Industrial robot cluster operation state intelligent monitoring and prediction maintenance system

Abstract

The invention discloses an industrial robot cluster operation state intelligent monitoring and prediction maintenance system, which comprises a cloud main system and a plurality of subsystems, and is characterized in that the subsystems are arranged corresponding to regional robot clusters; the cloud main system comprises a core platform layer, a communication layer, a logic layer and a storage layer; each subsystem comprises a regional communication layer, a regional logic layer and a regional storage layer, and the regional communication layers are used for realizing data transmission in the subsystems, among the subsystems and between the subsystems and the cloud main system; the regional logic layer is internally provided with a data preprocessing module, a multi-source data fusion alignment module, a regional anomaly monitoring module, a robot regional collaboration and optimization module and a predictive maintenance module. The industrial robot cluster operation state intelligent monitoring and prediction maintenance system aims at improving cluster monitoring and maintenance efficiency, reducing non-planned shutdown and guaranteeing stable and efficient operation of a production line.

Description

Technical Field

[0001] The present invention belongs to the technical field of industrial robots, and specifically relates to an intelligent monitoring and predictive maintenance system for the operating status of an industrial robot cluster. Background Art

[0002] In modern industrial production, especially in the automobile manufacturing industry, industrial robot clusters have become key equipment. Their efficient collaborative work plays a vital role in improving the efficiency of production lines and reducing unplanned downtime. Robots such as industrial six-axis manipulators undertake core tasks such as welding, assembly and handling, ensuring the stability and efficiency of the production process. However, traditional monitoring and maintenance methods usually rely on fixed maintenance plans and periodic inspections, lack real-time response capabilities and targeted abnormal monitoring methods, and are difficult to effectively respond to the dynamic operation status of robot clusters. In complex and changing industrial environments, traditional monitoring systems face many challenges, such as inconsistency of multi-source data, noise interference, and insufficient data integration technology, which lead to limitations in fault prediction and response speed of the system, increasing the risk of production downtime and maintenance costs. Especially in the abnormal monitoring of cluster robots, there is currently no perfect technology to achieve collaborative learning and real-time abnormal sharing between robots in different regions. Existing systems are usually limited to fault detection of single robots or local areas, and it is difficult to quickly identify and disseminate abnormal information within the cluster. Due to the lack of effective collaborative monitoring strategies, the abnormal identification and response of group robots are in a blank state, further limiting the reliability and efficiency of robot clusters in industrial production. Summary of the invention

[0003] In view of this, the purpose of the present invention is to provide an industrial robot cluster operating status intelligent monitoring and predictive maintenance system, aiming to improve cluster monitoring and maintenance efficiency, reduce unplanned downtime, and ensure stable and efficient operation of the production line.

[0004] In order to achieve the above object, the present invention provides the following technical solutions:

[0005] An industrial robot cluster operating status intelligent monitoring and predictive maintenance system, comprising a cloud main system and a plurality of subsystems, wherein the subsystems are arranged corresponding to regional robot clusters;

[0006] The cloud main system includes a core platform layer, a communication layer, a logic layer and a storage layer; the core platform layer is used to process computing tasks, coordinate data analysis and collaborative learning of each subsystem, and support efficient computing and task scheduling of the system; the communication layer is used to realize data transmission between the cloud main system and the subsystem, and ensure real-time synchronization and reliable transmission of data; the logic layer is used to receive abnormal data, similarity thresholds and similar area information from the subsystem, confirm the abnormal data, and further confirm similar areas according to the similarity thresholds, and is responsible for coordinating the initiation of cross-region collaborative learning and promoting collaborative optimization between similar areas; the storage layer is used to store abnormal data, historical monitoring data, similarity thresholds, similar area information and confirmed abnormal events from each subsystem for subsequent query, analysis and model update;

[0007] The subsystem includes a regional communication layer, a regional logic layer and a regional storage layer, and the regional communication layer is used to realize data transmission within the subsystem, between subsystems, and between the subsystem and the cloud main system;

[0008] The regional logic layer is provided with a data preprocessing module, a multi-source data fusion alignment module, a regional anomaly monitoring module, a robot regional collaboration and optimization module and a predictive maintenance module; the data processing module is used to fill in missing values ​​to ensure data integrity, and to perform data cleaning, outlier processing and data standardization on the missing filled data; the multi-source data fusion alignment module is used to align and normalize data from different sources; the regional anomaly monitoring module is used to capture abnormal behavior; the robot regional collaboration and optimization module is used to identify the most similar area after detecting an anomaly, share abnormal data, and realize cross-regional collaborative learning and parameter optimization; the predictive maintenance module is used to predict the future equipment status to issue an early warning;

[0009] The regional storage layer is used to store robot sensor data.

[0010] Furthermore, the method for filling missing values ​​in the data preprocessing module is:

[0011]

[0012] Where: X filled is the missing value to be filled; X LagI is the filling value obtained by Lagrange interpolation method; X nearest is the effective data point filling value obtained by the adjacent data filling method; X Grap hSAGE is the effective data point filling value obtained by the GraphSAGE filling method; ω1 and ω2 are weights, and: ω1+ω2=1;

[0013] The Lagrange interpolation method is:

[0014]

[0015] Wherein: is the supplementary value using the Lagrange filling strategy at time point t md ; and are the data values corresponding to the first three time points t md ―3, t md ―2 and t md ―1 of the selected missing region respectively;

[0016] The adjacent data filling method is as follows:

[0017]

[0018] Wherein: is the supplementary value obtained by the adjacent data filling strategy at time t mk ; t c is the central position time point in the data segment of the missing region; s represents the length of the extracted data segment;

[0019] The GraphSAGE filling method is as follows:

[0020]

[0021] Wherein: is the supplementary value predicted by Pred at time t mk ; is the feature representation of the time point t mk at the p-th layer;

[0022] The method for the data preprocessing module to process outliers in the data after missing filling is: calculate the first quartile (Q1) and the third quartile (Q3) of the data, that is:

[0023] IQR = Q3 - Q1

[0024] Based on IQR, calculate the outlier boundaries: X < Q1 - 1.5×IQR or x > Q3 + 1.5×IQR; all points falling outside this range are considered outliers; if the outliers are considered to be caused by errors or accidental large deviations and the number is small, these outliers are directly deleted from the data set; if there is a certain number of outliers, the average value of the overall data is used to replace the outliers;

[0025] The method for the data preprocessing module to perform data standardization processing on the data after missing filling is: convert the data into a form with zero mean and unit variance to eliminate the influence between data of different magnitudes, and the formula is as follows:

[0026]

[0027] Where: Z is the data obtained by data standardization; X is the data after missing filling; μ and σ are the mean and standard deviation of the data respectively.

[0028] Furthermore, the multi-source data fusion alignment module uses a dynamic time warping method to perform time series alignment on the multi-source data to eliminate the dimension, frequency and format differences of different robot data in the region. The method steps are as follows:

[0029] S11: Constructing time series data: Organize the preprocessed data into the form of time series. Each time series contains a series of data points, and each data point corresponds to a timestamp.

[0030] S12: Define reference template and test template: select one time series as the reference template and other time series as the test template and align them with the reference template;

[0031] S13: Calculate the distance matrix: construct an n*m matrix grid, where n and m are the lengths of the reference template and the test template respectively; each element (i, j) of the matrix represents the distance d between the i-th point in the reference template and the j-th point in the test template i,j :

[0032]

[0033] Where: x i is the horizontal coordinate of the i-th point in the reference template; y j is the ordinate of the jth point in the test template;

[0034] S14: DTM method: Given two time series P and Q of length LP and LQ respectively:

[0035] P=(P1,…,P i ,…,P LP )

[0036] Q=(q1,…,q i ,…,q LQ )

[0037] Where: P i represents the value of the i-th data point in the time series P; q i Represents the value of the i-th data point in the time series q;

[0038] The alignment between P and Q is represented by a matching path W, which is expressed as:

[0039] W=(w1,…,w l ,…,w k );wl =(α l ,β l ),k≥max(LP,LQ),1≤α l ≤LP,1≤β l ≤LQ

[0040] Among them: (α l ,β l ) represents the αth l The value matches the βth l Value; w l Indicates the path matched in step l;

[0041] The goal of the DTW method is to find the optimal matching path W so that the cumulative distance The minimum is achieved under the following three constraints:

[0042] (1) Boundary constraint: This constraint restricts the path to start at (1,1) and end at (LP,LQ) when aligning sequences, that is:

[0043] (α1,β1)=(1,1)

[0044] (α l ,β l )=(LP,LQ)

[0045] (2) Continuity constraint: This constraint restricts the temporally changing curved path when aligning sequences. Under this condition, the path must move forward one step at a time, that is: l ―α l+1 ≤1 and β l ―β l+1 ≤1;

[0046] (3) Monotonicity constraint: This condition preserves the time order of the points and restricts the path to move forward without decreasing, that is: α l ≥α l+1 And β l ≥β l+1 ;

[0047] Assume D∈R LP×LQ Represents the cumulative distance, then the global minimum cumulative distance can be obtained through the following dynamic programming:

[0048] D i,j =C i,j +min(D i―1,j ,D i―1,j―1 ,D i,j―1 )

[0049] Where: Initial value D 1,1 =C 1,1; The DTW distance between two sequences P and Q is expressed as DTW(P,Q), which is equivalent to D LP,LQ ,The optimal alignment path can be obtained by backtracking in the dynamic programming process.

