Servo motor and industrial robot

Abstract

The invention relates to a servo motor and an industrial robot, and belongs to the technical field of intelligent driving of servo motors and industrial robots. The servo motor comprises a motor body and further comprises a servo motor body, the multi-mode sensing module is used for forming an electromagnetic-heat-force-vibration four-domain sensing network and integrating electromagnetic-heat-force-vibration four-domain monitoring of the motor body; the multi-physics field construction module is used for motor three-dimensional reconstruction based on CT scanning and constructing an electromagnetic field-thermal field-structural field multi-physics field coupling model; the fault diagnosis module is used for identifying a fault type through the multi-physics field construction module; the maintenance strategy optimization module is used for backtracking a vibration propagation path in the digital mirror image when a fault is detected; the influence of different maintenance schemes on the work of the servo motor is simulated through digital mirror images, and the optimal scheme is selected for output. The industrial robot comprises a robot body and further comprises the servo motor.

Description

Technical Field

[0001] The present invention relates to a servo motor and an industrial robot, belonging to the technical field of intelligent driving of servo motors and industrial robots. Background Art

[0002] The core components of industrial robots can be likened to the three major systems of the human body: the servo motor serves as the "power muscle," the speed reducer acts as the "circulatory system," and the controller acts as the "nerve center." The servo motor system forms the foundation of the robot's motion execution, with its precision drive units embedded in the joints of the robotic arm, directly determining the device's kinematic performance. Currently, industrial robot joint actuation relies on servo systems for precise control. As application requirements for smooth operation and positioning accuracy increase, servo motor technical specifications are experiencing exponential growth. These requirements include: instantaneous high output torque to cope with sudden load changes, millisecond-level dynamic response to ensure trajectory tracking accuracy, excellent torque-inertia matching for agile start-stop control, and an ultra-wide speed range to meet operational requirements across a wide range of operating conditions, from low-speed, high-precision to high-speed, high-performance. These technological breakthroughs are supporting the evolution of modern industrial robots towards greater intelligence and dexterity.

[0003] Existing industrial robot servo motors generally have the following problems:

[0004] Fault diagnosis lag: Traditional detection relies on manual inspections or offline testing, which cannot capture hidden faults in dynamic working conditions in real time.

[0005] Parameter configuration error: Core parameters such as the number of motor pole pairs and encoder line count rely on manual calibration, which can easily lead to control inaccuracy due to installation deviations;

[0006] Insufficient environmental adaptability: The lack of dynamic compensation mechanism for environmental factors such as vibration and temperature affects the robot's repeatability.

[0007] Complex structural assembly and disassembly: Traditional connection methods rely on welding or complex bolt fixation, which has high maintenance costs.

[0008] For example, Chinese patent publication number CN115683235A discloses a method and device for detecting vibration faults in industrial robot servo motors. The method includes: simulating and testing vibration faults in servo motors under different operating conditions and different fault causes in simulation and laboratory environments, respectively, to obtain corresponding multi-sensor measurement signals; establishing a SAE neural network model; using the multi-sensor measurement signals obtained in the simulation environment to form a first unlabeled multidimensional signal sample set, and initializing and training the SAE neural network model; using the multi-sensor measurement signals obtained in the laboratory environment to form a second labeled multidimensional signal sample set, and fine-tuning the SAE neural network model; controlling the servo motor to be tested to operate according to test cases corresponding to different operating conditions, and inputting the collected multi-dimensional signal samples into the SAE neural network model for vibration anomaly detection. This method can achieve automatic and accurate detection of servo motor vibration faults and fault cause analysis. However, the fault detection is limited and still relies on manual inspections or offline testing, and cannot "capture hidden faults in dynamic conditions in real time." Summary of the Invention

[0009] The object of the present invention is to provide a servo motor and an industrial robot to solve the problem of delayed fault diagnosis and inability to capture hidden faults under dynamic working conditions in real time.

[0010] The servo motor of the present invention includes a motor body and further includes:

[0011] Multimodal sensing module: used to form an electromagnetic-thermal-mechanical-vibration four-domain sensing network, integrating electromagnetic-thermal-mechanical-vibration four-domain monitoring of the motor body;

[0012] Multi-physics construction module: used for 3D reconstruction of motors based on CT scans and construction of electromagnetic field, thermal field, and structural field multi-physics coupling models;

[0013] Fault diagnosis module: used to identify fault types through multi-physics field building modules;

[0014] Maintenance strategy optimization module: used to trace the vibration propagation path in the digital mirror when a fault is detected; simulate the impact of different maintenance plans on the servo motor operation through the digital mirror, and select the optimal plan for output.

