Multi-parameter monitoring and early warning method and device for brushless motor production line

Abstract

The invention discloses a multi-parameter monitoring and early warning method and device for a brushless motor production line, and relates to the field related to data early warning, and the method comprises the steps: traversing the brushless motor production line, carrying out the sensing deployment, determining a plurality of deployment sensors, carrying out the data collection of the brushless motor production line, obtaining a sensing parameter set, the method comprises the steps of preprocessing a sensing parameter set through a filtering algorithm, generating a sensing denoising parameter set, performing real-time monitoring based on the sensing denoising parameter set, generating a monitoring result, performing judgment according to the monitoring result, generating judgment data, performing grading processing according to the judgment data, and generating multi-stage early warning signals. And performing early warning feedback on the brushless motor production line through the multi-stage early warning signals. The technical problems of real-time monitoring and fault early warning in the brushless motor production line are solved. The technical effects of improving the stability and safety of the production line and optimizing the production efficiency are achieved.

Description

Technical Field

[0001] The present application relates to data early warning related fields, and in particular to a multi-parameter monitoring and early warning method and device for a brushless motor production line. Background Art

[0002] Brushless motors are widely used in modern industry, automobiles, home appliances and other fields. Their high efficiency, stability and long life make them the core drive components of many automated production lines. In the production process of brushless motors, the stability of the production line and the quality of the motors directly affect the performance and safety of the products. Since the brushless motor production line involves complex mechanical, electrical and control devices, various parameters such as temperature, vibration, current, voltage, etc. are constantly changing in different processes. Failure to monitor these key parameters in real time may lead to equipment failure, quality problems and even safety accidents.

[0003] Traditional monitoring methods for brushless motor production lines mainly rely on manual inspections or monitoring of a single parameter, which is not only inefficient but also unable to achieve comprehensive early warning of the production process. Summary of the invention

[0004] This application solves the technical problems of real-time monitoring and fault warning in brushless motor production lines by providing a multi-parameter monitoring and early warning method and device for brushless motor production lines, thereby achieving the technical effect of improving the stability and safety of the production line and optimizing production efficiency.

[0005] The present application provides a multi-parameter monitoring and early warning method for a brushless motor production line. The method is applied to a multi-parameter monitoring and early warning device for a brushless motor production line, including: traversing the brushless motor production line for sensor deployment, determining multiple deployed sensors, collecting data for the brushless motor production line through the multiple deployed sensors, and obtaining a sensor parameter set; pre-processing the sensor parameter set through a filtering algorithm to generate a sensor denoising parameter set; performing real-time monitoring based on the sensor denoising parameter set to generate monitoring results, performing judgments based on the monitoring results to generate judgment data; performing hierarchical processing based on the judgment data to generate a multi-level early warning signal, and providing early warning feedback to the brushless motor production line through the multi-level early warning signal.

[0006] In a possible implementation, the brushless motor production line is traversed to perform sensor deployment, a plurality of deployed sensors are determined, and the following processing is performed: the brushless motor production line is traversed to perform analysis according to the process flow, and a plurality of points to be monitored are determined; based on the plurality of points to be monitored, a production impact analysis is performed on the brushless motor production line, and a plurality of key nodes are determined; according to the plurality of key nodes, a correlation analysis is performed on a plurality of sensors to obtain a sensor network architecture; and sensor deployment is performed according to the sensor network architecture to determine the plurality of deployed sensors.

[0007] In a possible implementation, the sensor parameter set is preprocessed by a filtering algorithm to generate a sensor denoising parameter set, and the following processing is performed: the sensor signal of the sensor parameter set is subjected to wavelet decomposition to obtain sensor signal wavelet coefficients; threshold quantization is performed based on the sensor signal wavelet coefficients to determine the sensor signal wavelet selection threshold; the sensor signal wavelet coefficients are truncated according to the sensor signal wavelet selection threshold, and the noise signal less than the sensor signal wavelet selection threshold is set to zero to obtain valid signal information greater than the sensor signal wavelet selection threshold; the valid signal information is filtered and reconstructed to obtain the sensor denoising parameter set.

[0008] In a possible implementation, the sensing signal of the sensing parameter set is subjected to wavelet decomposition to obtain the wavelet coefficients of the sensing signal, and the following processing is performed: Among them, f(x) is the wavelet coefficient of the sensing signal, μ is the mean of x, σ is the standard deviation of x, μ is the distribution symmetry center of the sensing parameter set, σ is the distribution shape of the sensing parameter set, and e is the noise type in the process.

