Motor current loop state monitoring and evaluating method based on dynamic database

Abstract

The invention discloses a motor current loop state monitoring and evaluation method based on a dynamic database, and relates to the technical field of state monitoring and evaluation, and the method comprises the steps: building historical motor current loop state data features based on the dynamic database through employing to-be-processed motor current loop state data; constructing a motor current loop state monitoring and evaluation model based on a convolutional neural network according to the historical motor current loop state data features; according to the to-be-processed motor current loop state data, using the motor current loop state monitoring and evaluation model to obtain a motor current loop initial state monitoring and evaluation result; performing time sequence analysis by using the to-be-processed motor current loop state data to obtain the trend of the motor current loop state data; and obtaining a motor current loop state monitoring and evaluation result according to the motor current loop initial state monitoring and evaluation result and the motor current loop state data trend. According to the invention, monitoring and evaluation of the motor current loop state are realized, and stable, efficient and accurate output of the motor current loop state monitoring and evaluation result is ensured.

Description

Technical Field

[0001] The present invention belongs to the technical field of condition monitoring and evaluation, and in particular relates to a motor current loop condition monitoring and evaluation method based on a dynamic database. Background Art

[0002] As one of the most important power devices in modern industrial production, motors are widely used in various fields such as machinery manufacturing, transportation, and electric power. The normal operation of motors is crucial to the continuity and stability of industrial production. Therefore, monitoring and evaluating the status of the motor's current loop is of great practical significance. Traditional motor current monitoring methods mainly rely on regular manual inspections and simple instrumentation for measurement. This method has problems such as untimely monitoring, inaccurate data, and an inability to grasp the motor's operating status in real time. Therefore, with the continuous improvement of industrial automation, the demand for real-time and accurate monitoring of the motor's current loop status is becoming increasingly urgent, prompting the development of motor current loop status monitoring and evaluation methods based on dynamic databases.

[0003] However, the existing motor current loop condition monitoring and evaluation method based on dynamic database still has the following defects and shortcomings: (1) Data acquisition: Although sensor technology is constantly improving, there are still certain accuracy errors. The data acquisition frequency may not meet the monitoring requirements of the rapidly changing state of the motor current loop. At the same time, data loss and imperfect exception handling may occur during the actual acquisition process. (2) Database management method: As the motor's operating time increases, the amount of collected data will continue to increase. The existing database may have problems such as insufficient storage capacity and slow query speed, which will affect the efficiency of monitoring and evaluation. In addition, the operating status of the motor changes dynamically. The existing method may have delays in data update and synchronization, resulting in the monitoring and evaluation results not reflecting the real-time status of the motor; (3) State monitoring and evaluation: Existing methods often only focus on a few indicators such as the current size and fluctuation, and the evaluation indicators are relatively simple. Although existing methods can monitor the state of the motor current loop, their ability in fault diagnosis is limited.

[0004] Therefore, there is an urgent need for a motor current loop state monitoring and evaluation method based on a dynamic database to address the shortcomings of the existing technology. Summary of the Invention

[0005] The purpose of the present invention is to propose a motor current loop state monitoring and evaluation method based on a dynamic database to realize the monitoring and evaluation of the motor current loop state and ensure that the motor current loop state monitoring and evaluation results are output stably, efficiently and accurately.

[0006] To achieve the above object, the present invention provides a motor current loop state monitoring and evaluation method based on a dynamic database, comprising the following steps: S1. Using the motor current loop state data to be processed, establish historical motor current loop state data characteristics based on a dynamic database; S2. Constructing a motor current loop state monitoring and evaluation model based on a convolutional neural network according to the historical motor current loop state data characteristics; S3, obtaining a motor current loop initial state monitoring and evaluation result using the motor current loop state monitoring and evaluation model according to the motor current loop state data to be processed; S4, using the motor current loop state data to be processed to perform time series analysis to obtain the motor current loop state data trend; S5. Obtain a motor current loop state monitoring and evaluation result according to the motor current loop initial state monitoring and evaluation result and the motor current loop state data trend.

