Robot health status assessment method and system based on artificial intelligence

Abstract

The present invention discloses a robot health status assessment method and system based on artificial intelligence. The method includes data acquisition and fusion, digital twin health modeling, multi-scale predictive maintenance, fault-tolerant control, and health status assessment. The present invention relates to the field of digital robot health analysis technology. The method constructs an optimized feature set by fusing multi-source sensor data, implements digital twin health modeling using a dynamic dual-data stream neural differential equation that combines physical constraints and wear evolution, and outputs robot health parameters. Quantum annealing optimization and graph attention mechanism are introduced to construct a multi-level predictive maintenance architecture, realize fault propagation prediction and maintenance optimization from the part level to the system level, and realize fault-tolerant control by combining model predictive control. The accuracy, interpretability, and practicality of robot health assessment are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of digital robot health analysis, and specifically to a robot health status assessment method and system based on artificial intelligence. Background Art

[0002] The robot health status assessment method and system based on artificial intelligence refers to an intelligent technology system that uses machine learning, computer vision, and sensor data analysis technologies to conduct real-time monitoring, fault diagnosis, and performance prediction of key components such as the robot's mechanical structure, electronic components, and software operation. By collecting multiple information such as the robot's motion parameters, energy consumption data, and operation logs, and combining deep learning and anomaly detection algorithms to establish a health status model, it can achieve automated fault identification and remaining life prediction. Its core role is to improve operation and maintenance efficiency, reduce the risk of sudden failures, and extend the robot's service life through predictive maintenance strategies, thereby ensuring the stable operation of equipment in scenarios such as industrial automation and service robots.

[0003] However, existing robot health status assessment methods have the limitations of narrow dimensions for collecting robot health data and lack of multimodal fusion. They usually rely on only a single type of sensor (such as temperature, current or vibration), which makes it difficult to fully reflect the true health status of the robot during operation. Existing intelligent methods cannot be linked with maintenance strategy generation or control logic, making them difficult to use in actual engineering projects. In the existing robot health digital modeling process, traditional methods often use purely data-driven machine learning models, which lack consideration of the robot's body dynamics and energy conservation laws. Although the modeling results can fit the sample data, they lack physical interpretability and are difficult to promote for use in complex tasks or unknown working conditions. In the existing multi-scale predictive maintenance process of robots, existing methods often have technical problems such as the fragmentation of life cycle dimensions, and the independence and difficulty in coordinating prediction algorithms at different levels. Summary of the Invention

[0004] In view of the above situation, in order to overcome the defects of the prior art, the present invention provides a robot health status assessment method and system based on artificial intelligence. In view of the limitations of the existing robot health status assessment methods, the robot's health data collection dimension is narrow and there is a lack of multimodal fusion. Usually, only a single type of sensor (such as temperature, current or vibration) is relied upon, which makes it difficult to fully reflect the true health status of the robot during operation. The existing intelligent methods cannot be linked with maintenance strategy generation or control logic, and are difficult to be used in actual engineering projects. This solution creatively adopts an overall intelligent health assessment and processing method that combines digital twin health modeling, multi-scale hierarchical predictive maintenance and fault-tolerant control optimization, realizing full-cycle, hierarchical, high-precision intelligent diagnosis and dynamic regulation of the robot's operating status, significantly improving the assessment accuracy. In view of the fact that in the existing robot health digital modeling process, traditional methods mostly adopt pure data-driven machine The machine learning model lacks consideration of the robot's body dynamics and energy conservation laws. Although the modeling results can fit the sample data, they lack physical interpretability and are difficult to promote and use in complex tasks or unknown working conditions. This solution creatively adopts the dynamic dual-data stream neural ordinary differential equation modeling method to perform digital twin health modeling, and realizes the joint energy evolution modeling and wear trend prediction under the constraint of physical consistency, effectively improving the modeling accuracy and the degree of fit to the actual scenario; in the existing multi-scale predictive maintenance process of robots, there are technical problems that the existing methods often have the life cycle dimension split, and the prediction algorithms at different levels are independent of each other and difficult to coordinate. This solution creatively adopts a multi-time scale prediction architecture that combines quantum annealing optimization and graph attention network to perform multi-scale predictive maintenance, realizing cross-scale collaborative prediction and dynamic maintenance plan generation from part level, system level to machine level, and improving the timeliness of maintenance and resource scheduling optimization capabilities.

[0005] The technical solution adopted by the present invention is as follows: The present invention provides a robot health status assessment method based on artificial intelligence, which includes the following steps:

[0006] Step S1: data collection and fusion;

[0007] Step S2: Digital twin health modeling;

[0008] Step S3: multi-scale predictive maintenance;

[0009] Step S4: fault tolerance control;

[0010] Step S5: Health status assessment.

[0011] Furthermore, in step S1, the data acquisition and fusion is used to collect raw data, extract spatiotemporal features, and perform feature fusion. Specifically, the raw data set for robot health status assessment is obtained through sensor data collection and dynamic sampling coordination, and the optimized data for robot health status assessment is obtained through data preprocessing and process feature fusion.

[0012] The robot health status assessment raw data set includes vibration data, robot joint position and speed data, joint force data, joint torque data, voltage and current data, temperature data, control instruction data and maintenance log data;

[0013] The robot health status assessment optimization data specifically includes vibration signal time domain feature data, frequency domain feature data, state variable feature data, robot health derived feature data, load feature data, maintenance history feature data and robot health label data.

