Motor intelligent monitoring system and method based on artificial intelligence
Through the intelligent motor monitoring system based on artificial intelligence, data connection channels are built and fault perception is evaluated, the problem of poor motor fault monitoring in the existing technology is solved, and accurate prediction of motor fault risks and adaptive control of operating performance is achieved. .
Patent Information
- Application Number
- CN202411154994.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-22
- Publication Date
- 2024-11-22
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The prior art lacks effective mechanisms to monitor and predict motor failures, resulting in reduced equipment performance and increased risk of safety accidents.
Design an intelligent motor monitoring system based on artificial intelligence, including a monitoring log library module, a test data model module and a prediction module. By building a data connection channel, it evaluates fault perception capabilities and conducts artificial intelligence predictions to output fault risk results.
It realizes accurate prediction and monitoring of motor failure risks, improves the risk assessment and adaptive control capabilities of motor operating performance, and enhances the stability of fault perception and prediction accuracy.
Smart Images

Figure CN119001441A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of motor monitoring, and in particular to an artificial intelligence-based intelligent motor monitoring system and method. Background Art
[0002] With the continuous development of modern industrial technology, motors are widely used in various fields as power sources. During operation, motors may fail due to various reasons, resulting in decreased equipment performance, reduced production efficiency, and even safety accidents. In the prior art, there is a lack of an effective mechanism to monitor motor fault events through the chip's sensing capabilities, making it difficult to control and predict motor faults in a timely manner. Summary of the invention
[0003] The purpose of the present invention is to provide an artificial intelligence-based motor intelligent monitoring system and method to solve the problems raised in the above background technology.
[0004] In order to solve the above technical problems, the present invention provides the following technical solutions: An intelligent motor monitoring system based on artificial intelligence, the system includes: a monitoring log library module, a test data model module, an evaluation module and a prediction module; The monitoring log library module is used to establish a monitoring log library, which is respectively connected to the motor end and the chip end, and obtains the motor operation status data of the motor end and the protection mechanism triggering behavior data of the chip end; The test data model module constructs a test data model based on the monitoring log library, and the test data model is used to build a data connection channel between the motor end and the chip end to test the fault perception ability of the chip end when a fault occurs on the motor end; The evaluation module performs a historical evaluation of the fault perception capability based on the data connection channel; The prediction module performs artificial intelligence prediction of the fault risk of the motor end based on the historical evaluation results of the fault perception capability, and outputs the prediction result; The motor operation state is configured based on the speed span range of the motor, and one speed span range corresponds to one motor operation state, and the speed span range refers to a speed interval range formed by the motor transitioning from one speed to another speed; K motor operation state labels are initialized, wherein one motor operation state label corresponds to one motor operation state; The protection mechanism triggering behavior data refers to the condition group when the protection mechanism is triggered, and the condition group records the parameter calibration abnormality of the motor operation fed back by the motor end under each motor operating state; the parameter calibration refers to the intelligent adjustment of the various operating performances of the motor by the chip end under each motor operating state, and the parameter calibration abnormality refers to the error between the intelligently adjusted parameters and the standard parameters of each operating performance specified in the motor user manual, the percentage exceeding the preset error threshold, wherein when the error is lower than the preset error threshold, the parameter calibration abnormality is set to 0.
