Node fault intelligent diagnosis method and system of intelligent space sensor network

Abstract

The invention provides a node fault intelligent diagnosis method and system for an intelligent space sensor network, and the method comprises the steps: obtaining a real-time monitoring data set of all sensor nodes in a target sensor network, carrying out the state feature extraction of the real-time monitoring data set, generating a state feature set of each sensor node, and carrying out the detection of the state feature set of each sensor node; based on a preset fault diagnosis strategy model, carrying out multi-dimensional fault matching processing on the state feature set, determining a candidate fault type set of the sensing nodes, generating a node fault processing strategy set of the sensing nodes according to a strategy mapping relation between the candidate fault type set and a preset fault processing knowledge base, and sending the node fault processing strategy set to the fault diagnosis module; and performing node optimization operation on the fault nodes in the target sensor network based on the node fault processing strategy set, and feeding back optimized node operation parameters to a control terminal of the target sensor network. According to the method, the problem that the system stability is reduced due to traditional single-point repair is effectively avoided, and continuous and reliable operation of the overall performance of the network after fault repair is ensured.

Description

Technical Field

[0001] The present invention relates to the technical fields of data processing and fault diagnosis, and particularly to a method and system for intelligent fault diagnosis of nodes in an intelligent space sensing network. Background Art

[0002] In the technical field of intelligent space sensing networks, node fault diagnosis is the core link to ensure the reliable operation of the network. The key lies in achieving accurate fault location and repair through multi-dimensional data analysis. Existing technologies usually adopt a single-dimensional diagnosis mechanism. For example, they separately monitor abnormal device operation parameters or network communication interruption events for fault determination, or perform linear compensation processing on environmental interference through a fixed threshold method. Although such methods can achieve basic diagnosis in a single fault scenario, in practical applications, when facing complex faults caused by the coupling of hardware performance degradation, network topology fluctuations, and environmental interference, there are serious diagnostic blind spots: the correlation features between abnormal device loads and deteriorated communication links caused by traditional single-dimensional data collection are lost, resulting in misjudging the network performance degradation induced by hardware faults as independent events; at the same time, the static environmental interference compensation mechanism cannot capture the non-linear effects of the superposition of temperature gradients and electromagnetic noise on node stability, causing a high missed detection rate of intermittent faults. In addition, the existing step-by-step repair strategy lacks temporal coordination during the hardware reset and network reconstruction processes, easily causing parameter calibration conflicts and resulting in a decrease rather than an increase in the system stability after node optimization. How to achieve feature fusion of multi-source heterogeneous data, cross-dimensional accurate identification of complex faults, and adaptive collaborative execution of repair strategies has become the key technical bottleneck for improving the fault diagnosis efficiency of intelligent space sensing networks. Summary of the Invention

[0003] In view of this, at least one embodiment of the present invention provides a method and system for intelligent fault diagnosis of nodes in an intelligent space sensing network.

[0004] The technical solution of the embodiment of the present invention is realized as follows: On the one hand, an embodiment of the present invention provides a method for intelligent fault diagnosis of nodes in an intelligent space sensing network, including: Obtaining a real-time monitoring data set of all sensing nodes in the target sensing network, where the real-time monitoring data set includes device operation parameters, network communication parameters, and environmental interference parameters of each sensing node; Performing state feature extraction processing on the real-time monitoring data set to generate a state feature set for each sensing node, where the state feature set includes device operation state features, network connection stability features, and environmental interference correlation features; Based on a preset fault diagnosis strategy model, perform multi-dimensional fault matching processing on the state feature set to determine a candidate fault type set of the sensing node, where the candidate fault type set includes at least one candidate fault type having an associated relationship with the state feature set; According to the policy mapping relationship between the candidate fault type set and a preset fault processing knowledge base, generate a node fault processing policy set of the sensing node, where the node fault processing policy set includes an optimal processing policy for each candidate fault type; Based on the node fault processing policy set, perform node optimization operations on the faulty nodes in the target sensing network, and feedback the optimized node operation parameters to the control terminal of the target sensing network.

[0005] On the other hand, an embodiment of the present invention provides a computer system, including a memory and a processor, where the memory stores a computer program that can run on the processor, and when the processor executes the program, the steps in the above method are implemented.

[0006] The node fault intelligent diagnosis method for an intelligent space sensing network provided by the present invention constructs a multi-dimensional monitoring data set by synchronously collecting device operation parameters, network communication parameters, and environmental interference parameters in real time, and generates a state feature set including device operation state features, network connection stability features, and environmental interference association features based on state feature extraction processing. The fault diagnosis strategy model is used to perform multi-dimensional fault matching processing on the above features to accurately identify a composite fault type set under the combined action of hardware performance degradation, network link anomalies, and environmental interference. Furthermore, a node optimization strategy integrating hardware parameter calibration, network topology reconstruction, and environmental resistance enhancement is generated in combination with the fault processing knowledge base, realizing cross-dimensional collaborative diagnosis and adaptive repair of the fault causes of sensing nodes under complex working conditions; through the joint modeling of device energy consumption trends, network packet loss correlation matrices, and interference superposition effects during the feature extraction process, the fault diagnosis process can simultaneously capture the non-linear correlation relationships between the internal hardware state evolution of the node, the external network communication quality fluctuations, and the environmental interference propagation path, significantly improving the detection sensitivity to intermittent faults and hidden faults; at the same time, the generation and execution mechanism of the node optimization strategy effectively avoids the problem of system stability degradation caused by traditional single-point repair through the timing collaborative optimization of hardware reset instructions and communication link reconstruction protocols, ensuring the continuous and reliable operation of the overall network performance after fault repair.

[0007] It should be understood that the above general description and subsequent detailed description are only exemplary and explanatory, and do not limit the technical solutions of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1Schematic diagram of the implementation process of an intelligent node fault diagnosis method for an intelligent space sensing network provided by an embodiment of the present invention.

[0009] Figure 2 Schematic diagram of the hardware entity of a computer system provided by an embodiment of the present invention. Detailed implementation manners

[0010] An embodiment of the present invention provides an intelligent node fault diagnosis method for an intelligent space sensing network, and this method can be executed by a processor of a computer system. Among them, the computer system may refer to devices with data processing capabilities such as servers, laptop computers, tablet computers, desktop computers, etc.

[0011] Figure 1 Schematic diagram of the implementation process of an intelligent node fault diagnosis method for an intelligent space sensing network provided by an embodiment of the present invention, as Figure 1 shown, this method includes the following steps: Step S100: Obtain a real-time monitoring data set of all sensing nodes in the target sensing network, and the real-time monitoring data set includes device operation parameters, network communication parameters, and environmental interference parameters of each sensing node.

[0012] Device operation parameters are various data describing the operation state of the sensing node itself, such as the energy consumption of the node, the load condition of the hardware components, etc. Energy consumption reflects the energy consumed by the node during operation, and the load condition reflects the working intensity of the hardware components. Network communication parameters are data related to the communication of the sensing node in the network, such as packet loss rate, signal strength, communication interruption frequency, etc. The packet loss rate represents the proportion of lost data packets during data transmission, the signal strength reflects the strength of the communication signal between nodes, and the communication interruption frequency reflects the frequency of communication connection interruption. Environmental interference parameters refer to the relevant parameters of the environment where the sensing node is located that interfere with it, such as temperature gradient, electromagnetic noise, humidity, etc. The temperature gradient represents the rate of change of temperature in space, electromagnetic noise will interfere with the communication and operation of the node, and the change of humidity may affect the attenuation of the signal.

[0013] The specific implementation method of obtaining the real-time monitoring data set can be to install various sensors on the sensing nodes to collect corresponding data. For device operation parameters, current sensors and voltage sensors can be used to measure the energy consumption of the nodes, and load sensors can be used to monitor the load conditions of hardware components. For network communication parameters, network monitoring software can be used to count data such as packet loss rate, signal strength, and communication interruption frequency. For environmental interference parameters, temperature sensors can be used to measure temperature, electromagnetic sensors can be used to detect electromagnetic noise, and humidity sensors can be used to obtain humidity data. For example, in a sensing network of an intelligent building, temperature sensors, humidity sensors, current sensors, etc. will be installed on the sensing nodes of each room. Through these sensors, device operation parameters, network communication parameters, and environmental interference parameters are collected in real time, and then these data are transmitted to the data center for aggregation to form a real-time monitoring data set.

[0014] Step S200: Perform state feature extraction processing on the real-time monitoring data set to generate a state feature set for each sensing node, where the state feature set includes device operation state features, network connection stability features, and environmental interference correlation features.

[0015] The state feature extraction processing is to analyze and process the real-time monitoring data set to extract key features that can reflect the state of the sensing node. The device operation state features are the features that describe the operation status of the sensing node device, such as the energy consumption change trend based on time series and the hardware component load fluctuation curve. The energy consumption change trend reflects the change of the node's energy consumption over time, and the hardware component load fluctuation curve reflects the dynamic change of the hardware component load. The network connection stability features are used to measure the connection stability degree of the sensing node in the network, including the correlation matrix between the packet loss rate and the signal strength and the communication interruption frequency distribution map. The correlation matrix represents the mutual relationship between the packet loss rate and the signal strength, and the communication interruption frequency distribution map shows the distribution of communication interruptions in different time periods. The environmental interference correlation features are the features that reflect the influence of environmental interference on the sensing node, including the interference superposition effect of the temperature gradient and the electromagnetic noise and the quantization influence coefficient of the humidity change on the signal attenuation. The interference superposition effect reflects the influence of the combined action of the temperature gradient and the electromagnetic noise on the node, and the quantization influence coefficient is used to measure the specific influence degree of the humidity change on the signal attenuation.

[0016] As an implementation method, in step S200, performing state feature extraction processing on the real-time monitoring data set to generate a state feature set for each sensing node may specifically include the following steps S210 to S25 : Step S210: Perform periodic fluctuation pattern recognition processing on the device operation parameters to generate the device operation state features, where the device operation state features include the energy consumption change trend based on time series and the hardware component load fluctuation curve.

[0017] The periodic fluctuation pattern recognition process analyzes the device operation parameters to identify the periodic fluctuation patterns therein. The energy consumption change trend based on time series refers to arranging the energy consumption data of the nodes in chronological order and analyzing its change trend over time. The hardware component load fluctuation curve shows the change of the load data of the hardware components over time in the form of a curve.

[0018] In specific implementation, time series analysis algorithms such as ARIMA (Autoregressive Integrated Moving Average Model) can be used to process the device operation parameters. First, preprocess the collected device operation parameters, including operations such as data cleaning and normalization, to remove noise and outliers. Then, use the ARIMA model to model and predict the energy consumption data and the hardware component load data to obtain the energy consumption change trend and the hardware component load fluctuation curve. For example, in a sensing network in an industrial production environment, perform periodic fluctuation pattern recognition processing on the device operation parameters of a certain sensing node. Collect the energy consumption data and the hardware component load data of this node within a week, and use the ARIMA model for analysis. It is found that the energy consumption shows a periodic change trend at different time periods of each day, and there is also a corresponding fluctuation curve for the hardware component load. Through these characteristics, it can be judged whether the device operation status of the node is normal.

