Gear fault diagnosis methods, systems, motor controllers, and computer media
By constructing a sensorless gear system for simulation and experimental testing, the problems of diagnostic complexity and error in multi-gear systems are solved, and the accuracy and efficiency of gear fault diagnosis are improved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SUZHOU INOVANCE CONTROL TECH CO LTD
- Filing Date
- 2022-11-30
- Publication Date
- 2026-06-30
AI Technical Summary
Existing technologies for gear fault diagnosis require the creation of multiple gear models, which is labor-intensive, results in large errors, makes sensor placement difficult, causes severe signal interference, and results in low diagnostic accuracy.
By constructing a sensorless gear system, using gear parameters for simulation testing, identifying abnormal feature points, building an experimental testing platform, acquiring and comparing experimental data, extracting abnormal features, and generating target feature images for comparison to determine the fault type.
It reduces sensor deployment costs, improves diagnostic accuracy, reduces errors, and simplifies the diagnostic process for multi-gear systems.
Smart Images
Figure CN116296364B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of gear fault diagnosis technology, and in particular to a gear fault diagnosis method, system, motor controller, and computer-readable storage medium. Background Technology
[0002] With the development of industrial automation, rotating equipment plays an increasingly important role in the field of industrial automation. Gears, due to their wide range of applications, are considered core components in rotating equipment. However, gears are prone to various failures due to their continuous high-load operation in harsh environments. Currently, technicians often use sensors installed in the gear system to acquire vibration or electrical signals generated during operation. These signals are then analyzed and processed to create a specific model of the faulty gear. A fixed algorithm is then used to perform filtering, noise reduction, feature extraction, and feature recognition to complete the simulation and fault diagnosis process, ultimately determining the cause of the gear failure.
[0003] However, the above approach presents challenges when the gear system contains multiple gears. This necessitates creating multiple distinct gear models for each gear, and then performing model improvements, network partitioning, and optimization designs for each model during simulation analysis. This results in a significant drain on technical personnel's time and a potential large discrepancy between the obtained results and experimental data. Furthermore, this approach requires determining the placement and number of sensor points within the gear system. Additionally, the signals acquired by the sensors are often subject to interference due to the on-site working environment, increasing subsequent analysis time and affecting the accuracy of the results. Moreover, the fixed algorithm used in this approach may yield low-accuracy diagnostic results when multiple gear faults occur. Summary of the Invention
[0004] The main objective of this invention is to provide a gear fault diagnosis method, system, motor controller, and computer-readable storage medium, which enables the motor controller to construct a sensorless gear system based on the acquired gear parameters, and then perform simulation and experimental tests on the gear system to determine the cause of gear faults, thereby reducing the cost of placing sensors on the gears.
[0005] To achieve the above objectives, the present invention provides a gear fault diagnosis method, which includes the following steps:
[0006] Obtain the gear parameters of the target gear, construct a gear system based on the gear parameters, and then perform simulation testing on the gear system to obtain simulation results;
[0007] Based on the simulation results, abnormal feature points in the gear system are determined. An experimental test platform corresponding to the gear system is built based on the abnormal feature points, and experimental tests are conducted on the experimental test platform to obtain experimental data.
[0008] The experimental data is compared with the simulation results to determine whether the experimental data and the simulation results match.
[0009] If it is determined that the experimental data matches the simulation results, then the abnormal feature signals contained in the experimental data are identified, and the abnormal features are extracted from the abnormal feature signals.
[0010] A target feature image is generated based on the abnormal features, and the target feature image is compared with a preset standard feature image to obtain the gear fault type corresponding to the target gear.
[0011] Furthermore, the step of constructing a gear system based on the gear parameters and then performing simulation testing on the gear system to obtain simulation results includes:
[0012] Determine the gear model corresponding to the target gear based on the gear parameters;
[0013] The gear parameters are modified to determine the gear models corresponding to each of the other gears corresponding to the target gear.
[0014] The gear models are combined to construct a gear system, and simulation parameters corresponding to the gear system are set. Then, the gear system is simulated and tested based on the simulation parameters to obtain simulation results.
[0015] The gear model and the simulation parameters achieve real-time data exchange.
[0016] Furthermore, the step of performing simulation tests on the gear system based on each of the simulation parameters to obtain simulation results includes:
[0017] The gear system is simulated and tested according to the simulation parameters to obtain the meshing parameters generated by the target gear during meshing.
[0018] Determine the meshing time-domain diagram corresponding to the meshing parameters, and determine the target protrusion parameter in the meshing time-domain diagram, and the target position of the target protrusion parameter in the gear system;
[0019] The simulation results are obtained by integrating the target prominence parameters and the target position.
[0020] Furthermore, the step of constructing the experimental test platform corresponding to the gear system based on the abnormal feature points includes:
[0021] The abnormal location within the gear system is determined based on the abnormal feature points;
[0022] An experimental test platform corresponding to the gear system is constructed based on the abnormal location.
[0023] Furthermore, the step of conducting experimental tests on the experimental testing platform to obtain experimental data includes:
[0024] Acquire the test signals generated at the abnormal location under various preset detection conditions;
[0025] Extract the effective value from the test signal, and determine the initial vibration signal corresponding to the test signal based on the effective value;
[0026] The initial vibration signal is subjected to noise reduction processing to obtain the target vibration signal, and the target vibration signal is determined as experimental data.
[0027] Furthermore, after the step of comparing the experimental data with the simulation results to determine whether the experimental data and the simulation results match, the method further includes:
[0028] If it is determined that the experimental data does not match the simulation results, the gear parameters contained in the gear system are corrected, and the gear system is rebuilt based on the corrected gear parameters.