[0015] A multimodal sensing network is employed to achieve comprehensive monitoring of the motor's operating status through the fusion of electromagnetic, thermal, mechanical, and vibration sensors, avoiding the blind spots of single-parameter monitoring and improving the timeliness of fault warnings. A multi-physics coupling model is constructed using 3D reconstruction technology from CT scans to construct an electromagnetic, thermal, and structural field coupling model. This model accurately simulates the complex interactions within the motor's internal physical fields, providing theoretical support for design optimization and fault prediction. A closed-loop fault diagnosis system combines multi-physics models with real-time sensor data to intelligently identify fault types, reduce manual intervention, and improve diagnostic accuracy. Digital mirroring technology is used to trace back fault paths and simulate repair plans, selecting the optimal strategy, significantly reducing unplanned downtime and improving production efficiency.

[0016] Preferably, the multimodal perception module includes:

[0017] Electromagnetic field sensor: installed at the end of the stator winding, used to measure the air gap magnetic flux distribution in real time;

[0018] Temperature sensor: installed on the stator winding to measure temperature data in real time;

[0019] Stress sensor: installed on the stator core yoke to measure stress distribution in real time;

[0020] Vibration sensor: installed at the end of the output shaft of the motor body, used to measure vibration characteristics in real time.

[0021] Electromagnetic field sensors monitor the air gap flux density distribution in real time, optimizing electromagnetic design parameters, reducing the risk of magnetic circuit saturation, and improving motor efficiency. Temperature sensors accurately measure stator winding temperature, preventing insulation failure caused by overheating and extending motor life. Stress sensors monitor the stress distribution in the stator core to prevent mechanical fatigue and performance degradation caused by structural deformation. Vibration sensors capture output shaft vibration characteristics, enabling early detection of bearing wear or imbalance, reducing the probability of sudden failure.

[0022] Preferably, the multi-physics field building module includes:

[0023] Electromagnetic field model building unit: used to build a three-dimensional electromagnetic field mathematical model of the motor based on CT scanning;

[0024] Temperature model building unit: used to build a three-dimensional thermal field mathematical model of the motor based on CT scanning;

[0025] Stress model building unit: used to build a three-dimensional mathematical model of the stress field of the motor based on CT scanning;

[0026] Vibration model building unit: used to build a three-dimensional vibration field mathematical model of the motor based on CT scanning;

[0027] Multi-physics field construction unit: used to couple electromagnetic field mathematical models, thermal field mathematical models, stress field mathematical models, and vibration field mathematical models, and define boundary conditions and initial conditions;

[0028] Model verification unit: used to calibrate model parameters through physical test data;

[0029] Dynamic optimization unit: used to iteratively update the model through real-time sensor data to achieve virtual and real mutual control.

[0030] The electromagnetic field model, based on a three-dimensional model derived from CT scans, accurately calculates magnetic field distribution, optimizes coil layout, and reduces eddy current losses. The thermal field model predicts temperature gradient distribution, guiding the optimization of heat dissipation structures to avoid local overheating. The stress field model analyzes areas of mechanical stress concentration, optimizing material selection and structural design to enhance fatigue resistance. The vibration field model simulates vibration propagation paths, optimizes vibration reduction design, and reduces noise and mechanical wear. Model validation and dynamic optimization calibrate model parameters using physical test data and iterates updates based on real-time sensor data, enabling virtual-physical control and adaptability to dynamic operating conditions. Fault diagnosis is rapid, enabling real-time detection of hidden faults under dynamic operating conditions.

[0031] Preferably, the multi-physics field construction unit specifically includes:

[0032] Coupling variable definition subunit: used to define coupling variables to achieve data transfer between different physical fields. Coupling variables include temperature, stress, displacement, electromagnetic force, and vibration acceleration.

[0033] Boundary Condition and Load Setting Subunit: used to set boundary conditions and loads. Boundary conditions and loads are set according to the interaction and influence between different physical fields:

[0034] (1) Coupling of electromagnetic field and temperature field: the heat generated by the electromagnetic field serves as the heat source of the temperature field;

[0035] (2) Coupling of temperature field and stress field: thermal expansion or contraction caused by temperature change acts as a load in the stress field;

[0036] (3) Coupling of stress field and vibration field: the structural deformation caused by stress serves as the initial condition or boundary condition of the vibration field;

[0037] (4) Coupling of vibration field and electromagnetic field: dynamic inductance changes caused by vibration;

[0038] Meshing and Solver Configuration subunit: used to mesh the fully coupled model and configure the solver;

[0039] Solution and result analysis subunit: used to obtain the results of the comprehensive coupled model, analyze it, and evaluate the accuracy and reliability of the model.

