Chain saw motor self-protection system

Abstract

The invention provides a chain saw motor self-protection system, which belongs to the technical field of motor self-protection and comprises a temperature sensor module, a current sensor module, a vibration sensor module, a rotating speed sensor module, a data acquisition module, a motor rotating speed and data analysis unit, a wireless module and a recognition model and prediction model training unit. Vibration and current data of a chain saw motor are collected in real time, then the material to be cut is judged, and then the corresponding cutting speed is set according to the specific material, so that the cutting efficiency is higher, meanwhile, the chain saw is prevented from being damaged, meanwhile, possible faults or risks of the motor are predicted in real time, the speed of the motor is controlled in time, and the service life of the chain saw is prolonged. Faults or cutting accidents of the motor are effectively avoided, and self-protection of the motor is achieved.

Description

Technical Field

[0001] The invention relates to the technical field of motor self-protection, and in particular to a chain saw motor self-protection system. Background Art

[0002] Traditional motor protection devices are often based on circuit overcurrent protection. Sensors are installed in the internal circuit of the motor to detect whether the circuit is overloaded to ensure the safety of the motor. However, long-term operation of the motor causes serious heat accumulation inside the motor. The heat inside the motor cannot be dissipated efficiently and quickly, thereby damaging the motor and affecting its normal operation.

[0003] At present, the motor detects the actual fault point or high temperature to control the motor to stop and perform other operations. These control operations are relatively rough, which makes the user experience poor. At the same time, it is impossible to sense the cutting material in advance and accurately control the motor. It is impossible to achieve soft control and protection of the motor. Therefore, it is necessary to design a chain saw motor self-protection system. Summary of the invention

[0004] The purpose of the present invention is to provide a chain saw motor self-protection system to solve the technical problem that the existing chain saw motor cannot sense the cutting material and then make precise control and cannot accurately protect the motor.

[0005] In order to achieve the above object, the technical solution adopted by the present invention is as follows:

[0006] A chain saw motor self-protection system comprises a temperature sensor module, a current sensor module, a vibration sensor module, a rotation speed sensor module, a data acquisition module, a motor rotation speed and data analysis unit, a wireless module and a recognition model and prediction model training unit. The temperature sensor module, the current sensor module, the vibration sensor module and the rotation speed sensor module are all connected to the motor rotation speed and data analysis unit via the data acquisition module. The motor rotation speed and data analysis unit is connected to the recognition model and prediction model training unit and an external user's mobile phone via the wireless module. The motor rotation speed and data analysis unit is used to analyze the collected data to identify the material characteristics of the cut object, and then control the motor to be at an optimal cutting speed. The recognition model and prediction model training unit is used to remotely train the recognition model and prediction model in real time, and then send the trained model to the motor rotation speed and data analysis unit.

[0007] Furthermore, a temperature sensor module is installed inside the motor to monitor the temperature of the motor windings and bearings. The temperature sensor is embedded in or attached to the stator winding to directly measure the winding temperature. The vibration sensor module is used to collect the vibration of the chain saw motor to determine the hardness of the cutting object and whether there is any looseness inside the motor based on the vibration.

[0008] Furthermore, the chain saw motor includes a housing, a rotating shaft, a rotor assembly, an electric drive, a stator assembly and a connecting piece, the housing is fixed on the rotating shaft, the rotor assembly is arranged inside the housing, the electric drive is arranged inside the rotor assembly, the stator assembly is arranged inside the electric drive, the connecting piece is connected to the stator assembly, the rotating shaft passes through the stator assembly, and a moving bearing is arranged between the rotating shaft and the stator assembly, the rotating shaft passes through the connecting piece, and a supporting bearing is arranged between the rotating shaft and the connecting piece.

[0009] Furthermore, the motor speed and data analysis unit includes a motor speed control module, a cutting material identification module, a risk prediction module and a data update communication module. The cutting material identification module is used to identify the material properties of the object cut by the chain saw motor, and give specific motor control parameters according to the material properties, and transmit the motor control parameters to the motor speed control module. The risk prediction module is used to identify the current state of the motor, and then predict the risks that may occur in the future time period, and then make the control parameters of the control measures in advance, and then transmit the control parameters of the control measures to the motor speed control module. The data update communication module communicates with the recognition model and prediction model training unit through the wireless module at regular intervals, and regularly obtains updated recognition models and prediction models. When the user feeds back data to the data update communication module through the mobile phone according to the actual cutting scene, the data update communication module transmits the data to the recognition model and prediction model training unit through the wireless module for training.

