Intelligent remote control monitoring system for alternating current servo motor

Abstract

The invention discloses an intelligent remote control monitoring system for an alternating current servo motor, and relates to the technical field of motor control and monitoring, and the system collects operation data in real time through an integrated sensor installed on the servo motor, and transmits the operation data to a remote monitoring database through a wireless network. Through preprocessing and storing data, a magnetic field intensity change coefficient Cbh, a torque fluctuation amplitude coefficient Nbd and a current harmonic component influence coefficient Dlx are calculated, a comprehensive fault index DGZ of the AC servo motor is calculated through a fault evaluation module, and the comprehensive fault index DGZ is compared with a preset AC servo motor fault threshold A for preliminary evaluation. And predicting the fault probability through historical data and real-time data logistic regression, and performing secondary evaluation with a preset fault prediction threshold value Z. A regulation and control instruction is generated according to the evaluation result and transmitted to the servo motor through a wireless network, and intelligent adjustment and remote control over the running state of the motor are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of motor control and monitoring, and in particular to an intelligent remote control and monitoring system for an AC servo motor. Background Art

[0002] In the field of modern industrial automation, AC servo motors have become one of the key components of industrial drive equipment. With the rapid development of industrial technology and the popularization of intelligent manufacturing, traditional manual operation and regular maintenance methods can no longer meet the needs of contemporary efficient production. In order to improve the stability of production equipment, reduce manual maintenance costs, and prevent sudden failures from interfering with the production process, intelligent remote control monitoring systems have gradually become an indispensable technical means.

[0003] Fault monitoring and control are important issues that need to be solved in the operation of AC servo motors. Traditional motor fault monitoring relies on manual regular maintenance and simple alarm systems. This method not only has a slow response speed, but also makes it difficult to detect potential hidden dangers in a timely manner, which may cause abnormal operation or even shutdown of the equipment. In addition, traditional methods lack intelligent analysis methods in diagnosing the cause of the fault, and it is not easy to conduct a comprehensive evaluation based on multi-dimensional data. Problems can only be judged through a single parameter alarm, which not only increases maintenance costs, but may also shorten the service life of the equipment, affecting production efficiency and equipment stability. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides an intelligent remote control monitoring system for an AC servo motor, which solves the problems in the above-mentioned background technology.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: an AC servo motor intelligent remote control monitoring system, including an operation data acquisition module, a database processing module, a data integration module, a fault assessment module, a comprehensive fault prediction module and a remote monitoring control module;

[0006] The operation data acquisition module collects the operation data of the AC servo motor in real time during operation through an integrated sensor group installed at each position of the AC servo motor, and transmits it to a remote monitoring database through a wireless network;

[0007] The database processing module is used to pre-process the operating data in the database, obtain the AC servo motor working data group, store the AC servo motor working data group in real time to the remote monitoring database, and extract the real-time AC servo motor working data group;

[0008] The data integration module is used to summarize and calculate the extracted real-time AC servo motor working data group to obtain the magnetic field intensity variation coefficient Cbh, the torque fluctuation amplitude coefficient Nbd and the current harmonic component influence coefficient Dlx;

[0009] The fault assessment module is used to perform summary calculation based on the obtained magnetic field intensity variation coefficient Cbh, torque fluctuation amplitude coefficient Nbd and current harmonic component influence coefficient Dlx, obtain the comprehensive fault index DGZ of the AC servo motor, and perform preliminary comparative evaluation with the preset AC servo motor fault threshold A, and start the second evaluation mechanism process based on the evaluation result;

[0010] The comprehensive fault prediction module is used to perform logistic regression through the historical operation data of the AC servo motor when the initial evaluation result is that the AC servo motor is operating normally, and combine it with the comprehensive fault index DGZ of the AC servo motor to predict the fault probability, construct the AC servo motor fault probability prediction index DJL, and perform a secondary deep prediction evaluation with the preset fault prediction threshold Z, and generate relevant control and early warning instructions based on the evaluation results;

[0011] The remote monitoring control module is used to compare and correct the unqualified data from the two assessments based on the historical normal data in the remote monitoring database, and generate control instructions from the corrected parameters and transmit them to the AC servo motor via a wireless network.

[0012] Preferably, the operation data acquisition module includes a data acquisition unit and a data transmission unit;

[0013] The data acquisition unit is used to collect the AC servo motor operation data of the AC servo motor in real time during operation through an integrated sensor group installed at various positions of the AC servo motor; the integrated sensor group includes a Hall effect sensor, a current sensor, a rotary encoder, a torque sensor, a voltage sensor and an acceleration sensor;

[0014] The data transmission unit transmits the AC servo motor operation data to the remote monitoring database in real time through the wireless network and the wired network.