[0014] Furthermore, in step S2, the digital twin health modeling is used to construct a virtual digital twin model of the robot health status. Specifically, based on the robot health status evaluation optimization data, a dynamic dual data stream neural ordinary differential equation modeling method is used to perform digital twin health modeling to obtain the robot health parameters, including the following steps:

[0015] Step S21: physical constraint embedding modeling, specifically, based on the robot health status assessment optimization data, using a Hamiltonian neural network combined with the physical constraints of the dynamic system to perform dynamic consistency physical constraint modeling to obtain robot joint health assessment data;

[0016] The Hamiltonian neural network combined with the physical constraints of the dynamic system includes a generalized momentum definition, a Hamiltonian dynamic system definition, and a physical modeling loss function definition. The generalized momentum definition is used to map the actually observed robot joint angular velocity into the generalized momentum and use it as a prediction indicator.

[0017] The Hamiltonian dynamics system definition is used to construct a physical evolution model of the robot joint state;

[0018] Step S22: Wear evolution modeling, specifically, based on the robot health status assessment optimization data, by constructing a wear evolution neural ordinary differential equation model, and constructing a standard multi-layer perceptron structure to perform dynamic evolution of wear status and future wear prediction modeling, and calculate the robot joint wear rate and predicted wear value data;

[0019] Step S23: adversarial verification, specifically performing standard generative adversarial network training based on the predicted wear value data and the actual wear value data to verify the authenticity of the digital twin health modeling and obtain health modeling authenticity assessment data;

[0020] Step S24: digital twin health modeling, specifically performing digital twin health comprehensive modeling through the physical constraint embedding modeling, the wear evolution modeling, and the adversarial verification to obtain robot health parameters;

[0021] The robot health parameters include robot joint simulation consistency index, robot joint wear degree estimation, robot health prediction residual, health modeling authenticity assessment data and robot comprehensive health score.

[0022] Furthermore, in step S3, the multi-scale predictive maintenance is used to achieve cross-scale prediction from micro-wear to system-level failures. Specifically, based on the robot health parameters and the robot health status assessment optimization data, a multi-time-scale prediction architecture combining quantum annealing optimization and graph attention network is adopted to perform multi-scale predictive maintenance to obtain hierarchical predictive maintenance reference data, including the following steps:

[0023] Step S31: Part-level life prediction: Based on the robot health status evaluation optimization data, the robot health parameters of the robot that meet the requirements for preventive maintenance are input as raw data, and a long short-term memory neural network combined with quantum annealing optimization is used to perform part-level life prediction to obtain remaining life estimation data;

[0024] The quantum annealing optimized long short-term memory neural network specifically constructs an improved quantum annealing optimization algorithm and combines it with a standard long short-term memory neural network to perform part-level life prediction, and calculates the remaining life estimation data by modeling the output layer as a Bayesian linear regression;

[0025] The improved quantum annealing optimization algorithm specifically improves the standard quantum annealing optimization algorithm by introducing a third-order parameter interaction relationship modeling term and a test accuracy term;

[0026] Step S32: constructing a system-level fault propagation graph, specifically, based on the robot health parameters and the robot health status assessment optimization data, constructing a robot system topology graph and using a standard graph attention network method to perform fault propagation modeling, and obtaining fault propagation prediction data, including fault propagation probability matrix data and propagation path prediction data, by fault diffusion probability modeling;

[0027] Step S33: Optimizing the machine-level maintenance plan, specifically, optimizing the robot's maintenance plan based on the robot health parameters and the robot health status assessment optimization data, using a deep reinforcement learning method that combines an improved multi-objective reward function and quantum annealing strategy distillation to obtain optimized maintenance strategy prediction data;

[0028] The deep reinforcement learning method combining improved multi-objective reward function and quantum annealing strategy distillation includes constructing multi-objective reward function and quantum annealing strategy distillation improvement;

[0029] The quantum annealing strategy distillation improvement is specifically to optimize the weights of each reward item in the multi-objective reward function according to the improved quantum annealing optimization algorithm, and specifically to verify the accuracy function item in the multi-objective reward function formula by replacing the reward value with the test set;

[0030] The deep reinforcement learning method constructs robot maintenance state space parameters and robot maintenance action space parameters, and performs standard reinforcement learning training based on the multi-objective reward function;

[0031] Step S34: multi-scale integration, specifically integrating the remaining life estimation data, the fault propagation prediction data, and the optimized maintenance strategy prediction data, performing multi-scale predictive maintenance of robot health at the part level, system level, and machine level, and building a dynamic update mechanism to perform prediction optimization to obtain multi-scale integrated prediction data;

[0032] Step S35: hierarchical predictive maintenance, specifically performing hierarchical predictive maintenance based on the multi-scale integrated prediction data to obtain hierarchical predictive maintenance reference data;

[0033] The hierarchical predictive maintenance reference data includes part-level maintenance parameters, system-level maintenance parameters, and machine-level maintenance decisions;

[0034] The part-level maintenance parameters include part number, remaining useful life of the part, prediction uncertainty estimate, health status parameters, and temperature anomaly values;

[0035] The system-level maintenance parameters include fault propagation path number, fault propagation probability, fault path criticality assessment value and risk path chain position;

[0036] The machine-level maintenance decision includes the machine number, optional maintenance action set, optimal recommended maintenance action, maintenance action cost, maintenance downtime prediction time, maintenance improvement effect prediction value and maintenance strategy weight;

[0037] The part-level maintenance parameters are used to assist maintenance technicians in repairing or replacing parts; the system-level maintenance parameters are used to assist engineers in controlling fault propagation paths; and the machine-level maintenance decisions are used to assist robot managers in balancing maintenance planning strategies.

