Motor driver protection device

Abstract

The invention relates to the field of driver protection, in particular to a motor driver protection device which is characterized by comprising a sensing module, a fault prediction module, a dynamic control module, an execution module, a central processing unit, a memory module and a power management module. According to the motor driver protection device, key operation parameters such as current, voltage, temperature and rotating speed are collected in real time through the sensing module, intelligent prediction is carried out in combination with the fault prediction module, the dynamic control module can adjust the operation state of a motor in real time, and it is ensured that a system can rapidly respond and take corresponding protection measures when faults occur. And the central processing unit coordinates communication and data processing among the modules, stores historical data through the memory module, provides data support for fault prediction, and enhances the stability of the system and the capability of coping with complex fault scenes.

Description

Technical Field

[0001] The invention relates to the field of driver protection, in particular to a motor driver protection device. Background Art

[0002] With the development of industrial automation and intelligent manufacturing, motor drivers are widely used as core equipment in various industrial equipment, such as motors, fans, pumps, etc. The normal operation of these devices depends on the stability and efficiency of motor drivers. Therefore, how to ensure the reliability of motor drivers in long-term operation and avoid shutdowns or equipment damage caused by overload, overheating and other faults has become a research focus in the industry.

[0003] Existing motor drives usually rely on scheduled maintenance, manual monitoring, and simple fault protection mechanisms to prevent motor failures. However, these traditional technologies have many shortcomings, especially when faced with complex working conditions or sudden failures, they often cannot respond in time, thus affecting the safety and production efficiency of the equipment. The specific technical defects are as follows: Lack of real-time fault prediction and active protection mechanism: In traditional motor drive systems, fault detection mostly relies on preset simple parameter thresholds. For example, when the current, voltage or temperature exceeds a certain fixed value, the system will trigger an alarm or perform a shutdown operation. Although this method is effective in some scenarios, the problem is that when the motor drive is under high load or working for a long time, faults tend to accumulate gradually, and it is difficult to judge the potential trend of faults through a single threshold. For example, the temperature of the motor may rise slightly in a short period of time, but it does not exceed the preset safety value. The system will not respond, but this may indicate that more serious faults will occur in the future. Traditional threshold detection methods cannot achieve active prediction of faults and lack intelligent fault prevention mechanisms, resulting in the lack of effective protection measures for equipment before sudden faults occur, making it difficult to provide timely warnings.

[0004] Traditional motor drive protection mechanisms usually adopt simple overload protection, overtemperature protection or short-circuit protection. These protection methods are based on simple logical judgment, that is, when a certain parameter exceeds the safety range, the shutdown or load reduction operation is immediately triggered. The limitation of this protection method is that it cannot distinguish the severity of the fault, nor can it flexibly adjust the protection measures according to the actual operating status. For example, when the motor temperature rises slightly, if it only relies on a fixed threshold to trigger the protection operation, it may cause unnecessary shutdown or load reduction, affecting production efficiency. When the fault is serious, the system may cause equipment damage due to the lack of sufficient response mechanism. Therefore, the singleness and rigidity of traditional protection measures cannot adapt to complex changes in working conditions, which can easily cause overreaction and slow response.

[0005] The motor driver in the prior art usually adopts a fixed power output setting, and the power regulation is only started when a major fault occurs or the system enters the shutdown protection state. However, in the actual operation of the motor, the load and working conditions often change constantly, especially under heavy load or long-term operation, the power demand may fluctuate at any time. If the power of the motor driver cannot be dynamically adjusted according to the real-time operating status, two types of problems may occur: one is insufficient power output, causing the motor to overload under high load, causing equipment damage; the other is excessive power output, wasting energy and increasing the risk of overheating of the motor. In addition, when a fault occurs, the lag of power regulation may cause the fault to expand rapidly and aggravate damage. Therefore, the existing power control means lack adaptability and cannot be accurately adjusted according to the real-time needs of the motor. It is impossible to achieve energy-saving goals and it is difficult to effectively control the further expansion of the fault. Summary of the invention

[0006] The object of the present invention is to provide a motor driver protection device to solve the technical problems raised in the above background technology.

