Complex equipment data monitoring method and system based on knowledge graph and edge calculation

Abstract

The invention relates to the technical field of data monitoring, in particular to a complex equipment data monitoring method and system based on a knowledge graph and edge calculation. The method comprises the steps of multi-modal data acquisition and edge intelligent preprocessing; performing feature extraction on the preprocessed data; fusing multi-source heterogeneous data and constructing a dynamic knowledge graph; performing deep knowledge reasoning and layered fault early warning decision making; and performing self-optimization and knowledge closed-loop management based on early warning decision. According to the differential coding and self-adaptive compression algorithm of the edge layer, the data transmission quantity is reduced by 75%, the network bandwidth requirement is greatly reduced, and the system operation efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data monitoring, and in particular, to a complex equipment data monitoring method and system based on a knowledge graph and edge computing. Background Art

[0002] Currently, research in the field of complex equipment monitoring at home and abroad mainly focuses on the following directions: Cloud computing platforms are the most widely used technical routes at present. For example, a device health management system based on cloud computing processes massive monitoring data by constructing a distributed computing cluster. Although this solution has strong computing power, it has obvious limitations in practical applications: on the one hand, it is difficult to solve the problem of data transmission delay; on the other hand, when facing sudden failures, the response speed of cloud processing often cannot meet the real-time requirements.

[0003] Knowledge graph technology has become a research hotspot in recent years. Such as a device fault diagnosis method based on a knowledge graph, which realizes fault reasoning by constructing a device knowledge base. However, most existing solutions stay at the level of static knowledge representation and lack the ability to dynamically interact with real-time monitoring data. At the same time, these systems usually require complete device historical data as support, and for newly put into operation devices or sudden new fault modes, their diagnostic effects will significantly decline.

[0004] Edge computing technology provides a new idea for solving the above problems. Such as an edge intelligent monitoring device, which realizes data preprocessing by deploying lightweight algorithms at the device end. However, existing edge computing solutions generally have problems such as limited computing power and limited algorithm complexity, and it is difficult to handle fault diagnosis tasks that require complex reasoning.

[0005] Through the above analysis, it can be seen that the real-time bottleneck of complex equipment data monitoring and fault warning is manifested as the delay problem in the whole process of data acquisition, transmission, and processing. Taking a wind turbine as an example, the fault development of its key components often completes within dozens of milliseconds, while the response time of traditional monitoring systems is usually above the second level, which completely cannot meet the warning requirements. The knowledge fusion bottleneck is reflected in the insufficient ability to analyze the association of multi-source heterogeneous data. Existing monitoring systems often analyze parameters such as vibration, temperature, and current independently and lack an in-depth understanding of the mutual influence between parameters. For example, a bearing fault may simultaneously show abnormal vibration and temperature rise, but it is difficult for existing systems to establish a causal relationship between these two phenomena. The resource optimization bottleneck is mainly manifested in the unreasonable allocation of computing resources. On the one hand, the computing power of edge devices is not fully utilized; on the other hand, the cloud undertakes too many unnecessary computing tasks. This unreasonable resource allocation not only causes energy waste but also affects the overall performance of the system. Summary of the Invention

[0006] To solve the above-mentioned problems, the present invention provides a complex equipment data monitoring method and system based on a knowledge graph and edge computing.

[0007] In a first aspect, a complex equipment data monitoring method based on a knowledge graph and edge computing provided by the present invention adopts the following technical solutions: A complex equipment data monitoring method based on a knowledge graph and edge computing includes: Multi-modal data acquisition and edge intelligent preprocessing; Feature extraction from the preprocessed data; Multi-source heterogeneous data fusion and dynamic knowledge graph construction; Deep knowledge reasoning and hierarchical fault warning decision-making; Self-optimization based on warning decisions and knowledge closed-loop management.

[0008] Further, the multi-modal data acquisition and edge intelligent preprocessing include constructing a multi-modal data acquisition system based on a heterogeneous sensor network, deploying vibration, temperature, acoustic, and electrical parameter multi-type sensors at key parts of the equipment to form a dense monitoring network; adopting an adaptive sampling strategy to dynamically adjust the sampling frequency, and defining the calculation method of the equipment state change rate R ( t ) which is expressed as: Wherein, n represents the total number of monitoring parameters, represents the weight coefficient of the i th parameter, represents the value of the i th parameter at the t th moment, represents the sampling interval.

[0009] Further, the edge intelligent preprocessing includes, for the collected raw data, the edge node implementing a lightweight signal processing algorithm chain, including adaptive filtering, wavelet decomposition, and short-time Fourier transform. Among them, wavelet decomposition adopts a multi-resolution analysis method to decompose the signal into sub-signals of different frequency bands, which is expressed as: Wherein, is the scaling function, is the wavelet function, is the approximation coefficient, is the detail coefficient, j represents the decomposition level, k represents the time shift.