[0015] Preferably, the database processing module includes a data preprocessing unit and a data storage unit;

[0016] The data preprocessing unit is used to receive the AC servo motor operation data transmitted by the data transmission unit in real time, and perform data cleaning, data fusion, real-time monitoring, noise filtering and normalization processing on the AC servo motor operation data to obtain the AC servo motor working data group;

[0017] The AC servo motor working data group includes a magnetic field intensity change influence data group, an AC servo motor torque data group and a current harmonic data group;

[0018] The magnetic field intensity change impact data group includes magnetic field intensity cq, current density dm and rotor angular velocity zj;

[0019] The AC servo motor torque data group includes output torque nj, moment of inertia gl and rotor angular acceleration zj;

[0020] The current harmonic data group includes the current harmonic amplitude dl, the fundamental frequency current jd, the voltage harmonic amplitude dy and the effective voltage value yd;

[0021] The data storage unit stores the AC servo motor working data group in real time in the real-time data storage library through a remote monitoring database which is divided into a real-time data storage library and a historical data storage library. When new data is stored in the real-time data storage library, the database will automatically transfer the previous set of data to the historical data storage library for storage.

[0022] Preferably, the data integration module includes a magnetic field strength calculation unit, a torque fluctuation amplitude calculation unit and a current harmonic component influence calculation unit;

[0023] The magnetic field strength calculation unit is used to perform summary calculation based on the acquired magnetic field strength change impact data group to obtain the magnetic field strength change coefficient Cbh;

[0024] The magnetic field intensity variation coefficient Cbh is calculated by the following formula:

[0025]

[0026] In the formula, T represents the total duration of the monitoring period, and dt represents the differential symbol in calculus;

[0027] The torque fluctuation amplitude calculation unit is used to perform summary calculation based on the acquired AC servo motor torque data group to obtain the torque fluctuation amplitude coefficient Nbd;

[0028] The torque fluctuation amplitude coefficient Nbd is calculated by the following formula:

[0029]

[0030] In the formula, max(nj) and min(nj) represent the upper and lower limits of the output torque nj respectively, and max(nj)-min(nj) represents the maximum fluctuation amplitude of the output torque nj;

[0031] Preferably, the current harmonic component influence calculation unit is used to perform summary calculation based on the acquired current harmonic data group to obtain the current harmonic component influence coefficient Dlx;

[0032] The current harmonic component influence coefficient Dlx is calculated and obtained by the following formula:

[0033]

[0034] In the formula, k represents the weight coefficient.

[0035] Preferably, the fault assessment module includes an AC servo motor fault calculation unit and an AC servo motor fault assessment unit;

[0036] The AC servo motor fault calculation unit is used to perform summary calculation based on the obtained magnetic field intensity variation coefficient Cbh, torque fluctuation amplitude coefficient Nbd and current harmonic component influence coefficient Dlx to obtain the comprehensive fault index DGZ of the AC servo motor;

[0037] The comprehensive fault index DGZ of the AC servo motor is calculated by the following formula:

[0038]

[0039] Wherein, w1, w2 and w3 represent the weight coefficients of the magnetic field intensity variation coefficient Cbh, the torque fluctuation amplitude coefficient Nbd and the current harmonic component influence coefficient Dlx respectively, and w1+w2+w3=1, and the specific value is set by the user according to the actual situation, and exp(-Cbh) represents the negative exponential function of the magnetic field intensity variation coefficient Cbh.

[0040] Preferably, the AC servo motor fault assessment unit presets the AC servo motor fault threshold value A, and performs preliminary comparative assessment with the acquired comprehensive fault index DGZ of the AC servo motor, and generates alarm information according to the assessment result. The specific assessment scheme is as follows;

[0041] When the comprehensive fault index DGZ of the AC servo motor is less than or equal to the preset AC servo motor fault threshold A, it indicates that the AC servo motor is operating normally and no adjustment is required, and the secondary evaluation mechanism is triggered;

[0042] When the comprehensive fault index DGZ of the AC servo motor is greater than the preset AC servo motor fault threshold A, it indicates that the AC servo motor is operating abnormally. At this time, the first warning information is triggered and transmitted to the remote monitoring control module for regulation.

[0043] Preferably, the comprehensive fault prediction module includes an AC servo motor fault prediction calculation unit and an AC servo motor hidden danger prediction and evaluation unit;

[0044] The AC servo motor fault prediction calculation unit is used to perform logistic regression based on the change rate of historical AC servo motor operation data and real-time monitoring data over time when the AC servo motor is initially evaluated to be operating normally, and to predict the fault probability in combination with the comprehensive fault index DGZ of the AC servo motor, so as to construct the AC servo motor fault probability prediction index DJL;

[0045]

[0046] Where β0 represents the intercept term, which indicates the predicted probability when all eigenvalues ​​are zero, and β1 represents the regression coefficient of the comprehensive fault index DGZ of the AC servo motor.

