling in the first data visual area according to the matching and mapping result; When there is abnormal data, the target data dimension corresponding to the abnormal data is read, and the target second data visible area and the target third data visible area are matched according to the target data dimension. At the same time, the abnormal data is filled in the target second data visible area with the second data. At the same time, the warning information corresponding to the abnormal data is obtained, and the warning information is filled in the target third data visible area with the third data; Visual display module for Encapsulate the first data visible area after the first data is filled in, the second data visible area after the corresponding second data is filled in, and the third data visible area after the corresponding third data is filled in, to obtain a target visible area, wherein the target visible area corresponds to the data dimension one by one; According to the target visible area and the number of dimensions of the data dimension, an adaptive match is performed in the preset visual interface, and according to the matching results, the operation data, abnormal data and warning information are displayed in the preset visual interface respectively.

[0013] Furthermore, in the new energy motor control system based on abnormal diagnosis, in the visualization display module, adaptive matching is performed in a preset visual interface according to the number of dimensions of the target visual area and the data dimension, including: Obtaining first size information of a first data visible area, second size information of a second data visible area, and third size information of a third data visible area corresponding to each data dimension; Calculate the area allocation ratio of the target visible area of ​​each data dimension according to the first size information of the first data visible area, the second size information of the second data visible area, and the third size information of the third data visible area corresponding to each data dimension; ; in, Indicates The area allocation ratio of the target visual area of ​​each data dimension, Indicates The proportion value of the first data visible area in the data dimension; Indicated in The proportion value of the second data visible area in the data dimension; Indicated in The proportion value of the third data visible area in the data dimension; Indicates the ordinal value of the data dimension; Indicates The length of the first data visible area of ​​the data dimension; Indicates The width of the first data visible area of ​​the data dimension; Indicates The length of the second data visible area of ​​the data dimension; Indicates The width of the second data visible area of ​​the data dimension; Indicates The length of the third data visible area of ​​the data dimension; Indicates The width of the third data visible area of ​​the data dimension; Read the reference size information of the preset visual interface, and at the same time, obtain the number of dimensions of the data dimension, and determine the target area equally allocated to the target visual area corresponding to each data dimension according to the reference size information of the preset visual interface and the number of dimensions of the data dimension; ; in, Indicates the target area of ​​the target visual area corresponding to each data dimension, and the target area of ​​the target visual area corresponding to each data dimension is equal; Indicates the base length of the preset visual interface; Indicates the base width of the preset visual interface; The number of dimensions representing the data dimensions; Calculate the unit areas corresponding to the first data visible area, the second data visible area, and the third data visible area in the target visible area of ​​each data dimension according to the target area of ​​the target visible area and the area allocation ratio of the target visible area of ​​each data dimension; ; in, Indicates The unit area of ​​each data dimension; According to the unit areas corresponding to the first data visible area, the second data visible area and the third data visible area in the target visible area, the final area of ​​the first data visible area in the target visible area of ​​each data dimension is calculated respectively. , the final area of ​​the second data visible area And the final area of ​​the third data visible area ; ; ; ; The final area of ​​the first data visible area in the target visible area of ​​each data dimension , the final area of ​​the second data visible area And the final area of ​​the third data visible area Complete adaptive matching in the preset visual interface.

[0014] Compared with the prior art, the present invention has the following beneficial effects: 1. The data acquisition unit of the present invention collects the operating data of the new energy motor in real time by installing various sensors on the new energy motor. The data analysis unit uses a machine learning algorithm to establish an abnormal diagnosis model based on the mining of historical data to perform abnormality detection on the collected operating data. Once an abnormality is found, the abnormal warning unit will immediately generate a warning message and pass the warning notification to the management personnel through text messages or emails. At the same time, the visualization unit displays the warning information, the collected operating data, and the analyzed abnormal data in an intuitive manner, which is convenient for the management personnel to understand and control, thereby ensuring its stable and efficient operation.