[0019] Step S220: Perform link anomaly event correlation analysis processing on the network communication parameters, and extract the network connection stability features, where the network connection stability features include the correlation matrix between the packet loss rate and the signal strength and the communication interruption frequency distribution map.

[0020] The link anomaly event correlation analysis process analyzes the link anomaly events in the network communication parameters to find out their correlation relationships. The correlation matrix between the packet loss rate and the signal strength is a two-dimensional matrix used to represent the correlation degree between the packet loss rate and the signal strength at different values. The communication interruption frequency distribution map is a graph that statistically shows the communication interruption frequency according to time or other dimensions.

[0021] In specific implementation, an association rule mining algorithm, such as the Apriori algorithm, can be used to perform link anomaly event association analysis and processing. First, the collected network communication parameters are discretized, and the packet loss rate and signal strength are divided into different intervals. Then, the Apriori algorithm is used to mine the association rules between the packet loss rate and the signal strength to generate an association matrix. For the communication interruption frequency distribution map, statistical analysis methods can be used to count the time and frequency of communication interruptions and draw the distribution map. For example, in a wireless sensor network, link anomaly event association analysis and processing are performed on the network communication parameters of a certain sensor node. The packet loss rate, signal strength, and communication interruption frequency data of this node within one month are collected, and the association rule that when the signal strength is lower than a certain threshold, the packet loss rate will increase significantly is mined using the Apriori algorithm to generate an association matrix. At the same time, the time and frequency of communication interruptions are counted, and the communication interruption frequency distribution map is drawn. Through these features, the network connection stability of the node can be evaluated.

[0022] Step S230: Perform multi-source interference coupling analysis and processing on the environmental interference parameters to construct the environmental interference association features, where the environmental interference association features include the interference superposition effect of the temperature gradient and electromagnetic noise and the quantization influence coefficient of humidity change on signal attenuation.

[0023] Multi-source interference coupling analysis and processing analyze multiple interference sources in the environmental interference parameters and consider their coupling effects. The interference superposition effect of the temperature gradient and electromagnetic noise refers to the impact on the sensor node when the temperature gradient and electromagnetic noise act together. The quantization influence coefficient of humidity change on signal attenuation is a numerical value used to measure the specific impact degree of humidity change on signal attenuation.

[0024] In specific implementation, a multiple regression analysis method can be used to perform multi-source interference coupling analysis. First, historical data of environmental interference parameters are collected, including temperature gradient, electromagnetic noise, humidity, etc. Then, a multiple regression model is established, with signal attenuation as the dependent variable and temperature gradient, electromagnetic noise, and humidity as independent variables. The parameters of the model are estimated by the least squares method to obtain the quantization influence coefficient of humidity change on signal attenuation. For the interference superposition effect of temperature gradient and electromagnetic noise, the method of experimental design can be used to conduct experiments under different temperature gradients and electromagnetic noise conditions, measure the performance indicators of the nodes, and analyze their superposition effect. For example, in a smart home sensing network, multi-source interference coupling analysis is performed on the environmental interference parameters of a certain sensing node. The temperature gradient, electromagnetic noise, humidity, and signal attenuation data of the node under different environmental conditions are collected, and a model is established using the multiple regression analysis method. The quantization influence coefficient that the signal attenuation increases by 0.5 dB when the humidity increases by 1% is obtained. At the same time, through experimental design, the interference superposition effect that the communication performance of the node significantly decreases under the superposition condition of high temperature and strong electromagnetic noise is analyzed.

[0025] Step S240: Perform time-domain alignment processing on the energy consumption change trend and the hardware component load fluctuation curve to generate a first fusion feature vector; perform spatial mapping processing on the correlation matrix and the communication interruption frequency distribution map to generate a second fusion feature vector; perform weighted superposition processing on the interference superposition effect and the quantization influence coefficient to generate a third fusion feature vector.

[0026] Time-domain alignment processing aligns the energy consumption change trend and the hardware component load fluctuation curve in the time dimension so that they have corresponding values at the same time points. The first fusion feature vector is a feature vector obtained by fusing the energy consumption change trend and the hardware component load fluctuation curve after time-domain alignment. Spatial mapping processing maps the correlation matrix and the communication interruption frequency distribution map in the spatial dimension so that they can be represented in the same space. The second fusion feature vector is a feature vector obtained by fusing the correlation matrix and the communication interruption frequency distribution map after spatial mapping. Weighted superposition processing assigns different weights to the interference superposition effect and the quantization influence coefficient, and then superimposes them. The third fusion feature vector is a feature vector obtained by fusing the interference superposition effect and the quantization influence coefficient after weighted superposition.

[0027] In specific implementation, for time-domain alignment processing, a time synchronization algorithm such as NTP (Network Time Protocol) can be used to ensure that the timestamps of the energy consumption change trend and the load fluctuation curve of the hardware components are consistent. Then, the aligned data is normalized and then vector concatenation is performed to generate the first fusion feature vector. For spatial mapping processing, a spatial transformation algorithm such as PCA (Principal Component Analysis) can be used to map the correlation matrix and the communication interruption frequency distribution map into a low-dimensional space, and then vector concatenation is performed to generate the second fusion feature vector. For weight superposition processing, the weights of the interference superposition effect and the quantization influence coefficient can be determined according to experience or experiments, and then they are weighted and summed to generate the third fusion feature vector. For example, in an intelligent agricultural sensing network, the features of a certain sensing node are fused. The NTP protocol is used to perform time-domain alignment on the energy consumption change trend and the load fluctuation curve of the hardware components, and then the normalized data is concatenated into the first fusion feature vector. The PCA algorithm is used to map the correlation matrix and the communication interruption frequency distribution map into a two-dimensional space and concatenate them into the second fusion feature vector. According to experiments, the weight of the interference superposition effect is determined to be 0.6, and the weight of the quantization influence coefficient is 0.4. They are weighted and summed to generate the third fusion feature vector.

[0028] Step S250: Generate the state feature set including multi-dimensional correlation indicators according to the feature complementary relationship among the first fusion feature vector, the second fusion feature vector and the third fusion feature vector.

[0029] The feature complementary relationship means that the first fusion feature vector, the second fusion feature vector and the third fusion feature vector each contain different information and can complement each other. The multi-dimensional correlation indicator means that the state feature set contains correlation information in multiple dimensions and can comprehensively reflect the state of the sensing node.

[0030] In specific implementation, a feature fusion algorithm such as a neural network fusion algorithm can be used to generate the state feature set. First, the first fusion feature vector, the second fusion feature vector and the third fusion feature vector are used as inputs and input into a multi-layer perceptron (MLP) neural network. The MLP neural network includes an input layer, a hidden layer and an output layer. The input layer receives the three fusion feature vectors, the hidden layer performs a non-linear transformation on the input, and the output layer outputs the state feature set including multi-dimensional correlation indicators. For example, in an intelligent transportation sensing network, the first fusion feature vector, the second fusion feature vector and the third fusion feature vector of a certain sensing node are input into an MLP neural network with two hidden layers. After training and learning, the neural network outputs a state feature set including multi-dimensional correlation indicators such as device operation, network connection and environmental interference. Through this state feature set, the state of the node can be more comprehensively understood.

[0031] Step S300: Based on a preset fault diagnosis strategy model, perform multi-dimensional fault matching processing on the state feature set to determine a candidate fault type set of the sensing node, where the candidate fault type set includes at least one candidate fault type having an association relationship with the state feature set.

[0032] The preset fault diagnosis strategy model is a pre-constructed model for diagnosing faults of sensing nodes, which includes the association relationships between various fault types and state features. The multi-dimensional fault matching processing analyzes the state feature set from multiple dimensions to find the fault types that match the state feature set. The candidate fault type set is a set of possible fault types determined according to the matching results.

[0033] As an implementation manner, in step S300, based on a preset fault diagnosis strategy model, perform multi-dimensional fault matching processing on the state feature set to determine a candidate fault type set of the sensing node, which may specifically include the following steps S310 to S350: Step S310: Input the first fusion feature vector into the hardware degradation analysis module of the fault diagnosis strategy model, and generate a hardware-related fault set by matching a preset hardware failure mode library, where the hardware failure mode library includes power module anomalies, sensor drift, and circuit aging feature patterns.

[0034] The hardware degradation analysis module is a module in the fault diagnosis strategy model specifically used for analyzing hardware degradation. The preset hardware failure mode library is a database containing the feature patterns of various hardware failure modes. Power module anomaly refers to the situation where the power module cannot work properly, such as unstable voltage, insufficient power, etc. Sensor drift refers to the phenomenon that the measured value of the sensor deviates. Circuit aging feature pattern refers to the feature pattern of the performance degradation of the circuit as the usage time increases.

[0035] Specifically, the hardware degradation analysis module can adopt a rule-based matching algorithm. First, compare the first fusion feature vector with each feature pattern in the hardware failure mode library and calculate the similarity between them. The similarity can be calculated using measurement methods such as Euclidean distance and cosine similarity. When the similarity exceeds a certain threshold, it is considered that the feature pattern matches the first fusion feature vector, and the corresponding hardware fault type is added to the hardware-related fault set. For example, in an intelligent medical sensing network, input the first fusion feature vector of a certain sensing node into the hardware degradation analysis module, and the module compares the first fusion feature vector with the power module anomaly, sensor drift, and circuit aging feature patterns in the hardware failure mode library. If the calculated similarity between the first fusion feature vector and the power module anomaly feature pattern is 0.8, exceeding the preset threshold of 0.7, then the power module anomaly is added to the hardware-related fault set.

[0036] Step S320: Input the second fusion feature vector into the network topology analysis module of the fault diagnosis strategy model, and generate a network-related fault set by identifying communication link breakage features and routing table anomaly features. The communication link breakage features include neighbor node unreachable events and data retransmission count mutation patterns.

[0037] The network topology analysis module is a module in the fault diagnosis strategy model used to analyze the network topology structure and communication situation. The communication link breakage features refer to the relevant features of communication link interruption. The neighbor node unreachable event means that the node cannot communicate with adjacent nodes. The data retransmission count mutation pattern refers to the situation where the data retransmission count suddenly increases. The routing table anomaly features refer to the features of incorrect or inconsistent information in the routing table.

[0038] In specific implementation, the network topology analysis module can adopt a machine learning classification algorithm, such as support vector machine (SVM). First, use historical data to train the SVM, with the second fusion feature vector as the input and the communication link breakage features and routing table anomaly features as the output categories. After training, input the current second fusion feature vector into the trained SVM, and judge whether there is a communication link breakage or routing table anomaly according to the output result. If so, add the corresponding network fault type to the network-related fault set. For example, in an intelligent grid sensing network, input the second fusion feature vector of a certain sensing node into the network topology analysis module. The module uses the trained SVM to classify the second fusion feature vector, judges that there is a neighbor node unreachable event, and adds the fault type related to communication link breakage to the network-related fault set.

