Real-time monitoring and early warning method and system for variable-frequency energy-saving motor

Abstract

The invention discloses a real-time monitoring and early warning method and system for a variable-frequency energy-saving motor, and the method comprises the steps: collecting the operation parameters of the motor in real time through a multi-source sensor group disposed on the variable-frequency energy-saving motor; determining a current motor working condition according to the motor operation parameters, and determining a real-time load rate of the motor based on a preset load working condition correlation model; acquiring historical operation data of the variable-frequency energy-saving motor, and generating a dynamic threshold curve according to the historical operation data; generating a dynamic threshold according to the motor operation parameters and the dynamic threshold curve, performing health degree calculation on the variable-frequency energy-saving motor based on the dynamic threshold, and determining a life prediction value of the variable-frequency energy-saving motor according to the health degree; and when the life prediction value of the variable-frequency energy-saving motor is lower than a preset value, automatically triggering a frequency reduction instruction, switching to a field-oriented vector control mode, and synchronously generating an alarm and equipment health file of the variable-frequency energy-saving motor.

Description

Technical Field

[0001] The present invention relates to the technical field of motor monitoring and early warning, and particularly to a real-time monitoring and early warning method and system for a variable-frequency energy-saving motor. Background Art

[0002] A variable-frequency energy-saving motor is a motor system that adjusts the power frequency input to the motor through an inverter to control the motor speed and power. It usually combines an efficient motor design and advanced variable-frequency control technology, and can achieve energy-saving operation under different load conditions.

[0003] However, some current systems of variable-frequency energy-saving motors rely on periodic data collection (such as mean value calculation per unit time), unable to achieve millisecond-level response, and may miss transient faults. At the same time, most systems use static threshold values to judge abnormalities, making it difficult to adapt to complex working condition changes, and prone to false alarms or missed alarms. There are defects in terms of real-time performance, compatibility, algorithm accuracy, and closed-loop control, and the real-time performance and accuracy of the monitoring and early warning of variable-frequency energy-saving motors cannot be guaranteed. Summary of the Invention

[0004] The present invention provides a real-time monitoring and early warning method and system for a variable-frequency energy-saving motor to solve the technical problems that in the prior art, variable-frequency energy-saving motors have defects in terms of real-time performance, compatibility, algorithm accuracy, and closed-loop control, and the real-time performance and accuracy of the monitoring and early warning of variable-frequency energy-saving motors cannot be guaranteed.

[0005] To solve the above technical problems, an embodiment of the present invention provides a real-time monitoring and early warning method for a variable-frequency energy-saving motor, including:

[0006] Real-time collecting motor operation parameters through a multi-source sensor group configured on the variable-frequency energy-saving motor;

[0007] Determining the current motor working condition according to the motor operation parameters, and determining the real-time load rate of the motor based on a preset load working condition association model;

[0008] Obtaining the historical operation data of the variable-frequency energy-saving motor, and generating a dynamic threshold curve according to the historical operation data;

[0009] Generating a dynamic threshold according to the motor operation parameters and the dynamic threshold curve, calculating the health degree of the variable-frequency energy-saving motor based on the dynamic threshold, and determining the life prediction value of the variable-frequency energy-saving motor according to the health degree;

[0010] When the life prediction value of the variable-frequency energy-saving motor is lower than a preset threshold value, automatically triggering a frequency reduction instruction and switching to a field-oriented vector control mode, and simultaneously generating an alarm and an equipment health record for the variable-frequency energy-saving motor.

[0011] As a preferred solution, the multi-source sensor group configured on the variable-frequency energy-saving motor is used to collect the motor operation parameters in real time, specifically including:

[0012] The first temperature sensor arranged inside the stator winding of the variable-frequency energy-saving motor is used to collect the stator winding temperature;

[0013] The current sensor arranged on the variable-frequency energy-saving motor is used to collect the three-phase current of the variable-frequency energy-saving motor, and the harmonic distortion rate is calculated according to the three-phase current;

[0014] The vibration acceleration sensor arranged on the bearing of the variable-frequency energy-saving motor is used to collect the bearing vibration acceleration of the variable-frequency energy-saving motor;

[0015] The magnetic flux sensor arranged on the variable-frequency energy-saving motor is used to collect the magnetic flux density inside the variable-frequency energy-saving motor;

[0016] The second temperature sensor arranged at the inlet and outlet of the cooling system in the variable-frequency energy-saving motor is used to measure the temperature of the cooling medium, and calculate the temperature difference when the measured cooling medium passes through the inlet and outlet;

[0017] Among them, the multi-source sensor group includes: the first temperature sensor, the second temperature sensor, the current sensor, the vibration acceleration sensor and the magnetic flux sensor, and the motor operation parameters include: the stator winding temperature, the three-phase current harmonic distortion rate, the bearing vibration acceleration, the magnetic flux density value and the temperature difference between the inlet and outlet of the cooling system.

[0018] As a preferred solution, according to the motor operation parameters, the current motor working condition is determined, and based on the preset load working condition association model, the real-time load rate of the motor is determined, specifically including:

[0019] The stator winding temperature, the three-phase current harmonic distortion rate, the bearing vibration acceleration, the magnetic flux density value and the temperature difference between the inlet and outlet of the cooling system are comprehensively analyzed, and according to the preset motor operation state model, the current motor working condition is determined; among them, the current motor working condition includes: normal working condition, abnormal working condition, special working condition, fault working condition and protection working condition, and the motor operation state model is trained by combining historical motor operation parameters and historical motor working conditions;

[0020] The current motor working condition in the normal working condition, abnormal working condition, special working condition, fault working condition or protection working condition is input into the preset load working condition association model to determine the real-time load rate of the motor.

[0021] As a preferred solution, the construction method of the preset load working condition association model includes:

[0022] Collect historical load-related time-series data and its corresponding working condition parameters;

[0023] Calculate the rolling mean and standard deviation of the time-series data related to the historical load within a sliding window, and combine the lag terms of the historical load to determine the operating condition correlation characteristics between the time-series data related to the historical load and its corresponding operating condition parameters;

[0024] Construct an initial LSTM model, determine the adaptive learning rate and regularization, and train the initial LSTM model through the operating condition correlation characteristics until the preset number of iterations and preset termination conditions are reached, and then generate a preset load-operating condition correlation model.