[0029] The rebuilt gear system was subjected to simulation testing, and new simulation results were obtained.
[0030] Further, the step of extracting anomalous features from the anomalous feature signal includes:
[0031] The target feature signal is obtained by performing a noise reduction filtering operation on the abnormal feature signal;
[0032] Multiple preset processing algorithms are obtained, and abnormal features are extracted from the target feature signal based on each of the processing algorithms.
[0033] Further, the step of comparing the target feature image with a preset standard feature image to obtain the gear fault type corresponding to the target gear includes:
[0034] A preset standard feature image is obtained, and the target feature image is compared with the standard feature image to determine a standard fault feature in the standard feature image that is consistent with the abnormal feature contained in the target feature image;
[0035] The standard fault type corresponding to the standard feature is determined in the standard feature image, and the standard fault type is determined as the gear fault type corresponding to the target gear.
[0036] Furthermore, to achieve the above objectives, the present invention also provides a gear fault diagnosis system, the gear fault diagnosis system comprising:
[0037] The gear modeling and simulation module is used to acquire the gear parameters of the target gear, construct a gear system based on the gear parameters, and then perform simulation testing on the gear system to obtain simulation results. The simulation results are then input to the gear signal acquisition module. The modeling and simulation data within the gear modeling and simulation module are interconnected in real time.
[0038] The gear signal acquisition module is used to acquire the simulation results, determine the abnormal feature points in the gear system based on the simulation results, build an experimental test platform corresponding to the gear system based on the abnormal feature points, and conduct experimental tests on the experimental test platform to obtain experimental data. If it is determined that the experimental data matches the simulation results, the abnormal feature signals contained in the experimental data are determined, and the abnormal feature signals are input to the gear fault diagnosis module.
[0039] The gear fault diagnosis module is used to extract abnormal features from the abnormal feature signal, generate a target feature image based on the abnormal features, and compare the target feature image with a preset standard feature image to obtain the gear fault type corresponding to the target gear.
[0040] Furthermore, the gear signal acquisition module includes:
[0041] The experimental testing platform is used to control the signal acquisition unit to acquire the test signals generated when the abnormal position is running under preset detection conditions, and to input the test signals to the signal conversion unit;
[0042] The signal conversion unit is used to extract the effective value from the test signal, determine the initial vibration signal corresponding to the test signal based on the effective value, and then perform noise reduction processing on the initial vibration signal to obtain the target vibration signal, thereby determining the target vibration signal as experimental data.
[0043] Furthermore, the gear fault diagnosis module includes:
[0044] The filtering and noise reduction unit is used to perform noise reduction and filtering operations on the abnormal feature signal to obtain the target feature signal, and input the target feature signal to the feature extraction unit;
[0045] The feature extraction unit is used to acquire multiple preset processing algorithms, extract abnormal features from the target feature signal based on each of the processing algorithms, and then input the abnormal features to the feature recognition unit.
[0046] The feature recognition unit is used to acquire a preset standard feature image and compare the target feature image with the standard feature image to determine a standard fault feature in the standard feature image that is consistent with the abnormal feature contained in the target feature image.
[0047] In addition, to achieve the above objectives, the present invention also provides a motor controller, the motor controller comprising: a memory, a processor, and a gear fault diagnosis program stored in the memory and executable on the processor, wherein the gear fault diagnosis program, when executed by the processor, implements the steps of the gear fault diagnosis method as described above.
[0048] In addition, to achieve the above objectives, the present invention also provides a computer-readable storage medium storing a gear fault diagnosis program, which, when executed by a processor, implements the steps of the gear fault diagnosis method as described above.
[0049] The gear fault diagnosis method, motor controller, and computer-readable storage medium provided in this invention involve acquiring gear parameters of a target gear, constructing a gear system based on the gear parameters, and then performing simulation tests on the gear system to obtain simulation results. Based on the simulation results, abnormal feature points in the gear system are determined. An experimental test platform corresponding to the gear system is built based on the abnormal feature points, and experimental tests are performed on the experimental test platform to obtain experimental data. The experimental data is compared with the simulation results to determine whether the experimental data matches the simulation results. If the experimental data matches the simulation results, abnormal feature signals contained in the experimental data are determined, and abnormal features are extracted from the abnormal feature signals. A target feature image is generated based on the abnormal features, and the target feature image is compared with a preset standard feature image to obtain the gear fault type corresponding to the target gear.
[0050] In this embodiment, during operation, the motor controller first acquires the gear parameters of the target gear input by the technician. The motor controller then establishes a gear model corresponding to the target gear based on the acquired gear parameters, thereby constructing a gear system. The motor controller calls the simulation module to perform simulation testing on the gear system, obtaining simulation test results. Next, the motor controller identifies abnormal feature points in the gear system based on the simulation results and builds an experimental test platform corresponding to the gear system based on these abnormal feature points. The motor controller performs experimental testing on the experimental test platform and obtains experimental data. Then, the motor controller compares the acquired experimental data with the simulation results to determine if the experimental data matches the simulation. When the motor controller determines that the experimental data matches the simulation data, it identifies abnormal feature signals in the output system based on the experimental data and calls the feature extraction unit to perform feature extraction operations on the abnormal feature signals to obtain the abnormal features corresponding to the gear system. Finally, the terminal calls the feature recognition unit to generate a target feature image based on the abnormal features. Simultaneously, the motor controller acquires a preset standard feature image. The feature recognition unit then compares the acquired target feature image with the standard feature image to determine the gear fault type corresponding to the target gear.
