Servo motor micro-action non-power-outage self-checking method, system and device and medium

Through the combination of neural network model and high-precision servo motor and gearbox, the motor torque, speed and shaft current parameters are used for self-testing, which solves the detection difficulties and power outages caused by the long-term failure of the high-voltage switch operating mechanism, and realizes the High-precision, non-power failure detection.

CN118962434APending Publication Date: 2024-11-15ELECTRIC POWER RES INST OF GUANGXI POWER GRID CO LTD
View PDF 0 Cites 2 Cited by

Patent Information

Application Number
CN202410854651.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-06-28
Publication Date
2024-11-15

AI Technical Summary

Technical Problem

The high-voltage switch operating mechanism does not work for a long time, resulting in the inability to determine whether it can work normally. Regular inspections will cause power outages for users, and the judgment is expensive, so a continuous power detection method is urgently needed.

Method used

The neural network model is used to judge the motor torque, speed and shaft current parameters to determine whether it is a fault, type and degree of fault. Combined with a high-precision servo motor and gear box, it realizes a self-test of the high-voltage switch operating mechanism without power outage.

Benefits of technology

It realizes all-round high-precision automatic detection of mechanical failures, control failures and transmission component failures of high-voltage switch operating mechanisms, which maximizes judgment errors, avoids power outages from users, and reduces detection costs.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118962434A_ABST
    Figure CN118962434A_ABST
Patent Text Reader

Abstract

The invention discloses a servo motor micro-action non-power-outage self-checking method, system and device and a medium, and the method comprises the steps: carrying out the calculation of motor torque, rotating speed and shaft current parameters, whether a fault occurs or not, fault type judgment and fault degree, and inputting the parameters into a model for training; by inputting the existing motor torque, rotating speed and shaft current parameters into the model, whether a fault occurs, the fault type is judged, and the fault degree is judged. According to the servo motor micro-action non-power-outage self-checking method, system and device and the medium, the servo motor is controlled to be automatically executed through a program instruction, motor torque, rotating speed and q-axis current parameters are input into a trained neural network model for calculation and are compared with a model prediction result, when the error exceeds 5%, it is judged that the system has a jamming fault, and the self-checking process is finished. And when the error is less than 5%, the system is judged not to have a jam fault, so that judgment errors are avoided to the greatest extent, and all-dimensional high-precision automatic detection of mechanical faults, control faults and transmission part faults of the high-voltage switch operating mechanism is realized.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of motor technology, and in particular to a method, system, device and medium for self-checking micro-actions of a servo motor without power failure. Background Art

[0002] High-voltage switchgear is an indispensable and important part of the power system. During the operation of large power grids, the operating mechanism of high-voltage switches is in an inactive state for a long time. Due to the influence of the external environment and the degradation of the performance of its own components, re-operation may cause problems such as mechanism jamming. In severe cases, it may even cause the switch to refuse to operate, thus affecting the safe operation of the power grid. In order to timely grasp the working status of the switchgear and ensure the safe and reliable operation of the large power grid, according to the high-voltage switchgear maintenance rules formulated by the power company and the manufacturer, it is necessary to regularly carry out inspection operations on the high-voltage switchgear to determine whether there is any abnormality in the current operating state. However, due to the adjustment of the operation mode of the large power grid and the power outage of some large users, it is often impossible to shut down the high-voltage switchgear on schedule and conduct periodic inspections.

[0003] Based on the above, the problem existing in the prior art is that the high-voltage switch operating mechanism cannot be judged whether it can work normally due to long-term non-operation, and regular inspection will cause power outages and other problems for users. The judgment cost is too high, so there is an urgent need for a high-voltage switch operating mechanism inspection method without power outage. Summary of the invention

[0004] In view of the problems existing in the above-mentioned existing servo motor micro-action non-power-off self-test method, the present invention is proposed.

[0005] Therefore, the purpose of the present invention is to provide a servo motor micro-motion non-power-off self-test method, which aims to solve the problem that traditional detection schemes cannot determine in real time whether the motor drive mechanism is stuck or even stuck, while ensuring reliability and economy.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: including, calculating the motor torque, speed and shaft current parameters as well as whether there is a fault, fault type judgment and fault degree and inputting them into model training; by inputting the existing motor torque, speed and shaft current parameters into the model, judging whether there is a fault, fault type judgment and fault degree.

[0007] As a preferred solution of the servo motor micro-motion non-power-off self-test method of the present invention, wherein: the calculation method adopts a neural network, and sets a first hidden layer, a second hidden layer and an output layer, and takes the motor torque, speed and shaft current parameters as the input layer;

[0008] Specifically:

[0009] Input the motor torque, speed and shaft current parameters into the first hidden layer;

[0010] The first hidden layer filters the information to the second hidden layer;

[0011] The second hidden layer outputs the information to the output layer to obtain the calculation result;

[0012] Compare the calculated results with the model predictions;

[0013] The error will be compared to determine whether there is a fault, and the type and extent of the fault will be determined.