[0015] 2. The present invention monitors the feedback time of managers in real time through the early warning monitoring module, and can judge whether the managers respond to the early warning notification in time according to the length of the feedback time. If the feedback time is too long, it means that the managers have not taken timely action. At this time, the early warning monitoring module will issue a warning and inform the superiors so that the superiors can take timely measures to ensure the normal operation of the new energy motor. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a module schematic diagram of the new energy motor control system of the present invention. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only 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.

[0018] In order to solve the technical problem that the existing motor control system usually adopts simple speed control or position control to maintain the stable operation of the motor, when the motor fails, the existing control system cannot detect the abnormal situation in time and take corresponding measures, which leads to the unstable operation of the motor and the reduction of safety. Please refer to Figure 1 , this embodiment provides the following technical solutions: New energy motor control system based on abnormal diagnosis, including: A data acquisition unit, for: Install sensors on new energy motors to collect and pre-process the operating data of new energy motors in real time, including speed, load and temperature data. Data analysis unit for: By mining a large amount of historical data, we can analyze the currently collected operating data and automatically detect abnormal conditions in new energy motors; Abnormal warning unit, used for: Generate early warning information for detected abnormal situations and send early warning notifications to management personnel at the same time, so that management personnel can adjust the new energy motor control strategy and optimize the operating status of the new energy motor based on the collected operating data and abnormal data; Visualization unit for: Display the warning information generated by the abnormal warning unit, and visualize the collected operation data and analyzed abnormal data.

[0019] The technical effect of the above content is: the data acquisition unit can collect the operating data of the new energy motor in real time during operation through various sensors installed on the new energy motor. The data analysis unit uses a machine learning algorithm to establish an abnormal diagnosis model based on the mining of historical data to detect abnormalities in the collected operating data. Once an abnormality is found, the abnormal warning unit will immediately generate a warning message and send the warning notification to the management personnel through text messages or emails. At the same time, the visualization unit will display the warning information, the collected operating data, and the analyzed abnormal data in an intuitive manner, which is convenient for management personnel to understand and control. Based on the above operations, it can help management personnel to detect abnormal situations in time, so as to adjust the control of the new energy motor in time to solve the abnormal problems, thereby ensuring its stable and efficient operation.

[0020] The data acquisition unit comprises: Collection strategy module, used to: Set up data collection cycle strategies in advance, including data collection frequency and time points; Data acquisition module for: Through the installed sensors and according to the set collection cycle strategy, the data of the new energy motor during operation is collected in real time, and finally the operation data of the new energy motor is obtained; Among them, the temperature sensor is used to collect temperature information during the operation of the new energy motor and obtain temperature data; Speed ​​sensor: used to collect speed information during the operation of new energy motors and obtain speed data; Load sensor: used to collect load speed information during the operation of new energy motors and obtain load speed data; Data processing module for: After collecting the operating data of the new energy motor, the operating data is preprocessed, including format unification, denoising, and outlier and missing value processing.

[0021] The technical effect of the above content is: the data acquisition module is responsible for collecting real-time operating data from the new energy motor, and before data collection, it is necessary to set the data collection cycle through the collection strategy module, including the data collection frequency (for example, once per second or once per hour) and time points (for example, 8 am and 5 pm every day). The data acquisition module is responsible for collecting the operating data of the new energy motor in real time according to the set cycle through the sensors installed on the new energy motor. The sensors can be used to obtain temperature information, speed information, load speed information, etc., so as to obtain more comprehensive data, and the data processing module is responsible for pre-processing the collected operating data, including unifying the data format, removing noise, processing outliers and missing values, etc., so as to make subsequent abnormal diagnosis and analysis more accurate and reliable. Based on the above operations, the operating status of the new energy motor can be effectively monitored in real time, so as to facilitate subsequent data analysis and timely detection of problems.

[0022] Pre-processing, including: Format unification: used to unify the formats of raw data collected from different sensors into a standard format; De-noising: It is used to remove noise from running data by using linear filtering or Kalman filtering; Outlier and missing value processing: used to delete or replace outliers in the running data, and delete or use linear interpolation and polynomial interpolation to process missing values ​​in the running data; Among them, for outliers outside the normal range, the maximum or minimum value is used to replace them, and for outliers within the normal range, the average or median is used to replace them.