[0051] Thus, this invention employs a method where gear parameters of the target gear are input into a simulation testing platform. The platform then models the target gear based on these parameters, creating a sensorless gear system. Simulation testing is performed on this system to identify anomalous feature points. An experimental testing platform is then built based on these anomalous feature points. Experimental testing is conducted on this platform to determine fault characteristics within the gear system. Finally, the acquired fault characteristics are used to filter preset standard feature images to determine the corresponding gear fault type for the target gear. In other words, this invention solves the current problem where, when a gear system contains multiple gears, multiple different gear models need to be created for each gear, and then... Simulation analysis requires significant effort from various operations such as model improvement, network partitioning, and optimization design for different gear models. This invention addresses the challenge of determining sensor placement and quantity within a gear system by constructing a sensorless gear system. Furthermore, by filtering standard feature images based on fault characteristics to identify gear fault types, this invention overcomes the low accuracy of current fixed algorithms when diagnosing multiple gear faults. This allows motor controllers to construct sensorless gear systems based on acquired gear parameters, enabling simulation and experimental testing to determine fault causes and reducing the costs associated with deploying sensors on gears. Attached Figure Description
[0052] Figure 1 This is a schematic diagram of the structure of the motor controller in the hardware operating environment involved in the embodiments of the present invention;
[0053] Figure 2 This is a flowchart illustrating the first embodiment of the gear fault diagnosis method of the present invention;
[0054] Figure 3 This is a schematic diagram of the modeling and simulation process involved in an embodiment of the gear fault diagnosis method of the present invention;
[0055] Figure 4 This is a flowchart illustrating the simulation-guided experiment setup for an embodiment of the gear fault diagnosis method of the present invention.
[0056] Figure 5 This is a schematic diagram of the signal acquisition process involved in an embodiment of the gear fault diagnosis method of the present invention;
[0057] Figure 6This is a schematic diagram of the fault diagnosis process according to an embodiment of the gear fault diagnosis method of the present invention;
[0058] Figure 7 This is a spectrum diagram of gear wear faults in an embodiment of the gear fault diagnosis method of the present invention;
[0059] Figure 8 This is a schematic diagram of the functional modules involved in an embodiment of the gear fault diagnosis method of the present invention.
[0060] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation
[0061] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
[0062] Please refer to Figure 1 , Figure 1 This is a schematic diagram of the motor controller structure of the hardware operating environment involved in the embodiments of the present invention.
[0063] It should be noted that, Figure 1 This can be a schematic diagram of the hardware operating environment of the motor controller. In this embodiment of the invention, the motor controller can be a device that executes the gear fault diagnosis method of the present invention for a faulty gear. Specifically, the motor controller can be a mobile terminal, a data storage control terminal, a PC, or a portable computer, etc.
[0064] like Figure 1 As shown, the motor controller may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen or an input unit such as a keyboard; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). The memory 1005 may be a high-speed random access memory (RAM) or a stable non-volatile memory (NVM), such as a disk drive. The memory 1005 may also optionally be a storage device independent of the aforementioned processor 1001.
[0065] Those skilled in the art will understand that Figure 1 The structure shown does not constitute a limitation on the motor controller and may include more or fewer components than shown, or combine certain components, or have different component arrangements.
[0066] like Figure 1 As shown, the memory 1005, which serves as a storage medium, may include an operating system, a data storage module, a network communication module, a user interface module, and a gear fault diagnosis program.
[0067] exist Figure 1 In the motor controller shown, the network interface 1004 is mainly used for data communication with other devices; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the motor controller of the present invention can be set in the motor controller, and the motor controller calls the gear fault diagnosis program stored in the memory 1005 through the processor 1001 and executes the gear fault diagnosis method provided in the embodiment of the present invention.
[0068] Based on the above-described motor controller, various embodiments of the gear fault diagnosis method of the present invention are provided;
[0069] Please refer to Figure 2 , Figure 2 This is a flowchart illustrating the first embodiment of the gear fault diagnosis method of the present invention.
[0070] It should be understood that although the logical order is shown in the flowchart, in some cases, the gear fault diagnosis method of the present invention may of course perform the steps shown or described in a different order than that shown here.
[0071] In this embodiment, the gear fault diagnosis method of the present invention may include the following steps:
[0072] Step S10: Obtain the gear parameters of the target gear, construct a gear system based on the gear parameters, and then perform simulation testing on the gear system to obtain simulation results;
[0073] In this embodiment, when the motor controller is running, it first obtains the gear parameters of the target gear input by the technician into the motor controller. The motor controller then inputs the obtained gear parameters into the modeling unit, which models the target gear according to the gear parameters and obtains the gear model corresponding to the target gear. The modeling unit then assembles the gear model to establish a sensorless gear system. The motor controller calls the simulation unit to perform simulation testing on the gear system, thereby obtaining the simulation test results corresponding to the gear system.