[0040] Coupling variable definition clarifies key coupling variables such as temperature, stress, and displacement, enabling multi-physics data interaction and improving simulation accuracy. Define coupling relationships between electromagnetic and temperature fields, and between temperature and stress fields, to simulate physical interactions under actual working conditions. Optimize mesh density and solver algorithms to balance computational efficiency and accuracy, accelerating design iterations. The solution and results analysis subunit evaluates model accuracy, identifies potential design flaws, and guides parameter optimization.

[0041] Preferably, the electromagnetic field model building unit specifically includes:

[0042] Electromagnetic field geometry modeling subunit: used to build a 3D model of the motor based on CT scanning, set up analysis modules, and create an analytical geometry model;

[0043] Electromagnetic field meshing subunit: used to discretize the geometric three-dimensional model into finite elements or meshes;

[0044] Electromagnetic field solution setting subunit: used to select the solver type, set the excitation source and boundary conditions;

[0045] Electromagnetic field solution and post-processing subunit: used to solve the electromagnetic field distribution and visualize the results;

[0046] Electromagnetic Field Verification and Optimization Subunit: used to verify model accuracy by comparing experimental data or analytical solutions, and to optimize parameters to optimize performance.

[0047] Preferably, the fault diagnosis module diagnoses motor faults based on deep learning.

[0048] Deep learning algorithms automatically learn fault characteristics, reducing manual intervention and improving diagnostic robustness. They adapt to different operating conditions and fault types, reducing reliance on expert experience and enabling cross-scenario applications.

[0049] Preferably, the fault diagnosis module adopts an improved one-dimensional convolutional neural network, the input layer is the four-domain perception signal of electromagnetic-thermal-force-vibration, the middle layer contains 3 layers of convolution and 2 layers of LSTM, and the output layer is a Softmax classifier.

[0050] The input layer integrates electromagnetic, thermal, mechanical, and vibration signals for four-domain signal fusion, providing comprehensive diagnostic evidence and avoiding information silos. Three convolution layers extract local features, while two LSTM layers capture temporal dependencies and spatial and temporal features, improving fault classification accuracy. The output layer's Softmax classifier determines the probability of fault type, providing quantitative support for maintenance decisions.

[0051] Preferably, the maintenance strategy optimization module includes:

[0052] Fault tracing unit: used to trace the vibration propagation path in the digital image when a motor fault is detected;

[0053] Strategy optimization unit: used to simulate the impact of different maintenance plans on the production line through digital mirroring;

[0054] Output unit: used to select the optimal solution output;

[0055] Adaptive control unit: used to automatically reduce speed or stop the machine when a motor fault is detected.

[0056] Tracing vibration propagation paths in a digital image allows rapid location of fault sources, shortening troubleshooting time. The digital image simulates the impact of different maintenance options on the production line, selecting the lowest-cost, most efficient strategy. By combining fault types with production requirements, an actionable maintenance plan is generated to minimize downtime losses. Automatically reducing speed or shutting down the machine in the event of a fault prevents escalation and ensures the safety of personnel and equipment.

[0057] The industrial robot described in the present invention includes a robot body and the above-mentioned servo motor.

[0058] By integrating the above-mentioned servo motors, industrial robots can realize real-time monitoring and multi-physics field coupling analysis of the four domains of electromagnetic, thermal, force and vibration, accurately control joint motion parameters (such as torque, speed, and position), and significantly improve operation accuracy and dynamic response speed.

[0059] Compared with the existing technology, the servo motor and industrial robot of the present invention have the following beneficial effects:

[0060] The servo motor of the present invention has the following beneficial effects:

[0061] 1. Technical performance leap

[0062] Multi-dimensional perception and precise control achieve comprehensive monitoring of the motor's operating status through the electromagnetic-thermal-force-vibration four-domain perception network. Combined with the multi-physics field coupling model, it can accurately predict the electromagnetic force distribution, temperature gradient, stress concentration and vibration propagation path, thereby improving motor control accuracy and dynamic response speed, significantly outperforming traditional servo motors.

[0063] The electromagnetic field, thermal field, and structural field coupling model constructed based on CT scanning three-dimensional reconstruction technology can simulate the motor behavior under extreme working conditions (such as overload and high temperature), guide material selection and structural optimization (such as optimizing the thickness of the stator core silicon steel sheets and improving the layout of the heat dissipation ribs), thereby increasing the motor power density and reducing torque fluctuations.