[0007] Based on the above ideas, the present invention provides the following technical solutions: a motor driver protection device, characterized in that it includes a sensor module, a fault prediction module, a dynamic control module, an execution module, a central processing unit, a memory module and a power management module. The sensor module includes a current sensor, a voltage sensor, a temperature sensor and a speed sensor, which are respectively installed at key nodes of the motor and the driver. The sensor module is used to collect the operation data of the driver in real time, including current, voltage, temperature and speed. The operation data is transmitted to the fault prediction module and the central processing unit through the bus. The sensor module is connected to the dynamic control module and the execution module for providing real-time data support immediately when a fault occurs. The fault prediction module includes an embedded computing chip, the embedded chip performs calculation and analysis through historical data and real-time data, the embedded chip uses a long short-term memory network model to predict faults, the fault prediction module is electrically connected to the sensor module, the fault prediction module receives the current, voltage, temperature and speed data collected by the sensor module, and predicts the future operating state of the motor driver through a dynamic fault prediction algorithm, the fault prediction module is also connected to the dynamic control module, and when a potential fault is predicted, a warning signal is sent to the dynamic control module; The dynamic control module includes a digital signal processor, which is used to dynamically adjust the operating state of the motor according to the output signal of the fault prediction module. The dynamic control module receives the prediction results from the fault prediction module and the real-time data of the sensor module through the bus, and calculates the risk factor of the motor driver in real time. According to the level of the risk factor, the dynamic control module sends control signals of different levels to the execution module, thereby executing corresponding protective measures. The dynamic control module shares processing results and status information with the central processing unit to ensure the continuity and real-time performance of the control logic.

[0008] The execution module is connected to the dynamic control module through an electronic relay and a servo motor controller. The execution module is used to receive the control signal of the dynamic control module and trigger the corresponding protection measures according to the level of the signal. Specifically, when a minor fault is detected, the execution module reduces the output power of the motor driver through the servo motor controller; when a serious fault is detected, the execution module quickly cuts off the power supply through a high-speed electronic relay to prevent further damage to the motor. The execution module also maintains a communication connection with the sensor module to ensure continuous monitoring of the motor status during the execution of the protection operation.

[0009] The central processing unit is connected to the sensor module, fault prediction module, dynamic control module and execution module. The central processing unit is responsible for coordinating the communication and data processing between the modules, storing historical operation data and real-time status data through the memory module, and providing data support for the algorithm execution of the fault prediction module.

[0010] The memory module is used to store the historical operation data of the motor drive, including the historical records of current, voltage, temperature and speed, for the fault prediction module to perform machine learning model training and real-time reasoning. The memory module also temporarily stores real-time monitoring data to ensure that the dynamic control module can obtain sufficient data for protection decisions. The memory module communicates with the central processing unit and the fault prediction module to ensure efficient access to data; The power management module is electrically connected to the central processing unit to dynamically adjust the energy consumption strategy according to the motor operating status. When the system is in normal working state, the power management module reduces the frequency of data acquisition and the number of memory accesses to reduce overall power consumption; when the system detects a fault, the power management module increases the frequency of data acquisition and processing to ensure real-time monitoring and response protection operations. In addition, the power management module can maintain the low-power operation state of key modules during emergency shutdowns to ensure that the equipment can resume operation quickly.

[0011] The motor driver protection device collects key operating parameters such as current, voltage, temperature and speed in real time through the sensor module, and performs intelligent prediction in combination with the fault prediction module. The dynamic control module can adjust the motor operating status in real time to ensure that the system can respond quickly and take corresponding protective measures when a fault occurs. The central processing unit coordinates the communication and data processing between the modules, and stores historical data through the memory module to provide data support for fault prediction, enhancing the system's stability and ability to cope with complex fault scenarios. The power management module dynamically adjusts the energy consumption strategy according to the motor's operating status, improving the system's energy efficiency.

[0012] Preferably, the fault prediction module executes a machine learning dynamic fault prediction algorithm through an embedded chip, and the specific process includes: S1: obtain current, voltage, temperature and speed data from the sensor module in real time; S2: The LSTM model in the embedded chip accelerates the processing of historical data and real-time data by calling the accelerated matrix operation unit (MAC) on the chip to establish a prediction model; S3: The chip’s embedded memory caches input data and predicts the state at future times based on the fault prediction formula; S4: When the deviation between the prediction result and the safety threshold exceeds the set range, a warning signal is sent to the dynamic control module.

[0013] Through the dynamic fault prediction algorithm executed by the embedded chip, the motor drive protection device can use the long short-term memory network (LSTM) model to combine historical and real-time data for efficient fault prediction. The accelerated matrix operation unit (MAC) in the embedded chip can improve the data processing speed and ensure the accuracy of the system's prediction before the fault occurs. When the predicted value exceeds the safety threshold, the system can issue a warning signal in advance, effectively reducing the damage to the equipment caused by sudden faults, and enhancing the system's security and intelligent management capabilities.