[0025] As a preferred solution, the method for obtaining the historical operation data of the variable-frequency energy-saving motor and generating a dynamic threshold curve based on the historical operation data specifically includes:

[0026] Obtain the historical operation data of the variable-frequency energy-saving motor; wherein, the historical operation data includes historical load rate, temperature parameter time-series data, vibration parameter time-series data, current parameter time-series data, and magnetic flux parameter time-series data;

[0027] Divide the temperature parameter time-series data, vibration parameter time-series data, current parameter time-series data, and magnetic flux parameter time-series data according to the interval of the historical load rate;

[0028] Construct a historical load rate sequence based on the historical load rate, and obtain the historical temperature threshold, historical vibration threshold, historical harmonic threshold, and historical magnetic flux threshold;

[0029] Generate a dynamic threshold curve according to the historical temperature threshold, historical vibration threshold, historical harmonic threshold, and historical magnetic flux threshold, combined with the historical load rate sequence, and the divided temperature parameter time-series data, vibration parameter time-series data, current parameter time-series data, and magnetic flux parameter time-series data.

[0030] As a preferred solution, the method for generating a dynamic threshold according to the motor operation parameters and the dynamic threshold curve, calculating the health degree of the variable-frequency energy-saving motor based on the dynamic threshold, and determining the life prediction value of the variable-frequency energy-saving motor according to the health degree specifically includes:

[0031] Input the motor operation parameters into the dynamic threshold curve to generate current real-time dynamic thresholds corresponding to the stator winding temperature, three-phase current harmonic distortion rate, bearing vibration acceleration, magnetic flux density value, and cooling system inlet and outlet temperature difference; wherein, the dynamic threshold includes a dynamic temperature threshold, a dynamic vibration threshold, a dynamic harmonic threshold, and a dynamic magnetic flux threshold;

[0032] Compare the stator winding temperature and the temperature difference between the inlet and outlet of the cooling system with the dynamic temperature thresholds respectively, and calculate the first health degree according to the differences between the stator winding temperature and the temperature difference between the inlet and outlet of the cooling system and the dynamic temperature thresholds;

[0033] Compare the harmonic distortion rate of the three-phase current with the dynamic harmonic threshold, and calculate the second health degree according to the difference between the harmonic distortion rate of the three-phase current and the dynamic harmonic threshold;

[0034] Compare the bearing vibration acceleration with the dynamic vibration threshold, and calculate the third health degree according to the difference between the bearing vibration acceleration and the dynamic vibration threshold;

[0035] Compare the magnetic flux density value with the dynamic vibration magnetic flux, and calculate the fourth health degree according to the difference between the magnetic flux density value and the dynamic magnetic flux threshold;

[0036] Determine the life prediction value of the variable-frequency energy-saving motor according to the first health degree, the second health degree, the third health degree and the fourth health degree, in combination with the preset health weight coefficient.

[0037] As a preferred solution, it further includes:

[0038] When the life prediction value of the variable-frequency energy-saving motor is not lower than the preset threshold value, record the current motor operation parameters of the variable-frequency energy-saving motor in real time, and record the corresponding life prediction value in the equipment health file.

[0039] Correspondingly, the present invention also provides a real-time monitoring and early warning system for a variable-frequency energy-saving motor, including:

[0040] An acquisition module, configured to collect motor operation parameters in real time through a multi-source sensor group configured on the variable-frequency energy-saving motor;

[0041] A load module, configured to determine the current motor working condition according to the motor operation parameters, and determine the real-time motor load rate based on a preset load working condition association model;

[0042] A threshold module, configured to obtain the historical operation data of the variable-frequency energy-saving motor, and generate a dynamic threshold curve according to the real-time motor load rate and the historical operation data;

[0043] A prediction module, configured to calculate the health degree of the variable-frequency energy-saving motor according to the motor operation parameters and the dynamic threshold curve, and determine the life prediction value of the variable-frequency energy-saving motor according to the health degree;

[0044] A control module, configured to automatically trigger a frequency reduction command and switch to a field-oriented vector control mode when the life prediction value of the variable-frequency energy-saving motor is lower than the preset threshold value, and simultaneously generate an alarm and an equipment health file for the variable-frequency energy-saving motor.

[0045] Correspondingly, the present invention further provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, the real-time monitoring and early warning method for the variable-frequency energy-saving motor described in any one of the above is implemented.

[0046] Correspondingly, the present invention further provides a computer-readable storage medium. The computer-readable storage medium includes a stored computer program. When the computer program runs, the device where the computer-readable storage medium is located is controlled to execute the real-time monitoring and early warning method for the variable-frequency energy-saving motor described in any one of the above.

[0047] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0048] The technical solution of the present invention uses a multi-source sensor group configured on the variable-frequency energy-saving motor to collect the motor operation parameters in real time, and then determines the real-time load rate of the motor. A dynamic threshold curve is generated based on the historical operation data of the variable-frequency energy-saving motor, so as to determine the current dynamic threshold of the variable-frequency energy-saving motor, ensuring that the variable-frequency energy-saving motor can evaluate and predict the current variable-frequency energy-saving motor in real time, thereby improving the accuracy and efficiency of real-time monitoring and early warning. Finally, the life prediction value of the variable-frequency energy-saving motor is determined. When the life prediction value of the variable-frequency energy-saving motor is lower than the preset threshold, a frequency reduction instruction is automatically triggered and switched to the field-oriented vector control mode to ensure that the variable-frequency energy-saving motor can perform post-warning control, ensuring the closed-loop control of the overall motor process. At the same time, an alarm and a device health file for the variable-frequency energy-saving motor are generated synchronously to ensure its compatibility for alarm and query on other platforms, improving the overall reliability of the variable-frequency energy-saving motor. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 : is a flowchart of a real-time monitoring and early warning method for a variable-frequency energy-saving motor provided by an embodiment of the present invention;

[0050] Figure 2 : is a structural diagram of a real-time monitoring and early warning system for a variable-frequency energy-saving motor provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0051] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0052] Embodiment 1

[0053] Please refer to Figure 1 , a real-time monitoring and early warning method for a variable-frequency energy-saving motor provided by an embodiment of the present invention, including the following steps S101-S105:

[0054] S101: Real-time collect the motor operation parameters through a multi-source sensor group configured on the variable-frequency energy-saving motor.