[0007] Optionally, using the motor current loop state data to be processed to establish historical motor current loop state data features based on a dynamic database includes: S1-1, obtaining the motor current loop state data to be processed as the motor current loop state data feature to be processed; S1-2, establishing a historical motor current loop state database based on a dynamic database according to the motor current loop state data to be processed; S1-3, using the historical motor current loop state database to obtain corresponding historical motor current loop state data as a first initial feature of the historical motor current loop state data; S1-4, obtaining a second initial feature and a third initial feature of the historical motor current loop state data using the historical motor current loop state database according to the first initial feature of the historical motor current loop state data; S1-5, determining whether the first initial feature of the historical motor current loop state data completely corresponds to the feature of the motor current loop state data to be processed; if so, executing S1-6; otherwise, updating the historical motor current loop state database according to the first initial feature of the historical motor current loop state data, and returning to S1-3; S1-6, determining whether the second initial feature of the historical motor current loop state data completely corresponds to the feature of the motor current loop state data to be processed; if so, executing S1-7; otherwise, updating the historical motor current loop state database according to the second initial feature of the historical motor current loop state data, and returning to S1-3; S1-7, determining whether the third initial feature of the historical motor current loop state data completely corresponds to the feature of the motor current loop state data to be processed; if so, obtaining the first initial feature, the second initial feature, and the third initial feature of the historical motor current loop state data as the feature of the historical motor current loop state data; otherwise, updating the historical motor current loop state database according to the third initial feature of the historical motor current loop state data, and returning to S1-3; The motor current loop state data to be processed is motor current loop operation state data including abnormal operation state data of the motor current loop.

[0008] Optionally, constructing a motor current loop state monitoring and evaluation model based on a convolutional neural network according to the historical motor current loop state data features includes: S2-1, obtaining the current time as the starting time t of the historical motor current loop state data feature; S2-2, respectively obtain the historical motor current loop state data features at the starting time t, time t+1 and time t+2 as the training set, the first verification set and the second verification set; S2-3. Constructing a motor current loop initial state monitoring and evaluation model based on a convolutional neural network according to the training set, the first verification set, and the second verification set; S2-4. Obtain a motor current loop initial state monitoring and evaluation model based on the motor current loop initial state monitoring and evaluation model using the historical motor current loop state data characteristics.

[0009] Optionally, constructing a motor current loop initial state monitoring and evaluation model based on a convolutional neural network according to the training set, the first validation set, and the second validation set includes: S2-3-1. Using the training set as input and the training results of the motor current loop initial state monitoring and evaluation corresponding to the training set as output, a convolutional neural network is trained to obtain a motor current loop initial state monitoring and evaluation training model; S2-3-2, inputting the first verification set and the second verification set into the motor current loop initial state monitoring and evaluation model respectively to obtain a first motor current loop initial state monitoring and evaluation verification result and a second motor current loop initial state monitoring and evaluation verification result; S2-3-3. Determine whether the first motor current loop initial state monitoring evaluation verification result completely corresponds to the output result of the motor current loop initial state monitoring evaluation training model. If so, execute S2-3-4. Otherwise, update the training set according to the first verification set corresponding to the first motor current loop initial state monitoring evaluation verification result, and return to S2-3-1. S2-3-4. Determine whether the second motor current loop initial state monitoring evaluation verification result and the motor current loop initial state monitoring evaluation training model are completely corresponding. If so, obtain the motor current loop initial state monitoring evaluation training model as the motor current loop initial state monitoring evaluation model. Otherwise, update the training set according to the second verification set corresponding to the second motor current loop initial state monitoring evaluation verification result, and return to S2-3-1.

[0010] Optionally, obtaining the motor current loop initial state monitoring and evaluation model based on the motor current loop initial state monitoring and evaluation model by utilizing the historical motor current loop state data features includes: S2-4-1. Obtain historical motor current loop state data verification features according to the historical motor current loop state data features as the first basic feature, the second basic feature, and the third basic feature of the historical motor current loop state data features respectively; S2-4-2, inputting the first basic feature, the second basic feature, and the third basic feature of the historical motor current loop state data characteristics into the motor current loop initial state monitoring and evaluation model to obtain the first basic feature monitoring and evaluation result, the second basic feature monitoring and evaluation result, and the third basic feature monitoring and evaluation result; S2-4-3. Determine whether the first basic feature monitoring and evaluation result, the second basic feature monitoring and evaluation result, and the third basic feature monitoring and evaluation result are completely consistent. If so, obtain the motor current loop initial state monitoring and evaluation model as the motor current loop initial state monitoring and evaluation model. Otherwise, execute S2-4-4. S2-4-4. Determine whether the first basic feature monitoring and evaluation result, the second basic feature monitoring and evaluation result and the third basic feature monitoring and evaluation result are inconsistent with each other. If so, update the training set according to the first basic feature, the second basic feature and the third basic feature of the historical motor current loop state data feature, and return to S2-3-1. Otherwise, update the historical motor current loop state data verification feature according to the consistent historical motor current loop state data feature, and return to S2-4-1.