[0047] Preferably, the AC servo motor hidden danger prediction and evaluation unit is used to preset a fault prediction threshold Z, and then conduct a secondary comparative evaluation with the acquired AC servo motor fault probability prediction index DJL to further analyze and predict the fault hidden dangers of the AC servo motor. The specific evaluation scheme is as follows;

[0048] When the AC servo motor fault probability prediction index DJL ≤ the preset fault prediction threshold Z, it means that there is no hidden danger of fault in the AC servo motor and monitoring should be continued;

[0049] When the AC servo motor fault probability prediction index DJL> the preset fault prediction threshold Z, it indicates that the AC servo motor has a potential fault. At this time, the second warning information is triggered and transmitted to the remote monitoring control module for regulation.

[0050] Preferably, the remote monitoring control module includes an instruction generating unit and a remote control executing unit;

[0051] The instruction generation unit transmits the abnormal operation results of the AC servo motor generated by the initial evaluation and the secondary evaluation to the data storage unit, and marks the currently collected group of AC servo motor working data as fault data through the data storage unit, and then compares and corrects it with the average value of normal data that is not marked in the historical data, and further adjusts the control input value through the PID controller, generates the control instruction with the corrected parameter, and transmits it to the control unit of the AC servo motor through the wireless network;

[0052] The remote control execution unit receives control instructions in real time through the AC servo motor network communication interface, extracts target parameters and execution conditions of the control instructions, and converts the control instructions into execution signals through the programmable logic controller PLC. The actuator of the AC servo motor adjusts the operating state according to the received execution signal and monitors the operating state in real time through the integrated sensor group to generate feedback data.

[0053] The present invention provides an AC servo motor intelligent remote control monitoring system, which has the following beneficial effects:

[0054] (1) The system collects the motor's operating data in real time through an integrated sensor group and transmits it to a remote monitoring database through a wireless network. The data is preprocessed in the database to ensure accuracy and consistency, forming an effective data set. These data can not only reflect the current working status of the motor, but also calculate the magnetic field intensity variation coefficient Cbh, torque fluctuation amplitude coefficient Nbd and current harmonic component influence coefficient Dlx through the data integration module, which provides a solid foundation for further fault assessment and prediction.

[0055] (2) The system conducts a preliminary assessment of the motor's operating status through the fault assessment module, calculates the comprehensive fault index DGZ of the AC servo motor by integrating various coefficients, and makes a preliminary comparison with the preset AC servo motor fault threshold A. If DGZ exceeds the preset AC servo motor fault threshold A, the system will trigger an early warning, indicating that the motor is operating abnormally; if the index is within the normal range, the system will continue to execute the secondary assessment mechanism. By comprehensively evaluating the changing trends of historical data and current data, the system also predicts the motor's failure probability through a logistic regression model and generates a failure probability prediction index DJL, thereby making a more in-depth prediction of the motor's future operating status.

[0056] (3) When the system identifies that the motor may have a potential fault, the remote monitoring control module will automatically generate control instructions based on the fault assessment results and transmit these instructions to the motor control unit through the wireless network. The instruction generation module will correct the abnormal parameters based on the historical normal operation data and optimize the input control signal of the motor through the PID controller. The motor's actuator then adjusts the operating state based on these corrected parameters and feeds back real-time data through the sensor group to ensure that the system can effectively intervene before a fault occurs. Through this intelligent control and closed-loop feedback mechanism, the system realizes preventive maintenance and self-optimization of the motor, greatly improving the reliability and stability of the motor operation, while reducing downtime and maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 The present invention is a flow chart of an intelligent remote control monitoring system for an AC servo motor. DETAILED DESCRIPTION

[0058] 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.

[0059] Example 1

[0060] See also Figure 1 , the present invention provides an AC servo motor intelligent remote control monitoring system. To achieve the above purpose, the present invention is implemented through the following technical solutions: including an operation data acquisition module, a database processing module, a data integration module, a fault assessment module, a comprehensive fault prediction module and a remote monitoring control module;

[0061] The operation data acquisition module collects the operation data of the AC servo motor in real time during operation through an integrated sensor group installed at each position of the AC servo motor, and transmits it to a remote monitoring database through a wireless network;

[0062] The database processing module is used to pre-process the operating data in the database, obtain the AC servo motor working data group, store the AC servo motor working data group in real time to the remote monitoring database, and extract the real-time AC servo motor working data group;

[0063] The data integration module is used to summarize and calculate the extracted real-time AC servo motor working data group to obtain the magnetic field intensity variation coefficient Cbh, the torque fluctuation amplitude coefficient Nbd and the current harmonic component influence coefficient Dlx;

