Dynamic Tracking Method for Electromechanical Equipment Based on Multivariate Heterogeneous Data and Edge Computing

Abstract

The present invention belongs to the field of equipment operation and maintenance monitoring, and particularly relates to a dynamic tracking method for electromechanical equipment based on multi-source heterogeneous data and edge computing, including: presetting an equipment operation and maintenance monitoring network, determining a distributed edge-level control chain according to the distribution and operation attribute data of electromechanical equipment in the equipment operation and maintenance monitoring network, the distributed edge-level control chain being constructed by combining the equipment distribution state, operation load, monitoring device correlation coefficient and graph algorithm, and obtaining a multi-level tracking control space and two-way feedback control instructions by using the distributed edge-level control chain in combination with monitoring data to realize the uplink feedback and downlink electromechanical instruction control of the electromechanical equipment; by means of the construction of the distributed edge-level control chain and the application of the model, the present invention can effectively integrate equipment data, realize the precise monitoring and control of electromechanical equipment, improve the equipment operation and maintenance efficiency, and enhance the operation stability and reliability of the equipment.

Description

Technical Field

[0001] The present invention belongs to the field of equipment operation and maintenance monitoring, and particularly relates to a dynamic tracking method for electromechanical equipment based on multi-source heterogeneous data and edge computing. Background Art

[0002] Electromechanical equipment is increasingly widely and importantly applied in various fields, such as manufacturing, energy industry, transportation, etc. The normal operation of electromechanical equipment is directly related to production efficiency, product quality, and production safety. In the context of Industry 4.0 and intelligent manufacturing, real-time and accurate monitoring and tracking of electromechanical equipment have become key requirements for ensuring stable production; however, existing electromechanical equipment monitoring technologies have many deficiencies and defects. On the one hand, most existing technologies monitor equipment from a single-level perspective. For large and complex electromechanical equipment, which includes multiple hierarchical structures such as equipment level and component level, most monitoring methods only focus on tracking and monitoring the equipment as a whole, and it is difficult to penetrate into the subtle component level, resulting in the inability to detect potential faults and performance degradation at the component level in a timely manner. Moreover, due to the irregular distribution of monitoring devices, the data is chaotic, increasing the difficulty of processing; on the other hand, for some large-scale equipment with a wide distribution, the current control and monitoring methods are too centralized, and the data needs to be transmitted to the central control center for processing and analysis, which not only increases the burden of data transmission but also causes delays in monitoring and feedback, and cannot respond to equipment anomalies in a timely manner. Summary of the Invention

[0003] Aiming at the deficiencies of the prior art, the present invention proposes a dynamic tracking method for electromechanical equipment based on multi-source heterogeneous data and edge computing, including: presetting an equipment operation and maintenance monitoring network, determining a distributed edge-level control chain according to the distribution and operation attribute data of electromechanical equipment in the equipment operation and maintenance monitoring network, the distributed edge-level control chain is constructed by combining the equipment distribution status, operation load, monitoring device correlation coefficient with graph algorithms, and by combining the distributed edge-level control chain with monitoring data, using a distributed reinforcement control model to obtain a multi-level tracking control space and two-way feedback control instructions, so as to realize the upward feedback and downward electromechanical instruction control of electromechanical equipment; by constructing the distributed edge-level control chain and applying the model, the present invention can effectively integrate equipment data, realize accurate monitoring and control of electromechanical equipment, improve equipment operation and maintenance efficiency, and enhance equipment operation stability and reliability.

[0004] To achieve the above object, the present invention provides the following technical solutions:

[0005] A dynamic tracking method for electromechanical equipment based on multi-source heterogeneous data and edge computing, including:

[0006] Presetting an equipment operation and maintenance monitoring network, and determining a distributed edge-level control chain according to the distribution and operation attribute data of electromechanical equipment in the equipment operation and maintenance monitoring network;

[0007] Based on the data monitored by the device operation and maintenance monitoring network combined with the distributed edge - level control chain, through the configured distributed reinforcement control model, obtain the multi - level tracking control space and two - way feedback control instructions;

[0008] Based on the multi - level tracking control space and two - way feedback control instructions, perform the upward feedback of the electromechanical equipment and the control of the downward electromechanical instructions;

[0009] The distributed edge - level control chain is constructed by combining the distribution status, operating load of the electromechanical equipment in the device operation and maintenance monitoring network and the correlation coefficient of the corresponding monitoring equipment under each level of control nodes with the graph algorithm.

[0010] Specifically, the device operation and maintenance monitoring network includes a first - level directed electromechanical equipment simulation subnet and a second - level monitoring node chain;

[0011] The construction steps of the first - level directed electromechanical equipment simulation subnet include:

[0012] Obtain the distribution position, attributes and operation - related dynamic parameters of the electromechanical equipment. Take each sub - component in the electromechanical equipment as a node in the device operation and maintenance monitoring network to obtain the first - level node set;

[0013] The distribution position and attributes of the electromechanical equipment include the spatial coordinates, function labels and operation - related dynamic parameters corresponding to each sub - component; the operation - related dynamic parameters include: the energy transmission path, control instruction transmission priority and electromagnetic coupling intensity corresponding to each sub - component;

[0014] According to the energy transmission path, electromagnetic coupling intensity, energy transmission efficiency and control instruction transmission priority among the operation - related dynamic parameters of each node of the electromechanical equipment, through the Bayesian algorithm, obtain the directed correlation probability values between each node;

[0015] Take the directed correlation probability values between each node as the causal relationship verification factors between two nodes. Through the causal analysis algorithm, verify the causal relationship between each node to obtain the causal node set corresponding to the first - level node set.

[0016] Specifically, the construction steps of the first - level directed electromechanical equipment simulation subnet also include:

[0017] Based on the directed correlation probability values between each node combined with the preset correlation degree interval, obtain the directed correlation strength between each node;

[0018] According to the nodes with causal relationships and the nodes without causal relationships in the first - level node set, divide the directed correlation strength between each node into directed causal correlation strength and ordinary directed correlation strength;

[0019] Taking the directed causal association strength and the ordinary directed association strength as the directed connection relationships between nodes, and combining with the first-level node set and the corresponding position coordinates, the first-level directed electromechanical equipment simulation subnet is obtained through the hypergraph algorithm. At the same time, the corresponding directed causal association strength and ordinary directed association strength are marked on the directed connection relationships through the automatic annotation algorithm.