[0011] Optionally, obtaining the motor current loop initial state monitoring and evaluation result by using the motor current loop state monitoring and evaluation model according to the motor current loop state data to be processed includes: S3-1, pre-processing is performed in sequence according to the motor current loop state data to be processed to obtain motor current loop state data; S3-2, obtaining motor current loop abnormal state data corresponding to historical motor current loop state data according to the motor current loop state data; S3-3, determining whether the motor current loop state data contains the motor current loop abnormal state data; if so, re-collecting the motor current loop state data to be processed and returning to S2-1; otherwise, obtaining the motor current loop state data as the motor current loop state data feature and executing S3-4; S3-4. Obtain the motor current loop initial state monitoring and evaluation result based on the motor current loop state monitoring and evaluation model using the motor current loop state data feature.

[0012] Optionally, obtaining the motor current loop initial state monitoring and evaluation result based on the motor current loop state monitoring and evaluation model by utilizing the motor current loop state data feature includes: S3-4-1. Input the motor current loop state data characteristics into the motor current loop state monitoring and evaluation model to obtain a first motor current loop initial state monitoring and evaluation result and a second motor current loop initial state monitoring and evaluation result; S3-4-2. Determine whether the first motor current loop initial state monitoring and evaluation result and the second motor current loop initial state monitoring and evaluation result are exactly the same; if so, obtain the first motor current loop initial state monitoring and evaluation result and the second motor current loop initial state monitoring and evaluation result as the motor current loop initial state monitoring and evaluation result; otherwise, execute S3-4-3; S3-4-3. Determine whether the first motor current loop initial state monitoring and evaluation result is partially identical to the second motor current loop initial state monitoring and evaluation result. If so, update the motor current loop state data according to the partially different motor current loop initial state monitoring and evaluation results, and return to S3-1. Otherwise, update the training set according to the motor current loop state data features corresponding to the first motor current loop initial state monitoring and evaluation result and the second motor current loop initial state monitoring and evaluation result, and return to S2-3-1.

[0013] Optionally, performing time series analysis on the to-be-processed motor current loop state data to obtain a trend of the motor current loop state data includes: S4-1, performing time sequence division according to the motor current loop state data to be processed to obtain a continuous motor current loop state database to be processed; S4-2, performing abnormal value detection and data smoothing processing in sequence according to the continuous motor current loop state data to be processed to obtain continuous motor current loop state data; S4-3, using the continuous motor current loop state data to obtain motor current loop state data trends in consecutive time periods as motor current loop state data trends in a first time period, motor current loop state data trends in a second time period, and motor current loop state data trends in a third time period; S4-4, judging whether the motor current loop state data trend of the first time period, the motor current loop state data trend of the second time period and the motor current loop state data trend of the third time period are completely consistent; if so, obtaining the motor current loop state data trend of the first time period, the motor current loop state data trend of the second time period and the motor current loop state data trend of the third time period as the motor current loop state data trend; otherwise, executing S4-5; S4-5. Determine whether the motor current loop state data trend of the first time period, the motor current loop state data trend of the second time period, and the motor current loop state data trend of the third time period are completely inconsistent. If so, return to S4-2; otherwise, re-acquire the motor current loop state data trend of the continuous time period and return to S4-3.

[0014] Optionally, performing time-series division according to the to-be-processed motor current loop state data to obtain a continuous to-be-processed motor current loop state database includes: S4-1-1, obtaining a time window of the motor current loop state data to be processed according to the motor current state data to be processed and the initial characteristics of the corresponding motor current state data to be processed; S4-1-2, using the time window of the motor current loop state data to be processed to perform time sequence division on the motor current state data to be processed to obtain initial state data features of the motor current loop state data to be processed; S4-1-3, obtaining initial state data corresponding to the motor current loop state data to be processed according to the initial state data characteristics of the motor current loop state data to be processed; S4-1-4, obtaining a continuity state data feature corresponding to the motor current loop state data to be processed according to the initial state data feature of the motor current loop state data to be processed; S4-1-5, obtaining continuity status data corresponding to the motor current loop state data to be processed according to the continuity status data characteristics of the motor current loop state data to be processed; S4-1-6, obtaining the initial state data feature of the motor current loop state data to be processed and the continuity state data feature of the corresponding motor current loop state data to be processed as the state data feature of the motor current loop state data to be processed; S4-1-7, obtaining the initial state data corresponding to the motor current loop state data to be processed and the continuity state data corresponding to the motor current loop state data to be processed as the state data of the motor current loop state data to be processed; S4-1-8. Obtain the continuous motor current loop state database to be processed using the state data characteristics of the motor current loop state data to be processed and the state data of the motor current loop state data to be processed.