[0064] The fault assessment module is used to perform summary calculation based on the obtained magnetic field intensity variation coefficient Cbh, torque fluctuation amplitude coefficient Nbd and current harmonic component influence coefficient Dlx, obtain the comprehensive fault index DGZ of the AC servo motor, and perform preliminary comparative evaluation with the preset AC servo motor fault threshold A, and start the second evaluation mechanism process based on the evaluation result;

[0065] The comprehensive fault prediction module is used to perform logistic regression through the historical operation data of the AC servo motor when the initial evaluation result is that the AC servo motor is operating normally, and combine it with the comprehensive fault index DGZ of the AC servo motor to predict the fault probability, construct the AC servo motor fault probability prediction index DJL, and perform a secondary deep prediction evaluation with the preset fault prediction threshold Z, and generate relevant control and early warning instructions based on the evaluation results;

[0066] The remote monitoring control module is used to compare and correct the unqualified data from the two assessments based on the historical normal data in the remote monitoring database, and generate control instructions from the corrected parameters and transmit them to the AC servo motor via a wireless network.

[0067] In this embodiment, the operation data acquisition module relies on the integrated sensor group to collect key data of various parts of the motor in real time, ensure the immediacy and accuracy of the data during operation, and transmit it to the remote database through a wireless network. The database processing module cleans and merges these data to form a standardized motor working data group, improves the efficiency and reliability of data processing, and provides a solid data foundation for subsequent evaluation and prediction. The data integration module summarizes the real-time motor data, extracts the magnetic field intensity variation coefficient Cbh, the torque fluctuation amplitude coefficient Nbd and the current harmonic component influence coefficient Dlx, and can accurately evaluate the stability and health of the motor operation. The fault evaluation module calculates the comprehensive fault index DGZ of the AC servo motor based on these key coefficients, and compares it with the preset AC servo motor fault threshold A to form a preliminary evaluation result. When the motor runs normally, the system will trigger the comprehensive fault prediction module for in-depth evaluation, combining historical operation data and logistic regression algorithm to predict the probability of fault occurrence. This dual evaluation mechanism not only improves the fault detection accuracy of the system, but also enables the system to have fault prediction capabilities, thereby providing early warning before the fault occurs to avoid major losses. The remote monitoring and control module corrects abnormal parameters by comparing with historical normal data and generates control instructions to achieve automatic adjustment and control. The control instructions are transmitted to the motor control unit via a wireless network, and the motor is adaptively adjusted based on the feedback to ensure the continuous and stable operation of the system. Overall, this integrated and intelligent fault monitoring and control system significantly improves the stability of motor operation, the accuracy of fault warning, and the convenience of maintenance compared to traditional means. It not only reduces downtime, but also extends the service life of the motor, greatly improving the efficiency and safety of industrial production.

[0068] Example 2

[0069] This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically: the operation data acquisition module includes a data acquisition unit and a data transmission unit;

[0070] The data acquisition unit is used to collect the AC servo motor operation data of the AC servo motor in real time during operation through an integrated sensor group installed at various positions of the AC servo motor; the integrated sensor group includes a Hall effect sensor, a current sensor, a rotary encoder, a torque sensor, a voltage sensor and an acceleration sensor;

[0071] The data transmission unit transmits the AC servo motor operation data to the remote monitoring database in real time through the wireless network and the wired network.

[0072] The database processing module includes a data preprocessing unit and a data storage unit;

[0073] The data preprocessing unit is used to receive the AC servo motor operation data transmitted by the data transmission unit in real time, and perform data cleaning, data fusion, real-time monitoring, noise filtering and normalization processing on the AC servo motor operation data to obtain the AC servo motor working data group;

[0074] The AC servo motor working data group includes a magnetic field intensity change influence data group, an AC servo motor torque data group and a current harmonic data group;

[0075] The magnetic field intensity change impact data group includes magnetic field intensity cq, current density dm and rotor angular velocity zj;

[0076] The AC servo motor torque data group includes output torque nj, moment of inertia gl and rotor angular acceleration zj;

[0077] The current harmonic data group includes the current harmonic amplitude dl, the fundamental frequency current jd, the voltage harmonic amplitude dy and the effective voltage value yd;

[0078] The data storage unit stores the AC servo motor working data group in real time in the real-time data storage library through a remote monitoring database which is divided into a real-time data storage library and a historical data storage library. When new data is stored in the real-time data storage library, the database will automatically transfer the previous set of data to the historical data storage library for storage.

