Electric winch motor abnormity early warning system and early warning method

Abstract

The invention belongs to the technical field of equipment fault early warning, and particularly relates to an electric winch motor abnormity early warning system and early warning method. An electric winch motor abnormity early warning system comprises an on-site monitoring control module, a monitoring center and a management personnel terminal, the on-site monitoring control module comprises an equipment monitoring module, a control module, a single-chip microcomputer module and an Internet of Things module, the equipment monitoring module is electrically connected with the single-chip microcomputer module, the single-chip microcomputer module is electrically connected with the Internet of Things module, and the control module is electrically connected with the management personnel terminal. The Internet of Things module is in wireless connection with the monitoring center, and the monitoring center is used for analyzing monitoring data of the equipment monitoring module, sending a control signal to the control module and sending equipment maintenance information to the management personnel terminal. Parameters such as current, voltage and temperature of the motor during working of the winch are monitored in real time, the working state of the motor of the winch is analyzed by adopting a machine learning algorithm, early warning is performed on possible abnormal states, operation of the motor is controlled through the control module, and risk accidents are prevented.

Description

Technical Field

[0001] The invention belongs to the technical field of equipment failure early warning, and in particular relates to an abnormal early warning system and early warning method for an electric winch motor. Background Art

[0002] A winch is a machine used to lift vertically, pull heavy objects horizontally or at an angle. It is divided into three types: manual winch, electric winch and hydraulic winch. Electric winches are the main type and are widely used in the fields of construction, water conservancy projects, forestry, mining, docks, etc. As the main engineering machinery, electric winches are used frequently and have long operating time. Their working stability is the prerequisite for project progress and safety assurance.

[0003] At present, regular inspection and maintenance are basically adopted to ensure its normal operation. Repairs are usually carried out after a failure occurs. There is a lack of health monitoring during the use process, and it is impossible to predict possible failures during operation, which ultimately leads to delays in construction and even casualties. Summary of the invention

[0004] In view of the above problems, the purpose of the present invention is to provide an electric winch motor abnormality warning system and warning method. The system monitors the motor parameters such as current, voltage and temperature when the winch is working in real time, uses a machine learning algorithm to analyze the working status of the winch motor, and warns of possible abnormal conditions. The control module controls the operation of the motor to prevent risk accidents, ensure the safety of engineering operations, and realize intelligent and automated risk management.

[0005] The technical solution of the present invention is: an electric winch motor abnormality warning system, including a field monitoring control module, a monitoring center and a management personnel terminal, the field monitoring control module includes an equipment monitoring module, a control module, a single-chip computer module and an Internet of Things module, the control module, the single-chip computer module and the Internet of Things module are located in a control box, the equipment monitoring module is electrically connected to the single-chip computer module, the single-chip computer module is electrically connected to the Internet of Things module, the Internet of Things module and the monitoring center are wirelessly connected, the equipment monitoring module is used to monitor the operating parameters of the winch motor, the control module is used to control the brake and reducer of the winch motor, and the monitoring center is used to analyze the monitoring data of the equipment monitoring module and send control signals to the control module and send equipment maintenance information to the management personnel terminal.

[0006] The equipment monitoring module includes a current sensor, a voltage sensor and a temperature sensor, the current sensor and the voltage sensor are respectively connected to the circuit of the winch motor, the temperature sensor is located on the side of the winch motor away from the rope drum, and is used to collect the temperature of the winch motor. The current sensor, the voltage sensor and the temperature sensor are respectively electrically connected to the single-chip computer module in the control box, and the control box is fixed on the bottom frame.

[0007] The control module includes a PLC programmable controller and a relay, and the PLC programmable controller and the relay are respectively connected to the Internet of Things module, and are used to receive the control signal of the winch motor from the monitoring center, and control the winch motor according to the control signal.

[0008] An electric winch motor abnormality warning method, using the electric winch motor abnormality warning system as described above, comprises the following steps: S1: Use the equipment monitoring module to collect relevant parameters during the operation of the hoist motor: the current sensor and the voltage sensor collect the current and voltage data of the hoist motor respectively, and the temperature sensor is responsible for monitoring the temperature of the hoist motor during operation; the collected data is stored in the single-chip microcomputer module; S2: The MCU module pre-processes the collected data to obtain three feature vectors of current, voltage, and motor temperature; the IoT module sends the processed feature vectors to the monitoring center; S3: The monitoring center uses the improved support vector machine (SVM) model to identify and analyze abnormal conditions that may occur during the operation of the winch motor. When an abnormality occurs, the monitoring center sends a control signal to the PLC programmable controller, and the PLC programmable controller terminates the operation of the winch motor through a relay. At the same time, the monitoring center sends maintenance information to the management personnel terminal and arranges relevant personnel to perform maintenance.