[0050] Furthermore, the regional anomaly monitoring module combines the ETS model and the GAT-GRU model to comprehensively analyze the operating status of the industrial robot cluster, accurately detect and predict abnormal behaviors, and use an optimized fusion loss function to efficiently identify and warn of potential faults, providing reliable support for maintenance decisions and stable operation of the production line;

[0051] The GAT-GRU model includes a graph attention network GAT and a gated recurrent unit GRU; the graph attention network GAT dynamically calculates the importance weights between robot features and time through an attention mechanism, and combines the feature GAT and time GAT dual-channel design to capture the complex spatial and temporal dependencies of industrial robot cluster data; the gated recurrent unit GRU takes the graph embedding vector generated by the graph attention network GAT as input, and the gated recurrent unit GRU network dynamically adjusts the hidden state by updating the gate and resetting the gate based on the time series modeling process.

[0052] Furthermore, the ETS model predicts future data points through exponential smoothing. The principle is:

[0053] Smoothing equation:

[0054]

[0055] in: is the predicted value for the next time step; y t is the current observation value; is the current predicted value; T t is the trend term; α is the smoothing coefficient, and 0<α<1;

[0056] Trend Adjustment:

[0057]

[0058] Where: T t+1 is the trend component of the next time step; β is the trend smoothing parameter;

[0059] Seasonal Adjustment:

[0060]

[0061] Where: S t+m is the seasonal component after m steps; γ is the seasonal smoothing parameter; and m is the seasonal period.

[0062] Furthermore, the method of the graph attention network GAT to capture the complex spatial and temporal dependencies of industrial robot cluster data is:

[0063] Based on feature GAT: the number of key parameter features n inside the robot is taken as a node, the length of the time series intercepted by the sliding window function is taken as the number of features in each node, and the attention weight is calculated:

[0064]

[0065] in, is the attention coefficient between feature GAT node i and adjacent node j; LeakyReLU is a nonlinear activation function; W Fe is the weight matrix based on feature GAT; α is the learned weight vector; || represents the connection operation; h i and h j They represent the feature vectors of node i and node j in the feature GAT, respectively, representing all key parameter features of node i and node j;

[0066] Use the softmax function to normalize the attention weights of the features within the group:

[0067]

[0068] in: is the normalized attention weight between node i and its neighboring node j; N(i) is the set of neighboring nodes of node i;

[0069] Use the attention weights to perform weighted averaging on the features and update the feature representation:

[0070]

[0071] in: It is based on the overall influence of other nodes on node i in the feature GAT;

[0072] Based on time GAT: The length l intercepted by each sliding window function is taken as a node, the key parameter feature number n is taken as the feature in each node, and the learning parameter is adjusted to γ ​​and the weight matrix is ​​adjusted to W Ti ; The weight normalization is calculated through the softmax function, and the attention weight is used to update the node representation:

[0073]

[0074] in: It is the overall influence of other nodes on node i in the temporal GAT; is the normalized attention weight between node i and its neighboring node j in the temporal GAT; is the feature vector of node j in the time-based GAT, representing all key parameter features of node j;

[0075] Combining the outputs of parallel feature-based GAT and the output of time-based GAT Fusion is the output of the graph attention network GAT

[0076] Furthermore, the principle of the gated recurrent unit GRU is:

[0077] Update Gate:

[0078] z t =σ(W z ·[h t―1 ,x t ]+b z )

[0079] Where: z t is the update gate at time step t, controlling the previous hidden state; σ is the sigmoid function; W z is the weight matrix of the update gate; h t―1 is the hidden state of the previous time step; x t is the input of the current time step; b z is the bias term;

[0080] Reset the gate:

[0081] r t =σ(W r ·[h t―1 ,x t ]+b r )

[0082] Where: r t It is the reset gate, which determines how much information of the previous state is forgotten;

[0083] Candidate hidden states:

[0084]

[0085] in: is a candidate hidden state; W h is the weight matrix of the candidate hidden state; b h is the bias term; * represents the element-wise product, meaning that the output of the reset gate affects which parts of the hidden state should be retained;

[0086] Final hidden state:

[0087]

[0088] Where: ht is the hidden state at the current time step t, which is used for prediction or further processing;

[0089] Prediction output: GRU’s final hidden state h t It will be converted into the final output prediction through a fully connected layer

[0090]

[0091] Where: W o and b o are the weights and biases of the output layer.

[0092] Furthermore, the prediction output of the ETS model is set to The predicted output of the GAT-GRU model is The true observed value is y t , then the fusion loss function is defined as:

[0093] L=ε·L ETS +(1―ε)·L GRU

[0094] Where: ε is a weight parameter, and 0<ε<1, which is used to control the contribution ratio of the ETS model and the GAT-GRU model to the total loss; I ETS and L GRU are the prediction errors of the ETS model and the GAT-GRU model, respectively, expressed as:

[0095]

[0096] Where: y t is the actual value; is the predicted value calculated using the statistical model ETS; N is the total number of samples;

[0097]

[0098] in: is the predicted value obtained using the GAT-GRU model.

[0099] Furthermore, the robot regional collaboration and optimization module identifies the most similar region after detecting an anomaly, shares anomaly data, and implements cross-region collaborative learning and parameter optimization in the following steps:

[0100] S21: Similarity calculation: Assume that area A contains n robots, denoted as A1, A2, ...A n , region B contains m robots, denoted as B1, B2, …B m ; then robot A i and robot Bj The cosine similarity is:

[0101]

[0102] Where: cos(θ ij ) is the i-th robot A i With the jth robot B i Similarity of A i,k and B j,k Robot A i and B i The value of the kth feature; d is the dimension of the feature vector;

[0103] The similarities of all robot pairs are averaged to obtain the overall similarity between region A and region B:

[0104]

[0105] Where sim(A,B) is the average similarity between region A and region B; n and m represent the number of robots in region A and region B, respectively;

[0106] S22: Collaborative learning mechanism: determine whether the average similarity sim(A,B) between region A and region B is higher than the set similarity threshold: if so, there is similarity between region A and region B, and the confirmed abnormal data is broadcast from region A to region B to trigger collaborative learning of region B; if not, there is no similarity between region A and region B;

[0107] The dynamic update method of the similarity threshold is:

[0108]

[0109] Where: t is the similarity threshold at time step t; e t is the error of the current time step, that is, the deviation between the current false alarm rate or missed alarm rate and the set value; K p is the proportionality factor, used to adjust the immediate impact of the error; K i is the integral coefficient, which is used to adjust the cumulative effect of the error; K d is the differential coefficient, which is used to adjust the rate of change of the error; is the cumulative error from the initial time step to the current time step;

[0110] S23: Multi-objective optimization: Apply the NSGA-II multi-objective optimization algorithm to dynamically optimize the model parameters of each region. The objective function of the multi-objective optimization is:

[0111] min f(θ)=(f1(θ),f2(θ))

[0112] Among them, θ represents the set of model parameters to be optimized; f1(θ) is the accuracy target of the anomaly monitoring model, and the optimization goal is to maximize the accuracy; f2(θ) is the response time target, and the optimization goal is to minimize the response time;

[0113] Construct a Pareto optimal solution set to achieve a balance between multiple objectives; select the optimal parameter combination θ in the Pareto optimal solution set * Used to update the model;

[0114] S24: Dynamic parameter update: The loss function L(θ) is used to measure the prediction error of the model and is combined with the regularization term to prevent the model from overfitting:

[0115]

[0116] Where: L(θ) is the loss function, which is used to evaluate the prediction accuracy of the model; N is the number of samples, that is, the number of training data points used; y i is the actual observed value of the i-th sample; is the predicted value of the model for the i-th sample under parameter θ; λ is the regularization coefficient, which is used to control the influence of the regularization term on the loss and avoid overfitting of the model; Ω(θ) is the regularization term, which is used to penalize excessive parameter values; in the process of minimizing the loss function L(θ), the regional anomaly monitoring module of each region will update the parameters to enhance the monitoring accuracy while maintaining the stability of the model.

[0117] Further, the method for predicting the future operating state of the industrial robot cluster in the predictive maintenance module is:

[0118] Construct a TCN model and use it to predict the future operating status of the industrial robot cluster, and obtain the key parameter sequence that can characterize the robot status in the future;

[0119] According to historical data and expert experience, the warning threshold range of each key parameter is set, and the warning threshold is divided into two levels, namely the first warning threshold and the second warning threshold;

[0120] If the predicted value of the key parameter is greater than the set first-level warning threshold, a first-level warning is triggered; if the predicted value of the key parameter is between the first-level warning threshold and the second-level warning threshold, a second-level warning is triggered; or,

[0121] The comprehensive scoring method is used to combine the warning signals of various parameters into a global warning signal, and the global warning index is defined as:

[0122]

[0123] Where: i is the importance weight of each parameter; is the predicted value of the i-th parameter; is the set second-level warning threshold; when the global warning index CWI exceeds the set global warning threshold, a global warning signal is generated.

[0124] The beneficial effects of the present invention are:

[0125] The intelligent monitoring and predictive maintenance system for the operation status of industrial robot clusters of the present invention aims to improve the operation reliability and maintenance efficiency of robot clusters, reduce the risk of unplanned downtime, and optimize the efficiency of production lines. The system includes multiple subsystems and a cloud main system, and the overall design includes a cluster mutual learning strategy. Each subsystem is responsible for the collection, monitoring and preliminary analysis of data in the region, and realizes cross-regional collaborative management through the cloud. The subsystem includes five modules: data preprocessing module, multi-source data fusion alignment module, regional anomaly monitoring module, robot regional collaboration and optimization module, and predictive maintenance module, forming a complete monitoring and maintenance system in the region. The cloud main system is responsible for global data management, anomaly confirmation and cross-regional collaborative learning, and further confirms and judges the shared abnormal data of similar regions according to the similarity threshold, optimizes the model, and improves the overall detection and response capabilities. In the subsystem, the data preprocessing module is responsible for cleaning, missing filling and stabilization to ensure the accuracy and consistency of data input; the multi-source data fusion alignment module fuses data from different sources, solves the problem of inconsistent dimensions and acquisition frequency, and provides high-quality data for subsequent monitoring. The regional anomaly monitoring module performs fine monitoring of multidimensional data and identifies abnormal features. When an anomaly is detected, the robot regional collaboration and optimization module identifies similar areas based on cosine similarity, and uploads the anomaly data, similarity threshold, and similar area information to the cloud main system, and broadcasts them to these areas to trigger collaborative learning, thereby optimizing model parameters. The predictive maintenance module realizes future state prediction and fault warning, supports optimized maintenance plans, and reduces the risk of sudden failures. The system of the present invention realizes comprehensive monitoring and collaborative optimization of robot clusters, provides intelligent maintenance support for enterprises, and significantly improves the operational stability of robot clusters and production line efficiency.