[0009] In a possible implementation, real-time monitoring is performed based on the sensor denoising parameter set to generate monitoring results, and a judgment is made based on the monitoring results to generate judgment data, and the following processing is performed: timing analysis is performed based on the sensor denoising parameter set to determine the data time series; multiple sliding windows are set based on the data time series, and the sensor denoising parameter set is continuously tracked according to the multiple sliding windows to generate monitoring results; the historical production record data log of the brushless motor production line is retrieved, and operation analysis is performed through the historical production record data log to set the expected production operation threshold; it is determined whether the monitoring result meets the expected production operation threshold; if the monitoring result meets the expected production operation threshold, the production operation is deemed to be normal, and a plurality of normal operation labels are generated; the plurality of normal operation labels are added to the judgment data.

[0010] In a possible implementation, it is determined whether the monitoring result meets the expected threshold of the production operation, and the following processing is performed: if the monitoring result does not meet the expected threshold of the production operation, it is regarded as a production operation abnormality, and a plurality of operation abnormality labels are generated; the abnormality is traced according to the plurality of operation abnormality labels in combination with the sensor denoising parameter set, and a plurality of abnormal sliding windows are determined; the abnormal timestamp is extracted according to the plurality of abnormal sliding windows; the monitoring result is located according to the abnormal timestamp, and a plurality of abnormal data location information is determined; and the plurality of abnormal data location information is added to the judgment data.

[0011] In a possible implementation, the judgment data is graded and processed to generate a multi-level warning signal, and the following processing is performed: an impact analysis is performed according to the process flow based on the multiple abnormal data location information to determine a plurality of influencing factors; a deviation calculation is performed on the monitoring results according to the multiple influencing factors to determine a plurality of data deviation values; the data is graded according to the multiple data deviation values ​​to determine a plurality of warning levels; the multiple warning levels are matched with the monitoring results to generate a multi-level warning signal.

[0012] The present application also provides a multi-parameter monitoring and early warning device for a brushless motor production line, including: a data acquisition module, used to traverse the brushless motor production line for sensor deployment, determine multiple deployed sensors, and collect data on the brushless motor production line through the multiple deployed sensors to obtain a sensor parameter set; a data preprocessing module, used to preprocess the sensor parameter set through a filtering algorithm to generate a sensor denoising parameter set; a real-time monitoring module, used to perform real-time monitoring based on the sensor denoising parameter set, generate monitoring results, make judgments based on the monitoring results, and generate judgment data; a hierarchical processing module, used to perform hierarchical processing based on the judgment data, generate multi-level early warning signals, and provide early warning feedback to the brushless motor production line through the multi-level early warning signals. One or more technical solutions provided in the present application have at least the following technical effects or advantages:

[0013] The multi-parameter monitoring and early warning method and device for a brushless motor production line provided by the present application relates to the field of data early warning technology, solves the technical problems of real-time monitoring and fault early warning in a brushless motor production line, and achieves the technical effect of improving the stability and safety of the production line and optimizing production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solution of the embodiment of the present application, the accompanying drawings of the embodiment of the present application will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the device according to the embodiment of the present application. It should be understood that the previous or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0015] Figure 1 A schematic diagram of a process flow of a multi-parameter monitoring and early warning method for a brushless motor production line provided in an embodiment of the present application;

[0016] Figure 2 A schematic diagram of the structure of a multi-parameter monitoring and early warning device for a brushless motor production line provided in an embodiment of the present application. DETAILED DESCRIPTION

[0017] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0018] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0019] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, device, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0020] The embodiment of the present application provides a multi-parameter monitoring and early warning method for a brushless motor production line, and the method is applied to a multi-parameter monitoring and early warning device for a brushless motor production line, such as Figure 1 As shown, the method includes:

[0021] In step A100, traverse the brushless motor production line to perform sensor deployment, determine multiple deployed sensors, collect data on the brushless motor production line through the multiple deployed sensors, and obtain a sensor parameter set; in a possible implementation, step A100 further includes step A110, traverse the brushless motor production line to perform analysis according to the process flow, and determine multiple points to be monitored; execute step A120, perform production impact analysis on the brushless motor production line based on the multiple points to be monitored, and determine multiple key nodes; execute step A130, perform correlation analysis on multiple sensors according to the multiple key nodes, and obtain a sensor network architecture; execute step A140, perform sensor deployment according to the sensor network architecture, and determine the multiple deployed sensors.