[0009] In step S2, the single-chip microcomputer module uses a sliding average filter to process the current and voltage data. The specific process is: the 4 continuously monitored data are regarded as a queue, the length of the queue is fixed to 4, each time a new data is collected, it is put into the end of the queue, and the original data at the head of the queue is deleted, and the 4 data in the queue are arithmetic averaged to obtain a new filtering result. Assume that the original data X=(x1,x2,...x_n), the processed data is X'=(X1',X2',...XN'), and the Xi' calculation formula is: Xi'=1 / 4(Xi+X(i+1)+X(i+2)+X(i+3)), i=1,2,3...,n-3.

[0010] In step S3, the chicken swarm algorithm is used to optimize the penalty parameter c and the kernel function parameter g in the support vector machine SVM model, so as to identify and classify the collected data. The specific process is as follows: S31: Initial configuration algorithm parameters, including flock size, number of iterations, update frequency of population relationships, and the proportion of roosters, hens, and chicks in the flock; the position of each chicken in the flock is represented by two-dimensional coordinates (c, g), the classification accuracy of the SVM model is used as the fitness function, and the individual positions are randomly assigned before the iteration starts; S32: The rooster, hen and chick update their individual positions according to their respective position update strategies. If the fitness value of the new position is less than the fitness value of the old position, the position is updated, otherwise the position remains unchanged; S33: After reaching the maximum number of iterations, stop the calculation. At this time, the coordinates c and g at the position with the minimum fitness value are the optimal parameters.

[0011] In step S3, the monitoring center is equipped with an equipment monitoring database, in which the data include three characteristic vectors of the motor's current, voltage and temperature during each monitoring period and label values ​​1 and 0 corresponding to each time point, 1 represents normal equipment, 0 represents parameter abnormality, and an early warning is issued for training and testing of the SVM model.

[0012] The technical effects of the present invention are: 1. The on-site monitoring and control module of the present invention has a high degree of integration. Except for the equipment monitoring module which needs to be installed separately, the other modules are all installed in the control box in a centralized manner, which is convenient for installation; 2. The present invention adopts a machine learning algorithm to perform real-time analysis on the data collected on-site and to give early warning of possible faults. The entire fault identification process does not require human participation, thus realizing intelligent equipment supervision; 3. The present invention controls the operation of the motor through a PLC programmable controller, thus eliminating the potential safety hazards of accidents and realizing the automation of risk control.

[0013] The following is a further description with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 The present invention is an embodiment of an electric winch motor abnormality warning system structure control flow chart.

[0015] Figure 2 The present invention is a schematic structural diagram of an electric winch motor abnormality warning system according to an embodiment of the present invention.

[0016] Figure 3 It is a schematic diagram of the control box structure of an embodiment of the present invention.

[0017] Figure 4 This is a line graph before current data processing in Example 2.

[0018] Figure 5 This is a line graph of the current data after processing in Example 2.

[0019] Figure 6 This is a line graph of voltage data before processing in Example 2.

[0020] Figure 7 It is a line graph after voltage data processing in Example 2.

[0021] Figure 8 It is a scatter plot of the abnormality recognition results of the test set in Example 2.

[0022] Figure markings: 1-control box; 11-PLC programmable controller; 12-single chip microcomputer module; 13-relay; 14-Internet of Things module; 2-current sensor; 3-voltage sensor; 4-brake; 5-temperature sensor; 6-winch motor; 7-bottom frame; 8-rope drum; 9-reducer. Implementation

[0023] Example 1 Figure 1~Figure 3 As shown, an electric winch motor abnormality warning system includes a field monitoring control module, a monitoring center and a management personnel terminal, the field monitoring control module includes an equipment monitoring module, a control module, a single-chip computer module 12 and an Internet of Things module 14, the control module, the single-chip computer module 12 and the Internet of Things module 14 are located in a control box 1, the equipment monitoring module is electrically connected to the single-chip computer module 12, the single-chip computer module 12 is electrically connected to the Internet of Things module 14, the Internet of Things module 14 is wirelessly connected to the monitoring center, the equipment monitoring module is used to monitor the operating parameters of the winch motor 6, the control module is used to control the brake 4 and the reducer 9 of the winch motor 6, the monitoring center is used to analyze the monitoring data of the equipment monitoring module and send a control signal to the control module and send equipment maintenance information to the management personnel terminal.