[0126] The industrial robot cluster operating status intelligent monitoring and predictive maintenance system of the present invention has the following advantages:

[0127] 1. Advantages of system architecture design:

[0128] (1) Improvement of system data processing quality: The system of the present invention includes a cloud-based main system and multiple subsystems. By configuring a data preprocessing module in the regional logic layer of each subsystem and filling in missing values ​​in the data, the integrity and consistency of the data are ensured. By performing data cleaning, outlier processing and data standardization on the data, the data quality can be effectively improved, providing a reliable data basis for subsequent anomaly monitoring and fault prediction. (2) Accurate anomaly monitoring and fault prediction: The regional anomaly monitoring module in the subsystem architecture adopts the ETS model and the GAT-GRU model, combining the stability of the statistical model with the adaptability of the deep learning model, and can achieve refined monitoring under multi-dimensional data, effectively capture abnormal patterns in complex scenarios, improve the accuracy and timeliness of fault detection, and improve the reliability of monitoring results.

[0129] 2. Advantages of Subsystem Modular Design

[0130] (1) Efficient collaborative learning and dynamic optimization: With the support of the robot regional collaboration and optimization module, abnormal data between regions are shared, similar regions are identified through the cosine similarity analysis of the subsystem, and abnormal data are propagated to regions with similar characteristics, thereby achieving cross-regional collaborative learning. The NSGA-II multi-objective optimization algorithm in the system further balances monitoring accuracy and response time, dynamically adjusts model parameters within the region, and ensures efficient operation of each region in the cluster; (2) Optimize maintenance plans and resource allocation: Through the predictive maintenance module in the subsystem, the long-term operation characteristics of the robot are captured, the equipment status can be predicted in advance, and data support can be provided for maintenance decisions. This method makes maintenance plans more scientific and resource allocation more reasonable, significantly reducing unnecessary maintenance costs.

[0131] 3. Enhancement of overall system performance

[0132] (1) Reduce unplanned downtime: Based on the system's accurate fault prediction and real-time warning functions, the failure risk of robot clusters can be greatly reduced, and unplanned downtime can be reduced, thereby improving the stability and efficiency of the production line, reducing production losses, and improving overall production efficiency. (2) Enhance the scalability and adaptability of the system: The modular design of the system is flexible and can be easily integrated into industrial environments of different types and sizes to meet the needs of various application scenarios. The system structure is convenient for future technology upgrades and expansion adjustments, and has high long-term application value and good scalability. BRIEF DESCRIPTION OF THE DRAWINGS

[0133] In order to make the purpose, technical solution and beneficial effects of the present invention clearer, the present invention provides the following drawings for illustration:

[0134] Figure 1 This is an architecture diagram of the industrial robot cluster intelligent monitoring and predictive maintenance system of the present invention;

[0135] Figure 2 This is the software architecture diagram of the cloud main system; Figure 3 It is the main interface for monitoring the robot cluster of the cloud main system;

[0136] Figure 4 Provide detailed analysis of regional robots for the cloud main system; Figure 5 It is the subsystem software architecture diagram;

[0137] Figure 6 This is a schematic diagram of the overall cluster mutual learning strategy flow of the system;

[0138] Figure 7 An example diagram of filling in missing data for the subsystem data preprocessing module;

[0139] Figure 8 It is a DTM flow chart of the subsystem multi-source data fusion and alignment module;

[0140] Fig. 9 This is the ETS model workflow diagram for the subsystem regional anomaly monitoring module;

[0141] Fig.10 It is a schematic diagram of the GAT model structure of the subsystem regional anomaly monitoring module;

[0142] Fig.11 This is a schematic diagram of the GRU model structure of the subsystem area anomaly monitoring module;

[0143] Fig.12 It is the flow chart of the subsystem regional collaborative optimization module;

[0144] Fig.13 The overall structure diagram of the TCN model for the subsystem predictive maintenance module;

[0145] Fig.14 This is a flow chart of the five modules included in the subsystem. DETAILED DESCRIPTION

[0146] The present invention is further described below in conjunction with the accompanying drawings and specific embodiments so that those skilled in the art can better understand the present invention and implement it, but the embodiments are not intended to limit the present invention.

[0147] like Figure 1As shown, the intelligent monitoring and predictive maintenance system for the operation status of industrial robot clusters in this embodiment includes a cloud-based main system and multiple subsystems, and the subsystems are set corresponding to the regional robot clusters. Each subsystem is regarded as an independent operating unit, which contains five modules: data preprocessing module, multi-source data fusion alignment module, regional anomaly monitoring module, robot regional collaboration and optimization module, and predictive maintenance module. Each subsystem is responsible for the robot data collection, processing, monitoring and maintenance in its area, and realizes the integration of module functions and the independence of monitoring within the area through a three-layer architecture (regional communication layer, regional logic layer, and regional storage layer). The cloud-based main system undertakes global management and data coordination tasks to ensure the coordinated operation and optimization of each subsystem.

[0148] 1. System architecture design

[0149] In the design of the system of this embodiment, each robot area is regarded as an independent subsystem. The main components of the subsystem include: data preprocessing module, multi-source data fusion alignment module, regional anomaly monitoring module, robot regional collaboration and optimization module and predictive maintenance module. Each subsystem is responsible for data collection, monitoring and maintenance of the robots in the area, and realizes global collaboration and intelligent management through the integrated cloud main system. Based on this architecture, the system also integrates cluster mutual learning strategies, so that each subsystem can efficiently share abnormal knowledge and improve the overall abnormal monitoring efficiency of the cluster.

[0150] 1.1. Cloud main system architecture design

[0151] The cloud main system is responsible for cluster-level global management and coordination, achieving collaborative learning and unified control among regions. The cloud main system software architecture is as follows: Figure 2 In this embodiment, the cloud main system includes a core platform layer, a communication layer, a logic layer, a storage layer and a front-end display layer.

[0152] The core platform layer is used to handle computing tasks. The core platform layer is equipped with high-performance computing servers (such as GPU servers) and a technology stack to support the front-end and back-end, including Vue.js, JavaScript and HTML (front-end display framework), Django (back-end framework) and MySQL database. The core platform layer is responsible for handling complex computing tasks, data management and processing, model optimization and scheduling functions of the cloud main system to ensure the efficiency and scalability of the system.

[0153] The communication layer is used to realize data transmission between the cloud main system and subsystems, ensure the real-time transmission of abnormal data, monitoring results and optimization instructions, and maintain the synchronization and integrity of the system.

[0154] The logic layer is the core functional module of the cloud main system, receiving abnormal data, similarity thresholds, and similar area information from each subsystem. The logic layer first confirms whether the uploaded abnormal data is valid through equipment engineers, and further confirms similar areas based on the set similarity thresholds. The confirmed abnormal data will be transmitted to these similar areas, and the logic layer is responsible for coordinating and initiating cross-region collaborative learning to promote collaborative optimization and model updates between similar areas.

[0155] The storage layer is used to store abnormal data, historical monitoring data and confirmed abnormal events from each subsystem, support model optimization, historical tracing and further analysis, and provide a reliable data foundation for long-term optimization and abnormal analysis of the system.

[0156] Front-end display layer: provides a real-time interactive interface. The main page displays the distribution of all robots in each area, as well as overall operation information (such as the number of running robots, abnormal detection ratio, and production efficiency, etc.). Figure 3 The sub-interface supports viewing the operation details of robots in specific areas, including statistical analysis (such as trend strength, seasonal strength, etc.) and in-depth analysis results (such as anomaly detection, predictive maintenance warning), and provides maintenance options to support the arrangement of maintenance tasks, such as Figure 4 The intuitive interactive function of the front-end display layer helps managers make efficient decisions and significantly improves the convenience of system monitoring and maintenance.

[0157] Under the control of the cloud main system, each subsystem will upload data to the cloud when it detects an anomaly. After the engineer confirms the nature of the abnormal data, the cloud main system further confirms similar areas based on the uploaded similar area information and transmits the abnormal data to these similar areas, triggering collaborative learning and model optimization.

[0158] 1.2. Subsystem Architecture Design

[0159] The subsystem of each robot area includes the following five modules: data preprocessing module, which ensures the integrity and consistency of data and solves the problem of missing data by using a comprehensive filling method of Lagrange interpolation, neighboring data filling method and GraphSAGE filling method; multi-source data fusion alignment module, which processes data from different devices through time series alignment and feature normalization technology; anomaly monitoring module, which combines the improved ETS model and GAT-GRU joint model for anomaly detection; robot area collaboration and optimization module, which is used to realize collaborative learning between different areas of the robot cluster. When an anomaly occurs in a certain area and is confirmed, the system selects similar areas based on cosine similarity to share anomaly data and trigger collaborative learning; and predictive maintenance module, which uses a temporal convolutional network (TCN) to predict future equipment status and establish an early warning system. Subsystem architecture and functions: Each subsystem consists of a three-layer structure, including a regional communication layer, a regional logic layer and a regional storage layer, such as Figure 5 shown.