[0064] 2. Enhanced maintenance reliability

[0065] Through the deep learning fault diagnosis module, real-time analysis of four-domain perception signals can predict faults such as bearing wear and insulation aging in advance. Combined with digital mirroring technology to trace the vibration propagation path, the fault location time is shortened and the unplanned downtime rate is reduced.

[0066] 3. Energy efficiency and environmental benefits

[0067] The multi-physics field coupling model guides the optimization of servo motor parameters (such as current harmonic suppression and heat dissipation structure improvement), thereby improving the overall energy efficiency of the motor, reducing energy consumption at the same power, and reducing carbon emissions.

[0068] 4. Adaptive security control

[0069] When a motor fault is detected, the adaptive control unit can automatically trigger speed reduction (speed reduced to a safe threshold) or shutdown protection to avoid safety accidents such as robot arm collision and workpiece damage. At the same time, through the coupling analysis of electromagnetic field and vibration field, the vibration suppression strategy is optimized to reduce the robot's operating noise and improve the working environment.

[0070] The industrial robot described in the present invention has the following beneficial effects:

[0071] 1. Enhanced fault prediction and health management (PHM) capabilities

[0072] Through the servo motor's deep learning fault diagnosis module, the industrial robot can analyze four-domain perception signals in real time and predict typical faults such as bearing wear and insulation aging 15-30 days in advance. Combined with digital mirroring technology, it can trace the vibration propagation path and locate the fault source efficiently, significantly reducing the risk of unplanned downtime.

[0073] 2. Maintenance cost and cycle optimization

[0074] The maintenance strategy optimization module supports simulating the impact of different maintenance plans on the production line (such as maintenance time and fluctuations in defective product rates) in a digital mirror. After selecting the optimal plan, maintenance time is shortened, spare parts inventory costs are reduced, and maintenance costs throughout the entire life cycle are reduced.

[0075] 3. Adaptive control and enhanced safety

[0076] When a motor fault is detected, the adaptive control unit can automatically trigger speed reduction (speed reduced to a safe threshold) or shutdown protection to avoid safety accidents such as robot arm collision and workpiece damage. At the same time, through the coupling analysis of electromagnetic field and vibration field, the vibration suppression strategy is optimized to reduce the robot's operating noise.

[0077] 4. Improved energy efficiency and reliability

[0078] The multi-physics field coupling model guides the optimization of servo motor parameters (such as current harmonic suppression and heat dissipation structure improvement), thereby improving the overall energy efficiency of industrial robots, extending MTBF (mean time between failures), and adapting to high-load and continuous production scenarios.

[0079] 5. Enhanced design iteration and customization capabilities

[0080] Based on the three-dimensional reconstruction and dynamic optimization unit of CT scanning, industrial robot manufacturers can quickly verify the impact of new joint designs (such as lightweight materials and modular structures) on overall performance, shorten the product development cycle, and support the rapid customization of robot functions in flexible production lines.

[0081] 6. Intelligent production network integration

[0082] The digital mirroring technology of servo motors can be seamlessly connected to the factory's MES / ERP system to achieve cloud-based monitoring and collaborative scheduling of robot health status and maintenance plans, providing key device-level data support for the Industrial Internet platform and promoting the transformation to intelligent manufacturing. BRIEF DESCRIPTION OF THE DRAWINGS

[0083] Figure 1 This is a structural block diagram of a servo motor described in the present invention. DETAILED DESCRIPTION

[0084] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0085] Example 1

[0086] like Figure 1 As shown, this embodiment discloses a servo motor, including a motor body, and further comprising;

[0087] Multimodal sensing module: used to form an electromagnetic-thermal-mechanical-vibration four-domain sensing network, integrating electromagnetic-thermal-mechanical-vibration four-domain monitoring of the motor body;

[0088] Multi-physics construction module: used for 3D reconstruction of motors based on CT scans and construction of electromagnetic field, thermal field, and structural field multi-physics coupling models;

[0089] Fault diagnosis module: used to identify fault types through multi-physics field building modules;

[0090] Maintenance strategy optimization module: used to trace the vibration propagation path in the digital mirror when a fault is detected; simulate the impact of different maintenance plans on the servo motor operation through the digital mirror, and select the optimal plan for output.

[0091] Fault diagnosis has evolved from "passive response" to "active prevention"; control performance has evolved from "single working condition adaptation" to "multi-process intelligent switching"; maintenance strategy has evolved from "regular replacement" to "on-demand maintenance"; system reliability has evolved from "single-machine redundancy" to "full-link fault tolerance."