[0055] As a preferred solution of this embodiment, the real-time collection of the motor operation parameters through a multi-source sensor group configured on the variable-frequency energy-saving motor specifically includes:

[0056] Collect the stator winding temperature through a first temperature sensor arranged inside the stator winding of the variable-frequency energy-saving motor;

[0057] Collect the three-phase current of the variable-frequency energy-saving motor through a current sensor arranged on the variable-frequency energy-saving motor, and calculate the harmonic distortion rate according to the three-phase current;

[0058] Collect the bearing vibration acceleration of the variable-frequency energy-saving motor through a vibration acceleration sensor arranged on the bearing of the variable-frequency energy-saving motor;

[0059] Collect the magnetic flux density inside the variable-frequency energy-saving motor through a magnetic flux sensor arranged on the variable-frequency energy-saving motor;

[0060] Measure the temperature of the cooling medium through a second temperature sensor arranged at the inlet and outlet of the cooling system in the variable-frequency energy-saving motor, and calculate the temperature difference when the measured cooling medium passes through the inlet and outlet;

[0061] Among them, the multi-source sensor group includes: a first temperature sensor, a second temperature sensor, a current sensor, a vibration acceleration sensor and a magnetic flux sensor, and the motor operation parameters include: stator winding temperature, three-phase current harmonic distortion rate, bearing vibration acceleration, magnetic flux density value and cooling system inlet and outlet temperature difference.

[0062] In this embodiment, the multi-source sensor group comprehensively collects various operating parameters of the motor, including the stator winding temperature, the three-phase current harmonic distortion rate, the bearing vibration acceleration, the magnetic flux density value, and the temperature difference between the inlet and outlet of the cooling system. Specifically, the first temperature sensor, such as a PT100 platinum resistance temperature sensor, can collect the temperature data of the stator winding in real time, convert the collected temperature signal into an electrical signal, and transmit it to the monitoring system. The current sensor, including but not limited to a Hall current sensor, is installed on the three-phase power line of the variable-frequency energy-saving motor to collect the three-phase current data in real time, convert the collected three-phase current signal into a digital signal, and calculate the harmonic distortion rate of the three-phase current through algorithms such as Fourier transform. The vibration acceleration sensor, which can be a piezoelectric acceleration sensor, etc., is installed on the bearing seat of the variable-frequency energy-saving motor to collect the vibration acceleration data of the bearing in real time, convert the vibration acceleration signal into a digital signal, and perform spectrum analysis. The magnetic flux sensor, such as a Hall effect sensor, is installed near the stator core or air gap of the variable-frequency energy-saving motor to collect the magnetic flux density inside the motor in real time, convert the magnetic flux density signal into a digital signal, and transmit it to the monitoring system. The second temperature sensor, which can be a thermal resistance temperature sensor, is installed at the inlet and outlet of the cooling system respectively to measure the inlet and outlet temperatures of the cooling medium in real time and calculate the temperature difference between the inlet and outlet of the cooling medium.

[0063] In this embodiment, through the multi-source sensor monitoring scheme, the operating state of the variable-frequency energy-saving motor can be comprehensively and real-time monitored and evaluated, providing a strong guarantee for the safe and efficient operation of the motor. And the real-time monitoring data can timely detect abnormal changes in the motor operation, such as abnormal temperature rise, increased vibration acceleration, increased harmonic distortion rate, etc., so as to realize early warning of faults.

[0064] S102: Determine the current motor operating condition according to the motor operating parameters, and determine the real-time load rate of the motor based on the preset load condition association model.

[0065] As a preferred solution, the step of determining the current motor operating condition according to the motor operating parameters and determining the real-time load rate of the motor based on the preset load condition association model specifically includes:

[0066] Comprehensively analyze the stator winding temperature, the three-phase current harmonic distortion rate, the bearing vibration acceleration, the magnetic flux density value, and the temperature difference between the inlet and outlet of the cooling system, and determine the current motor operating condition according to the preset motor operating state model; wherein, the current motor operating condition includes: normal condition, abnormal condition, special condition, fault condition, and protection condition, and the motor operating state model is trained by combining historical motor operating parameters and historical motor operating conditions;

[0067] Input the current motor operating condition in normal condition, abnormal condition, special condition, fault condition or protection condition into a preset load condition correlation model to determine the real-time load rate of the motor.

[0068] In this embodiment, multi-source data such as the collected stator winding temperature, three-phase current harmonic distortion rate, bearing vibration acceleration, magnetic flux density value, and temperature difference between the inlet and outlet of the cooling system are comprehensively analyzed, and the stator winding temperature, three-phase current harmonic distortion rate, bearing vibration acceleration, magnetic flux density value, and temperature difference between the inlet and outlet of the cooling system are input into the motor operating state model to determine the current motor operating condition, including normal condition, abnormal condition, special condition, fault condition, and protection condition. Furthermore, the determined current motor operating condition is input into the preset load condition correlation model, and through model calculation, the real-time load rate of the motor is determined, thereby providing a basis for optimizing the operation of the motor. Further, the motor operating state model is constructed by training using historical motor operating parameters (such as current, temperature, vibration, etc.) combined with historical motor operating conditions, such as normal condition, abnormal condition, special condition, fault condition, and protection condition.

[0069] In this embodiment, the motor operating state model can be constructed by fitting historical motor operating parameters combined with historical motor operating conditions, and the load condition correlation model is also obtained by fitting the corresponding load data under each condition.

[0070] In this embodiment, the calculation formula for the stator winding temperature is:

[0071] ;

[0072] Among them, is the stator winding temperature, is the ambient temperature, is the effective value of the stator current, is the stator resistance, and are the core loss and mechanical loss respectively, is the product of the heat dissipation coefficient and the surface area. When the load increases, the current rises, resulting in a significant increase in the winding temperature rise. If the efficiency of the cooling system remains unchanged, the temperature rise is approximately directly proportional to the square of the load current.

[0073] The calculation formula for the three-phase current harmonic distortion rate (THDi) is:

[0074] ;

[0075] Among them, \(I_{n}\) is the effective value of the \(n\)th harmonic current. At high loads, the magnetic field distortion inside the motor intensifies, leading to an increase in harmonic currents (such as the 5th and 7th harmonics). A THDi exceeding 5% may indicate abnormal load or non-linear effects of the frequency converter.

[0076] The calculation formula for the bearing vibration acceleration is:

[0077] ;

[0078] Wherein, is the load torque, is the rotational speed, is the bearing wear. When the load increases, the radial / axial force of the bearing increases, and the vibration amplitude rises. In addition, spectrum analysis is also required. Among them, low-frequency vibration (<1 kHz) may be caused by load fluctuations or mechanical imbalance; high-frequency vibration (>10 kHz) may be caused by local damage to the bearing.