[0015] Optionally, obtaining the motor current loop state monitoring and evaluation result according to the motor current loop initial state monitoring and evaluation result and the motor current loop state data trend includes: S5-1, obtaining a trend of the motor current loop initial state monitoring and evaluation result according to the motor current loop initial state monitoring and evaluation result; S5-2, determine whether the trend of the motor current loop initial state monitoring evaluation result is exactly the same as the trend of the motor current loop state data; if so, obtain the motor current loop initial state monitoring evaluation result as the motor current loop state monitoring evaluation result; otherwise, update the continuous motor current loop state data according to the motor current loop initial state monitoring evaluation result corresponding to the motor current loop initial state monitoring evaluation result, and return to S4-3. Compared with the closest prior art, the present invention has the following beneficial effects: The present invention ensures that the motor current loop state monitoring and evaluation model makes judgments based on the latest motor current loop state data by updating the historical motor current loop state database, reduces misjudgments and missed judgments caused by outdated data, and improves the accuracy of fault diagnosis; by updating the historical motor current loop state data characteristics, it ensures that the motor current loop state monitoring and evaluation model can accurately monitor and evaluate, and improves the accuracy and reliability of state monitoring and evaluation; the motor current loop state monitoring and evaluation results are obtained by combining the motor current loop initial state monitoring and evaluation results and the motor current loop state data trend, thereby achieving stable, efficient and accurate output of the motor current loop state monitoring and evaluation results. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0017] Figure 1 This is a flow chart of a motor current loop state monitoring and evaluation method based on a dynamic database according to an embodiment of the present invention. DETAILED DESCRIPTION

[0018] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with specific embodiments of the present invention and corresponding drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0019] The terms used in the embodiments of the present invention are only used to explain the specific embodiments of the present invention and are not intended to limit the present invention.

[0020] like Figure 1 As shown, an embodiment of the present invention provides a motor current loop state monitoring and evaluation method based on a dynamic database, comprising the following steps: S1. Using the motor current loop state data to be processed, establish historical motor current loop state data characteristics based on a dynamic database; S2. Constructing a motor current loop state monitoring and evaluation model based on a convolutional neural network according to the historical motor current loop state data characteristics; S3, obtaining a motor current loop initial state monitoring and evaluation result using the motor current loop state monitoring and evaluation model according to the motor current loop state data to be processed; S4, using the motor current loop state data to be processed to perform time series analysis to obtain the motor current loop state data trend; S5. Obtain a motor current loop state monitoring and evaluation result according to the motor current loop initial state monitoring and evaluation result and the motor current loop state data trend.

[0021] S1 specifically includes: S1-1, obtaining the motor current loop state data to be processed as the motor current loop state data feature to be processed; S1-2, establishing a historical motor current loop state database based on a dynamic database according to the motor current loop state data to be processed; S1-3, using the historical motor current loop state database to obtain corresponding historical motor current loop state data as a first initial feature of the historical motor current loop state data; S1-4, obtaining a second initial feature and a third initial feature of the historical motor current loop state data using the historical motor current loop state database according to the first initial feature of the historical motor current loop state data; S1-5, determining whether the first initial feature of the historical motor current loop state data completely corresponds to the feature of the motor current loop state data to be processed; if so, executing S1-6; otherwise, updating the historical motor current loop state database according to the first initial feature of the historical motor current loop state data, and returning to S1-3; S1-6, determining whether the second initial feature of the historical motor current loop state data completely corresponds to the feature of the motor current loop state data to be processed; if so, executing S1-7; otherwise, updating the historical motor current loop state database according to the second initial feature of the historical motor current loop state data, and returning to S1-3; S1-7, determining whether the third initial feature of the historical motor current loop state data completely corresponds to the feature of the motor current loop state data to be processed; if so, obtaining the first initial feature, the second initial feature, and the third initial feature of the historical motor current loop state data as the feature of the historical motor current loop state data; otherwise, updating the historical motor current loop state database according to the third initial feature of the historical motor current loop state data, and returning to S1-3; The motor current loop state data to be processed is motor current loop operation state data including abnormal operation state data of the motor current loop.

[0022] S2 specifically includes: S2-1, obtaining the current time as the starting time t of the historical motor current loop state data feature; S2-2, respectively obtain the historical motor current loop state data features at the starting time t, time t+1 and time t+2 as the training set, the first verification set and the second verification set; S2-3. Constructing a motor current loop initial state monitoring and evaluation model based on a convolutional neural network according to the training set, the first verification set, and the second verification set; S2-4. Obtain a motor current loop initial state monitoring and evaluation model based on the motor current loop initial state monitoring and evaluation model using the historical motor current loop state data characteristics.