[0020] Specifically, the construction steps of the first-level directed electromechanical equipment simulation subnet further include:

[0021] Based on the types and association strengths of the directed connection relationships between the nodes of the first-level directed electromechanical equipment simulation subnet, through the preset color mapping table and the kernel function in the support vector machine, a color mapping function for each type of directed association relationship and the corresponding association strength is constructed.

[0022] The color mapping table includes color types and color level gradients.

[0023] The color mapping function for each type of directed association relationship and the corresponding association strength is built into the directed connection relationship between the corresponding nodes.

[0024] At the same time, the first-level directed electromechanical equipment simulation subnet with the built-in color mapping function is input into the 3D simulation algorithm and combined with the HSL model. According to the changes in the types and association strengths of the directed connection relationships between the nodes, the color, color corresponding brightness, and chromaticity changes of the directed connection relationships between the nodes of the first-level directed electromechanical equipment simulation subnet are simulated and verified for training to obtain the 3D first-level directed electromechanical equipment simulation subnet.

[0025] Specifically, an intensity adjustment factor is built into each connection relationship in the first-level directed electromechanical equipment simulation subnet; the intensity adjustment factor includes a positive intensity adjustment factor and a negative intensity adjustment factor.

[0026] The intensity adjustment factor is obtained by fitting through a multiple regression function according to the energy transfer delay change rate, electromagnetic coupling strength change rate, and control delay change rate, as well as the positive and negative signs corresponding to the energy transfer delay change rate, electromagnetic coupling strength change rate, and control delay change rate, and the brightness and chromaticity of the color corresponding to the directed connection relationship.

[0027] Specifically, the construction steps of the second-level monitoring node chain include:

[0028] Obtain the failure frequency corresponding to each node in the 3D first-level directed electromechanical equipment simulation subnet, the corresponding associated failure nodes, and the corresponding associated failure frequencies.

[0029] Based on the obtained failure frequency corresponding to each node, the corresponding associated failure nodes, and the corresponding associated failure frequencies, probability clustering is performed through the adaptive clustering algorithm combined with the Bayesian algorithm to obtain the set of associated failure nodes.

[0030] According to the associated fault node set, through the three-dimensional simulation algorithm in the three-dimensional first-level directed electromechanical equipment simulation subnet, when simulating the occurrence of a fault in a node in the corresponding associated fault node set, the probability of the occurrence of a fault in the corresponding associated fault node obtained by the Bayesian algorithm is calculated;

[0031] Based on the probability of the occurrence of a fault in the corresponding associated fault node obtained and combined with the preset associated fault accuracy rate threshold, probability clustering simulation training is carried out to obtain all associated fault node sets that meet the associated fault accuracy rate threshold.

[0032] Specifically, the steps for constructing the secondary monitoring node chain further include:

[0033] Obtain the node with the largest data collection load in each associated fault node set as the load master node for the regional division of the corresponding associated fault node set, and obtain the regional division load master node set;

[0034] Based on the directed causal association strength and ordinary directed association strength marked corresponding to the directed connection relationship in the associated fault node set, the spatial distance between the edge nodes between the associated fault node sets, the function consistency and causal association strength, and the maximum load processing energy corresponding to each tracking control node in the distributed edge layer control chain, and combining the condition of minimizing the directed association strength between the divided regions and maximizing the directed association strength between each associated fault node set within the region, the regional division load master node set is divided into regions through the hypergraph partitioning algorithm to obtain the completed regional division load master node subset space;

[0035] Based on the completed regional division load master node subset space, combined with the strength adjustment factor and the maximum load processing energy corresponding to each tracking control node in real time, through the three-dimensional simulation algorithm combined with the hypergraph partitioning algorithm, the boundary range corresponding to each regional division load master node subset space is adjusted in real time.

[0036] Specifically, the steps for constructing the secondary monitoring node chain further include:

[0037] Based on each completed regional division load master node subset space, a data monitoring point is set to obtain a data monitoring point set, and a directed monitoring connection relationship is constructed based on the data transmission direction and control instruction execution priority order between the regional division load master node subset spaces corresponding to the data monitoring point set;

[0038] Based on the directed monitoring connection relationship and the data monitoring point set, the secondary monitoring node chain is obtained;

[0039] Based on the secondary monitoring node chain, a random data acquisition index chain is constructed between each data monitoring point in the secondary monitoring node chain and each associated fault node set within the space of the corresponding regional division load master node subset through a random algorithm combined with a discrimination algorithm, and data acquisition rules are set for the random data acquisition index chains corresponding to the same data monitoring point.

[0040] Specifically, the construction steps of the distributed edge hierarchical control chain include:

[0041] Construct a distributed federated tracking control model based on the distributed federated algorithm combined with the reinforcement learning algorithm, and deploy the edge tracking control submodel in the distributed federated tracking control model to each data monitoring point to obtain an edge control node set;

[0042] Based on the association coupling between the corresponding nodes in the space of each regional division load master node subset in the data monitoring point set and the operation priority of the device sub-components, construct the information sharing connection relationship corresponding to every two edge control nodes in the edge control node set;

[0043] Based on the edge control node set and the information sharing connection relationship, obtain the distributed edge hierarchical control chain.

[0044] Specifically, the data acquisition rules include:

[0045] Set the same data acquisition frequency for the nodes with causal relationships in all associated fault node sets in the same regional division load master node subset space and the nodes with an association strength of medium or above in the corresponding ordinary directed association strength;

[0046] Each random data acquisition index chain corresponding to an associated fault node set randomly acquires data from only one node in the associated fault node set at a time, and marks the acquired data with the label serial number of the corresponding associated fault node set;

[0047] Configure the acquisition frequency fluctuation mapping function of the intensity adjustment factor and the data acquisition frequency, and configure the acquisition frequency fluctuation mapping function into all random data acquisition index chains;

[0048] When the current intensity adjustment factor changes, the data acquisition frequency corresponding to the random data acquisition index chain is adjusted in real time through the acquisition frequency fluctuation mapping function.