[0092] The multimodal perception module includes:

[0093] Electromagnetic field sensor: installed at the end of the stator winding, used to measure the air gap magnetic flux distribution in real time; specifically, three micro Hall sensors (range ±5T, resolution 1mT) are embedded at the end of the stator winding to measure the air gap magnetic flux distribution in real time;

[0094] Temperature sensor: set on the stator winding, used to measure temperature data in real time; specifically,

[0095] Stress sensors are installed in the stator core yoke to measure stress distribution in real time. Specifically, fiber grating sensors (FBGs, with a wavelength accuracy of 1pm / °C) are embedded in the stator core yoke and used inverse finite element modeling to invert stress distribution. NTC thermistors (with an accuracy of ±0.5°C) are embedded in the stator windings and used in conjunction with a heat conduction model to calculate hotspot temperatures.

[0096] Vibration sensor: It is installed at the end of the output shaft of the motor body and is used to measure the vibration characteristics in real time. Specifically, a three-axis MEMS accelerometer is integrated at the end of the motor output shaft, and the vibration characteristic frequency band is extracted through wavelet packet decomposition.

[0097] The multiphysics building blocks include:

[0098] Electromagnetic field model building unit: used to build a three-dimensional electromagnetic field mathematical model of the motor based on CT scanning;

[0099] Temperature model building unit: used to build a three-dimensional thermal field mathematical model of the motor based on CT scanning;

[0100] Stress model building unit: used to build a three-dimensional mathematical model of the stress field of the motor based on CT scanning;

[0101] Vibration model building unit: used to build a three-dimensional vibration field mathematical model of the motor based on CT scanning;

[0102] Multi-physics field construction unit: used to couple electromagnetic field mathematical models, thermal field mathematical models, stress field mathematical models, and vibration field mathematical models, and define boundary conditions and initial conditions;

[0103] Model verification unit: used to calibrate model parameters through physical test data;

[0104] Dynamic optimization unit: used to iteratively update the model through real-time sensor data to achieve virtual and real mutual control.

[0105] Electromagnetic field modeling steps

[0106] Model creation: Select a solver and coordinate system based on the analysis object, then use the software's graphics capabilities to create a model or import a CAD model. For a three-phase asynchronous motor, for example, you need to construct the stator core, windings, rotor core, windings, motion domain (Band), and solution domain (Region).

[0107] Adding Materials: Select a component in the project tree and access the material library through the Properties interface to assign corresponding materials to each component. If there are no suitable options in the material library, you need to add a new material according to the rules.

[0108] Pre-processing settings:

[0109] Motion body settings: Select the Band domain, AssignBand in Model and perform MotionSetup, set the Type, Data, and Mechanical tabs as required, and check ConsiderMechanicalTransient when considering the startup process.

[0110] Boundary condition setting: Select boundary conditions according to the characteristics of the model. For example, right-click the graph and select SelectEdges. After selecting the edge of the Region, select VetorPotential in Boundaries to set it.

[0111] Excitation Source Settings: Set the excitation source based on the solver type and excitation source type. Taking the winding as an example, select the winding in the project tree, right-click and select Coil to set up Coil Excitation. Add the winding and configure the power supply. Set the iron loss and eddy current loss solution options as needed.

[0112] Mesh division settings: Select the components to be divided in the project tree bar for mesh division.

[0113] Solution settings: Right-click Analysis in the project management bar and select AddSolution Setup, and make corresponding settings according to different solvers.

[0114] Post-processing: Check the electromagnetic field related parameters and field quantity results, focus on the force results and field distribution diagram, use electromagnetic theory knowledge to analyze the accuracy of simulation data, and accumulate experience to solve possible problems.

[0115] Temperature field modeling steps

[0116] 3D modeling: Determine the work name and analysis title, set the analysis module, and create the analysis geometry model. For example, when simulating the temperature field of the surrounding rock of a roadway, create a rectangular model of the roadway and surrounding rock and add monitoring points.

[0117] Element selection: Select appropriate element types and options based on your analysis requirements.

[0118] Determination of physical property parameters: define the thermal conductivity, specific heat capacity, density and other thermal physical parameters of the material.

[0119] Meshing: When meshing the model, you can initially use a structured mesh to ensure computational accuracy and speed, while also paying attention to the number and quality of meshes. To improve computational efficiency, you can simplify the model, such as scaling down the complete model.

[0120] Solver configuration: Select an appropriate solver and configure related parameters, such as time unit, output time step, etc.

[0121] Heat source model loading: Set the heat source according to the actual situation, such as setting the internal forced convection boundary to simulate the impact of wind flow on the surrounding rock, including parameters such as wind speed and wind temperature.