[0010] Furthermore, the identification model and prediction model training unit includes a cutting material identification model training module and a motor risk prediction model training module. The cutting material identification model training module and the motor risk prediction model training module are used to obtain relevant operation and cutting data of the corresponding series model motors from the Internet in real time, update the cutting material identification model and the motor risk prediction model regularly, and reach the updated model to the cutting material identification module and the risk prediction module.

[0011] Furthermore, the process of identification by the cutting material identification module is as follows:

[0012] Step 1: When the chain saw motor cuts an object, the vibration sensor module, the temperature sensor module, the current sensor module and the speed sensor module collect the data of the motor and send it to the motor speed and data analysis unit to obtain initial analysis data. When the motor starts cutting, it starts to collect vibration data, temperature data, speed and current data after a fixed time, and then transmits the collected data to the motor speed and data analysis unit. The data is used as initial data and as data for initial judgment of cutting properties;

[0013] Step 2: The collected data is transmitted to the motor speed and data analysis unit to identify and judge the characteristics of the cutting material. By collecting the vibration data, temperature data, speed and current data of various objects when cutting, the collected data is the same as the set benchmark cutting state, and then all the collected data is input into the recognition model and prediction model training unit for training to obtain the recognition model, and then the recognition model is transmitted to the motor speed and data analysis unit through the network. The motor speed and data analysis unit periodically obtains the updated recognition model from the set Internet system to make the recognition analysis data more accurate;

[0014] The collected data is transferred to the recognition training model for recognition, and then the recognition training model outputs the characteristic data of the specific cutting material;

[0015] Step 3: The motor speed and data analysis unit sets the corresponding initial optimal speed according to the characteristics of the cutting material. The motor speed and data analysis unit contains mapping labels of relevant cutting material characteristic data and cutting control parameters. Through the output cutting material characteristics, the corresponding optimal control parameters are directly found, and then the motor speed control and data analysis device controls the corresponding speed of the chain saw motor;

[0016] Step 4: Collect data again, and identify and judge the optimal cutting speed again through the motor speed and data analysis unit based on the collected data and material characteristics, and then the motor speed and data analysis unit controls the corresponding cutting speed. After the set parameters are output, the sensor collects data in real time, and then compares the collected data with the output control parameters, and then determines whether the last control parameter is already the optimal data. If it is the optimal data, continue to use the last control parameter for control. When the collected data shows that it is not the optimal data, it is put into the recognition model for re-identification, and then the secondary output material characteristics are obtained, and then the corresponding control parameters are searched to control the chain saw motor;

[0017] Step 5: Upload the collected and identified material data to the user's mobile phone. The user checks whether the cutting material is correct. If not, enter the correct cutting material. Then the motor speed and data analysis unit replaces the corresponding cutting material parameters to achieve real-time parameter update. After one cutting is completed, the motor speed control and data analysis device will transmit the data of the cutting material judged by the collected data of this cutting to the bound user's mobile phone. The user checks whether it is consistent with the material he actually cut. If it is consistent, he will confirm it. If it is not consistent, he will enter the actual cutting material and then search for the material characteristic data from the Internet. Then return to the motor speed and data analysis unit, and then the motor speed and data analysis unit will feed back to the recognition model and prediction model training unit. The recognition model and prediction model training unit will further refine the recognition model and then transmit it back to the motor speed and data analysis unit.

[0018] Furthermore, the specific process of risk prediction module predicting risk is as follows: obtaining the Yuxing parameters of the same series of motors before failure or accident, summarizing the collected data, and then classifying it. The trained model is classified according to the type of fault. During identification, the risk prediction module directly identifies and outputs the fault type and risk level. When there is no fault risk, it outputs a normal value. When there is a risk of fault, the motor speed control module is used to control the motor to reduce speed, stop running, or sound an alarm to inform the user, and transmit the fault risk to the user's mobile phone in real time. After checking the mobile phone, the user will feedback the actual risk of the motor. If there is no risk, the user will feedback risk-free data, and then the recognition model and prediction model training unit will retrain and update a new risk prediction model.

