State perception and hidden danger assessment method and system based on switch cabinet

Abstract

The invention discloses a state sensing and hidden danger assessment method and system based on a switch cabinet, and relates to the technical field of power equipment monitoring, and the method comprises the steps: collecting the state data of the switch cabinet in real time; transmitting the switch cabinet state data to a cloud server through the Internet of Things; after receiving the switch cabinet state data, the cloud server performs distributed encryption storage on the switch cabinet state data by using a block chain method; adopting a biological heuristic swarm intelligence algorithm to carry out self-adaptive optimization on the switch cabinet state data which are stored in a distributed encryption manner, and identifying an abnormal state; constructing a multi-dimensional clustering risk factor through a multi-dimensional clustering algorithm based on the fault risk factor; and predicting hidden dangers existing in the switch cabinet through the multi-dimensional clustering risk factors, and generating a fault prediction report. According to the method, the data identification abnormal state is optimized through the biological heuristic algorithm, and the fault prediction precision is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power equipment monitoring, and particularly to a method and system for state perception and hidden danger assessment based on switchgear. Background Art

[0002] In recent years, with the intelligent and digital transformation of power equipment, the switchgear, as an important power facility, its state monitoring and hidden danger assessment have gradually become the core issues in the construction of smart grids. The real-time state perception technology of switchgear gradually relies on advanced technologies such as the Internet of Things, cloud computing, and big data analysis, making the monitoring of equipment status more accurate and real-time. And blockchain technology, due to its decentralized and immutable characteristics, has become an important means to ensure the credibility of switchgear state data in terms of ensuring data storage security and transparency. In addition, bio-inspired swarm intelligence algorithms (such as ant colony algorithms) and machine learning methods have also been widely applied in anomaly detection and prediction models, and the accuracy and adaptive ability of data analysis can be improved by optimizing the algorithms.

[0003] However, existing technical solutions often have problems such as inefficient data storage and management, and low accuracy in abnormal state recognition and fault prediction. Traditional data storage methods may face the risks of single-point failures and data tampering, and existing anomaly recognition and hidden danger assessment methods have certain limitations in dealing with complex multi-dimensional switchgear states. Therefore, how to use more advanced and secure technologies to improve the intelligent management level of switchgear has become an important direction of current technological development. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a method for state perception and hidden danger assessment based on switchgear to solve the problems of the security of switchgear state data storage, low accuracy in abnormal state recognition, and low accuracy in fault risk assessment.

[0006] To solve the above technical problems, the present invention provides the following technical solutions:

[0007] In the first aspect, the present invention provides a method for state perception and hidden danger assessment based on switchgear, which includes: collecting switchgear state data in real time;

[0008] transmitting the switchgear state data to a cloud server through the Internet of Things;

[0009] After receiving the switchgear state data, the cloud server uses the blockchain method to perform distributed encrypted storage on the switchgear state data;

[0010] Adopt a bio-inspired swarm intelligence algorithm to adaptively optimize the status data of switchgear for distributed encrypted storage and identify abnormal statuses;

[0011] Conduct multi-dimensional evaluation on abnormal statuses, quantify the impact of switchgear status data in different dimensions on fault risks through multiple regression analysis, and output fault risk factors;

[0012] Based on the fault risk factors, construct multi-dimensional clustering risk factors through a multi-dimensional clustering algorithm;

[0013] Predict potential hazards in the switchgear through multi-dimensional clustering risk factors and generate a fault prediction report.

[0014] As a preferred solution of the switchgear-based status perception and hazard assessment method described in the present invention, wherein: the step of transmitting the switchgear status data to the cloud server through the Internet of Things is as follows,

[0015] Use edge computing to calibrate, denoise, and timestamp the switchgear status data to generate standard status data;

[0016] Adopt a distributed encryption mechanism to fragment and encrypt the standard status data, and associate each piece of encrypted standard status data through a hash chain, and encapsulate it into a structured data packet;

[0017] Dynamically aggregate the structured data packets through an Internet of Things gateway to form an aggregated data block;

[0018] Transmit the aggregated data block to the cloud server through the MQTT protocol.