[0014] As a preferred solution of the servo motor micro-motion non-power-off self-test method of the present invention, the motor torque, speed and shaft current parameters are input into the first hidden layer specifically as follows:

[0015] Z [1] =W [1] X+b [1] +λ1|W [1] || 2 +α1·sin(β1X)+δ1(W [1] X) 2

[0016]

[0017] The first hidden layer filters the information to the second hidden layer as follows:

[0018] Z [2] =W [2] A [1] +b [2] +λ2|W [2] || 2 +α2·cos(β2A [1] )+δ2(W [2] A [1] ) 2

[0019]

[0020] The second hidden layer outputs the information to the output layer to obtain the calculation result:

[0021] Z [3] =W [3] A [2] +b [3] +λ3|W [3] || 2 +α3·tan(β3A [2] )+δ3(W [3] A [2] ) 2

[0022]

[0023] Where X is the input data matrix, dimension is (n x ,m), where n x is the number of features, m is the number of samples; W [l] is the weight matrix between the neurons in the lth layer and the l+1th layer, with a dimension of (n [l] ,n [l-1] );b [l] is the bias vector of the lth layer, with dimension (n [l] ,1);Z [l] is the weighted input of the lth layer, which is a linear combination of weights and inputs, plus bias and other nonlinear terms; A [l] is the activation output of the lth layer, which is the result of applying the activation function and normalization; λ is the regularization coefficient used to prevent overfitting; ||W [l] || 2 is the L2 norm of the weight matrix, which is used for regularization; α and β are parameter terms that introduce nonlinearity, which are used to adjust the amplitude of the nonlinear term and the amplitude of the input data; δ is the coefficient of the nonlinear term, which is used to introduce the square term and increase the complexity of the model; sin, cos, and tan are trigonometric functions used to introduce nonlinearity; γ is the coefficient of the linear term, which is used to adjust the amplitude of the linear combination; θ is the coefficient of the cubic term, which is used to introduce higher-order nonlinearity; LayerNorm is layer normalization, which is used to standardize the input of each layer; BatchNorm is batch normalization, which is used to standardize the data of each batch.

[0024] As a preferred solution of the servo motor micro-motion non-power-off self-test method described in the present invention, the output of each hidden layer becomes the input of the next layer, and an activation function is applied to the output layer to obtain the final output result.

[0025] In view of the problems existing in the above-mentioned existing servo motor micro-action non-power-off self-test system, the present invention is proposed.

[0026] Therefore, the purpose of the present invention is to provide a servo motor micro-motion non-power-off self-test system, which aims to solve the problem that traditional detection schemes cannot determine in real time whether the motor drive mechanism is stuck or even stuck, while ensuring reliability and economy. At the same time, it also solves the problem of large-scale power outages for users caused by regular inspection operations on high-voltage switchgear.

[0027] To solve the above technical problems, the present invention provides the following technical solutions: including setting a detection module to detect the motor and feeding back the detection data to the input module, and the input module calculates the data through the calculation module and then feeds back to the output module; the output module will determine whether the motor is faulty, and determine the fault type and fault degree.

[0028] As a preferred solution of the servo motor micro-motion non-power-off self-test system described in the present invention, the motor torque, speed and shaft current parameters of the motor are detected by the detection module; the motor torque, speed and shaft current parameters are imported from the input module to the calculation module for calculation; the calculation module calculates and compares through the first hidden layer and the second hidden layer respectively; the calculation is output to the output module, and the output module judges whether the comparison error is a fault, and determines the fault type and fault degree.

[0029] As a preferred solution of the servo motor micro-motion non-power-off self-test system of the present invention, the input module inputs the motor torque, speed and shaft current parameters into the first hidden layer specifically as follows:

[0030] Z [1] =W [1] X+b [1] +λ1|W [1] || 2 +α1·sin(β1X)+δ1(W [1] X) 2

[0031]

[0032] The first hidden layer filters the information to the second hidden layer as follows:

[0033] Z [2] =W [2] A [1] +b [2] +λ2|W [2] || 2 +α2·cos(β2A [1] )+δ2(W [2] A [1] ) 2

[0034]

[0035] The second hidden layer outputs the information to the output module to obtain the calculation result:

[0036] Z [3] =W [3] A [2] +b [3] +λ3|W [3] ||2 +α3·tan(β3A [2] )+δ3(W [3] A [2] ) 2

[0037]