[0019] The present invention has the following beneficial effects due to the adoption of the above technical solution:

[0020] The present invention collects the vibration and current data of the chain saw motor in real time, determines what material is being cut, and then sets the corresponding cutting speed according to the specific material, so as to improve the cutting efficiency and avoid damage to the chain saw. At the same time, the present invention predicts possible failures or risks of the motor in real time, controls the speed of the motor in time, effectively avoids motor failures or cutting accidents, and realizes self-protection of the motor. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 It is a module block diagram of the protection system of the present invention;

[0022] Figure 2 It is a cross-sectional view of the chain saw motor of the present invention.

[0023] In the attached drawings, 1-housing, 2-rotating shaft, 3-rotor assembly, 4-electric drive, 5-stator assembly, 6-motion bearing, 7-connector, 8-support bearing. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below with reference to the accompanying drawings and preferred embodiments. However, it should be noted that many details listed in the specification are only for the purpose of enabling the reader to have a thorough understanding of one or more aspects of the present invention, and these aspects of the present invention can be implemented even without these specific details.

[0025] like Figure 1 As shown, a chain saw motor self-protection system includes a temperature sensor module, a current sensor module, a vibration sensor module, a speed sensor module, a data acquisition module, a motor speed and data analysis unit, a wireless module and a recognition model and prediction model training unit. The temperature sensor module, the current sensor module, the vibration sensor module and the speed sensor module are all connected to the motor speed and data analysis unit through the data acquisition module. The motor speed and data analysis unit is connected to the recognition model and prediction model training unit and an external user's mobile phone through the wireless module; the motor speed and data analysis unit is used to analyze the collected data to identify the material characteristics of the cut object, and then control the motor to be at an optimal cutting speed. The recognition model and prediction model training unit is used to remotely train the recognition model and prediction model in real time, and then send the trained model to the motor speed and data analysis unit.

[0026] In an embodiment of the present invention, a temperature sensor module is installed inside the motor to monitor the temperature of the motor windings and bearings. The temperature sensor is embedded in or attached to the stator windings to directly measure the winding temperature. The vibration sensor module is used to collect the vibration of the chain saw motor to determine the hardness of the cutting object and whether there is any looseness inside the motor based on the vibration.

[0027] In the embodiment of the present invention, Figure 2 As shown, the chain saw motor includes a housing 1, a rotating shaft 2, a rotor assembly 3, an electric drive 4, a stator assembly 5 and a connecting piece 7. The housing 1 is fixed on the rotating shaft 2, the rotor assembly 3 is arranged inside the housing 1, the electric drive 4 is arranged inside the rotor assembly 3, the stator assembly 5 is arranged inside the electric drive 4, the connecting piece 7 is connected to the stator assembly 5, the rotating shaft 2 passes through the stator assembly 5, and a moving bearing 6 is arranged between the rotating shaft 2 and the stator assembly 5, the rotating shaft 2 passes through the connecting piece 7, and a supporting bearing 8 is arranged between the rotating shaft 2 and the connecting piece 7.

[0028] The motor shaft 2 is an outer rotor with 12 slots and 14 poles, with a rotor outer diameter of 62mm, a rotor inner diameter of 56.6mm, a permanent magnet outer diameter of 56.6mm, a permanent magnet inner diameter of 50.6mm, a stator outer diameter of 49.4mm, a shaft diameter of 12mm, and an axial length of 25mm.

[0029] The electric drive 4 has a winding spacing of 0.02mm, a slot insulation of 0.15mm, an end winding ≤5mm, and a split winding form. When the speed is less than 5100rpm in low-speed conditions, each phase has 8 turns of winding with 5 wires per turn wound in parallel. When the speed is less than 11000rpm in medium-speed conditions, the winding is changed to 4 turns of winding with 10 wires per turn wound in parallel per phase through a tap. When the speed is less than 21000rpm in high-speed conditions, the winding is changed to 2 turns of winding with 20 wires per turn wound in parallel per phase through a tap.

[0030] The rotor assembly 3 and the stator assembly 5 are made of JFE 0.1mm JNEX900 silicon steel sheet, the shaft is 45 steel, ball bearings, and the magnetic steel is NdFeB N48 radial magnetization. The permanent magnet is attached to the inner side of the outer rotor, and the permanent magnet is installed in two axial segments. The permanent magnet has an arc. The maximum speed of the motor under no-load weak magnetic control is 21000RPM, and the load is 11000RPM, 1.6N·m, and the output speed of 4N·m under load is ≥4250RPM. The chain saw motor has the characteristics of high speed, which can make the saw blade rotate more times per unit time, thereby achieving fast cutting. The speed of the electric saw motor can reach several 14000rpm, which can quickly and accurately complete the cutting operation, reducing the operation time and labor costs.