[0005] Further, the test data model module includes a data channel unit and a test unit; The data channel unit is used to configure a motor end interface for each motor operation status tag, so a total of K motor end interfaces are obtained, and any motor end interface is recorded as , x represents the number of the motor operation status label, and x≤K; Based on each protection mechanism processing unit inside the chip end, W chip end interface data collection clusters are constructed, wherein one protection mechanism processing unit corresponds to one chip end interface, so a total of W chip end interfaces are obtained, and one protection mechanism processing unit constructs one chip end interface data collection cluster; any chip end interface is recorded as , y represents the number of the protection mechanism processing unit, and y≤W; the chip end interface The corresponding chip-side interface data collection cluster is recorded as ,in, represents the calibration anomaly set of the ath condition group, A represents the total number of condition groups, and ,in, represents the parameter calibration abnormality corresponding to the rth operating performance, and R represents the total number of operating performances; Based on the motor end interface Chip-side interface , build a data connection channel, denoted as ; The test unit is used to construct a calibration abnormal behavior diagram analysis model, wherein the calibration abnormal behavior diagram is a regular polygon containing R sides, and each side of the regular polygon has a unique attribute of an operating performance, then the rth side of the regular polygon corresponds to the unique attribute of the rth operating performance; starting from the central symmetric point of the regular polygon, a vertical ray is drawn to each side, then a total of R vertical rays are obtained, and the length of the vertical ray is the parameter calibration abnormality corresponding to the operating performance under the unique attribute of the side; the end points of the R vertical rays are connected in sequence to form a test diagram, which is recorded as RC; Calibrate anomaly set The corresponding test graph is recorded as , get the test image The area of , and the area As the ath condition group, the chip side has the fault perception capability when a fault occurs on the motor side.
[0006] Furthermore, the historical evaluation of the fault perception capability includes: In the data connection channel In the above, based on the corresponding fault perception capability under each condition group, the fault perception stability of the chip end to the motor end is evaluated, and the fault perception stability value is calculated. The specific calculation formula is as follows: in, Indicates the chip end interface The corresponding protection mechanism processing unit is connected to the motor end interface The corresponding fault perception stability value of the motor operation state, V represents the expected value of fault perception stability.
[0007] Furthermore, the artificial intelligence prediction of the fault risk at the motor end includes: Based on the interaction between the chip-side interface and the motor-side interface, the artificial intelligence prediction value is calculated. The specific calculation formula is as follows: Among them, PV represents the artificial intelligence prediction value, SV represents the fault perception stability value threshold, if represents the judgment function, Indicates if the fault sensing stable value is less than or equal to the fault perception stability value threshold, then , otherwise let .
[0008] An artificial intelligence-based motor intelligent monitoring method, the method comprising the following steps: Establish a monitoring log library, connect to the motor side and the chip side respectively, and obtain the motor operation status data of the motor side and the protection mechanism triggering behavior data of the chip side respectively; Based on the monitoring log library, a test data model is constructed, wherein the test data model is used to construct a data connection channel between the motor end and the chip end to test the fault perception capability of the chip end when a fault occurs on the motor end; Historical evaluation of fault perception capabilities based on data connection channels; Based on the historical evaluation results of fault perception capabilities, artificial intelligence predicts the fault risk at the motor end and outputs the prediction results.
[0009] Furthermore, the establishment process of the monitoring log library is as follows: The motor operation state is configured based on the speed span range of the motor, and one speed span range corresponds to one motor operation state, and the speed span range refers to a speed interval range formed by the motor transitioning from one speed to another speed; K motor operation state labels are initialized, wherein one motor operation state label corresponds to one motor operation state; The protection mechanism triggering behavior data refers to the condition group when the protection mechanism is triggered, and the condition group records the parameter calibration abnormality of the motor operation fed back by the motor end under each motor operating state; the parameter calibration refers to the intelligent adjustment of the various operating performances of the motor by the chip end under each motor operating state, and the parameter calibration abnormality refers to the error between the intelligently adjusted parameters and the standard parameters of each operating performance specified in the motor user manual, the percentage exceeding the preset error threshold, wherein when the error is lower than the preset error threshold, the parameter calibration abnormality is set to 0.