[0160] The regional communication layer is used to realize data transmission within the subsystem, between subsystems, and between the subsystem and the main system. The data transmission within the subsystem and between the subsystem and the main system can ensure the synchronization of data within the region, and upload the abnormal data, similarity threshold and similar area information to the cloud main system in real time after the abnormality is detected. The data transmission between subsystems can receive the abnormal data transmitted by other subsystems through the communication layer and transmit it to the logic layer for parameter optimization.

[0161] The regional logic layer is equipped with a data preprocessing module, a multi-source data fusion alignment module, a regional anomaly monitoring module, a robot regional collaboration and optimization module, and a predictive maintenance module; the data processing module is used to fill in missing values ​​to ensure data integrity, and to perform data cleaning, outlier processing, and data standardization on the missing data after filling; the multi-source data fusion alignment module is used to align and normalize data from different sources; the regional anomaly monitoring module is used to capture abnormal behavior; the robot regional collaboration and optimization module is used to identify the most similar area after detecting an anomaly, share abnormal data, and realize cross-regional collaborative learning and parameter optimization; the predictive maintenance module is used to predict the future equipment status to issue an early warning. That is, in this embodiment, the regional logic layer is used to complete data preprocessing, fusion, monitoring, and optimization. When an anomaly is detected in this area, the logic layer analyzes the abnormal situation, triggers the predictive maintenance module, and uploads the abnormal data, similarity threshold, and similar area information to the main system through the communication layer; after receiving the abnormal data of other subsystems, the parameters are updated according to the similarity and the current model state to improve the system's recognition accuracy for similar anomalies.

[0162] The regional storage layer is used to store the status data from each robot sensor, which is convenient for subsequent model optimization and abnormal analysis. This data will be updated periodically to ensure continuous learning and accurate prediction of the model.

[0163] 1.3 Cluster mutual learning strategy

[0164] This strategy significantly improves the response speed and fault prevention capabilities of the robot cluster in abnormal monitoring through collaborative learning, dynamic updating, and adaptive similarity adjustment between regions, thereby improving production efficiency, reducing failure rates, and effectively reducing maintenance costs. The overall process of the mutual learning strategy is as follows: Figure 6 shown.

[0165] 1.3.1. Initialization of the fusion model

[0166] In this embodiment, the robot cluster in each subsystem area is equipped with a fusion anomaly monitoring model that combines the improved ETS model (exponential smoothing state space model) and the GAT-GRU model (graph attention network-gated recurrent unit model). The model is initially trained with periodic data of normal operating parameters in the region. The initial model training takes into account the possible differences in robot models in the region, so that the model adapts to the different operating characteristics of the robots in the group, thereby enhancing the synergy of the robots within the subsystem in anomaly monitoring. The fusion model combines the advantages of ETS in time series smoothing, the accuracy of GAT in spatial relationship modeling, and the powerful ability of GRU in long-term dependency modeling, ensuring that the monitoring model is sensitive to periodic anomalies and can identify nonlinear features in complex scenarios.

[0167] 1.3.2. Upload and confirm abnormal data of subsystem

[0168] During the actual operation, the sub-models in each subsystem monitor the operating status of the robots in the area in real time and upload the monitoring data to the main cloud system. When a subsystem detects an abnormal event, the abnormal data will be uploaded to the cloud through the communication layer, and the engineering and technical personnel will confirm the authenticity of the abnormal data. If the abnormal event is confirmed to be a real fault, the abnormal data and the corresponding subsystem ID will be stored and recorded to facilitate accurate tracking and comparison in subsequent similar area analysis. This confirmation mechanism ensures that the system is based on reliable abnormal information during collaborative learning, prevents false alarm data from spreading between clusters, and reduces the false alarm rate of the overall system.

[0169] 1.3.3. Periodic Similarity Detection

[0170] In order to improve the effectiveness of abnormal data transmission between regions, the system of this embodiment designs a regular similarity detection mechanism between the cloud main system and each subsystem. Each subsystem periodically aligns the key parameters of the robots in the area during the monitoring period to generate a function distribution of the parameters. On this basis, each subsystem calculates the similarity between itself and other subsystem models respectively, thereby quantifying the differences in predicted data between different subsystems. This similarity value will be uploaded to the cloud main system along with the detected abnormal data. By receiving these similarity data and abnormal information, the cloud main system can more effectively analyze the applicability and reference value of abnormal data in different regions. When conducting collaborative learning, the system gives priority to subsystems with high similarity to the fault area for abnormal data sharing based on these similarity results, so as to ensure the effectiveness and accuracy of abnormal transmission, reduce interference in information transmission and improve the overall collaborative learning effect.

[0171] 1.3.4. Similar area data broadcast and dynamic threshold adjustment

[0172] The cloud main system broadcasts the abnormal data of other subsystems with similar characteristics to each subsystem based on the similarity detection results. Based on the set threshold conditions, the system will trigger the sharing mechanism of abnormal data when the similarity between the two areas is higher than the set threshold to ensure that only the most relevant subsystems share data and improve learning efficiency. In order to further optimize the adaptability of the system, this embodiment uses a PID (proportional-integral-differential) control algorithm to dynamically adjust the similarity threshold so that the system can automatically adapt to the appropriate collaborative learning range under different abnormal conditions and operating environments. In actual operation, when a similar area receives abnormal data shared by other subsystems, it will trigger the parameter update of the regional model to enhance the detection accuracy of the model for similar anomalies. Through dynamic threshold control, the system can adjust the coverage of collaborative learning in a timely manner, making the collaborative learning between subsystems more flexible and efficient. The monitoring results after the similar area model is updated will be further uploaded to the main system for reference and optimization by other subsystems to form a closed-loop learning mechanism.

[0173] 2. Data preprocessing module

[0174] In this embodiment, the data preprocessing module is used to process the monitoring data of the robot cluster in the industrial production environment. The module first fills in the missing data points, and then performs data cleaning, outlier processing and data standardization to ensure the quality of the data and provide high-quality input for subsequent abnormal monitoring and predictive maintenance analysis. Before conducting a study on the multi-source data fusion technology of the robot cluster, the multi-dimensional data collected by the robot cluster must be fully preprocessed, which is specifically divided into the following steps.

[0175] 2.1 Missing Data Filling

[0176] In the operation data of the robot cluster, data missing is a common problem, which may be caused by equipment failure, data transmission interruption or other technical problems. To ensure the integrity of the data, the following two methods are combined to perform comprehensive data filling.

[0177] 2.1.1. Neighboring Data Filling

[0178] Using data from adjacent time points to fill missing values ​​is suitable for situations where there is less missing data and the time series is continuous. mk , the total length of the missing region is s, and data segments of length s / 2 are extracted before and after the missing region respectively, without any calculation, and directly used as the filling value of the missing region. In this embodiment, the adjacent data filling method is:

[0179]

[0180] in: Yes mk The supplementary value obtained by using the adjacent data filling strategy at the time point; t c is the central position time point in the missing area data segment; s is the length of the extracted data segment.

[0181] 2.1.2 Lagrangian filling

[0182] When dealing with missing values ​​in time series, the Lagrange interpolation method is a classic polynomial interpolation method that accurately estimates the value of the unknown point by constructing a polynomial using known data points adjacent to the missing point. The general formula of Lagrange interpolation is defined as:

[0183]

[0184] Where: L(t) is the interpolation polynomial used to predict any time point t; y i corresponds to the time point t i The known data value of i (t) is the i-th basis polynomial, which is calculated as follows: This product traverses all indexes j except i to construct a polynomial. In this embodiment, for the time t at which the data is missing, md , select the first three time points t of the missing region md ―3.t md -2 and t md ―1, the corresponding data values ​​are and By substituting the data of these three points into the Lagrange interpolation polynomial, we get t md The predicted data value at the moment is. In this embodiment, the Lagrange interpolation method is:

[0185]

[0186] in: At time point t md Supplementary values ​​using Lagrangian filling strategy; and The first three time points t of the selected missing region are md ―3.t md -2 and t md -The data value corresponding to 1.

[0187] 2.1.3 GraphSAGE filling

[0188] In the GraphSAGE model, a one-way propagation relationship between nodes is defined, and a network structure containing P layers is constructed. This setting enables the model to iteratively update the node features of each layer, and finally effectively estimate and fill t through the prediction function of Pred. md In this embodiment, the GraphSAGE filling method is:

[0189]

[0190] in: is predicted by Pred mk The supplementary value of the moment; is t of the pth layer mk Feature representation at a time point.

[0191] 2.1.4 Comprehensive gap filling

[0192] Combining the three methods of neighboring data filling, Lagrange filling and GraphSAGE filling, the weight coefficients ω1 and ω2 are set to satisfy ω1+ω2=1. Figure 7 As shown, the method for filling missing values ​​in the data preprocessing module of this embodiment is:

[0193]

[0194] Where: X filled is the missing value to be filled; X LagI is the filling value obtained by Lagrange interpolation method; X nearest is the effective data point filling value obtained by the adjacent data filling method; X Grap hSAGE is the effective data point filling value obtained by the GraphSAGE filling method; ω1 and ω2 are weights, and: ω1+ω2=1.

[0195] By comprehensively using these three filling methods, the integrity and consistency of the data can be effectively guaranteed. This not only helps to avoid possible errors in subsequent analysis but also ensures the accuracy and reliability of the analysis results. The integrity of the data is the basis for ensuring accurate prediction and anomaly detection of the model. Therefore, this comprehensive data filling strategy is crucial.