[0038] Where X is the input data matrix, dimension is (n x ,m), where n x is the number of features, m is the number of samples; W [l] is the weight matrix between the neurons in the lth layer and the l+1th layer, with a dimension of (n [l] ,n [l-1] );b [l] is the bias vector of the lth layer, with dimension (n [l] ,1);Z [l] is the weighted input of the lth layer, which is a linear combination of weights and inputs, plus bias and other nonlinear terms; A [l] is the activation output of the lth layer, which is the result of applying the activation function and normalization; λ is the regularization coefficient used to prevent overfitting; ||W [l] || 2 is the L2 norm of the weight matrix, which is used for regularization; α and β are parameter terms that introduce nonlinearity, which are used to adjust the amplitude of the nonlinear term and the amplitude of the input data; δ is the coefficient of the nonlinear term, which is used to introduce the square term and increase the complexity of the model; sin, cos, and tan are trigonometric functions used to introduce nonlinearity; γ is the coefficient of the linear term, which is used to adjust the amplitude of the linear combination; θ is the coefficient of the cubic term, which is used to introduce higher-order nonlinearity; LayerNorm is layer normalization, which is used to standardize the input of each layer; BatchNorm is batch normalization, which is used to standardize the data of each batch.

[0039] In view of the problems existing in the above-mentioned prior art servo motor micro-motion non-power-off self-test device, the present invention is proposed.

[0040] Therefore, the purpose of the present invention is to provide a servo motor micro-action non-power-off self-test device, and its purpose is to use the device to determine whether the detection can work normally.

[0041] In order to solve the above technical problems, the present invention provides the following technical solutions: including, an isolating switch casing, the rotating shaft is arranged in the isolating switch casing, and the rotating shaft is connected to the motor drive rod, and is connected to the contact through the motor drive rod; a connecting rod, which connects the A-phase rotating rod, the B-phase rotating rod and the C-phase rotating rod, each of the phase rotating rods is connected to an isolating switch casing, and the contact is connected to the operating rod; the moving range and accuracy of the connecting rod system are controlled by the moving angles of the A-phase rotating rod, the B-phase rotating rod, the motor drive rod and the C-phase rotating rod, and the maximum range of the moving angle is 30°; also including a high-precision servo motor, a gear box and an isolating switch, the high-precision servo motor is directly connected to the gear box, the gear box is connected to the rotating shaft, the servo motor is connected to the connecting rod through the motor drive rod after being reduced by a worm and worm gear, the reduction ratio of the worm and worm gear reduction gearbox can be selected as 50:1 or 100:1, and the worm and worm gear reduction gearbox amplifies the motor torque.

[0042] As a preferred solution of the servo motor micro-motion non-power-off self-test device described in the present invention, the motor shaft is connected to the reduction gear box, and the contacts are driven to move through the motor shaft. The motor shaft rotates so that the contacts move slightly within 1 mm in the closed state, and the contacts do not separate.

[0043] As a preferred solution of the servo motor micro-motion non-power-off self-test device described in the present invention, wherein: the motor shaft is connected to the reduction gear box, and the contacts are driven to move through the motor shaft. The motor shaft rotates so that the contacts move slightly within 1 mm in the closed state, and the contacts do not separate; by adjusting the movement angle of the operating lever, the contacts can only move within the movement range; the maximum movement angle range is 60°, and the maximum movement range is 150mm.

[0044] The beneficial effects of the present invention are as follows: under normal working conditions, when the high-voltage switchgear carries load current, the main contact moves a tiny distance of <1mm but the contact is not separated, and the servo motor is automatically executed by controlling the program instructions, and the motor torque, speed and q-axis current parameters are input into the trained neural network model for calculation and compared with the model prediction results. When the error exceeds 5%, it is judged that a jamming fault has occurred in the system, and when the error is less than 5%, it is judged that no jamming fault has occurred in the system, thereby avoiding misjudgment to the greatest extent and realizing all-round high-precision automatic detection of mechanical faults, control faults and transmission component faults of the high-voltage switch operating mechanism. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0046] Figure 1 It is a schematic diagram of the overall structure of the servo motor micro-action non-power-off self-test device of the present invention.

[0047] Figure 2 This is a schematic diagram of the contact structure of the servo motor micro-action non-power-off self-test device of the present invention.

[0048] Figure 3 The present invention is a schematic diagram of the torque characteristics of the servo motor under different working conditions of the servo motor micro-action non-stop self-test method, system, device and medium, including Figure 3 (a) Torque 正常动作 and Figure 3 (b) Torque 故障 action.

[0049] Figure 4 The servo motor micro-action non-stop self-checking method, system, device and medium of the present invention are schematic diagrams of the servo motor speed characteristics under different working conditions, including Figure 4 (a)q-axis current 正常动作 and Figure 4 (b)q-axis current 故障动作 .

[0050] Figure 5 The servo motor micro-action non-stop self-check method, system, device and medium of the present invention are schematic diagrams of servo motor q-axis current characteristics under different working conditions, including Figure 5 (a) Speed 正常动作 and Figure 5 (b) Speed 故障动作 .