[0014] Preferably, the fault prediction formula includes: P(t+Δt)=f(W⋅D(t)+b) Among them, P(t+Δt) represents the predicted value of the motor driver state at the future time t+Δt, which is the output of the fault prediction algorithm; W is the weight matrix, which is used to weight the input data. This matrix is ​​trained by the machine learning model (LSTM) and represents the importance of different input features. D(t) is the real-time data input vector at the current time t, including the parameters of current, temperature, speed and voltage; b is the bias term, which adjusts the offset of the prediction model output; f is the activation function, which is used to perform nonlinear transformation on linear output and improve the fitting ability of the model.

[0015] The fault prediction formula achieves accurate prediction of the motor state at future moments by weighting input data and combining it with the long short-term memory network (LSTM) model. Using real-time data vectors and historical data to predict the future motor operation state can detect potential fault problems earlier. Through the automatic optimization of the prediction weight matrix, the algorithm can adapt to different working conditions and environments, improve the reliability and flexibility of system prediction, and further reduce the risk of equipment failure.

[0016] Preferably, the dynamic control module adopts a multi-level risk assessment algorithm and uses a risk factor calculation formula to perform risk assessment on the motor driver. The specific steps include: S1: Get real-time data of current, temperature and speed from the sensor module; S2: Calculate the risk factor according to the risk factor calculation formula; S3: Divide the risk factors into different fault levels and send corresponding control signals to the dynamic control module.

[0017] The dynamic control module can calculate the changes in current, temperature and speed in real time and generate corresponding risk factors. According to the risk factors, the system can automatically classify different fault levels and take corresponding protective measures. This multi-level protection mechanism not only improves the accuracy of motor drive protection, but also can intervene in time at the early stage of the fault to avoid more serious faults, thereby enhancing the stability and safety of the equipment.

[0018] Preferably, the risk factor calculation formula includes:

[0019] Among them, R(t) is the risk factor, which is the real-time fault risk value of the motor drive calculated at the current time t; α, β and γ are weighting coefficients, which are used to adjust the influence weights of current, temperature and speed on risk factors respectively. In actual use, the values ​​of these coefficients can be adjusted according to the characteristics of the equipment or the fault history; dI(t) is the current change rate, which indicates the rate of change of current over time; dT(t) is the temperature change rate, which indicates the rate of change of temperature over time; dw(t) is the speed change rate, which indicates the rate of change of the motor speed over time and is used to detect whether the motor has load fluctuations.

[0020] The risk factor calculation formula combines the current change rate, temperature change rate and speed change rate to comprehensively evaluate the operating status of the motor drive. Through dynamic adjustment of the weighting coefficient, the system can optimize the response speed to different parameters according to the operating characteristics of the equipment. This formula effectively identifies abnormal trends in operation and responds to protection in a timely manner, reducing the risk of damage to the motor drive due to load fluctuations, overheating or current abnormalities, and improving the reliability of the equipment.

[0021] Preferably, the dynamic control module dynamically adjusts the output power of the motor through an adaptive power control algorithm, and the specific steps of the adaptive power control algorithm include: S1: receiving the risk factor value of the multi-level risk assessment algorithm; S2: Preset multiple fault level thresholds based on the risk factor R(t) calculated in real time: Warning threshold R(w): When R(t) exceeds this threshold but does not reach the fault level, the execution module sends a warning signal to the central control system through the communication interface to remind the operator to check, but no immediate protective measures are taken; Fault threshold R(f): When R(t) reaches or exceeds this threshold, the dynamic control module triggers some protection measures and adjusts the power output of the motor through the adaptive power adjustment formula; Emergency stop threshold R(e): When R(t) reaches or exceeds this threshold, the execution module triggers an emergency stop operation through a high-speed electronic relay, cutting off the power supply to the motor driver to prevent equipment damage.

[0022] The adaptive power control algorithm generates risk factor values ​​through a multi-level risk assessment algorithm, and can flexibly adjust power according to different fault level thresholds. When the fault is minor, the system only sends a warning signal to avoid unnecessary shutdown operations; when the fault is serious, the system will dynamically adjust the motor power according to the risk factor calculated in real time, and even trigger an emergency shutdown in an emergency. This dynamic and flexible protection mechanism improves the system's ability to respond to different fault conditions and significantly improves the working stability and safety of the equipment.

[0023] Preferably, the adaptive power adjustment formula includes:

[0024] Among them, G(t) power gain control quantity is the motor output power after adjustment at time t, which is the result of dynamically adjusting the motor driver output; K p is the proportionality coefficient, which indicates the response speed of the power gain to the prediction deviation; K d is the differential coefficient, which is used to adjust the response of the power gain to the rate of change of the deviation; δ(t) is the prediction deviation, which represents the difference between the predicted state value and the current actual state;.