[0038] Furthermore, in step S4, the fault-tolerant control is used to maintain the basic functions of the robot when a fault occurs. Specifically, based on the hierarchical predictive maintenance reference data and the robot health status assessment optimization data, the health status of the robot's key components is dynamically mapped into control constraints, a model predictive controller with health limits is constructed, and fault-tolerant control is performed to obtain fault occurrence control instruction data;

[0039] The fault occurrence control instruction data includes control amount adjustment data and safety action limitation data.

[0040] Furthermore, in step S5, the health status assessment is used to generate a comprehensive health status assessment result, specifically by combining the robot health parameters, the hierarchical predictive maintenance reference data and the fault occurrence control instruction data to perform a comprehensive assessment of the robot health status and obtain the robot health status comprehensive assessment reference data.

[0041] The artificial intelligence-based robot health status assessment system provided by the present invention includes a data acquisition and fusion module, a digital twin health modeling module, a multi-scale predictive maintenance module, a fault-tolerant control module, and a health status assessment module;

[0042] The data acquisition and fusion module is used for data acquisition and fusion, and obtains robot health status evaluation and optimization data through data acquisition and fusion, and sends the robot health status evaluation and optimization data to the digital twin health modeling module, the multi-scale predictive maintenance module and the fault tolerance control module;

[0043] The digital twin health modeling module is used for digital twin health modeling, obtains robot health parameters through digital twin health modeling, and sends the robot health parameters to the multi-scale predictive maintenance module and the health status assessment module;

[0044] The multi-scale predictive maintenance module is used for multi-scale predictive maintenance, obtains hierarchical predictive maintenance reference data through multi-scale predictive maintenance, and sends the hierarchical predictive maintenance reference data to the fault tolerance control module and the health status assessment module;

[0045] The fault tolerance control module is used for fault tolerance control, obtains fault occurrence control instruction data through fault tolerance control, and sends the fault occurrence control instruction data to the health status assessment module;

[0046] The health status assessment module is used for health status assessment, and obtains comprehensive assessment reference data of the robot's health status through health status assessment.

[0047] The beneficial effects achieved by the present invention using the above scheme are as follows:

[0048] (1) In view of the limitations of the existing robot health status assessment methods, such as the narrow dimension of robot health data collection and the lack of multimodal fusion, which usually rely on only a single type of sensor (such as temperature, current or vibration), it is difficult to fully reflect the real health status of the robot during operation. The existing intelligent methods cannot be linked with maintenance strategy generation or control logic, making them difficult to use in actual engineering. This solution creatively adopts an overall intelligent health assessment and processing method that combines digital twin health modeling, multi-scale hierarchical predictive maintenance and fault-tolerant control optimization, realizing full-cycle, hierarchical, high-precision intelligent diagnosis and dynamic regulation of the robot's operating status, significantly improving the assessment accuracy.

[0049] (2) In the existing digital modeling process of robot health, there is a technical problem that traditional methods mostly use pure data-driven machine learning models, which lack consideration of the robot's body dynamics and energy conservation laws. Although the modeling results can fit the sample data, they lack physical interpretability and are difficult to promote and use in complex tasks or unknown working conditions. This solution creatively adopts a dynamic dual-data stream neural ordinary differential equation modeling method to perform digital twin health modeling, realizing joint energy evolution modeling and wear trend prediction under physical consistency constraints, effectively improving modeling accuracy and actual scenario fitting.

[0050] (3) In view of the technical problems in the existing multi-scale predictive maintenance process of robots, existing methods often have the problem of life cycle dimension fragmentation, and prediction algorithms at different levels are independent of each other and difficult to coordinate. This solution creatively adopts a multi-time scale prediction architecture that combines quantum annealing optimization and graph attention network to perform multi-scale predictive maintenance, realizing cross-scale collaborative prediction and dynamic maintenance plan generation from part level, system level to machine level, and improving maintenance timeliness and resource scheduling optimization capabilities. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 A schematic diagram of the process of the robot health status assessment method based on artificial intelligence provided by the present invention;

[0052] Figure 2 A schematic diagram of the artificial intelligence-based robot health status assessment system provided by the present invention;

[0053] Figure 3 Schematic diagram of the process of digital twin health modeling in step S2;

[0054] Figure 4 Schematic diagram of the process of multi-scale predictive maintenance in step S3.

[0055] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention. DETAILED DESCRIPTION

[0056] 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; based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0057] In the description of the present invention, it should be understood that terms such as "upper", "lower", "front", "back", "left", "right", "top", "bottom", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the accompanying drawings. They are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific direction, be constructed and operated in a specific direction. Therefore, they should not be understood as limiting the present invention.

[0058] Example 1, see Figure 1 The present invention provides a robot health status assessment method based on artificial intelligence, which includes the following steps:

[0059] Step S1: data collection and fusion;

[0060] Step S2: Digital twin health modeling;

[0061] Step S3: multi-scale predictive maintenance;

[0062] Step S4: fault tolerance control;

[0063] Step S5: Health status assessment.