[0019] As a preferred solution of the switchgear-based status perception and hazard assessment method described in the present invention, wherein: after the cloud server receives the switchgear status data, use the blockchain method to perform distributed storage on the switchgear status data, and the specific steps are as follows,

[0020] Adopt a smart contract to verify data block tampering and perform secondary encryption using the public key encryption method; save the data block after secondary encryption, the hash chain, and the timestamp marking information through the cloud server;

[0021] Use the cloud server as a node in the distributed storage network to integrate and generate a new block;

[0022] When generating a new block, verify the consistency of the hash value of the new block with the hash value of the previous block to form a data chain;

[0023] According to the POW consensus, verify the position of the new block data chain and store it in the blockchain to expand the existing data chain.

[0024] As a preferred solution of the switchgear-based state perception and hidden danger assessment method of the present invention, wherein: the bio-inspired swarm intelligence algorithm is used to adaptively optimize the switchgear state data stored in a distributed and encrypted manner to identify abnormal states. The specific steps are as follows:

[0025] Convert the data chain in the distributed storage into a high-dimensional data point, and construct ant colony agents to search for the optimal pattern in the data space;

[0026] Introduce topology optimization, construct the mutual relationship of ant colony agents with a fractal network topology, and use the topological structure to globally analyze and optimize the information transmission and cooperation of ant colony agents through self-similarity;

[0027] Based on the state of the ant colony agents, use the adaptive particle swarm optimization algorithm for clustering analysis to obtain the abnormal degree of the ant colony agent state;

[0028] Set the state determination threshold to τ;

[0029] If δ(t)>τ, it means that the ant colony data block is in an abnormal state;

[0030] If δ(t)≤τ, it means that the ant colony data block is in a normal state.

[0031] As a preferred solution of the switchgear-based state perception and hidden danger assessment method of the present invention, wherein: the abnormal state is evaluated in multiple dimensions, and the influence of switchgear state data in different dimensions on the fault risk is quantified through multiple regression analysis, and the fault risk factor is output. The specific steps are as follows:

[0032] Use the blockchain to extract the switchgear state data, adopt Z-score standardization, and normalize the switchgear data and the abnormal state to obtain the normalized state parameters;

[0033] Adopt the time series analysis tool to construct a multi-dimensional feature space with the normalized state parameters;

[0034] For the multi-dimensional feature space, adopt multiple regression analysis to obtain the influence of the fault risk through historical fault data;

[0035] Verify the influence of the obtained fault risk through multiple regression and output the fault risk factor.

[0036] As a preferred solution of the switchgear-based state perception and hidden danger assessment method of the present invention, wherein: based on the fault risk factor, a multi-dimensional clustering risk factor is constructed through a multi-dimensional clustering algorithm. The specific steps are as follows:

[0037] Adopt the hierarchical clustering algorithm to form a dendrogram with the fault risk factors for clustering analysis;

[0038] Based on the clustering results, use Bayesian inference to dynamically update the clustering results, and adjust the fault risk factors of the clustering centers according to the historical switchgear data;

[0039] Based on the adjusted clustering fault risk factors, use Bayesian network to update the relationship between the fault risk factors of each clustering;

[0040] According to the switchgear status data and the posterior probability of the updated clustering fault factors, dynamically adjust the multi-dimensional clustering risk factors.

[0041] As a preferred solution of the switchgear-based status perception and hidden danger assessment method described in the present invention, wherein: predicting the hidden dangers existing in the switchgear through the multi-dimensional clustering risk factors, and generating a fault prediction report, the specific steps are as follows.

[0042] Use the multi-dimensional clustering risk factors, and use Bayesian network inference to dynamically update the multi-dimensional clustering centers, and re-evaluate and adjust the multi-dimensional clustering risk factors;

[0043] Extract the historical switchgear status fault data through the blockchain, and fine-tune the adjusted multi-dimensional clustering risk factor center to obtain the latest multi-dimensional clustering risk factor analysis result;

[0044] Based on the latest multi-dimensional clustering risk factor analysis result, list the hidden dangers existing in the switchgear corresponding to the clustering risk factors of each dimension and the probability of the occurrence of the hidden dangers, and generate a detailed fault prediction report.