[0025] dδ(t) is the rate of change of the prediction deviation, which is used to detect whether the deviation between the predicted value and the actual value increases sharply in a short period of time, thereby dynamically adjusting the power output.

[0026] Through the adaptive power adjustment formula, the system can adjust the output power of the motor in real time according to the prediction deviation and the rate of change of the deviation. The combination of proportional coefficient and differential coefficient enables the system to respond quickly to the prediction deviation while avoiding over-response during the power adjustment process to maintain system stability. The detection of the rate of change of the prediction deviation ensures that the system can adjust the power in time when the load fluctuates violently or the fault trend intensifies to avoid further damage to the system. This power adjustment mechanism improves the control accuracy of the system and its adaptability to complex fault scenarios.

[0027] Compared with the prior art, the present invention has the following beneficial effects: By integrating multiple sensor modules (including current sensors, voltage sensors, temperature sensors, and speed sensors), real-time monitoring of key operating parameters of the motor driver is achieved, ensuring that the equipment is always under effective monitoring during operation. At the same time, the fault prediction module executed by the embedded chip can predict possible motor failures in advance through the long short-term memory network (LSTM) model, combining historical data with real-time data. Unlike traditional passive fault handling methods, the device has active prevention capabilities. When abnormal conditions that may occur in the future are detected, warnings can be issued in advance to avoid damage to the equipment caused by sudden failures, thereby improving the operating safety and reliability of the equipment. .

[0028] The dynamic control module uses a multi-level risk assessment algorithm, which can calculate the risk factor of the motor driver based on the real-time collected current, temperature, speed and other data, and divide different fault levels by risk factors. Depending on the fault level, the system can take different protective measures, including issuing early warning signals, reducing motor power, reducing speed, and even performing emergency shutdown operations when necessary. This multi-level protection mechanism enables the system to respond flexibly and promptly when facing different levels of faults, which not only ensures the safety of the equipment, but also avoids overreaction, and improves the accuracy of protection and the reliability of the system.

[0029] The adaptive power control algorithm dynamically adjusts the motor's output power based on the risk factors and fault levels calculated in real time. By analyzing the predicted deviation and its rate of change in real time, the system can adjust the power output under different load conditions to maintain stable operation of the motor. The algorithm can not only quickly reduce power when a fault occurs to prevent further damage, but also optimize the motor's energy consumption under normal operating conditions to achieve efficient operation. In addition, the system has a flexible energy management function that can automatically adjust the energy consumption strategy according to the different working conditions of the motor, reduce ineffective energy consumption, extend the service life of the equipment, and thus significantly reduce maintenance costs and energy costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 The present invention is a schematic diagram of the module relationship of a motor driver protection device. DETAILED DESCRIPTION

[0031] A motor driver protection device, characterized in that it includes a sensor module, a fault prediction module, a dynamic control module, an execution module, a central processing unit, a memory module and a power management module. The sensor module includes a current sensor, a voltage sensor, a temperature sensor and a speed sensor, which are respectively installed at key nodes of the motor and the driver. The sensor module is used to collect the operation data of the driver in real time, including current, voltage, temperature and speed. The operation data is transmitted to the fault prediction module and the central processing unit through the bus. The sensor module is connected to the dynamic control module and the execution module for providing real-time data support immediately when a fault occurs. The fault prediction module includes an embedded computing chip, the embedded chip performs calculation and analysis through historical data and real-time data, the embedded chip uses a long short-term memory network model to predict faults, the fault prediction module is electrically connected to the sensor module, the fault prediction module receives the current, voltage, temperature and speed data collected by the sensor module, and predicts the future operating state of the motor driver through a dynamic fault prediction algorithm, the fault prediction module is also connected to the dynamic control module, and when a potential fault is predicted, a warning signal is sent to the dynamic control module; The dynamic control module includes a digital signal processor, which is used to dynamically adjust the operating state of the motor according to the output signal of the fault prediction module. The dynamic control module receives the prediction results from the fault prediction module and the real-time data of the sensor module through the bus, and calculates the risk factor of the motor driver in real time. According to the level of the risk factor, the dynamic control module sends control signals of different levels to the execution module, thereby executing corresponding protective measures. The dynamic control module shares processing results and status information with the central processing unit to ensure the continuity and real-time performance of the control logic.