[0064] By performing the above operations, we can address the technical problems in existing robot health status assessment methods, such as the narrow dimensions of robot health data collection and the lack of multimodal fusion. These methods usually rely on a single type of sensor (such as temperature, current or vibration), which makes it difficult to fully reflect the true health status of the robot during operation. Existing intelligent methods cannot be linked with maintenance strategy generation or control logic, making them difficult to use in actual engineering projects. This solution creatively adopts an overall intelligent health assessment and processing method that combines digital twin health modeling, multi-scale hierarchical predictive maintenance, and fault-tolerant control optimization, realizing full-cycle, hierarchical, high-precision intelligent diagnosis and dynamic regulation of the robot's operating status, significantly improving the assessment accuracy.

[0065] Example 2, see Figure 1 and Figure 2 In step S1, the data acquisition and fusion is used to collect raw data, extract spatiotemporal features and perform feature fusion. Specifically, the raw data set for robot health status assessment is obtained through sensor data collection and dynamic sampling coordination, and the robot health status assessment optimization data is obtained through data preprocessing and process feature fusion;

[0066] The robot health status assessment raw data set includes vibration data, robot joint position and speed data, joint force data, joint torque data, voltage and current data, temperature data, control instruction data and maintenance log data;

[0067] The robot health status assessment optimization data specifically includes vibration signal time domain feature data, frequency domain feature data, state variable feature data, robot health derived feature data, load feature data, maintenance history feature data and robot health label data;

[0068] The robot health-derived characteristic data specifically includes wear rate characteristics, cumulative wear characteristics, and temperature change characteristics;

[0069] The load characteristic data specifically includes load ratio characteristics and drive current peak characteristics;

[0070] The maintenance history feature data includes the time interval feature since the last maintenance, the robot's cumulative operating time feature, and the parts replacement frequency feature;

[0071] The robot health label data specifically refers to part-level fault type labels, system-level fault propagation labels, and machine-level maintenance action labels.

[0072] Example 3, see Figure 1 、 Figure 2 and Figure 3 This embodiment is based on the above embodiment. In step S2, the digital twin health modeling is used to construct a virtual digital twin model of the robot's health status. Specifically, based on the robot health status evaluation optimization data, a dynamic dual-data stream neural ordinary differential equation modeling method is used to perform digital twin health modeling to obtain the robot health parameters, including the following steps:

[0073] Step S21: physical constraint embedding modeling, specifically, based on the robot health status assessment optimization data, using a Hamiltonian neural network combined with the physical constraints of the dynamic system to perform dynamic consistency physical constraint modeling to obtain robot joint health assessment data;

[0074] The Hamiltonian neural network combined with the physical constraints of the dynamic system includes the definition of generalized momentum, the definition of the Hamiltonian dynamic system, and the definition of the physical modeling loss function. The generalized momentum definition is used to map the actually observed robot joint angular velocity into generalized momentum and use it as a prediction indicator. The calculation formula is:

[0075] p=M(q)·q0;

[0076] Where p is the generalized momentum value, M(·) is the mass matrix calculation function, q is the joint angle value, and q0 is the joint angular velocity value;

[0077] The Hamiltonian dynamics system definition is used to construct the physical evolution model of the robot joint state, and the calculation formula is:

[0078] ;

[0079] Where, The whole is the differential value of the joint angle, is the Hamiltonian function fitted by the neural network, is the momentum gradient operator, q is the joint angle value, p is the generalized momentum value, The whole is the momentum differential, is the joint angle gradient operator, is the external disturbance torque parameter;

[0080] The calculation formula of the physical modeling loss function is defined as:

[0081] ;

[0082] Where, is the physical modeling loss function, The overall angular velocity output loss is, among which, is the gradient of the neural network estimate of the Hamiltonian function with respect to momentum p, which is used to represent the theoretical system speed of physical modeling. is the actual robot joint angular velocity collected by the sensor, The overall constraint momentum evolution loss, is the physical consistency weight, where is the gradient of the neural network estimate of the Hamiltonian function to the joint angle q, which is used to represent the potential energy gradient of physical modeling, M -1 (·) is the inverse function of the mass matrix calculation function;

[0083] Preferably, the physical consistency weight The specific value of is 0.5;

[0084] Step S22: Wear evolution modeling, specifically, based on the robot health status assessment optimization data, by constructing a wear evolution neural ordinary differential equation model, and constructing a standard multi-layer perceptron structure to perform dynamic evolution of wear status and future wear prediction modeling, and calculate the robot joint wear rate and predicted wear value data;

[0085] The calculation formula for the wear evolution God ordinary differential equation modeling is:

[0086] ;

[0087] Where, The overall output is the robot joint wear evolution rate modeling at the current moment, which is used to represent the growth rate of joint wear. is the wear evolution differential equation representation function established by the standard multilayer perceptron, w is the wear amount of the robot joint, which is used to represent the cumulative loss of the robot bearings and joints, and x is the original signal of the vibration sensor. is the multilayer perceptron function, concat(·) is the vector concatenation function, and FFT(x) is the frequency domain feature extraction function;

[0088] The loss function calculation formula for the standard multilayer perceptron structure to perform dynamic evolution of wear state and future wear prediction modeling is:

[0089] ;