[0024] The equipment monitoring module includes a current sensor 2, a voltage sensor 3 and a temperature sensor 5. The current sensor 2 and the voltage sensor 3 are respectively connected to the circuit of the winch motor 6. The temperature sensor 5 is located on the side of the winch motor 6 away from the rope drum 8 and is used to collect the temperature of the winch motor 6. The current sensor 2, the voltage sensor 3 and the temperature sensor 5 are respectively electrically connected to the single-chip computer module 12 in the control box 1. The control box 1 is fixed on the bottom frame 7.

[0025] The control module includes a PLC programmable controller 11 and a relay 13, and the PLC programmable controller 11 and the relay 13 are respectively connected to the Internet of Things module 14, and are used to receive the control signal of the monitoring center to the winch motor, and control the winch motor 6 according to the control signal.

[0026] Embodiment 2 A method for early warning of abnormality of an electric winch motor, using the electric winch motor abnormality early warning system as described above, comprises the following steps: S1: Use the equipment monitoring module to collect relevant parameters of the hoist motor 6 during operation: the current sensor 2 and the voltage sensor 3 collect the current and voltage data of the hoist motor 6 respectively, and the temperature sensor 5 is responsible for monitoring the temperature of the hoist motor 6 during operation; the collected data is stored in the single-chip computer module 12; S2: The single-chip computer module 12 pre-processes the collected data to obtain three feature vectors of current, voltage, and motor temperature; the Internet of Things module 14 sends the processed feature vectors to the monitoring center; S3: The monitoring center identifies and analyzes abnormal conditions that may occur during the operation of the hoist motor 6 through an improved support vector machine SVM model. When an abnormality occurs, the monitoring center sends a control signal to the PLC programmable controller 11, and the PLC programmable controller 11 terminates the operation of the hoist motor 6 through the relay 13; at the same time, the monitoring center sends maintenance information to the management personnel terminal and arranges relevant personnel to perform maintenance.

[0027] In step S2, the single-chip microcomputer module 11 uses a sliding average filter to process the current and voltage data. The specific process is: the 4 continuously monitored data are regarded as a queue, the length of the queue is fixed to 4, each time a new data is collected, it is put into the end of the queue, and the original data at the head of the queue is deleted, and the 4 data in the queue are arithmetic averaged to obtain a new filtering result. Assume that the original data X=(x1,x2,...x_n), the processed data is X'=(X1',X2',...XN'), and the Xi' calculation formula is: Xi'=1 / 4(Xi+X(i+1)+X(i+2)+X(i+3)), i=1,2,3...,n-3.

[0028] In step S3, the chicken swarm algorithm is used to optimize the penalty parameter c and the kernel function parameter g in the support vector machine SVM model, so as to identify and classify the collected data. The specific process is as follows: S31: Initial configuration algorithm parameters, including flock size, number of iterations, update frequency of population relationships, and the proportion of roosters, hens, and chicks in the flock; the position of each chicken in the flock is represented by two-dimensional coordinates (c, g), the classification accuracy of the SVM model is used as the fitness function, and the individual positions are randomly assigned before the iteration starts; S32: The rooster, hen and chick update their individual positions according to their respective position update strategies. If the fitness value of the new position is less than the fitness value of the old position, the position is updated, otherwise the position remains unchanged; S33: After reaching the maximum number of iterations, stop the calculation. At this time, the coordinates c and g at the position with the minimum fitness value are the optimal parameters.

[0029] In step S3, the monitoring center is equipped with an equipment monitoring database, in which the data include three characteristic vectors of the motor's current, voltage and temperature during each monitoring period and label values ​​1 and 0 corresponding to each time point, 1 represents normal equipment, 0 represents parameter abnormality, and an early warning is issued for training and testing of the SVM model. Example