[0079] In this embodiment, through the precise design of the operation data acquisition module and the database processing module, all-round real-time monitoring of the operating status of the AC servo motor is realized. The data acquisition unit relies on a variety of high-precision sensors to accurately collect the operating parameters of the motor during operation. The collection of this multi-dimensional data ensures a comprehensive grasp of the complex working conditions of the motor. The data transmission unit uses wireless and wired networks to achieve instant data transmission, ensuring that the system can be remotely monitored in real time. The database processing module uses advanced data preprocessing technologies such as data cleaning, normalization and noise filtering to not only improve the accuracy and reliability of the data, but also automatically archive and manage real-time data and historical data, providing a rich reference basis for subsequent analysis and prediction. Overall, this integrated design of data acquisition, transmission and processing significantly improves data quality, real-time performance and system monitoring depth, reduces the blind spots of equipment failures, and lays a solid foundation for fault prediction and early warning.

[0080] Example 3

[0081] This embodiment is explained in Example 2. Please refer to Figure 1 , specifically: the data integration module includes a magnetic field strength calculation unit, a torque fluctuation amplitude calculation unit and a current harmonic component influence calculation unit;

[0082] The magnetic field strength calculation unit is used to perform summary calculation based on the acquired magnetic field strength change impact data group to obtain the magnetic field strength change coefficient Cbh;

[0083] The magnetic field intensity variation coefficient Cbh is calculated by the following formula:

[0084]

[0085] In the formula, T represents the total duration of the monitoring period, and dt represents the differential symbol in calculus;

[0086] The torque fluctuation amplitude calculation unit is used to perform summary calculation based on the acquired AC servo motor torque data group to obtain the torque fluctuation amplitude coefficient Nbd;

[0087] The torque fluctuation amplitude coefficient Nbd is calculated by the following formula:

[0088]

[0089] In the formula, max(nj) and min(nj) represent the upper and lower limits of the output torque nj respectively, and max(nj)-min(nj) represents the maximum fluctuation amplitude of the output torque nj;

[0090] The current harmonic component influence calculation unit is used to perform summary calculation based on the acquired current harmonic data group to obtain the current harmonic component influence coefficient Dlx;

[0091] The current harmonic component influence coefficient Dlx is calculated and obtained by the following formula:

[0092]

[0093] In the formula, k represents the weight coefficient.

[0094] In this embodiment, the data integration module calculates the magnetic field intensity variation coefficient Cbh, the torque fluctuation amplitude coefficient Nbd and the current harmonic component influence coefficient Dlx respectively through the magnetic field intensity calculation unit, the torque fluctuation amplitude calculation unit and the current harmonic component influence calculation unit. This refined sub-module calculation method has a high degree of accuracy and can more comprehensively reflect the changes in various core parameters of the AC servo motor during operation. Through the separate calculation of magnetic field intensity, torque fluctuation and current harmonics, the system can quickly identify any abnormal fluctuations or potential problems, and conduct accurate fault assessment and early warning based on this. This modular design not only improves the system's sensitivity to different types of motor failures, but also improves the overall intelligence of operation monitoring by summarizing and analyzing these key data, so that the operating status of the motor can be monitored and controlled in real time and accurately, thereby greatly reducing unexpected downtime and maintenance costs.

[0095] Example 4

[0096] This embodiment is explained in Example 3, please refer to Figure 1 ,Specifically: the fault assessment module includes an AC servo motor fault calculation unit and an AC servo motor fault assessment unit;

[0097] The AC servo motor fault calculation unit is used to perform summary calculation based on the obtained magnetic field intensity variation coefficient Cbh, torque fluctuation amplitude coefficient Nbd and current harmonic component influence coefficient Dlx to obtain the comprehensive fault index DGZ of the AC servo motor;

[0098] The comprehensive fault index DGZ of the AC servo motor is calculated by the following formula:

[0099]

[0100] Wherein, w1, w2 and w3 represent the weight coefficients of the magnetic field intensity variation coefficient Cbh, the torque fluctuation amplitude coefficient Nbd and the current harmonic component influence coefficient Dlx respectively, and w1+w2+w3=1, and the specific value is set by the user according to the actual situation, and exp(-Cbh) represents the negative exponential function of the magnetic field intensity variation coefficient Cbh.

[0101] The AC servo motor fault assessment unit performs a preliminary comparative assessment by presetting the AC servo motor fault threshold value A and the obtained comprehensive fault index DGZ of the AC servo motor, and generates alarm information according to the assessment result. The specific assessment scheme is as follows;

[0102] When the comprehensive fault index DGZ of the AC servo motor is less than or equal to the preset AC servo motor fault threshold A, it indicates that the AC servo motor is operating normally and no adjustment is required, and the secondary evaluation mechanism is triggered;

[0103] When the comprehensive fault index DGZ of the AC servo motor is greater than the preset AC servo motor fault threshold A, it indicates that the AC servo motor is operating abnormally. At this time, the first warning information is triggered and transmitted to the remote monitoring control module for regulation.