[0090] Where, is the wear evolution modeling loss function, w pred (·) Joint wear prediction function, used to represent the robot joint wear value predicted based on the wear evolution neural ordinary differential equation modeling, w real is the wear amount actually measured, is the regularization coefficient, is the gradient of the neural network parameters, ||·|| Fro is the Frobenius norm operator;

[0091] Step S23: adversarial verification, specifically performing standard generative adversarial network training based on the predicted wear value data and the actual wear value data to verify the authenticity of the digital twin health modeling and obtain health modeling authenticity assessment data;

[0092] Step S24: digital twin health modeling, specifically performing digital twin health comprehensive modeling through the physical constraint embedding modeling, the wear evolution modeling, and the adversarial verification to obtain robot health parameters;

[0093] The robot health parameters include robot joint simulation consistency index, robot joint wear degree estimation, robot health prediction residual, health modeling authenticity assessment data and robot comprehensive health score;

[0094] The calculation formula of the robot comprehensive health score is:

[0095] ;

[0096] Where, is the robot's comprehensive health score, is the Sigmoid function, is the joint energy weight, It is a robot joint simulation consistency indicator, specifically used to indicate the angular velocity output loss value. is the cumulative wear weight, w(t) is the estimated wear degree of the robot joint, is the health prediction residual weight, is the residual error of the robot health prediction, specifically the residual error between the predicted value and the actual value. is the health modeling authenticity assessment weight, is health modeling authenticity assessment data, specifically indicating the difference between the robot health state generated by the adversarial verification and the real robot health state;

[0097] Preferably, Table 1 is a table showing the meaning of the values ​​of the robot comprehensive health score. When When , it indicates that the robot is in poor health and needs preventive maintenance.

[0098] Table 1 Meaning of robot comprehensive health score values

[0099]

[0100] By performing the above operations, we can address the technical problems in the existing digital modeling process of robot health, such as the fact that traditional methods mostly use purely data-driven machine learning models, lack consideration of the robot's body dynamics and energy conservation laws, and although the modeling results can fit the sample data, they lack physical interpretability and are difficult to promote and use in complex tasks or unknown working conditions. This solution creatively adopts a dynamic dual-data stream neural ordinary differential equation modeling method to perform digital twin health modeling, realizing joint energy evolution modeling and wear trend prediction under physical consistency constraints, effectively improving modeling accuracy and actual scenario fitting.

[0101] Example 4, see Figure 1 、 Figure 2and Figure 4 This embodiment is based on the above embodiment. In step S3, the multi-scale predictive maintenance is used to achieve cross-scale prediction from micro-wear to system-level failure. Specifically, based on the robot health parameters and the robot health status assessment optimization data, a multi-time-scale prediction architecture combining quantum annealing optimization and graph attention network is adopted to perform multi-scale predictive maintenance and obtain hierarchical predictive maintenance reference data, including the following steps:

[0102] Step S31: Part-level life prediction: Based on the robot health status evaluation optimization data, the robot health parameters of the robot that meet the requirements for preventive maintenance are input as raw data, and a long short-term memory neural network combined with quantum annealing optimization is used to perform part-level life prediction to obtain remaining life estimation data;

[0103] The quantum annealing optimized long short-term memory neural network specifically constructs an improved quantum annealing optimization algorithm and combines it with a standard long short-term memory neural network to perform part-level life prediction, and calculates the remaining life estimation data by modeling the output layer as a Bayesian linear regression;

[0104] The improved quantum annealing optimization algorithm specifically improves the standard quantum annealing optimization algorithm by introducing a third-order parameter interaction relationship modeling term and a test accuracy term. The calculation formula is:

[0105] ;

[0106] Where H(·) is the output of the improved quantum annealing optimization algorithm, z is the set of hyperparameters of the standard long short-term memory neural network, The whole is a bivariate coupling relationship modeling term between hyperparameters, which is used to represent the interaction strength between model parameters, where i is the first hyperparameter index, j is the second hyperparameter index, and J ij is the hyperparameter interaction strength identifier, z i is the model hyperparameter corresponding to the first hyperparameter i, z j is the model hyperparameter corresponding to the second hyperparameter j, The overall hyperparameters individually influence the modeling term, h i is the preference parameter of the model hyperparameter corresponding to the first hyperparameter i, The whole is a third-order interaction relationship modeling item, is the third-order control weight, k is the third hyperparameter index, is the parameter that affects the model performance when all three hyperparameters are activated together, z k is the model hyperparameter corresponding to the third hyperparameter k, is the feedback coefficient, Acc(·) is the test set verification accuracy function;

[0107] The calculation formula for modeling the output layer as Bayesian linear regression is:

[0108] ;

[0109] Where, is the estimated remaining lifespan, is the probability density function of the normal distribution, is the predicted mean mapping function, h T is the output hidden state of a standard LSTM neural network, is the prediction variance mapping function;

[0110] Step S32: constructing a system-level fault propagation graph, specifically, based on the robot health parameters and the robot health status assessment optimization data, constructing a robot system topology graph and using a standard graph attention network method to perform fault propagation modeling, and obtaining fault propagation prediction data, including fault propagation probability matrix data and propagation path prediction data, by fault diffusion probability modeling;

[0111] The calculation formula for the fault diffusion probability modeling is:

[0112] ;

[0113] Where P(·) is the fault propagation probability prediction function, is a node and nodes The edge parameters, is the node index of the robot system topology graph, is the neighbor node index of the robot system topology graph, u is the learnable weight value, is the corresponding node of the L-th layer graph attention network The output vector of element-wise multiplication operator, is the corresponding node of the L-th layer graph attention network The output vector of , L is the total number of layers of the graph attention network, and the specific value is 3;