[0022] While traversing the brushless motor production line, it is necessary to conduct a detailed analysis of each link in the process flow, which may include the rotor section, the group section, and multiple monitored points that may have problems or need to be focused on. The multiple monitored points may include quality monitoring points for raw materials, quality control points for key processes, and equipment operation status monitoring points. Further, production impact analysis is performed based on the multiple monitored points to determine which nodes have a decisive influence on the overall efficiency of the production line and product quality. The multiple key points determined may include raw material quality inspection nodes, key process quality control nodes, equipment operation monitoring nodes, etc.

[0023] Further, sensor types are selected according to multiple key nodes. The sensor types may include temperature sensors, pressure sensors, displacement sensors, vibration sensors, etc., and their installation locations are determined at the same time to achieve real-time monitoring of multiple key nodes. According to the layout of the production line and the distribution of key nodes, a suitable network topology (such as star, mesh, etc.) is selected to build a sensor network architecture. Based on the sensor network architecture, multiple sensors are installed, debugged, calibrated, and other operations are performed to ensure that the sensors can accurately and stably monitor the status of key nodes and transmit data to the monitoring center.

[0024] Finally, real-time data collection is performed on the brushless motor production line through multiple deployed sensors. The data usually exists in the form of analog signals or digital signals, and is transmitted to the data acquisition device by wired or wireless means, so as to obtain the sensor parameter set, which provides strong guarantee for the stable operation of the production line and product quality.

[0025] Execute step A200, pre-process the sensing parameter set by filtering algorithm to generate a sensing denoising parameter set; in a possible implementation, step A200 further includes step A210, performing wavelet decomposition on the sensing signal of the sensing parameter set to obtain the sensing signal wavelet coefficient; in a possible implementation, step A210 further includes step A211, Among them, f(x) is the wavelet coefficient of the sensing signal, μ is the mean of x, σ is the standard deviation of x, μ is the distribution symmetry center of the sensing parameter set, σ is the distribution shape of the sensing parameter set, and e is the noise type in the process.

[0026] First, the sensor signal corresponding to the sensor parameter is extracted based on the sensor parameter set, and each sensor parameter corresponds to at least one sensor signal. The sensor signal of the sensor parameter set is decomposed by wavelet to obtain the sensor signal wavelet coefficient. The formula is:

[0027]

[0028] Among them, f(x) is the wavelet coefficient of the sensor signal, μ is the mean of x, σ is the standard deviation of x, μ is the distribution symmetry center of the sensor parameter set, σ is the distribution shape of the sensor parameter set, and e is the noise type in the process. The σ is the discrete degree of x, and the smaller σ is, the thinner the shape is.

[0029] Execute step A220, perform threshold quantization according to the sensor signal wavelet coefficients, and determine the sensor signal wavelet selection threshold; execute step A230, intercept the sensor signal wavelet coefficients according to the sensor signal wavelet selection threshold, set the noise signal less than the sensor signal wavelet selection threshold to zero, and obtain valid signal information greater than the sensor signal wavelet selection threshold; execute step A240, filter and reconstruct the valid signal information to obtain the sensor denoising parameter set.

[0030] Threshold quantization is performed based on the sensor signal wavelet coefficients. The threshold quantization is to determine one or more thresholds, and the sensor signal wavelet selection threshold is determined. The sensor signal wavelet selection threshold is used to distinguish useful information and noise in the signal. The sensor signal wavelet coefficients are further intercepted according to the sensor signal wavelet selection threshold, which means that the wavelet coefficients smaller than the threshold (usually corresponding to noise) are set to zero, while the wavelet coefficients larger than the threshold (corresponding to the valid signal) are retained.

[0031] Finally, the intercepted effective signal information is filtered and reconstructed. Filtering and reconstruction is to reassemble the processed wavelet coefficients into an approximate version of the original signal, but most of the noise has been removed at this time. Through inverse wavelet transform (i.e. wavelet reconstruction), a sensor denoising parameter set can be obtained. The sensor denoising parameter set is the denoised signal. By selecting a suitable wavelet basis and threshold strategy, the noise can be effectively removed while retaining the important features in the signal.