[0010] Furthermore, the construction process of the data connection channel is as follows: For each motor operation status label, a motor end interface is configured, and a total of K motor end interfaces are obtained. Any motor end interface is recorded as , x represents the number of the motor operation status label, and x≤K; Based on each protection mechanism processing unit inside the chip end, W chip end interface data collection clusters are constructed, wherein one protection mechanism processing unit corresponds to one chip end interface, so a total of W chip end interfaces are obtained, and one protection mechanism processing unit constructs one chip end interface data collection cluster; any chip end interface is recorded as , y represents the number of the protection mechanism processing unit, and y≤W; the chip end interface The corresponding chip-side interface data collection cluster is recorded as ,in, represents the calibration anomaly set of the ath condition group, A represents the total number of condition groups, and ,in, represents the parameter calibration abnormality corresponding to the rth operating performance, and R represents the total number of operating performances; Based on the motor end interface Chip-side interface , build a data connection channel, denoted as .
[0011] Furthermore, the specific implementation process of the test chip end's fault perception capability when a fault occurs at the motor end includes: Construct a calibration abnormal behavior diagram analysis model, wherein the calibration abnormal behavior diagram is a regular polygon containing R edges, and each edge of the regular polygon has a unique attribute of operating performance, then the rth edge of the regular polygon corresponds to the unique attribute of the rth operating performance; starting from the central symmetric point of the regular polygon, a vertical ray is drawn to each edge, and a total of R vertical rays are obtained, and the length of the vertical ray is the parameter calibration abnormality corresponding to the operating performance under the unique attribute of the edge; the end points of the R vertical rays are connected in sequence to form a test diagram, which is recorded as RC; Calibrate anomaly set The corresponding test graph is recorded as , get the test image The area of , and the area As the ath condition group, the chip side has the fault perception capability when a fault occurs on the motor side.
[0012] According to the above method, the area The larger the value, the weaker the chip's ability to sense motor faults is, because the chip often uses algorithm control to adjust the motor's operating parameters. When the motor's operating parameter calibration error feedback is too large, it means that the chip needs a greater control force to respond to the protection mechanism, making the triggering condition accuracy of the protection mechanism insensitive. Furthermore, the specific implementation process of the historical evaluation of the fault perception capability includes: In the data connection channel In the above, based on the corresponding fault perception capability under each condition group, the fault perception stability of the chip end to the motor end is evaluated, and the fault perception stability value is calculated. The specific calculation formula is as follows: in, Indicates the chip end interface The corresponding protection mechanism processing unit is connected to the motor end interface The corresponding fault perception stability value of the motor operation state, V represents the expected value of fault perception stability.
[0013] Furthermore, the specific implementation process of artificial intelligence prediction of the fault risk at the motor end includes: Based on the interaction between the chip-side interface and the motor-side interface, the artificial intelligence prediction value is calculated. The specific calculation formula is as follows: Among them, PV represents the artificial intelligence prediction value, SV represents the fault perception stability value threshold, if represents the judgment function, Indicates if the fault sensing stable value is less than or equal to the fault perception stability value threshold, then , otherwise let ; According to the above method, the area The smaller the value, the more sensitive the triggering accuracy of the chip protection mechanism is, and the smaller the gap with the expected value of fault perception stability is. The larger the value, the better the fault perception stability; and the prediction value is the probability of non-good stability behavior in the process of sensing motor-end faults at the chip end. The larger the probability, the more accurate the prediction.