[0074] For example, during operation, the motor controller first acquires the gear coordinates (x, y), number of teeth z, module m, pressure angle α, tooth thickness d, tooth width b, inner diameter k, keyway depth p, and height q of each of the multiple target gears input by the technician, as well as the gear type. When the modeling unit determines that the gear type corresponding to each target gear is a spur gear, the modeling unit determines the involute standard spur gear meshing relationship corresponding to the spur gear from the preset gear meshing relationships. The modeling unit then applies the gear coordinates (x, y), number of teeth z, module m, pressure angle α, tooth thickness d, tooth width b, inner diameter k, keyway depth p, and height q of the target gears input by the technician according to the involute standard spur gear meshing relationship. The first gear parameters, such as d, tooth width b, inner diameter k, keyway depth p, and height q, are calculated to obtain the base circle diameter, addendum circle diameter, and dedendum circle diameter parameters of the target gear. These parameters are then defined as the second gear parameters of the target gear. Next, the motor controller integrates the first and second gear parameters corresponding to each target gear to obtain the individual gear parameters for each target gear. Based on these parameters, each target gear is modeled to obtain its corresponding gear model. Finally, the modeling unit executes the following steps based on the gear models: Figure 3 The assembly selection operation shown in the figure then assembles the established gear models according to the selected gear assembly model to generate a sensorless gear system. The established gear system is then imported into the simulation unit, which performs simulation testing on the gear system to obtain simulation results.
[0075] It is understood that in this embodiment, in addition to spur gears, gear types may also include helical gears and herringbone gears. Similarly, the modeling unit should preset the gear meshing relationships corresponding to each of the other gear types such as helical gears and herringbone gears. Of course, there are many ways to set the specific gear types and gear meshing relationships, and this invention does not limit them.
[0076] Furthermore, in this embodiment, in addition to the number of teeth, module, pressure angle, tooth thickness, tooth width, inner diameter, keyway depth, and height of the gear, other gear parameters obtained by the technician can also be set as the first gear parameters. Similarly, in addition to the base circle diameter, addendum circle diameter, base circle diameter, and dedendum circle diameter of the gear, other gear parameters can also be set as the second gear parameters. The present invention does not impose any restrictions on this.
[0077] Furthermore, in a feasible embodiment, the step S10 above, "constructing a gear system based on the gear parameters, and then performing simulation testing on the gear system to obtain simulation results," may specifically include:
[0078] Step S101: Determine the gear model corresponding to the target gear based on the gear parameters;
[0079] Step S102: Modify the gear parameters to determine the gear models corresponding to each of the other gears corresponding to the target gear;
[0080] Step S103: Combine the gear model wheels to construct a gear system, set the simulation parameters corresponding to the gear system, and then perform simulation tests on the gear system based on the simulation parameters to obtain simulation results;
[0081] Step S104: The gear model and the simulation parameters achieve real-time data exchange;
[0082] For example, please refer to Figure 3 , Figure 3 This is a schematic diagram of the modeling and simulation process involved in an embodiment of the gear fault diagnosis method of the present invention, as shown below. Figure 3 As shown, the modeling unit first models the target gear based on its gear parameters to obtain a gear model. Then, the modeling unit determines the gear parameters of each other gear in the field gear system corresponding to the target gear, modifies the acquired gear parameters based on the gear parameters of each other gear, and generates gear models corresponding to each other gear. After that, the modeling unit assembles the generated gear models to generate a gear system, and inputs the gear system into the simulation unit. The simulation unit sets simulation parameters such as material properties, mesh generation, load parameters, contact conditions, and boundary conditions in the gear system. The simulation unit then performs simulation tests on the gear system according to each simulation parameter and generates simulation results. The gear model generated by the modeling unit on the modeling simulation platform can communicate with the simulation parameters in the simulation test unit within the platform in real time.
[0083] Furthermore, in a feasible embodiment, the step of "performing simulation tests on the gear system based on each of the simulation parameters to obtain simulation results" in step S103 above may specifically include:
[0084] Step S1031: Perform simulation tests on the gear system according to the simulation parameters to obtain the meshing parameters generated by the target gear during meshing;
[0085] Step S1032: Determine the meshing time domain diagram corresponding to the meshing parameters, and determine the target protruding parameter in the meshing time domain diagram, and the target position of the target protruding parameter in the gear system;
[0086] Step S1033: Integrate the target protrusion parameters and the target position to obtain the simulation results;
[0087] For example, when acquiring a gear system, the simulation unit first sets simulation parameters such as material properties, mesh generation, load parameters, contact conditions, and boundary conditions in the gear system. Then, the simulation unit calls the internally configured visualization sub-unit, which calculates each simulation parameter according to a preset dynamic analysis solution method to generate meshing parameters such as meshing force, stiffness, and strain values of each gear in the gear system during meshing. Next, the visualization sub-unit generates time-domain plots of each meshing parameter changing over time, and then determines the changing trend of each meshing parameter during the operation of the gear system based on each time-domain plot, and generates analysis reports corresponding to each changing trend. Finally, the simulation unit determines the target protrusion parameter in the gear system based on the analysis report, and determines the target position of the target protrusion signal in the gear system, thereby integrating the target protrusion parameter and target position determination to obtain the simulation results, and uploading the simulation results to the motor controller.
[0088] Step S20: Determine the abnormal feature points in the gear system based on the simulation results, build an experimental test platform corresponding to the gear system based on the abnormal feature points, and conduct experimental tests on the experimental test platform to obtain experimental data.
[0089] In this embodiment, when the motor controller obtains the simulation results, it determines the abnormal feature points in the gear system based on the target position contained in the simulation results. At the same time, the motor controller obtains the physical model corresponding to the target gear and builds the physical model based on the abnormal feature points to obtain the experimental test platform corresponding to the target gear. The motor controller then calls the working condition control unit to control the experimental test platform to enter each preset working condition, and collects the signal parameters generated by the experimental test platform under each working condition through the signal acquisition unit. The motor controller then obtains experimental data based on each signal parameter.