[0051] Figure 6 The present invention is a schematic diagram of the motor torque at the moment of opening and closing of the servo motor micro-action without power-off self-test method, system, device and medium, including Figure 6 (a) Torque change at the moment of opening the brake and Figure 5 (b) Torque change at the moment of closing the circuit breaker.

[0052] Figure 7 A schematic diagram of the topological connection of the servo motor micromotion test of the servo motor micromotion non-power-off self-test method, system, device and medium of the present invention.

[0053] Figure 8 It is a schematic diagram of the servo motor micro-action non-power-off self-checking system of the present invention. DETAILED DESCRIPTION

[0054] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0055] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0056] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0057] Secondly, the present invention is described in detail with reference to the schematic diagram. When describing the embodiments of the present invention in detail, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0058] Example 1

[0059] Reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, provides a servo motor micro-action non-power-off self-test device, including an isolating switch housing 507, a rotating shaft 506 is arranged in the isolating switch housing 507, and the rotating shaft 506 is connected to the motor driving rod 504, and is connected to the contact 509 through the motor driving rod 504; a connecting rod 502, which connects the A-phase rotating rod 501, the B-phase rotating rod 503 and the C-phase rotating rod 505, each phase rotating rod is connected to an isolating switch housing 507, and the contact 509 is connected to the operating rod 510.

[0060] The moving range and accuracy of the connecting rod system are controlled by the moving angle α of the A-phase rotating rod 501, the B-phase rotating rod 503, the motor driving rod 504 and the C-phase rotating rod 505, and the maximum range of the moving angle α is 30°.

[0061] By adjusting the movement angle α, the movement range and accuracy of the connecting rod system are controlled to ensure that the micro-movement of the contact 509 can be performed accurately.

[0062] During use, it also includes a high-precision servo motor, a gear box and an isolating switch (not shown in the figure). The high-precision servo motor is directly connected to the gear box, and the gear box is connected to the rotating shaft. The servo motor is connected to the connecting rod 510 through the motor drive rod 504 after being reduced by the worm and worm gear. The reduction ratio of the worm and worm gear reduction gearbox can be selected as 50:1 or 100:1, and the worm and worm gear reduction gearbox amplifies the motor torque.

[0063] The motor shaft 506 is connected to the reduction gear box, and the contact 509 is driven to move by the motor shaft 506. The motor shaft 506 rotates to make the contact 509 move slightly within 1 mm in the closed state, and the contact 509 does not separate; by adjusting the movement angle β of the operating rod 510, the contact 509 can only move within the movement range H; the maximum range of the movement angle β is 60°, and the maximum range of the movement H is 150 mm.

[0064] By adjusting the position and movement angle β of the operating rod 510, the movement range of the contact can be precisely controlled to ensure the accuracy of micro-motion detection. The operating rod 510 controls the micro-motion range of the contact within 1 mm. During operation, the movement of the operating rod 510 is monitored in real time by the sensor to ensure the safety and reliability of the operation process. The movement data of the contact 509 of the operating rod 510 is input into the neural network model for analysis to determine whether there is a fault in the system.

[0065] Since the motor shaft 506 is connected to the reduction gear box, considering the error of the mechanical structure, after rotating through a certain idle angle, the contact 509 starts to move. According to the calculated angle, the motor shaft 506 rotates so that the contact 509 moves slightly within 1 mm in the closed state, and the contacts do not separate.

[0066] Example 2

[0067] Reference Figures 1 to 5 , which is the second embodiment of the present invention. This embodiment is different from the first embodiment in that: a servo motor micro-action non-stop self-detection method calculates the motor torque, speed and shaft current parameters as well as whether there is a fault, the fault type and the fault degree and inputs them into the model training together; by inputting the existing motor torque, speed and shaft current parameters into the model, it judges whether there is a fault, the fault type and the fault degree.

[0068] Compared with Example 1, further, first, parameters such as the motor torque, speed and q-axis current are input into the input layer of the model, and then these parameters pass through the first hidden layer, in which neurons process and transform the information through weights and activation functions, and the processed information is passed to the second hidden layer to further extract features and perform transformations.

[0069] The output of the second hidden layer is fed into the output layer to generate a calculation result of the motor state, such as the predicted torque, speed or current value. This calculation result is compared with the actual measured value to detect possible differences. If there is a significant difference, the system will compare it with the known fault mode to determine whether there is a fault. The size and direction of the difference are also used to determine the type and extent of the fault.