[0196] 2.2. Outlier handling (IQR)

[0197] In this embodiment, the method for the data preprocessing module to handle outliers in the data after missing value filling is as follows: Calculate the first quartile (Q1) and the third quartile (Q3) of the data, that is:

[0198] IQR = Q3 - Q1

[0199] Based on the IQR, calculate the outlier boundaries: x < Q1 - 1.5×IQR or x > Q3 + 1.5×IQR; all points falling outside this range are considered outliers; if the outliers are considered to be caused by errors or accidental large deviations and the number is small, these outliers are directly deleted from the dataset; if there is a certain number of outliers, the average value of the overall data is used to replace the outliers.

[0200] 2.3. Data standardization

[0201] In this embodiment, the method for the data preprocessing module to perform data standardization on the data after missing value filling is as follows: Convert the data into a form with zero mean and unit variance to eliminate the influence between data of different magnitudes. The formula is as follows:

[0202]

[0203] Where: Z is the data obtained by data standardization processing; X is the data after missing value filling; μ and σ are the mean and standard deviation of the data.

[0204] The data preprocessing module outputs high-quality data, providing reliable input for subsequent anomaly detection and predictive maintenance. The comprehensive preprocessing method adopted by the data preprocessing module improves the accuracy and efficiency of the entire monitoring system.

[0205] 3. Multi-source data fusion and alignment module

[0206] The multi-source data fusion and alignment module in the subsystem aims to process the data of different robots in the area to solve the problems of differences in data dimensions, data ranges, data collection frequencies, and data upload formats. In this embodiment, the multi-source data fusion and alignment method (DTM) is adopted to ensure the consistency and comparability of the data, thereby improving the accuracy of subsequent analysis.

[0207] DTW (Dynamic Time Warping) is an algorithm that can measure the similarity between two different time series data and adjust their lengths. Figure 8 Compared with the Euclidean distance, which can more accurately measure the similarity of sequence data, the DTW method is used to align the data collected by the robot, which can ensure that the morphology of different time series data is as consistent as possible, so as to facilitate subsequent data fusion.

[0208] Specifically, in this embodiment, the multi-source data fusion alignment module uses a dynamic time warping method to align the time series of multi-source data to eliminate the dimension, frequency and format differences of different robot data in the region. The method steps are as follows.

[0209] S11: Construct time series data: Organize the preprocessed data into the form of time series. Each time series contains a series of data points, and each data point corresponds to a timestamp.

[0210] S12: Define reference template and test template: Select one time series as the reference template and other time series as test templates and align them with the reference template.

[0211] S13: Calculate the distance matrix: construct an n*m matrix grid, where n and m are the lengths of the reference template and the test template respectively; each element (i, j) of the matrix represents the distance d between the i-th point in the reference template and the j-th point in the test template i,j :

[0212]

[0213] Where: x i is the horizontal coordinate of the i-th point in the reference template; y j is the ordinate of the jth point in the test template.

[0214] S14: DTM method: Given two time series P and Q of length LP and LQ respectively:

[0215] P=(P1,…,P i ,…,P LP )

[0216] Q=(q1,…,q i ,…,q LQ )

[0217] Where: P i represents the value of the i-th data point in the time series P; q i Represents the value of the i-th data point in the time series Q;

[0218] The alignment between P and Q is represented by a matching path W, which is expressed as:

[0219] W=(w1,…,w l ,…,w k );w l =(α l ,β l ),k≥max(LP,LQ),1≤α l ≤LP,1≤β l ≤LQ

[0220] Among them: (α l ,β l ) represents the αth l The value matches the βth l Value; w l Indicates the path matched in step l.

[0221] The goal of the DTW method is to find the optimal matching path W so that the cumulative distance The minimum is achieved under the following three constraints:

[0222] (1) Boundary constraint: This constraint restricts the path to start at (1,1) and end at (LP,LQ) when aligning sequences, that is:

[0223] (α1,β1)=(1,1)

[0224] (α l ,β l )=(LP,LQ)

[0225] (2) Continuity constraint: This constraint restricts the temporally changing curved path when aligning sequences. Under this condition, the path must move forward one step at a time, that is: l ―α l+1 ≤1 and β l ―β l+1 ≤1.

[0226] (3) Monotonicity constraint: This condition preserves the time order of the points and restricts the path to move forward without decreasing, that is: α l ≥α l+1 And β l ≥β l+1 .

[0227] Assume D∈R LP×LQ Represents the cumulative distance, then the global minimum cumulative distance can be obtained through the following dynamic programming:

[0228] D i,j =C i,j +min(D i―1,j ,D i―1,j―1 ,Di,j―1 )

[0229] Where: Initial value D 1,1 =C 1,1 ; The DTW distance between two sequences P and Q is expressed as DTW(P,Q), which is equivalent to D LP,LQ ,The optimal alignment path can be obtained by backtracking in the dynamic programming process.

[0230] Through the above-mentioned multi-source data fusion and alignment module, the system can effectively process multiple data from different robots in the area, providing a consistent and accurate data basis for abnormal monitoring and equipment maintenance. This method significantly improves the flexibility of data processing and the effectiveness of subsequent analysis, and is one of the key technologies of the present invention.

[0231] 4. Regional abnormality monitoring module

[0232] The anomaly monitoring module uses a joint deep learning method that combines the improved ETS model (exponential smoothing state space model) and the GAT-GRU model (graph attention network-gated recurrent unit model) to monitor the preprocessed data of the industrial robot cluster for anomalies. Specifically, the ETS model first models the time series data, decomposes the trend, seasonality and residual components in the time series, smoothes the fluctuations in the data and extracts the periodic behavior characteristics, providing a stable baseline for anomaly monitoring, while effectively reducing the impact of noise interference and ensuring the robustness of the initial modeling. In the deep learning part, the joint architecture of GAT and GRU is used to achieve deep modeling of the spatial and temporal characteristics of the data. By integrating the time series stability of the ETS model and the spatial and temporal characteristics of the GAT-GRU model, the anomaly monitoring module can comprehensively analyze the operating status of the industrial robot cluster, accurately detect and predict abnormal behaviors, and optimize the comprehensive loss function to ensure efficient identification and early warning of potential faults, providing reliable support for maintenance decisions and stable operation of the production line.

[0233] The regional anomaly monitoring module of this embodiment combines the ETS model and the GAT-GRU model to comprehensively analyze the operating status of the industrial robot cluster, accurately detect and predict abnormal behaviors, and use an optimized fusion loss function to efficiently identify and warn of potential faults, providing reliable support for maintenance decisions and stable operation of the production line. The GAT-GRU model includes a graph attention network GAT and a gated recurrent unit GRU; the graph attention network GAT dynamically calculates the importance weights between robot features and time through an attention mechanism, and combines the dual-channel design of feature GAT and time GAT to capture the complex spatial and temporal dependencies of industrial robot cluster data; the gated recurrent unit GRU takes the graph embedding vector generated by the graph attention network GAT as input, and the gated recurrent unit GRU network dynamically adjusts the hidden state through update gates and reset gates based on the time series modeling process.

[0234] 4.1. ETS model (exponential smoothing state space model)

[0235] The ETS model is a time series forecasting model that is suitable for processing data with trends and seasonality, such as Fig. 9 The model predicts future data points through exponential smoothing. The principle is:

[0236] Smoothing equation:

[0237]

[0238] in: is the predicted value for the next time step; y t is the current observation value; is the current predicted value; T t is the trend term; α is the smoothing coefficient, and 0<α<1, which adjusts the emphasis on historical data.

[0239] Trend Adjustment:

[0240]

[0241] Where: T t+1 is the trend component of the next time step; β is the trend smoothing parameter;

[0242] Seasonal Adjustment:

[0243]

[0244] Where: S t+m is the seasonal component after m steps; γ is the seasonal smoothing parameter; and m is the seasonal period.

[0245] 4.2 GAT-GRU Model

[0246] GAT dynamically calculates the importance weights between robot features through the attention mechanism, captures the complex spatial dependencies and interaction characteristics within the robot cluster, and embeds each robot feature into a graph representation with a global context. Subsequently, the graph embedding vector generated by GAT is input into the GRU model to further analyze the dynamic changes of the time series. GRU effectively captures long-term time dependencies through the update gate and reset gate mechanism, while suppressing irrelevant information, thereby accurately identifying abnormal patterns in time series, such as Fig.10 shown.

[0247] 4.2.1 Graph Attention Network GAT

[0248] GAT dynamically calculates the importance weights between robot features and time through the attention mechanism, and combines the dual-channel design of feature GAT and time GAT to capture the complex spatial and temporal dependencies of industrial robot cluster data. Specifically, in this embodiment, the method of using the graph attention network GAT to capture the complex spatial and temporal dependencies of industrial robot cluster data is as follows.

[0249] (1) Based on feature GAT: The number of key parameter features n inside the robot is taken as a node, and the length of the time series intercepted by the sliding window function is taken as the number of features in each node, and the attention weight is calculated:

[0250]

[0251] in, is the attention coefficient between feature GAT node i and adjacent node j; LeakyReLU is a nonlinear activation function; W Fe is the weight matrix based on feature GAT; α is the learned weight vector; || represents the connection operation; h i and h j They represent the feature vectors of node i and node j in the feature GAT respectively, representing all the key parameter features of node i and node j.

[0252] Use the softmax function to normalize the attention weights of the features within the group:

[0253]

[0254] in: is the normalized attention weight between node i and its neighboring node j; N(i) is the set of neighboring nodes of node i.

[0255] Use the attention weights to perform weighted averaging on the features and update the feature representation:

[0256]

[0257] in: It is based on the overall impact of other nodes on node i in the feature GAT.