[0010] Further, the feature extraction of the preprocessed data includes using time-domain, frequency-domain, and time-frequency-domain feature extraction methods with optimized computational complexity in the feature extraction process. For different types of signals, kurtosis, peak factor, and spectral entropy sensitive feature indicators are calculated. At the same time, multi-scale analysis based on a sliding window is introduced to capture the trend changes of parameters. The mathematical representation of the sliding window analysis is as follows: where, w is the window length. For each window, statistical features are calculated and their changing trends are tracked: where, represents the feature extraction function, is the window step size, is the sampling interval.

[0011] Further, the multi-source heterogeneous data fusion and dynamic knowledge graph construction include deploying a distributed fog computing cluster between edge nodes and the cloud. The fog computing layer receives feature data streams from multiple edge nodes and first performs spatio-temporal alignment processing to solve the asynchrony and inconsistency problems of multi-source data. The spatio-temporal alignment uses an improved dynamic time warping algorithm and combines Kalman filtering for timestamp correction. The optimization objective function is: where, is the time offset, representing the time delay between different data sources, is the feature weight, represents the data source X in t the i th feature at time Y and the distance metric between the t + τ th feature at time j in the data source

[0012] Further, the multi-source heterogeneous data fusion and dynamic knowledge graph construction also include, after spatio-temporal alignment, using an information fusion framework based on Dempster-Shafer evidence theory to integrate feature evidence from different sources to achieve multi-modal data fusion, which is expressed as: where, represents the confidence of the set , represents the confidence assignment of the th data source to the set A , represents the total number of data sources, Represents the reliability weight of the th data source, which is dynamically adjusted to adapt to the changes in working conditions.

[0013] Furthermore, the multi-source heterogeneous data fusion and dynamic knowledge graph construction also include representing the topological relationship, functional dependence, and fault propagation path between equipment components using the semantic triple structure of entity-relationship-attribute, and based on the graph evolution mechanism of incremental learning, using semi-supervised learning methods to acquire new knowledge, fusing the results of equipment operation data mining and expert feedback, automatically identifying new entity associations through relation extraction algorithms, and using the remote supervision method for relation extraction, whose objective function is: Where, is the training set, is the probability of the relationship under the condition of the given entity pair , is the model parameter, is the regularization coefficient.

[0014] Furthermore, the deep knowledge reasoning and hierarchical fault warning decision-making include using the structured knowledge graph and real-time status data from the fog computing layer to construct a multi-layer hybrid architecture of deep learning and knowledge reasoning. The reasoning process combines induction and deduction, and realizes probability reasoning through the Markov Logic Network MLN. Its joint probability distribution is expressed as: Where, represents the joint probability of state x, Z represents the normalization factor, represents the number of times the formula is satisfied under state x.

[0015] Furthermore, the self-optimization and knowledge closed-loop management based on warning decision-making include defining a multi-dimensional evaluation index set to monitor the operation status of the system in real time, including warning accuracy, recall rate, timeliness, and resource utilization rate as key indicators, using the Analytic Hierarchy Process AHP to determine the weight vector and calculate the comprehensive performance index. The self-optimization mechanism uses the feature contribution degree analysis method to evaluate the contribution of each feature to fault identification by calculating the mutual information, and dynamically adjusts the feature weights and selection strategies, which is expressed as: Where, The feature X i and the fault class Y The mutual information value between them, represents the feature X i takes the value of x iand the probability distribution of the joint failure type is y , indicating the marginal probability that the feature X i takes the value x i . indicating the marginal probability that the failure type Y takes the value y .

[0016] In a second aspect, a complex equipment data monitoring system based on a knowledge graph and edge computing includes: A data acquisition module configured to perform multimodal data acquisition and edge intelligent preprocessing; A feature extraction module configured to extract features from the preprocessed data; A graph module configured to perform multi-source heterogeneous data fusion and construct a dynamic knowledge graph; An early warning module configured to perform in-depth knowledge reasoning and hierarchical fault early warning decision-making; An optimization module configured to perform self-optimization based on the early warning decision and knowledge closed-loop management.

[0017] In a third aspect, the present invention provides a computer-readable storage medium storing multiple instructions, and the instructions are adapted to be loaded and executed by a processor of a terminal device to perform the complex equipment data monitoring method based on a knowledge graph and edge computing.

[0018] In a fourth aspect, the present invention provides a terminal device including a processor and a computer-readable storage medium. The processor is used to implement each instruction; the computer-readable storage medium is used to store multiple instructions, and the instructions are adapted to be loaded and executed by the processor to perform the complex equipment data monitoring method based on a knowledge graph and edge computing.