[0090] For example, when the motor controller acquires simulation results, it determines abnormal feature points in the gear system based on the target positions contained in the simulation results. Then, the motor controller acquires the physical models corresponding to each gear in the gear system and splices the physical models based on the abnormal feature points to obtain the experimental test platform corresponding to the gear system. After that, the motor controller controls the experimental test platform to run under different working conditions such as forward speed, reverse speed, constant speed, and acceleration and deceleration through the working condition control unit. At the same time, during the operation of the experimental test platform, the motor controller acquires the test signals emitted by the abnormal feature points in the experimental test platform during the operation through the signal acquisition unit. Finally, the motor controller calls the internally configured signal conversion unit to convert the acquired test signals to obtain experimental data.
[0091] Furthermore, in a feasible embodiment, the step of "building an experimental test platform corresponding to the gear system based on the abnormal feature points" in step S20 above may specifically include:
[0092] Step S201: Determine the abnormal location within the gear system based on the abnormal feature points;
[0093] Step S202: Construct an experimental test platform corresponding to the gear system based on the abnormal location;
[0094] For example, the motor controller determines abnormal feature points in the gear system based on the target positions contained in the simulation results, and determines the abnormal positions of the abnormal feature points in the gear system. Then, the motor controller obtains the physical models corresponding to each gear in the gear system, and splices the physical models based on the abnormal positions to obtain the experimental test platform corresponding to the gear system.
[0095] Furthermore, in a feasible embodiment, the step of "performing experimental tests on the experimental testing platform to obtain experimental data" in step S20 above may specifically include:
[0096] Step S203: Obtain the test signals generated when the abnormal location is running under preset detection conditions;
[0097] Step S204: Extract the effective value from the test signal, and determine the initial vibration signal corresponding to the test signal based on the effective value;
[0098] Step S205: Perform noise reduction processing on the initial vibration signal to obtain the target vibration signal, and determine the target vibration signal as experimental data;
[0099] For example, please refer to Figure 5 , Figure 5The diagram illustrates the signal acquisition process of an embodiment of the gear fault diagnosis method of the present invention. As shown, the motor controller first controls the experimental test platform to enter different preset working conditions such as forward speed, reverse speed, constant speed, and acceleration / deceleration through the working condition control unit. Simultaneously, the motor controller controls the signal acquisition unit through the CPU to acquire electrical signals such as current, voltage, and potential generated by abnormal positions within the experimental test platform under each working condition. Then, the motor controller controls the signal acquisition unit to input the acquired electrical signals to the signal conversion unit through the CAN communication serial port. The signal conversion unit identifies the electrical signals through its internally configured vibration identification chip and converts them into initial vibration signals. The signal conversion unit inputs the acquired initial vibration signals to the gear fault diagnosis module through the CAN communication serial port. The noise reduction and filtering unit configured within the gear fault diagnosis module performs noise reduction and filtering on the initial vibration signals to improve the signal-to-noise ratio and reduce noise interference, thereby obtaining the target vibration signal. The gear fault diagnosis module then determines the target vibration signal as experimental data.
[0100] Step S30: Compare the experimental data with the simulation results to determine whether the experimental data and the simulation results match;
[0101] For example, the motor controller compares the acquired experimental data with the simulation results and determines the deviation value between the experimental data and the simulation results, and then judges whether the experimental data and the simulation results match based on the magnitude of the deviation value.
[0102] Step S40: If it is determined that the experimental data matches the simulation results, then the abnormal feature signals contained in the experimental data are identified, and the abnormal features are extracted from the abnormal feature signals.
[0103] In this embodiment, when the motor controller determines that the deviation between the experimental data and the simulation results is less than a preset deviation threshold, it determines that the experimental data and the simulation results match. The motor controller then identifies the abnormal signal generated in the experimental data as the abnormal feature signal corresponding to the gear system and inputs the abnormal feature signal to the feature extraction unit. The feature extraction unit then extracts features from the abnormal feature signal to obtain abnormal features.
[0104] For example, please refer to Figure 4 , Figure 4 This is a flowchart illustrating the simulation-guided experiment setup for an embodiment of the gear fault diagnosis method of the present invention, as shown below. Figure 4As shown, when the motor controller determines that the deviation between the experimental data and the simulation results is less than the preset deviation percentage, the motor controller determines that the experimental data and the simulation results match. The motor controller then identifies the abnormal signal appearing in the target vibration signal as the abnormal feature signal corresponding to the gear system and inputs the abnormal feature signal to the feature extraction unit. The feature extraction unit performs feature extraction on the abnormal feature signal according to multiple preset processing algorithms to obtain the abnormal features corresponding to the gear system.
[0105] Furthermore, in a feasible embodiment, the step of "extracting abnormal features from the abnormal feature signal" in step S40 above may specifically include:
[0106] Step S401: Perform noise reduction filtering on the abnormal feature signal to obtain the target feature signal;
[0107] Step S402: Obtain multiple preset processing algorithms, and extract abnormal features from the target feature signal based on each of the processing algorithms;
[0108] For example, please refer to Figure 6 , Figure 6 This is a schematic diagram of the fault diagnosis process according to an embodiment of the gear fault diagnosis method of the present invention. The motor controller inputs the acquired abnormal feature signal to the gear fault diagnosis module. The gear fault diagnosis module calls the internally configured filtering and noise reduction unit to process the vibration spectrum corresponding to the abnormal feature signal, thereby dividing the frequency signal contained in the vibration spectrum into high-frequency and low-frequency parts according to different frequencies. Then, the filtering and noise reduction unit performs windowing processing on the low-frequency part according to a preset first time interval, thereby obtaining first information in the low-frequency part. At the same time, the filtering and noise reduction unit performs windowing processing on the high-frequency part according to a second time interval less than the first time interval, thereby obtaining second information in the high-frequency part. Then, the filtering and noise reduction unit... The first and second information are integrated to filter the vibration signal. The integrated first and second information are then used to obtain the target feature signal, which is input to the feature extraction unit. The feature extraction unit samples the target feature signal at preset third time intervals to acquire discrete vibration signals. The feature extraction unit performs framing and windowing operations on the acquired discrete vibration signals and uses a Fast Fourier Transform (FFT) method to transform the acquired discrete signals into frequency domain signals. The prominent components in the frequency signals are then converted into energy. The feature extraction unit represents the energy using video graphs such as spectrograms or envelope spectra to obtain the target feature image. Finally, the feature extraction unit uses methods such as... Figure 6One or more of the following processing algorithms, such as wavelet transform, morphological filtering, empirical mode decomposition, global average empirical mode decomposition, convolutional neural network, reinforcement learning, and deep learning, are used to perform image enhancement, texture analysis, image segmentation, image feature recognition, and image matching operations on the target feature image, thereby identifying abnormal features in the target feature image.