[0049] Specifically, the steps for obtaining the multi-level tracking control space and the bidirectional feedback control instruction include:

[0050] Based on the three-dimensional first-level directed electromechanical device simulation subnet, conduct electromechanical device operation simulation. At the same time, through the dynamic acquisition frequency configured by the secondary monitoring node chain combined with the acquisition frequency fluctuation mapping function, collect data from the nodes corresponding to the three-dimensional first-level directed electromechanical device simulation subnet to obtain the simulated tracking dataset space;

[0051] Synchronously input the dataset obtained by dividing the corresponding area in the simulated tracking dataset space into the load master node subset space to the corresponding edge control node, and use the configured discrimination algorithm to discriminate the operating states of the corresponding acquisition nodes and the associated fault node sets, obtain the multi-level tracking control space, and mark the label numbers of the associated fault node sets corresponding to the acquisition nodes;

[0052] Based on the discrimination accuracy rate of the fault operating states of the corresponding acquisition nodes and the associated fault node sets in the multi-level tracking control space, combined with the preset discrimination accuracy rate threshold, adjust the intensity adjustment factor and the dynamic acquisition frequency through the three-dimensional simulation algorithm, and conduct cyclic simulation training on the overall electromechanical device operation state tracking process corresponding to the three-dimensional first-level directed electromechanical device simulation subnet, the secondary monitoring node chain, and the distributed edge level control chain;

[0053] When the discrimination accuracy rate of the fault operating states of the corresponding acquisition nodes and the associated fault node sets is greater than the preset discrimination accuracy rate threshold, output the discrimination results corresponding to each edge control node.

[0054] Specifically, the steps for obtaining the multi-level tracking control space and the bidirectional feedback control instructions further include:

[0055] According to the discrimination results corresponding to each edge control node, generate corresponding bidirectional feedback control instructions through the edge tracking control sub-model configured by the corresponding edge control node;

[0056] Share the bidirectional feedback control instructions along the direction of the distributed edge level control chain according to the priority of the corresponding edge control node in the distributed edge level control chain;

[0057] At the same time, transmit the bidirectional feedback control instructions along the random data acquisition index chain to the nodes in the associated fault node sets with discrimination faults for association control and fault early warning, and feedback and upload the corresponding fault early warning to the edge early warning interface. At the same time, according to the mapping relationship between the fault severity and the intensity adjustment factor, perform real-time dynamic adjustment and display on the color type and color depth of the directed connection relationship corresponding to the three-dimensional first-level directed electromechanical device simulation subnet.

[0058] Specifically, the steps for discriminating the operating states of the corresponding acquisition nodes and the associated fault node sets include:

[0059] If it is determined that there is a fault in the corresponding acquisition node, the associated fault nodes are re-determined through the Bayesian algorithm and the associated fault accuracy threshold, and the discrimination fault results and location information corresponding to the acquisition node and the associated fault nodes with re-determined faults are output;

[0060] If it is determined that there is no fault in the corresponding acquisition node but there is a fault in the set of associated fault nodes, the location information and fault results corresponding to the acquisition node with the corresponding fault are obtained through the Bayesian algorithm and the associated fault accuracy threshold between the nodes in the set of associated fault nodes.

[0061] Compared with the prior art, the beneficial effects of the present invention are:

[0062] Aiming at the deficiencies of the prior art, the present invention obtains detailed attributes of each sub-component of the electromechanical equipment through multi-source heterogeneous data, constructs a first-level directed electromechanical equipment simulation subnet, and determines node associations and causal relationships with the help of the Bayesian algorithm, causal analysis algorithm, etc., overcoming the problem that it is difficult to deeply monitor at the component level in the prior art. At the same time, a distributed edge-level control chain is built using the distributed federated algorithm and the reinforcement learning algorithm, and the edge tracking control sub-model is deployed to the data monitoring points, solving the problems of heavy data transmission burden and monitoring feedback delay in centralized control. The secondary monitoring node chain performs regional division and data collection according to the fault frequency and association situation, combines the intensity adjustment factor and the dynamic collection frequency, and cooperates with the three-dimensional simulation algorithm for cyclic training to achieve accurate discrimination of the equipment operation state, generate two-way feedback control instructions and transmit them, realizing associated control and fault warning, comprehensively improving the accuracy and real-time performance of the monitoring and control of large and complex electromechanical equipment, effectively avoiding potential faults, and reducing the difficulty of data processing. Description of the Drawings

[0063] Figure 1 It is a flowchart of the electromechanical equipment dynamic tracking method based on multi-source heterogeneous data and edge computing according to an embodiment of the present invention;

[0064] Figure 2 It is an architecture diagram of the three-dimensional first-level directed electromechanical equipment simulation subnet according to an embodiment of the present invention. Detailed Embodiments

[0065] In the automated production lines of large factories, numerous electromechanical devices are widely distributed and have complex structures, including multi-layer structures such as the device level and component level. Existing monitoring methods are difficult to deeply monitor subtle components, and centralized control leads to data transmission delays, making it impossible to detect component faults and respond to anomalies in a timely manner. For this reason, please refer to Figure 1 , an embodiment provided by the present invention: an electromechanical equipment dynamic tracking method based on multi-source heterogeneous data and edge computing, the steps include:

[0066] S1. Preset an equipment operation and maintenance monitoring network, and determine a distributed edge - level control chain according to the distribution and operation attribute data of the electromechanical equipment in the equipment operation and maintenance monitoring network;

[0067] S2. Through the distributed edge - level control chain, combine the data monitored by the equipment operation and maintenance monitoring network, and obtain a multi - level tracking control space and a two - way feedback control instruction through a configured distributed reinforcement control model;

[0068] S3. Based on the multi - level tracking control space and the two - way feedback control instruction, perform the up - link feedback of electromechanical equipment and the down - link electromechanical instruction control;

[0069] The distributed edge - level control chain is constructed by combining the distribution status, operation load of the electromechanical equipment in the equipment operation and maintenance monitoring network and the correlation coefficient of the corresponding monitoring equipment under each level of control node with a graph algorithm.

[0070] Further, please refer to Figure 2 , the equipment operation and maintenance monitoring network in this embodiment includes a first - level directed electromechanical equipment simulation subnet and a second - level monitoring node chain.

[0071] Further, the construction steps of the first - level directed electromechanical equipment simulation subnet in this embodiment include:

[0072] Obtain the distribution position, attributes and operation - related dynamic parameters of the electromechanical equipment. Take each sub - component in the electromechanical equipment as a node in the equipment operation and maintenance monitoring network to obtain a first - level node set;

[0073] The distribution position and attributes of the electromechanical equipment include the spatial coordinates, function labels and operation - related dynamic parameters corresponding to each sub - component; the operation - related dynamic parameters include: the energy transmission path corresponding to each sub - component, the control instruction transmission priority, and the electromagnetic coupling strength;

[0074] In this embodiment, taking the air - conditioning control system in a shopping mall as an example, take each air - conditioner and each sub - component in the ventilation system, such as fans, compressors, valves, sensors, etc. as nodes, and obtain their spatial coordinates (specific positions in the equipment room or pipelines), function labels (such as refrigeration, ventilation, monitoring, etc.) and operation - related dynamic parameters (energy transmission path, such as electrical energy to mechanical energy to drive the fan operation, control instruction transmission priority, that is, which control instructions are executed first, and the electromagnetic coupling strength mainly for the electromagnetic interference situation between electrical components).