[0019] In summary, the present invention has the following beneficial technical effects: The complex equipment data monitoring and hierarchical fault early warning system based on a knowledge graph and edge computing proposed by the present invention has significant technical advantages and application values. By deploying a lightweight analysis model at the edge layer, the system realizes millisecond-level data preprocessing and feature extraction. Compared with the traditional cloud centralized processing architecture, the data response delay is reduced by more than 85%, effectively meeting the real-time monitoring requirements under complex working conditions; at the same time, the differential coding and adaptive compression algorithms at the edge layer reduce the data transmission volume by 75%, greatly reducing the network bandwidth requirements and improving the system operation efficiency.

[0020] The dynamic knowledge graph middleware established by the system at the fog computing layer innovatively solves the problems of spatio-temporal alignment and semantic fusion of multi-source heterogeneous data. The data fusion accuracy rate has increased by 23%. Especially in the case of drastic changes in equipment working conditions or partial failure of sensors, the system can still maintain high data consistency, providing a reliable data basis for fault diagnosis. The knowledge reasoning engine based on deep reinforcement learning, combined with the digital twin model of the equipment's entire life cycle, enables the system to achieve a fault prediction accuracy rate of 92% under complex working conditions, an increase of about 15 percentage points compared with the existing technology; the average early warning lead time has been extended by 2.8 times, providing sufficient preparation time for maintenance decision-making and effectively avoiding sudden shutdown accidents.

[0021] The system's innovatively designed hierarchical early warning mechanism based on the fault propagation path significantly reduces the false alarm rate, significantly improves the accurate positioning ability of early warnings, greatly improves the average fault positioning accuracy, reduces the maintenance troubleshooting time, and improves the maintenance efficiency. The system can adaptively adjust the early warning strategy according to the severity, influence range, and evolution trend of faults, avoiding the flooding or lack of early warning information and realizing the reasonable allocation of early warning resources. The system has the ability of continuous learning. Through the incremental update and self-optimization mechanism of the knowledge graph, with the increase of operation time, the prediction accuracy shows a steady upward trend.

[0022] The system's hierarchical early warning mechanism and emergency response strategy effectively reduce the equipment safety accident rate. Especially in high-risk working conditions, the system's early warning function can detect potential safety risk events in advance, providing strong protection for personnel and equipment safety. The system adopts a modular design, supports the rapid adaptation of different types of equipment, significantly reduces the deployment cost, and improves the system's application scope and promotion value.

[0023] In summary, the present invention realizes the closed-loop management of complex equipment's entire life cycle data and hierarchical fault early warning by constructing an intelligent collaborative architecture of "edge perception - cloud cognition". While improving the real-time performance, accuracy, and reliability of the system, it significantly reduces the equipment maintenance cost, improves the equipment operation efficiency, and provides a new generation of intelligent solutions with significant practical value for the predictive maintenance of high-end equipment. Description of the Drawings

[0024] Figure 1 is a schematic diagram of a complex equipment data monitoring method based on a knowledge graph and edge computing in Embodiment 1 of the present invention: Figure 2 is a comparison chart of the fault early warning accuracy rate in Embodiment 1 of the present invention; Figure 3 is a comparison chart of the fault early warning lead time in Embodiment 1 of the present invention; Figure 4 is a comparison chart of the system response time in Embodiment 1 of the present invention; Figure 5 It is the comparison chart of the data compression ratio in Embodiment 1 of the present invention. Specific Embodiment

[0025] The present invention will be further described in detail below with reference to the accompanying drawings.

[0026] Embodiment 1 Refer to Figure 1 , a complex equipment data monitoring method based on a knowledge graph and edge computing in this embodiment, includes: Multi-modal data collection and edge intelligent preprocessing; Feature extraction is performed on the preprocessed data; Multi-source heterogeneous data fusion and dynamic knowledge graph construction; Deep knowledge reasoning and hierarchical fault warning decision-making; Self-optimization based on warning decisions and knowledge closed-loop management.

[0027] Specifically: Step S1, multi-modal data collection and edge intelligent preprocessing: This step realizes the full-range real-time collection and intelligent front-end processing of the operation state data of complex equipment. First, a multi-modal data collection system based on a heterogeneous sensor network is constructed, and various types of sensors such as vibration, temperature, acoustics, and electrical parameters are deployed at key parts of the equipment to form a dense monitoring network. These sensors are connected to the edge computing node through the industrial field bus to achieve the centralized aggregation of data. The edge computing node is based on an embedded computing platform, equipped with a dedicated digital signal processing chip and a field programmable gate array, and has strong real-time data processing capabilities. To adapt to different operating conditions, the system designs an adaptive sampling strategy, and the sampling frequency can be dynamically adjusted. The formula is as follows: Among them, represents the actual sampling frequency at time t, represents the basic sampling frequency, R ( t ) represents the equipment state change rate, indicating the severity of the change in the equipment operation parameters, represents the adjustment coefficient; Define the calculation method of the equipment state change rate R ( t ) as: Among them, n represents the total number of monitoring parameters, represents the weight coefficient of the i th parameter, represents the i th parameter att The value of the moment represents the sampling interval. This adaptive sampling strategy can reduce the sampling frequency to save resources when the device state is stable, and increase the sampling frequency to capture more details when the state changes rapidly.