[0109] Furthermore, in a feasible embodiment, after step S30 above, the gear fault diagnosis method of the present invention may further include:
[0110] Step A10: If it is determined that the experimental data does not match the simulation results, the gear parameters contained in the gear system are corrected, and the gear system is rebuilt based on the corrected gear parameters;
[0111] Step A20: Perform simulation tests on the re-established gear system and obtain new simulation results;
[0112] For example, when the motor controller determines that the deviation between the experimental data and the simulation results is greater than a preset deviation percentage, it determines that the experimental data and the simulation results do not match. Therefore, it modifies and re-silences the parameters of each gear in the gear system to obtain new gear models. Then, the motor controller builds each new gear model through the modeling unit to generate a new gear system and inputs the new gear system into the simulation unit. The simulation unit then performs simulation testing on the new gear system to obtain simulation results.
[0113] Step S50: Generate a target feature image based on the abnormal features, and compare the target feature image with a preset standard feature image to obtain the gear fault type corresponding to the target gear;
[0114] For example, please refer to Figure 7 , Figure 7 This is a gear wear fault spectrum diagram according to an embodiment of the gear fault diagnosis method of the present invention. The motor controller inputs the acquired abnormal features to the feature recognition unit configured in the gear fault diagnosis module, and the feature recognition unit generates a spectrum diagram of the gear wear fault based on the acquired abnormal features. Figure 7 The target feature image is shown. At the same time, the motor controller reads the storage device to obtain the standard feature image and inputs the standard feature image to the feature recognition unit. The feature recognition unit compares the obtained target feature image and the standard feature image to determine the gear fault type corresponding to the gear system.
[0115] Furthermore, in a feasible embodiment, the step S50 above, "comparing the target feature image with a preset standard feature image to obtain the gear fault type corresponding to the target gear," may specifically include:
[0116] Step S501: Obtain a preset standard feature image, and compare the target feature image with the standard feature image to determine a standard fault feature in the standard feature image that is consistent with the abnormal feature contained in the target feature image;
[0117] Step S502: Determine the standard fault type corresponding to the standard feature in the standard feature image, and determine the standard fault type as the gear fault type corresponding to the target gear;
[0118] For example, the motor controller first reads the storage device to obtain a standard feature image containing a standard fault feature and a standard fault type corresponding to each standard fault feature. The standard feature image is then input to the feature recognition unit in the gear fault diagnosis module. The feature recognition unit filters the standard feature image based on the obtained target feature image to determine the standard fault feature that is consistent with the abnormal feature contained in the target feature image, and determines the standard fault type corresponding to the standard fault feature. Then, the standard fault type is determined as the gear fault type corresponding to the gear system.
[0119] In this embodiment, during operation, the motor controller first acquires the gear parameters of the target gear input by the technician. The motor controller then inputs these parameters to the modeling unit, which models the target gear based on these parameters to obtain a corresponding gear model. The modeling unit then assembles the gear model to establish a sensorless gear system. The motor controller calls the simulation unit to perform a simulation test on the gear system, thereby obtaining the simulation test results. Afterward, when acquiring the simulation results, the motor controller determines abnormal feature points in the gear system based on the target positions contained within the simulation results. Simultaneously, the motor controller acquires the physical model corresponding to the target gear and builds an experimental test platform based on the abnormal feature points. The motor controller then calls the operating condition control unit to control the experimental test platform to enter various preset operating conditions, and collects the signal parameters generated by the experimental test platform under each operating condition through the signal acquisition unit. The motor controller then obtains experimental data based on these signal parameters. Next, the motor controller compares the acquired experimental data with the simulation results and determines the deviation value between the experimental data and the simulation results. Then, based on the magnitude of the deviation value, it judges whether the experimental data and the simulation results match. When the motor controller determines that the deviation value between the experimental data and the simulation results is less than the preset deviation threshold, it determines that the experimental data and the simulation results match. The motor controller then identifies the abnormal signals generated in the experimental data as abnormal feature signals corresponding to the gear system and inputs the abnormal feature signals to the feature extraction unit. The feature extraction unit extracts features from the abnormal feature signals to obtain abnormal features. Finally, the motor controller inputs the obtained abnormal features to the feature recognition unit configured in the gear fault diagnosis module. The feature recognition unit generates a target feature image based on the obtained abnormal features. At the same time, the motor controller reads the storage device to obtain a standard feature image and inputs the standard feature image to the feature recognition unit. The feature recognition unit compares the obtained target feature image and the standard feature image to determine the gear fault type corresponding to the gear system.