[0031] In the embodiment of the present invention, Figure 1 As shown, the motor speed and data analysis unit includes a motor speed control module, a cutting material identification module, a risk prediction module and a data update communication module. The cutting material identification module is used to identify the material characteristics of the object cut by the chain saw motor, and give specific motor control parameters according to the material characteristics, and transmit the motor control parameters to the motor speed control module. The risk prediction module is used to identify the current state of the motor, and then predict the risks that may occur in the future time period, and then make the control parameters of the control measures in advance, and then transmit the control parameters of the control measures to the motor speed control module. The data update communication module communicates with the recognition model and prediction model training unit through the wireless module at regular intervals, and regularly obtains updated recognition models and prediction models. When the user feeds back data to the data update communication module through the mobile phone according to the actual cutting scene, the data update communication module transmits the data to the recognition model and prediction model training unit through the wireless module for training.

[0032] In the embodiment of the present invention, Figure 1 As shown, the identification model and prediction model training unit includes a cutting material identification model training module and a motor risk prediction model training module. The cutting material identification model training module and the motor risk prediction model training module are used to obtain relevant operation and cutting data of the corresponding series of motors from the Internet in real time, update the cutting material identification model and the motor risk prediction model regularly, and reach the updated model to the cutting material identification module and the risk prediction module.

[0033] In the embodiment of the present invention, the process of identification by the cutting material identification module is as follows:

[0034] Step 1: When the chain saw motor cuts an object, the vibration sensor module, the temperature sensor module, the current sensor module and the speed sensor module collect the data of the motor and send it to the motor speed and data analysis unit to obtain initial analysis data. When the motor starts cutting, it starts to collect vibration data, temperature data, speed and current data after a fixed time, and then transmits the collected data to the motor speed and data analysis unit. The data is used as initial data and as data for initial judgment of cutting properties;

[0035] Step 2: The collected data is transmitted to the motor speed and data analysis unit to identify and judge the characteristics of the cutting material. By collecting the vibration data, temperature data, speed and current data of various objects when cutting, the collected data is the same as the set benchmark cutting state, and then all the collected data is input into the recognition model and prediction model training unit for training to obtain the recognition model, and then the recognition model is transmitted to the motor speed and data analysis unit through the network. The motor speed and data analysis unit periodically obtains the updated recognition model from the set Internet system to make the recognition analysis data more accurate;

[0036] The collected data is transferred to the recognition training model for recognition, and then the recognition training model outputs the characteristic data of the specific cutting material;

[0037] Step 3: The motor speed and data analysis unit sets the corresponding initial optimal speed according to the characteristics of the cutting material. The motor speed and data analysis unit contains mapping labels of relevant cutting material characteristic data and cutting control parameters. Through the output cutting material characteristics, the corresponding optimal control parameters are directly found, and then the motor speed control and data analysis device controls the corresponding speed of the chain saw motor;

[0038] Step 4: Collect data again, and identify and judge the optimal cutting speed again through the motor speed and data analysis unit based on the collected data and material characteristics, and then the motor speed and data analysis unit controls the corresponding cutting speed. After the set parameters are output, the sensor collects data in real time, and then compares the collected data with the output control parameters, and then determines whether the last control parameter is already the optimal data. If it is the optimal data, continue to use the last control parameter for control. When the collected data shows that it is not the optimal data, it is put into the recognition model for re-identification, and then the secondary output material characteristics are obtained, and then the corresponding control parameters are searched to control the chain saw motor;

[0039] Step 5: Upload the collected and identified material data to the user's mobile phone. The user checks whether the cutting material is correct. If not, enter the correct cutting material. Then the motor speed and data analysis unit replaces the corresponding cutting material parameters to achieve real-time parameter update. After one cutting is completed, the motor speed control and data analysis device will transmit the data of the cutting material judged by the collected data of this cutting to the bound user's mobile phone. The user checks whether it is consistent with the material he actually cut. If it is consistent, he will confirm it. If it is not consistent, he will enter the actual cutting material and then search for the material characteristic data from the Internet. Then return to the motor speed and data analysis unit, and then the motor speed and data analysis unit will feed back to the recognition model and prediction model training unit. The recognition model and prediction model training unit will further refine the recognition model and then transmit it back to the motor speed and data analysis unit.