[0023] The technical effect of the above content is: in order to better analyze and understand the operation data, the operation data needs to be converted into a unified format, which can reduce the problems caused by format differences caused by different sensors, and at the same time improve the comparability and readability of the operation data. Linear filtering or Kalman filtering is used to remove noise in the operation data to avoid noise from interfering with subsequent analysis. By processing outliers and missing values ​​in the operation data, it is possible to effectively avoid outliers and missing values ​​affecting subsequent analysis. By preprocessing the operation data, it is convenient for subsequent analysis and decision-making.

[0024] Data Analysis Unit, including: Data collection module for: Collect historical data of new energy motors in the past time period and process the collected historical data, including cleaning, deduplication and normalization; Among them, data cleaning: used to check and process errors, missing values ​​and outliers in historical data; Data deduplication: used to eliminate duplicate data in historical data; Data normalization: used to scale historical data so that it falls between 0 and 1; Feature extraction module for: Extract features of historical data such as speed, load, and temperature based on the characteristics of new energy motors; Model building modules for: Based on the collected historical data and extracted features, a machine learning algorithm is used to establish an abnormality diagnosis model, and the established model is trained and evaluated; Model application module for: The trained abnormal diagnosis model is used to analyze the currently collected operating data. When the predicted value of a data point differs from the normal range, it is determined that an abnormality exists in the new energy motor.

[0025] Model building modules, including: Data partitioning module, used to: The collected historical data and extracted features are randomly divided into training sets and test sets, with a ratio of 8:2. Model training module, used to: The abnormal diagnosis model is trained using the training set. During the training process, the optimal hyperparameters are selected through cross-validation and grid search. Model evaluation module for: Use the test set to test and evaluate the anomaly diagnosis model, including accuracy, precision, recall, and F1 score. If the performance of the anomaly diagnosis model does not meet the requirements, return to the feature extraction module to re-extract features. Model optimization module for: According to the evaluation results of the model evaluation module, the abnormal diagnosis model is optimized, including modifying the algorithm, adjusting hyperparameters, and increasing training data.

[0026] The technical effect of the above content is: the data collection module is responsible for collecting historical data of new energy motors, and cleaning, deduplication and normalization of the collected historical data, so as to effectively process the data and improve the effect of subsequent modeling. The feature extraction module is responsible for extracting useful feature information according to the characteristics of new energy motors. The model construction module uses historical data and feature information to construct an abnormal diagnosis model. By using training sets and test sets to train and evaluate the abnormal diagnosis model, the abnormal diagnosis model can be optimized to improve the performance of the abnormal diagnosis model. Finally, the model application module applies the trained abnormal diagnosis model to practice, so as to analyze the collected operating data. If the predicted value of the data point is significantly different from the normal range, it means that the new energy motor may have an abnormal situation, so that the abnormal problem of the new energy motor can be detected in time, so that the management personnel can make corresponding adjustments according to the data in time.

[0027] Abnormal warning unit, including: Early warning notification module, used to: Generate warning information based on detected abnormal situations, and send warning notifications to managers via email or SMS; After receiving the early warning notification, the management personnel formulate corresponding solutions based on the collected operation data and abnormal data, such as replacing the faulty motor or modifying the operation parameters; The management personnel will adjust and control the new energy motor according to the formulated solution, and continuously monitor the operating status of the new energy motor after the adjustment is completed; Early warning monitoring module, used for: After sending the early warning notification, monitor the response of the management personnel to determine whether the management personnel responded to the early warning notification in a timely manner; Among them, the early warning monitoring module specifically executes the following processes: Design monitoring strategy: set the monitoring start time in advance, and the start time is to start the early warning monitoring module within 10 seconds after the early warning notification is issued; Get feedback information: When managers receive warning notifications, they can send feedback on the warning notifications regularly; Check feedback time: monitor the feedback time of managers in real time, and judge whether managers respond to early warning notifications in a timely manner based on the length of feedback time; Abnormal warning processing: Based on the early warning monitoring results, warnings will be issued to managers who have given feedback for too long in a row and their superiors will be informed.