[0070] The motor torque, speed and shaft current parameters are input to the first hidden layer as follows:

[0071] Z [1] =W [1] X+b [1] +λ1|W [1] || 2 +α1·sin(β1X)+δ1(W [1] X) 2

[0072]

[0073] The first hidden layer filters the information to the second hidden layer as follows:

[0074] Z [2] =W [2] A [1] +b [2] +λ2|W [2] || 2 +α2·cos(β2A [1] )+δ2(W [2] A [1] ) 2

[0075]

[0076] The second hidden layer outputs the information to the output layer to obtain the calculation result:

[0077] Z [3] =W [3] A [2] +b [3] +λ3|W [3] || 2 +α3·tan(β3A [2] )+δ3(W [3] A [2] ) 2

[0078]

[0079] Where X is the input data matrix, dimension is (n x ,m), where n xis the number of features, m is the number of samples; W [l] is the weight matrix between the neurons in the lth layer and the l+1th layer, with a dimension of (n [l] ,n [l-1] );b [l] is the bias vector of the lth layer, with dimension (n [l] ,1);Z [l] is the weighted input of the lth layer, which is a linear combination of weights and inputs, plus bias and other nonlinear terms; A [l] is the activation output of the lth layer, which is the result of applying the activation function and normalization; λ is the regularization coefficient used to prevent overfitting; ||W [l] || 2 is the L2 norm of the weight matrix, which is used for regularization; α and β are parameter terms that introduce nonlinearity, which are used to adjust the amplitude of the nonlinear term and the amplitude of the input data; δ is the coefficient of the nonlinear term, which is used to introduce the square term and increase the complexity of the model; sin, cos, and tan are trigonometric functions used to introduce nonlinearity; γ is the coefficient of the linear term, which is used to adjust the amplitude of the linear combination; θ is the coefficient of the cubic term, which is used to introduce higher-order nonlinearity; LayerNorm is layer normalization, which is used to standardize the input of each layer; BatchNorm is batch normalization, which is used to standardize the data of each batch.

[0080] During use, the output of each hidden layer becomes the input of the next layer, and the activation function is applied to the output layer to obtain the final output result.

[0081] The contact 509 moves slightly within 1 mm in the closed state. During this process, it is determined whether the motor torque exceeds or is lower than the ideal torque by 5%. When it exceeds the ideal torque by 5%, it is determined that a jam or stuck fault has occurred. When it does not exceed the ideal torque by 5%, it is determined that no jam or stuck fault has occurred, thereby realizing non-interruption operation detection.

[0082] The contact 509 moves slightly within 1 mm in the closed state. During this process, it is determined whether the motor speed exceeds or is lower than the ideal speed by 5%. When it exceeds the ideal speed by 5%, it is determined that a jam or stuck fault has occurred. When it does not exceed the ideal speed by 5%, it is determined that a jam or stuck fault has not occurred, thereby realizing non-interruption operation detection.

[0083] The contacts move slightly within 1mm in the closed state. During this process, it is determined whether the motor's q-axis current exceeds or is lower than the ideal q-axis current by 5%. When it exceeds the ideal current by 5%, it is determined that a jam or stuck fault has occurred. When it is lower than the ideal torque by 5%, it is determined that no fault has occurred, thus achieving non-stop power-on operation detection.

[0084] The remaining structures are the same as those of Example 1.

[0085] Example 3

[0086] Reference Figures 1 to 8 , which is the third embodiment of the present invention. This embodiment is different from the second embodiment in that: the servo motor micro-motion non-power-off self-test system is configured with a detection module 100 to detect the motor and feed back the detection data to the input module 200. The input module 200 calculates the data through the calculation module 300 and then feeds back the data to the output module 400; the output module 400 determines whether the motor is faulty and determines the fault type and fault degree.

[0087] Compared with Example 2, further, the motor torque, speed and shaft current parameters of the motor are detected by the detection module 100; the motor torque, speed and shaft current parameters are imported into the calculation module 300 by the input module 200 for calculation; the calculation module 300 calculates and compares through the first hidden layer 301 and the second hidden layer 302 respectively; the calculation is output to the output module 400, and the output module 400 determines whether the comparison error is a fault, and determines the fault type and fault degree.

[0088] The drive system and control system are started through the power supply, allowing the control system to interact with the input system and display system. The control system drives the motor through the drive system and interacts with each other through the high-voltage isolation switch.

[0089] The detection module 100 is responsible for detecting the motor torque, speed and shaft current parameters of the motor through the q-axis current detection module, torque sensor, speed sensor and magnetic encoding position detector;

[0090] These parameters are introduced into the calculation module 300 through the input module 200 to exceed the 5% difference of the current envelope, torque envelope, speed envelope and position envelope, where they are processed and calculated through the first hidden layer 301 and the second hidden layer 302 to generate a prediction of the motor state;

[0091] After the calculation is completed, the result is transmitted to the output module 400, where the comparison error is analyzed to determine whether there is a fault and to determine the type and extent of the fault, and then returned to the system to complete the cycle, which can realize real-time monitoring and fault diagnosis of the motor's operating status, providing important support for the safe operation of the motor.