[0104] In this embodiment, the operating status of the AC servo motor can be accurately monitored and evaluated in real time, and the magnetic field strength variation coefficient Cbh, the torque fluctuation amplitude coefficient Nbd and the current harmonic component influence coefficient Dlx are summarized by the fault calculation unit to obtain the comprehensive fault index DGZ. This index is combined with the weight coefficient set by the user, and the evaluation model can be flexibly adjusted to adapt to different operating conditions. By comparing the comprehensive fault index DGZ with the preset AC servo motor fault threshold A, the system can detect whether the motor has a potential fault in time. When the comprehensive fault index DGZ exceeds the preset threshold, the system automatically triggers an early warning, responds quickly and transmits it to the remote monitoring module for regulation. This mechanism not only realizes efficient fault detection and early warning, but also ensures that the system can intervene in time before potential problems develop into serious faults, reducing downtime and maintenance costs, and significantly improving the operational safety and stability of the motor system.

[0105] Example 5

[0106] This embodiment is explained in Example 4. Please refer to Figure 1 , specifically: the comprehensive fault prediction module includes an AC servo motor fault prediction calculation unit and an AC servo motor hidden danger prediction and evaluation unit;

[0107] The AC servo motor fault prediction calculation unit is used to perform logistic regression based on the change rate of historical AC servo motor operation data and real-time monitoring data over time when the AC servo motor is initially evaluated to be operating normally, and to predict the fault probability in combination with the comprehensive fault index DGZ of the AC servo motor, so as to construct the AC servo motor fault probability prediction index DJL;

[0108]

[0109] Where β0 represents the intercept term, which indicates the predicted probability when all eigenvalues ​​are zero, and β1 represents the regression coefficient of the comprehensive fault index DGZ of the AC servo motor.

[0110] The AC servo motor hidden danger prediction and evaluation unit is used to preset a fault prediction threshold Z, and then conduct a secondary comparative evaluation with the acquired AC servo motor fault probability prediction index DJL to further analyze and predict the fault hidden dangers of the AC servo motor. The specific evaluation scheme is as follows;

[0111] When the AC servo motor fault probability prediction index DJL ≤ the preset fault prediction threshold Z, it means that there is no hidden danger of fault in the AC servo motor and monitoring should be continued;

[0112] When the AC servo motor fault probability prediction index DJL> the preset fault prediction threshold Z, it indicates that the AC servo motor has a potential fault. At this time, the second warning information is triggered and transmitted to the remote monitoring control module for regulation.

[0113] In this embodiment, the comprehensive fault prediction module constructs the AC servo motor fault probability prediction index DJL using a logistic regression model by combining historical data and real-time monitoring data. The core advantage of this module lies in its dual evaluation mechanism: first, the relationship between the motor comprehensive fault index DGZ and historical operation data is analyzed through logistic regression to accurately predict the potential fault probability. Secondly, by comparing the prediction index DJL with the preset fault prediction threshold Z for a second time, the system can deeply evaluate the potential fault hazards of the motor. When the AC servo motor fault probability prediction index DJL exceeds the preset fault prediction threshold Z, the system can trigger the second-level warning in time and generate corresponding control instructions. This method not only improves the accuracy of fault prediction, but also ensures early warning of motor hidden dangers, thereby significantly reducing the risk of faults, improving the operating reliability and maintenance efficiency of the motor, and providing a strong guarantee for the stable operation of industrial equipment.

[0114] Example 6

[0115] This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically: the remote monitoring control module includes an instruction generating unit and a remote control executing unit;

[0116] The instruction generation unit transmits the abnormal operation results of the AC servo motor generated by the initial evaluation and the secondary evaluation to the data storage unit, and marks the currently collected group of AC servo motor working data as fault data through the data storage unit, and then compares and corrects it with the average value of normal data that is not marked in the historical data, and further adjusts the control input value through the PID controller, generates the control instruction with the corrected parameter, and transmits it to the control unit of the AC servo motor through the wireless network;

[0117] The remote control execution unit receives control instructions in real time through the AC servo motor network communication interface, extracts target parameters and execution conditions of the control instructions, and converts the control instructions into execution signals through the programmable logic controller PLC. The actuator of the AC servo motor adjusts the operating state according to the received execution signal and monitors the operating state in real time through the integrated sensor group to generate feedback data.

[0118] In this embodiment, through the instruction generation unit and remote control execution unit of the remote monitoring control module, the AC servo motor intelligent monitoring system realizes accurate fault correction and adaptive control. Based on the initial and secondary evaluations, the instruction generation unit optimizes the control input value using the PID controller by marking the fault data and comparing and correcting it with the normal data, thereby generating accurate control instructions. These instructions are transmitted to the motor control unit via a wireless network to ensure the real-time and effectiveness of the adjustment. The remote control execution unit converts the control instructions into execution signals through the PLC, adjusts the operating status of the motor in real time, and monitors the feedback data through the integrated sensor group. This refined control not only improves the system's ability to adjust the motor's operating status, but also significantly improves the rapidity of fault response and the accuracy of repair, ensuring the stable operation of the motor and maximizing production efficiency.