[0028] The technical effect of the above content is: the early warning notification module can generate early warning information based on the detected abnormal situation, and send early warning notifications to management personnel via email or text message, so as to remind management personnel to pay attention to the abnormal situation of the new energy motor and take timely measures. After receiving the early warning notification, the management personnel can formulate corresponding solutions (such as replacing the faulty motor or modifying the operating parameters) based on the collected operating data and abnormal data, so as to control and adjust the new energy motor in time after the abnormal situation is found, thereby ensuring the normal operation of the new energy motor. The early warning monitoring module will monitor the response of the management personnel to determine whether they have responded to the early warning notification in time, so as to ensure that the management personnel can respond to the early warning notification in time and take timely action to solve the problem, thereby improving the operating efficiency of the new energy motor.

[0029] The visualization unit provides a display interface for managers, including the following functions: Data visualization function: Use line charts, bar charts and pie charts to visualize the collected operation data and analyzed abnormal data on the display interface; Early warning function: When early warning information appears, real-time prompts are given on the display interface, such as pop-up windows or voice prompts; Backup and recovery function: Back up the displayed data regularly and restore from the backup data when the data is damaged or lost.

[0030] The technical effects of the above content are as follows: the data visualization function adopts a variety of chart forms, such as line charts, bar charts and pie charts, etc., which can clearly display the collected operation data and the abnormal data obtained by analysis on the display interface, so that managers can quickly identify abnormal situations. The early warning prompt function can immediately provide real-time prompts on the display interface when early warning information appears, such as pop-up windows or voice prompts, so that managers can understand the abnormal situation of the motor at the first time and take timely measures. The backup and recovery function can regularly back up the displayed data to prevent data damage or loss. When there is a problem with the data, it can be restored from the backup data to ensure the integrity and continuity of the data.

[0031] Working principle: By collecting operating data in real time and performing preprocessing, the impact of sensor errors on the data can be eliminated or reduced. The preprocessed operating data is then analyzed through machine learning technology to find out possible abnormalities. If an abnormality is found, an early warning message is generated and an early warning notification is sent to the management personnel so that the management personnel can control the new energy motor in time. At the same time, after sending the early warning notification, the feedback from the management personnel is monitored to ensure that the management personnel responds to the early warning notification in time, and the early warning information, the collected operating data, and the analyzed abnormal data are visualized to allow the management personnel to understand the operating status of the new energy motor more intuitively. Based on the above operations, the operating status of the new energy motor can be finely monitored and controlled, thereby ensuring the stable and efficient operation of the new energy motor.

[0032] In one embodiment, a new energy motor control system based on abnormal diagnosis, a visualization unit, includes: The node determination module is used to: Acquire the data dimensions of the collected operation data, and create a multi-dimensional first visualization node according to the data dimensions of the operation data, and at the same time, construct a first warning sub-node and a second warning sub-node attached to the first visualization node of each data dimension; Obtain a data visualization function project, and create a multi-project second visualization node according to the data visualization function project; The visible area determination module is used to: Reading a target number of first visualization nodes and creating a first data visualization area of ​​the target number; Creating a second data visible area corresponding to the first data visible area according to the first warning sub-node, and creating a third data visible area corresponding to the first data visible area according to the second warning sub-node; Data filling module, used for: Acquire the association relationship between the first visualization node and the second visualization node, and determine the target visualization function item in each first data visual area according to the association relationship; Matching and mapping the running data in the first visualization node in the target visualization function project, and completing the first data filling in the first data visual area according to the matching and mapping result; When there is abnormal data, the target data dimension corresponding to the abnormal data is read, and the target second data visible area and the target third data visible area are matched according to the target data dimension. At the same time, the abnormal data is filled in the target second data visible area with the second data. At the same time, the warning information corresponding to the abnormal data is obtained, and the warning information is filled in the target third data visible area with the third data; Visual display module for Encapsulate the first data visible area after the first data is filled in, the second data visible area after the corresponding second data is filled in, and the third data visible area after the corresponding third data is filled in, to obtain a target visible area, wherein the target visible area corresponds to the data dimension one by one; According to the target visible area and the number of dimensions of the data dimension, an adaptive match is performed in the preset visual interface, and the operation data, abnormal data and warning information are displayed in the preset visual interface according to the matching results.