[0258] (2) Based on time GAT: The length l intercepted by each sliding window function is taken as a node, the key parameter feature number n is taken as the feature in each node, and the learning parameter is adjusted to γ ​​and the weight matrix is ​​adjusted to W Ti ; The weight normalization is calculated through the softmax function, and the attention weight is used to update the node representation:

[0259]

[0260] in: It is the overall influence of other nodes on node i in the temporal GAT; is the normalized attention weight between node i and its neighboring node j in the temporal GAT; is the feature vector of node j in the time-based GAT, representing all key parameter features of node j.

[0261] Combining the outputs of parallel feature-based GAT and the output of time-based GAT Fusion is the output of the graph attention network GAT

[0262] 4.2.2 Gated Recurrent Unit (GRU)

[0263] Taking the graph embedding vector generated by GAT as input, the GRU network dynamically adjusts the hidden state through the update gate and reset gate based on the time series modeling process. Specifically, Fig.11 As shown, the principle of the gated recurrent unit GRU is:

[0264] Update Gate:

[0265] z t =σ(W z ·[h t―1 ,x t ]+b z )

[0266] Where: z t is the update gate at time step t, controlling the previous hidden state; σ is the sigmoid function; W z is the weight matrix of the update gate; h t―1 is the hidden state of the previous time step; x t is the input of the current time step; b z is the bias term.

[0267] Reset the gate:

[0268] r t =σ(W r ·[h t―1 ,x t ]+b r )

[0269] Where: r t It is the reset gate that determines how much information of the previous state is forgotten.

[0270] Candidate hidden states:

[0271]

[0272] in: is a candidate hidden state; W h is the weight matrix of the candidate hidden state; b h is the bias term; * denotes element-wise multiplication, meaning that the output of the reset gate affects which parts of the hidden state should be kept.

[0273] Final hidden state:

[0274]

[0275] Where: h t is the hidden state at the current time step t, which is used for prediction or further processing.

[0276] Prediction output: GRU’s final hidden state h t It will be converted into the final output prediction through a fully connected layer

[0277]

[0278] Where: W o and b o are the weights and biases of the output layer.

[0279] 4.3 Weighted Loss Function

[0280] In order to optimize the prediction performance of the ETS model and the GAT-GRU model at the same time, a weighted loss function can be defined, which combines the prediction errors of the two models and balances the contribution of the two models to the final performance by adjusting the weights.

[0281] 4.3.1 Fusion Loss Function

[0282] Set the prediction output of the ETS model to The predicted output of the GAT-GRU model is The true observed value is y t , then the fusion loss function is defined as:

[0283] L=ε·L ETS +(1―ε)·L GRU

[0284] Among them: ε is a weight parameter, and 0<ε<1), which is used to control the contribution ratio of the ETS model and the GAT-GRU model to the total loss; L ETS and L GRU are the prediction errors of the ETS model and the GAT-GRU model, which are usually calculated using the mean square error (MSE) and expressed as:

[0285]

[0286] Where: y t is the actual value; is the predicted value calculated using the statistical model ETS; N is the total number of samples.

[0287]

[0288] in: is the predicted value obtained using the GAT-GRU model.

[0289] 4.3.2 Parameter adjustment and optimization

[0290] To find the optimal ε, cross-validation or other model selection techniques can be used to evaluate the model performance under different ε values. In addition, gradient descent or other optimization algorithms can be used to minimize the loss function L to adjust the parameters of the ETS and GAT-GRU models.

[0291] Through this weighted loss function, we can effectively combine the ETS model's ability to capture trends and seasonality in time series data and the GAT-GRU model's advantages in dealing with complex long-term dependencies to achieve more accurate and robust anomaly monitoring performance, which not only improves the accuracy of predictions, but also brings greater flexibility and efficiency to the practical application of the system.

[0292] 5. Robot regional collaboration and optimization module

[0293] The core goal of the robot regional collaboration and optimization module is to achieve efficient collaborative learning and dynamic optimization between regions within the robot cluster to enhance the accuracy and response speed of overall abnormality monitoring. In this embodiment, the robot regional collaboration and optimization module consists of the following key steps, including similarity calculation, collaborative learning mechanism, application of multi-objective optimization algorithm, dynamic parameter update and adaptive feedback control mechanism. The specific process is as follows: Fig.12In this embodiment, the robot regional collaboration and optimization module identifies the most similar region after detecting an anomaly, shares anomaly data, and implements cross-region collaborative learning and parameter optimization.

[0294] S21: Similarity calculation:

[0295] When a robot in a certain area detects an anomaly, the anomaly data will be uploaded to the cloud and confirmed by the equipment engineer as a valid anomaly. The confirmed anomaly data will be used to identify other similar areas through similarity calculation to trigger the collaborative learning process. The similarity uses the cosine similarity method to quantify the feature similarity of different areas. Specifically, assume that area A contains n robots, denoted as A1, A2, ...A n , region B contains m robots, denoted as B1, B2, …B m ; then robot A i and robot B j The cosine similarity is:

[0296]

[0297] Where: cos(θ ij ) is the i-th robot A i With the jth robot B i Similarity of A i,k and B j,k Robot A i and B i The value of the kth feature; d is the dimension of the feature vector. In order to obtain the overall similarity between region A and region B, the similarities of all robot pairs are averaged to obtain the overall similarity between region A and region B:

[0298]

[0299] Among them, sim(A,B) is the average similarity between area A and area B; n and m represent the number of robots in area A and area B respectively. When the average similarity sim(A,B) between areas is higher than a certain set threshold, the system can consider that the two areas have high similarity in operation characteristics.

[0300] S22: Collaborative learning mechanism: determine whether the average similarity sim(A,B) between region A and region B is higher than the set similarity threshold: if so, there is similarity between region A and region B, and the confirmed abnormal data is broadcast from region A to region B to trigger collaborative learning of region B; if not, there is no similarity between region A and region B;

[0301] To further optimize the effects of collaborative learning and parameter updating, this embodiment adopts an adaptive feedback control mechanism. This mechanism dynamically adjusts the similarity threshold of collaborative learning by monitoring the actual operating performance of each regional model, so as to adaptively adjust the collaborative learning range. Specifically, this embodiment adopts PID control to update the similarity threshold, that is, the dynamic update method of the similarity threshold is:

[0302]

[0303] Where: t is the similarity threshold at time step t; e t is the error of the current time step, that is, the deviation between the current false alarm rate or missed alarm rate and the set value; K p is the proportionality factor, used to adjust the immediate impact of the error; K i is the integral coefficient, which is used to adjust the cumulative effect of the error; K d is the differential coefficient, which is used to adjust the rate of change of the error; is the cumulative error from the initial time step to the current time step.

[0304] By adaptively adjusting the similarity threshold δ, the system can dynamically adapt to different anomaly types and regional characteristics, making collaborative learning and anomaly monitoring more flexible and efficient.

[0305] S23: Multi-objective optimization: Based on regional collaborative learning, in order to strike a balance between monitoring accuracy and response time, the NSGA-II multi-objective optimization algorithm is applied to dynamically optimize the model parameters of each region. The objective function of the multi-objective optimization is:

[0306] min f(θ)=(f1(θ),f2(θ))

[0307] Among them, θ represents the set of model parameters to be optimized; f1(θ) is the accuracy target of the anomaly monitoring model, which is defined as the accuracy score, and the optimization goal is to maximize the accuracy; f2(θ) is the response time target, which is defined as the average detection time of the model, and the optimization goal is to minimize the response time.

[0308] The NSGA-II algorithm constructs a Pareto optimal solution set through non-dominated sorting and crowding comparison to achieve a balance among multiple objectives; the optimal parameter combination θ is selected from the Pareto optimal solution set. * Used to update the model and improve the overall performance of anomaly detection in the region.

[0309] S24: Dynamic parameter update: abnormal data obtained through collaborative learning and optimal parameters θ calculated by multi-objective optimization *, the abnormal monitoring model of each area will perform dynamic parameter updates. The loss function L(θ) is used to measure the prediction error of the model and is combined with the regularization term to prevent the model from overfitting:

[0310]

[0311] Where: L(θ) is the loss function, which is used to evaluate the prediction accuracy of the model; N is the number of samples, that is, the number of training data points used; y i is the actual observed value of the i-th sample; is the predicted value of the model for the i-th sample under parameter θ; λ is the regularization coefficient, which is used to control the influence of the regularization term on the loss and avoid overfitting of the model; Ω(θ) is the regularization term, which is used to penalize excessive parameter values; in the process of minimizing the loss function L(θ), the regional anomaly monitoring module of each region will update the parameters to enhance the monitoring accuracy while maintaining the stability of the model.

[0312] In summary, the robot regional collaboration and optimization module of this embodiment realizes efficient collaborative learning and model optimization among regions through similarity calculation, collaborative learning, multi-objective optimization and adaptive feedback control mechanism. Cosine similarity is used to judge the similarity of regional features and determine the broadcast range of collaborative learning; the NSGA-II optimization algorithm ensures that the model strikes a balance between accuracy and response time; the PID control mechanism dynamically adjusts the similarity threshold to enhance system adaptability. While improving the accuracy and response speed of abnormal monitoring, this module significantly enhances the collaborative ability and system reliability of the robot cluster.

[0313] 6. Predictive maintenance module

[0314] The predictive maintenance module of this embodiment adopts a time convolutional network (TCN) model. The predictive maintenance module is used to predict the future operating status of the industrial robot cluster and issue fault warnings in advance according to the prediction results to optimize the maintenance plan. Fig.13 This module is specially designed with primary and secondary alarm systems to respond to predicted potential problems with different levels of urgency.

[0315] Specifically, the method for predicting the future operating status of an industrial robot cluster in a predictive maintenance module is as follows.