[0075] According to the energy transmission path, the electromagnetic coupling strength, the energy transmission efficiency and the control instruction transmission priority among the operation - related dynamic parameters of each node of the electromechanical equipment, obtain the directed correlation probability value between each node through the Bayesian algorithm;

[0076] Take the directed association probability value between each node as the causal relationship verification factor between two nodes, and verify the causal relationship between each node through a causal analysis algorithm to obtain the causal node set corresponding to the first-level node set.

[0077] Based on the directed association probability value between each node and combined with a preset association degree interval, obtain the directed association strength between each node;

[0078] According to the nodes with causal relationships and the nodes without causal relationships in the first-level node set, divide the directed association strength between each node into directed causal association strength and ordinary directed association strength;

[0079] Take the directed causal association strength and the ordinary directed association strength as the directed connection relationship between each node, combine with the first-level node set and the corresponding position coordinates, and obtain the first-level directed electromechanical equipment simulation subnet through a hypergraph algorithm. At the same time, label the corresponding directed causal association strength and ordinary directed association strength on the directed connection relationship through an automatic annotation algorithm.

[0080] Based on the type and association strength of the directed connection relationship between each node in the first-level directed electromechanical equipment simulation subnet, through a preset color mapping table and the kernel function in the support vector machine, construct a color mapping function for each type of directed association relationship and the corresponding association strength;

[0081] The color mapping table includes color types and color level gradients; further, the color types and color level gradients in this embodiment are customized by those skilled in the art according to usage habits.

[0082] Embed the color mapping function of each type of directed association relationship and the corresponding association strength into the directed connection relationship between the corresponding nodes;

[0083] At the same time, input the first-level directed electromechanical equipment simulation subnet with the embedded color mapping function into a three-dimensional simulation algorithm and combine with the HSL model. According to the type and association strength change of the directed connection relationship between each node, perform simulation verification training on the color and the corresponding brightness and chromaticity change of the directed connection relationship between each node in the first-level directed electromechanical equipment simulation subnet to obtain a three-dimensional first-level directed electromechanical equipment simulation subnet.

[0084] Further, in this embodiment, an intensity adjustment factor is embedded in each connection relationship in the first-level directed electromechanical equipment simulation subnet; the intensity adjustment factor includes a positive intensity adjustment factor and a negative intensity adjustment factor;

[0085] The intensity adjustment factor in this embodiment is obtained by fitting a multivariate regression function based on the energy transfer delay change rate, the electromagnetic coupling intensity change rate and the control delay change rate, as well as the positive and negative signs corresponding to the energy transfer delay change rate, the electromagnetic coupling intensity change rate and the control delay change rate, and the brightness and chromaticity of the color corresponding to the directed connection relationship.

[0086] Furthermore, in this embodiment, when constructing a first-level directed electromechanical equipment simulation subnet in the equipment operation and maintenance monitoring network, the process obtains electromechanical equipment attributes from multiple dimensions, providing a basis for fully understanding the equipment status. By using the Bayesian algorithm and causal analysis algorithm, the directed association probability value and causal relationship are determined through the node operation associated dynamic parameters. Compared with traditional methods, it can deeply explore the potential causal relationship between components, accurately locate the source of the fault, and prevent the fault in advance.

[0087] This process obtains the directed association strength based on the association probability value combined with the preset association degree interval, further divides the directed causal association strength and the ordinary directed association strength, and constructs and annotates the simulated subnet with the help of the hypergraph algorithm and the automatic annotation algorithm to clearly show the connection relationship and association degree of each component, so that the operation and maintenance personnel can quickly locate the key nodes and improve the efficiency of troubleshooting; secondly, the mapping function is constructed and built-in based on the color mapping table and the support vector machine kernel function, and the simulation verification training is carried out in combination with the three-dimensional simulation algorithm and the HSL model to convert the abstract association relationship and strength into intuitive color, brightness and chromaticity changes, so that the operation and maintenance personnel can intuitively understand the dynamics of the equipment and find abnormalities in time; thirdly, the strength adjustment factor is obtained by fitting the multivariate regression function from the energy transfer delay change rate, the electromagnetic coupling strength change rate and the control delay change rate, and the directed connection relationship strength can be dynamically adjusted according to the real-time operation status of the equipment, so that the simulated subnet is more in line with the actual operation situation, which greatly enhances the real-time and accuracy of monitoring, and provides a strong guarantee for the stable operation and efficient operation and maintenance of the equipment.

[0088] Furthermore, the steps of constructing the secondary monitoring node chain in this embodiment include:

[0089] Obtaining the fault frequency corresponding to each node in the three-dimensional first-level directed electromechanical equipment simulation subnet and the corresponding associated fault nodes and the corresponding associated fault frequencies;

[0090] Based on the acquired fault frequency corresponding to each node and the corresponding associated fault nodes and the corresponding associated fault frequencies, probability clustering is performed through an adaptive clustering algorithm combined with a Bayesian algorithm to obtain a set of associated fault nodes;

[0091] According to the associated fault node set, a three-dimensional simulation algorithm in a three-dimensional first-level directed electromechanical equipment simulation subnet is used to simulate the failure of a node in the corresponding associated fault node set, and the probability of the corresponding associated fault node failing is obtained by using a Bayesian algorithm;

[0092] Based on obtaining the probability of a corresponding associated fault node having a fault and combining with a preset associated fault accuracy rate threshold, perform probability clustering simulation training to obtain all associated fault node sets that meet the associated fault accuracy rate threshold.