[0032] Execute step A300, perform real-time monitoring based on the sensor denoising parameter set, generate monitoring results, perform determination according to the monitoring results, and generate determination data;

[0033] In a possible implementation, step A300 further includes step A310, performing a timing analysis based on the sensor denoising parameter set to determine the data time series; executing step A320, setting multiple sliding windows based on the data time series, and continuously tracking the sensor denoising parameter set according to the multiple sliding windows to generate monitoring results; executing step A330, retrieving the historical production record data log of the brushless motor production line, performing operation analysis through the historical production record data log, and setting the expected threshold of production operation; firstly, performing a timing analysis based on the sensor denoising parameter set, and the timing analysis is used to record the law of the sensor denoising parameter set changing over time. The time series of the sensor denoising parameter set, that is, the order and trend of the sensor denoising parameter set changing over time, can be determined through the timing analysis, and further, multiple sliding windows are set based on the determined data time series. The sliding window refers to a window of a fixed size that can be moved on the time series, and the data in the window is processed and analyzed. By setting multiple sliding windows to continuously track the sensor denoising parameter set, the monitoring results are generated, and the historical production record data log of the brushless motor production line is retrieved for operation analysis, so as to obtain the normal operation status and possible problems of the production line. On this basis, the expected production operation threshold is set. The production operation expected threshold is used to determine whether the current production operation status is normal. The operation status of the brushless motor production line can be monitored in real time, potential problems can be discovered in time, and corresponding measures can be taken to ensure the stable operation of the production line.

[0034] Execute step A340 to determine whether the monitoring result meets the production operation expected threshold;

[0035] In one possible implementation, step A340 further includes step A341, if the monitoring result does not meet the expected threshold of the production operation, it is regarded as a production operation abnormality, and multiple operation abnormality labels are generated; step A342 is executed, abnormality tracing is performed according to the multiple operation abnormality labels in combination with the sensor denoising parameter set, and multiple abnormal sliding windows are determined; step A343 is executed, abnormal timestamps are extracted according to the multiple abnormal sliding windows; step A344 is executed, the monitoring result is located according to the abnormal timestamp, and multiple abnormal data location information is determined; step A345 is executed, and the multiple abnormal data location information is added to the judgment data.

[0036] The generated monitoring results are compared with the expected threshold of production operation set above. If the monitoring results fail to meet the expected threshold of production operation, it is determined that the production operation is abnormal, and multiple operation abnormality tags are generated. The multiple operation abnormality tags are used to mark abnormal conditions occurring on the production line, and further combined with the generated operation abnormality tags and the sensor denoising parameter set, an abnormality tracing analysis is performed, and the abnormality tracing analysis is used to find the specific cause or source of the abnormality. Through comparative analysis, multiple abnormal sliding windows can be determined, and the data in the multiple abnormal sliding windows is significantly different from the normal state.

[0037] Further, based on the determined abnormal sliding window, the corresponding timestamp is extracted. The timestamp is used to characterize the time point when the abnormality occurs, providing key information for subsequent positioning and troubleshooting. At the same time, the extracted abnormal timestamp is used to accurately locate the monitoring results. This allows accurate identification of the time periods in which the data is abnormal. Finally, the location information of these abnormal data is sorted out, including the time when the abnormality occurred, the specific value of the abnormal data, etc., so as to determine the location information of multiple abnormal data, and finally add the sorted abnormal data location information to the judgment data. The judgment information is crucial for subsequent analysis, processing and decision-making, and can help relevant personnel quickly understand the abnormal situations occurring on the production line and take corresponding countermeasures.

[0038] Execute step A350. If the monitoring result meets the expected threshold value of the production operation, the production operation is deemed to be normal, and a plurality of normal operation labels are generated. Execute step A360 to add the plurality of normal operation labels to the determination data.

[0039] If the monitoring result meets the expected threshold, the production operation is considered normal, indicating that the production operation is in a normal state and generating multiple normal operation tags. The multiple normal operation tags can be used to mark the normal operation state of the production line and serve as a basis for subsequent analysis and decision-making. The generated normal operation tags are added to the judgment data for further analysis and processing.