[0033] In this embodiment, the data dimension refers to the data type corresponding to the operating data, including speed, load and temperature data.

[0034] In this embodiment, the first visualization node refers to a node created according to data dimensions and used to store operating data of different data dimensions, and each data dimension corresponds to a first visualization node.

[0035] In this embodiment, the first warning sub-node refers to a node that records abnormal data in the first visualization node.

[0036] In this embodiment, the second warning sub-node refers to a node that records the warning information in the first visualization node.

[0037] In this embodiment, the second visualization node refers to a node that records visualization function items when visually displaying the operating data of the corresponding data dimension. The visualization function items are methods of visually displaying the operating data of different data dimensions, including line charts, bar charts, and pie charts.

[0038] In this embodiment, the first data visual area refers to an area for visually displaying specific operation data content of each data dimension.

[0039] In this embodiment, the second data visual area refers to an area for visually displaying abnormal data in each data dimension.

[0040] In this embodiment, the third visual area refers to an area for visually displaying the warning information in each data dimension.

[0041] In this embodiment, the target visualization function item refers to the specific method required for visually displaying the operating data of each data dimension, which is one or more of a line chart, a bar chart, and a pie chart.

[0042] In this embodiment, matching and mapping the operation data in the first visualization node in the target visualization function item refers to filling or converting the operation data in a chart corresponding to the corresponding display method, that is, visually displaying the corresponding operation data through the chart.

[0043] In this embodiment, the first data filling refers to filling in the operating data in a corresponding display chart (line chart, bar chart, pie chart).

[0044] In this embodiment, the target data dimension refers to the data dimension corresponding to the abnormal data, that is, the running data of which data dimension the abnormal data belongs to.

[0045] In this embodiment, the target second data visible area refers to an area for visually displaying abnormal data of the target data dimension.

[0046] In this embodiment, the target third data visual area refers to an area for visually displaying the warning information corresponding to the abnormal data.

[0047] In this embodiment, filling in the second data refers to displaying the abnormal data in the target second data visualization area.

[0048] In this embodiment, filling in the third data refers to visually displaying the warning information in the target third data visual area.

[0049] In this embodiment, the target visible area refers to the final display area obtained by summarizing the operation data display area, the abnormal data display area, and the warning information display area of ​​the same data dimension.

[0050] In this embodiment, the preset visual interface is set in advance, including visual interfaces of different sizes.

[0051] The working principle and beneficial effects of the above technical solution are: by determining the data dimension of the operating data, matching the recording nodes and visualization display areas of the operating data, abnormal data and warning information under each data dimension according to the data dimension, and visually displaying different visualization contents in the corresponding areas according to the configuration results, so as to realize regular and orderly display of the content to be displayed, and finally, encapsulating different visualization display areas under the same data dimension, effectively determining the area required for the visualization of each data dimension, matching the corresponding visual interface from the preset visual interface, and finally realizing effective display of the data, thereby ensuring the comprehensiveness and reliability of the display of different types of data.