[0040] In an embodiment of the present invention, the specific process of risk prediction module predicting risk is: obtaining the Yuxing parameters of motors of the same series and model before failure or accident, and summarizing the collected data, and then classifying it. The trained model is classified according to the type of fault. During identification, the risk prediction module directly identifies and outputs the fault type and the level of risk. When there is no risk of failure, it outputs a normal value. When there is a risk of failure, the motor speed control module is used to control the motor to reduce speed, stop running, or sound an alarm to inform the user, and transmit the fault risk to the user's mobile phone in real time. After checking, the user's mobile phone will feedback the actual risk that the motor may have. If there is no risk, the user will feedback risk-free data, and then the recognition model and prediction model training unit will retrain and update a new risk prediction model.

[0041] Monitoring the temperature of key parts such as motor windings and bearings is essential to ensure safe operation of the motor. Excessive temperature will not only reduce motor efficiency, but may also cause aging of insulation materials, damage to mechanical components, and even cause fire. Building a comprehensive and effective chain saw motor self-protection system that can not only respond quickly in emergency situations, but also prevent potential problems through continuous data collection and analysis, thereby significantly extending the life of the motor and ensuring the safety of operators.

[0042] The system collects the vibration and current data of the chain saw motor in real time, determines what material is being cut, and then sets the corresponding cutting speed based on the specific material, making the cutting more efficient while avoiding damage to the chain saw. At the same time, it predicts possible failures or risks of the motor in real time, controls the speed of the motor in time, effectively avoids motor failures or cutting accidents, and achieves self-protection of the motor.

[0043] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A chain saw motor self-protection system, characterized in that: It includes a temperature sensor module, a current sensor module, a vibration sensor module, a speed sensor module, a data acquisition module, a motor speed and data analysis unit, a wireless module and a recognition model and prediction model training unit. The temperature sensor module, the current sensor module, the vibration sensor module and the speed sensor module are connected to the motor speed and data analysis unit through the data acquisition module. The motor speed and data analysis unit is connected to the recognition model and prediction model training unit and an external user's mobile phone through the wireless module; the motor speed and data analysis unit is used to analyze the collected data to identify the material characteristics of the cut object, and then control the motor to be at the optimal cutting speed. The recognition model and prediction model training unit is used to remotely train the recognition model and prediction model in real time, and then send the trained model to the motor speed and data analysis unit.

2. A chain saw motor self-protection system according to claim 1, characterized in that: The temperature sensor module is installed inside the motor to monitor the temperature of the motor windings and bearings. The temperature sensor is embedded in or close to the stator windings to directly measure the winding temperature. The vibration sensor module is used to collect the vibration of the chain saw motor to determine the hardness of the cutting object and whether there is any looseness inside the motor based on the vibration.

3. A chain saw motor self-protection system according to claim 1, characterized in that: The chain saw motor comprises a housing (1), a rotating shaft (2), a rotor assembly (3), an electric drive (4), a stator assembly (5) and a connecting piece (7); the housing (1) is fixed on the rotating shaft (2); the rotor assembly (3) is arranged inside the housing (1); the electric drive (4) is arranged inside the rotor assembly (3); the stator assembly (5) is arranged inside the electric drive (4); the connecting piece (7) is connected to the stator assembly (5); the rotating shaft (2) passes through the stator assembly (5); a moving bearing (6) is arranged between the rotating shaft (2) and the stator assembly (5); the rotating shaft (2) passes through the connecting piece (7); and a supporting bearing (8) is arranged between the rotating shaft (2) and the connecting piece (7).

4. A chain saw motor self-protection system according to claim 1, characterized in that: The motor speed and data analysis unit includes a motor speed control module, a cutting material identification module, a risk prediction module and a data update communication module. The cutting material identification module is used to identify the material properties of the object cut by the chain saw motor, and give specific motor control parameters according to the material properties, and transmit the motor control parameters to the motor speed control module. The risk prediction module is used to identify the current state of the motor, and then predict the risks that may occur in the future time period, and then make the control parameters of the control measures in advance, and then transmit the control parameters of the control measures to the motor speed control module. The data update communication module communicates with the recognition model and prediction model training unit through the wireless module at regular intervals, and regularly obtains updated recognition models and prediction models. When the user feeds back data to the data update communication module through the mobile phone according to the actual cutting scene, the data update communication module transmits the data to the recognition model and prediction model training unit through the wireless module for training.