[0023] S2-3 specifically includes: S2-3-1. Using the training set as input and the training results of the motor current loop initial state monitoring and evaluation corresponding to the training set as output, a convolutional neural network is trained to obtain a motor current loop initial state monitoring and evaluation training model; S2-3-2, inputting the first verification set and the second verification set into the motor current loop initial state monitoring and evaluation model respectively to obtain a first motor current loop initial state monitoring and evaluation verification result and a second motor current loop initial state monitoring and evaluation verification result; S2-3-3. Determine whether the first motor current loop initial state monitoring evaluation verification result completely corresponds to the output result of the motor current loop initial state monitoring evaluation training model. If so, execute S2-3-4. Otherwise, update the training set according to the first verification set corresponding to the first motor current loop initial state monitoring evaluation verification result, and return to S2-3-1. S2-3-4. Determine whether the second motor current loop initial state monitoring evaluation verification result and the motor current loop initial state monitoring evaluation training model are completely corresponding. If so, obtain the motor current loop initial state monitoring evaluation training model as the motor current loop initial state monitoring evaluation model. Otherwise, update the training set according to the second verification set corresponding to the second motor current loop initial state monitoring evaluation verification result, and return to S2-3-1.

[0024] S2-4 specifically includes: S2-4-1. Obtain historical motor current loop state data verification features according to the historical motor current loop state data features as first, second, and third basic features of the historical motor current loop state data features, respectively; S2-4-2, inputting the first basic feature, the second basic feature, and the third basic feature of the historical motor current loop state data characteristics into the motor current loop initial state monitoring and evaluation model to obtain the first basic feature monitoring and evaluation result, the second basic feature monitoring and evaluation result, and the third basic feature monitoring and evaluation result; S2-4-3. Determine whether the first basic feature monitoring and evaluation result, the second basic feature monitoring and evaluation result, and the third basic feature monitoring and evaluation result are completely consistent. If so, obtain the motor current loop initial state monitoring and evaluation model as the motor current loop initial state monitoring and evaluation model. Otherwise, execute S2-4-4. S2-4-4. Determine whether the first basic feature monitoring and evaluation result, the second basic feature monitoring and evaluation result and the third basic feature monitoring and evaluation result are inconsistent with each other. If so, update the training set according to the first basic feature, the second basic feature and the third basic feature of the historical motor current loop state data feature, and return to S2-3-1. Otherwise, update the historical motor current loop state data verification feature according to the consistent historical motor current loop state data feature, and return to S2-4-1.

[0025] S3 specifically includes: S3-1, pre-processing is performed in sequence according to the motor current loop state data to be processed to obtain motor current loop state data; S3-2, obtaining motor current loop abnormal state data corresponding to historical motor current loop state data according to the motor current loop state data; S3-3, determining whether the motor current loop state data contains the motor current loop abnormal state data; if so, re-collecting the motor current loop state data to be processed and returning to S2-1; otherwise, obtaining the motor current loop state data as the motor current loop state data feature and executing S3-4; S3-4. Obtain the motor current loop initial state monitoring and evaluation result based on the motor current loop state monitoring and evaluation model using the motor current loop state data feature.

[0026] S3-4 specifically includes: S3-4-1. Input the motor current loop state data characteristics into the motor current loop state monitoring and evaluation model to obtain a first motor current loop initial state monitoring and evaluation result and a second motor current loop initial state monitoring and evaluation result; S3-4-2. Determine whether the first motor current loop initial state monitoring and evaluation result and the second motor current loop initial state monitoring and evaluation result are exactly the same; if so, obtain the first motor current loop initial state monitoring and evaluation result and the second motor current loop initial state monitoring and evaluation result as the motor current loop initial state monitoring and evaluation result; otherwise, execute S3-4-3; S3-4-3. Determine whether the first motor current loop initial state monitoring and evaluation result is partially identical to the second motor current loop initial state monitoring and evaluation result. If so, update the motor current loop state data according to the partially different motor current loop initial state monitoring and evaluation results, and return to S3-1. Otherwise, update the training set according to the motor current loop state data features corresponding to the first motor current loop initial state monitoring and evaluation result and the second motor current loop initial state monitoring and evaluation result, and return to S2-3-1.

[0027] S4 specifically includes: S4-1, performing time sequence division according to the motor current loop state data to be processed to obtain a continuous motor current loop state database to be processed; S4-2, performing abnormal value detection and data smoothing processing in sequence according to the continuous motor current loop state data to be processed to obtain continuous motor current loop state data; S4-3, using the continuous motor current loop state data to obtain motor current loop state data trends in consecutive time periods as motor current loop state data trends in a first time period, motor current loop state data trends in a second time period, and motor current loop state data trends in a third time period; S4-4, judging whether the motor current loop state data trend of the first time period, the motor current loop state data trend of the second time period and the motor current loop state data trend of the third time period are completely consistent; if so, obtaining the motor current loop state data trend of the first time period, the motor current loop state data trend of the second time period and the motor current loop state data trend of the third time period as the motor current loop state data trend; otherwise, executing S4-5; S4-5. Determine whether the motor current loop state data trend of the first time period, the motor current loop state data trend of the second time period, and the motor current loop state data trend of the third time period are completely inconsistent. If so, return to S4-2; otherwise, re-acquire the motor current loop state data trend of the continuous time period and return to S4-3.