[0028] For the collected raw data, the edge node implements a lightweight signal processing algorithm chain, including adaptive filtering, wavelet decomposition, and short-time Fourier transform, etc., to remove environmental noise and sensor drift interference. The mathematical expression of the adaptive filter is: where is the filtered signal, is the k th filter coefficient, is the input signal, M is the filter order. The filter coefficients are dynamically updated by the least mean square error (LMS) algorithm: where is the learning rate, is the estimation error, defined as , is the desired response.

[0029] Wavelet decomposition uses the multi-resolution analysis method to decompose the signal into sub-signals of different frequency bands. The formula is as follows: where is the scaling function, is the wavelet function, is the approximation coefficient, is the detail coefficient. j represents the decomposition level, k represents the time translation; Short-time Fourier transform (STFT) is used to analyze the time-frequency characteristics of the signal. The formula is as follows: where is the window function, is the time offset, is the angular frequency. For edge computing, Hamming window or rectangular window is usually used to reduce the computational burden; In the feature extraction stage, time-domain, frequency-domain, and time-frequency-domain feature extraction methods with optimized computational complexity are adopted to calculate sensitive feature indicators such as kurtosis, peak factor, and spectral entropy for different types of signals. At the same time, multi-scale analysis based on a sliding window is introduced to capture the trend change of parameters. The mathematical representation of the sliding window analysis is: Among them, w is the window length. For each window, statistical features are calculated and their changing trends are tracked: Among them, represents the feature extraction function, is the window step size, is the sampling interval; To reduce the communication load, the edge layer also implements feature dimensionality reduction and differential coding compression based on principal component analysis, and the data compression rate can reach more than 85% without losing key information. Principal component analysis (PCA) is achieved through eigenvalue decomposition of the covariance matrix, and the specific formula is as follows: Among them, is the covariance matrix, is the eigenvalue, is the corresponding eigenvector.

[0030] Differential coding compression is based on the difference representation of adjacent sampling points, and the formula is as follows: For signals with slow changes, the differences are usually small and can be represented with fewer bits. In actual implementation, an adaptive quantization method is adopted to further improve the compression effect, and the formula is as follows: Among them, is the quantization function, is the adaptive quantization step size, which is dynamically adjusted according to the local variance of the signal.

[0031] Step S2, Multi-source heterogeneous data fusion and dynamic knowledge graph construction: This step realizes the multi-source heterogeneous data fusion and the dynamic construction of the equipment knowledge graph based on the fog computing layer. First, a distributed fog computing cluster is deployed between the edge nodes and the cloud, adopting a containerized microservice architecture to ensure the scalability and flexibility of data processing. The fog computing layer receives the feature data streams from multiple edge nodes and first performs spatio-temporal alignment processing to solve the problems of asynchrony and inconsistency of multi-source data. Spatio-temporal alignment adopts an improved dynamic time warping algorithm (DTW), combined with Kalman filtering for timestamp correction, and its core optimization objective function is: Among them, is the time offset, representing the time delay between different data sources, is the feature weight, represents the data source X in t thei a feature and the data source Y at the moment t + τ the j distance metric between features; For data streams with inconsistent frequencies, the system uses an adaptive interpolation algorithm for resampling to ensure data continuity and consistency. After spatio-temporal alignment, the system performs multi-modal data fusion, adopting an information fusion framework based on Dempster-Shafer evidence theory, and integrating feature evidence from different sources through a confidence assignment function. The specific formula is as follows: where, represents the confidence of the set , represents the confidence assignment of the th data source to the set A , represents the total number of data sources, represents the reliability weight of the th data source, which is dynamically adjusted to adapt to working condition changes; is the conflict metric, calculated as follows: where, and are the basic probability assignments of two evidence sources to sets $B$ and $C$ respectively, and the summation range is all pairs of sets with empty intersections; To dynamically adjust the data source weights, the system defines a reliability evaluation function: where, represents the historical accuracy of the data source , represents the current signal quality, represents the consistency metric with other data sources; The combination rule of Dempster-Shafer evidence theory is used to integrate multiple evidence sources, and the formula is as follows: where, represents the basic probability assignment to the set after combination, and represent the basic probability assignments of two evidence sources to the sets and respectively.

[0032] For the case of multiple (more than two) evidence sources, it is achieved by gradually combining them in pairs, and the formula is as follows: Among them, represents the Dempster combination operator.