[0032] The execution module is connected to the dynamic control module through an electronic relay and a servo motor controller. The execution module is used to receive the control signal of the dynamic control module and trigger the corresponding protection measures according to the level of the signal. Specifically, when a minor fault is detected, the execution module reduces the output power of the motor driver through the servo motor controller; when a serious fault is detected, the execution module quickly cuts off the power supply through a high-speed electronic relay to prevent further damage to the motor. The execution module also maintains a communication connection with the sensor module to ensure continuous monitoring of the motor status during the execution of the protection operation.

[0033] The central processing unit is connected to the sensor module, fault prediction module, dynamic control module and execution module. The central processing unit is responsible for coordinating the communication and data processing between the modules, storing historical operation data and real-time status data through the memory module, and providing data support for the algorithm execution of the fault prediction module.

[0034] The memory module is used to store the historical operation data of the motor drive, including the historical records of current, voltage, temperature and speed, for the fault prediction module to perform machine learning model training and real-time reasoning. The memory module also temporarily stores real-time monitoring data to ensure that the dynamic control module can obtain sufficient data for protection decisions. The memory module communicates with the central processing unit and the fault prediction module to ensure efficient access to data; The power management module is electrically connected to the central processing unit to dynamically adjust the energy consumption strategy according to the motor operating status. When the system is in normal working state, the power management module reduces the frequency of data acquisition and the number of memory accesses to reduce overall power consumption; when the system detects a fault, the power management module increases the frequency of data acquisition and processing to ensure real-time monitoring and response protection operations. In addition, the power management module can maintain the low-power operation state of key modules during emergency shutdowns to ensure that the equipment can resume operation quickly.

[0035] The motor driver protection device collects key operating parameters such as current, voltage, temperature and speed in real time through the sensor module, and performs intelligent prediction in combination with the fault prediction module. The dynamic control module can adjust the motor operating status in real time to ensure that the system can respond quickly and take corresponding protective measures when a fault occurs. The central processing unit coordinates the communication and data processing between the modules, and stores historical data through the memory module to provide data support for fault prediction, thereby enhancing the stability of the system and its ability to cope with complex fault scenarios. The power management module dynamically adjusts the energy consumption strategy according to the operating status of the motor, thereby improving the energy efficiency of the system. Overall, the device integrates real-time monitoring, fault prediction and dynamic adjustment functions, effectively extending the service life of the motor and reducing the failure rate.

[0036] Specifically, the fault prediction module executes the machine learning dynamic fault prediction algorithm through the embedded chip. The specific process includes: S1: obtain current, voltage, temperature and speed data from the sensor module in real time; S2: The LSTM model in the embedded chip accelerates the processing of historical data and real-time data by calling the accelerated matrix operation unit (MAC) on the chip to establish a prediction model; S3: The chip’s embedded memory caches input data and predicts the state at future times based on the fault prediction formula; S4: When the deviation between the prediction result and the safety threshold exceeds the set range, a warning signal is sent to the dynamic control module.

[0037] Through the dynamic fault prediction algorithm executed by the embedded chip, the motor drive protection device can use the long short-term memory network (LSTM) model to combine historical and real-time data for efficient fault prediction. The accelerated matrix operation unit (MAC) in the embedded chip can improve the data processing speed and ensure the accuracy of the system's prediction before the fault occurs. When the predicted value exceeds the safety threshold, the system can issue a warning signal in advance, effectively reducing the damage to the equipment caused by sudden faults, and enhancing the system's security and intelligent management capabilities.

[0038] When used specifically: Current sensors, voltage sensors, temperature sensors and speed sensors installed at key nodes of the motor and drive are used to collect the drive's operating data in real time, including current, voltage, temperature and speed. The data is transmitted to the embedded computing chip via a high-speed bus.

[0039] The embedded computing chip receives real-time data from the sensor and calls the embedded cache module to pre-process the data to remove noise and invalid data. At the same time, historical operation data is loaded from the memory module as training data for the machine learning model.

[0040] When the predicted value deviates from the safe range of the actual operating value, the embedded chip sends a warning signal to the dynamic control module through the communication interface. When it exceeds the preset safety threshold, a fault alarm is issued. Through this algorithm, the system can detect potential fault problems of the motor drive in advance and dynamically adjust the operating state of the motor through the predicted deviation $\delta(t)$, ensuring that the equipment takes effective measures before the fault occurs and reducing the damage caused by sudden faults.

[0041] The embedded chip processes historical data and real-time data through the long short-term memory network (LSTM) model.