[0093] Obtain the node with the largest data collection load in each associated fault node set as the load master node for the regional division of the corresponding associated fault node set, and obtain the set of load master nodes for regional division;

[0094] Based on the directed causal association strength and ordinary directed association strength marked corresponding to the directed connection relationship in the associated fault node set, the spatial distance between edge nodes between associated fault node sets, functional consistency and causal association strength, and the maximum load processing energy corresponding to each tracking control node in the distributed edge hierarchical control chain, and combining the condition of minimizing the directed association strength between divided regions and maximizing the directed association strength between each associated fault node set within the region, perform regional division on the set of load master nodes for regional division through a hypergraph partitioning algorithm to obtain the spatial subset of the load master nodes for regional division that has been divided;

[0095] Based on the spatial subset of the load master nodes for regional division that has been divided, combine the intensity adjustment factor and the maximum load processing energy corresponding to each tracking control node in real time, and through a three-dimensional simulation algorithm combined with a hypergraph partitioning algorithm, adjust the boundary range corresponding to each spatial subset of the load master nodes for regional division in real time;

[0096] Further, in this embodiment, when the intensity adjustment factor is a positive intensity adjustment factor, the boundary range corresponding to the spatial subset of the load master nodes for regional division becomes larger within the data processing load range of the corresponding data monitoring point, and vice versa.

[0097] Set a data monitoring point based on each spatial subset of the load master nodes for regional division that has been divided to obtain a set of data monitoring points, and construct a directed monitoring connection relationship based on the data transmission direction and the execution priority order of control instructions between the spatial subsets of the load master nodes for regional division corresponding to the set of data monitoring points;

[0098] Obtain a secondary monitoring node chain based on the directed monitoring connection relationship and the set of data monitoring points;

[0099] Based on the secondary monitoring node chain, through a random algorithm combined with a discrimination algorithm, construct a random data collection index chain between each data monitoring point in the secondary monitoring node chain and each associated fault node set within the corresponding spatial subset of the load master nodes for regional division, and set data collection rules for the random data collection index chain corresponding to the same data monitoring point.

[0100] Further, the data collection rules in this embodiment include:

[0101] For nodes with a causal relationship in all associated faulty node sets in the subset space of the load master nodes in the same area division and nodes with an associated strength equal to or above medium in the corresponding ordinary directed association strength, set the same data collection frequency;

[0102] For each associated faulty node set, the corresponding random data collection index chain randomly collects data from only one node in the associated faulty node set at a time, and marks the collected data with the label serial number of the corresponding associated faulty node set;

[0103] Configure the acquisition frequency fluctuation mapping function of the intensity adjustment factor and the data collection frequency, and configure the acquisition frequency fluctuation mapping function into all random data collection index chains;

[0104] When the current intensity adjustment factor changes, the data collection frequency corresponding to the random data collection index chain is adjusted in real time through the acquisition frequency fluctuation mapping function.

[0105] Further, in this embodiment, when the change corresponding to the intensity adjustment factor exceeds the normal change threshold, the corresponding acquisition frequency also continuously increases.

[0106] Further, the construction steps of the distributed edge hierarchical control chain in this embodiment include:

[0107] Construct a distributed federated tracking control model based on the distributed federated algorithm combined with the reinforcement learning algorithm, and deploy the edge tracking control sub-model in the distributed federated tracking control model to each data monitoring point to obtain an edge control node set;

[0108] Based on the association coupling between the corresponding nodes in the subset space of the load master nodes in each area division of the data monitoring point set and the operation priority of the device sub-components, construct the information sharing connection relationship corresponding to the two-by-two edge control nodes in the edge control node set;

[0109] Based on the edge control node set and the information sharing connection relationship, obtain the distributed edge hierarchical control chain.

[0110] Further, the acquisition steps of the multi-level tracking control space and the two-way feedback control instruction in this embodiment include:

[0111] Based on the three-dimensional first-level directed electromechanical device simulation subnet, perform electromechanical device operation simulation, and at the same time collect data from the nodes corresponding to the three-dimensional first-level directed electromechanical device simulation subnet through the dynamic acquisition frequency configured by the secondary monitoring node chain combined with the acquisition frequency fluctuation mapping function to obtain the simulation tracking data set space;

[0112] Divide the dataset obtained by partitioning the corresponding region in the analog tracking dataset space into subsets of load master nodes and synchronously input it into the corresponding edge control nodes. Use the configured discrimination algorithm to discriminate the operating states of the corresponding acquisition nodes and the associated fault node sets, obtain a multi-level tracking control space, and mark the label numbers of the associated fault node sets corresponding to the acquisition nodes.

[0113] Further, the steps of discriminating the operating states of the corresponding acquisition nodes and the associated fault node sets in this embodiment include:

[0114] If a fault is detected in the corresponding acquisition node, perform secondary discrimination on the associated fault nodes using the Bayesian algorithm and the associated fault accuracy threshold, and output the discrimination fault results and location information corresponding to the acquisition node and the associated fault nodes with faults detected in the secondary discrimination.

[0115] If no fault is detected in the corresponding acquisition node but a fault exists in the associated fault node set, obtain the location information and fault results corresponding to the acquisition node with a fault through the Bayesian algorithm and the associated fault accuracy threshold corresponding to the nodes in the associated fault node set.

[0116] Based on the discrimination accuracy rate of the fault operating states of the corresponding acquisition nodes and the associated fault node sets in the multi-level tracking control space and in combination with a preset discrimination accuracy threshold, adjust the intensity adjustment factor and the dynamic acquisition frequency through a three-dimensional simulation algorithm, and perform cyclic simulation training on the overall electromechanical equipment operation state tracking process corresponding to the three-dimensional primary directed electromechanical equipment simulation subnet, the secondary monitoring node chain, and the distributed edge-level control chain.

[0117] When the discrimination accuracy rate of the fault operating states of the corresponding acquisition nodes and the associated fault node sets is greater than the preset discrimination accuracy threshold, output the discrimination results corresponding to each edge control node.

[0118] According to the discrimination results corresponding to each edge control node, generate corresponding two-way feedback control instructions through the edge tracking control sub-model configured in the corresponding edge control node.

[0119] Share the two-way feedback control instructions along the direction of the distributed edge-level control chain according to the priority of the corresponding edge control node in the distributed edge-level control chain.

[0120] Meanwhile, the two-way feedback control instructions are transmitted along the random data acquisition index chain to the nodes in the associated fault node set corresponding to the existing discrimination faults for association control and fault warning, and the corresponding fault warnings are feedback uploaded to the edge warning interface. At the same time, according to the mapping relationship between the fault severity and the intensity adjustment factor, the color type and color depth of the directed connection relationship of the three-dimensional first-level directed electromechanical equipment simulation subnet are dynamically adjusted and displayed in real time.