[0014] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: in an artificial intelligence-based motor intelligent monitoring system and method provided by the present invention, a monitoring log library is established, which is respectively connected to the motor end and the chip end, and the motor operation status data of the motor end and the protection mechanism triggering behavior data of the chip end are respectively obtained; based on the monitoring log library, a test data model is constructed, and the test data model is used to construct a data connection channel between the motor end and the chip end to test the fault perception ability of the chip end when a fault occurs at the motor end; based on the data connection channel, a historical evaluation of the fault perception ability is performed; based on the historical evaluation results of the fault perception ability, the fault risk of the motor end is predicted by artificial intelligence, and the prediction result is output; further, the risk of the motor operation performance can be predicted based on the protection mechanism triggering behavior inside the chip, and at the same time, the chip end can adaptively perceive the regulation behavior of the motor end, and the perception ability can be evaluated. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings: Figure 1 It is a structural schematic diagram of an artificial intelligence-based motor intelligent monitoring system of the present invention; Figure 2 It is a schematic diagram of the steps of an artificial intelligence-based motor intelligent monitoring method of the present invention. DETAILED DESCRIPTION
[0016] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0017] See also Figure 1-Figure 2 , the present invention provides a technical solution: See also Figure 1 , In the first embodiment of the present invention: a motor intelligent monitoring system based on artificial intelligence is provided, the system comprises: a monitoring log library module, a test data model module, an evaluation module and a prediction module; The monitoring log library module is used to establish a monitoring log library, which is connected to the motor end and the chip end respectively, and obtains the motor operation status data of the motor end and the protection mechanism triggering behavior data of the chip end respectively; The motor operation state is configured based on the speed span range of the motor, and one speed span range corresponds to one motor operation state. The speed span range refers to the speed interval range formed by the motor transitioning from one speed to another. K motor operation state labels are initialized, wherein one motor operation state label corresponds to one motor operation state. The protection mechanism triggering behavior data refers to the condition group when the protection mechanism is triggered, and the condition group records the abnormality of the parameter calibration of the motor operation fed back by the motor end under each motor operation state; parameter calibration refers to the intelligent adjustment of various operating performances of the motor by the chip end under each motor operation state, and the abnormality of parameter calibration refers to the error between the intelligently adjusted parameters and the standard parameters of various operating performances specified in the motor user manual, and the percentage exceeding the preset error threshold, wherein when the error is lower than the preset error threshold, the abnormality of parameter calibration is set to 0; The test data model module builds a test data model based on the monitoring log library. The test data model is used to build a data connection channel between the motor end and the chip end to test the fault perception ability of the chip end when a fault occurs on the motor end; Wherein, the test data model module includes a data channel unit and a test unit; The data channel unit is used to configure a motor end interface for each motor operation status tag, so a total of K motor end interfaces are obtained. Any motor end interface is recorded as , x represents the number of the motor operation status label, and x≤K; Based on each protection mechanism processing unit inside the chip end, W chip end interface data collection clusters are constructed, wherein one protection mechanism processing unit corresponds to one chip end interface, so a total of W chip end interfaces are obtained, and one protection mechanism processing unit constructs one chip end interface data collection cluster; any chip end interface is recorded as , y represents the number of the protection mechanism processing unit, and y≤W; the chip end interface The corresponding chip-side interface data collection cluster is recorded as ,in, represents the calibration anomaly set of the ath condition group, A represents the total number of condition groups, and ,in, represents the parameter calibration abnormality corresponding to the rth operating performance, and R represents the total number of operating performances; Based on the motor end interface Chip-side interface , build a data connection channel, denoted as ; The test unit is used to construct a calibration abnormal behavior diagram analysis model. The calibration abnormal behavior diagram is a regular polygon containing R edges, and each edge of the regular polygon has a unique attribute of an operating performance. The rth edge of the regular polygon corresponds to the unique attribute of the rth operating performance. Starting from the central symmetric point of the regular polygon, a vertical ray is drawn to each edge, and a total of R vertical rays are obtained. The length of the vertical ray is the parameter calibration abnormality corresponding to the operating performance under the unique attribute of the edge. The end points of the R vertical rays are connected in sequence to form a test diagram, which is recorded as RC. Calibrate anomaly set The corresponding test graph is recorded as , get the test image The area of , and the area As the fault sensing capability of the chip side when a fault occurs on the motor side under the ath condition group; An evaluation module that performs a historical evaluation of the fault perception capability based on the data connection channel; The historical evaluation of fault perception capability includes: In the data connection channel In the above, based on the corresponding fault perception capability under each condition group, the fault perception stability of the chip end to the motor end is evaluated, and the fault perception stability value is calculated. The specific calculation formula is as follows: in, Indicates the chip end interface The corresponding protection mechanism processing unit is connected to the motor end interface The corresponding fault perception stability value of the motor operation state, V represents the expected value of fault perception stability The prediction module uses artificial intelligence to predict the fault risk of the motor end based on the historical evaluation results of the fault perception capability and outputs the prediction results; Among them, artificial intelligence prediction of fault risks at the motor end includes: Based on the interaction between the chip-side interface and the motor-side interface, the artificial intelligence prediction value is calculated. The specific calculation formula is as follows: Among them, PV represents the artificial intelligence prediction value, SV represents the fault perception stability value threshold, if represents the judgment function, Indicates if the fault sensing stable value is less than or equal to the fault perception stability value threshold, then , otherwise let .