[0040] Execute step A400, perform hierarchical processing according to the determination data, generate a multi-level warning signal, and provide warning feedback to the brushless motor production line through the multi-level warning signal. In a possible implementation, step A400 further includes step A410, based on the multiple abnormal data location information, perform impact analysis according to the process flow to determine multiple impact factors; execute step A420, perform deviation calculation on the monitoring results according to the multiple impact factors to determine multiple data deviation values; execute step A430, perform grading according to the multiple data deviation values ​​to determine multiple warning levels; execute step A440, match the multiple warning levels with the monitoring results to generate a multi-level warning signal.

[0041] First, based on the location information of multiple abnormal data, the production process is traced back to conduct a detailed impact analysis, so as to identify the process links or parameters that cause the abnormal data, and determine multiple influencing factors, and perform deviation calculation on the monitoring results based on the determined multiple influencing factors. The deviation calculation refers to comparing the actual monitoring data with the expected data (or historical normal data) to determine the degree of data deviation and generate multiple data deviation values, which are used to reflect the difference between the actual production status and the expected status.

[0042] Furthermore, according to the magnitude of the multiple data deviation values, a classification process is performed to determine multiple warning levels. The multiple warning levels can be divided into several levels such as slight, medium, and severe, and each level corresponds to a different data deviation range. In this way, the severity of the abnormal situation is quantified, providing a basis for the generation of subsequent warning signals.

[0043] Finally, the determined multiple warning levels are matched with the monitoring results to generate a multi-level warning signal. The multi-level warning signal can be in the form of sound, light, text prompt, etc., which is used to issue a warning to the operators or managers on the production line to remind them to pay attention to the abnormal situation of the brushless motor production line. The level of the multiple warning signals should correspond to the level of the data deviation value to ensure the accuracy and effectiveness of the warning, and at the same time, the brushless motor production line is given early warning feedback through the multi-level warning signal. The early warning feedback can include shutdown inspection, adjustment of process parameters, replacement of faulty parts, etc. It can timely notify relevant personnel to take necessary measures to deal with abnormal situations and prevent the problem from further deteriorating.

[0044] The embodiment of the present application solves the technical problems of real-time monitoring and fault warning in the brushless motor production line, and achieves the technical effect of improving the stability and safety of the production line and optimizing production efficiency.

[0045] In the above, refer to Figure 1 The multi-parameter monitoring and early warning method for a brushless motor production line according to an embodiment of the present application is described in detail. Figure 2 A multi-parameter monitoring and early warning device for a brushless motor production line according to an embodiment of the present application is described.

[0046] The multi-parameter monitoring and early warning device for a brushless motor production line according to the embodiment of the present application is used to solve the technical problems of real-time monitoring and fault early warning in the brushless motor production line. The technical effect of improving the stability and safety of the production line and optimizing production efficiency is achieved. The multi-parameter monitoring and early warning device for a brushless motor production line includes: a data acquisition module 10, a data preprocessing module 20, a real-time monitoring module 30, and a hierarchical processing module 40.

[0047] The data acquisition module 10 is used to traverse the brushless motor production line for sensor deployment, determine a plurality of deployed sensors, collect data on the brushless motor production line through the plurality of deployed sensors, and obtain a sensor parameter set;

[0048] A data preprocessing module 20, configured to preprocess the sensing parameter set by a filtering algorithm to generate a sensing denoising parameter set;

[0049] A real-time monitoring module 30, configured to perform real-time monitoring based on the sensor denoising parameter set, generate monitoring results, make judgments based on the monitoring results, and generate judgment data;

[0050] The grading processing module 40 is used to perform grading processing according to the determination data, generate a multi-level warning signal, and provide warning feedback to the brushless motor production line through the multi-level warning signal.

[0051] The specific configuration of the data acquisition module 10 will be described in detail below. As described above, the brushless motor production line is traversed for sensor deployment, and multiple deployed sensors are determined. The data acquisition module 10 may further include: traversing the brushless motor production line and analyzing it according to the process flow to determine multiple points to be monitored; performing production impact analysis on the brushless motor production line based on the multiple points to be monitored to determine multiple key nodes; performing correlation analysis on multiple sensors according to the multiple key nodes to obtain a sensor network architecture; performing sensor deployment according to the sensor network architecture to determine the multiple deployed sensors.