[0028] S4-1 includes: S4-1-1, obtaining a time window of the motor current loop state data to be processed according to the motor current state data to be processed and the initial characteristics of the corresponding motor current state data to be processed; S4-1-2, using the time window of the motor current loop state data to be processed to perform time sequence division on the motor current state data to be processed to obtain initial state data features of the motor current loop state data to be processed; S4-1-3, obtaining initial state data corresponding to the motor current loop state data to be processed according to the initial state data characteristics of the motor current loop state data to be processed; S4-1-4, obtaining a continuity state data feature corresponding to the motor current loop state data to be processed according to the initial state data feature of the motor current loop state data to be processed; S4-1-5, obtaining continuity status data corresponding to the motor current loop state data to be processed according to the continuity status data characteristics of the motor current loop state data to be processed; S4-1-6, obtaining the initial state data feature of the motor current loop state data to be processed and the continuity state data feature of the corresponding motor current loop state data to be processed as the state data feature of the motor current loop state data to be processed; S4-1-7, obtaining the initial state data corresponding to the motor current loop state data to be processed and the continuity state data corresponding to the motor current loop state data to be processed as the state data of the motor current loop state data to be processed; S4-1-8. Obtain the continuous motor current loop state database to be processed using the state data characteristics of the motor current loop state data to be processed and the state data of the motor current loop state data to be processed.

[0029] S5 specifically includes: S5-1, obtaining a trend of the motor current loop initial state monitoring and evaluation result according to the motor current loop initial state monitoring and evaluation result; S5-2. Determine whether the trend of the motor current loop initial state monitoring and evaluation result is exactly the same as the trend of the motor current loop state data. If so, obtain the motor current loop initial state monitoring and evaluation result as the motor current loop state monitoring and evaluation result. Otherwise, update the continuous motor current loop state data according to the motor current loop initial state monitoring and evaluation result corresponding to the motor current loop initial state monitoring and evaluation result according to the trend of the motor current loop initial state monitoring and evaluation result, and return to S4-3.

[0030] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0031] The present invention is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0032] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0033] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0034] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered by the scope of protection of the claims of the present invention.

Claims

1. A motor current loop state monitoring and evaluation method based on a dynamic database, characterized in that: The specific steps include: S1. Using the motor current loop state data to be processed, establish historical motor current loop state data characteristics based on a dynamic database; S2. Constructing a motor current loop state monitoring and evaluation model based on a convolutional neural network according to the historical motor current loop state data characteristics; S3, obtaining a motor current loop initial state monitoring and evaluation result using the motor current loop state monitoring and evaluation model according to the motor current loop state data to be processed; S4, using the motor current loop state data to be processed to perform time series analysis to obtain the motor current loop state data trend; S5. Obtain a motor current loop state monitoring and evaluation result according to the motor current loop initial state monitoring and evaluation result and the motor current loop state data trend.

2. The motor current loop state monitoring and evaluation method based on a dynamic database according to claim 1 is characterized in that: The features of historical motor current loop state data established based on the dynamic database using the motor current loop state data to be processed include: S1-1, obtaining the motor current loop state data to be processed as the motor current loop state data feature to be processed; S1-2, establishing a historical motor current loop state database based on a dynamic database according to the motor current loop state data to be processed; S1-3, using the historical motor current loop state database to obtain corresponding historical motor current loop state data as a first initial feature of the historical motor current loop state data; S1-4, obtaining a second initial feature and a third initial feature of the historical motor current loop state data using the historical motor current loop state database according to the first initial feature of the historical motor current loop state data; S1-5, determining whether the first initial feature of the historical motor current loop state data completely corresponds to the feature of the motor current loop state data to be processed; if so, executing S1-6; otherwise, updating the historical motor current loop state database according to the first initial feature of the historical motor current loop state data, and returning to S1-3; S1-6, determining whether the second initial feature of the historical motor current loop state data completely corresponds to the feature of the motor current loop state data to be processed; if so, executing S1-7; otherwise, updating the historical motor current loop state database according to the second initial feature of the historical motor current loop state data, and returning to S1-3; S1-7, determining whether the third initial feature of the historical motor current loop state data completely corresponds to the feature of the motor current loop state data to be processed; if so, obtaining the first initial feature, the second initial feature, and the third initial feature of the historical motor current loop state data as the feature of the historical motor current loop state data; otherwise, updating the historical motor current loop state database according to the third initial feature of the historical motor current loop state data, and returning to S1-3; The motor current loop state data to be processed is motor current loop operation state data including abnormal operation state data of the motor current loop.