[0120] Thus, this invention employs a method where gear parameters of the target gear are input into a simulation testing platform. The platform then models the target gear based on these parameters, creating a sensorless gear system. Simulation testing is performed on this system to identify anomalous feature points. An experimental testing platform is then built based on these anomalous feature points. Experimental testing is conducted on this platform to determine fault characteristics within the gear system. Finally, the acquired fault characteristics are used to filter preset standard feature images to determine the corresponding gear fault type for the target gear. In other words, this invention solves the current problem where, when a gear system contains multiple gears, multiple different gear models need to be created for each gear, and then... Simulation analysis requires significant effort from various operations such as model improvement, network partitioning, and optimization design for different gear models. This invention addresses the challenge of determining sensor placement and quantity within a gear system by constructing a sensorless gear system. Furthermore, by filtering standard feature images based on fault characteristics to identify gear fault types, this invention overcomes the low accuracy of current fixed algorithms when diagnosing multiple gear faults. This allows motor controllers to construct sensorless gear systems based on acquired gear parameters, enabling simulation and experimental testing to determine fault causes and reducing the costs associated with deploying sensors on gears.
[0121] In addition, the present invention also provides a gear fault diagnosis system, please refer to... Figure 8 , Figure 8 This is a schematic diagram of the functional modules involved in an embodiment of the gear fault diagnosis method of the present invention, as shown below. Figure 8 As shown, the gear fault diagnosis system of the present invention includes:
[0122] The gear modeling and simulation module 10 is used to acquire the gear parameters of the target gear, construct a gear system based on the gear parameters, and then perform simulation testing on the gear system to obtain simulation results. The simulation results are then input to the gear signal acquisition module. The modeling and simulation data within the gear modeling and simulation module are interconnected in real time.
[0123] The gear signal acquisition module 20 is used to acquire the simulation results, determine the abnormal feature points in the gear system based on the simulation results, build an experimental test platform corresponding to the gear system based on the abnormal feature points, and conduct experimental tests on the experimental test platform to obtain experimental data. If it is determined that the experimental data matches the simulation results, the abnormal feature signal contained in the experimental data is determined, and the abnormal feature signal is input to the gear fault diagnosis module.
[0124] The gear fault diagnosis module 30 is used to extract abnormal features from the abnormal feature signal, generate a target feature image based on the abnormal features, and compare the target feature image with a preset standard feature image to obtain the gear fault type corresponding to the target gear.
[0125] Furthermore, the gear signal acquisition module 20 includes:
[0126] The experimental testing platform is used to control the signal acquisition unit to acquire the test signals generated when the abnormal position is running under preset detection conditions, and to input the test signals to the signal conversion unit;
[0127] The signal conversion unit is used to extract the effective value from the test signal, determine the initial vibration signal corresponding to the test signal based on the effective value, and then perform noise reduction processing on the initial vibration signal to obtain the target vibration signal, thereby determining the target vibration signal as experimental data.
[0128] Furthermore, the gear fault diagnosis module 30 includes:
[0129] The filtering and noise reduction unit is used to perform noise reduction and filtering operations on the abnormal feature signal to obtain the target feature signal, and input the target feature signal to the feature extraction unit;
[0130] The feature extraction unit is used to acquire multiple preset processing algorithms, extract abnormal features from the target feature signal based on each of the processing algorithms, and then input the abnormal features to the feature recognition unit.
[0131] The feature recognition unit is used to acquire a preset standard feature image and compare the target feature image with the standard feature image to determine a standard fault feature in the standard feature image that is consistent with the abnormal feature contained in the target feature image.
[0132] Furthermore, the present invention also provides a motor controller having a gear fault diagnosis program that can run on a processor, wherein when the motor controller executes the gear fault diagnosis program, it implements the steps of the gear fault diagnosis method as described in any of the above embodiments.
[0133] The specific embodiments of the motor controller of the present invention are basically the same as the embodiments of the gear fault diagnosis method described above, and will not be repeated here.
[0134] Furthermore, the present invention also provides a computer-readable storage medium storing a gear fault diagnosis program, which, when executed by a processor, implements the steps of the gear fault diagnosis method as described in any of the above embodiments.
[0135] The specific embodiments of the computer-readable storage medium of this invention are basically the same as the embodiments of the gear fault diagnosis method described above, and will not be repeated here.
[0136] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.
[0137] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.
[0138] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a motor controller (which can be a device for executing the gear fault diagnosis method of the present invention for faulty gears, specifically a mobile terminal, data storage control terminal, PC, or portable computer, etc.) to execute the methods described in the various embodiments of the present invention.
[0139] The above are merely preferred embodiments of the present invention and do not limit the patent scope of the present invention. Any equivalent structural or procedural transformations made based on the content of the present invention's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of the present invention.
Claims
1. A method for diagnosing gear faults, characterized in that, The gear fault diagnosis method includes the following steps: The gear parameters of the target gear are obtained, and a gear system is constructed based on the gear parameters. Then, the gear system is simulated and tested to obtain simulation results. Based on the simulation results, abnormal feature points in the gear system are determined. An experimental test platform corresponding to the gear system is built based on the abnormal feature points, and experimental tests are conducted on the experimental test platform to obtain experimental data. The experimental data is compared with the simulation results to determine whether the experimental data and the simulation results match. If it is determined that the experimental data matches the simulation results, then the abnormal feature signals contained in the experimental data are identified, and the abnormal features are extracted from the abnormal feature signals. A target feature image is generated based on the abnormal features, and the target feature image is compared with a preset standard feature image to obtain the gear fault type corresponding to the target gear.