[0114] Step S33: Optimizing the machine-level maintenance plan, specifically, optimizing the robot's maintenance plan based on the robot health parameters and the robot health status assessment optimization data, using a deep reinforcement learning method that combines an improved multi-objective reward function and quantum annealing strategy distillation to obtain optimized maintenance strategy prediction data;

[0115] The deep reinforcement learning method combining improved multi-objective reward function and quantum annealing strategy distillation includes constructing multi-objective reward function and quantum annealing strategy distillation improvement;

[0116] The calculation formula of the multi-objective reward function is:

[0117] ;

[0118] Where r(s,a) is a multi-objective reward function, where s is the robot maintenance state space parameter, a is the robot maintenance action space parameter, cost(a) is the maintenance cost reward, downtime(a) is the expected downtime reward, reliability_gain(a) is the performance improvement reward, safety_improvement(a) is the safety improvement reward, remaining_life_boost(a) is the key component life positive improvement reward, and resource_usage(a) is the resource consumption reward.

[0119] The quantum annealing strategy distillation improvement is specifically to optimize the weights of each reward item in the multi-objective reward function according to the improved quantum annealing optimization algorithm, and specifically to verify the accuracy function item in the multi-objective reward function formula by replacing the reward value with the test set;

[0120] The deep reinforcement learning method constructs robot maintenance state space parameters and robot maintenance action space parameters, and performs standard reinforcement learning training based on the multi-objective reward function;

[0121] The robot maintenance state space parameters include remaining life estimation, vibration index, temperature monitoring value, fault sequence, time interval since last maintenance and load ratio;

[0122] The robot maintenance motion space parameters specifically include routine inspection motion, parts replacement motion, fault calibration motion, emergency shutdown maintenance motion and load scheduling motion;

[0123] Step S34: multi-scale integration, specifically integrating the remaining life estimation data, the fault propagation prediction data, and the optimized maintenance strategy prediction data, performing multi-scale predictive maintenance of robot health at the part level, system level, and machine level, and building a dynamic update mechanism to perform prediction optimization to obtain multi-scale integrated prediction data;

[0124] Step S35: hierarchical predictive maintenance, specifically performing hierarchical predictive maintenance based on the multi-scale integrated prediction data to obtain hierarchical predictive maintenance reference data;

[0125] The hierarchical predictive maintenance reference data includes part-level maintenance parameters, system-level maintenance parameters, and machine-level maintenance decisions;

[0126] The part-level maintenance parameters include part number, remaining useful life of the part, prediction uncertainty estimate, health status parameters, and temperature anomaly values;

[0127] The system-level maintenance parameters include fault propagation path number, fault propagation probability, fault path criticality assessment value and risk path chain position;

[0128] The machine-level maintenance decision includes the machine number, optional maintenance action set, optimal recommended maintenance action, maintenance action cost, maintenance downtime prediction time, maintenance improvement effect prediction value and maintenance strategy weight;

[0129] The part-level maintenance parameters are used to assist maintenance technicians in repairing or replacing parts; the system-level maintenance parameters are used to assist engineers in controlling fault propagation paths; and the machine-level maintenance decisions are used to assist robot managers in balancing maintenance planning strategies.

[0130] By performing the above operations, this solution creatively adopts a multi-time-scale prediction architecture that combines quantum annealing optimization and graph attention network to perform multi-scale predictive maintenance, addressing the technical problems in existing multi-scale predictive maintenance of robots, such as the fragmentation of lifecycle dimensions and the independence and difficulty in coordination of prediction algorithms at different levels. This architecture realizes cross-scale collaborative prediction and dynamic maintenance plan generation from the part level, system level to the machine level, thereby improving maintenance timeliness and resource scheduling optimization capabilities.

[0131] Example 5, see Figure 1 and Figure 2 This embodiment is based on the above embodiment. In step S4, the fault-tolerant control is used to maintain the basic functions of the robot when a fault occurs. Specifically, based on the hierarchical predictive maintenance reference data and the robot health status assessment optimization data, the health status of the robot's key components is dynamically mapped into control constraints, a model predictive controller with health limits is constructed, and fault-tolerant control is performed to obtain fault occurrence control instruction data;

[0132] The fault occurrence control instruction data includes control amount adjustment data and safety action limitation data.

[0133] Example 6, see Figure 1 and Figure 2 This embodiment is based on the above embodiment. In step S5, the health status assessment is used to generate a comprehensive health status assessment result. Specifically, the robot health status comprehensive assessment is performed by combining the robot health parameters, the hierarchical predictive maintenance reference data and the fault occurrence control instruction data to obtain the robot health status comprehensive assessment reference data.