[0079] The calculation formula for the magnetic flux density is:

[0080] ;

[0081] Wherein, is the number of turns of the winding, is the magnetic path length, is the magnetic permeability correction coefficient. When the load increases, the stator current increases, resulting in an increase in the magnetic flux density. If the magnetic flux density deviates from the rated value (such as ±0.5 mT), it may indicate overload or inter-turn short circuit of the winding.

[0082] The calculation formula for the temperature difference between the inlet and outlet of the cooling system is:

[0083] ;

[0084] Wherein, is the total loss power, is the specific heat capacity of the cooling medium, is the mass flow rate of the cooling medium. When the load increases, the motor loss power increases. If the cooling flow rate is constant, the temperature difference significantly increases. Under typical operating conditions, a temperature difference >5°C may indicate overload.

[0085] As a preferred solution, the construction method of the preset load condition association model includes:

[0086] Collect historical load-related time-series data and their corresponding operating condition parameters;

[0087] Calculate the rolling mean and standard deviation of the historical load-related time series data within a sliding window, and combine the lag terms of the historical load to determine the operating condition correlation characteristics between the historical load-related time series data and its corresponding operating condition parameters;

[0088] Construct an initial LSTM model, determine the adaptive learning rate and regularization, and train the initial LSTM model through the operating condition correlation characteristics until the preset number of iterations and preset termination conditions are reached, and then generate a preset load-operating condition correlation model.

[0089] In this embodiment, first perform multi-source heterogeneous data integration, collect load-related time series data (such as current, vibration, temperature) and operating condition parameters (parameters corresponding to normal operating conditions, abnormal operating conditions, special operating conditions, fault operating conditions, and protection operating conditions), use exponential moving average (EMA) to eliminate noise interference, and separate the high-frequency noise and low-frequency trend components in the signal through variational mode decomposition (VMD). Then, calculate the time series characteristics, determine the mean and variance within the sliding window, introduce the lag terms of the historical load to capture time series dependencies, construct the cross-term of the environmental parameters and the load, and determine the operating condition correlation characteristics between the historical load-related time series data and its corresponding operating condition parameters, so as to quantify the dynamic impact of external conditions on the load.

[0090] In this embodiment, use a bidirectional LSTM layer (BiLSTM) to capture forward and backward time series characteristics simultaneously, combine a convolutional block attention module (CBAM) to highlight key operating condition parameters, set a shared layer for the LSTM to extract common time series characteristics, and the fully connected layer outputs the load value (regression task) and the operating condition status label respectively, and automatically assigns task weights according to the training loss, so as to train and optimize the model, determine the adaptive learning rate and regularization. Among them, the AdamW optimizer (combined with weight decay) can be used, and L2 regularization is used in combination with the Dropout layer to prevent overfitting. Furthermore, train the initial LSTM model through the operating condition correlation characteristics.

[0091] Furthermore, train the initial LSTM model through the operating condition correlation characteristics until the preset number of iterations and preset termination conditions are reached, and then generate a preset load-operating condition correlation model; among them, the preset termination condition includes: terminate the training if the validation set loss does not decrease for n consecutive rounds, and n can be set to 10.

[0092] S103: Obtain the historical operation data of the variable frequency energy-saving motor, and generate a dynamic threshold curve according to the historical operation data.

[0093] As a preferred solution, the obtaining the historical operation data of the variable frequency energy-saving motor and generating a dynamic threshold curve according to the historical operation data specifically includes:

[0094] Obtain the historical operation data of the variable-frequency energy-saving motor; wherein, the historical operation data includes historical load rate, temperature parameter time-series data, vibration parameter time-series data, current parameter time-series data, and magnetic flux parameter time-series data;

[0095] According to the interval of the historical load rate, divide the temperature parameter time-series data, vibration parameter time-series data, current parameter time-series data, and magnetic flux parameter time-series data;

[0096] Construct a historical load rate sequence based on the historical load rate, and obtain the historical temperature threshold, historical vibration threshold, historical harmonic threshold, and historical magnetic flux threshold;

[0097] According to the historical temperature threshold, historical vibration threshold, historical harmonic threshold, and historical magnetic flux threshold, combined with the historical load rate sequence, and the divided temperature parameter time-series data, vibration parameter time-series data, current parameter time-series data, and magnetic flux parameter time-series data, generate a dynamic threshold curve.

[0098] In this embodiment, collect the historical operation data of the variable-frequency energy-saving motor, including historical load rate, temperature parameter time-series data, vibration parameter time-series data, current parameter time-series data, and magnetic flux parameter time-series data, and divide the temperature parameter time-series data, vibration parameter time-series data, current parameter time-series data, and magnetic flux parameter time-series data according to the interval of the historical load rate. Thus, construct a historical load rate sequence based on the historical load rate data, and obtain the historical temperature threshold, historical vibration threshold, historical harmonic threshold, and historical magnetic flux threshold. Combine the historical load rate sequence and the divided time-series data of each parameter, and use the historical threshold to generate a dynamic threshold curve. The dynamic threshold curve can dynamically adjust the threshold according to different load rate intervals, so as to more accurately monitor the operation state of the motor.

[0099] In this embodiment, the dynamic threshold curve can dynamically adjust the threshold according to the actual operation load rate of the motor, avoid misjudgment or missed judgment caused by a fixed threshold, so as to more accurately monitor the operation state of the motor, and can timely detect abnormal changes in the motor operation, give early warning of potential faults, reduce equipment damage and downtime, and realize accurate monitoring and optimal control of the operation state of the variable-frequency energy-saving motor, with significant economic benefits and application value.

[0100] S104: Generate a dynamic threshold according to the motor operation parameters and the dynamic threshold curve, calculate the health degree of the variable-frequency energy-saving motor based on the dynamic threshold, and determine the life prediction value of the variable-frequency energy-saving motor according to the health degree.