[0018] See also Figure 2 In the second embodiment, a motor intelligent monitoring method based on artificial intelligence is provided, and the method comprises the following steps: Establish a monitoring log library, connect to the motor side and the chip side respectively, and obtain the motor operation status data of the motor side and the protection mechanism triggering behavior data of the chip side respectively; The motor operation state is configured based on the speed span range of the motor, and one speed span range corresponds to one motor operation state. The speed span range refers to the speed interval range formed by the motor transitioning from one speed to another speed; K motor operation state labels are initialized, where one motor operation state label corresponds to one motor operation state; The protection mechanism triggering behavior data refers to the condition group when the protection mechanism is triggered, and the condition group records the abnormality of the parameter calibration of the motor operation fed back by the motor end under each motor operation state; parameter calibration refers to the intelligent adjustment of various operating performances of the motor by the chip end under each motor operation state, and the abnormality of parameter calibration refers to the error between the intelligently adjusted parameters and the standard parameters of various operating performances specified in the motor user manual, and the percentage exceeding the preset error threshold, wherein when the error is lower than the preset error threshold, the abnormality of parameter calibration is set to 0; Based on the monitoring log library, a test data model is constructed. The test data model is used to build a data connection channel between the motor end and the chip end to test the chip end's fault perception ability when a fault occurs on the motor end; The process of building a data connection channel is as follows: For each motor operation status label, a motor end interface is configured, and a total of K motor end interfaces are obtained. Any motor end interface is recorded as , x represents the number of the motor operation status label, and x≤K; Based on each protection mechanism processing unit inside the chip end, W chip end interface data collection clusters are constructed, wherein one protection mechanism processing unit corresponds to one chip end interface, so a total of W chip end interfaces are obtained, and one protection mechanism processing unit constructs one chip end interface data collection cluster; any chip end interface is recorded as , y represents the number of the protection mechanism processing unit, and y≤W; the chip end interface The corresponding chip-side interface data collection cluster is recorded as ,in, represents the calibration anomaly set of the ath condition group, A represents the total number of condition groups, and ,in, represents the parameter calibration abnormality corresponding to the rth operating performance, and R represents the total number of operating performances; Based on the motor end interface Chip-side interface , build a data connection channel, denoted as ; The specific implementation process of testing the chip's fault perception capability when a fault occurs on the motor side includes: Construct a calibration abnormal behavior diagram analysis model. The calibration abnormal behavior diagram is a regular polygon with R edges, and each edge of the regular polygon has a unique attribute of operating performance. The rth edge of the regular polygon corresponds to the unique attribute of the rth operating performance. Take the central symmetric point of the regular polygon as the starting point and make a vertical ray to each edge. Then a total of R vertical rays are obtained. The length of the vertical ray is the parameter calibration abnormality corresponding to the operating performance under the unique attribute of the edge. Connect the end points of the R vertical rays in sequence to form a test diagram, which is recorded as RC. Calibrate anomaly set The corresponding test graph is recorded as , get the test image The area of , and the area As the fault sensing capability of the chip side when a fault occurs on the motor side under the ath condition group; Historical evaluation of fault perception capabilities based on data connection channels; In the data connection channel In the above, based on the corresponding fault perception capability under each condition group, the fault perception stability of the chip end to the motor end is evaluated, and the fault perception stability value is calculated. The specific calculation formula is as follows: in, Indicates the chip end interface The corresponding protection mechanism processing unit is connected to the motor end interface The corresponding fault perception stability value of the motor operation state, V represents the expected value of fault perception stability; Based on the historical evaluation results of fault perception capabilities, artificial intelligence is used to predict the fault risks at the motor end and output the prediction results; Based