[0134] Example 7, see Figure 1 and Figure 2 , this embodiment is based on the above embodiment. The artificial intelligence-based robot health status assessment system provided by the present invention includes a data acquisition and fusion module, a digital twin health modeling module, a multi-scale predictive maintenance module, a fault-tolerant control module and a health status assessment module;

[0135] The data acquisition and fusion module is used for data acquisition and fusion, and obtains robot health status evaluation and optimization data through data acquisition and fusion, and sends the robot health status evaluation and optimization data to the digital twin health modeling module, the multi-scale predictive maintenance module and the fault tolerance control module;

[0136] The digital twin health modeling module is used for digital twin health modeling, obtains robot health parameters through digital twin health modeling, and sends the robot health parameters to the multi-scale predictive maintenance module and the health status assessment module;

[0137] The multi-scale predictive maintenance module is used for multi-scale predictive maintenance, obtains hierarchical predictive maintenance reference data through multi-scale predictive maintenance, and sends the hierarchical predictive maintenance reference data to the fault tolerance control module and the health status assessment module;

[0138] The fault tolerance control module is used for fault tolerance control, obtains fault occurrence control instruction data through fault tolerance control, and sends the fault occurrence control instruction data to the health status assessment module;

[0139] The health status assessment module is used for health status assessment, and obtains comprehensive assessment reference data of the robot's health status through health status assessment.

[0140] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0141] While the embodiments of the present invention have been shown and described, it will be apparent to those skilled in the art that various changes, modifications, substitutions, and alterations can be made to the embodiments without departing from the principles and spirit of the invention.

[0142] The present invention and its embodiments are described above. This description is not restrictive. The drawings show only one embodiment of the present invention, and the actual structure is not limited thereto. In short, if a person skilled in the art is inspired by this and, without departing from the purpose of the present invention, designs structures and embodiments similar to this technical solution without inventiveness, they shall fall within the scope of protection of the present invention.

Claims

1. A robot health status assessment method based on artificial intelligence, characterized by: The method comprises the following steps: Step S1: data acquisition and fusion, which is used to collect raw data, extract spatiotemporal features and perform feature fusion, specifically obtaining a raw data set for robot health status assessment through sensor data collection and dynamic sampling coordination, and obtaining optimized data for robot health status assessment through data preprocessing and process feature fusion; The robot health status assessment optimization data specifically includes vibration signal time domain feature data, frequency domain feature data, state variable feature data, robot health derived feature data, load feature data, maintenance history feature data and robot health label data; Step S2: Digital twin health modeling, using a dynamic dual-data stream neural ordinary differential equation modeling method to perform digital twin health modeling and obtain robot health parameters, including the following steps: Step S21: Physical constraint embedding modeling, using a Hamiltonian neural network combined with the physical constraints of the dynamic system to perform dynamic consistency physical constraint modeling; Step S22: Wear evolution modeling; Step S23: Adversarial verification; Step S24: Digital twin health modeling; Step S3: Multi-scale predictive maintenance, using a multi-time-scale prediction architecture that combines quantum annealing optimization and graph attention networks to perform multi-scale predictive maintenance and obtain hierarchical predictive maintenance reference data, including the following steps: Step S31: Part-level life prediction, using a long short-term memory neural network that combines quantum annealing optimization to perform part-level life prediction; Step S32: System-level fault propagation graph construction; Step S33: Machine-level maintenance plan optimization; Step S34: Multi-scale integration; Step S35: Hierarchical predictive maintenance; The quantum annealing optimization specifically improves the standard quantum annealing optimization algorithm by introducing a third-order parameter interaction relationship modeling term and a test accuracy term; Step S4: Fault tolerance control, obtaining fault occurrence control instruction data; Step S5: Health status assessment, used to generate a comprehensive health status assessment result, specifically combining the robot health parameters, the hierarchical predictive maintenance reference data and the fault occurrence control instruction data to perform a comprehensive assessment of the robot health status and obtain the robot health status comprehensive assessment reference data.

2. The method for evaluating robot health status based on artificial intelligence according to claim 1, characterized in that: In step S2, the digital twin health modeling is used to construct a virtual digital twin model of the robot's health status. Specifically, based on the robot health status evaluation optimization data, a dynamic dual data stream neural ordinary differential equation modeling method is used to perform digital twin health modeling to obtain the robot health parameters, including the following steps: Step S21: physical constraint embedding modeling, specifically, based on the robot health status assessment optimization data, using a Hamiltonian neural network combined with the physical constraints of the dynamic system to perform dynamic consistency physical constraint modeling to obtain robot joint health assessment data; The Hamiltonian neural network combined with the physical constraints of the dynamic system includes a generalized momentum definition, a Hamiltonian dynamic system definition, and a physical modeling loss function definition. The generalized momentum definition is used to map the actually observed robot joint angular velocity into the generalized momentum and use it as a prediction indicator. The Hamiltonian dynamics system definition is used to construct a physical evolution model of the robot joint state; Step S22: Wear evolution modeling, specifically, based on the robot health status assessment optimization data, by constructing a wear evolution neural ordinary differential equation model, and constructing a standard multi-layer perceptron structure to perform dynamic evolution of wear status and future wear prediction modeling, and calculate the robot joint wear rate and predicted wear value data; Step S23: adversarial verification, specifically performing standard generative adversarial network training based on the predicted wear value data and the actual wear value data to verify the authenticity of the digital twin health modeling and obtain health modeling authenticity assessment data; Step S24: digital twin health modeling, specifically performing digital twin health comprehensive modeling through the physical constraint embedding modeling, the wear evolution modeling, and the adversarial verification to obtain robot health parameters; The robot health parameters include robot joint simulation consistency index, robot joint wear degree estimation, robot health prediction residual, health modeling authenticity assessment data and robot comprehensive health score.