[0039] Step S330: Input the third fusion feature vector into the environmental resistance analysis module of the fault diagnosis strategy model, and generate an environment-related fault set by analyzing the deviation between the interference superposition effect and the node anti-interference threshold. The node anti-interference threshold is adjusted according to the stable operation data under historical environmental parameters.

[0040] The environmental resistance analysis module is a module in the fault diagnosis strategy model used to analyze the node's resistance to environmental interference. The deviation between the interference superposition effect and the node anti-interference threshold refers to the difference between the actual value of the interference superposition effect and the anti-interference threshold that the node can withstand. The node anti-interference threshold is determined according to the stable operation data of the node under historical environmental parameters and will be adjusted as the environment changes.

[0041] In specific implementation, the environmental resistance analysis module can adopt a threshold comparison algorithm. First, compare the interference superposition effect value in the third fusion feature vector with the node anti-interference threshold. If the interference superposition effect value exceeds the node anti-interference threshold, it is considered that there is an environment-related fault, and the corresponding fault type is added to the environment-related fault set. For example, in an intelligent meteorological sensing network, the third fusion feature vector of a certain sensing node is input into the environmental resistance analysis module. The module compares the interference superposition effect value with the node anti-interference threshold adjusted according to historical environmental data, and finds that the interference superposition effect value exceeds the threshold, and adds the fault type caused by environmental interference to the environment-related fault set.

[0042] Step S340: Evaluate the fault coupling degree of the hardware-related fault set, the network-related fault set, and the environment-related fault set, and calculate the conditional triggering probability between any two fault types.

[0043] Fault coupling degree evaluation is to analyze the degree of mutual correlation between different fault types in the hardware-related fault set, the network-related fault set, and the environment-related fault set. Conditional triggering probability refers to the probability that another fault type occurs under the condition that one fault type occurs.

[0044] In specific implementation, a Bayesian network can be used to evaluate the fault coupling degree. First, construct a Bayesian network, use the fault types in the hardware-related fault set, the network-related fault set, and the environment-related fault set as nodes, and determine the conditional probability distribution between nodes according to historical fault data. Then, use the Bayesian inference algorithm to calculate the conditional triggering probability between any two fault types. For example, in an intelligent industrial sensing network, a Bayesian network is constructed using historical fault data, and the abnormal power supply module, communication link break, and environmental interference fault are used as nodes. Through the Bayesian inference algorithm, the conditional triggering probability that the communication link breaks under the condition that the power supply module is abnormal is calculated to be 0.3.

[0045] Step S350: Perform combined optimization processing on the fault types with strong correlation relationships according to the conditional triggering probability, and generate the candidate fault type set including the main fault type and the derivative fault type.

[0046] A strong correlation relationship means that the conditional triggering probability between two fault types is relatively high. Combined optimization processing is to combine and optimize the fault types with strong correlation relationships to determine the main fault type and the derivative fault type. The main fault type is the main reason for the occurrence of other faults, and the derivative fault type is other faults caused by the main fault type.

[0047] In specific implementation, a clustering algorithm, such as the K-Means algorithm, can be used for combined optimization processing. First, a similarity matrix between fault types is constructed based on the conditional trigger probability. Then, the K-Means algorithm is used to cluster the fault types, and the fault types with higher conditional trigger probabilities are grouped into one category. In each category, the fault type with the maximum conditional trigger probability is selected as the main fault type, and other fault types are used as derivative fault types. For example, in an intelligent logistics sensing network, a similarity matrix is constructed based on the conditional trigger probability evaluated according to the fault coupling degree, and the K-Means algorithm is used to cluster the fault types into two categories. In one of the categories, the conditional trigger probability of the abnormal power supply module is the largest, which is used as the main fault type, and the communication link break and sensor drift are used as derivative fault types, generating a candidate fault type set including the main fault type and derivative fault types.

[0048] Step S400: Generate a node fault handling strategy set for the sensing node according to the policy mapping relationship between the candidate fault type set and a preset fault handling knowledge base, where the node fault handling strategy set includes an optimal handling strategy for each candidate fault type.

[0049] The preset fault handling knowledge base is a database storing handling strategies corresponding to various fault types. The policy mapping relationship refers to the corresponding relationship between the fault types in the candidate fault type set and the handling strategies in the fault handling knowledge base. The node fault handling strategy set is a set of optimal handling strategies for each candidate fault type generated according to the policy mapping relationship.

[0050] As an implementation manner, in step S400, generating the node fault handling strategy set for the sensing node according to the policy mapping relationship between the candidate fault type set and the preset fault handling knowledge base may specifically include the following steps S410 to S440: Step S410: Retrieve a benchmark handling strategy set corresponding to the main fault type from the fault handling knowledge base, where the benchmark handling strategy set includes a hardware reset instruction, a communication link reconstruction protocol, and an environment adaptive calibration scheme.

[0051] The benchmark handling strategy set is a series of basic handling strategies formulated in advance for the main fault type. The hardware reset instruction is an instruction used to reset the hardware device to restore it to the initial state. The communication link reconstruction protocol is a protocol used to re-establish the communication link to ensure normal data transmission. The environment adaptive calibration scheme is a scheme for automatically adjusting node parameters according to environmental changes to adapt to the environment.

[0052] In specific implementation, a keyword matching algorithm can be used to retrieve a set of benchmark processing strategies corresponding to the main fault type from the fault handling knowledge base. The name of the main fault type is used as a keyword to search in the fault handling knowledge base, and the processing strategies containing this keyword are found and added to the set of benchmark processing strategies. For example, in an intelligent education sensing network, the main fault type is abnormal power module. Using the keyword matching algorithm to search in the fault handling knowledge base for processing strategies containing "abnormal power module", the hardware reset instruction, the communication link reconstruction protocol, and the environment adaptive calibration scheme are added to the set of benchmark processing strategies.

[0053] Step S420: Perform strategy derivation processing on the set of benchmark processing strategies according to the derived fault type: Embed voltage compensation parameters for the characteristics of circuit aging in the hardware reset instruction; add a path optimization rule based on the load status of neighbor nodes to the communication link reconstruction protocol; configure an interference shielding threshold in the environment adaptive calibration scheme.

[0054] Strategy derivation processing is to further optimize and expand the set of benchmark processing strategies according to the derived fault type. The voltage compensation parameter for the characteristics of circuit aging is a parameter set to compensate for the voltage drop caused by circuit aging. The path optimization rule based on the load status of neighbor nodes is a rule for selecting the optimal path according to the load conditions of neighbor nodes when re - establishing the communication link. The interference shielding threshold is a threshold for shielding environmental interference.

[0055] In specific implementation, for the hardware reset instruction, according to the analysis result of the characteristics of circuit aging, determine the specific value of the voltage compensation parameter and embed it into the hardware reset instruction. For the communication link reconstruction protocol, by monitoring the load status of neighbor nodes, formulate a path optimization rule and add it to the communication link reconstruction protocol. For the environment adaptive calibration scheme, configure the interference shielding threshold according to the type and intensity of environmental interference. For example, in an intelligent tourism sensing network, the derived fault types include circuit aging and unstable communication link. For the hardware reset instruction, after analyzing the characteristics of circuit aging, determine that the voltage compensation parameter is 5V and embed it into the hardware reset instruction. For the communication link reconstruction protocol, after monitoring the load conditions of neighbor nodes, formulate the path optimization rule as selecting the neighbor node with the lightest load as the communication path and add it to the communication link reconstruction protocol. For the environment adaptive calibration scheme, configure the interference shielding threshold as 10dB according to the intensity of electromagnetic noise.

[0056] Step S430: Evaluate the execution priority of the derived processing strategies. The execution priority evaluation is sorted based on the product index of the strategy execution time and the fault repair probability.

[0057] Execution priority evaluation sorts the derived processing strategies and determines their execution order. Strategy execution time refers to the time required to execute a specific processing strategy. Fault repair probability refers to the probability that a specific processing strategy will successfully repair a fault. The product metric is the product of strategy execution time and fault repair probability.

[0058] In specific implementations, historical data can be used to calculate the execution time and fault recovery probability of each processing strategy. Then, a product index is calculated for each processing strategy, and the strategies are ranked in ascending order of product index. For example, in an intelligent financial sensor network, there are three derived processing strategies: Strategy A, Strategy B, and Strategy C. Historical data statistics show that Strategy A's execution time is 10 minutes and its fault recovery probability is 0.8; Strategy B's execution time is 15 minutes and its fault recovery probability is 0.6; and Strategy C's execution time is 20 minutes and its fault recovery probability is 0.5. The calculated product index for Strategy A is 8, Strategy B's is 9, and Strategy C's is 10. The strategies are ranked in ascending order of product index: Strategy A, Strategy B, and Strategy C.

[0059] Step S440: Selecting a processing strategy that meets a preset repair success rate according to the sorting result to generate the node fault processing strategy set, and configuring execution condition constraints and a rollback mechanism for each processing strategy.

[0060] The preset repair success rate is the minimum probability that a pre-defined processing strategy will successfully repair a fault. Execution constraints are the conditions that must be met to execute a processing strategy. A rollback mechanism is a mechanism that restores a node to its pre-execution state if a processing strategy fails.

[0061] During specific implementation, processing strategies are sequentially selected from the sorting result until the cumulative repair success rate of the selected processing strategy reaches the preset repair success rate. The selected processing strategies are added to the node fault handling strategy set. For each processing strategy, execution condition constraints are configured according to its characteristics and requirements. For example, for a hardware reset instruction, the execution condition constraint can be that the hardware state of the node is normal. At the same time, a rollback mechanism is set for each processing strategy so that when the processing strategy fails to execute, the node can be restored to the state before execution. For example, in an intelligent entertainment sensing network, the preset repair success rate is 0.9. The sorting result is strategy A, strategy B, and strategy C. The fault repair probability of strategy A is 0.8, and the fault repair probability of strategy B is 0.6. First, select strategy A, and the cumulative repair success rate is 0.8, which does not reach the preset repair success rate. Then select strategy B, and the cumulative repair success rate is 0.8+(1 - 0.8)×0.6 = 0.92, which reaches the preset repair success rate. Add strategy A and strategy B to the node fault handling strategy set. Configure the execution condition constraint for strategy A as the hardware temperature of the node being within the normal range, and set a rollback mechanism for both strategy A and strategy B so that when the execution fails, the hardware configuration and communication parameters of the node are restored.

[0062] Step S500: Based on the node fault handling strategy set, perform a node optimization operation on the faulty nodes in the target sensing network, and feedback the optimized node operation parameters to the control terminal of the target sensing network.