3. The motor current loop state monitoring and evaluation method based on a dynamic database according to claim 1 is characterized in that: Building a motor current loop state monitoring and evaluation model based on a convolutional neural network according to the historical motor current loop state data features includes: S2-1, obtaining the current time as the starting time t of the historical motor current loop state data feature; S2-2, respectively obtain the historical motor current loop state data features at the starting time t, time t+1 and time t+2 as the training set, the first verification set and the second verification set; S2-3. Constructing a motor current loop initial state monitoring and evaluation model based on a convolutional neural network according to the training set, the first verification set, and the second verification set; S2-4. Obtain a motor current loop initial state monitoring and evaluation model based on the motor current loop initial state monitoring and evaluation model using the historical motor current loop state data characteristics.

4. The motor current loop state monitoring and evaluation method based on a dynamic database according to claim 3 is characterized in that: Constructing a motor current loop initial state monitoring and evaluation model based on a convolutional neural network according to the training set, the first verification set, and the second verification set includes: S2-3-1. Using the training set as input and the training results of the motor current loop initial state monitoring and evaluation corresponding to the training set as output, a convolutional neural network is trained to obtain a motor current loop initial state monitoring and evaluation training model; S2-3-2, inputting the first verification set and the second verification set into the motor current loop initial state monitoring and evaluation model respectively to obtain a first motor current loop initial state monitoring and evaluation verification result and a second motor current loop initial state monitoring and evaluation verification result; S2-3-3. Determine whether the first motor current loop initial state monitoring evaluation verification result completely corresponds to the output result of the motor current loop initial state monitoring evaluation training model. If so, execute S2-3-4. Otherwise, update the training set according to the first verification set corresponding to the first motor current loop initial state monitoring evaluation verification result, and return to S2-3-1. S2-3-4. Determine whether the second motor current loop initial state monitoring evaluation verification result and the motor current loop initial state monitoring evaluation training model are completely corresponding. If so, obtain the motor current loop initial state monitoring evaluation training model as the motor current loop initial state monitoring evaluation model. Otherwise, update the training set according to the second verification set corresponding to the second motor current loop initial state monitoring evaluation verification result, and return to S2-3-1.

5. The motor current loop state monitoring and evaluation method based on a dynamic database according to claim 4 is characterized in that: Obtaining a motor current loop initial state monitoring and evaluation model based on the motor current loop initial state monitoring and evaluation model by utilizing the historical motor current loop state data features includes: S2-4-1. Obtain historical motor current loop state data verification features according to the historical motor current loop state data features as first, second, and third basic features of the historical motor current loop state data features, respectively; S2-4-2, inputting the first basic feature, the second basic feature, and the third basic feature of the historical motor current loop state data characteristics into the motor current loop initial state monitoring and evaluation model to obtain the first basic feature monitoring and evaluation result, the second basic feature monitoring and evaluation result, and the third basic feature monitoring and evaluation result; S2-4-3. Determine whether the first basic feature monitoring and evaluation result, the second basic feature monitoring and evaluation result, and the third basic feature monitoring and evaluation result are completely consistent. If so, obtain the motor current loop initial state monitoring and evaluation model as the motor current loop initial state monitoring and evaluation model. Otherwise, execute S2-4-4. S2-4-4. Determine whether the first basic feature monitoring and evaluation result, the second basic feature monitoring and evaluation result and the third basic feature monitoring and evaluation result are inconsistent with each other. If so, update the training set according to the first basic feature, the second basic feature and the third basic feature of the historical motor current loop state data feature, and return to S2-3-1. Otherwise, update the historical motor current loop state data verification feature according to the consistent historical motor current loop state data feature, and return to S2-4-1.

6. The motor current loop state monitoring and evaluation method based on a dynamic database according to claim 5 is characterized in that: Acquiring the motor current loop initial state monitoring and evaluation result by using the motor current loop state monitoring and evaluation model according to the motor current loop state data to be processed includes: S3-1, pre-processing is performed in sequence according to the motor current loop state data to be processed to obtain motor current loop state data; S3-2, obtaining motor current loop abnormal state data corresponding to historical motor current loop state data according to the motor current loop state data; S3-3, determining whether the motor current loop state data contains the motor current loop abnormal state data; if so, re-collecting the motor current loop state data to be processed and returning to S2-1; otherwise, obtaining the motor current loop state data as the motor current loop state data feature and executing S3-4; S3-4. Obtain the motor current loop initial state monitoring and evaluation result based on the motor current loop state monitoring and evaluation model using the motor current loop state data feature.