[0030] Based on Example 1 and Example 2, this example will use the system to perform abnormal warning of the electric winch motor. The electric winch abnormal warning is performed based on the data collected by the current sensor, voltage sensor and temperature sensor over a period of time. The specific steps are as follows: S1: Use the equipment monitoring module to collect relevant parameters of the equipment during operation in a certain period of time: the current sensor and the voltage sensor collect the current and voltage data of the motor respectively, and the temperature sensor is responsible for monitoring the temperature of the motor. A total of 441 sets of data are collected and stored in the single-chip microcomputer module, as shown in Table 1 below; Table 1: Part of the original collected data Current (A) Voltage (V) Temperature (°C) 14.72 222.5875186 52 14.76 222.5680225 52 14.62 222.3793261 66 14.62 222.5968323 78 14.7 222.4749774 79 S2: The single-chip microcomputer module uses a sliding average filter to pre-process the collected current and voltage data. The four consecutively collected data are regarded as a queue. The length of the queue is fixed to 4. Each time a new data is collected, it is put into the end of the queue, and the original data at the head of the queue is deleted. The four data in the queue are arithmetic averaged to obtain a new filtering result. Assume that the original data X=(x1,x2,...xn), the processed data is X'=(X1',X2',...XN'), and the Xi' calculation formula is as follows: Xi'=1 / 4(Xi+X(i+1)+X(i+2)+X(i+3)),i=1,2,3...,n-3 According to the above formula, the original data of current and voltage are processed. The results before and after processing are as follows Figure 4 , Figure 5 , Figure 6 , Figure 7 As shown; S3: The IoT module sends the processed feature quantity to the monitoring center, which issues an early warning for abnormal conditions that may occur during the operation of the electric winch through the improved support vector machine (SVM) model. The abnormal conditions are determined according to the following requirements: the temperature of the winch motor shall not exceed 110°C, the power supply voltage shall not exceed ±5% of the rated value, and the current shall not exceed 1.2 times the rated value. The data is classified according to the above requirements, with corresponding label values ​​of 1 and 0, where 1 represents normal equipment and 0 represents parameter abnormality, and an early warning is issued. First, the collected data is divided into a test set and a training set, with 356 sets in the training set and 85 sets in the test set. The data are assigned labels of 0 and 1 according to the above requirements. At the same time, in order to eliminate the influence of the variable dimension, the current, voltage and temperature data are normalized according to the following formula: yi=(xi-xmin) / (xmax-xmin ),i=1,2,3...N Among them, xi and yi are the data before and after normalization, respectively, and xmin and xmax are the minimum and maximum values ​​of the data before normalization, respectively; Then the chicken swarm algorithm is used to analyze the training set data to solve the penalty parameter c and kernel function parameter g of the SVM model. The initial value of the algorithm is: the number of iterations M=500, the total number of chickens pop=50, of which the proportion of hens is 0.7, the proportion of roosters is 0.15, and the proportion of chicks is 0.15. The position coordinates of each chicken are (c, g). Because the iterative process is too cumbersome, the calculation is completed with the help of MATLAB. The fitness function code is as follows: fitfunc=svmtrain(train_labels,train_data,cmd) Among them, svmtrain is the SVM model function; train_labels is the training set data label, train_data is the training set data, including current, voltage and temperature data; cmd is the model parameter.

[0031] According to the position update strategy of roosters, hens and chicks, iterative calculations are performed to obtain the optimal parameters c=18.3412 and g=7.7801. The optimal parameters are substituted into the SVM model to test the test set data. The classification results of the model for the test set are as follows: Figure 8 .from Figure 8 It can be seen that among the 85 test sets, only 5 groups were not correctly classified, and the accuracy of the model classification was 94.12%, that is, the early warning method of the present invention can identify 94.12% of the abnormal states of the electric winch, and the recognition accuracy is relatively high.

[0032] When an abnormal state is identified, the monitoring center sends a control signal to the control module, and the PLC programmable controller controls the relay to terminate the motor operation; at the same time, the monitoring center sends maintenance information to the management personnel terminal and arranges relevant personnel to perform maintenance.

[0033] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by any technician familiar with the technical field within the technical scope disclosed by the present invention should be covered within the protection scope of the present invention.

Claims

1. An electric winch motor abnormality warning system, characterized in that: The invention comprises a field monitoring control module, a monitoring center and a management personnel terminal. The field monitoring control module comprises a device monitoring module, a control module, a single-chip computer module (12) and an Internet of Things module (14). The control module, the single-chip computer module (12) and the Internet of Things module (14) are located in a control box (1). The device monitoring module is electrically connected to the single-chip computer module (12). The single-chip computer module (12) is electrically connected to the Internet of Things module (14). The Internet of Things module (14) is wirelessly connected to the monitoring center. The device monitoring module is used to monitor the operating parameters of a hoist motor (6). The control module is used to control a brake (4) and a reducer (9) of the hoist motor (6). The monitoring center is used to analyze the monitoring data of the device monitoring module and send a control signal to the control module and send device maintenance information to the management personnel terminal.