[0063] The node optimization operation is an operation to repair and optimize faulty nodes according to the node fault handling strategy set. The optimized node operation parameters refer to the device operation parameters, network communication parameters, environmental interference parameters, etc. of the node after the node optimization operation. The control terminal is a terminal device used to monitor and manage the target sensing network.

[0064] As an implementation manner, in step S500, based on the node fault handling strategy set, performing a node optimization operation on the faulty nodes in the target sensing network may specifically include the following steps S510 to S550: Step S510: Select the target processing strategy with the highest priority according to the execution priority evaluation result, parse the hardware reset instruction in the target processing strategy, and inject the voltage compensation parameter.

[0065] The target processing strategy is the processing strategy with the highest priority selected from the node fault handling strategy set. Parsing the hardware reset instruction is to extract and understand the specific operation steps and parameters in the hardware reset instruction. Injecting the voltage compensation parameter is to add the previously configured voltage compensation parameter for the circuit aging characteristics to the hardware reset instruction.

[0066] In specific implementation, according to the execution priority evaluation result, the processing strategy with the highest priority is selected as the target processing strategy. The parsing algorithm is used to parse the hardware reset instruction in the target processing strategy to extract the reset hardware device and operation steps. Then, the voltage compensation parameter is injected into the hardware reset instruction. For example, in an intelligent energy sensing network, the execution priority evaluation result shows that strategy A has the highest priority, and strategy A is used as the target processing strategy. The hardware reset instruction in strategy A is parsed to obtain that the hardware device to be reset is the sensor module, and the operation steps are to turn off the power and then turn on the power after waiting for 5 seconds. The previously configured voltage compensation parameter of 3V is injected into the hardware reset instruction so that when the power is turned on, an additional 3V voltage compensation is provided for the sensor module.

[0067] Step S520: After performing the hardware reset operation on the faulty node, monitor the recovery status of the energy consumption change trend and the load fluctuation curve in real time. If the preset stable interval is not reached, trigger the communication link reconstruction protocol.

[0068] The recovery status of the energy consumption change trend and the load fluctuation curve refers to whether the energy consumption change trend and the load fluctuation curve return to the normal state after performing the hardware reset operation on the faulty node. The preset stable interval is the normal range of the energy consumption change trend and the load fluctuation curve set in advance. The communication link reconstruction protocol is the protocol configured previously for re - establishing the communication link.

[0069] In specific implementation, after performing the hardware reset operation on the faulty node, use sensors to monitor the energy consumption change trend and the load fluctuation curve in real time. Compare the monitored data with the preset stable interval. If the preset stable interval is not reached, trigger the communication link reconstruction protocol. For example, in an intelligent transportation sensing network, after performing the hardware reset operation on the faulty node, monitor the energy consumption change trend and the load fluctuation curve in real time. The preset stable interval is that the energy consumption change rate is within ±5%, and the fluctuation range of the load fluctuation curve is within ±10%. The monitored energy consumption change rate is 8%, exceeding the preset stable interval, and the communication link reconstruction protocol is triggered.

[0070] Step S530: Re - establish the data transmission link between the faulty node and its neighbor nodes according to the path optimization rule, and verify whether the packet loss rate drops to the preset communication quality threshold.

[0071] The path optimization rule is the path optimization rule configured previously based on the load status of neighbor nodes. The data transmission link is the link used for data transmission between the faulty node and its neighbor nodes. The preset communication quality threshold is the highest allowable value of the packet loss rate set in advance.

[0072] During specific implementation, according to the path optimization rule, the optimal neighbor node is selected as the target node for data transmission. The data transmission link between the faulty node and the neighbor node is re-established using the network protocol. After establishing the link, the packet loss rate is monitored and compared with the preset communication quality threshold. For example, in an intelligent industrial sensing network, the path optimization rule is to select the neighbor node with the lightest load as the communication path. The faulty node re-establishes the data transmission link with the neighbor node with the lightest load through the network protocol. After establishing the link, the monitored packet loss rate is 8%, and the preset communication quality threshold is 5%. The packet loss rate has not dropped to the preset communication quality threshold.

[0073] Step S540: If the packet loss rate is still higher than the communication quality threshold, activate the interference shielding threshold in the environment adaptive calibration scheme, and synchronously adjust the signal transmission power and receiving sensitivity parameters.

[0074] The interference shielding threshold is a previously configured threshold for shielding environmental interference. The signal transmission power refers to the power of the signal transmitted by the faulty node. The receiving sensitivity parameter refers to the sensitivity of the faulty node to receive signals.

[0075] During specific implementation, when the packet loss rate is still higher than the communication quality threshold, activate the interference shielding threshold in the environment adaptive calibration scheme. According to the requirements of the interference shielding threshold, synchronously adjust the signal transmission power and receiving sensitivity parameters. For example, in an intelligent agricultural sensing network, the packet loss rate is 8%, which is higher than the preset communication quality threshold of 5%. The activated interference shielding threshold in the environment adaptive calibration scheme is 10 dB. According to the requirements of the interference shielding threshold, increase the signal transmission power by 2 dB, and adjust the receiving sensitivity parameter to be able to receive signals with an intensity below 10 dB.

[0076] Step S550: Package the optimized node operating parameters and the network topology structure into a configuration update packet, and broadcast the configuration update packet to all associated nodes through the distributed synchronization mechanism of the target sensing network.

[0077] The optimized node operating parameters are the device operating parameters, network communication parameters, and environmental interference parameters, etc. of the faulty node after node optimization operations. The network topology structure is the connection relationship between nodes in the target sensing network. The configuration update packet is a data packet that packages the optimized node operating parameters and the network topology structure together. The distributed synchronization mechanism is a mechanism used to synchronize node configurations in the target sensing network.

[0078] During specific implementation, the optimized node operation parameters and network topology structure are sorted out and encapsulated to generate a configuration update package. Using the distributed synchronization mechanism of the target sensing network, the configuration update package is broadcast to all associated nodes. For example, in an intelligent medical sensing network, the optimized node operation parameters and network topology structure are encapsulated into a configuration update package in JSON format. Through the distributed synchronization mechanism of the target sensing network, the configuration update package is broadcast to all associated nodes related to the faulty node, enabling them to update their configuration information.

[0079] As an implementation manner, the method provided by the embodiments of the present invention further includes the following steps S560 to S5100: Step S560: After the broadcast of the configuration update package is completed, start a cross-node collaborative verification process: the neighbor node sends a verification data packet to the faulty node and records the end-to-end transmission delay.

[0080] The cross-node collaborative verification process is a process for verifying whether the node optimization operation is successful. The verification data packet is a data packet for verifying the communication performance of the node. The end-to-end transmission delay refers to the time required for the verification data packet to be sent from the neighbor node to the faulty node.

[0081] During specific implementation, after the broadcast of the configuration update package is completed, the neighbor node sends a verification data packet to the faulty node according to a preset rule. The sending time and receiving time of the verification data packet are recorded using a timestamp, and the end-to-end transmission delay is calculated. For example, in an intelligent education sensing network, after the broadcast of the configuration update package is completed, neighbor node A sends a verification data packet to faulty node B. Neighbor node A records the sending time as t1, and faulty node B records the receiving time as t2. The end-to-end transmission delay is t2 - t1.

[0082] Step S570: If the transmission delay exceeds the preset delay tolerance, it is determined that the current optimization operation has not completely repaired the communication link breakage characteristics in the network-related fault set, and the rollback mechanism is triggered to restore to the previous stable configuration.

[0083] The preset delay tolerance is the maximum allowable value of the end-to-end transmission delay set in advance. The rollback mechanism is a mechanism that restores the node to the state before execution when the execution of the previous configuration processing strategy fails.

[0084] During specific implementation, the calculated end-to-end transmission delay is compared with a preset delay tolerance. If the transmission delay exceeds the preset delay tolerance, it is determined that the current optimization operation has not fully repaired the communication link breakage feature, triggering a rollback mechanism to restore the node to the previous stable configuration. For example, in an intelligent tourism sensing network, the preset delay tolerance is 100 ms, and the calculated end-to-end transmission delay is 120 ms, exceeding the preset delay tolerance. It is determined that the current optimization operation has not fully repaired the communication link breakage feature, triggering a rollback mechanism to restore the hardware configuration and communication parameters of the node to the previous stable configuration.

[0085] Step S580: If the transmission delay meets the requirements, collect the real-time operation data of the faulty node to generate a verification feature set, and input the verification feature set into the fault diagnosis strategy model for secondary fault matching.

[0086] The verification feature set is a feature set generated based on the real-time operation data of the faulty node for verifying whether the fault is repaired. Secondary fault matching is to input the verification feature set into the fault diagnosis strategy model again for fault matching.

[0087] During specific implementation, when the transmission delay meets the requirements, use sensors to collect the real-time operation data of the faulty node, including device operation parameters, network communication parameters, and environmental interference parameters, etc. Perform feature extraction processing on these data to generate a verification feature set. Input the verification feature set into the fault diagnosis strategy model for secondary fault matching. For example, in an intelligent financial sensing network, the transmission delay is 80 ms, meeting the preset delay tolerance. Collect the real-time operation data of the faulty node, perform feature extraction processing on it to generate a verification feature set. Input the verification feature set into the fault diagnosis strategy model for secondary fault matching to check whether there are other fault types.

[0088] Step S590: When none of the fault types in the candidate fault type set exist in the secondary matching result, confirm that the node optimization operation is successful and persistently store the current configuration parameters in the fault handling knowledge base.

[0089] The secondary matching result refers to the result obtained after inputting the verification feature set into the fault diagnosis strategy model for secondary fault matching. Persistent storage is to save the current configuration parameters in the fault handling knowledge base for subsequent use.

[0090] In specific implementation, when none of the fault types in the candidate fault type set exists in the secondary matching result, it indicates that the node optimization operation is successful. The configuration parameters of the current node, including device operation parameters, network communication parameters, and environmental interference parameters, etc., are saved to the fault handling knowledge base. For example, in an intelligent entertainment sensing network, the secondary matching result shows that none of the fault types in the candidate fault type set exists. It is confirmed that the node optimization operation is successful, and the configuration parameters of the current node are saved to the fault handling knowledge base for reference when similar faults occur subsequently.

[0091] Step S5100: If a new fault type is detected, generate an incremental policy based on the similarity between the new fault type and the historical processing policies, and add the incremental policy to the node fault handling policy set.

[0092] The new fault type is a previously unseen fault type detected during the secondary fault matching process. Incremental policy generation is to generate a new processing policy according to the similarity between the new fault type and the historical processing policies. The incremental policy is the newly generated processing policy.