[0119] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An AC servo motor intelligent remote control monitoring system, characterized in that: It includes operation data acquisition module, database processing module, data integration module, fault assessment module, comprehensive fault prediction module and remote monitoring and control module; The operation data acquisition module collects the operation data of the AC servo motor in real time during operation through an integrated sensor group installed at each position of the AC servo motor, and transmits it to a remote monitoring database through a wireless network; The database processing module is used to pre-process the operating data in the database, obtain the AC servo motor working data group, store the AC servo motor working data group in real time to the remote monitoring database, and extract the real-time AC servo motor working data group; The data integration module is used to summarize and calculate the extracted real-time AC servo motor working data group to obtain the magnetic field intensity variation coefficient Cbh, the torque fluctuation amplitude coefficient Nbd and the current harmonic component influence coefficient Dlx; The fault assessment module is used to perform summary calculation based on the obtained magnetic field intensity variation coefficient Cbh, torque fluctuation amplitude coefficient Nbd and current harmonic component influence coefficient Dlx, obtain the comprehensive fault index DGZ of the AC servo motor, and perform preliminary comparative evaluation with the preset AC servo motor fault threshold A, and start the second evaluation mechanism process based on the evaluation result; The comprehensive fault prediction module is used to perform logistic regression through the historical operation data of the AC servo motor when the initial evaluation result is that the AC servo motor is operating normally, and combine it with the comprehensive fault index DGZ of the AC servo motor to predict the fault probability, construct the AC servo motor fault probability prediction index DJL, and perform a secondary deep prediction evaluation with the preset fault prediction threshold Z, and generate relevant control and early warning instructions based on the evaluation results; The remote monitoring control module is used to compare and correct the unqualified data from the two assessments based on the historical normal data in the remote monitoring database, and generate control instructions from the corrected parameters and transmit them to the AC servo motor via a wireless network.

2. The intelligent remote control monitoring system for AC servo motor according to claim 1, characterized in that: The operation data acquisition module includes a data acquisition unit and a data transmission unit; The data acquisition unit is used to collect the AC servo motor operation data of the AC servo motor in real time during operation through an integrated sensor group installed at various positions of the AC servo motor; the integrated sensor group includes a Hall effect sensor, a current sensor, a rotary encoder, a torque sensor, a voltage sensor and an acceleration sensor; The data transmission unit transmits the AC servo motor operation data to the remote monitoring database in real time through the wireless network and the wired network.

3. The intelligent remote control monitoring system for AC servo motor according to claim 2, characterized in that: The database processing module includes a data preprocessing unit and a data storage unit; The data preprocessing unit is used to receive the AC servo motor operation data transmitted by the data transmission unit in real time, and perform data cleaning, data fusion, real-time monitoring, noise filtering and normalization processing on the AC servo motor operation data to obtain the AC servo motor working data group; The AC servo motor working data group includes a magnetic field intensity change influence data group, an AC servo motor torque data group and a current harmonic data group; The magnetic field intensity change impact data group includes magnetic field intensity cq, current density dm and rotor angular velocity zj; The AC servo motor torque data group includes output torque nj, moment of inertia gl and rotor angular acceleration zj; The current harmonic data group includes the current harmonic amplitude dl, the fundamental frequency current jd, the voltage harmonic amplitude dy and the effective voltage value yd; The data storage unit stores the AC servo motor working data group in real time in the real-time data storage library through a remote monitoring database which is divided into a real-time data storage library and a historical data storage library. When new data is stored in the real-time data storage library, the database will automatically transfer the previous set of data to the historical data storage library for storage.

4. The intelligent remote control monitoring system for AC servo motor according to claim 3 is characterized in that: The data integration module includes a magnetic field intensity calculation unit, a torque fluctuation amplitude calculation unit and a current harmonic component influence calculation unit; The magnetic field strength calculation unit is used to perform summary calculation based on the acquired magnetic field strength change impact data group to obtain the magnetic field strength change coefficient Cbh; The magnetic field intensity variation coefficient Cbh is calculated by the following formula: In the formula, T represents the total duration of the monitoring period, and dt represents the differential symbol in calculus; The torque fluctuation amplitude calculation unit is used to perform summary calculation based on the acquired AC servo motor torque data group to obtain the torque fluctuation amplitude coefficient Nbd; The torque fluctuation amplitude coefficient Nbd is calculated and obtained by the following formula: Wherein, max(nj) and min(nj) represent the upper limit and lower limit of the output torque nj respectively, and max(nj)-min(nj) represents the maximum fluctuation amplitude of the output torque nj.