[0092] The servo motor rotor position, speed, torque and stator current are used to determine whether the motor torque, speed, q-axis current and position exceed or fall below the ideal value by 5%. The calculated difference is input into the neural network and the model is trained to obtain information on whether there is a fault, the type of fault and the degree of fault.

[0093] The input module 200 inputs the motor torque, speed and shaft current parameters into the first hidden layer 301 specifically as follows:

[0094] Z [1] =W [1] X+b [1] +λ1|W [1] || 2 +α1·sin(β1X)+δ1(W [1] X) 2

[0095]

[0096] The first hidden layer 301 filters the information to the second hidden layer 302 specifically as follows:

[0097] Z [2] =W [2] A [1] +b [2] +λ2|W [2] || 2 +α2·cos(β2A [1] )+δ2(W [2] A [1] ) 2

[0098]

[0099] The second hidden layer 302 outputs the information to the output module 400 to obtain the calculation result:

[0100] Z [3] =W [3] A [2] +b [3] +λ3|W [3] || 2 +α3·tan(β3A [2] )+δ3(W [3] A [2] ) 2

[0101]

[0102] Where X is the input data matrix, dimension is (n x ,m), where n x is the number of features, m is the number of samples; W [l] is the weight matrix between the neurons in the lth layer and the l+1th layer, with a dimension of (n [l] ,n [l-1] );b [l] is the bias vector of the lth layer, with dimension (n [l] ,1);Z [l] is the weighted input of the lth layer, which is a linear combination of weights and inputs, plus bias and other nonlinear terms; A [l]is the activation output of the lth layer, which is the result of applying the activation function and normalization; λ is the regularization coefficient used to prevent overfitting; ||W [l] || 2 is the L2 norm of the weight matrix, which is used for regularization; α and β are parameter terms that introduce nonlinearity, which are used to adjust the amplitude of the nonlinear term and the amplitude of the input data; δ is the coefficient of the nonlinear term, which is used to introduce the square term and increase the complexity of the model; sin, cos, and tan are trigonometric functions used to introduce nonlinearity; γ is the coefficient of the linear term, which is used to adjust the amplitude of the linear combination; θ is the coefficient of the cubic term, which is used to introduce higher-order nonlinearity; LayerNorm is layer normalization, which is used to standardize the input of each layer; BatchNorm is batch normalization, which is used to standardize the data of each batch.

[0103] The contact 509 moves slightly within 1 mm in the closed state. During this process, it is determined whether the motor torque exceeds or is lower than the ideal torque by 5%. When it exceeds the ideal torque by 5%, it is determined that a jam or stuck fault has occurred. When it does not exceed the ideal torque by 5%, it is determined that no jam or stuck fault has occurred, thereby realizing non-interruption operation detection.

[0104] The contact 509 moves slightly within 1 mm in the closed state. During this process, it is determined whether the motor speed exceeds or is lower than the ideal speed by 5%. When it exceeds the ideal speed by 5%, it is determined that a jam or stuck fault has occurred. When it does not exceed the ideal speed by 5%, it is determined that a jam or stuck fault has not occurred, thereby realizing non-interruption operation detection.

[0105] The contacts move slightly within 1mm in the closed state. During this process, it is determined whether the motor's q-axis current exceeds or is lower than the ideal q-axis current by 5%. When it exceeds the ideal current by 5%, it is determined that a jam or stuck fault has occurred. When it is lower than the ideal torque by 5%, it is determined that no fault has occurred, thus achieving non-stop power-on operation detection.

[0106] When the servo motor starts and moves at a uniform low speed, the motor torque will gradually increase to a relatively stable level. At the moment of opening, the motor torque will drop significantly, forming a torque difference. When the torque difference exceeds 5% of the ideal torque, it is judged that the motor has been opened successfully. When the torque difference is lower than 5% of the ideal torque, it is judged that the motor has not been opened successfully.

[0107] When the servo motor starts and moves at a uniform low speed, the motor torque will gradually increase to a relatively stable level. At the moment of closing, the motor torque will increase significantly, forming a torque difference. When the torque difference exceeds the ideal torque by 5%, it is judged that the motor has been successfully closed. When the torque difference is lower than the ideal torque by 5%, it is judged that the motor has not been successfully closed.

[0108] In order to ensure the operating accuracy and reliability of the contacts during micro-movement, the servo motor uses magnetic encoding signal sensors, speed and torque sensors to detect the motor rotor position, speed and stator current in real time to ensure the safety and reliability of the movement process. The servo motor makes decisions based on the comprehensive evaluation module to control the servo motor.