[0093] In specific implementation, when a new fault type is detected, use a similarity calculation algorithm to calculate the similarity between the new fault type and the fault types in the historical processing policies. Select the closest historical processing policy according to the similarity, modify and optimize it to generate an incremental policy. Add the incremental policy to the node fault handling policy set. For example, in an intelligent energy sensing network, a new fault type of sensor accuracy degradation is detected during the secondary fault matching. Use the cosine similarity algorithm to calculate the similarity between this fault type and the fault types in the historical processing policies, and find that the similarity with the sensor drift fault type is the highest. Modify and optimize the processing policy for the sensor drift fault, add steps for sensor calibration to generate an incremental policy. Add the incremental policy to the node fault handling policy set.

[0094] As an implementation manner, the method provided by the embodiments of the present invention further includes the following steps S5110 to S5150: Step S5110: After the broadcast of the configuration update packet is completed, obtain the collaborative verification data set of the fault node and its neighbor nodes, where the collaborative verification data set includes real-time monitoring results of the optimized device operation parameters, network communication parameters, and environmental interference parameters.

[0095] The collaborative verification data set is a data set used to verify the effect of the node optimization operation, and includes real-time monitoring results of the fault node and its neighbor nodes. The optimized device operation parameters, network communication parameters, and environmental interference parameters are the corresponding parameters of the node after the node optimization operation.

[0096] In specific implementation, after the broadcast of the configuration update package is completed, sensors and monitoring devices are used to obtain the real-time operation data of the faulty node and its neighbor nodes, including device operation parameters, network communication parameters, environmental interference parameters, etc. These data are sorted and summarized to generate a collaborative verification data set. For example, in an intelligent transportation sensing network, after the broadcast of the configuration update package is completed, a current sensor, network monitoring software, and environmental sensors are used to obtain the device operation parameters, network communication parameters, and environmental interference parameters of the faulty node and its neighbor nodes respectively. These data are sorted into a tabular collaborative verification data set.

[0097] Step S5120: Perform a fault elimination verification process on the collaborative verification data set: Input the real-time monitoring results into the fault diagnosis strategy model to regenerate a set of candidate fault types for verification.

[0098] The fault elimination verification process analyzes the collaborative verification data set to verify whether the node optimization operation has eliminated the fault. The set of candidate fault types for verification is a set of possible fault types regenerated based on the real-time monitoring results.

[0099] In specific implementation, the real-time monitoring results in the collaborative verification data set are input into the fault diagnosis strategy model, and according to the previous fault matching process, a set of candidate fault types for verification is regenerated. For example, in an intelligent industrial sensing network, the real-time monitoring results of the collaborative verification data set are input into the fault diagnosis strategy model, and after being processed by the hardware degradation analysis module, network topology analysis module, and environmental resistance analysis module, a set of candidate fault types for verification is regenerated.

[0100] Step S5130: When there is an intersection between the set of candidate fault types for verification and the set of candidate fault types, it is determined that the node optimization operation has not completely eliminated the target fault type, and an incremental strategy optimization process is triggered.

[0101] The incremental strategy optimization process is a process of further optimizing the processing strategy when the node optimization operation has not completely eliminated the target fault type.

[0102] In specific implementation, the set intersection algorithm is used to calculate the intersection of the set of candidate fault types for verification and the set of candidate fault types. If the intersection is not empty, it is determined that the node optimization operation has not completely eliminated the target fault type, and an incremental strategy optimization process is triggered. For example, in an intelligent agricultural sensing network, the set of candidate fault types for verification is {power module abnormal, communication link broken}, and the set of candidate fault types is {power module abnormal, sensor drift}. The calculated intersection is {power module abnormal}, and since the intersection is not empty, it is determined that the node optimization operation has not completely eliminated the target fault type, and an incremental strategy optimization process is triggered.

[0103] Step S5140: Based on the remaining fault types corresponding to the intersection, extract the optimized compensation strategies for historical handling failure cases from the fault handling knowledge base, and generate a compensatory node optimization instruction in combination with the state feature set.

[0104] The remaining fault types refer to the fault types in the intersection of the candidate fault type set for verification and the candidate fault type set. These fault types indicate the faults that are not completely eliminated after the node optimization operation. The optimized compensation strategies for historical handling failure cases are extracted from the cases stored in the fault handling knowledge base that have previously handled the same or similar faults but unsuccessfully, and are improvement strategies used to make up for the deficiencies of the previous handling strategies. The state feature set includes device operation state features, network connection stability features, and environmental interference correlation features, etc., which can reflect the current overall state of the node.

[0105] In specific implementation, first analyze the remaining fault types corresponding to the intersection to determine their fault characteristics and possible causes. Then, in the fault handling knowledge base, use methods such as keyword matching and similarity search to find historical handling failure cases related to the remaining fault types. For the found cases, extract the optimized compensation strategies, which may include adjusting hardware parameters, modifying communication protocols, enhancing environmental adaptability measures, etc. Next, in combination with the current node's state feature set, comprehensively consider the device operation situation, network connection status, and environmental interference factors of the node, and further adjust and optimize the extracted optimized compensation strategies to generate a compensatory node optimization instruction. For example, in an intelligent logistics sensing network, the remaining fault type is "abnormal power supply module". From the fault handling knowledge base, a historical handling failure case is found, and it is found that the fault is not resolved due to the unreasonable setting of the voltage regulation range of the power supply module. The extracted optimized compensation strategy is to expand the voltage regulation range and add voltage fluctuation monitoring and automatic adjustment mechanisms. In combination with the current node's state feature set, it is found that the device load is high and the environmental temperature is unstable. Further optimize the strategy, on the basis of expanding the voltage regulation range, dynamically adjust the voltage regulation parameters according to the device load and environmental temperature, and generate a compensatory node optimization instruction.

[0106] Step S5150: After executing the compensatory node optimization instruction, collect the verification data set again until there is no intersection between the candidate fault type set for verification and the candidate fault type set, and add the finally effective optimized strategy parameters and corresponding monitoring data to the incremental learning module of the fault handling knowledge base.

[0107] Executing the compensatory node optimization instruction is to perform further optimization operations on the faulty node according to the operation steps and parameters specified in the instruction. Re-collecting the verification data set is to re-obtain the collaborative verification data set of the faulty node and its neighbor nodes after executing the optimization instruction, including the real-time monitoring results of the optimized device operation parameters, network communication parameters, and environmental interference parameters. The incremental learning module is a part of the fault handling knowledge base, which is used to store new optimization strategy parameters and monitoring data for continuous learning and improvement of the fault handling strategy in the future.

[0108] In specific implementation, operate on the faulty node according to the compensatory node optimization instruction, such as adjusting the parameters of the hardware device, modifying the network configuration, starting the environment adaptation measures, etc. After the operation is completed, use sensors and monitoring devices to re-collect the real-time operation data of the faulty node and its neighbor nodes to generate a new verification data set. Input the new verification data set into the fault diagnosis strategy model to re-generate the set of candidate fault types for verification. Then, check whether there is an intersection between the set of candidate fault types for verification and the set of candidate fault types. If there is an intersection, it means that there are still residual faults unresolved, and it is necessary to execute the incremental strategy optimization process again to generate a new compensatory node optimization instruction and execute it. If there is no intersection, it indicates that the node optimization operation has successfully eliminated the target fault type. At this time, add the finally effective optimization strategy parameters, such as hardware configuration parameters, network protocol settings, environment adaptation thresholds, etc., and the corresponding monitoring data, such as device operation status data, network communication performance data, environmental interference parameters, etc., to the incremental learning module of the fault handling knowledge base. For example, in an intelligent medical sensing network, after executing the compensatory node optimization instruction, re-collect the verification data set, and generate the set of candidate fault types for verification through the fault diagnosis strategy model. After multiple iterative optimizations, finally, there is no intersection between the set of candidate fault types for verification and the set of candidate fault types. Add the finally adjusted hardware parameters, network communication protocol settings, and the monitored data such as device energy consumption, signal strength, and environmental temperature collected to the incremental learning module of the fault handling knowledge base.

[0109] As an implementation manner, the method provided by the embodiment of the present invention further includes the following steps S5131 to S5135: Step S5131: In the incremental strategy optimization process, real-time monitor the change trend of the environmental interference parameter. When it is detected that the interference source intensity exceeds the coverage range of the current interference shielding threshold, trigger the environmental resistance enhancement mode.

[0110] The change trend of environmental interference parameters refers to the variation of environmental interference parameters (such as temperature gradient, electromagnetic noise, humidity, etc.) over time. The interference source intensity refers to the intensity of the interference generated by interference sources (such as electromagnetic radiation sources, high-temperature areas, etc.). The current interference shielding threshold refers to the threshold currently set by the node for shielding environmental interference. The environmental resistance enhancement mode is a special working mode in which the node will take more powerful measures to resist environmental interference.

[0111] In specific implementation, in the incremental strategy optimization process, environmental sensors are used to monitor environmental interference parameters in real time. For example, a temperature sensor monitors the temperature gradient, an electromagnetic sensor monitors the electromagnetic noise intensity, and a humidity sensor monitors the humidity change, etc. The monitored data is analyzed to calculate the change trend of the interference parameters. For example, the change rate over a period of time is calculated to determine whether the interference intensity is increasing or decreasing. The current interference source intensity is compared with the current interference shielding threshold. If the interference source intensity exceeds the coverage range of the current interference shielding threshold, it indicates that the current interference shielding measures are insufficient to cope with environmental interference. At this time, the environmental resistance enhancement mode is triggered. For example, in a sensing network of an intelligent industrial workshop, in the incremental strategy optimization process, the electromagnetic noise intensity is monitored in real time through an electromagnetic sensor. When it is detected that the electromagnetic noise intensity suddenly increases and exceeds the currently set interference shielding threshold, the environmental resistance enhancement mode is triggered.

[0112] Step S5132: In the environmental resistance enhancement mode, reallocate the signal modulation scheme of the faulty node according to the interference source type: adopt a frequency band hopping modulation strategy for electromagnetic noise interference and enable a thermal stability compensation algorithm for temperature gradient interference.

[0113] The signal modulation scheme refers to the methods and ways of modulating signals. Different signal modulation schemes can improve the transmission performance of signals in different environments. The frequency band hopping modulation strategy is a signal modulation strategy that rapidly switches the transmission frequency band of the signal between different frequency bands to avoid electromagnetic noise interference in the target frequency band. The thermal stability compensation algorithm is an algorithm used to compensate for the influence of temperature gradient on signal transmission and device performance. It can dynamically adjust the parameters of the device according to temperature changes to maintain the stability of the device.