[0045] In the second aspect, the present invention provides a switchgear-based status perception and hidden danger assessment system, including a data acquisition module, a data transmission module, a data storage module, an anomaly detection module, a risk assessment module, a clustering modeling module, and a prediction report module;

[0046] The data acquisition module collects switchgear status data in real time;

[0047] The data transmission module transmits the switchgear status data to the cloud server through the Internet of Things;

[0048] The data storage module, after the cloud server receives the switchgear status data, uses the blockchain method to perform distributed encrypted storage on the switchgear status data;

[0049] The anomaly detection module uses a bio-inspired swarm intelligence algorithm to adaptively optimize the distributed encrypted storage of switchgear status data and identify abnormal states;

[0050] The risk assessment module performs multi-dimensional assessment on the abnormal state, quantifies the influence of switchgear status data in different dimensions on the fault risk through multiple regression analysis, and outputs fault risk factors;

[0051] The clustering and modeling module constructs multi-dimensional clustering risk factors through a multi-dimensional clustering algorithm based on fault risk factors.

[0052] The prediction report module predicts potential hazards in the switchgear through multi-dimensional clustering risk factors and generates a fault prediction report.

[0053] In a third aspect, the present invention provides a computer device, including a memory and a processor, where the memory stores a computer program, and: when the computer program is executed by the processor, any step of the method for state perception and potential hazard assessment based on switchgear as described in the first aspect of the present invention is implemented.

[0054] In a fourth aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored, and: when the computer program is executed by the processor, any step of the method for state perception and potential hazard assessment based on switchgear as described in the first aspect of the present invention is implemented.

[0055] The beneficial effects of the present invention are as follows: The present invention combines Internet of Things, blockchain technology and bio-inspired swarm intelligence algorithm to provide an efficient solution for state data collection, encrypted storage and anomaly identification of switchgear. Data is transmitted through the Internet of Things and blockchain is used to ensure data security and immutability, avoiding the risk of single-point failure. The bio-inspired algorithm optimizes data to identify abnormal states, improving the accuracy of fault prediction. Based on multi-dimensional fault risk factor assessment and clustering analysis, it can accurately evaluate the impact of each dimension on the risk, generate accurate fault prediction reports, thereby enhancing the intelligence and security of the system and reducing the operation risk of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can obtain other drawings according to these drawings without creative efforts.

[0057] Figure 1 It is a flowchart of the method for state perception and potential hazard assessment based on switchgear in Embodiment 1.

[0058] Figure 2 It is a module diagram of the system for state perception and potential hazard assessment based on switchgear in Embodiment 1. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0059] Embodiment 1, referring to Figure 1 and Figure 2, which is the first embodiment of the present invention. This embodiment provides a method for state perception and hidden danger assessment based on switchgear, including the following steps:

[0060] S1. Collect switchgear state data in real time.

[0061] Furthermore, the switchgear state data includes temperature data, humidity data, and voltage data;

[0062] Specifically, multiple sensors need to be installed in the switchgear to monitor these key parameters first. The temperature sensor can detect the temperature change inside the switchgear in real time, and the humidity sensor is used to monitor the environmental humidity to prevent equipment failures caused by excessive moisture; the voltage sensor is responsible for monitoring the voltage fluctuation of the power. Each sensor transmits the collected data to the edge computing device through the Internet of Things technology for preliminary data calibration, denoising, and timestamp marking. After being processed by edge computing, the data is packaged in a standard format and ready to be transmitted to the cloud server for further analysis and storage. This can ensure that the switchgear state data can timely and accurately reflect the equipment operation situation and provide reliable data support for subsequent fault prediction and risk assessment.

[0063] S2. Transmit the switchgear state data to the cloud server through the Internet of Things.

[0064] Furthermore, use edge computing to perform data calibration, denoising, and timestamp marking on the switchgear state data to generate standard state data;

[0065] Adopt a distributed encryption mechanism to fragment and encrypt the standard state data, and associate each piece of encrypted standard state data through a hash chain to encapsulate it into a structured data packet;

[0066] It should be noted that the distributed encryption mechanism refers to enhancing the security and anti-tampering ability of data by splitting the data into several parts and encrypting and storing them on multiple nodes. In the present invention, after being processed by edge computing, the standard state data is fragmented and encrypted and associated through a hash chain. This encryption mechanism effectively avoids the risks of single-point failure and data leakage, is particularly suitable for the management of large-scale Internet of Things devices, and improves the security and privacy protection of data.

[0067] Dynamically aggregate the structured data packets through the Internet of Things gateway to form an aggregated data block;

[0068] It should be noted that a structured data packet is a way to organize and encapsulate processed data in a certain format. Through structured encapsulation, data can not only improve storage efficiency, but also provide a consistent format for subsequent data processing, reducing the parsing difficulty. In the present invention, the encapsulation of structured data packets helps with data transmission and storage, and better meets the requirements of blockchain and cloud computing. At the same time, through the dynamic aggregation of the Internet of Things gateway, data from different switchgears can be effectively integrated, optimizing the efficiency and accuracy of data transmission.