[0101] As a preferred solution, generating a dynamic threshold according to the motor operating parameters and the dynamic threshold curve, calculating the health degree of the variable-frequency energy-saving motor based on the dynamic threshold, and determining the life prediction value of the variable-frequency energy-saving motor according to the health degree, specifically including:

[0102] Inputting the motor operating parameters into the dynamic threshold curve to generate current real-time dynamic thresholds corresponding to the stator winding temperature, three-phase current harmonic distortion rate, bearing vibration acceleration, magnetic flux density value, and temperature difference between the inlet and outlet of the cooling system; wherein, the dynamic threshold includes a dynamic temperature threshold, a dynamic vibration threshold, a dynamic harmonic threshold, and a dynamic magnetic flux threshold;

[0103] Comparing the stator winding temperature and the temperature difference between the inlet and outlet of the cooling system with the dynamic temperature threshold respectively, and calculating the first health degree according to the differences between the stator winding temperature and the temperature difference between the inlet and outlet of the cooling system and the dynamic temperature threshold;

[0104] Comparing the three-phase current harmonic distortion rate with the dynamic harmonic threshold, and calculating the second health degree according to the difference between the three-phase current harmonic distortion rate and the dynamic harmonic threshold;

[0105] Comparing the bearing vibration acceleration with the dynamic vibration threshold, and calculating the third health degree according to the difference between the bearing vibration acceleration and the dynamic vibration threshold;

[0106] Comparing the magnetic flux density value with the dynamic vibration magnetic flux, and calculating the fourth health degree according to the difference between the magnetic flux density value and the dynamic magnetic flux threshold;

[0107] Determining the life prediction value of the variable-frequency energy-saving motor according to the first health degree, the second health degree, the third health degree, and the fourth health degree, in combination with a preset health weight coefficient.

[0108] In this embodiment, the collected motor operating parameters (stator winding temperature, three-phase current harmonic distortion rate, bearing vibration acceleration, magnetic flux density value, and temperature difference between the inlet and outlet of the cooling system) are input into the dynamic threshold curve. The dynamic threshold curve can be generated based on historical operating data and can dynamically adjust the threshold according to different load rates, including dynamic temperature threshold, dynamic vibration threshold, dynamic harmonic threshold, and dynamic magnetic flux threshold. The stator winding temperature and the temperature difference between the inlet and outlet of the cooling system are respectively compared with the dynamic temperature threshold, and the first health degree is calculated according to the difference. The smaller the difference, the higher the health degree. Similarly, the current harmonic health degree (the second health degree), the vibration health degree (the third health degree), and the magnetic flux health degree (the fourth health degree) follow the same logic. Furthermore, based on the first health degree, the second health degree, the third health degree, and the fourth health degree, combined with the preset health weight coefficients, the life prediction value of the variable-frequency energy-saving motor is comprehensively calculated. The health weight coefficients can be adjusted according to the influence degree of different parameters on the motor life to more accurately reflect the actual health condition of the motor.

[0109] In this embodiment, the calculation formula for the first health degree is:

[0110] ;

[0111] The calculation formula for the second health degree is:

[0112] ;

[0113] The calculation formula for the third health degree is:

[0114] ;

[0115] The calculation formula for the fourth health degree is:

[0116] ;

[0117] Based on the first health degree, the second health degree, the third health degree, and the fourth health degree, combined with the preset health weight coefficients, determine the life prediction value of the variable-frequency energy-saving motor:

[0118] ;

[0119] Wherein, , , and are the preset health weight coefficients, which are allocated according to the influence degree of different parameters on the motor life. The health weight coefficients can be adjusted according to the actual application scenario and experience to more accurately reflect the influence of different parameters on the motor life. , , and They are the first health level, the second health level, the third health level, and the fourth health level respectively.

[0120] S105: When the life prediction value of the variable-frequency energy-saving motor is lower than the preset threshold, an automatic frequency reduction command is triggered and switched to the field-oriented vector control mode. At the same time, an alarm and a device health file for the variable-frequency energy-saving motor are generated synchronously.

[0121] In this embodiment, when the monitored parameters (such as temperature, current harmonic distortion rate, vibration acceleration, etc.) exceed the preset dynamic threshold, the control unit automatically triggers a frequency reduction command. The triggering logic of the frequency reduction command can be customized according to different application scenarios and motor characteristics. After the frequency reduction command is triggered, the control unit automatically switches to the field-oriented vector control mode to optimize the operation efficiency and stability of the motor. The FOC mode (field-oriented vector control) ensures that the motor can still maintain high efficiency and stability during low-frequency operation by precisely controlling the magnitude and direction of the magnetic field. When the frequency reduction command is triggered or an abnormality is detected, the alarm system immediately issues an alarm and records the relevant data in the health file. Among them, the health file system regularly updates the operation status and historical data of the device to provide support for the maintenance and management of the device.

[0122] It can be understood that through real-time monitoring, intelligent control, and health management, the efficient and stable operation of the variable-frequency energy-saving motor is achieved. By automatically triggering the frequency reduction command and switching to the field-oriented vector control mode, the optimal operation state of the motor under different load conditions is ensured. At the same time, the synchronous generation of the alarm and the device health file provides strong support for the maintenance and management of the device. This solution has broad application prospects in the fields of industry, commerce, and transportation.

[0123] As a preferred solution, it further includes:

[0124] When the life prediction value of the variable-frequency energy-saving motor is not lower than the preset threshold, the current motor operation parameters of the variable-frequency energy-saving motor are recorded in real time, and the corresponding life prediction value is recorded in the device health file.

[0125] In this embodiment, when the life prediction value of the variable-frequency energy-saving motor is not lower than the preset threshold, it means that the current life prediction value of the variable-frequency energy-saving motor is relatively high. It only needs to keep the variable-frequency energy-saving motor running normally and record the current life prediction value in the device health file, without corresponding alarms. At the same time, the device health file can be recorded in the cloud server, and users can query and read it on different corresponding device platforms, improving the query compatibility of the variable-frequency energy-saving motor and the overall reliability of the variable-frequency energy-saving motor.

[0126] Implementing the above embodiments has the following effects:

[0127] The technical solution of the present invention collects the motor operation parameters in real time through a multi-source sensor group configured on a variable-frequency energy-saving motor, and then determines the real-time load rate of the motor. A dynamic threshold curve is generated based on the historical operation data of the variable-frequency energy-saving motor, so as to determine the current dynamic threshold of the variable-frequency energy-saving motor, ensuring that the variable-frequency energy-saving motor can evaluate and predict the current variable-frequency energy-saving motor in real time, thereby improving the accuracy and efficiency of real-time monitoring and early warning. Finally, by determining the life prediction value of the variable-frequency energy-saving motor, when the life prediction value of the variable-frequency energy-saving motor is lower than the preset threshold, a frequency reduction command is automatically triggered and switched to the field-oriented vector control mode to ensure that the variable-frequency energy-saving motor can perform post-warning control, ensuring the closed-loop control of the overall motor process. At the same time, an alarm and equipment health file of the variable-frequency energy-saving motor are generated synchronously to ensure its compatibility for alarm and query on other platforms, improving the overall reliability of the variable-frequency energy-saving motor.