[0042] Specifically, the fault prediction formula includes: P(t+Δt)=f(W⋅D(t)+b) Among them, P(t+Δt) represents the predicted value of the motor driver state at the future time t+Δt, which is the output of the fault prediction algorithm; W is the weight matrix, which is used to weight the input data. This matrix is ​​trained by the machine learning model (LSTM) and represents the importance of different input features. D(t) is the real-time data input vector at the current time t, including the parameters of current, temperature, speed and voltage; b is the bias term, which adjusts the offset of the prediction model output; f is the activation function, which is used to perform nonlinear transformation on linear output and improve the fitting ability of the model.

[0043] The fault prediction formula achieves accurate prediction of the motor state at future moments by weighting input data and combining it with the long short-term memory network (LSTM) model. Using real-time data vectors and historical data to predict the future motor operation state can detect potential fault problems earlier. Through the automatic optimization of the prediction weight matrix, the algorithm can adapt to different working conditions and environments, improve the reliability and flexibility of system prediction, and further reduce the risk of equipment failure.

[0044] Specifically, the dynamic control module adopts a multi-level risk assessment algorithm and uses a risk factor calculation formula to perform risk assessment on the motor driver. The specific steps include: S1: Get real-time data of current, temperature and speed from the sensor module; S2: Calculate the risk factor according to the risk factor calculation formula; S3: Divide the risk factors into different fault levels and send corresponding control signals to the dynamic control module.

[0045] The dynamic control module can calculate the changes in current, temperature and speed in real time and generate corresponding risk factors. According to the risk factors, the system can automatically classify different fault levels and take corresponding protective measures. This multi-level protection mechanism not only improves the accuracy of motor drive protection, but also can intervene in time at the early stage of the fault to avoid more serious faults, thereby enhancing the stability and safety of the equipment.

[0046] When used specifically: Through the sensor module (current, temperature, speed sensor), the motor operation data is collected in real time. These data include current value I(t), temperature value T(t) and speed w(t), and are transmitted to the dynamic control module through the bus.

[0047] The digital signal processor (DSP) in the dynamic control module calculates the risk factor of the motor based on the data collected in real time.

[0048] According to the calculated risk factor R(t), the system divides it into three levels: R(w): Warning level. When R(t) exceeds this value but is lower than the fault level, the system issues a warning signal but does not take protective measures. R(f): Fault level. When R(t) exceeds this value, the system triggers some protection measures. R(e): Emergency shutdown level. When R(t) exceeds this value, the system immediately triggers shutdown protection.

[0049] According to the risk level, the dynamic control module sends the corresponding control signal to the execution module to perform load reduction, frequency reduction or emergency shutdown operations.

[0050] By calculating risk factors in real time and classifying different fault levels, the system can flexibly respond to faults of varying degrees. The algorithm effectively reduces downtime losses caused by overprotection while ensuring that equipment is fully protected in high-risk situations.

[0051] Specifically, the risk factor calculation formula includes:

[0052] Among them, R(t) is the risk factor, which is the real-time fault risk value of the motor drive calculated at the current time t; α, β and γ are weighting coefficients, which are used to adjust the influence weights of current, temperature and speed on risk factors respectively. In actual use, the values ​​of these coefficients can be adjusted according to the characteristics of the equipment or the fault history; dI(t) is the current change rate, which indicates the rate of change of current over time; dT(t) is the temperature change rate, which indicates the rate of change of temperature over time; dw(t) is the speed change rate, which indicates the rate of change of the motor speed over time and is used to detect whether the motor has load fluctuations.

[0053] The risk factor calculation formula combines the current change rate, temperature change rate and speed change rate to comprehensively evaluate the operating status of the motor drive. Through dynamic adjustment of the weighting coefficient, the system can optimize the response speed to different parameters according to the operating characteristics of the equipment. This formula effectively identifies abnormal trends in operation and responds to protection in a timely manner, reducing the risk of damage to the motor drive due to load fluctuations, overheating or current abnormalities, and improving the reliability of the equipment.

[0054] Specifically, the dynamic control module dynamically adjusts the output power of the motor through an adaptive power control algorithm, and the specific steps of the adaptive power control algorithm include: S1: receiving the risk factor value of the multi-level risk assessment algorithm; S2: Preset multiple fault level thresholds based on the risk factor R(t) calculated in real time: Warning threshold R(w): When R(t) exceeds this threshold but does not reach the fault level, the execution module sends a warning signal to the central control system through the communication interface to remind the operator to check, but no immediate protective measures are taken; Fault threshold R(f): When R(t) reaches or exceeds this threshold, the dynamic control module triggers some protection measures and adjusts the power output of the motor through the adaptive power adjustment formula; Emergency stop threshold R(e): When R(t) reaches or exceeds this threshold, the execution module triggers an emergency stop operation through a high-speed electronic relay, cutting off the power supply to the motor driver to prevent equipment damage.