[0114] In specific implementation, first, by analyzing the environmental interference parameters, determine the type of interference source, whether it is electromagnetic noise interference, temperature gradient interference, or other types of interference. If it is electromagnetic noise interference, adopt the frequency band hopping modulation strategy. The implementation of this strategy can be achieved by pre-setting a group of available frequency bands. When it is detected that a certain frequency band is affected by electromagnetic noise interference, automatically switch to another frequency band for signal transmission. For example, in a wireless sensor network, pre-set 10 available frequency bands. When it is detected that frequency band 3 is severely affected by electromagnetic noise interference, switch the signal transmission to frequency band 7. If it is temperature gradient interference, enable the thermal stability compensation algorithm. This algorithm can dynamically adjust the working parameters of the device according to the temperature changes monitored by the temperature sensor in real time, such as adjusting the signal transmission power, adjusting the working frequency of the hardware components, etc., to compensate for the impact of the temperature gradient on the device performance. For example, when the temperature rises, appropriately reduce the signal transmission power to reduce the signal distortion caused by the temperature rise.

[0115] Step S5133: Reconstruct the physical layer communication protocol between the faulty node and its neighbor nodes based on the updated signal modulation scheme, and synchronously adjust the data frame length and the check code redundancy ratio.

[0116] The physical layer communication protocol refers to the rules and standards followed for communication at the physical layer, which stipulates the signal transmission method, coding method, modulation method, etc. The data frame length refers to the length of each data frame in data transmission, and the check code redundancy ratio refers to the proportion of the check code in the data frame. The check code is used to detect and correct errors in data transmission.

[0117] In specific implementation, reconstruct the physical layer communication protocol between the faulty node and its neighbor nodes according to the updated signal modulation scheme. For example, if the frequency band hopping modulation strategy is adopted, it is necessary to modify the frequency band selection and switching rules in the physical layer communication protocol; if the thermal stability compensation algorithm is enabled, it is necessary to adjust the signal parameters and device working mode in the protocol. At the same time, synchronously adjust the data frame length and the check code redundancy ratio. When the environmental interference increases, appropriately increasing the data frame length can improve the data transmission efficiency, but may increase the error rate. Therefore, it is necessary to correspondingly increase the check code redundancy ratio to improve the reliability of data transmission. The specific adjustment can be determined according to experiments and experience. For example, in a sensor network of an intelligent building, reconstruct the physical layer communication protocol according to the updated signal modulation scheme, change the original fixed frequency band selection rule to a dynamic frequency band hopping rule. At the same time, increase the data frame length from the original 100 bytes to 120 bytes, and increase the check code redundancy ratio from the original 10% to 15%.

[0118] Step S5134: collecting the reconstructed network communication parameters to generate an anti-interference performance evaluation index. When the evaluation index does not reach a preset resistance threshold, iteratively updating the parameter combination of the frequency band hopping modulation strategy and the thermal stability compensation algorithm.

[0119] The anti-interference performance evaluation index is used to assess a node's anti-interference performance. It is calculated by collecting and comprehensively calculating reconstructed network communication parameters, such as packet loss rate, signal strength, and bit error rate. The preset resistance threshold is a pre-set minimum requirement for anti-interference performance. The parameter combination of the band hopping modulation strategy and the thermal stability compensation algorithm refers to the combination of parameters such as the band switching rules and switching frequency in the band hopping modulation strategy, and the temperature compensation coefficient and parameter adjustment range in the thermal stability compensation algorithm.

[0120] In specific implementations, network monitoring equipment is used to collect reconstructed network communication parameters. For example, packet loss rate is calculated by counting the number of lost packets within a set time period, signal strength is measured using a signal strength sensor, and bit error rate is calculated by analyzing errors in data transmission. Based on the collected network communication parameters, an anti-interference performance evaluation index is calculated. For example, a weighted average method can be used to sum parameters such as packet loss rate, signal strength, and bit error rate according to preset weights to obtain a comprehensive anti-interference performance evaluation index. The calculated evaluation index is compared with a preset anti-interference threshold. If the evaluation index does not meet the preset anti-interference threshold, it indicates that the current parameter combination of the frequency band hopping modulation strategy and the thermal stability compensation algorithm does not meet the anti-interference requirements and requires iterative updating of the parameter combination. Optimization algorithms, such as genetic algorithms and particle swarm algorithms, can be used to search and optimize the parameter combination to find a more optimal parameter combination. For example, in an intelligent traffic sensor network, after collecting the reconstructed network communication parameters, the calculated anti-interference performance evaluation index is 0.7, and the preset anti-interference threshold is 0.8. The genetic algorithm is used to iteratively optimize the band switching frequency of the band hopping modulation strategy and the temperature compensation coefficient of the thermal stability compensation algorithm. After multiple iterations, a better set of parameter combinations is found, which improves the anti-interference performance evaluation index to 0.85.

[0121] Step S5135: Encapsulate the optimized parameter combination and the physical layer communication protocol into an environmental resistance enhancement package, and distribute it to the node group in the same type of interference area through the distributed synchronization mechanism.

[0122] The environmental resistance enhancement package is a data packet that encapsulates the optimized frequency hopping modulation strategy, the parameter combination of the thermal stability compensation algorithm, and the reconstructed physical layer communication protocol. The node group in the same type of interference area refers to a group of nodes that are affected by the same type of environmental interference (such as electromagnetic noise interference, temperature gradient interference, etc.). The distributed synchronization mechanism is a mechanism used to synchronize node configurations and data in the network.

[0123] In specific implementation, the optimized frequency hopping modulation strategy, the parameter combination of the thermal stability compensation algorithm, and the reconstructed physical layer communication protocol are sorted out and encapsulated to generate the environmental resistance enhancement package. This package can be stored in a set file format, such as JSON, XML, etc. Then, through the distributed synchronization mechanism, the environmental resistance enhancement package is directed and distributed to the node groups in the same type of interference area. During the distribution process, methods such as broadcasting and multicasting can be used to ensure that each node can receive the environmental resistance enhancement package. For example, in a sensing network of a large factory, the optimized parameter combination and the physical layer communication protocol are encapsulated into a JSON-format environmental resistance enhancement package. Through the distributed synchronization mechanism, this package is directed and distributed to the node group affected by electromagnetic noise interference, enabling these nodes to update their signal modulation schemes and physical layer communication protocols and improve their anti-interference capabilities.

[0124] As an implementation manner, the method provided by the embodiment of the present invention may further include the following steps S5136 to S51310: Step S5136: Deploy a cross-node collaborative maintenance mechanism in the node group in the same type of interference area, and periodically collect the state feature sets of each node in the group to generate a group health map.

[0125] The cross-node collaborative maintenance mechanism is a mechanism used to achieve collaborative maintenance and management in a node group. It can enable nodes to cooperate with each other to jointly cope with failures and environmental interferences. The group health map is a map used to intuitively display the overall health status of a node group. It is obtained by collecting the state feature sets of each node in the group, including device operation state features, network connection stability features, and environmental interference correlation features, and performing comprehensive analysis and visualization processing.

[0126] In specific implementation, a cross-node collaborative maintenance mechanism is established in the node group of the same type of interference area. The collaboration between nodes can be achieved by setting up a dedicated collaborative management node or adopting a distributed algorithm. The state feature sets of each node in the group are periodically collected, and the collection period can be set according to the actual situation, such as every hour, every day, etc. The collected state feature sets are comprehensively analyzed. For example, the average device operation parameters, network communication performance indicators, environmental interference intensity, etc. of the nodes in the group are calculated. The analysis results are visually displayed in the form of a graph to generate a group health graph. For example, in a sensing network of an intelligent city, a cross-node collaborative maintenance mechanism is deployed in the node group affected by temperature gradient interference. The state feature sets of each node in the group are collected every 6 hours, and indicators such as the average energy consumption, average packet loss rate, and average temperature gradient of the nodes are calculated. These indicators are displayed in the form of a heat map to generate a group health graph, and the health status of different nodes is represented by the depth of the color.

[0127] Step S5137: Perform topological vulnerability analysis on the group health graph to identify a set of critical nodes with overloaded communication links or unbalanced hardware loads.

[0128] Topological vulnerability analysis is to analyze the topological structure of the node group to find out the parts that are prone to failures or performance bottlenecks. Overloaded communication link means that the load of the communication link exceeds its carrying capacity, resulting in problems such as data transmission delay and packet loss. Unbalanced hardware load means that the load distribution of the hardware components of the node is uneven, with too high a hardware load on some nodes and too low a hardware load on other nodes. The set of critical nodes refers to the set composed of nodes that have an important impact on the network performance and stability in the node group.

[0129] In specific implementation, graph theory and network analysis methods are used to perform topological vulnerability analysis on the group health graph. By analyzing the connection relationship and communication traffic between nodes, the communication load and hardware load of each node are calculated. According to the preset threshold, it is judged whether there is an overloaded communication link or an unbalanced hardware load. If the communication load of a certain node exceeds the carrying capacity of the communication link, or the hardware load of a certain node is too high, that node is identified as a critical node. For example, in a sensing network of an intelligent energy grid, topological vulnerability analysis is performed on the group health graph. By calculating the communication traffic between nodes and the load of hardware components, it is found that the communication traffic of node A exceeds the carrying capacity of its communication link, and the hardware CPU load of node B is too high. Node A and node B are identified as critical nodes and form a set of critical nodes.

[0130] Step S5138: Generate a load migration strategy and a link reconstruction strategy based on the spatial distribution characteristics of the key node set: Migrate the data forwarding tasks of overloaded nodes to idle nodes, and add redundant communication links on the critical path.

[0131] The spatial distribution characteristics of the key node set refer to the geographical location distribution of key nodes in the node group. The load migration strategy is a strategy for balancing node loads. It migrates the data forwarding tasks of overloaded nodes to idle nodes to relieve the burden on overloaded nodes. The link reconstruction strategy is a strategy for optimizing the network topology. It improves the reliability and fault tolerance of the network by adding redundant communication links on the critical path.

[0132] In specific implementation, first analyze the spatial distribution characteristics of the key node set to understand the geographical locations of key nodes and their connection relationships with other nodes. For key nodes with overloaded communication links or unbalanced hardware loads, generate a load migration strategy. The idle nodes can be determined through network monitoring and load prediction algorithms, and the data forwarding tasks of overloaded nodes are migrated to idle nodes. For example, by real-time monitoring the load conditions of nodes, it is found that the load of node A is too high while the load of node C is low, and part of the data forwarding tasks of node A are migrated to node C. At the same time, generate a link reconstruction strategy according to the positions of key nodes and the network topology. Add redundant communication links on the critical path to improve the reliability of the network. For example, add a backup communication link on the critical path between node A and node B, so that when the main link fails, it can be automatically switched to the backup link.

[0133] Step S5139: During the execution of the load migration strategy, continuously monitor the hardware load fluctuation curve of the migration target node. When it is detected that the load mutation exceeds the hardware stability interval, automatically roll back to the previous stable topology configuration.

[0134] The execution process of the load migration strategy is the process of migrating the data forwarding tasks of overloaded nodes to idle nodes. The migration target node refers to the idle node that receives the data forwarding tasks. The hardware load fluctuation curve refers to the curve of the hardware load of the migration target node changing over time. The hardware stability interval refers to the load range within which the hardware of the migration target node can operate stably.