[0033] On this basis, the system constructs a multi-level dynamic knowledge graph, and the knowledge graph uses the semantic triple structure of "entity-relationship-attribute" (s, r, o) to represent the topological relationship, functional dependence, and fault propagation path among equipment components. The initialization of the knowledge graph integrates the equipment design model, historical maintenance records, and expert experience rules. By using an ontology modeling tool to construct a domain vocabulary and concept hierarchy, the knowledge graph can be formally represented as: Among them, is the entity set, representing equipment components, sensors, fault modes, etc. is the relationship set, defining various associations between entities. is the attribute set, describing the characteristics of entities. is the attribute value range; To realize the dynamic update and self-evolution of the knowledge graph, the system designs a graph evolution mechanism based on incremental learning, and the formula is as follows: Among them, represents the state of the knowledge graph at time t, represents the state of the knowledge graph at time t+1, represents the knowledge increment at time t, such as newly added entities, relationships, and attributes; The acquisition of new knowledge adopts a semi-supervised learning method, which fuses the results of equipment operation data mining and expert feedback, and automatically identifies new entity associations through a relationship extraction algorithm. The relationship extraction adopts a remote supervision method, and its objective function is: Among them, is the training set, is the given entity pair under the condition of relationship probability, is the model parameter, is the regularization coefficient; In specific implementation, a multi-layer neural network model is adopted, and the formula is as follows: Among them, and are the vector representations of the subject and object entities respectively, Denotes vector concatenation, and are network parameters, is the activation function, is the given subject entity s and object entity o Under the conditions, the relationship r Probability distribution; The knowledge graph also contains a complex set of constraint rules , used to verify the consistency and validity of new knowledge. To support efficient querying, the system uses a graph database to implement knowledge storage and designs a multi-granularity index structure to support complex path search and pattern matching. Each entity node in the knowledge graph is dynamically mapped to the real-time data stream, and the knowledge and data are deeply integrated through the attribute update function. The specific formula is as follows: Among them, Represents the entity e At t The attribute value at the moment, f Represents the attribute update function, Represents the entity e At t The relevant data set at the moment.

[0034] Step S3, Deep knowledge reasoning and hierarchical fault warning decision: This step realizes deep knowledge reasoning based on the cloud and intelligent hierarchical fault warning decision. A high-performance computing cluster is deployed in the cloud, and a distributed parallel computing framework is adopted to provide powerful computing power support for complex knowledge reasoning and pattern recognition. First, use the structured knowledge graph and real-time status data from the fog computing layer to construct a multi-layer deep learning and knowledge reasoning hybrid architecture. The system innovatively designs an inference engine that combines knowledge graph embedding and deep reinforcement learning, maps the entities and relationships in the knowledge graph to a low-dimensional continuous vector space, and is represented as and . Among them, represents the vectors of entity e and entity r, W e and W r Are embedding matrices. On this basis, the system uses a graph neural network to encode the topological structure of the equipment system, and the node representation is iteratively updated through the message passing mechanism. The specific formula is as follows: Among them, Represents the feature of node v at layer l+1, Represents the activation function, Represents the weight matrix of the l-th layer, AGGREGATEDenotes the neighbor node feature aggregation function, Denotes the feature representation of node u at the l-th layer, N ( v ) Denotes the neighbor set of node v ; The reasoning process combines induction and deduction. Probabilistic reasoning is achieved through a Markov Logic Network (MLN), and its joint probability distribution is expressed as: where, Denotes the joint probability of state x, Z Denotes the normalization factor, Denotes the number of times the formula is satisfied under state x. The Markov Logic Network can seamlessly integrate logical rules and probability models, making it suitable for handling uncertain reasoning in knowledge graphs; The rules in MLN are provided by domain experts and automatically discovered through a data-driven approach. Automatic rule discovery uses an association rule mining algorithm to calculate the confidence and support of the rules: where, and Are sets of predicates, Is the size of the dataset. The system retains rules whose confidence and support both exceed the threshold as candidate rules for MLN.

[0035] Rule weight learning uses the contrast divergence algorithm, and the formula is as follows: where, Denotes the i th logical formula F i The weight parameter in the Markov Logic Network. The higher the weight, the more important or the more likely the logical rule is to be true. Is the probability of the observed data x ;

[0036] Denotes in the observed data x , the i th logical formula F i The number of times it is satisfied; Denotes the expected number of times the logical formula F i is satisfied under the current model parameters w; The weight update formula is: where, Is obtained by sampling using the MCMC method Expected estimation is the learning rate

[0037] Specifically, the system has developed a causal reasoning mechanism for fault diagnosis. By combining Bayesian networks with Granger causality tests, it identifies the causal relationships between parameter anomalies and constructs a fault propagation graph. In the graph, nodes represent abnormal features and edges represent the intensity of causal influence