2. According to claim 1, an electric winch motor abnormality warning system is characterized in that: The equipment monitoring module comprises a current sensor (2), a voltage sensor (3) and a temperature sensor (5); the current sensor (2) and the voltage sensor (3) are respectively connected to the circuit of the hoist motor (6); the temperature sensor (5) is located on the side of the hoist motor (6) away from the rope drum (8) and is used to collect the temperature of the hoist motor (6); the current sensor (2), the voltage sensor (3) and the temperature sensor (5) are respectively electrically connected to the single chip microcomputer module (12) in the control box (1); and the control box (1) is fixedly arranged on the bottom frame (7).

3. According to claim 1, the electric winch motor abnormality warning system is characterized in that: The control module comprises a PLC programmable controller (11) and a relay (13), wherein the PLC programmable controller (11) and the relay (13) are respectively connected to an Internet of Things module (14) and are used to receive a control signal from the monitoring center to the hoist motor, and control the hoist motor (6) according to the control signal.

4. An electric winch motor abnormality warning method, using an electric winch motor abnormality warning system as claimed in claims 1 to 3, characterized in that: The following steps are involved: S1: using the equipment monitoring module to collect relevant parameters of the hoisting machine motor (6) during operation: the current sensor (2) and the voltage sensor (3) respectively collect the current and voltage data of the hoisting machine motor (6), and the temperature sensor (5) is responsible for monitoring the temperature of the hoisting machine motor (6) during operation; the collected data is stored in the single chip computer module (12); S2: The single-chip computer module (12) pre-processes the collected data to obtain three feature vectors of current, voltage, and motor temperature; the Internet of Things module (14) sends the processed feature vectors to the monitoring center; S3: The monitoring center uses an improved support vector machine (SVM) model to identify and analyze abnormal conditions that may occur during the operation of the hoist motor (6). When an abnormality occurs, the monitoring center sends a control signal to the PLC programmable controller (11), and the PLC programmable controller (11) terminates the operation of the hoist motor (6) through the relay (13). At the same time, the monitoring center sends maintenance information to the management personnel terminal and arranges relevant personnel to perform maintenance.

5. The electric winch motor abnormality early warning method according to claim 4, characterized in that: In step S2, the single-chip computer module (11) uses a sliding average filter to process the current and voltage data. The specific process is as follows: the four continuously monitored data are regarded as a queue, the length of the queue is fixed to 4, each time a new data is collected, it is put into the end of the queue, and the original data at the head of the queue is deleted, and the four data in the queue are arithmetic averaged to obtain a new filtering result. Assume that the original data X=(x1,x2,...x_n), the processed data is X'=(X1',X2',...XN'), and the calculation formula of Xi' is: Xi'=1 / 4(Xi+X(i+1)+X(i+2)+X(i+3)), i=1,2,3...,n-3.

6. The electric winch motor abnormality early warning method according to claim 4, characterized in that: In step S3, the chicken swarm algorithm is used to optimize the penalty parameter c and the kernel function parameter g in the support vector machine SVM model, so as to identify and classify the collected data. The specific process is as follows: S31: Initial configuration algorithm parameters, including flock size, number of iterations, update frequency of population relationships, and the proportion of roosters, hens, and chicks in the flock; the position of each chicken in the flock is represented by two-dimensional coordinates (c, g), the classification accuracy of the SVM model is used as the fitness function, and the individual positions are randomly assigned before the iteration starts; S32: The rooster, hen and chick update their individual positions according to their respective position update strategies. If the fitness value of the new position is less than the fitness value of the old position, the position is updated, otherwise the position remains unchanged; S33: After reaching the maximum number of iterations, stop the calculation. At this time, the coordinates c and g at the position with the minimum fitness value are the optimal parameters.

7. The electric winch motor abnormality early warning method according to claim 4, characterized in that: In step S3, the monitoring center is equipped with an equipment monitoring database, in which the data include three characteristic vectors of the motor's current, voltage and temperature during each monitoring period and label values ​​1 and 0 corresponding to each time point, 1 represents normal equipment, 0 represents parameter abnormality, and an early warning is issued for training and testing of the SVM model.

Images