[0135] In specific implementation, during the execution of the load migration strategy, a hardware load sensor is used to monitor the hardware load fluctuation curve of the migration target node in real time. The monitored curve is analyzed to calculate the change rate and fluctuation amplitude of the load. When it is detected that the load mutation exceeds the hardware stability interval, it indicates that the hardware of the migration target node cannot withstand the suddenly increased load, which may lead to hardware failures or performance degradation. At this time, it automatically reverts to the previous stable topology configuration, and redistributes the data forwarding task to the original nodes. For example, in a sensing network of an intelligent logistics warehouse, when executing the load migration strategy to migrate the data forwarding task of node A to node C, during the migration process, the hardware CPU load fluctuation curve of node C is monitored in real time. When it is detected that the CPU load suddenly increases from 20% to 80%, exceeding the hardware stability interval (30% - 70%), it automatically reverts to the previous stable topology configuration and redistributes the data forwarding task to node A.

[0136] Step S51310: Integrate the successfully implemented load migration strategy and link reconstruction strategy into a group maintenance knowledge base, and establish a policy mapping channel between the group maintenance knowledge base and the fault handling knowledge base.

[0137] The group maintenance knowledge base is a knowledge base used to store and manage node group maintenance strategies, which includes successfully implemented load migration strategies, link reconstruction strategies, etc. The policy mapping channel is a channel used to establish a connection between the group maintenance knowledge base and the fault handling knowledge base. Through this channel, information sharing and policy coordination between the two knowledge bases can be achieved.

[0138] In specific implementation, the successfully implemented load migration strategy and link reconstruction strategy are sorted out and summarized and stored in the group maintenance knowledge base. The group maintenance knowledge base can be stored in the form of a database. Each strategy can include information such as the name of the strategy, applicable scenarios, specific operation steps, and effect evaluation. At the same time, a policy mapping channel is established between the group maintenance knowledge base and the fault handling knowledge base. Information sharing between the two knowledge bases can be achieved by establishing an association table or interface. For example, when a fault related to node load or network topology appears in the fault handling knowledge base, the corresponding load migration strategy or link reconstruction strategy can be obtained from the group maintenance knowledge base through the policy mapping channel for fault handling. In a sensing network of an intelligent medical park, the successfully implemented load migration strategy and link reconstruction strategy are stored in the group maintenance knowledge base, and a policy mapping channel is established with the fault handling knowledge base. When a fault of excessive node load occurs, the load migration strategy can be obtained from the group maintenance knowledge base for handling.

[0139] As an implementation manner, the method provided by the embodiment of the present invention may further include the following steps S51311~S51315: Step S51311: When the group health map continuously shows that the target node is in a high-load state, start the preventive node maintenance process: predict the remaining hardware life based on the state feature set, and generate a maintenance priority list.

[0140] The target node refers to the node that is continuously in a high-load state in the group health map. The preventive node maintenance process is a process of pre-maintaining the node to avoid node failures. The remaining hardware life refers to the time that the node's hardware device can still work normally under the current usage state. The maintenance priority list is generated based on factors such as the remaining hardware life and importance of the node, and is used to determine the node maintenance order.

[0141] In specific implementation, when the group health map continuously shows that the target node is in a high-load state, it indicates that there may be a risk of hardware aging or performance degradation for this node, and the preventive node maintenance process is started. Based on the state feature set of the target node, machine learning algorithms or physical models are used to predict the remaining hardware life. For example, the support vector machine (SVM) algorithm can be used. The device operation parameters (such as energy consumption, temperature, hardware load, etc.) in the state feature set are used as inputs to train a prediction model to predict the remaining hardware life. According to the prediction results and factors such as the importance of the node in the network, a maintenance priority list is generated. The importance can be evaluated based on the function of the node, the number of connected nodes, etc. For example, in a sensing network of an intelligent transportation hub, node A is continuously in a high-load state in the group health map. Using the SVM algorithm, the remaining hardware life of node A is predicted to be 6 months based on its state feature set. Considering that node A is connected to multiple important monitoring devices, it is ranked at the top of the maintenance priority list.

[0142] Step S51312: Inject hardware self-check instructions into the target node according to the maintenance priority list, and obtain the memory bad block distribution data and the power module output stability curve.

[0143] The hardware self-check instruction is an instruction used to let the node's hardware device perform self-check. The memory bad block distribution data refers to the distribution of damaged storage blocks in the node's memory. The power module output stability curve refers to the curve of the power module output voltage or current changing with time, which reflects the output stability of the power module.

[0144] In specific implementation, according to the maintenance priority list, hardware self-check instructions are sequentially injected into the target node. The hardware self-check instructions can be sent to the target node through the network communication protocol. After receiving the instructions, the target node starts the hardware self-check program. During the self-check process, the bad block distribution data of the memory and the output stability curve of the power module are obtained. For the bad block distribution data of the memory, each memory block can be subjected to read and write tests through the memory self-check algorithm, the damaged memory blocks are marked, and their positions and quantities are recorded. For the output stability curve of the power module, voltage sensors and current sensors can be used to monitor the output voltage and current of the power module in real time, and the monitoring data is recorded in chronological order to form the output stability curve. For example, in a sensing network of intelligent industrial automation, according to the maintenance priority list, hardware self-check instructions are injected into the target node B. The target node B starts the hardware self-check program, and it is detected through the memory self-check algorithm that there are 3 bad blocks in the memory, located at addresses 0x100, 0x200, and 0x300 respectively. At the same time, the output of the power module is monitored using voltage sensors and current sensors, and the changes in the output voltage and current over time are recorded to generate the output stability curve of the power module.

[0145] Step S51313: Perform an address remapping operation on the bad block distribution data of the memory, and at the same time apply feedback voltage regulation to the output stability curve of the power module.

[0146] The address remapping operation refers to remapping the addresses of the bad blocks in the memory to other available memory blocks to avoid read and write operations on the bad blocks and improve the reliability of the memory. The feedback voltage regulation refers to adjusting the output voltage of the power module in real time according to the output stability curve of the power module to keep it stable.

[0147] In specific implementation, for the memory bad block distribution data, an address remapping algorithm is used to remap the addresses of the bad blocks. First, scan the available storage blocks in the memory to find sufficient free space to replace the bad blocks. Then, modify the address mapping table of the memory to map the addresses of the bad blocks to the addresses of the available storage blocks. In subsequent read and write operations, the system will automatically access the remapped addresses. For the output stability curve of the power supply module, a feedback control algorithm, such as a PID (Proportional-Integral-Derivative) controller, is used to adjust the input parameters of the power supply module in real time according to the changes in the output stability curve to maintain the stability of the output voltage. For example, when the output voltage is lower than the set value, increase the input voltage of the power supply module; when the output voltage is higher than the set value, lower the input voltage of the power supply module. In a sensing network of an intelligent smart home, an address remapping operation is performed on the memory bad block distribution data of the target node C, remapping the address 0x100 of the bad block to the address 0x500 of the available storage block. At the same time, a PID controller is used to perform feedback voltage regulation on the output stability curve of the power supply module. When the output voltage drops, the input voltage of the power supply module is increased in a timely manner to keep the output voltage within a stable range.

[0148] Step S51314: Recalculate the predicted value of the remaining hardware life after completing the self-maintenance operation. If the predicted value does not reach the preset safety threshold, trigger a node retirement warning and send a data backup instruction to adjacent nodes.

[0149] The self-maintenance operation refers to maintenance operations such as address remapping operations and feedback voltage regulation performed on the target node. The predicted value of the remaining hardware life is the remaining hardware life predicted again based on the set of node state characteristics after completing the self-maintenance operation. The preset safety threshold is the lowest safety value of the remaining hardware life set in advance. The node retirement warning is a reminder signal used to indicate that the remaining hardware life of the node is insufficient and retirement processing is required. The data backup instruction is an instruction used to let adjacent nodes back up the data of the target node.

[0150] In specific implementation, after completing the self-maintenance operation, collect the set of node state characteristics again, and use the previous prediction model to recalculate the predicted value of the remaining hardware life. Compare the predicted value with the preset safety threshold. If the predicted value does not reach the preset safety threshold, it means that the remaining hardware life of the node is not sufficient to ensure its normal operation, and a node retirement warning is triggered. At the same time, send a data backup instruction to adjacent nodes to let adjacent nodes back up the data of the target node to prevent data loss. For example, in a sensing network of an intelligent education campus, after completing the self-maintenance operation on the target node D, the recalculated predicted value of the remaining hardware life is 3 months, and the preset safety threshold is 6 months. Since the predicted value does not reach the preset safety threshold, a node retirement warning is triggered, and a data backup instruction is sent to adjacent nodes, and the adjacent nodes start to back up the data of the target node D.

[0151] Step S51315: During the period when the node retirement warning is in effect, gradually migrate the data forwarding tasks of the target node to the standby node until its communication link load drops to zero, then perform a safe power-off operation, and update the topological structure data of the group health map.

[0152] The period when the node retirement warning is in effect refers to the time period from triggering the node retirement warning to completing the node retirement process. The standby node refers to a node that is pre-set to replace the target node for work. The communication link load refers to the data transmission volume of the target node on the communication link. The safe power-off operation refers to turning off the power of the node on the premise of ensuring the safety of the node data. The topological structure data of the group health map refers to the data in the group health map that reflects the connection relationship between nodes and the network topology structure.

[0153] In specific implementation, during the period when the node retirement warning is in effect, gradually migrate the data forwarding tasks of the target node to the standby node according to a preset strategy. A phased migration method can be adopted. First, migrate some non-critical data forwarding tasks, and then migrate the critical data forwarding tasks. During the migration process, real-time monitor the communication link load of the target node. When the communication link load drops to zero, it means that the target node no longer undertakes data forwarding tasks, and a safe power-off operation can be performed. The safe power-off operation can be carried out according to the shutdown process of the node to ensure that the data of the node is properly saved. At the same time, update the topological structure data of the group health map, remove the target node from the map, and update the connection relationship related to the target node. For example, in a sensing network of an intelligent tourist scenic area, during the period when the node retirement warning is in effect, gradually migrate the data forwarding tasks of the target node E to the standby node F. After a period of migration, the communication link load of the target node E drops to zero, and a safe power-off operation is performed. At the same time, update the topological structure data of the group health map, delete the target node E from the map, and update the connection relationship between the adjacent nodes and the standby node F.

[0154] It can be understood that in the above introductions of the embodiments of the present invention, various algorithms involved, such as genetic algorithms, cosine similarity algorithms, time synchronization algorithms, etc., can be obtained from relevant content in the prior art. For the sake of saving space, they are not elaborated in the embodiments of the present invention. In addition, those skilled in the art can make detailed supplements according to the common general knowledge in the art when implementing the solution of the present invention. For example, according to the general knowledge in the art, normalization can be used to eliminate the dimension conflict before feature fusion, interpolation can be used to eliminate the dimension difference, historical data, experience or business scenario requirements can be combined to reasonably set the threshold, and the model can be trained based on the general model training method, etc. The present invention will no longer give redundant introductions to the overly detailed implementation process.