5. A chain saw motor self-protection system according to claim 1, characterized in that: The identification model and prediction model training unit includes a cutting material identification model training module and a motor risk prediction model training module. The cutting material identification model training module and the motor risk prediction model training module are used to obtain relevant operation and cutting data of the corresponding series and model motors from the Internet in real time, update the cutting material identification model and the motor risk prediction model regularly, and transmit the updated model to the cutting material identification module and the risk prediction module.

6. A chain saw motor self-protection system according to claim 4, characterized in that: The process of identification by the cutting material identification module is as follows: Step 1: When the chain saw motor cuts an object, the vibration sensor module, the temperature sensor module, the current sensor module and the speed sensor module collect the data of the motor and send it to the motor speed and data analysis unit to obtain initial analysis data. When the motor starts cutting, it starts to collect vibration data, temperature data, speed and current data after a fixed time, and then transmits the collected data to the motor speed and data analysis unit. The data is used as initial data and as data for initial judgment of cutting properties; Step 2: The collected data is transmitted to the motor speed and data analysis unit to identify and judge the characteristics of the cutting material. By collecting the vibration data, temperature data, speed and current data of various objects when cutting, the collected data is the same as the set benchmark cutting state, and then all the collected data is input into the recognition model and prediction model training unit for training to obtain the recognition model, and then the recognition model is transmitted to the motor speed and data analysis unit through the network. The motor speed and data analysis unit periodically obtains the updated recognition model from the set Internet system to make the recognition analysis data more accurate; The collected data is transferred to the recognition training model for recognition, and then the recognition training model outputs the characteristic data of the specific cutting material; Step 3: The motor speed and data analysis unit sets the corresponding initial optimal speed according to the characteristics of the cutting material. The motor speed and data analysis unit contains mapping labels of relevant cutting material characteristic data and cutting control parameters. Through the output cutting material characteristics, the corresponding optimal control parameters are directly found, and then the motor speed control and data analysis device controls the corresponding speed of the chain saw motor; Step 4: Collect data again, and identify and judge the optimal cutting speed again through the motor speed and data analysis unit based on the collected data and material characteristics, and then the motor speed and data analysis unit controls the corresponding cutting speed. After the set parameters are output, the sensor collects data in real time, and then compares the collected data with the output control parameters, and then determines whether the last control parameter is already the optimal data. If it is the optimal data, continue to use the last control parameter for control. When the collected data shows that it is not the optimal data, it is put into the recognition model for re-identification, and then the secondary output material characteristics are obtained, and then the corresponding control parameters are searched to control the chain saw motor; Step 5: Upload the collected and identified material data to the user's mobile phone. The user checks whether the cutting material is correct. If not, enter the correct cutting material. Then the motor speed and data analysis unit replaces the corresponding cutting material parameters to achieve real-time parameter update. After one cutting is completed, the motor speed control and data analysis device will transmit the data of the cutting material judged by the collected data of this cutting to the bound user's mobile phone. The user checks whether it is consistent with the material he actually cut. If it is consistent, he will confirm it. If it is not consistent, he will enter the actual cutting material and then search for the material characteristic data from the Internet. Then return to the motor speed and data analysis unit, and then the motor speed and data analysis unit will feed back to the recognition model and prediction model training unit. The recognition model and prediction model training unit will further refine the recognition model and then transmit it back to the motor speed and data analysis unit.

7. A chain saw motor self-protection system according to claim 4, characterized in that: The specific process of risk prediction module predicting risk is as follows: obtaining the Yuxing parameters of the same series of motors before failure or accident, summarizing the collected data, and then classifying it. The trained model is classified according to the type of fault. During identification, the risk prediction module directly identifies and outputs the fault type and risk level. When there is no fault risk, it outputs a normal value. If there is a risk of fault, the motor speed control module is used to control the motor to reduce speed, stop running, or sound an alarm to inform the user, and transmit the fault risk to the user's mobile phone in real time. After checking the mobile phone, the user will feedback the actual risk of the motor. If there is no risk, the user will feedback risk-free data, and then the recognition model and prediction model training unit will retrain and update a new risk prediction model.

Images