[0122] Result data output: Run the calculation, output the temperature field distribution, isotherms and other results, and analyze the changes of surrounding rock temperature with time and position under different parameter conditions.

[0123] Stress field modeling steps

[0124] Establish a geological geometric model: discretize the plane structure, characterize different structural areas, select key nodes and connect them to form the model outline.

[0125] Assign unit attributes: Select an appropriate unit type, such as the 8node 183 unit, which has many advantages such as hyperelasticity and plasticity.

[0126] Define model material properties: assign corresponding rock parameters to different regions, such as density, Young's modulus, and Poisson's ratio.

[0127] Cell meshing: Set different cell properties according to the study area, specify the cell shape for meshing, and re-mesh key areas to improve simulation accuracy.

[0128] Apply loads and constraints: Add reasonable constraint boundaries based on the actual geological background, combine the plate motion trajectory and velocity, convert displacement loads into stress loads, and apply appropriate stress magnitude and direction.

[0129] Analysis of simulation results: After setting the boundaries and stress magnitude and direction, perform solution calculations and select corresponding contents to generate graphs, such as displacement field, stress field, deformation field and other vector diagrams, to analyze the kinematic characteristics of the plate.

[0130] Vibration field modeling steps

[0131] Creation and simplification of geometric models: Determine the analysis objectives, create the geometric model, and simplify it according to actual conditions to improve computational efficiency.

[0132] Definition of material properties and boundary conditions: Define material properties for each component in the model, such as elastic modulus and density; set reasonable boundary conditions, such as fixed supports and elastic supports, to simulate actual constraints.

[0133] Meshing and quality control: Select an appropriate meshing strategy, mesh the model, and evaluate the mesh quality to ensure that the mesh can accurately describe the model's geometry and physical properties.

[0134] Analysis of stimulus and response:

[0135] Excitation input method: Set the excitation source according to actual conditions, such as simple harmonic force, impact load, etc., and determine the input position and method of the excitation.

[0136] Response extraction and analysis: Run simulations to extract the model’s vibration responses, such as displacement, velocity, acceleration, etc., and analyze vibration characteristics.

[0137] Simulation verification of control effect:

[0138] Steps of simulation test: conduct simulation test and record relevant data.

[0139] Post-processing and evaluation of results: Post-process the simulation results, such as drawing frequency response curves and vibration mode diagrams, evaluate the control effect, and adjust and optimize the model based on the evaluation results.

[0140] The multi-physics building unit selects a simulation software interface or module that supports multi-physics coupling. Currently, there are many mature simulation software on the market that support multi-physics coupling modeling, such as COMSOL Multiphysics, ANSYS, ABAQUS, etc. These software provide a rich set of physical field interfaces and coupling tools that can easily realize data transfer and interaction between different physical fields. Specifically including:

[0141] Coupling variable definition subunit: used to define coupling variables to achieve data transfer between different physical fields. Coupling variables include temperature, stress, displacement, electromagnetic force, and vibration acceleration.

[0142] Coupling variable definition clarifies key coupling variables such as temperature, stress, and displacement, enabling multi-physics data interaction and improving simulation accuracy. Define coupling relationships between electromagnetic and temperature fields, and between temperature and stress fields, to simulate physical interactions under actual working conditions. Optimize mesh density and solver algorithms to balance computational efficiency and accuracy, accelerating design iterations. The solution and results analysis subunit evaluates model accuracy, identifies potential design flaws, and guides parameter optimization.

[0143] Boundary Condition and Load Setting Subunit: used to set boundary conditions and loads. Boundary conditions and loads are set according to the interaction and influence between different physical fields:

[0144] (1) Coupling of electromagnetic field and temperature field: the heat generated by the electromagnetic field serves as the heat source of the temperature field;

[0145] (2) Coupling of temperature field and stress field: thermal expansion or contraction caused by temperature change acts as a load in the stress field;

[0146] (3) Coupling of stress field and vibration field: the structural deformation caused by stress serves as the initial condition or boundary condition of the vibration field;

[0147] (4) Coupling of vibration field and electromagnetic field: dynamic inductance changes caused by vibration;

[0148] In coupled models, boundary conditions and loads must be appropriately set. Boundary conditions are constraints on physical quantities or their derivatives at the model's boundaries, such as fixed constraints, symmetric boundaries, and periodic boundaries. Loads are external forces or excitations acting on the model, such as electromagnetic forces, heat flow, and pressure. In coupled models, boundary conditions and loads must be set to account for the interactions and influences between the different physical fields.