[0128] Embodiment 2

[0129] Please refer to Figure 2 , which is a real-time monitoring and early warning system for a variable-frequency energy-saving motor provided by the present invention, including:

[0130] An acquisition module 201, configured to collect motor operation parameters in real time through a multi-source sensor group configured on a variable-frequency energy-saving motor;

[0131] A load module 202, configured to determine the current motor operating condition according to the motor operation parameters, and determine the real-time load rate of the motor based on a preset load condition association model;

[0132] A threshold module 203, configured to obtain the historical operation data of the variable-frequency energy-saving motor, and generate a dynamic threshold curve according to the real-time load rate of the motor and the historical operation data;

[0133] A prediction module 204, configured to calculate the health degree of the variable-frequency energy-saving motor according to the motor operation parameters and the dynamic threshold curve, and determine the life prediction value of the variable-frequency energy-saving motor according to the health degree;

[0134] A control module 205, configured to automatically trigger a frequency reduction command and switch to the field-oriented vector control mode when the life prediction value of the variable-frequency energy-saving motor is lower than a preset threshold, and simultaneously generate an alarm and an equipment health file of the variable-frequency energy-saving motor synchronously.

[0135] As a preferred solution, the collecting of the motor operation parameters in real time through a multi-source sensor group configured on a variable-frequency energy-saving motor specifically includes:

[0136] Collecting the stator winding temperature through a first temperature sensor disposed inside the stator winding of the variable-frequency energy-saving motor;

[0137] Collect the three-phase current of the variable-frequency energy-saving motor through the current sensor set on the variable-frequency energy-saving motor, and calculate the harmonic distortion rate based on the three-phase current;

[0138] Collect the bearing vibration acceleration of the variable-frequency energy-saving motor through the vibration acceleration sensor set on the bearing of the variable-frequency energy-saving motor;

[0139] Collect the magnetic flux density inside the variable-frequency energy-saving motor through the magnetic flux sensor set on the variable-frequency energy-saving motor;

[0140] Measure the temperature of the cooling medium through the second temperature sensor set at the inlet and outlet of the cooling system in the variable-frequency energy-saving motor, and calculate the temperature difference of the measured cooling medium when passing through the inlet and outlet;

[0141] Among them, the multi-source sensor group includes: a first temperature sensor, a second temperature sensor, a current sensor, a vibration acceleration sensor and a magnetic flux sensor, and the motor operation parameters include: stator winding temperature, three-phase current harmonic distortion rate, bearing vibration acceleration, magnetic flux density value and cooling system inlet and outlet temperature difference.

[0142] As a preferred solution, determining the current motor working condition according to the motor operation parameters and determining the real-time load rate of the motor based on a preset load working condition association model specifically includes:

[0143] Comprehensively analyze the stator winding temperature, three-phase current harmonic distortion rate, bearing vibration acceleration, magnetic flux density value and cooling system inlet and outlet temperature difference, and determine the current motor working condition according to a preset motor operation state model; among them, the current motor working condition includes: normal working condition, abnormal working condition, special working condition, fault working condition and protection working condition, and the motor operation state model is trained through historical motor operation parameters combined with historical motor operation conditions;

[0144] Input the current motor working condition in the normal working condition, abnormal working condition, special working condition, fault working condition or protection working condition into a preset load working condition association model to determine the real-time load rate of the motor.

[0145] As a preferred solution, the construction method of the preset load working condition association model includes:

[0146] Collect historical load-related time series data and its corresponding working condition parameters;

[0147] Calculate the rolling mean and standard deviation within a sliding window for the historical load-related time series data, and combine the lag terms of the historical load to determine the working condition association characteristics of the historical load-related time series data and its corresponding working condition parameters;

[0148] Construct an initial LSTM model, determine the adaptive learning rate and regularization, and train the initial LSTM model with the working condition related features until the preset number of iterations and preset termination conditions are reached, and then generate a preset load working condition related model.

[0149] As a preferred solution, obtaining the historical operation data of the variable frequency energy-saving motor and generating a dynamic threshold curve according to the historical operation data specifically includes:

[0150] Obtain the historical operation data of the variable frequency energy-saving motor; wherein, the historical operation data includes historical load rate, temperature parameter time series data, vibration parameter time series data, current parameter time series data, and magnetic flux parameter time series data;

[0151] Divide the temperature parameter time series data, vibration parameter time series data, current parameter time series data, and magnetic flux parameter time series data according to the interval of the historical load rate;

[0152] Construct a historical load rate sequence according to the historical load rate, and obtain the historical temperature threshold, historical vibration threshold, historical harmonic threshold, and historical magnetic flux threshold;

[0153] Generate a dynamic threshold curve according to the historical temperature threshold, historical vibration threshold, historical harmonic threshold, and historical magnetic flux threshold, in combination with the historical load rate sequence, and the divided temperature parameter time series data, vibration parameter time series data, current parameter time series data, and magnetic flux parameter time series data.

[0154] As a preferred solution, generating a dynamic threshold according to the motor operation parameters and the dynamic threshold curve, calculating the health degree of the variable frequency energy-saving motor based on the dynamic threshold, and determining the life prediction value of the variable frequency energy-saving motor according to the health degree specifically includes:

[0155] Input the motor operation parameters into the dynamic threshold curve to generate current real-time dynamic thresholds corresponding to the stator winding temperature, three-phase current harmonic distortion rate, bearing vibration acceleration, magnetic flux density value, and cooling system inlet and outlet temperature difference; wherein, the dynamic thresholds include dynamic temperature threshold, dynamic vibration threshold, dynamic harmonic threshold, and dynamic magnetic flux threshold;

[0156] Compare the stator winding temperature and the cooling system inlet and outlet temperature difference with the dynamic temperature threshold respectively, and calculate the first health degree according to the differences between the stator winding temperature and the cooling system inlet and outlet temperature difference and the dynamic temperature threshold;

[0157] Compare the three-phase current harmonic distortion rate with the dynamic harmonic threshold, and calculate the second health degree according to the difference between the three-phase current harmonic distortion rate and the dynamic harmonic threshold;

[0158] Compare the bearing vibration acceleration with the dynamic vibration threshold, and calculate the third health degree according to the difference between the bearing vibration acceleration and the dynamic vibration threshold;

[0159] Compare the magnetic flux density value with the dynamic vibration magnetic flux, and calculate the fourth health degree according to the difference between the magnetic flux density value and the dynamic magnetic flux threshold;

[0160] Determine the life prediction value of the variable-frequency energy-saving motor according to the first health degree, the second health degree, the third health degree and the fourth health degree, in combination with a preset health weight coefficient.