2. The gear fault diagnosis method as described in claim 1, characterized in that, The step of constructing a gear system based on the gear parameters, and then performing simulation tests on the gear system to obtain simulation results includes: Determine the gear model corresponding to the target gear based on the gear parameters; The gear parameters are modified to determine the gear models corresponding to each of the other gears corresponding to the target gear. The gear models are combined to construct a gear system, and the simulation parameters corresponding to the gear system are set. Then, the gear system is simulated and tested based on the simulation parameters to obtain simulation results. The gear model and the simulation parameters achieve real-time data exchange.
3. The gear fault diagnosis method as described in claim 2, characterized in that, The step of performing simulation tests on the gear system based on each of the simulation parameters to obtain simulation results includes: The gear system is simulated and tested according to the simulation parameters to obtain the meshing parameters generated by the target gear during meshing. Determine the meshing time-domain diagram corresponding to the meshing parameters, and determine the target protrusion parameter in the meshing time-domain diagram, and the target position of the target protrusion parameter in the gear system; The simulation results are obtained by integrating the target prominence parameters and the target position.
4. The gear fault diagnosis method as described in claim 3, characterized in that, The steps of building the experimental test platform corresponding to the gear system based on the abnormal feature points include: The abnormal location within the gear system is determined based on the abnormal feature points; An experimental test platform corresponding to the gear system is constructed based on the abnormal location.
5. The gear fault diagnosis method as described in claim 4, characterized in that, The step of conducting experimental tests on the experimental testing platform to obtain experimental data includes: Acquire the test signals generated at the abnormal location under various preset detection conditions; Extract the effective value from the test signal, and determine the initial vibration signal corresponding to the test signal based on the effective value; The initial vibration signal is subjected to noise reduction processing to obtain the target vibration signal, and the target vibration signal is determined as experimental data.
6. The gear fault diagnosis method as described in claim 1, characterized in that, After the step of comparing the experimental data with the simulation results to determine whether the experimental data and the simulation results match, the method further includes: If it is determined that the experimental data does not match the simulation results, the gear parameters contained in the gear system are corrected, and the gear system is rebuilt based on the corrected gear parameters. The rebuilt gear system was subjected to simulation testing, and new simulation results were obtained.
7. The gear fault diagnosis method as described in claim 1, characterized in that, The step of extracting anomalous features from the anomalous feature signal includes: The target feature signal is obtained by performing a noise reduction filtering operation on the abnormal feature signal; Multiple preset processing algorithms are obtained, and abnormal features are extracted from the target feature signal based on each of the processing algorithms.
8. The gear fault diagnosis method as described in claim 1, characterized in that, The step of comparing the target feature image with a preset standard feature image to obtain the gear fault type corresponding to the target gear includes: A preset standard feature image is obtained, and the target feature image is compared with the standard feature image to determine a standard fault feature in the standard feature image that is consistent with the abnormal feature contained in the target feature image; In the standard feature image, the standard fault type corresponding to the standard feature is determined, and the standard fault type is determined as the gear fault type corresponding to the target gear.
9. A gear fault diagnosis system, characterized in that, The gear fault diagnosis system includes: The gear modeling and simulation module is used to acquire the gear parameters of the target gear, construct a gear system based on the gear parameters, and then perform simulation testing on the gear system to obtain simulation results. The simulation results are then input to the gear signal acquisition module. The modeling and simulation data within the gear modeling and simulation module are interconnected in real time. The gear signal acquisition module is used to acquire the simulation results, determine the abnormal feature points in the gear system based on the simulation results, build an experimental test platform corresponding to the gear system based on the abnormal feature points, and conduct experimental tests on the experimental test platform to obtain experimental data. If it is determined that the experimental data matches the simulation results, the abnormal feature signals contained in the experimental data are determined, and the abnormal feature signals are input to the gear fault diagnosis module. The gear fault diagnosis module is used to extract abnormal features from the abnormal feature signal, generate a target feature image based on the abnormal features, and compare the target feature image with a preset standard feature image to obtain the gear fault type corresponding to the target gear.
10. The gear fault diagnosis system as described in claim 9, characterized in that, The gear signal acquisition module includes: The experimental testing platform is used to control the signal acquisition unit to acquire the test signals generated when the abnormal position is running under preset detection conditions, and to input the test signals to the signal conversion unit; The signal conversion unit is used to extract the effective value from the test signal, determine the initial vibration signal corresponding to the test signal based on the effective value, and then perform noise reduction processing on the initial vibration signal to obtain the target vibration signal, thereby determining the target vibration signal as experimental data.
11. The gear fault diagnosis system as described in claim 10, characterized in that, The gear fault diagnosis module includes: The filtering and noise reduction unit is used to perform noise reduction and filtering operations on the abnormal feature signal to obtain the target feature signal, and input the target feature signal to the feature extraction unit; The feature extraction unit is used to acquire multiple preset processing algorithms, extract abnormal features from the target feature signal based on each of the processing algorithms, and then input the abnormal features to the feature recognition unit. The feature recognition unit is used to acquire a preset standard feature image and compare the target feature image with the standard feature image to determine a standard fault feature in the standard feature image that is consistent with the abnormal feature contained in the target feature image.
12. A motor controller, characterized in that, The motor controller includes: a memory, a processor, and a gear fault diagnosis program stored in the memory and executable on the processor, wherein when the gear fault diagnosis program is executed by the processor, it implements the steps of the gear fault diagnosis method as described in any one of claims 1 to 8.
13. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a gear fault diagnosis program, which, when executed by a processor, implements the steps of the gear fault diagnosis method as described in any one of claims 1 to 8.