[0055] The adaptive power control algorithm generates risk factor values ​​through a multi-level risk assessment algorithm, and can flexibly adjust power according to different fault level thresholds. When the fault is minor, the system only sends a warning signal to avoid unnecessary shutdown operations; when the fault is serious, the system will dynamically adjust the motor power according to the risk factor calculated in real time, and even trigger an emergency shutdown in an emergency. This dynamic and flexible protection mechanism improves the system's ability to respond to different fault conditions and significantly improves the working stability and safety of the equipment.

[0056] Specifically, the adaptive power adjustment formula includes:

[0057] Among them, G(t) power gain control quantity is the motor output power after adjustment at time t, which is the result of dynamically adjusting the motor driver output; K p is the proportionality coefficient, which indicates the response speed of the power gain to the prediction deviation; K d is the differential coefficient, which is used to adjust the response of the power gain to the rate of change of the deviation; δ(t) is the prediction deviation, which represents the difference between the predicted state value and the current actual state;.

[0058] dδ(t) is the rate of change of the prediction deviation, which is used to detect whether the deviation between the predicted value and the actual value increases sharply in a short period of time, thereby dynamically adjusting the power output.

[0059] The value of G(t) directly determines the output power of the motor. When the prediction deviation is large, the system will adjust the motor's operating state by increasing or decreasing the power output. For example, if the actual speed of the motor is lower than the predicted speed, G(t) will increase to increase the output power; conversely, if the actual speed is too fast, G(t) will decrease to reduce the power output.

[0060] When the deviation change rate is too large, it means that the motor state is rapidly deteriorating (for example, the temperature rises rapidly, the speed fluctuates sharply). At this time, the differential term of G(t) will quickly adjust the output power, reduce the power output, and prevent the fault from further expanding.

[0061] The adaptive power control formula can dynamically respond to the state changes during motor operation to ensure that the power output matches the motor demand. When the motor operation state deviates from the normal value, the power output is adjusted appropriately to stabilize the motor operation and prevent the fault from expanding. This dynamic adjustment method can effectively reduce power consumption while improving the operating efficiency and stability of the motor.

[0062] Through the adaptive power adjustment formula, the system can adjust the output power of the motor in real time according to the prediction deviation and the rate of change of the deviation. The combination of proportional coefficient and differential coefficient enables the system to respond quickly to the prediction deviation while avoiding over-response during the power adjustment process to maintain system stability. The detection of the rate of change of the prediction deviation ensures that the system can adjust the power in time when the load fluctuates violently or the fault trend intensifies to avoid further damage to the system. This power adjustment mechanism improves the control accuracy of the system and its adaptability to complex fault scenarios.

Claims

1. A motor driver protection device, characterized in that: It includes a sensor module, a fault prediction module, a dynamic control module, an execution module, a central processing unit, a memory module and a power management module. The sensor module includes a current sensor, a voltage sensor, a temperature sensor and a speed sensor, which are respectively installed at key nodes of the motor and the driver. The sensor module is used to collect the operation data of the driver in real time, including current, voltage, temperature and speed. The operation data is transmitted to the fault prediction module and the central processing unit through the bus. The sensor module is connected to the dynamic control module and the execution module for providing real-time data support immediately when a fault occurs. The fault prediction module includes an embedded computing chip, the embedded chip performs calculation and analysis through historical data and real-time data, the embedded chip uses a long short-term memory network model to predict faults, the fault prediction module is electrically connected to the sensor module, the fault prediction module receives the current, voltage, temperature and speed data collected by the sensor module, and predicts the future operating state of the motor driver through a dynamic fault prediction algorithm, the fault prediction module is also connected to the dynamic control module, and when a potential fault is predicted, a warning signal is sent to the dynamic control module; The dynamic control module includes a digital signal processor, and the digital signal processor is used to dynamically adjust the running state of the motor according to the output signal of the fault prediction module. The dynamic control module receives the prediction result from the fault prediction module and the real-time data of the sensor module through the bus, and calculates the risk factor of the motor driver in real time. According to the level of the risk factor, the dynamic control module sends different levels of control signals to the execution module, so as to execute corresponding protective measures. The dynamic control module shares the processing results and status information with the central processing unit to ensure the continuity and real-time performance of the control logic; The execution module is connected to the dynamic control module through an electronic relay and a servo motor controller, and the execution module is used to receive a control signal from the dynamic control module and trigger corresponding protective measures according to the level of the signal; The central processing unit is connected to the sensor module, the fault prediction module, the dynamic control module and the execution module. The central processing unit is responsible for coordinating the communication and data processing between the modules, storing the historical operation data and the real-time status data through the memory module, and providing data support for the algorithm execution of the fault prediction module; The memory module is used to store the historical operation data of the motor drive, including the historical records of current, voltage, temperature and speed, for the fault prediction module to perform machine learning model training and real-time reasoning. The memory module also temporarily stores real-time monitoring data to ensure that the dynamic control module can obtain sufficient data for protection decisions. The memory module communicates with the central processing unit and the fault prediction module to ensure efficient access to data; The power management module is electrically connected to the central processing unit to dynamically adjust the energy consumption strategy according to the motor operation status.