[0052] In one embodiment, in a new energy motor control system based on abnormal diagnosis, in a visualization display module, adaptive matching is performed in a preset visual interface according to the number of dimensions of a target visual area and a data dimension, including: Obtaining first size information of a first data visible area, second size information of a second data visible area, and third size information of a third data visible area corresponding to each data dimension; Calculate the area allocation ratio of the target visible area of ​​each data dimension according to the first size information of the first data visible area, the second size information of the second data visible area, and the third size information of the third data visible area corresponding to each data dimension; ; in, Indicates The area allocation ratio of the target visual area of ​​each data dimension, Indicates The proportion value of the first data visible area in the data dimension; Indicated in The proportion value of the second data visible area in the data dimension; Indicated in The proportion value of the third data visible area in the data dimension; Indicates the ordinal value of the data dimension; Indicates The length of the first data visible area of ​​the data dimension; Indicates The width of the first data visible area of ​​the data dimension; Indicates The length of the second data visible area of ​​the data dimension; Indicates The width of the second data visible area of ​​the data dimension; Indicates The length of the third data visible area of ​​the data dimension; Indicates The width of the third data visible area of ​​the data dimension; Read the reference size information of the preset visual interface, and at the same time, obtain the number of dimensions of the data dimension, and determine the target area equally allocated to the target visual area corresponding to each data dimension according to the reference size information of the preset visual interface and the number of dimensions of the data dimension; ; in, Indicates the target area of ​​the target visual area corresponding to each data dimension, and the target area of ​​the target visual area corresponding to each data dimension is equal; Indicates the base length of the preset visual interface; Indicates the base width of the preset visual interface; The number of dimensions representing the data dimensions; Calculate the unit areas corresponding to the first data visible area, the second data visible area, and the third data visible area in the target visible area of ​​each data dimension according to the target area of ​​the target visible area and the area allocation ratio of the target visible area of ​​each data dimension; ; in, Indicates The unit area of ​​each data dimension; According to the unit areas corresponding to the first data visible area, the second data visible area and the third data visible area in the target visible area, the final area of ​​the first data visible area in the target visible area of ​​each data dimension is calculated respectively. , the final area of ​​the second data visible area And the final area of ​​the third data visible area ; ; ; ; The final area of ​​the first data visible area in the target visible area of ​​each data dimension , the final area of ​​the second data visible area And the final area of ​​the third data visible area Complete adaptive matching in the preset visual interface.

[0053] The working principle and beneficial effect of the above technical solution are: by respectively determining the area allocation ratio within the target visible area corresponding to each data dimension and equally allocating the target area to the target visible area corresponding to each data dimension, and then calculating the unit area corresponding to the first data visible area, the second data visible area and the third data visible area in the target visible area of ​​each data dimension respectively through the target area, thereby effectively realizing the acquisition of the final area of ​​the first data visible area, the second data visible area and the third data visible area in the target visible area, providing data support for the configuration of the preset visual interface, thereby ensuring the accuracy and comprehensiveness of the adaptive configuration of the preset visual interface, and improving the user experience.

[0054] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0055] While the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that many changes, modifications, substitutions and variations can be made to the embodiments without departing from the principles and spirit of the invention.

Claims

1. A new energy motor control system based on abnormal diagnosis, characterized in that: include: A data acquisition unit, for: Install sensors on new energy motors to collect and pre-process the operating data of new energy motors in real time, including speed, load and temperature data. Data analysis unit for: By mining a large amount of historical data, we can analyze the currently collected operating data and automatically detect abnormal conditions in new energy motors; Abnormal warning unit, used for: Generate early warning information for detected abnormal situations and send early warning notifications to management personnel at the same time, so that management personnel can adjust the new energy motor control strategy and optimize the operating status of the new energy motor based on the collected operating data and abnormal data; Visualization unit for: Displays the warning information generated by the abnormal warning unit, and visualizes the collected operation data and analyzed abnormal data. The visualization unit provides a display interface for managers, including the following functions: Data visualization function: Use line charts, bar charts and pie charts to visualize the collected operation data and analyzed abnormal data on the display interface; Early warning function: when early warning information appears, real-time prompts will be given on the display interface; Backup and recovery function: Back up the displayed data regularly and restore from the backup data when the data is damaged or lost.

2. The new energy motor control system based on abnormal diagnosis according to claim 1 is characterized in that: The data acquisition unit comprises: Collection strategy module, used to: Set the data collection cycle in advance, including the frequency and time of data collection; Data acquisition module for: Through the installed sensors and according to the set collection cycle, the data of the new energy motor during operation is collected in real time, and finally the operation data of the new energy motor is obtained; Data processing module for: After collecting the operating data of the new energy motor, the operating data is preprocessed, including format unification, denoising, and outlier and missing value processing.