[0038] For complex fault patterns, the system adopts a deep reinforcement learning framework, models the fault diagnosis process as a Markov decision process (MDP), and optimizes the diagnostic strategy through a policy network The design of the reward function includes multi-dimensional objectives such as diagnostic accuracy, time efficiency, and cost control. Based on the inference results, the system has implemented an innovative hierarchical fault warning decision-making mechanism, dividing the warning level into a three-level system of "monitoring - warning - emergency". The system calculates the risk value through a risk assessment function, and the formula is as follows where represents the risk value of the fault f at t time, represents the severity of the fault represents the probability of the fault occurring given the current data conditions represents the scope of influence The warning trigger adopts a multi-threshold dynamic adjustment mechanism. According to the operating conditions of the equipment, environmental conditions, and historical reliability data, it adaptively adjusts the warning threshold, and the formula is as follows where represents the warning threshold at time t represents the basic threshold is the adjustment factor related to the current working condition c, historical performance h, and environmental condition e Each level of warning is equipped with a detailed response strategy library. By combining decision trees with case-based reasoning, it generates targeted disposal suggestions, including multi-dimensional measures such as parameter adjustment, load control, and maintenance plans. The warning effect is continuously optimized through a closed-loop feedback mechanism, and the knowledge base and model parameters are updated using maintenance records and manual feedback to achieve the continuous evolution of the system

[0039] Step S4, System self-optimization and knowledge closed-loop management This step realizes the adaptive optimization of the early warning system and the closed-loop management of equipment full life cycle knowledge. A cross-level linkage self-evolution mechanism is constructed to ensure that the system can continuously adapt to the changes in the equipment operation environment and new fault modes. First, the system establishes an all-round performance evaluation framework by defining a multi-dimensional evaluation index set Real-time monitor the system operation status, including key indicators such as early warning accuracy rate, recall rate, timeliness, resource utilization rate, etc. Each indicator is normalized through a normalization function, and the formula is as follows: Among them, represents the i-th performance indicator after normalization, represents the original indicator value, represents the indicator i 's historical minimum and maximum values; The analytic hierarchy process (AHP) is used to determine the weight vector and calculate the comprehensive performance index, and the formula is as follows: Among them, PI represents the comprehensive performance index, represents the weight of the i-th indicator, represents the i-th performance indicator after normalization, k represents the total number of indicators; The system regularly executes the self-diagnosis process. When PI is lower than the set threshold or a performance decline trend is detected, the self-optimization mechanism is triggered. The self-optimization mechanism first adopts the feature contribution degree analysis method, evaluates the contribution of each feature to fault identification by calculating the mutual information, and dynamically adjusts the feature weights and selection strategies. The formula is as follows: For model parameter optimization, the system designs a hierarchical optimization framework, combines Bayesian optimization and evolutionary algorithms, and finds the optimal model configuration through the hyperparameter optimization function. The formula is as follows: Among them, represents the optimal model parameters, represents the loss function, represents the validation data set, represents the model parameters.

[0040] To adapt to equipment aging and working condition drift, the system realizes a model update mechanism that combines incremental learning and transfer learning. The formula is as follows: Among them, represents the updated model, Represents the current model, Represents the new dataset, U Represents the update operator while maintaining historical knowledge and integrating new data; The knowledge graph evolution adopts a two - layer update strategy: at the micro level, incremental updates of knowledge units are achieved through entity - relationship update functions, and the formula is as follows: Among them, Represents the amount of knowledge graph update at the micro level, f Represents the update function, Represents the measured data, Represents the existing knowledge; At the macro level, it is through the ontology reconstruction algorithm. The specific formula is as follows: Among them, Represents the updated ontology, Represents the original ontology, R Represents the reconstruction algorithm, Represents the newly added knowledge; In particular, the system innovatively introduces a knowledge distillation mechanism based on the case library, converts the implicit knowledge accumulated in maintenance practice into explicit rules, and models through the case expression where F Represents the fault feature set, S is the scenario description, A is the disposal action, R is the result evaluation. The system designs an interactive knowledge acquisition interface to support experts in inputting empirical knowledge through natural language or semi - structured templates, and extracts knowledge elements that conform to the ontology from the text T in accordance with the ontology O .