on the interaction between the chip-side interface and the motor-side interface, the artificial intelligence prediction value is calculated. The specific calculation formula is as follows: Among them, PV represents the artificial intelligence prediction value, SV represents the fault perception stability value threshold, if represents the judgment function, Indicates if the fault sensing stable value is less than or equal to the fault perception stability value threshold, then , otherwise let ; For example, the operating states of the motor include: static state: the motor is not rotating. At this time, the input voltage is zero or too small to make the motor rotate. In this state, there is only a static magnetic field inside the motor and the current is zero; starting state: the motor begins to transition from a static state to a rotating state. During the starting process, the torque and current of the motor will increase instantly until they reach a steady state. At this time, the motor needs to overcome the inertia and braking torque of the rotor. The motor in the starting state may be subjected to greater mechanical and electrical stresses; steady-state working state: the motor runs at a stable speed under a constant load. At this time, the input power of the motor is equal to the output power, and the output torque and speed remain stable. In the steady-state working state, the motor's current, voltage, power, efficiency and other parameters are relatively stable; overload state: when the load borne by the motor exceeds its rated load, the motor will enter an overload state. In this state, the motor may not work properly and may experience abnormal conditions such as heating and smoke. The overload state will seriously affect the life of the motor. No-load state: The motor runs without load or with light load. At this time, the output power of the motor is zero or very small, and the speed reaches the highest. However, since power is consumed only by load wind resistance and mechanical friction resistance, the motor in the no-load state has low working efficiency, is prone to overheating, and the life of the motor may be affected. Braking state: In some applications, the motor may need to transition from a running state to a stopped state, which involves a braking process. The braking state is a state in which the motor slows down and stops rotating, and additional braking equipment or algorithms may be required to achieve this. Speed changing state: The motor may need to change the speed during operation to adapt to different work requirements. The speed changing state can be a gradual acceleration or deceleration, or a sudden change in speed.
[0019] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.
[0020] Finally, it should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.
Claims
1. A motor intelligent monitoring method based on artificial intelligence, characterized in that: The method comprises the following steps: Establish a monitoring log library, connect to the motor side and the chip side respectively, and obtain the motor operation status data of the motor side and the protection mechanism triggering behavior data of the chip side respectively; Based on the monitoring log library, a test data model is constructed, wherein the test data model is used to construct a data connection channel between the motor end and the chip end to test the fault perception capability of the chip end when a fault occurs on the motor end; Historical evaluation of fault perception capabilities based on data connection channels; Based on the historical evaluation results of fault perception capabilities, artificial intelligence predicts the fault risk at the motor end and outputs the prediction results.
2. The method for intelligent motor monitoring based on artificial intelligence according to claim 1, characterized in that: The process of establishing the monitoring log library is as follows: The motor operation state is configured based on the speed span range of the motor, and one speed span range corresponds to one motor operation state, and the speed span range refers to a speed interval range formed by the motor transitioning from one speed to another speed; K motor operation state labels are initialized, wherein one motor operation state label corresponds to one motor operation state; The protection mechanism triggering behavior data refers to the condition group when the protection mechanism is triggered, and the condition group records the parameter calibration abnormality of the motor operation fed back by the motor end under each motor operating state; the parameter calibration refers to the intelligent adjustment of the various operating performances of the motor by the chip end under each motor operating state, and the parameter calibration abnormality refers to the error between the intelligently adjusted parameters and the standard parameters of each operating performance specified in the motor user manual, the percentage exceeding the preset error threshold, wherein when the error is lower than the preset error threshold, the parameter calibration abnormality is set to 0.