[0161] As a preferred solution, it further includes:

[0162] A recording module, configured to record the current motor operating parameters of the variable-frequency energy-saving motor in real time when the life prediction value of the variable-frequency energy-saving motor is not lower than a preset threshold value, and record the corresponding life prediction value in the equipment health file.

[0163] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working process of the device described above can refer to the corresponding process in the foregoing method embodiment, and will not be described in detail here.

[0164] Implementing the above embodiments has the following effects:

[0165] The technical solution of the present invention uses a multi-source sensor group configured on the variable-frequency energy-saving motor to collect motor operating parameters in real time, and then determines the real-time load rate of the motor. The dynamic threshold curve is generated through the historical operating data of the variable-frequency energy-saving motor, so as to determine the current dynamic threshold of the variable-frequency energy-saving motor, so as to ensure that the variable-frequency energy-saving motor can evaluate and predict the current variable-frequency energy-saving motor in real time, thereby improving the accuracy and efficiency of real-time monitoring and early warning. Finally, by determining the life prediction value of the variable-frequency energy-saving motor, and when the life prediction value of the variable-frequency energy-saving motor is lower than the preset threshold value, automatically trigger a frequency reduction command and switch to the field-oriented vector control mode to ensure that the variable-frequency energy-saving motor can perform post-warning control, ensure the closed-loop control of the overall motor process, and simultaneously generate the alarm and equipment health file of the variable-frequency energy-saving motor to ensure its compatibility for alarm and query on other platforms, improving the overall reliability of the variable-frequency energy-saving motor.

[0166] Embodiment III

[0167] Correspondingly, the present invention also provides a terminal device, including: a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the real-time monitoring and early warning method of the variable-frequency energy-saving motor described in any one of the above embodiments.

[0168] The terminal device of this embodiment includes: a processor, a memory, and a computer program and computer instructions stored in the memory and executable on the processor. When the processor executes the computer program, it implements each step in the first embodiment above, such as Figure 1 the steps S101 to S105 shown. Alternatively, when the processor executes the computer program, it implements the functions of each module / unit in the above device embodiment, such as the prediction module 204.

[0169] Exemplarily, the computer program can be divided into one or more modules / units. The one or more modules / units are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units can be a series of computer program instruction segments capable of performing specific functions, and this instruction segment is used to describe the execution process of the computer program in the terminal device. For example, the prediction module 204 is used to calculate the health degree of the variable-frequency energy-saving motor according to the motor operation parameters and the dynamic threshold curve, and determine the life prediction value of the variable-frequency energy-saving motor according to the health degree.

[0170] The terminal device can be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The terminal device may include, but is not limited to, a processor and a memory. Those skilled in the art can understand that the schematic diagram is only an example of the terminal device, and does not constitute a limitation on the terminal device. It may include more or fewer components than shown, or combine certain components, or different components. For example, the terminal device may further include input / output devices, network access devices, buses, etc.

[0171] The so-called processor may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The processor is the control center of the terminal device, and connects various parts of the entire terminal device through various interfaces and lines.

[0172] The memory can be used to store the computer programs and / or modules. By running or executing the computer programs and / or modules stored in the memory and invoking the data stored in the memory, the processor realizes various functions of the terminal device. The memory mainly includes a program storage area and a data storage area. Among them, the program storage area can store an operating system, application programs required for at least one function, etc.; the data storage area can store data created according to the use of the mobile terminal, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0173] Among them, if the modules / units integrated in the terminal device are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above-mentioned embodiment methods of the present invention, it can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disc, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc. It should be noted that the content included in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.

[0174] Embodiment 4

[0175] Correspondingly, the present invention also provides a computer-readable storage medium. The computer-readable storage medium includes a stored computer program. Among them, when the computer program runs, it controls the device where the computer-readable storage medium is located to execute the real-time monitoring and early warning method of the variable-frequency energy-saving motor described in any one of the above embodiments.

[0176] The specific embodiments described above further elaborate on the objective, technical solution, and beneficial effects of the present invention. It should be understood that the above description is only for the specific embodiments of the present invention and is not used to limit the protection scope of the present invention. In particular, it is pointed out that for those skilled in the art, any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A real-time monitoring and early warning method for variable frequency energy-saving motors, characterized in that: include: The multi-source sensor group configured on the variable frequency energy-saving motor can collect the motor operating parameters in real time; Determine the current motor operating condition according to the motor operating parameters, and determine the real-time motor load rate based on a preset load condition association model; Obtain historical operating data of variable frequency energy-saving motors, and generate dynamic threshold curves based on the historical operating data; Generate a dynamic threshold value according to the motor operating parameters and the dynamic threshold curve, calculate the health of the variable frequency energy-saving motor based on the dynamic threshold value, and determine the life prediction value of the variable frequency energy-saving motor according to the health; When the predicted life value of the variable frequency energy-saving motor is lower than a preset value, a frequency reduction instruction is automatically triggered and the control mode is switched to a magnetic field-oriented vector control mode, and an alarm and equipment health file of the variable frequency energy-saving motor are simultaneously generated.

2. A real-time monitoring and early warning method for variable frequency energy-saving motors as claimed in claim 1, characterized in that: The multi-source sensor group configured on the variable frequency energy-saving motor collects the motor operating parameters in real time, specifically including: The temperature of the stator winding is collected by a first temperature sensor disposed inside the stator winding of the variable frequency energy-saving motor; The three-phase current of the variable frequency energy-saving motor is collected by a current sensor provided on the variable frequency energy-saving motor, and the harmonic distortion rate is calculated according to the three-phase current; The vibration acceleration of the bearing of the variable frequency energy-saving motor is collected by a vibration acceleration sensor arranged on the bearing of the variable frequency energy-saving motor; The magnetic flux density inside the variable frequency energy-saving motor is collected by a magnetic flux sensor provided on the variable frequency energy-saving motor; The temperature of the cooling medium is measured by a second temperature sensor disposed at the inlet and outlet of the cooling system in the variable frequency energy-saving motor, and the temperature difference of the cooling medium when passing through the inlet and outlet is calculated; Among them, the multi-source sensor group includes: a first temperature sensor, a second temperature sensor, a current sensor, a vibration acceleration sensor and a flux sensor, and the motor operating parameters include: stator winding temperature, three-phase current harmonic distortion rate, bearing vibration acceleration, flux density value and cooling system inlet and outlet temperature difference.