2. A motor driver protection device according to claim 1, characterized in that: The fault prediction module executes the machine learning dynamic fault prediction algorithm through the embedded chip. The specific process includes: S1: obtain current, voltage, temperature and speed data from the sensor module in real time; S2: The LSTM model in the embedded chip accelerates the processing of historical data and real-time data by calling the accelerated matrix operation unit (MAC) on the chip to establish a prediction model; S3: The chip’s embedded memory caches input data and predicts the state at future times based on the fault prediction formula; S4: When the deviation between the prediction result and the safety threshold exceeds the set range, a warning signal is sent to the dynamic control module.

3. A motor driver protection device according to claim 2, characterized in that: The fault prediction formula includes: P(t+Δt)=f(W⋅D(t)+b) Among them, P(t+Δt) represents the predicted value of the motor driver state at the future time t+Δt, which is the output of the fault prediction algorithm; W is the weight matrix, which is used to weight the input data. This matrix is ​​trained by the machine learning model (LSTM) and represents the importance of different input features. D(t) is the real-time data input vector at the current time t, including the parameters of current, temperature, speed and voltage; b is the bias term, which adjusts the offset of the prediction model output; f is the activation function, which is used to perform nonlinear transformation on linear output and improve the fitting ability of the model.

4. A motor driver protection device according to claim 3, characterized in that: The dynamic control module adopts a multi-level risk assessment algorithm and uses a risk factor calculation formula to perform risk assessment on the motor driver. The specific steps include: S1: Get real-time data of current, temperature and speed from the sensor module; S2: Calculate the risk factor according to the risk factor calculation formula; S3: Divide the risk factors into different fault levels and send corresponding control signals to the dynamic control module.

5. A motor driver protection device according to claim 4, characterized in that: The risk factor calculation formula includes: Among them, R(t) is the risk factor, which is the real-time fault risk value of the motor drive calculated at the current time t; α, β and γ are weighting coefficients, which are used to adjust the influence weights of current, temperature and speed on risk factors respectively. In actual use, the values ​​of these coefficients can be adjusted according to the characteristics of the equipment or the fault history; dI(t) is the current change rate, which indicates the rate of change of current over time; dT(t) is the temperature change rate, which indicates the rate of change of temperature over time; dw(t) is the speed change rate, which indicates the rate of change of the motor speed over time and is used to detect whether the motor has load fluctuations.

6. A motor driver protection device according to claim 5, characterized in that: The dynamic control module dynamically adjusts the output power of the motor through an adaptive power control algorithm. The specific steps of the adaptive power control algorithm include: S1: receiving the risk factor value of the multi-level risk assessment algorithm; S2: Preset multiple fault level thresholds based on the risk factor R(t) calculated in real time: Warning threshold R(w): When R(t) exceeds this threshold but does not reach the fault level, the execution module sends a warning signal to the central control system through the communication interface to remind the operator to check, but no immediate protective measures are taken; Fault threshold R(f): When R(t) reaches or exceeds this threshold, the dynamic control module triggers some protection measures and adjusts the power output of the motor through the adaptive power adjustment formula; Emergency stop threshold R(e): When R(t) reaches or exceeds this threshold, the execution module triggers an emergency stop operation through a high-speed electronic relay, cutting off the power supply to the motor driver to prevent equipment damage.

7. A motor driver protection device according to claim 6, characterized in that: The adaptive power adjustment formula includes: Among them, G(t) power gain control quantity is the motor output power after adjustment at time t, which is the result of dynamically adjusting the motor driver output; K p is the proportionality coefficient, which indicates the response speed of the power gain to the prediction deviation; K d is the differential coefficient, which is used to adjust the response of the power gain to the rate of change of the deviation; δ(t) is the prediction deviation, which indicates the difference between the predicted state value and the current actual state; dδ(t) is the rate of change of the prediction deviation, which is used to detect whether the deviation between the predicted value and the actual value increases sharply in a short period of time, thereby dynamically adjusting the power output.

Images