[0316] 6.1. Building TCN Model

[0317] The TCN model is used to predict the future operating status of the industrial robot cluster and obtain the key parameter sequence that can characterize the robot status in the future. Specifically, TCN consists of multiple layers of one-dimensional convolutional layers, and each layer of convolution uses dilated convolution to process sequence data with time dependence. Residual connections are used to alleviate the gradient vanishing problem in deep networks, thereby improving the stability and accuracy of the model in long-term series prediction. The multi-source data of the robots in each region are passed into the TCN network as input features. The network automatically learns the temporal dynamic features of the data, captures long-term dependencies, and provides accurate support for the prediction of the future status of the robot cluster.

[0318] 6.2 Predictive maintenance and early warning

[0319] 6.2.1 Fault Prediction

[0320] Prediction goal: Use the trained TCN model to predict the operating status of the equipment in the next few time steps, including the trend changes of key parameters such as temperature, vibration, pressure, etc.

[0321] Prediction results: The output prediction results include a sequence of equipment status parameters for a period of time in the future. These predicted values ​​are compared with the actual equipment status in operation to identify potential abnormal trends.

[0322] 6.2.2 Early Warning Mechanism

[0323] Level 1 Warning (Warning): When the predicted value is greater than or equal to the level 1 warning threshold and less than the level 2 warning threshold, the system issues a level 1 warning signal to remind maintenance personnel to pay attention to the equipment status, but no immediate action is required. Level 2 Warning (Critical Alert): When the predicted value is greater than or equal to the level 2 warning threshold, and the trend is clearly developing in the direction of deterioration, the system issues a level 2 warning signal, requiring immediate inspection or maintenance operations. That is, the generation of the warning signal is based on the comparison between the predicted value and the threshold. is the predicted value, T1 and T2 are the thresholds of the first-level warning and the second-level warning respectively. Then the warning condition is: if It is a first-level warning; if the actual observation value ≥T2, it is a level 2 warning.

[0324] Multivariate early warning comprehensive analysis: When processing multi-source equipment data, it may involve early warnings of multiple monitoring parameters. This embodiment can also use a comprehensive scoring method to integrate the early warning signals of each parameter into a global early warning signal, and define the global early warning index as:

[0325]

[0326] Where: iis the importance weight of each parameter; is the predicted value of the i-th parameter; is the set second-level warning threshold; when the global warning index CWI exceeds the set global warning threshold, a global warning signal is generated.

[0327] Through the application of TCN, factories can achieve accurate predictive maintenance in the complex production environment of robot clusters, providing more robust protection for industrial production. This method not only improves the safety and stability of the system, but also enhances the factory's ability to cope with complex and changing production environments, effectively reducing unplanned downtime and the economic losses it brings.

[0328] The intelligent monitoring and predictive maintenance system for the operation status of industrial robot clusters in this embodiment includes multiple subsystems and a cloud main system, which work together to achieve real-time monitoring, collaborative learning and predictive maintenance of cluster equipment. In the system architecture design, the subsystem is responsible for the collection, monitoring and processing of robot data in the area. The subsystem contains five core modules: data preprocessing, multi-source data fusion alignment, regional anomaly monitoring, robot regional collaboration and optimization, and predictive maintenance module. The five module processes of the subsystem are as follows: Fig.14 As shown. The synergy of these modules ensures the smooth flow of data from collection and processing to anomaly detection and predictive maintenance. This subsystem integrates advanced data processing technology, deep learning models and time series analysis methods to achieve efficient equipment status monitoring and potential fault prediction. The robot cluster intelligent monitoring and maintenance system of this embodiment not only improves the timeliness and accuracy of maintenance, but also makes maintenance decisions more scientific and systematic through an intelligent early warning mechanism, significantly reduces the risk of unplanned downtime, improves production efficiency, and enhances the operational stability of the industrial robot cluster and the productivity of the enterprise.

[0329] The above-described embodiments are only preferred embodiments for fully illustrating the present invention, and the protection scope of the present invention is not limited thereto. Equivalent substitutions or changes made by those skilled in the art based on the present invention are within the protection scope of the present invention. The protection scope of the present invention shall be subject to the claims.

Claims

1. An industrial robot cluster operating status intelligent monitoring and predictive maintenance system, characterized by: It includes a cloud main system and multiple subsystems, and the subsystems are correspondingly set with regional robot clusters; The cloud main system includes a core platform layer, a communication layer, a logic layer and a storage layer; The core platform layer is used to process computing tasks, coordinate data analysis and collaborative learning of each subsystem, and support efficient computing and task scheduling of the system; The communication layer is used to realize data transmission between the cloud main system and the subsystems, and ensure real-time synchronization and reliable transmission of data; The logic layer is used to receive abnormal data, similarity thresholds and similar area information from the subsystems, confirm the abnormal data, further confirm the similar areas according to the similarity thresholds, and at the same time be responsible for coordinating and starting cross-regional collaborative learning to promote collaborative optimization between similar areas; The storage layer is used to store abnormal data, historical monitoring data, similarity thresholds, similar area information and confirmed abnormal events from each subsystem for subsequent query, analysis and model update; The subsystem includes a regional communication layer, a regional logic layer and a regional storage layer. The regional communication layer is used to realize data transmission within the subsystem, between subsystems and between the subsystem and the cloud main system; The regional logic layer is provided with a data preprocessing module, a multi-source data fusion and alignment module, a regional anomaly monitoring module, a robot regional collaboration and optimization module and a predictive maintenance module; the data processing module is used to fill in missing values to ensure data integrity, and perform data cleaning, outlier processing and data standardization processing on the data after missing value filling; the multi-source data fusion and alignment module is used to align and normalize data from different sources; the regional anomaly monitoring module is used to capture abnormal behaviors; The robot regional collaboration and optimization module is used to identify the most similar area after detecting an anomaly, share abnormal data, and realize cross-regional collaborative learning and parameter optimization; the predictive maintenance module is used to predict the future device state to issue an early warning in advance; The regional storage layer is used to store robot sensor data.

2. The intelligent monitoring and predictive maintenance system for the operation status of industrial robot clusters according to claim 1 is characterized by: The method for the data preprocessing module to fill in missing values is: Where: X filled is the missing value to be filled; X LagI is the filling value obtained by Lagrange interpolation method; X nearest is the effective data point filling value obtained by the adjacent data filling method; X GraphSAGE is the effective data point filling value obtained by the GraphSAGE filling method; ω1 and ω2 are weights, and: ω1+ω2=1; The Lagrange interpolation method is: in: At time point t md Supplementary values ​​using Lagrangian filling strategy; and The first three time points t of the selected missing region are md ―3.t md -2 and t md -The data value corresponding to 1; The adjacent data filling method is: in: Yes mk The supplementary value obtained by the adjacent data filling strategy at the time point; t c is the time point at the center of the missing region data segment; s represents the length of the extracted data segment; The GraphSAGE filling method is: in: is predicted by Pred mk The supplementary value of the moment; is t of the pth layer mk Feature representation at a time point; The method for the data preprocessing module to perform outlier processing on the data after missing value filling is: calculate the first quartile (Q1) and the third quartile (Q3) of the data, that is: IQR = Q3 - Q1 Based on IQR, calculate the boundaries of outliers: x < Q1 - 1.5×IQR or x > Q3 + 1.5×IQR; all points falling outside this range are considered outliers; if the outliers are considered to be caused by errors or accidental large deviations and the number is small, these outliers are directly deleted from the dataset; if there are a certain number of outliers, the average value of the overall data is used to replace the outliers; The method for the data preprocessing module to perform data standardization processing on the data after missing value filling is: convert the data into a form with zero mean and unit variance to eliminate the influence between data of different magnitudes. The formula is as follows: Where: Z is the data obtained by data standardization; X is the data after missing filling; μ and σ are the mean and standard deviation of the data respectively.

3. The intelligent monitoring and predictive maintenance system for the operation status of industrial robot clusters according to claim 1 is characterized by: The multi-source data fusion alignment module uses a dynamic time warping method to align the time series of multi-source data to eliminate the dimension, frequency and format differences of different robot data in the region. The method steps are as follows: S11: Constructing time series data: Organize the preprocessed data into the form of time series. Each time series contains a series of data points, and each data point corresponds to a timestamp. S12: Define reference template and test template: select one time series as the reference template and other time series as the test template and align them with the reference template; S13: Calculate the distance matrix: construct an n*m matrix grid, where n and m are the lengths of the reference template and the test template respectively; Each element (i, j) of the matrix represents the distance d between the i-th point in the reference template and the j-th point in the test template. i,j : Where: x i is the horizontal coordinate of the i-th point in the reference template; y j is the ordinate of the jth point in the test template; S14: DTM method: Given two time series P and Q of length LP and LQ respectively: P=(P1,…,P i ,…,P LP ) Q=(q1,…,q i ,…,q LQ ) Where: P i represents the value of the i-th data point in the time series P; q i Represents the value of the i-th data point in the time series Q; The alignment between P and Q is represented by a matching path W, which is expressed as: W=(w1,…,w l ,…,w k );w l =(α l ,β l ),k≥max(LP,LQ),1≤α l ≤LP,1≤β l ≤LQ Among them: (α l ,β l ) represents the αth l The value matches the βth l Value; w l Indicates the path matched in step l; The goal of the DTW method is to find the optimal matching path W so that the cumulative distance The minimum is achieved under the following three constraints: (1) Boundary constraint: This constraint restricts the path to start at (1,1) and end at (LP,LQ) when aligning sequences, that is: (α1,β1)＝(1,1) <h2 style=";text-align:left;direction:ltr">(α<h2 style=";text-align:left;direction:ltr"> l <h2 style=";text-align:left;direction:ltr"> ,β<h2 style=";text-align:left;direction:ltr"> l <h2 style=";text-align:left;direction:ltr"> )=(LP,LQ) (2) Continuity constraint: This constraint restricts the temporally changing curved path when aligning sequences. Under this condition, the path must move forward one step at a time, that is: l ―α l+1 ≤1 and β l ―β l+1 ≤1; (3) Monotonicity constraint: This condition preserves the time order of the points and restricts the path to move forward without decreasing, that is: α l ≥α l+1 And β l ≥β l+1 ; Assume D∈R LP×LQ Represents the cumulative distance, then the global minimum cumulative distance can be obtained through the following dynamic programming: D i,j =C i,j +min(D i―1,j ,D i―1,j―1 ,D i,j―1 ) Where: Initial value D 1,1 =C 1,1 ; The DTW distance between two sequences P and Q is expressed as DTW(P,Q), which is equivalent to D LP,LQ ,The optimal alignment path can be obtained by backtracking in the dynamic programming process.