[0121] Furthermore, when a fault occurs in the sub-component corresponding to a node, the degree of influence on the associated sub-components will change, that is, the association strength between the corresponding nodes will change. When the association strength changes, the color type mapping and color depth mapping of the directed connection relationship between the corresponding nodes will change in real time. Through this visual change, it is possible to better track and monitor the operating status of the corresponding sub-components and determine whether there are abnormalities in the corresponding sub-components.

[0122] Taking the above air conditioning and ventilation system as an example, the corresponding data acquisition and status discrimination process includes:

[0123] Based on the three-dimensional first-level directed electromechanical equipment simulation subnet, the operation of the air conditioning and ventilation system is simulated. At the same time, the secondary monitoring node chain combines the dynamic acquisition frequency to collect data from the nodes of the simulation subnet to obtain the simulation tracking dataset space. The dataset of the load main node subset space in the corresponding area is input into the edge control node, and the operation status of the acquisition node and the associated fault node set is judged through the discrimination algorithm, and the label serial number is marked to obtain the multi-level tracking control space. For example, if it is found that the data of a certain temperature sensor acquisition node is abnormal, the associated nodes such as the air conditioner unit are re-discriminated through the Bayesian algorithm and the associated fault accuracy threshold.

[0124] The loop training and instruction generation process includes:

[0125] According to the discrimination accuracy rate and the preset discrimination accuracy rate threshold, the intensity adjustment factor and the dynamic acquisition frequency are adjusted through the three-dimensional simulation algorithm, and the whole system is loop-simulated and trained. When the discrimination accuracy rate is greater than the preset discrimination accuracy rate threshold, the discrimination result of the edge control node is output. According to the result, a two-way feedback control instruction is generated through the edge tracking control sub-model, shared along the distributed edge hierarchical control chain, and transmitted to the fault node through the random data acquisition index chain for association control and fault warning, and then feedback to the edge warning interface. At the same time, according to the mapping relationship between the fault severity and the intensity adjustment factor, the color type and depth of the directed connection relationship of the three-dimensional first-level directed electromechanical equipment simulation subnet are dynamically adjusted and displayed. For example, when the air conditioner compressor fails severely, the color of the corresponding connection relationship becomes red and the depth deepens, intuitively presenting the fault state.

[0126] Furthermore, from the perspective of data collection and analysis in this embodiment, the use of the adaptive clustering algorithm and the Bayesian algorithm for probability clustering of fault frequencies and associated fault information can accurately identify the associated fault node set. Then, combined with the three-dimensional simulation algorithm and the Bayesian algorithm, the fault probability is obtained and simulation training is carried out to ensure that the obtained associated fault node set has a high accuracy rate, laying a foundation for subsequent accurate monitoring. By establishing an association between the intensity adjustment factor and the spatial boundary range of the regional division load main node subset and the data collection frequency, the monitoring range and data collection frequency can be adjusted in real time according to changes such as energy transfer, electromagnetic coupling, and control delay. When the intensity adjustment factor changes beyond the normal threshold, the collection frequency is dynamically adjusted to ensure the pertinence and timeliness of data collection.

[0127] In terms of monitoring network construction, based on the hypergraph segmentation algorithm, combined with the directed association strength, spatial distance, functional consistency, and maximum load processing energy, the regional division load main node set is divided, and the boundary range is adjusted in real time, which can effectively optimize the monitoring area and balance the data processing load. A secondary monitoring node chain and a random data collection index chain are constructed, and reasonable data collection rules are set. Different collection frequencies are set for nodes with different association strengths, and tags are randomly collected and numbered. The collection frequency is adjusted in real time in cooperation with the collection frequency fluctuation mapping function, which not only ensures the comprehensiveness of data but also avoids data redundancy and improves the monitoring efficiency.

[0128] For equipment status tracking and control, the three-dimensional first-level directed electromechanical equipment simulation subnet and the secondary monitoring node chain are used to obtain the simulation tracking data set space. The discriminant algorithm and the Bayesian algorithm are used to discriminate the operating states of the collection nodes and the associated fault node set, and a multi-level tracking control space is constructed. Then, the intensity adjustment factor and the dynamic collection frequency are optimized through cyclic simulation training to ensure the discrimination accuracy rate. When the discrimination accuracy rate reaches the standard, two-way feedback control instructions are generated, shared and transmitted along the distributed edge-level control chain to the fault nodes for associated control and fault warning. At the same time, the warning is fed back to the edge warning interface to achieve all-round monitoring and timely response to the equipment. In addition, according to the mapping relationship between the fault severity and the intensity adjustment factor, the color type and depth of the directed connection relationship of the three-dimensional first-level directed electromechanical equipment simulation subnet are dynamically adjusted and displayed, and the color mapping is changed in real time based on the change of the node association strength, enabling the operation and maintenance personnel to more intuitively and accurately track the operating states of the sub-components through visualization means, timely judge whether the sub-components are abnormal, greatly improving the efficiency and accuracy of equipment operation and maintenance and effectively ensuring the stable operation of the equipment.

[0129] The embodiments of the present invention have been described above in conjunction with the accompanying drawings. However, the present invention is not limited to the above specific embodiments. The above specific embodiments are merely illustrative rather than restrictive. Under the inspiration of the present invention, those of ordinary skill in the art can also make changes, modifications, substitutions, and variations to the above embodiments without departing from the spirit of the present invention and the scope protected by the claims. All of these fall within the protection scope of the present invention.