[0109] Because in the closed state, the micro-motion of the servo motor of 1mm before the contacts separate is basically consistent with the change in the torque of the complete opening, and the resistance basically does not change. Therefore, the method proposed in this scheme can completely replace the complete opening and closing with the micro-motion of 1mm, avoiding power outages caused by inspection operations in the power grid, realizing non-stop detection of the high-voltage switch operating mechanism, and timely grasping the status information of the electrical and mechanical components of the switch equipment.

[0110] The remaining structure is the same as that of Example 2.

[0111] Importantly, it should be noted that the construction and arrangement of the present application shown in a plurality of different exemplary embodiments are only exemplary. Although only a few embodiments are described in detail in this disclosure, it should be readily understood by those who refer to this disclosure that many modifications are possible (e.g., the size, scale, structure, shape and proportion of various elements, and parameter values ​​(e.g., temperature, pressure, etc.), installation arrangement, use of materials, color, directional changes, etc.) without substantially departing from the novel teachings and advantages of the subject matter described in the application. For example, the element shown as integrally formed can be composed of multiple parts or elements, the position of the element can be inverted or otherwise changed, and the nature or number or position of the discrete element can be changed or changed. Therefore, all such modifications are intended to be included in the scope of the present invention. The order or sequence of any process or method steps can be changed or reordered according to alternative embodiments. In the claims, any "device plus function" clause is intended to cover the structure of performing the function described herein, and is not only structurally equivalent but also equivalent structure. Without departing from the scope of the present invention, other replacements, modifications, changes and omissions can be made in the design, operating conditions and arrangement of the exemplary embodiments. Therefore, the invention is not limited to a specific embodiment, but extends to numerous modifications still falling within the scope of the appended claims.

[0112] Additionally, in order to provide a concise description of exemplary embodiments, all features of an actual embodiment (ie, those features that are not relevant to the best mode presently contemplated for carrying out the invention or those that are not relevant to implementing the invention) may not be described.

[0113] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for self-checking servo motor micro-movement without power failure. Features: The motor torque, speed and shaft current parameters as well as whether there is a fault, fault type and fault degree are calculated and input into the model training; By inputting the existing motor torque, speed and shaft current parameters into the model, it is possible to determine whether there is a fault, the type of fault and the degree of the fault.

2. The servo motor micro-motion non-power-off self-test method according to claim 1, Features: The model adopts a neural network, and sets a first hidden layer, a second hidden layer and an output layer, and takes the motor torque, speed and shaft current parameters as the input layer; Specifically: Input the motor torque, speed and shaft current parameters into the first hidden layer; The first hidden layer filters the information to the second hidden layer; The second hidden layer outputs the information to the output layer to obtain the calculation result; Compare the calculated results with the model predictions; The error will be compared to determine whether there is a fault, and the type and extent of the fault will be determined.

3. The servo motor micro-motion non-power-off self-test method according to claim 1 or 2, Features: The motor torque, speed and shaft current parameters are input into the first hidden layer as follows: Z [1] =W [1] X+b [1] +λ 1 |W [1] || 2 +a 1 ·sin(β 1 X)+d 1 (W [1] X) 2 The first hidden layer filters the information to the second hidden layer as follows: Z [2] =W [2] A [1] +b [2] +λ 2 |W [2] || 2 +a 2 ·cos(β 2 A [1] )+d 2 (W [2] A [1] ) 2 The second hidden layer outputs the information to the output layer to obtain the calculation result: Z [3] =W [3] A [2] +b [3] +λ 3 |W [3] || 2 +a 3 ·tan(β 3 A [2] )+d 3 (W [3] A [2] ) 2 Where X is the input data matrix, dimension is (n x ,m), where n x is the number of features, m is the number of samples; W [l] is the weight matrix between the neurons in the lth layer and the l+1th layer, with a dimension of (n [l] ,n [l-1] );b [l] is the bias vector of the lth layer, with dimension (n [l] ,1);Z [l] is the weighted input of the lth layer, which is a linear combination of weights and inputs, plus bias and other nonlinear terms; A [l] is the activation output of the lth layer, which is the result of applying the activation function and normalization; λ is the regularization coefficient used to prevent overfitting; ||W [l] || 2 is the L2 norm of the weight matrix, which is used for regularization; α and β are parameter terms that introduce nonlinearity, which are used to adjust the amplitude of the nonlinear term and the amplitude of the input data; δ is the coefficient of the nonlinear term, which is used to introduce the square term and increase the complexity of the model; sin, cos, and tan are trigonometric functions used to introduce nonlinearity; γ is the coefficient of the linear term, which is used to adjust the amplitude of the linear combination; θ is the coefficient of the cubic term, which is used to introduce higher-order nonlinearity; LayerNorm is layer normalization, which is used to standardize the input of each layer; BatchNorm is batch normalization, which is used to standardize the data of each batch.

4. The servo motor micro-motion non-power-off self-test method according to claim 3, Features: The output of each hidden layer becomes the input of the next layer, and the activation function is applied at the output layer to obtain the final output result.