3. The new energy motor control system based on abnormal diagnosis according to claim 2 is characterized in that: The sensor comprises: Temperature sensor: used to collect temperature information during the operation of new energy motors and obtain temperature data; Speed ​​sensor: used to collect speed information during the operation of new energy motors and obtain speed data; Load sensor: used to collect load speed information during the operation of new energy motors and obtain load speed data.

4. The new energy motor control system based on abnormal diagnosis according to claim 2 is characterized in that: The preprocessing comprises: Format unification: used to unify the formats of raw data collected from different sensors into a standard format; De-noising: It is used to remove noise from running data by using linear filtering or Kalman filtering; Outlier and missing value processing: used to delete or replace outliers in the running data, and delete or use linear interpolation and polynomial interpolation to process missing values ​​in the running data; Among them, for outliers outside the normal range, the maximum or minimum value is used to replace them, and for outliers within the normal range, the average or median is used to replace them.

5. The new energy motor control system based on abnormal diagnosis according to claim 1 is characterized in that: The data analysis unit comprises: Data collection module for: Collect historical data of new energy motors in the past time period and process the collected historical data, including cleaning, deduplication and normalization, including: Data cleaning: used to check and process errors, missing values ​​and outliers in historical data; Data deduplication: used to eliminate duplicate data in historical data; Data normalization: used to scale historical data so that it falls between 0 and 1; Feature extraction module for: Extract the features of historical data based on the characteristics of new energy motors; Model building modules for: Based on the collected historical data and extracted features, a machine learning algorithm is used to establish an abnormality diagnosis model, and the established model is trained and evaluated; Model application module for: The trained abnormal diagnosis model is used to analyze the currently collected operating data. When the predicted value of a data point differs from the normal range, it is determined that an abnormality exists in the new energy motor.

6. The new energy motor control system based on abnormal diagnosis according to claim 5 is characterized in that: The model building module comprises: Data partitioning module, used to: The collected historical data and extracted features are randomly divided into training sets and test sets, with a ratio of 8:

2. Model training module, used to: The abnormal diagnosis model is trained using the training set. During the training process, the optimal hyperparameters are selected through cross-validation and grid search. Model evaluation module for: Use the test set to test and evaluate the anomaly diagnosis model, including accuracy, precision, recall, and F1 score. If the performance of the anomaly diagnosis model does not meet the requirements, return to the feature extraction module to re-extract features. Model optimization module for: According to the evaluation results of the model evaluation module, the abnormal diagnosis model is optimized, including modifying the algorithm, adjusting hyperparameters, and increasing training data.

7. The new energy motor control system based on abnormal diagnosis according to claim 1 is characterized in that: The abnormal warning unit comprises: Early warning notification module, used to: Generate warning information based on detected abnormal situations, and send warning notifications to managers via email or SMS; After receiving the early warning notification, the management personnel will formulate corresponding solutions based on the collected operation data and abnormal data; The management personnel will adjust and control the new energy motor according to the formulated solution, and continuously monitor the operating status of the new energy motor after the adjustment is completed; Early warning monitoring module, used for: After sending the early warning notification, the response of the manager is monitored to determine whether the manager responds to the early warning notification in a timely manner.

8. The new energy motor control system based on abnormal diagnosis according to claim 7 is characterized in that: The early warning monitoring module specifically performs the following process: Design monitoring strategy: set the monitoring start time in advance, and the start time is to start the early warning monitoring module within 10 seconds after the early warning notification is issued; Get feedback information: When managers receive warning notifications, they can send feedback on the warning notifications regularly; Check feedback time: monitor the feedback time of managers in real time, and judge whether managers respond to early warning notifications in a timely manner based on the length of feedback time; Abnormal warning processing: Based on the early warning monitoring results, warnings will be issued to managers who have given feedback for too long in a row and their superiors will be informed.