[0069] The aggregated data blocks are transmitted to the cloud server through the MQTT protocol.

[0070] Specifically, using the MQTT protocol makes the transmission of switchgear status data more efficient and stable. The lightweight feature of the MQTT protocol makes it particularly suitable for large-scale data transmission of Internet of Things devices. Compared with the traditional HTTP protocol, MQTT can provide more efficient and real-time message delivery in an environment with limited or unstable bandwidth. Through the MQTT protocol, data can be transmitted to the cloud server more quickly and reliably, providing real-time basic data support for subsequent data processing, analysis, and fault prediction.

[0071] Preferably, through the combination of edge computing, distributed encryption, hash chain, and the MQTT protocol, not only the security, real-time performance, and reliability of switchgear data management are improved, but also precise technical guarantees are provided for fault prediction and hidden danger assessment, effectively improving the intelligent level and operation safety of power facilities.

[0072] S3. After the cloud server receives the switchgear status data, it uses the blockchain method to perform distributed encrypted storage on the switchgear status data.

[0073] Furthermore, a smart contract is used to verify data block tampering, and the public key encryption method is used for secondary encryption;

[0074] Specifically, the verification of data block tampering by the smart contract significantly improves the security and integrity of the data. In traditional data storage methods, data tampering and forgery may lead to serious consequences, while the smart contract can perform verification automatically and error-free, greatly improving the efficiency and reliability of data processing. Especially in large-scale Internet of Things or power equipment management, the smart contract can ensure the security and credibility of all data in a distributed environment, avoiding data tampering caused by human or technical problems.

[0075] The data blocks after secondary encryption are saved by the cloud server together with the hash chain and timestamp marking information;

[0076] Specifically, the combination of the hash chain and the timestamp marking enables each piece of data to be accurately marked and traced. In this way, not only can data tampering be prevented, but also the generation time and order of the data can be accurately tracked. This is crucial for device status monitoring and fault prediction because the accuracy of the timestamp determines the accuracy of fault diagnosis. Compared with the prior art, the introduction of the hash chain makes data storage not only more secure but also improves the efficiency and accuracy of data traceability.

[0077] Use the cloud server as a node in the distributed storage network to integrate and generate a new block;

[0078] When generating a new block, perform consistency verification on the hash value of the new block and the hash value of the previous block to form a data chain;

[0079] It should be noted that using the cloud server as a node in the distributed storage network can ensure data redundancy backup and high availability. By dispersing the data storage in multiple nodes, the single point of failure problem that may occur in centralized storage is avoided, and the reliability of data storage is improved. In the present invention, this distributed storage structure ensures that even if some nodes fail, the entire data chain can still maintain integrity and consistency, thus providing higher fault tolerance and data protection.

[0080] According to the POW consensus, verify the position of the new block data chain and store it in the blockchain to expand the existing data chain.

[0081] Specifically, the use of the POW consensus mechanism ensures the effectiveness and legality of the new block. In traditional blockchain applications, the POW consensus can prevent attacks by malicious nodes, ensure that the new blocks in the blockchain network meet the computing requirements, and prevent the generation of "forged" blocks. In the present invention, the POW consensus mechanism effectively solves the data consistency problem in a multi-node environment, ensures the stability and security of the blockchain. Especially in large-scale device management, it can provide strong security guarantees and reliable fault warning mechanisms.

[0082] S4. Adopt a bio-inspired swarm intelligence algorithm to adaptively optimize the switch cabinet status data stored in a distributed and encrypted manner and identify abnormal states. (Dynamic scheduling and load forecasting)

[0083] Furthermore, convert the data chain in the distributed storage into a high-dimensional data point, construct ant colony intelligent agents, and search for the optimal pattern in the data space. The expression is as follows:

[0084] x i (t + 1) = x i (t) + αv i (t);

[0085] where x i represents the position, t represents the time, and v i represents the agent speed, α represents the inertia weight, and i is the quantity;

[0086] It should be noted that based on high-dimensional data analysis, by using the real-time collected switchgear status data (such as temperature, humidity, and voltage), combined with the load change information, the ant colony agent or particle swarm optimization algorithm is used to optimize the scheduling strategy of switchgear equipment. Specifically, when it is predicted that a certain device may fail due to environmental factors (such as too high temperature or too high humidity), the load distribution can be automatically adjusted through dynamic scheduling, and the start and stop of the device can be intelligently controlled, thus avoiding equipment overload or failure. This combination of high-dimensional data analysis and dynamic scheduling makes fault prediction and equipment scheduling more intelligent and accurate, improving the overall efficiency and reliability.