Claims

1. A dynamic tracking method for electromechanical equipment based on multi-source heterogeneous data and edge computing, characterized in that including: a preset device operation and maintenance monitoring network, determining a distributed edge - level control chain according to the distribution and operation attribute data of electromechanical devices in the device operation and maintenance monitoring network; combining the data monitored by the device operation and maintenance monitoring network through the distributed edge - level control chain, and obtaining a multi - level tracking control space and a two - way feedback control instruction through a configured distributed reinforcement control model; based on the multi - level tracking control space and the two - way feedback control instruction, performing the uplink feedback of electromechanical devices and the downlink electromechanical instruction control; the distributed edge - level control chain is constructed by combining the distribution state, operation load of electromechanical devices in the device operation and maintenance monitoring network and the correlation coefficient of the corresponding monitoring devices under each level of control nodes through a graph algorithm; the device operation and maintenance monitoring network includes a first - level directed electromechanical device simulation subnet and a second - level monitoring node chain; the construction steps of the first - level directed electromechanical device simulation subnet include: First, construct a first - level node set by extracting the spatial coordinates, function labels of electromechanical device sub - components and operation parameters including energy transmission paths, control instruction priorities, and electromagnetic coupling intensities. Secondly, calculate the directed correlation probability values between nodes based on the Bayesian algorithm combined with energy transmission efficiency, electromagnetic coupling data, and control priorities, and verify and generate a causal node set through a causal analysis algorithm. Thirdly, divide the directed causal correlation intensity and ordinary correlation intensity according to a preset correlation degree interval, and use a hypergraph algorithm to integrate node coordinates and correlation intensities to construct a labeled first - level directed electromechanical device simulation subnet. Fourthly, use a support vector machine kernel function to map the association type and intensity to a preset color gradient, embed a three - dimensional simulation algorithm combined with the HSL model to achieve dynamic color rendering. Finally, fuse the energy transfer delay change rate, electromagnetic coupling intensity change rate, control delay change rate and their positive and negative signs through a multiple regression function, combine with color brightness and chromaticity parameters, generate positive and negative intensity adjustment factors to embed the connection relationship, and dynamically adjust the strength of the directed connection relationship.

2. The dynamic tracking method for electromechanical equipment based on multi-source heterogeneous data and edge computing according to claim 1, characterized in that the construction steps of the first - level directed electromechanical device simulation subnet include: obtain the distribution position, attributes and operation - related dynamic parameters of electromechanical devices, and take each sub - component in the electromechanical device as a node in the device operation and maintenance monitoring network to obtain a first - level node set; the distribution position and attributes of the electromechanical device include the spatial coordinates, function labels and operation - related dynamic parameters corresponding to each sub - component; the operation - related dynamic parameters include: the energy transmission path, control instruction transmission priority and electromagnetic coupling intensity corresponding to each sub - component; according to the energy transmission path, electromagnetic coupling intensity, energy transmission efficiency and control instruction transmission priority among the operation - related dynamic parameters of each node of the electromechanical device, obtain the directed correlation probability values between each node through the Bayesian algorithm; take the directed correlation probability values between each node as the causal relationship verification factor between two nodes, and verify the causal relationship between each node through a causal analysis algorithm to obtain the causal node set corresponding to the first - level node set.

3. The dynamic tracking method for electromechanical equipment based on multi-source heterogeneous data and edge computing according to claim 2, wherein, the construction steps of the first - level directed electromechanical device simulation subnet further include: based on the directed correlation probability values between each node combined with a preset correlation degree interval, obtain the directed correlation intensity between each node; According to the nodes with causal relationships and the nodes without causal relationships in the first-level node set, the directed association strength between each pair of nodes is divided into directed causal association strength and ordinary directed association strength; Taking the directed causal association strength and the ordinary directed association strength as the directed connection relationships between each pair of nodes, and combining with the first-level node set and the corresponding position coordinates, a first-level directed electromechanical equipment simulation subnet is obtained through the hypergraph algorithm. At the same time, through the automatic annotation algorithm, the corresponding directed causal association strength and ordinary directed association strength are marked on the directed connection relationships.

4. The dynamic tracking method for electromechanical equipment based on multi-source heterogeneous data and edge computing according to claim 3, wherein, The construction steps of the first-level directed electromechanical equipment simulation subnet further include: Based on the type and association strength of the directed connection relationships between the nodes in the first-level directed electromechanical equipment simulation subnet, through a preset color mapping table and the kernel function in the support vector machine, a color mapping function for each type of directed association relationship and the corresponding association strength is constructed; The color mapping table includes color types and color level gradients; The color mapping function for each type of directed association relationship and the corresponding association strength is built into the directed connection relationship between the corresponding nodes; At the same time, the first-level directed electromechanical equipment simulation subnet with the built-in color mapping function is input into the 3D simulation algorithm and combined with the HSL model. According to the type and the change of the association strength of the directed connection relationships between the nodes, the color, the corresponding brightness and chromaticity changes of the directed connection relationships between the nodes in the first-level directed electromechanical equipment simulation subnet are simulated and verified, and a 3D first-level directed electromechanical equipment simulation subnet is obtained.

5. The dynamic tracking method for electromechanical equipment based on multi-source heterogeneous data and edge computing according to claim 4, characterized in that, Each connection relationship in the first-level directed electromechanical equipment simulation subnet has a built-in strength adjustment factor; the strength adjustment factor includes a positive strength adjustment factor and a negative strength adjustment factor; The strength adjustment factor is obtained by fitting through a multiple regression function according to the energy transfer delay change rate, the electromagnetic coupling strength change rate, and the control delay change rate, as well as the positive and negative signs corresponding to the energy transfer delay change rate, the electromagnetic coupling strength change rate, and the control delay change rate, and the brightness and chromaticity of the color corresponding to the directed connection relationship.

6. The dynamic tracking method for electromechanical equipment based on multi-source heterogeneous data and edge computing according to claim 5, wherein, The construction steps of the second-level monitoring node chain include: Obtaining the failure frequency corresponding to each node, the corresponding associated failure nodes, and the corresponding associated failure frequencies in the 3D first-level directed electromechanical equipment simulation subnet; Based on the obtained failure frequency corresponding to each node, the corresponding associated failure nodes, and the corresponding associated failure frequencies, probability clustering is performed through the adaptive clustering algorithm combined with the Bayesian algorithm to obtain an associated failure node set; According to the associated failure node set, through the 3D simulation algorithm in the 3D first-level directed electromechanical equipment simulation subnet, when a node in the corresponding associated failure node set fails, the probability of the corresponding associated failure node failing obtained through the Bayesian algorithm is simulated; Based on the obtained probability of the corresponding associated failure node failing and combining with a preset associated failure accuracy threshold, probability clustering simulation training is performed to obtain all associated failure node sets that meet the associated failure accuracy threshold.