9. The new energy motor control system based on abnormal diagnosis according to claim 1 is characterized in that: Visualization unit, including: The node determination module is used to: Acquire the data dimensions of the collected operation data, and create a multi-dimensional first visualization node according to the data dimensions of the operation data, and at the same time, construct a first warning sub-node and a second warning sub-node attached to the first visualization node of each data dimension; Obtain a data visualization function project, and create a multi-project second visualization node according to the data visualization function project; The visible area determination module is used to: Reading a target number of first visualization nodes and creating a first data visualization area of ​​the target number; Creating a second data visible area corresponding to the first data visible area according to the first warning sub-node, and creating a third data visible area corresponding to the first data visible area according to the second warning sub-node; Data filling module, used for: Acquire the association relationship between the first visualization node and the second visualization node, and determine the target visualization function item in each first data visual area according to the association relationship; Matching and mapping the running data in the first visualization node in the target visualization function project, and completing the first data filling in the first data visual area according to the matching and mapping result; When there is abnormal data, the target data dimension corresponding to the abnormal data is read, and the target second data visible area and the target third data visible area are matched according to the target data dimension. At the same time, the abnormal data is filled in the target second data visible area with the second data. At the same time, the warning information corresponding to the abnormal data is obtained, and the warning information is filled in the target third data visible area with the third data; Visual display module for Encapsulate the first data visible area after the first data is filled in, the second data visible area after the corresponding second data is filled in, and the third data visible area after the corresponding third data is filled in, to obtain a target visible area, wherein the target visible area corresponds to the data dimension one by one; According to the target visible area and the number of dimensions of the data dimension, an adaptive match is performed in the preset visual interface, and the operation data, abnormal data and warning information are displayed in the preset visual interface according to the matching results.

10. The new energy motor control system based on abnormal diagnosis according to claim 9 is characterized in that: In the visualization display module, adaptive matching is performed in the preset visual interface according to the target visual area and the number of dimensions of the data dimension, including: Obtaining first size information of a first data visible area, second size information of a second data visible area, and third size information of a third data visible area corresponding to each data dimension; Calculate the area allocation ratio of the target visible area of ​​each data dimension according to the first size information of the first data visible area, the second size information of the second data visible area, and the third size information of the third data visible area corresponding to each data dimension; ； in, Indicates The area allocation ratio of the target visual area of ​​each data dimension, Indicates The proportion value of the first data visible area in the data dimension; Indicated in The proportion value of the second data visible area in the data dimension; Indicated in The proportion value of the third data visible area in the data dimension; Indicates the ordinal value of the data dimension; Indicates The length of the first data visible area of ​​the data dimension; Indicates The width of the first data visible area of ​​the data dimension; Indicates The length of the second data visible area of ​​the data dimension; Indicates The width of the second data visible area of ​​the data dimension; Indicates The length of the third data visible area of ​​the data dimension; Indicates The width of the third data visible area of ​​the data dimension; Read the reference size information of the preset visual interface, and at the same time, obtain the number of dimensions of the data dimension, and determine the target area equally allocated to the target visual area corresponding to each data dimension according to the reference size information of the preset visual interface and the number of dimensions of the data dimension; ； in, Indicates the target area of ​​the target visual area corresponding to each data dimension, and the target area of ​​the target visual area corresponding to each data dimension is equal; Indicates the base length of the preset visual interface; Indicates the base width of the preset visual interface; The number of dimensions representing the data dimensions; Calculate the unit areas corresponding to the first data visible area, the second data visible area, and the third data visible area in the target visible area of ​​each data dimension according to the target area of ​​the target visible area and the area allocation ratio of the target visible area of ​​each data dimension; ； in, Indicates The unit area of ​​each data dimension; According to the unit areas corresponding to the first data visible area, the second data visible area and the third data visible area in the target visible area, the final area of ​​the first data visible area in the target visible area of ​​each data dimension is calculated respectively. , the final area of ​​the second data visible area And the final area of ​​the third data visible area ; ； ； ； The final area of ​​the first data visible area in the target visible area of ​​each data dimension , the final area of ​​the second data visible area And the final area of ​​the third data visible area Complete adaptive matching in the preset visual interface.

Images