7. The motor current loop state monitoring and evaluation method based on a dynamic database according to claim 6 is characterized in that: Obtaining the motor current loop initial state monitoring and evaluation result based on the motor current loop state monitoring and evaluation model by utilizing the motor current loop state data feature includes: S3-4-1. Input the motor current loop state data characteristics into the motor current loop state monitoring and evaluation model to obtain a first motor current loop initial state monitoring and evaluation result and a second motor current loop initial state monitoring and evaluation result; S3-4-2. Determine whether the first motor current loop initial state monitoring and evaluation result and the second motor current loop initial state monitoring and evaluation result are exactly the same; if so, obtain the first motor current loop initial state monitoring and evaluation result and the second motor current loop initial state monitoring and evaluation result as the motor current loop initial state monitoring and evaluation result; otherwise, execute S3-4-3; S3-4-3. Determine whether the first motor current loop initial state monitoring and evaluation result is partially identical to the second motor current loop initial state monitoring and evaluation result. If so, update the motor current loop state data according to the partially different motor current loop initial state monitoring and evaluation results, and return to S3-1. Otherwise, update the training set according to the motor current loop state data features corresponding to the first motor current loop initial state monitoring and evaluation result and the second motor current loop initial state monitoring and evaluation result, and return to S2-3-1.

8. The motor current loop state monitoring and evaluation method based on a dynamic database according to claim 1 is characterized in that: Using the to-be-processed motor current loop state data to perform time sequence analysis to obtain the motor current loop state data trend includes: S4-1, performing time sequence division according to the motor current loop state data to be processed to obtain a continuous motor current loop state database to be processed; S4-2, performing abnormal value detection and data smoothing processing in sequence according to the continuous motor current loop state data to be processed to obtain continuous motor current loop state data; S4-3, using the continuous motor current loop state data to obtain motor current loop state data trends in consecutive time periods as motor current loop state data trends in a first time period, motor current loop state data trends in a second time period, and motor current loop state data trends in a third time period; S4-4, judging whether the motor current loop state data trend of the first time period, the motor current loop state data trend of the second time period and the motor current loop state data trend of the third time period are completely consistent; if so, obtaining the motor current loop state data trend of the first time period, the motor current loop state data trend of the second time period and the motor current loop state data trend of the third time period as the motor current loop state data trend; otherwise, executing S4-5; S4-5. Determine whether the motor current loop state data trend of the first time period, the motor current loop state data trend of the second time period, and the motor current loop state data trend of the third time period are completely inconsistent. If so, return to S4-2; otherwise, re-acquire the motor current loop state data trend of the continuous time period and return to S4-3.

9. The motor current loop state monitoring and evaluation method based on a dynamic database according to claim 8, characterized in that: The method of performing time sequence division according to the motor current loop state data to be processed to obtain a continuous motor current loop state database to be processed includes: S4-1-1, obtaining a time window of the motor current loop state data to be processed according to the motor current state data to be processed and the initial characteristics of the corresponding motor current state data to be processed; S4-1-2, using the time window of the motor current loop state data to be processed to perform time sequence division on the motor current state data to be processed to obtain initial state data features of the motor current loop state data to be processed; S4-1-3, obtaining initial state data corresponding to the motor current loop state data to be processed according to the initial state data characteristics of the motor current loop state data to be processed; S4-1-4, obtaining a continuity state data feature corresponding to the motor current loop state data to be processed according to the initial state data feature of the motor current loop state data to be processed; S4-1-5, obtaining continuity status data corresponding to the motor current loop state data to be processed according to the continuity status data characteristics of the motor current loop state data to be processed; S4-1-6, obtaining the initial state data feature of the motor current loop state data to be processed and the continuity state data feature of the corresponding motor current loop state data to be processed as the state data feature of the motor current loop state data to be processed; S4-1-7, obtaining the initial state data corresponding to the motor current loop state data to be processed and the continuity state data corresponding to the motor current loop state data to be processed as the state data of the motor current loop state data to be processed; S4-1-8. Obtain the continuous motor current loop state database to be processed using the state data characteristics of the motor current loop state data to be processed and the state data of the motor current loop state data to be processed.

10. The motor current loop state monitoring and evaluation method based on a dynamic database according to claim 9, characterized in that: Acquiring a motor current loop state monitoring and evaluation result according to the motor current loop initial state monitoring and evaluation result and the motor current loop state data trend includes: S5-1, obtaining a trend of the motor current loop initial state monitoring and evaluation result according to the motor current loop initial state monitoring and evaluation result; S5-2. Determine whether the trend of the motor current loop initial state monitoring and evaluation result is exactly the same as the trend of the motor current loop state data. If so, obtain the motor current loop initial state monitoring and evaluation result as the motor current loop state monitoring and evaluation result. Otherwise, update the continuous motor current loop state data according to the motor current loop initial state monitoring and evaluation result corresponding to the motor current loop initial state monitoring and evaluation result according to the trend of the motor current loop initial state monitoring and evaluation result, and return to S4-3.

Images