3. A real-time monitoring and early warning method for variable frequency energy-saving motors as claimed in claim 2, characterized in that: Determining the current motor operating condition according to the motor operating parameters, and determining the motor real-time load rate based on a preset load operating condition association model, specifically includes: The stator winding temperature, three-phase current harmonic distortion rate, bearing vibration acceleration, magnetic flux density value and cooling system inlet and outlet temperature difference are comprehensively analyzed, and the current motor operating condition is determined according to a preset motor operating state model; wherein the current motor operating condition includes: normal operating condition, abnormal operating condition, special operating condition, fault operating condition and protection operating condition, and the motor operating state model is obtained by training through historical motor operating parameters combined with historical motor operating conditions; The current motor operating condition, whether in normal operating condition, abnormal operating condition, special operating condition, fault operating condition or protection operating condition, is input into a preset load operating condition association model to determine the real-time load rate of the motor.

4. A real-time monitoring and early warning method for a variable frequency energy-saving motor as described in any one of claims 1 to 3, characterized in that: The method for constructing the preset load condition association model includes: Collect historical load-related time series data and its corresponding operating parameters; The rolling mean and standard deviation of the historical load-related time series data in the sliding window are calculated, and the operating condition correlation characteristics of the historical load-related time series data and its corresponding operating condition parameters are determined in combination with the lag term of the historical load; An initial LSTM model is constructed, and an adaptive learning rate and regularization are determined. The initial LSTM model is trained using the operating condition association features until a preset number of iterations and a preset termination condition are reached, thereby generating a preset load operating condition association model.

5. A real-time monitoring and early warning method for variable frequency energy-saving motors as claimed in claim 1, characterized in that: The acquiring of historical operating data of the variable frequency energy-saving motor and generating a dynamic threshold curve according to the historical operating data specifically includes: Acquire historical operation data of the variable frequency energy-saving motor; wherein the historical operation data includes historical load rate, temperature parameter time series data, vibration parameter time series data, current parameter time series data and flux parameter time series data; Dividing the temperature parameter time series data, the vibration parameter time series data, the current parameter time series data and the flux parameter time series data according to the interval of the historical load rate; Construct a historical load rate sequence according to the historical load rate, and obtain a historical temperature threshold, a historical vibration threshold, a historical harmonic threshold, and a historical flux threshold; A dynamic threshold curve is generated based on the historical temperature threshold, historical vibration threshold, historical harmonic threshold and historical flux threshold, combined with the historical load rate sequence, and the divided temperature parameter time series data, vibration parameter time series data, current parameter time series data and flux parameter time series data.

6. A real-time monitoring and early warning method for variable frequency energy-saving motors as claimed in claim 5, characterized in that: The generating of a dynamic threshold value according to the motor operating parameter and the dynamic threshold curve, calculating the health of the variable frequency energy-saving motor based on the dynamic threshold value, and determining the life prediction value of the variable frequency energy-saving motor according to the health, specifically includes: Input the motor operating parameters into the dynamic threshold curve to generate current real-time dynamic thresholds corresponding to stator winding temperature, three-phase current harmonic distortion rate, bearing vibration acceleration, magnetic flux density value and cooling system inlet and outlet temperature difference; wherein the dynamic thresholds include dynamic temperature threshold, dynamic vibration threshold, dynamic harmonic threshold and dynamic magnetic flux threshold; Comparing the stator winding temperature and the cooling system inlet and outlet temperature difference with the dynamic temperature threshold, and calculating the first health degree according to the difference between the stator winding temperature and the cooling system inlet and outlet temperature difference and the dynamic temperature threshold; Comparing the three-phase current harmonic distortion rate with the dynamic harmonic threshold, and calculating the second health degree according to the difference between the three-phase current harmonic distortion rate and the dynamic harmonic threshold; comparing the bearing vibration acceleration with the dynamic vibration threshold, and calculating a third health degree according to a difference between the bearing vibration acceleration and the dynamic vibration threshold; Comparing the magnetic flux density value with the dynamic vibration magnetic flux, and calculating a fourth health level according to a difference between the magnetic flux density value and the dynamic magnetic flux threshold; According to the first health degree, the second health degree, the third health degree and the fourth health degree, combined with a preset health weight coefficient, a life prediction value of the variable frequency energy-saving motor is determined.

7. A real-time monitoring and early warning method for variable frequency energy-saving motors as claimed in claim 1, characterized in that: Also includes: When the life prediction value of the variable frequency energy-saving motor is not lower than a preset value, the current motor operating parameters of the variable frequency energy-saving motor are recorded in real time, and the corresponding life prediction value is recorded in the equipment health file.

8. A real-time monitoring and early warning system for variable frequency energy-saving motors, characterized in that: include: The acquisition module is used to collect the motor operating parameters in real time through a multi-source sensor group configured on the variable frequency energy-saving motor; A load module, used to determine the current motor working condition according to the motor operating parameters, and determine the real-time motor load rate based on a preset load working condition association model; The threshold module is used to obtain the historical operating data of the variable frequency energy-saving motor and generate a dynamic threshold curve according to the real-time load rate of the motor and the historical operating data; A prediction module, configured to calculate the health of the variable frequency energy-saving motor according to the motor operating parameters and the dynamic threshold curve, and determine a life prediction value of the variable frequency energy-saving motor according to the health; The control module is used to automatically trigger a frequency reduction instruction and switch to a magnetic field oriented vector control mode when the life prediction value of the variable frequency energy-saving motor is lower than a preset value, and simultaneously generate an alarm and equipment health file of the variable frequency energy-saving motor.

9. A terminal device, characterized in that: It includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the real-time monitoring and early warning method of the variable frequency energy-saving motor as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the real-time monitoring and early warning method for the variable frequency energy-saving motor according to any one of claims 1 to 7.

Images