[0041] To achieve intelligent allocation of resources, the system adopts an edge - fog - cloud three - layer resource dynamic allocation mechanism, estimates future loads through a load prediction model , and optimizes the resource allocation strategy using a reinforcement learning framework. The state transition function is: Among them, Represents t the state at time Represents the resource allocation action, Represents the environmental factors; Step S5, Maintenance decision support and system integration application: This step realizes the maintenance decision-making support and industrial system integration application based on the early warning results. First, a multi-level maintenance decision-making support model is constructed to convert the fault early warning results into specific maintenance action suggestions. The system uses a risk assessment matrix to evaluate the fault risk level, and the formula is as follows: Where, S represents the severity of the fault, P represents the probability of the fault occurrence, D represents the detectability of the fault; According to the risk level, the system automatically generates maintenance suggestions, including three types of measures: emergency disposal, planned maintenance, and condition monitoring. For critical faults, the system provides case-based maintenance guidance, retrieves the historical case library through the similarity function, and provides a reference solution for maintenance personnel. The formula is as follows: Where, represents the comprehensive similarity between case C 1 and case C 2, and the value range is usually [0,1]; represents the weight coefficient of the i th feature, representing the importance of this feature in the similarity calculation, satisfying ; represents the similarity function of the i th feature, calculating the similarity degree between the features of case C 1 and the features of case C 2; and respectively represent the C th feature value of case C 1 and case The system also develops a maintenance resource optimization module to optimize the maintenance task sequencing and resource allocation through an integer programming model. The objective function is designed as: Where, represents the cost of executing the th maintenance task, including labor cost, material cost, equipment downtime cost, etc.; represents the decision variable, indicating whether to execute the th maintenance task, and the value is 0 or 1; Consider constraints such as personnel skills, tool availability, and task priorities. For enterprise-level application requirements, the system designs a standardized interface and integration framework to support seamless docking with industrial software platforms such as enterprise resource planning (ERP), manufacturing execution system (MES), and computerized maintenance management system (CMMS). The interface adopts the RESTful architecture and the OPC UA industrial communication protocol to ensure the real-time and reliability of data exchange. Through a secure mobile application, maintenance personnel can access device data and repair guidance on-site, improving repair efficiency. The system deployment adopts a modular design, supporting flexible expansion from a single-machine version to an enterprise-level distributed deployment to adapt to the application requirements of enterprises of different scales. Finally, the system provides a continuous improvement mechanism. Through maintenance feedback and effect evaluation, the early warning rules and decision-making models are continuously optimized to form a closed-loop equipment health management system. Through maintenance decision support and system integration applications, the present invention closely combines the fault early warning of complex equipment with daily operation and maintenance management, providing a practical overall solution for enterprises to achieve intelligent operation and maintenance of equipment.

[0042] Experimental verification: To verify the effectiveness of the "Complex Equipment Data Monitoring Method Based on Knowledge Graph and Edge Computing" of the present invention, a comprehensive simulation experiment evaluation system was designed. The experiment constructed a digital twin model of complex equipment based on the MATLAB environment, and simulated and tested five typical fault scenarios (bearing fault, gear crack, motor overheating, eccentricity fault, and looseness fault), and collected various types of sensing data such as vibration, temperature, current, acoustics, and speed. The experiment adopted a comparative research method, using traditional monitoring methods and the method of the present invention to process the same simulated fault data respectively, and focused on evaluating four key indicators: system response time, fault early warning accuracy rate, early warning lead time, and data compression rate, as Figure 2 、 Figure 3 、 Figure 4 and Figure 5 shown. Through a large number of repeated experiments and statistical analysis, the technical advantages of the present invention were quantitatively evaluated. The results show that the present invention is significantly superior to traditional methods in various performance indicators, especially in terms of real-time response ability and early warning lead time.

[0043] Embodiment 2 This embodiment provides a complex equipment data monitoring system based on a knowledge graph and edge computing, including: A data acquisition module, configured to: A computer-readable storage medium, in which multiple instructions are stored, and the instructions are adapted to be loaded and executed by a processor of a terminal device for the "Complex Equipment Data Monitoring Method Based on Knowledge Graph and Edge Computing".

[0044] A terminal device includes a processor and a computer-readable storage medium. The processor is used to implement each instruction; the computer-readable storage medium is used to store multiple instructions, and the instructions are adapted to be loaded and executed by the processor for the described method for monitoring complex equipment data based on a knowledge graph and edge computing.

[0045] The above are all preferred embodiments of the present invention, and the protection scope of the present invention is not limited thereby. Therefore, all equivalent changes made according to the structure, shape, and principle of the present invention shall be covered within the protection scope of the present invention.

Claims

1. A complex equipment data monitoring method based on a knowledge graph and edge computing, characterized in that Including: Multi-modal data acquisition and edge intelligent preprocessing; Feature extraction from the preprocessed data; Multi-source heterogeneous data fusion and dynamic knowledge graph construction; Deep knowledge reasoning and hierarchical fault warning decision-making; Self-optimization based on warning decision-making and knowledge closed-loop management.

2. The complex equipment data monitoring method based on a knowledge graph and edge computing according to claim 1, wherein The multi-modal data acquisition and edge intelligent preprocessing include constructing a multi-modal data acquisition system based on a heterogeneous sensor network, deploying multi-type sensors such as vibration, temperature, acoustics, and electrical parameters at key parts of the equipment to form a dense monitoring network; adopting an adaptive sampling strategy to dynamically adjust the sampling frequency, and defining the rate of change of the equipment state R ( t ) calculation method, expressed as: Among them, n represents the total number of monitoring parameters, represents the i weight coefficient of the th parameter, i represents the value of the t th parameter at the time, and represents the sampling interval.