7. The dynamic tracking method for electromechanical equipment based on multi-source heterogeneous data and edge computing according to claim 6, wherein The construction steps of the second-level monitoring node chain further include: Obtain the node with the largest data collection load in each associated fault node set as the load master node for the regional division of the corresponding associated fault node set, and obtain the set of load master nodes for regional division; Based on the directed causal association strength and ordinary directed association strength marked corresponding to the directed connection relationship in the associated fault node set, the spatial distance between the edge nodes between the associated fault node sets, the functional consistency and causal association strength, and the maximum load processing energy corresponding to each tracking control node in the distributed edge hierarchical control chain, combined with the condition of minimizing the directed association strength between the divided regions and maximizing the directed association strength between each associated fault node set within the region, perform regional division on the set of load master nodes for regional division through the hypergraph partitioning algorithm, and obtain the space of the subset of load master nodes for regional division after division; Based on the space of the subset of load master nodes for regional division after division, combined with the strength adjustment factor and the maximum load processing energy corresponding to each tracking control node in real time, adjust the boundary range corresponding to the space of each subset of load master nodes for regional division in real time through the three-dimensional simulation algorithm combined with the hypergraph partitioning algorithm.

8. The dynamic tracking method for electromechanical equipment based on multi-source heterogeneous data and edge computing according to claim 7, characterized in that, The construction steps of the secondary monitoring node chain further include: Set a data monitoring point based on each subset of load master nodes for regional division after division, obtain the set of data monitoring points, and construct a directed monitoring connection relationship based on the data transmission direction and the execution priority order of control instructions between the subsets of load master nodes for regional division corresponding to the set of data monitoring points; Obtain the secondary monitoring node chain based on the directed monitoring connection relationship and the set of data monitoring points; Based on the secondary monitoring node chain, construct a random data collection index chain between each data monitoring point in the secondary monitoring node chain and each associated fault node set within the corresponding subset of load master nodes for regional division through the random algorithm combined with the discrimination algorithm, and set data collection rules for the random data collection index chains corresponding to the same data monitoring point.

9. The dynamic tracking method for electromechanical equipment based on multi-source heterogeneous data and edge computing according to claim 8, characterized in that The construction steps of the distributed edge hierarchical control chain include: Construct a distributed federated tracking control model based on the distributed federated algorithm combined with the reinforcement learning algorithm, and deploy the edge tracking control sub-model in the distributed federated tracking control model to each data monitoring point to obtain the set of edge control nodes; Construct the information sharing connection relationship corresponding to each pair of edge control nodes in the set of edge control nodes based on the association coupling between the nodes corresponding to each subset of load master nodes for regional division in the set of data monitoring points and the operation priority of the device sub-components; Obtain the distributed edge hierarchical control chain based on the set of edge control nodes and the information sharing connection relationship.

10. The dynamic tracking method for electromechanical equipment based on multi-source heterogeneous data and edge computing according to claim 9, wherein The data collection rules include: Set the same data collection frequency for the nodes with causal relationships in all associated fault node sets in the same subset of load master nodes for regional division and the nodes with an association strength of medium or above in the corresponding ordinary directed association strength; Each random data collection index chain corresponding to an associated fault node set randomly collects data from only one node in the associated fault node set at a time, and marks the collected data with the label serial number of the corresponding associated fault node set. Configure an acquisition frequency fluctuation mapping function for the intensity adjustment factor and data acquisition frequency, and configure the acquisition frequency fluctuation mapping function into all random data acquisition index chains; When the current intensity adjustment factor changes, the data acquisition frequency corresponding to the random data acquisition index chain is adjusted in real time through the acquisition frequency fluctuation mapping function.

11. The dynamic tracking method for electromechanical equipment based on multi-source heterogeneous data and edge computing according to claim 10, characterized in that, The steps for obtaining the multi-level tracking control space and two-way feedback control instructions include: Based on the three-dimensional first-level directed electromechanical device simulation subnet, perform electromechanical device operation simulation. At the same time, through the second-level monitoring node chain and the dynamic acquisition frequency configured by the acquisition frequency fluctuation mapping function, data acquisition is performed on the nodes corresponding to the three-dimensional first-level directed electromechanical device simulation subnet to obtain a simulated tracking dataset space; The dataset obtained by dividing the corresponding region in the simulated tracking dataset space into the load main node subset space is synchronously input into the corresponding edge control node. Through the configured discrimination algorithm, the operation states of the corresponding acquisition node and the associated fault node set are discriminated to obtain the multi-level tracking control space and mark the label numbers of the associated fault node sets corresponding to the acquisition node; Based on the discrimination accuracy rate of the operation states of the corresponding acquisition node and the associated fault node set in the multi-level tracking control space, combined with the preset discrimination accuracy rate threshold, the intensity adjustment factor and the dynamic acquisition frequency are adjusted through a three-dimensional simulation algorithm. The overall electromechanical device operation state tracking process corresponding to the three-dimensional first-level directed electromechanical device simulation subnet, the second-level monitoring node chain, and the distributed edge level control chain is subjected to cyclic simulation training; When the discrimination accuracy rate of the operation states of the corresponding acquisition node and the associated fault node set is greater than the preset discrimination accuracy rate threshold, the discrimination results corresponding to each edge control node are output.

12. The method for dynamically tracking electromechanical equipment based on multi-source heterogeneous data and edge computing according to claim 11, wherein The steps for obtaining the multi-level tracking control space and two-way feedback control instructions further include: According to the discrimination results corresponding to each edge control node, corresponding two-way feedback control instructions are generated through the edge tracking control sub-model configured by the corresponding edge control node; Share the two-way feedback control instructions along the direction of the distributed edge level control chain according to the priority of the corresponding edge control node in the distributed edge level control chain; At the same time, transmit the two-way feedback control instructions along the random data acquisition index chain to the nodes in the associated fault node set with discrimination faults for associated control and fault warning, and feedback and upload the corresponding fault warning to the edge warning interface. At the same time, according to the mapping relationship between the fault severity and the intensity adjustment factor, the color type and color depth of the directed connection relationship corresponding to the three-dimensional first-level directed electromechanical device simulation subnet are adjusted and displayed in real time dynamically.

13. The dynamic tracking method for electromechanical equipment based on multi-source heterogeneous data and edge computing according to claim 11, characterized in that, The steps for discriminating the operation states of the corresponding acquisition node and the associated fault node set include: If a fault is discriminated in the corresponding acquisition node, the associated fault nodes are secondarily discriminated through the Bayesian algorithm and the associated fault accuracy rate threshold, and the discrimination fault results and location information corresponding to the acquisition node and the associated fault nodes with secondary discrimination faults are output; If it is determined that there is no fault in the corresponding acquisition node while there is a fault in the associated fault node set, the position information and fault results corresponding to the acquisition node with a fault are obtained through the corresponding Bayesian algorithm and the associated fault accuracy threshold among the nodes in the associated fault node set.

Images