[0155] Figure 2 The following is a schematic diagram of the hardware entity of a computer system provided by an embodiment of the present invention. As Figure 2 shown, the hardware entity of the computer system 1000 includes: a processor 1001 and a memory 1002. Among them, the memory 1002 stores a computer program that can run on the processor 1001, and when the processor 1001 executes the program, it implements the steps in the method of any of the above embodiments.

[0156] The memory 1002 stores a computer program that can run on the processor. The memory 1002 is configured to store instructions and applications executable by the processor 1001, and can also cache data to be processed or already processed by the processor 1001 and each module in the computer system 1000 (for example, image data, audio data, voice communication data, and video communication data), and can be implemented by flash memory (FLASH) or random access memory (Random Access Memory, RAM).

[0157] When the processor 1001 executes the program, it implements the steps of the node fault intelligent diagnosis method of the intelligent space sensing network in any of the above items. The processor 1001 generally controls the overall operation of the computer system 1000.

[0158] As mentioned above, the above are only the embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, and all of them should be covered within the protection scope of the present invention.

Claims

1. An intelligent diagnosis method for node faults in an intelligent space sensing network, characterized in that, Including: Obtain the real-time monitoring data set of all sensor nodes in the target sensor network, where the real-time monitoring data set includes the device operation parameters, network communication parameters, and environmental interference parameters of each sensor node; Perform state feature extraction processing on the real-time monitoring data set to generate a state feature set for each sensor node, where the state feature set includes device operation state features, network connection stability features, and environmental interference correlation features; Based on a preset fault diagnosis strategy model, perform multi-dimensional fault matching processing on the state feature set to determine a candidate fault type set for the sensor node, where the candidate fault type set includes at least one candidate fault type associated with the state feature set; According to the policy mapping relationship between the candidate fault type set and a preset fault processing knowledge base, generate a node fault processing strategy set for the sensor node, where the node fault processing strategy set includes the optimal processing strategy for each candidate fault type; Based on the node fault processing strategy set, perform node optimization operations on the faulty nodes in the target sensor network, and feedback the optimized node operation parameters to the control terminal of the target sensor network.

2. The method according to claim 1, wherein The performing state feature extraction processing on the real-time monitoring data set to generate a state feature set for each sensor node includes: Perform periodic fluctuation pattern recognition processing on the device operation parameters to generate the device operation state features, where the device operation state features include the energy consumption change trend based on the time series and the hardware component load fluctuation curve; Perform link anomaly event correlation analysis processing on the network communication parameters to extract the network connection stability features, where the network connection stability features include the correlation matrix between the packet loss rate and the signal strength and the communication interruption frequency distribution map; Perform multi-source interference coupling analysis processing on the environmental interference parameters to construct the environmental interference correlation features, where the environmental interference correlation features include the interference superposition effect of the temperature gradient and the electromagnetic noise and the quantization influence coefficient of the humidity change on the signal attenuation; Perform time-domain alignment processing on the energy consumption change trend and the hardware component load fluctuation curve to generate a first fusion feature vector; perform spatial mapping processing on the correlation matrix and the communication interruption frequency distribution map to generate a second fusion feature vector; perform weight superposition processing on the interference superposition effect and the quantization influence coefficient to generate a third fusion feature vector; According to the feature complementary relationship between the first fusion feature vector, the second fusion feature vector, and the third fusion feature vector, generate the state feature set including multi-dimensional correlation indicators.

3. The method according to claim 2, characterized in that, The based on a preset fault diagnosis strategy model, performing multi-dimensional fault matching processing on the state feature set to determine a candidate fault type set for the sensor node includes: Input the first fusion feature vector into the hardware degradation analysis module of the fault diagnosis strategy model, and generate a hardware-related fault set by matching a preset hardware failure mode library, where the hardware failure mode library includes power module anomalies, sensor drift, and circuit aging feature patterns; Input the second fused feature vector into the network topology analysis module of the fault diagnosis strategy model, and generate a network-related fault set by identifying communication link breakage features and routing table anomaly features. The communication link breakage features include neighbor node unreachable events and data retransmission count mutation patterns; Input the third fused feature vector into the environmental resistance analysis module of the fault diagnosis strategy model, and generate an environment-related fault set by analyzing the deviation between the interference superposition effect and the node anti-interference threshold. The node anti-interference threshold is adjusted according to the stable operation data under historical environmental parameters; Evaluate the fault coupling degree of the hardware-related fault set, the network-related fault set, and the environment-related fault set, and calculate the conditional trigger probability between any two fault types; Perform combined optimization processing on the fault types with strong correlation relationships according to the conditional trigger probability, and generate the candidate fault type set including the main fault type and the derivative fault type.

4. The method according to claim 3, characterized in that, Generate the node fault handling strategy set of the target sensor node according to the strategy mapping relationship between the candidate fault type set and the preset fault handling knowledge base, including: Retrieve the benchmark handling strategy set corresponding to the main fault type from the fault handling knowledge base. The benchmark handling strategy set includes hardware reset instructions, communication link reconstruction protocols, and environment adaptive calibration schemes; Perform strategy derivation processing on the benchmark handling strategy set according to the derivative fault type: embed voltage compensation parameters for circuit aging characteristics in the hardware reset instructions; add path selection rules based on the load status of neighbor nodes to the communication link reconstruction protocol; configure interference shielding thresholds in the environment adaptive calibration scheme; Evaluate the execution priority of the derived handling strategies. The execution priority evaluation is sorted based on the product index of the strategy execution time and the fault repair probability; Select the handling strategies that meet the preset repair success rate according to the sorting result to generate the node fault handling strategy set, and configure execution condition constraints and rollback mechanisms for each handling strategy.

5. The method according to claim 4, wherein Perform node optimization operations on the fault nodes in the target sensor network based on the node fault handling strategy set, including: Select the target handling strategy with the highest priority according to the execution priority evaluation result, parse the hardware reset instruction in the target handling strategy, and inject the voltage compensation parameters; After performing the hardware reset operation on the fault node, monitor the recovery status of the energy consumption change trend and the load fluctuation curve in real time. If the preset stable interval is not reached, trigger the communication link reconstruction protocol; Re-establish the data transmission link between the fault node and the neighbor nodes according to the path selection rules, and verify whether the packet loss rate drops to the preset communication quality threshold; If the packet loss rate is still higher than the communication quality threshold, activate the interference shielding threshold in the environment adaptive calibration scheme, and synchronously adjust the signal transmission power and the receiving sensitivity parameters; Encapsulate the optimized node operation parameters and the network topology structure into a configuration update packet, and broadcast the configuration update packet to all associated nodes through the distributed synchronization mechanism of the target sensing network.

6. The method according to claim 5, wherein The method further includes: After the broadcast of the configuration update packet is completed, start a cross-node collaborative verification process: the neighbor node sends a verification data packet to the faulty node and records the end-to-end transmission delay; If the transmission delay exceeds the preset delay tolerance, it is determined that the current optimization operation has not fully repaired the communication link breakage characteristics in the network-related fault set, and the rollback mechanism is triggered to restore to the previous stable configuration; If the transmission delay meets the requirements, collect the real-time operation data of the faulty node to generate a verification feature set, and input the verification feature set into the fault diagnosis policy model for secondary fault matching; When none of the fault types in the candidate fault type set exist in the secondary matching result, confirm that the node optimization operation is successful and persistently store the current configuration parameters in the fault processing knowledge base; If a new fault type is detected, generate an incremental policy based on the similarity between the new fault type and the historical processing strategy, and add the incremental policy to the node fault processing strategy set.

7. The method according to claim 6, wherein The method further includes: After the broadcast of the configuration update packet is completed, obtain the collaborative verification data set of the faulty node and its neighbor nodes, where the collaborative verification data set includes the real-time monitoring results of the optimized device operation parameters, network communication parameters, and environmental interference parameters; Perform a fault elimination verification process on the collaborative verification data set: input the real-time monitoring results into the fault diagnosis policy model to regenerate a set of candidate fault types for verification; When there is an intersection between the set of candidate fault types for verification and the candidate fault type set, it is determined that the node optimization operation has not fully eliminated the target fault type, and an incremental policy optimization process is triggered; Based on the residual fault type corresponding to the intersection, extract the optimization compensation strategy of the historical processing failure case from the fault processing knowledge base, and generate a compensatory node optimization instruction in combination with the state feature set; After executing the compensatory node optimization instruction, collect the verification data set again until there is no intersection between the set of candidate fault types for verification and the candidate fault type set, and add the finally effective optimization strategy parameters and corresponding monitoring data to the incremental learning module of the fault processing knowledge base.

8. The method according to claim 7, wherein The method further includes: During the incremental policy optimization process, continuously monitor the change trend of the environmental interference parameters. When it is detected that the interference source intensity exceeds the coverage range of the current interference shielding threshold, trigger the environmental resistance enhancement mode; In the environmental resistance enhancement mode, reallocate the signal modulation scheme of the faulty node according to the interference source type: adopt a frequency band hopping modulation strategy for electromagnetic noise interference, and enable a thermal stability compensation algorithm for temperature gradient interference; Based on the updated signal modulation scheme, reconstruct the physical layer communication protocol between the faulty node and its neighbor nodes, and synchronously adjust the data frame length and the check code redundancy ratio; Collect the reconstructed network communication parameters to generate anti-interference performance evaluation indicators. When the evaluation indicators do not reach the preset resistance threshold, iteratively update the parameter combination of the frequency band hopping modulation strategy and the thermal stability compensation algorithm; Package the optimized parameter combination and the physical layer communication protocol into an environmental resistance enhancement package, and directionally distribute it to the node group in the same type of interference area through the distributed synchronization mechanism.

9. The method according to claim 8, wherein The method further includes: Deploy a cross-node collaborative maintenance mechanism in the node group in the same type of interference area, and periodically collect the state feature set of each node in the group to generate a group health map; Conduct a topological vulnerability analysis on the group health map to identify a key node set with communication link overload or hardware load imbalance; Generate a load migration strategy and a link reconstruction strategy according to the spatial distribution characteristics of the key node set: migrate the data forwarding task of the overloaded node to the idle node, and add redundant communication links on the critical path; During the execution of the load migration strategy, real-time monitor the hardware load fluctuation curve of the migration target node. When it is detected that the load mutation exceeds the hardware stability interval, automatically roll back to the previous stable topology configuration; Integrate the successfully implemented load migration strategy and link reconstruction strategy into a group maintenance knowledge base, and establish a strategy mapping channel between the group maintenance knowledge base and the fault handling knowledge base.

10. A computer system, comprising a memory and a processor, the memory storing a computer program executable on the processor, characterized in that, When the processor executes the program, it implements the steps in the method according to any one of claims 1 to 9.

Images