3. A complex equipment data monitoring method based on a knowledge graph and edge computing according to claim 2, characterized in that, The edge intelligent preprocessing includes, for the collected raw data, the edge node implementing a lightweight signal processing algorithm chain, including adaptive filtering, wavelet decomposition, and short-time Fourier transform. Among them, wavelet decomposition uses a multi-resolution analysis method to decompose the signal into sub-signals of different frequency bands, expressed as: Among them, is a scaling function, is a wavelet function, are approximation coefficients, are detail coefficients, j represents the decomposition level, k represents time translation.

4. A complex equipment data monitoring method based on a knowledge graph and edge computing according to claim 3, characterized in that The feature extraction from the preprocessed data includes, in the feature extraction link, using time-domain, frequency-domain, and time-frequency domain feature extraction methods with optimized computational complexity, calculating kurtosis, peak factor, and spectral entropy sensitive feature indicators for different types of signals, and at the same time introducing multi-scale analysis based on a sliding window to capture parameter trend changes. The mathematical representation of the sliding window analysis is: Among them, w is the window length. For each window, statistical features are calculated and their changing trends are tracked: Among them, represents the feature extraction function, is the window step size, is the sampling interval.

5. The complex equipment data monitoring method based on a knowledge graph and edge computing according to claim 4, characterized in that, The multi-source heterogeneous data fusion and dynamic knowledge graph construction includes deploying a distributed fog computing cluster between the edge node and the cloud. The fog computing layer receives the feature data streams from multiple edge nodes and first performs spatio-temporal alignment processing to solve the problems of asynchrony and inconsistency of multi-source data. The spatio-temporal alignment uses an improved dynamic time warping algorithm and combines Kalman filtering for timestamp correction. The optimization objective function is: Among them, is the time offset, representing the time delay between different data sources. is the feature weight. represents the data source X at t the i th feature at time Y in the data source t + τ and the j th feature at time 6. The complex equipment data monitoring method based on a knowledge graph and edge computing according to claim 5, wherein, The multi-source heterogeneous data fusion and dynamic knowledge graph construction also includes, after spatio-temporal alignment, using an information fusion framework based on Dempster-Shafer evidence theory to integrate feature evidence from different sources through a confidence assignment function to achieve multi-modal data fusion, expressed as: Among them, represents the confidence level of the set , represents the confidence level assignment of the th data source to the set A , represents the total number of data sources represents the reliability weight of the th data source, which is dynamically adjusted to adapt to the changes in working conditions.

7. A complex equipment data monitoring method based on a knowledge graph and edge computing according to claim 6, characterized in that The multi-source heterogeneous data fusion and dynamic knowledge graph construction also includes representing the topological relationship, functional dependence, and fault propagation path between equipment components using an entity-relationship-attribute semantic triple structure, and based on an incremental learning-based graph evolution mechanism, using a semi-supervised learning method to acquire new knowledge, fusing the results of equipment operation data mining and expert feedback, and automatically identifying new entity associations through a relation extraction algorithm. The relation extraction uses a remote supervision method, and its objective function is: Among them, is the training set, is the given entity pair under the condition of probability of is the model parameter, is the regularization coefficient.

8. A complex equipment data monitoring method based on a knowledge graph and edge computing according to claim 7, characterized in that, The deep knowledge reasoning and hierarchical fault warning decision-making includes using the structured knowledge graph and real-time status data from the fog computing layer to construct a multi-layer deep learning and knowledge reasoning hybrid architecture. The reasoning process combines induction and deduction, and realizes probabilistic reasoning through a Markov logic network MLN. Its joint probability distribution is expressed as: wherein, represents the joint probability of state x, Z represents the normalization factor, represents the number of times the formula is satisfied under state x.

9. A complex equipment data monitoring method based on a knowledge graph and edge computing according to claim 8, characterized in that The self-optimization based on warning decision-making and knowledge closed-loop management includes real-time monitoring of the system operation status by defining a multi-dimensional evaluation index set, including warning accuracy, recall rate, timeliness, and resource utilization rate as key indicators, using the analytic hierarchy process AHP to determine the weight vector and calculate the comprehensive performance index. The self-optimization mechanism uses a feature contribution degree analysis method to evaluate the contribution of each feature to fault identification by calculating mutual information, and dynamically adjusts the feature weights and selection strategies, expressed as: Among them, feature X i and the mutual information value between the fault class Y and the fault type represents the feature X i takes the value x i and the fault type is y of the joint probability distribution represents the feature X i takes the value x i of the marginal probability represents the marginal probability of the fault type Y taking the value y of the marginal probability 10. A complex equipment data monitoring system based on a knowledge graph and edge computing, characterized in that, Including: A data acquisition module configured for multi-modal data acquisition and edge intelligent preprocessing; The feature extraction module is configured to extract features from the preprocessed data; The atlas module is configured for multi-source heterogeneous data fusion and dynamic knowledge graph construction; The early warning module is configured for deep knowledge reasoning and hierarchical fault early warning decision-making; The optimization module is configured for self-optimization based on early warning decisions and knowledge closed-loop management.

Images