3. The method for evaluating robot health status based on artificial intelligence according to claim 2, characterized in that: In step S3, the multi-scale predictive maintenance is used to achieve cross-scale prediction from micro-wear to system-level failures. Specifically, based on the robot health parameters and the robot health status assessment optimization data, a multi-time-scale prediction architecture combining quantum annealing optimization and graph attention network is used to perform multi-scale predictive maintenance to obtain hierarchical predictive maintenance reference data, including the following steps: Step S31: Part-level life prediction: Based on the robot health status evaluation optimization data, the robot health parameters of the robot that meet the requirements for preventive maintenance are input as raw data, and a long short-term memory neural network combined with quantum annealing optimization is used to perform part-level life prediction to obtain remaining life estimation data; The quantum annealing optimized long short-term memory neural network specifically constructs an improved quantum annealing optimization algorithm and combines it with a standard long short-term memory neural network to perform part-level life prediction, and calculates the remaining life estimation data by modeling the output layer as a Bayesian linear regression; Step S32: constructing a system-level fault propagation graph, specifically, based on the robot health parameters and the robot health status assessment optimization data, constructing a robot system topology graph and using a standard graph attention network method to perform fault propagation modeling, and obtaining fault propagation prediction data, including fault propagation probability matrix data and propagation path prediction data, by fault diffusion probability modeling; Step S33: Optimizing the machine-level maintenance plan, specifically, optimizing the robot's maintenance plan based on the robot health parameters and the robot health status assessment optimization data, using a deep reinforcement learning method that combines an improved multi-objective reward function and quantum annealing strategy distillation to obtain optimized maintenance strategy prediction data; Step S34: multi-scale integration, specifically integrating the remaining life estimation data, the fault propagation prediction data, and the optimized maintenance strategy prediction data, performing multi-scale predictive maintenance of robot health at the part level, system level, and machine level, and building a dynamic update mechanism to perform prediction optimization to obtain multi-scale integrated prediction data; Step S35: hierarchical predictive maintenance, specifically performing hierarchical predictive maintenance based on the multi-scale integrated prediction data to obtain hierarchical predictive maintenance reference data; The hierarchical predictive maintenance reference data includes part-level maintenance parameters, system-level maintenance parameters, and machine-level maintenance decisions; The part-level maintenance parameters include part number, remaining useful life of the part, prediction uncertainty estimate, health status parameters, and temperature anomaly values; The system-level maintenance parameters include fault propagation path number, fault propagation probability, fault path criticality assessment value and risk path chain position; The machine-level maintenance decision includes the machine number, optional maintenance action set, optimal recommended maintenance action, maintenance action cost, maintenance downtime prediction time, maintenance improvement effect prediction value and maintenance strategy weight; The part-level maintenance parameters are used to assist maintenance technicians in repairing or replacing parts; the system-level maintenance parameters are used to assist engineers in controlling fault propagation paths; and the machine-level maintenance decisions are used to assist robot managers in balancing maintenance planning strategies.

4. The method for evaluating robot health status based on artificial intelligence according to claim 3, characterized in that: In step S33, the deep reinforcement learning method combining the improved multi-objective reward function and quantum annealing strategy distillation includes constructing a multi-objective reward function and quantum annealing strategy distillation improvement; The quantum annealing strategy distillation improvement is specifically to optimize the weights of each reward item in the multi-objective reward function according to the improved quantum annealing optimization algorithm, and specifically to verify the accuracy function item in the multi-objective reward function formula by replacing the reward value with the test set; The deep reinforcement learning method constructs robot maintenance state space parameters and robot maintenance action space parameters, and performs standard reinforcement learning training based on the multi-objective reward function.

5. The method for evaluating robot health status based on artificial intelligence according to claim 4, characterized in that: In step S4, the fault-tolerant control is used to maintain the basic functions of the robot when a fault occurs. Specifically, based on the hierarchical predictive maintenance reference data and the robot health status assessment optimization data, the health status of the robot's key components is dynamically mapped into control constraints, a model predictive controller with health limits is constructed, and fault-tolerant control is performed to obtain fault occurrence control instruction data; The fault occurrence control instruction data includes control amount adjustment data and safety action limitation data.

6. An artificial intelligence-based robot health status assessment system, configured to implement the artificial intelligence-based robot health status assessment method according to any one of claims 1 to 5, characterized in that: It includes data acquisition and fusion module, digital twin health modeling module, multi-scale predictive maintenance module, fault-tolerant control module and health status assessment module.

7. The artificial intelligence-based robot health status assessment system according to claim 6, characterized in that: The data acquisition and fusion module is used for data acquisition and fusion, and obtains robot health status evaluation and optimization data through data acquisition and fusion, and sends the robot health status evaluation and optimization data to the digital twin health modeling module, the multi-scale predictive maintenance module and the fault tolerance control module; The digital twin health modeling module is used for digital twin health modeling, obtains robot health parameters through digital twin health modeling, and sends the robot health parameters to the multi-scale predictive maintenance module and the health status assessment module; The multi-scale predictive maintenance module is used for multi-scale predictive maintenance, obtains hierarchical predictive maintenance reference data through multi-scale predictive maintenance, and sends the hierarchical predictive maintenance reference data to the fault tolerance control module and the health status assessment module; The fault tolerance control module is used for fault tolerance control, obtains fault occurrence control instruction data through fault tolerance control, and sends the fault occurrence control instruction data to the health status assessment module; The health status assessment module is used for health status assessment, and obtains comprehensive assessment reference data of the robot's health status through health status assessment.

Images