3. The motor intelligent monitoring method based on artificial intelligence according to claim 2 is characterized in that: The process of constructing the data connection channel is as follows: For each motor operation status label, a motor end interface is configured, and a total of K motor end interfaces are obtained. Any motor end interface is recorded as , x represents the number of the motor operation status label, and x≤K; Based on each protection mechanism processing unit inside the chip end, W chip end interface data collection clusters are constructed, wherein one protection mechanism processing unit corresponds to one chip end interface, so a total of W chip end interfaces are obtained, and one protection mechanism processing unit constructs one chip end interface data collection cluster; any chip end interface is recorded as , y represents the number of the protection mechanism processing unit, and y≤W; the chip end interface The corresponding chip-side interface data collection cluster is recorded as ,in, represents the calibration anomaly set of the ath condition group, A represents the total number of condition groups, and ,in, represents the parameter calibration abnormality corresponding to the rth operating performance, and R represents the total number of operating performances; Based on the motor end interface Chip-side interface , build a data connection channel, denoted as .
4. The motor intelligent monitoring method based on artificial intelligence according to claim 3 is characterized in that: The specific implementation process of the test chip end's fault perception capability when a fault occurs at the motor end includes: Construct a calibration abnormal behavior diagram analysis model, wherein the calibration abnormal behavior diagram is a regular polygon containing R edges, and each edge of the regular polygon has a unique attribute of operating performance, then the rth edge of the regular polygon corresponds to the unique attribute of the rth operating performance; starting from the central symmetric point of the regular polygon, a vertical ray is drawn to each edge, then a total of R vertical rays are obtained, and the length of the vertical ray is the parameter calibration abnormality corresponding to the operating performance under the unique attribute of the edge; the end points of the R vertical rays are connected in sequence to form a test diagram, which is recorded as RC; Calibrate anomaly set The corresponding test graph is recorded as , get the test image The area of , and the area As the ath condition group, the chip side has the fault perception capability when a fault occurs on the motor side.
5. The method for intelligent motor monitoring based on artificial intelligence according to claim 4 is characterized in that: The specific implementation process of the historical evaluation of the fault perception capability includes: In the data connection channel In the above, based on the corresponding fault perception capability under each condition group, the fault perception stability of the chip end to the motor end is evaluated, and the fault perception stability value is calculated. The specific calculation formula is as follows: in, Indicates the chip end interface The corresponding protection mechanism processing unit is connected to the motor end interface The corresponding fault perception stability value of the motor operation state, V represents the expected value of fault perception stability.
6. The motor intelligent monitoring method based on artificial intelligence according to claim 5 is characterized in that: The specific implementation process of artificial intelligence prediction of the fault risk at the motor end includes: Based on the interaction between the chip-side interface and the motor-side interface, the artificial intelligence prediction value is calculated. The specific calculation formula is as follows: Among them, PV represents the artificial intelligence prediction value, SV represents the fault perception stability value threshold, if represents the judgment function, Indicates if the fault sensing stable value is less than or equal to the fault perception stability value threshold, then , otherwise let .