[0087] Introduce topological optimization, construct the relationship between ant colony agents in a fractal network topology, and use the topological structure to conduct overall analysis through self-similarity to optimize the information transmission and cooperation of ant colony agents. The expression is as follows:

[0088]

[0089] where T(x, y) is the optimized ant colony agent, x is the normal state of the ant colony agent, y is the abnormal state of the ant colony agent, f(x) represents the state evaluation of the ant colony agent, f(y) represents the optimization state target of the ant colony agent, d(x, y) represents the distance metric of the ant colony agent, β is the parameter controlling self-similarity, and dx represents the accumulation process of optimizing a certain dimension;

[0090] It should be noted that the fractal network topology has unique advantages in optimizing information transmission and cooperation, which can help the algorithm analyze data flow and trends more accurately. By applying topological optimization to the construction of the data model, the accuracy of load prediction can be improved. Especially in a changing load environment, it can better cope with load fluctuations and make timely adjustments.

[0091] Based on the state of the ant colony agent, use the adaptive particle swarm optimization algorithm for clustering analysis to obtain the abnormality degree of the ant colony agent state. The expression is as follows:

[0092]

[0093] where δ represents the abnormality degree of the ant colony agent state, represents the summation of all ant colony agents, d(x i , x j ) represents the distance metric between ant colony agents, n is the total number of ant colony agents, and σ 2 represents the detection parameter for controlling abnormality, ∥xi -x j ∥ 2 Expressed as the straight-line distance in the agent, x i is the state vector, x j is the state feature;

[0094] Set the state determination threshold to τ;

[0095] When δ(t) > τ, it indicates that the ant colony data block is in an abnormal state;

[0096] When δ(t) ≤ τ, it indicates that the ant colony data block is in a normal state.

[0097] Specifically, the combination of the adaptive particle swarm optimization algorithm and the state anomaly degree can evaluate the anomaly degree in multiple dimensions, and dynamically adjust the criteria for anomaly judgment as the time step changes. This dynamically adjusted mechanism can better adapt to the changing device state and automatically optimize the prediction model according to new data. For example, by calculating the anomaly degree between different ant colony agents, potential hazards in the switchgear can be more accurately identified, especially when the load fluctuates greatly or external environmental factors change violently, which can improve the flexibility and reliability of prediction. In addition, based on this analysis, a real-time fault warning report can be generated to help maintenance personnel take timely measures, thus effectively avoiding accidents.

[0098] S5. Conduct multi-dimensional evaluation on the abnormal state, quantify the influence of switchgear state data in different dimensions on the fault risk through multiple regression analysis, and output the fault risk factor.

[0099] Furthermore, use blockchain to extract switchgear state data, adopt Z-score standardization, and normalize the switchgear data and the abnormal state to obtain the normalized state parameters;

[0100] Specifically, extracting switchgear state data through blockchain technology can ensure that the data is not tampered with during the entire acquisition, storage, and transmission process, improving the reliability and transparency of the data. Combining with Z-score standardization can unify the scale and dimension of the data, eliminate interference between different data types, and make subsequent analysis more accurate.

[0101] Use time series analysis tools to construct a multi-dimensional feature space with the normalized state parameters;

[0102] It should be noted that the state data of the switchgear usually has time series characteristics. Time series analysis tools can effectively capture the time patterns of the switchgear state changes by processing time-dependent relationships. This process maps the data to a multi-dimensional feature space to ensure that the trend of the device state changes can be understood from multiple perspectives.

[0103] For a multi-dimensional feature space, multiple regression analysis is adopted to obtain the impact of fault risks through historical fault data.

[0104] Specifically, multiple regression analysis can comprehensively analyze multiple influencing factors in historical fault data, assign weights to each influencing factor, and thus form a clear fault risk model. Compared with traditional single-factor analysis, multiple regression analysis is more comprehensive, can consider the interaction between multiple factors, and thus can more accurately evaluate fault risks.