[0052] The specific configuration of the item classification module 20 will be described in detail below. As described above, the sensor parameter set is preprocessed by a filtering algorithm to generate a sensor denoising parameter set, and the item classification module 20 may further include: performing wavelet decomposition on the sensor signal of the sensor parameter set to obtain sensor signal wavelet coefficients; performing threshold quantization according to the sensor signal wavelet coefficients to determine the sensor signal wavelet selection threshold; intercepting the sensor signal wavelet coefficients according to the sensor signal wavelet selection threshold, setting the noise signal less than the sensor signal wavelet selection threshold to zero, and obtaining valid signal information greater than the sensor signal wavelet selection threshold; filtering and reconstructing the valid signal information to obtain the sensor denoising parameter set.

[0053] The specific configuration of the data preprocessing module 20 will be described in detail below. As described above, the sensor signal of the sensor parameter set is subjected to wavelet decomposition to obtain the sensor signal wavelet coefficients. The data preprocessing module 20 may further include: Among them, f(x) is the wavelet coefficient of the sensing signal, μ is the mean of x, σ is the standard deviation of x, μ is the distribution symmetry center of the sensing parameter set, σ is the distribution shape of the sensing parameter set, and e is the noise type in the process.

[0054] The specific configuration of the real-time monitoring module 30 will be described in detail below. As described above, real-time monitoring is performed based on the sensor denoising parameter set to generate monitoring results, and judgment is performed based on the monitoring results to generate judgment data. The real-time monitoring module 30 may further include: performing time series analysis based on the sensor denoising parameter set to determine the data time series; setting multiple sliding windows based on the data time series, continuously tracking the sensor denoising parameter set according to the multiple sliding windows, and generating monitoring results; retrieving the historical production record data log of the brushless motor production line, performing operation analysis through the historical production record data log, and setting the expected production operation threshold; judging whether the monitoring result meets the expected production operation threshold; if the monitoring result meets the expected production operation threshold, the production operation is deemed to be normal, and multiple normal operation tags are generated; and the multiple normal operation tags are added to the judgment data.

[0055] The specific configuration of the real-time monitoring module 30 will be described in detail below. As described above, to determine whether the monitoring result meets the expected threshold of the production operation, the real-time monitoring module 30 may further include: if the monitoring result does not meet the expected threshold of the production operation, it is regarded as an abnormal production operation, and multiple abnormal operation labels are generated; abnormality tracing is performed according to the multiple abnormal operation labels combined with the sensor denoising parameter set, and multiple abnormal sliding windows are determined; abnormal timestamps are extracted according to the multiple abnormal sliding windows; the monitoring result is located according to the abnormal timestamp, and multiple abnormal data location information is determined; and the multiple abnormal data location information is added to the judgment data.

[0056] The specific configuration of the hierarchical processing module 40 will be described in detail below. As described above, hierarchical processing is performed according to the determination data to generate a multi-level warning signal. The hierarchical processing module 40 may further include: performing an impact analysis according to the process flow based on the multiple abnormal data location information to determine multiple impact factors; performing deviation calculation on the monitoring results according to the multiple impact factors to determine multiple data deviation values; performing grading according to the multiple data deviation values ​​to determine multiple warning levels; matching the multiple warning levels with the monitoring results to generate a multi-level warning signal.

[0057] The multi-parameter monitoring and early warning device for a brushless motor production line provided in the embodiment of the present application can execute the multi-parameter monitoring and early warning method for a brushless motor production line provided in any embodiment of the present application, and has the corresponding functional modules and beneficial effects of the execution method.

[0058] Although the present application makes various references to certain modules in the device according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present application.

[0059] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. A multi-parameter monitoring and early warning method for a brushless motor production line, characterized in that: The method comprises: Traversing the brushless motor production line to perform sensor deployment, determining a plurality of deployed sensors, collecting data on the brushless motor production line through the plurality of deployed sensors, and obtaining a sensor parameter set; Preprocessing the sensor parameter set by a filtering algorithm to generate a sensor denoising parameter set; Perform real-time monitoring based on the sensor denoising parameter set to generate monitoring results, make judgments based on the monitoring results, and generate judgment data; Gradual processing is performed according to the determination data to generate a multi-level warning signal, and warning feedback is provided to the brushless motor production line through the multi-level warning signal.

2. The multi-parameter monitoring and early warning method for a brushless motor production line according to claim 1, characterized in that: Traverse the brushless motor production line to perform sensor deployment and determine multiple deployed sensors. The method includes: Traverse the brushless motor production line and analyze it according to the process flow to determine multiple points to be monitored; Based on the multiple monitoring points, a production impact analysis is performed on the brushless motor production line to determine multiple key nodes; Performing correlation analysis on multiple sensors according to the multiple key nodes to obtain a sensor network architecture; Sensor deployment is performed according to the sensor network architecture to determine the multiple deployed sensors.