4. The intelligent monitoring and predictive maintenance system for the operation status of industrial robot clusters according to claim 1 is characterized in that: The regional anomaly monitoring module combines the ETS model and the GAT-GRU model to comprehensively analyze the operating status of the industrial robot cluster, accurately detect and predict abnormal behaviors, and use an optimized fusion loss function to efficiently identify and warn of potential faults, providing reliable support for maintenance decisions and stable operation of the production line. The GAT-GRU model includes a graph attention network GAT and a gated recurrent unit GRU; the graph attention network GAT dynamically calculates the importance weights between robot features and time through an attention mechanism, and combines the dual-channel design of feature GAT and time GAT to capture the complex spatial and temporal dependencies of industrial robot cluster data; The gated recurrent unit GRU takes the graph embedding vector generated by the graph attention network GAT as input, and the gated recurrent unit GRU network dynamically adjusts the hidden state by updating the gate and resetting the gate based on the time series modeling process.

5. The intelligent monitoring and predictive maintenance system for the operation status of industrial robot clusters according to claim 4 is characterized by: The ETS model predicts future data points through exponential smoothing. The principle is: Smoothing equation: in: is the predicted value for the next time step; y t is the current observation value; is the current predicted value; T t is the trend term; α is the smoothing coefficient, and 0<α<1; Trend Adjustment: Where: T t+1 is the trend component of the next time step; β is the trend smoothing parameter; Seasonal Adjustment: Where: S t+m is the seasonal component after m steps; γ is the seasonal smoothing parameter; and m is the seasonal period.

6. The intelligent monitoring and predictive maintenance system for the operation status of industrial robot clusters according to claim 4 is characterized by: The method of the graph attention network GAT to capture the complex spatial and temporal dependencies of industrial robot cluster data is: Based on feature GAT: the number of key parameter features n inside the robot is taken as a node, the length of the time series intercepted by the sliding window function is taken as the number of features in each node, and the attention weight is calculated: in, is the attention coefficient between feature GAT node i and adjacent node j; LeakyReLU is a nonlinear activation function; W Fe is the weight matrix based on feature GAT; α is the learned weight vector; || represents the connection operation; h i and h j They represent the feature vectors of node i and node j in the feature GAT, respectively, representing all key parameter features of node i and node j; Use the softmax function to normalize the attention weights of the features within the group: in: is the normalized attention weight between node i and its neighboring node j in the feature GAT; N(i) is the set of neighboring nodes of node i in the feature GAT; Use the attention weights to perform weighted averaging on the features and update the feature representation: in: It is the overall influence of other nodes on node i based on the feature GAT; Based on time GAT: The length l intercepted by each sliding window function is taken as a node, the key parameter feature number n is taken as the feature in each node, and the learning parameter is adjusted to γ ​​and the weight matrix is ​​adjusted to W Ti ; The weight normalization is calculated through the softmax function, and the attention weight is used to update the node representation: in: It is the overall influence of other nodes on node i in the temporal GAT; is the normalized attention weight between node i and its neighboring node j in the temporal GAT; is the feature vector of node j in the time-based GAT, representing all key parameter features of node j; Combining the outputs of parallel feature-based GAT and the output of time-based GAT Fusion is the output of the graph attention network GAT 7. The intelligent monitoring and predictive maintenance system for the operation status of industrial robot clusters according to claim 4 is characterized by: The principle of the gated recurrent unit GRU is: Update Gate: z t =σ(W z ·[h t―1 ,x t ]+b z ) Where: z t is the update gate at time step t, controlling the previous hidden state; σ is the sigmoid function; W z is the weight matrix of the update gate; h t―1 is the hidden state of the previous time step; x t is the input of the current time step; b z is the bias term; Reset the gate: r t =σ(W r ·[h t―1 ,x t ]+b r ) Where: r t It is the reset gate, which determines how much information of the previous state is forgotten; Candidate hidden states: in: is a candidate hidden state; W h is the weight matrix of the candidate hidden state; b h is the bias term; * represents the element-wise product, meaning that the output of the reset gate affects which parts of the hidden state should be retained; Final hidden state: Where: h t is the hidden state at the current time step t, which is used for prediction or further processing; Prediction output: GRU’s final hidden state h t It will be converted into the final output prediction through a fully connected layer Where: W o and b o are the weights and biases of the output layer.

8. The intelligent monitoring and predictive maintenance system for the operation status of industrial robot clusters according to claim 4 is characterized by: Set the prediction output of the ETS model to The predicted output of the GAT-GRU model is The true observed value is y t , then the fusion loss function is defined as: L=ε·L ETS +(1−ε)·L GRU Where: ε is a weight parameter, and 0<ε<1, which is used to control the contribution ratio of the ETS model and the GAT-GRU model to the total loss; L ETS and L GRU are the prediction errors of the ETS model and the GAT-GRU model, respectively, expressed as: Where: y t is the actual value; is the predicted value calculated using the statistical model ETS; N is the total number of samples; in: is the predicted value obtained using the GAT-GRU model.

9. The intelligent monitoring and predictive maintenance system for the operation status of industrial robot clusters according to claim 1 is characterized by: The robot regional collaboration and optimization module identifies the most similar region after detecting an anomaly, shares anomaly data, and implements cross-region collaborative learning and parameter optimization in the following steps: S21: Similarity calculation: Assume that area A contains n robots, denoted as A1, A2, ...A n , region B contains m robots, denoted as B1, B2, …B m ; then robot A i and robot B j The cosine similarity is: Where: cos(θ ij ) is the i-th robot A i With the jth robot B i Similarity of i,k and B j,k Robot A i and B i The value of the kth feature; d is the dimension of the feature vector; The similarities of all robot pairs are averaged to obtain the overall similarity between region A and region B: Where sim(A,B) is the average similarity between region A and region B; n and m represent the number of robots in region A and region B, respectively; S22: Collaborative learning mechanism: determine whether the average similarity sim(A,B) between region A and region B is higher than the set similarity threshold: if so, there is similarity between region A and region B, and the confirmed abnormal data is broadcast from region A to region B to trigger collaborative learning of region B; if not, there is no similarity between region A and region B; The dynamic update method of the similarity threshold is: Where: t is the similarity threshold at time step t; e t is the error of the current time step, that is, the deviation between the current false alarm rate or missed alarm rate and the set value; K p is the proportionality factor, used to adjust the immediate impact of the error; K i is the integral coefficient, which is used to adjust the cumulative effect of the error; K d is the differential coefficient, which is used to adjust the rate of change of the error; is the cumulative error from the initial time step to the current time step; S23: Multi-objective optimization: Apply the NSGA-II multi-objective optimization algorithm to dynamically optimize the model parameters of each region. The objective function of the multi-objective optimization is: min f(θ)=(f1(θ),f2(θ)) Among them, θ represents the set of model parameters to be optimized; f1(θ) is the accuracy target of the anomaly monitoring model, and the optimization goal is to maximize the accuracy; f2(θ) is the response time target, and the optimization goal is to minimize the response time; Construct a Pareto optimal solution set to achieve a balance between multiple objectives; select the optimal parameter combination θ in the Pareto optimal solution set * Used to update the model; S24: Dynamic parameter update: The loss function L(θ) is used to measure the prediction error of the model and is combined with the regularization term to prevent the model from overfitting: Where: L(θ) is the loss function, which is used to evaluate the prediction accuracy of the model; N is the number of samples, that is, the number of training data points used; y i is the actual observed value of the i-th sample; is the predicted value of the model for the i-th sample under parameter θ; λ is the regularization coefficient, which is used to control the influence of the regularization term on the loss and avoid overfitting of the model; Ω(θ) is the regularization term, which is used to penalize excessive parameter values; in the process of minimizing the loss function L(θ), the regional anomaly monitoring module of each region will update the parameters to enhance the monitoring accuracy while maintaining the stability of the model.

10. The industrial robot cluster operating status intelligent monitoring and predictive maintenance system according to claim 1, characterized in that: The method for predicting the future operating state of the industrial robot cluster in the predictive maintenance module is: Construct a TCN model and use it to predict the future operating status of the industrial robot cluster, and obtain the key parameter sequence that can characterize the robot status in the future; According to historical data and expert experience, the warning threshold range of each key parameter is set, and the warning threshold is divided into two levels, namely the first warning threshold and the second warning threshold; If the predicted value of the key parameter is greater than the set first-level warning threshold, a first-level warning is triggered; if the predicted value of the key parameter is between the first-level warning threshold and the second-level warning threshold, a second-level warning is triggered; or, The comprehensive scoring method is used to combine the warning signals of various parameters into a global warning signal, and the global warning index is defined as: Where: i is the importance weight of each parameter; is the predicted value of the i-th parameter; The second level warning threshold is set; When the global warning index CWI exceeds the set global warning threshold, a global warning signal is generated.

Images