[0149] Meshing and Solver Configuration subunit: used to mesh the fully coupled model and configure the solver;

[0150] Mesh the coupled model and configure the solver. Meshing is the process of discretizing the geometric model into finite elements or a mesh. The quality and density of the mesh directly impact computational accuracy and efficiency. In coupled models, since interactions between different physical fields may be concentrated in certain areas, mesh refinement is required in these areas to improve computational accuracy. Solver configuration involves selecting the appropriate solver type and parameters to ensure the stability and convergence of the coupled model.

[0151] Solution and result analysis subunit: used to obtain the results of the comprehensive coupled model, analyze it, and evaluate the accuracy and reliability of the model.

[0152] Run simulations, obtain coupled model results, and analyze them. Coupled model results may include information on multiple physical fields, such as electromagnetic field distribution, temperature distribution, stress distribution, and vibration characteristics. By analyzing these results, you can understand the interactions and influences between different physical fields, evaluate the accuracy and reliability of the model, and provide a scientific basis for engineering design and optimization.

[0153] Preferably, the fault diagnosis module diagnoses motor faults based on deep learning.

[0154] Deep learning algorithms automatically learn fault characteristics, reducing manual intervention and improving diagnostic robustness. They adapt to different operating conditions and fault types, reducing reliance on expert experience and enabling cross-scenario applications.

[0155] Preferably, the fault diagnosis module adopts an improved one-dimensional convolutional neural network, the input layer is the four-domain perception signal of electromagnetic-thermal-force-vibration, the middle layer contains 3 layers of convolution and 2 layers of LSTM, and the output layer is a Softmax classifier.

[0156] The input layer integrates electromagnetic, thermal, force and vibration signals to perform four-domain signal fusion, providing a comprehensive diagnostic basis and avoiding information silos.

[0157] Three convolution layers extract local features, while a two-layer LSTM captures temporal dependencies and spatial and temporal features, improving fault classification accuracy. The Softmax classifier in the output layer determines the probability of fault type, providing quantitative support for maintenance decisions.

[0158] The maintenance strategy optimization module includes:

[0159] Fault tracing unit: used to trace the vibration propagation path in the digital image when a motor fault is detected;

[0160] Strategy optimization unit: used to simulate the impact of different maintenance plans on the production line through digital mirroring;

[0161] Output unit: used to select the optimal solution output;

[0162] Adaptive control unit: used to automatically reduce speed or stop the machine when a motor fault is detected.

[0163] Tracing vibration propagation paths in a digital image allows rapid location of fault sources, shortening troubleshooting time. The digital image simulates the impact of different maintenance options on the production line, selecting the lowest-cost, most efficient strategy. By combining fault types with production requirements, an actionable maintenance plan is generated to minimize downtime losses. Automatically reducing speed or shutting down the machine in the event of a fault prevents escalation and ensures the safety of personnel and equipment.

[0164] For example, bearing failure prediction and maintenance decision-making

[0165] Fault evolution process:

[0166] T = 0h: Pitting with a diameter of 0.1mm (depth of 0.02mm) appears on the bearing outer ring;

[0167] T = 100h: The energy of the vibration signal in the 850Hz frequency band increases by 12dB, and the 1D-CNN model predicts a failure probability of 85%;

[0168] T=150h: The fiber Bragg grating sensor detects that the core stress reaches 75 MPa (close to the warning threshold of 80 MPa).

[0169] Digital Twin Decision Making:

[0170] Two scenarios are simulated in the digital mirror:

[0171] Plan A: Replace the bearing immediately (downtime 2 hours, cost $500);

[0172] Plan B: Continue to operate until T = 200h (stoppage risk probability 30%, shutdown loss $20,000).

[0173] Optimal decision: Choose Option A, and the production line OEE loss is reduced from 2.5% to 0.3%.

[0174] Example 2

[0175] The industrial robot described in the present invention includes a robot body and the above-mentioned servo motor.

[0176] By integrating the above-mentioned servo motors, industrial robots can realize real-time monitoring and multi-physics field coupling analysis of the four domains of electromagnetic, thermal, force and vibration, accurately control joint motion parameters (such as torque, speed, and position), and significantly improve operation accuracy and dynamic response speed.

[0177] The above is only a preferred specific implementation method of this embodiment, but the protection scope of this embodiment is not limited to this. Any technician familiar with this technical field can make equivalent replacements or changes based on the technical solution and inventive concept of this embodiment within the technical scope disclosed in this embodiment, and they should be covered by the protection scope of this embodiment.