3. The multi-parameter monitoring and early warning method for a brushless motor production line according to claim 1, characterized in that: Preprocessing the sensing parameter set by a filtering algorithm to generate a sensing denoising parameter set includes: Performing wavelet decomposition on the sensor signal of the sensor parameter set to obtain the sensor signal wavelet coefficients; Perform threshold quantization according to the sensor signal wavelet coefficient to determine the sensor signal wavelet selection threshold; According to the sensor signal wavelet selection threshold, the sensor signal wavelet coefficients are intercepted, the noise signal less than the sensor signal wavelet selection threshold is set to zero, and the effective signal information greater than the sensor signal wavelet selection threshold is obtained; The effective signal information is filtered and reconstructed to obtain the sensor denoising parameter set.

4. The multi-parameter monitoring and early warning method for a brushless motor production line according to claim 1, characterized in that: Performing wavelet decomposition on the sensor signal of the sensor parameter set to obtain the sensor signal wavelet coefficient, the method comprising: Among them, f(x) is the wavelet coefficient of the sensing signal, μ is the mean of x, σ is the standard deviation of x, μ is the distribution symmetry center of the sensing parameter set, σ is the distribution shape of the sensing parameter set, and e is the noise type in the process.

5. The multi-parameter monitoring and early warning method for a brushless motor production line according to claim 2, characterized in that: Based on the sensor denoising parameter set, real-time monitoring is performed to generate monitoring results, and judgment is performed according to the monitoring results to generate judgment data. The method includes: Performing time series analysis according to the sensor denoising parameter set to determine a data time series; Setting a plurality of sliding windows based on the data time series, continuously tracking the sensor denoising parameter set according to the plurality of sliding windows, and generating a monitoring result; Retrieving historical production record data logs of the brushless motor production line, performing operation analysis based on the historical production record data logs, and setting production operation expected thresholds; Determining whether the monitoring result meets the expected threshold of production operation; If the monitoring result meets the expected threshold of production operation, the production operation is deemed to be normal, and a plurality of normal operation tags are generated; The plurality of normal operating tags are added to the determination data.

6. The multi-parameter monitoring and early warning method for a brushless motor production line according to claim 5, characterized in that: Determining whether the monitoring result meets the expected threshold of production operation, the method includes: If the monitoring result does not meet the expected threshold of the production operation, it is regarded as a production operation abnormality, and a plurality of operation abnormality tags are generated; Perform anomaly tracing according to the multiple operation anomaly labels in combination with the sensor denoising parameter set to determine multiple anomaly sliding windows; Extracting abnormal timestamps according to the multiple abnormal sliding windows; Locating the monitoring result according to the abnormal timestamp to determine multiple abnormal data location information; The plurality of abnormal data location information are added to the determination data.

7. The multi-parameter monitoring and early warning method for a brushless motor production line according to claim 6, characterized in that: Performing hierarchical processing according to the determination data to generate a multi-level warning signal, the method includes: Performing an impact analysis according to the process flow based on the plurality of abnormal data location information to determine a plurality of impact factors; Performing deviation calculation on the monitoring result according to the multiple influencing factors to determine multiple data deviation values; Classifying the multiple data deviation values ​​to determine multiple warning levels; The multiple warning levels are matched with the monitoring results to generate a multi-level warning signal.

8. A multi-parameter monitoring and early warning device for a brushless motor production line, characterized in that: The device is used to implement the multi-parameter monitoring and early warning method for a brushless motor production line according to any one of claims 1 to 7, and the device comprises: A data acquisition module, used to traverse the brushless motor production line for sensor deployment, determine a plurality of deployed sensors, collect data on the brushless motor production line through the plurality of deployed sensors, and obtain a sensor parameter set; A data preprocessing module, used to preprocess the sensor parameter set through a filtering algorithm to generate a sensor denoising parameter set; A real-time monitoring module, used to perform real-time monitoring based on the sensor denoising parameter set, generate monitoring results, make judgments based on the monitoring results, and generate judgment data; The hierarchical processing module is used to perform hierarchical processing according to the determination data, generate multi-level warning signals, and provide early warning feedback to the brushless motor production line through the multi-level warning signals.

Images