5. A servo motor micro-motion non-stop self-test system, Features: The method for self-checking the micro-action of the servo motor without power failure according to any one of claims 1 to 4 further comprises: A detection module (100) is provided to detect the motor and feed back the detection data to the input module (200); the input module (200) calculates the data through the calculation module (300) and then feeds back the data to the output module (400); The output module (400) determines whether the motor is faulty and determines the fault type and fault degree.

6. The servo motor micro-motion non-stop self-test system according to claim 5, Features: Detecting motor torque, rotation speed and shaft current parameters of the motor through a detection module (100); Importing motor torque, rotation speed and shaft current parameters from the input module (200) into the calculation module (300) for calculation; The calculation module (300) calculates the comparison through the first hidden layer (301) and the second hidden layer (302) respectively; After calculation, the error is output to the output module (400), and the output module (400) determines whether the comparison error is a fault, and determines the fault type and fault degree.

7. The servo motor micro-motion non-stop self-test system according to claim 5 or 6, Features: The input module (200) inputs the motor torque, rotation speed and shaft current parameters into the first hidden layer (301) specifically as follows: Z [1] =W [1] X+b [1] +λ 1 |W [1] || 2 +a 1 ·sin(β 1 X)+d 1 (W [1] X) 2 The first hidden layer (301) filters the information to the second hidden layer (302) as follows: Z [2] =W [2] A [1] +b [2] +λ 2 |W [2] || 2 +a 2 ·cos(β 2 A [1] )+d 2 (W [2] A [1] ) 2 The second hidden layer (302) outputs the information to the output module (400) to obtain the calculation result: Z [3] =W [3] A [2] +b [3] +λ 3 |W [3] || 2 +a 3 ·tan(β 3 A [2] )+d 3 (W [3] A [2] ) 2 Where X is the input data matrix, dimension is (n x ,m), where n x is the number of features, m is the number of samples; W [l] is the weight matrix between the neurons in the lth layer and the l+1th layer, with a dimension of (n [l] ,n [l-1] );b [l] is the bias vector of the lth layer, with dimension (n [l] ,1);Z [l] is the weighted input of the lth layer, which is a linear combination of weights and inputs, plus bias and other nonlinear terms; A [l] is the activation output of the lth layer, which is the result of applying the activation function and normalization; λ is the regularization coefficient used to prevent overfitting; ||W [l] || 2 is the L2 norm of the weight matrix, which is used for regularization; α and β are parameter terms that introduce nonlinearity, which are used to adjust the amplitude of the nonlinear term and the amplitude of the input data; δ is the coefficient of the nonlinear term, which is used to introduce the square term and increase the complexity of the model; sin, cos, and tan are trigonometric functions used to introduce nonlinearity; γ is the coefficient of the linear term, which is used to adjust the amplitude of the linear combination; θ is the coefficient of the cubic term, which is used to introduce higher-order nonlinearity; LayerNorm is layer normalization, which is used to standardize the input of each layer; BatchNorm is batch normalization, which is used to standardize the data of each batch.

8. A servo motor micro-motion non-power-off self-test device, Features: The servo motor micro-motion non-stop self-test system applied to any one of claims 5 to 7 further comprises: An isolating switch housing (507), wherein the rotating shaft (506) is disposed in the isolating switch housing (507), and the rotating shaft (506) is connected to a motor drive rod (504), and is connected to a contact (509) via the motor drive rod (504); A connecting rod (502) connecting the A-phase rotating rod (501), the B-phase rotating rod (503) and the C-phase rotating rod (505), each of the phase rotating rods being connected to an isolating switch housing (507), and the contact (509) being connected to an operating rod (510); The moving range and accuracy of the connecting rod system are controlled by the moving angles (α) of the A-phase rotating rod (501), the B-phase rotating rod (503), the motor driving rod (504) and the C-phase rotating rod (505), and the maximum range of the moving angle (α) is 30°.

9. The servo motor micro-motion non-power-off self-test device according to claim 8, Features: The motor shaft (506) is connected to the reduction gear box, and the contact (509) is driven to move by the motor shaft (506). The motor shaft (506) rotates so that the contact (509) slightly moves within 1 mm in the closed state, and the contact (509) does not separate; By adjusting the movement angle (β) of the operating rod (510), the contact (509) can only move within the movement range (H); The maximum range of the movement angle (β) is 60°, and the maximum range of the movement (H) is 150 mm.

10. A computer-readable storage medium storing computer-executable instructions, Features: When the computer executable instructions are executed by the processor, the servo motor micro-action non-power-off self-checking system described in any one of claims 5 to 7 can be realized.

Citation Information

Cited By

  • Abnormal vibration detection method and device, electronic equipment and storage medium

    CN120558555A

  • Isolation switch control device and control method

    CN120675011A