5. The intelligent remote control monitoring system for AC servo motor according to claim 4, characterized in that: The current harmonic component influence calculation unit is used to perform summary calculation based on the acquired current harmonic data group to obtain the current harmonic component influence coefficient Dlx; The current harmonic component influence coefficient Dlx is calculated and obtained by the following formula: In the formula, k represents the weight coefficient.

6. The intelligent remote control monitoring system for AC servo motor according to claim 5, characterized in that: The fault assessment module includes an AC servo motor fault calculation unit and an AC servo motor fault assessment unit; The AC servo motor fault calculation unit is used to perform summary calculation based on the obtained magnetic field intensity variation coefficient Cbh, torque fluctuation amplitude coefficient Nbd and current harmonic component influence coefficient Dlx to obtain the comprehensive fault index DGZ of the AC servo motor; The comprehensive fault index DGZ of the AC servo motor is calculated by the following formula: Wherein, w1, w2 and w3 represent the weight coefficients of the magnetic field intensity variation coefficient Cbh, the torque fluctuation amplitude coefficient Nbd and the current harmonic component influence coefficient Dlx respectively, and w1+w2+w3=1, and the specific value is set by the user according to the actual situation, and exp(-Cbh) represents the negative exponential function of the magnetic field intensity variation coefficient Cbh.

7. The intelligent remote control monitoring system for AC servo motor according to claim 6, characterized in that: The AC servo motor fault assessment unit performs a preliminary comparative assessment by presetting the AC servo motor fault threshold value A and the obtained comprehensive fault index DGZ of the AC servo motor, and generates alarm information according to the assessment result. The specific assessment scheme is as follows; When the comprehensive fault index DGZ of the AC servo motor is less than or equal to the preset AC servo motor fault threshold A, it indicates that the AC servo motor is operating normally and no adjustment is required, and the secondary evaluation mechanism is triggered; When the comprehensive fault index DGZ of the AC servo motor is greater than the preset AC servo motor fault threshold A, it indicates that the AC servo motor is operating abnormally. At this time, the first warning information is triggered and transmitted to the remote monitoring control module for regulation.

8. The intelligent remote control monitoring system for AC servo motor according to claim 7, characterized in that: The comprehensive fault prediction module includes an AC servo motor fault prediction calculation unit and an AC servo motor hidden danger prediction and evaluation unit; The AC servo motor fault prediction calculation unit is used to perform logistic regression based on the change rate of historical AC servo motor operation data and real-time monitoring data over time when the AC servo motor is initially evaluated to be operating normally, and to predict the fault probability in combination with the comprehensive fault index DGZ of the AC servo motor, so as to construct the AC servo motor fault probability prediction index DJL; Where β0 represents the intercept term, which indicates the predicted probability when all eigenvalues ​​are zero, and β1 represents the regression coefficient of the comprehensive fault index DGZ of the AC servo motor.

9. The intelligent remote control monitoring system for AC servo motor according to claim 8, characterized in that: The AC servo motor hidden danger prediction and evaluation unit is used to preset a fault prediction threshold Z, and then conduct a secondary comparative evaluation with the acquired AC servo motor fault probability prediction index DJL to further analyze and predict the fault hidden dangers of the AC servo motor. The specific evaluation scheme is as follows; When the AC servo motor fault probability prediction index DJL ≤ the preset fault prediction threshold Z, it means that there is no hidden danger of fault in the AC servo motor and monitoring should be continued; When the AC servo motor fault probability prediction index DJL> the preset fault prediction threshold Z, it indicates that the AC servo motor has a potential fault. At this time, the second warning information is triggered and transmitted to the remote monitoring control module for regulation.

10. The intelligent remote control monitoring system for AC servo motor according to claim 9, characterized in that: The remote monitoring control module includes an instruction generation unit and a remote control execution unit; The instruction generation unit transmits the abnormal operation results of the AC servo motor generated by the initial evaluation and the secondary evaluation to the data storage unit, and marks the currently collected group of AC servo motor working data as fault data through the data storage unit, and then compares and corrects it with the average value of normal data that is not marked in the historical data, and further adjusts the control input value through the PID controller, generates the control instruction with the corrected parameter, and transmits it to the control unit of the AC servo motor through the wireless network; The remote control execution unit receives control instructions in real time through the AC servo motor network communication interface, extracts target parameters and execution conditions of the control instructions, and converts the control instructions into execution signals through the programmable logic controller PLC. The actuator of the AC servo motor adjusts the operating state according to the received execution signal and monitors the operating state in real time through the integrated sensor group to generate feedback data.

Images