Claims

1. A servo motor, comprising a motor body, characterized in that: Also includes; Multimodal sensing module: used to form an electromagnetic-thermal-mechanical-vibration four-domain sensing network, integrating electromagnetic-thermal-mechanical-vibration four-domain monitoring of the motor body; Multi-physics construction module: used for 3D reconstruction of motors based on CT scans and construction of electromagnetic field, thermal field, and structural field multi-physics coupling models; Fault diagnosis module: used to identify fault types through multi-physics field building modules; Maintenance strategy optimization module: used to trace the vibration propagation path in the digital mirror when a fault is detected; simulate the impact of different maintenance plans on the servo motor operation through the digital mirror, and select the optimal plan for output.

2. A servo motor according to claim 1, characterized in that: The multimodal perception module includes: Electromagnetic field sensor: installed at the end of the stator winding, used to measure the air gap magnetic flux distribution in real time; Temperature sensor: installed on the stator winding to measure temperature data in real time; Stress sensor: installed on the stator core yoke to measure stress distribution in real time; Vibration sensor: installed at the end of the output shaft of the motor body, used to measure vibration characteristics in real time.

3. The servo motor according to claim 1, characterized in that: The multiphysics building blocks include: Electromagnetic field model building unit: used to build a three-dimensional electromagnetic field mathematical model of the motor based on CT scanning; Temperature model building unit: used to build a three-dimensional thermal field mathematical model of the motor based on CT scanning; Stress model building unit: used to build a three-dimensional mathematical model of the stress field of the motor based on CT scanning; Vibration model building unit: used to build a three-dimensional vibration field mathematical model of the motor based on CT scanning; Multi-physics field construction unit: used to couple electromagnetic field mathematical models, thermal field mathematical models, stress field mathematical models, and vibration field mathematical models, and define boundary conditions and initial conditions; Model verification unit: used to calibrate model parameters through physical test data; Dynamic optimization unit: used to iteratively update the model through real-time sensor data to achieve virtual and real mutual control.

4. A servo motor according to claim 3, characterized in that: The multi-physics field construction unit specifically includes: Coupling variable definition subunit: used to define coupling variables to achieve data transfer between different physical fields. Coupling variables include temperature, stress, displacement, electromagnetic force, and vibration acceleration. Boundary Condition and Load Setting Subunit: used to set boundary conditions and loads. Boundary conditions and loads are set according to the interaction and influence between different physical fields: (1) Coupling of electromagnetic field and temperature field: the heat generated by the electromagnetic field serves as the heat source of the temperature field; (2) Coupling of temperature field and stress field: thermal expansion or contraction caused by temperature change acts as a load in the stress field; (3) Coupling of stress field and vibration field: the structural deformation caused by stress serves as the initial condition or boundary condition of the vibration field; (4) Coupling of vibration field and electromagnetic field: dynamic inductance changes caused by vibration; Meshing and Solver Configuration subunit: used to mesh the fully coupled model and configure the solver; Solution and result analysis subunit: used to obtain the results of the comprehensive coupled model, analyze it, and evaluate the accuracy and reliability of the model.

5. The servo motor according to claim 3, characterized in that: The electromagnetic field model establishment unit specifically includes: Electromagnetic field geometry modeling subunit: used to build a 3D model of the motor based on CT scanning, set up analysis modules, and create an analytical geometry model; Electromagnetic field meshing subunit: used to discretize the geometric three-dimensional model into finite elements or meshes; Electromagnetic field solution setting subunit: used to select the solver type, set the excitation source and boundary conditions; Electromagnetic field solution and post-processing subunit: used to solve the electromagnetic field distribution and visualize the results; Electromagnetic Field Verification and Optimization Subunit: used to verify model accuracy by comparing experimental data or analytical solutions, and to optimize parameters to optimize performance.

6. The servo motor according to claim 1, characterized in that: The fault diagnosis module diagnoses motor faults based on deep learning.

7. The servo motor according to claim 1, characterized in that: The fault diagnosis module adopts an improved one-dimensional convolutional neural network. The input layer is the four-domain perception signal of electromagnetic, thermal, force and vibration. The middle layer contains 3 layers of convolution and 2 layers of LSTM. The output layer is a Softmax classifier.

8. The servo motor according to claim 1, characterized in that: The maintenance strategy optimization module includes: Fault tracing unit: used to trace the vibration propagation path in the digital image when a motor fault is detected; Strategy optimization unit: used to simulate the impact of different maintenance plans on the production line through digital mirroring; Output unit: used to select the optimal solution output; Adaptive control unit: used to automatically reduce speed or stop the machine when a motor fault is detected.

9. An industrial robot, comprising a robot body, characterized in that: It also includes a servo motor as described in any one of claims 1-8.

Images