7. An artificial intelligence-based motor intelligent monitoring system, which executes an artificial intelligence-based motor intelligent monitoring method as claimed in any one of claims 1 to 6, characterized in that: The system includes: a monitoring log library module, a test data model module, an evaluation module and a prediction module; The monitoring log library module is used to establish a monitoring log library, which is respectively connected to the motor end and the chip end, and obtains the motor operation status data of the motor end and the protection mechanism triggering behavior data of the chip end; The test data model module constructs a test data model based on the monitoring log library, and the test data model is used to build a data connection channel between the motor end and the chip end to test the fault perception ability of the chip end when a fault occurs on the motor end; The evaluation module performs a historical evaluation of the fault perception capability based on the data connection channel; The prediction module performs artificial intelligence prediction of the fault risk of the motor end based on the historical evaluation results of the fault perception capability, and outputs the prediction result; The motor operation state is configured based on the speed span range of the motor, and one speed span range corresponds to one motor operation state, and the speed span range refers to a speed interval range formed by the motor transitioning from one speed to another speed; K motor operation state labels are initialized, wherein one motor operation state label corresponds to one motor operation state; The protection mechanism triggering behavior data refers to the condition group when the protection mechanism is triggered, and the condition group records the parameter calibration abnormality of the motor operation fed back by the motor end under each motor operating state; the parameter calibration refers to the intelligent adjustment of the various operating performances of the motor by the chip end under each motor operating state, and the parameter calibration abnormality refers to the error between the intelligently adjusted parameters and the standard parameters of each operating performance specified in the motor user manual, the percentage exceeding the preset error threshold, wherein when the error is lower than the preset error threshold, the parameter calibration abnormality is set to 0.
8. The motor intelligent monitoring system based on artificial intelligence according to claim 7 is characterized in that: The test data model module includes a data channel unit and a test unit; The data channel unit is used to configure a motor end interface for each motor operation status tag, so a total of K motor end interfaces are obtained, and any motor end interface is recorded as , x represents the number of the motor operation status label, and x≤K; Based on each protection mechanism processing unit inside the chip end, W chip end interface data collection clusters are constructed, wherein one protection mechanism processing unit corresponds to one chip end interface, so a total of W chip end interfaces are obtained, and one protection mechanism processing unit constructs one chip end interface data collection cluster; any chip end interface is recorded as , y represents the number of the protection mechanism processing unit, and y≤W; the chip end interface The corresponding chip-side interface data collection cluster is recorded as ,in, represents the calibration anomaly set of the ath condition group, A represents the total number of condition groups, and ,in, represents the parameter calibration abnormality corresponding to the rth operating performance, and R represents the total number of operating performances; Based on the motor end interface Chip-side interface , build a data connection channel, denoted as ; The test unit is used to construct a calibration abnormal behavior diagram analysis model, wherein the calibration abnormal behavior diagram is a regular polygon containing R sides, and each side of the regular polygon has a unique attribute of an operating performance, then the rth side of the regular polygon corresponds to the unique attribute of the rth operating performance; starting from the central symmetric point of the regular polygon, a vertical ray is drawn to each side, then a total of R vertical rays are obtained, and the length of the vertical ray is the parameter calibration abnormality corresponding to the operating performance under the unique attribute of the side; the end points of the R vertical rays are connected in sequence to form a test diagram, which is recorded as RC; Calibrate anomaly set The corresponding test graph is recorded as , get the test image The area of , and the area As the ath condition group, the chip side has the fault perception capability when a fault occurs on the motor side.
9. The motor intelligent monitoring system based on artificial intelligence according to claim 8, characterized in that: The historical evaluation of the fault perception capability includes: In the data connection channel In the above, based on the corresponding fault perception capability under each condition group, the fault perception stability of the chip end to the motor end is evaluated, and the fault perception stability value is calculated. The specific calculation formula is as follows: in, Indicates the chip end interface The corresponding protection mechanism processing unit is connected to the motor end interface The corresponding fault perception stability value of the motor operation state, V represents the expected value of fault perception stability.
10. The motor intelligent monitoring system based on artificial intelligence according to claim 9, characterized in that: The artificial intelligence prediction of the fault risk at the motor end includes: Based on the interaction between the chip-side interface and the motor-side interface, the artificial intelligence prediction value is calculated. The specific calculation formula is as follows: Among them, PV represents the artificial intelligence prediction value, SV represents the fault perception stability value threshold, if represents the judgment function, Indicates if the fault sensing stable value is less than or equal to the fault perception stability value threshold, then , otherwise let .