[0105] Perform multiple regression verification on the obtained impact of fault risks and output fault risk factors.

[0106] Specifically, the calculated fault risk factors can calculate a quantitative risk value for each device state. This process enables decision-makers to prioritize high-risk devices according to the level of risk factors, thereby optimizing maintenance strategies, reducing unnecessary downtime and maintenance costs, and improving the operation and maintenance efficiency of equipment.

[0107] S6. Based on the fault risk factors, construct multi-dimensional clustering risk factors through a multi-dimensional clustering algorithm.

[0108] It should be noted that the hierarchical clustering algorithm is used to form a dendrogram of the fault risk factors for clustering analysis.

[0109] Specifically, clustering the fault risk factors through the hierarchical clustering algorithm can effectively organize and display the relationships between these factors, and aggregate related factors together according to different similarities. This process not only improves the efficiency of risk factor analysis, but also helps to identify which factors have similar influence patterns under the same fault scenario. Through the structure of the dendrogram, the mutual relationships of various risk factors can be clearly displayed, providing an intuitive basis for subsequent fault prediction and maintenance decision-making.

[0110] Based on the clustering results, use Bayesian inference to dynamically update the clustering results, and adjust the fault risk factors of the clustering center according to the historical switchgear data.

[0111] Specifically, the introduction of Bayesian inference can dynamically adjust the clustering results according to historical data and current switchgear state data. This dynamic update mechanism can cope with changes in equipment states, not only quickly adapt to new data, but also adjust the risk factors of the clustering center according to the actual occurrence of faults, ensuring the accuracy of fault prediction. Compared with traditional static clustering methods, Bayesian inference improves real-time performance and flexibility, and can also cope with fluctuations in equipment states and environmental conditions.

[0112] Based on the adjusted clustering fault risk factors, the Bayesian network is used to update the relationships among the clustering fault risk factors, and the expression is as follows;

[0113] P(θ∣X)=P(X)P(X∣θ)P(θ);

[0114] Among them, P(θ∣X) represents the posterior probability of the updated clustering fault factor, P(X) is the normalization factor, P(X∣θ) represents the observation probability when determining the clustering fault factor, P(θ) is the historical fault risk based on the unobserved fault factor, X is the switchgear equipment status data, and θ is the fault risk factor of the switchgear;

[0115] It should be noted that the Bayesian network can model and capture the complex dependencies among the fault risk factors. Through training based on historical data, the Bayesian network can assign appropriate weights to each fault risk factor, thereby helping the model understand which factors have a more significant impact on the occurrence of faults in different scenarios. This optimization mechanism can not only make judgments on individual factors but also comprehensively consider the interactions among multiple factors, improving the comprehensiveness and accuracy of fault prediction.

[0116] According to the switchgear status data and the posterior probability of the updated clustering fault factor, the multi-dimensional clustering risk factors are dynamically adjusted.

[0117] Specifically, through the dynamic adjustment of the multi-dimensional clustering risk factors, the subtle changes in the equipment status and complex fault patterns can be captured in real time. This adjustment mechanism ensures that the risk factors of each cluster can reflect the actual operating status of the current switchgear and are updated according to real-time data, further improving the accuracy of the fault risk assessment. Through this dynamic adjustment, the accuracy of fault prediction can be continuously optimized under changing environmental and operating conditions, avoiding the biases that may occur based on static models.

[0118] S7. Predict the potential hazards in the switchgear through the multi-dimensional clustering risk factors and generate a fault prediction report.

[0119] Furthermore, using the multi-dimensional clustering risk factors, the Bayesian network inference is used to dynamically update the multi-dimensional clustering centers and re-evaluate and adjust the multi-dimensional clustering risk factors;

[0120] Specifically, by dynamically adjusting the clustering risk factors, not only the fault prediction ability of the equipment is optimized, but also the modern equipment environmental protection design concept is met. Especially in terms of energy efficiency optimization and emission control, the system can accurately identify potential hidden dangers before a fault occurs, and comprehensively consider environmental protection factors such as energy conservation and low nitrogen emissions during the equipment maintenance and optimization process, thereby effectively reducing the environmental impact caused by equipment failures. This comprehensive method can ensure the high efficiency, safety and environmental protection of equipment operation, and truly achieve the balance of multiple goals.

[0121] Extract historical switchgear state fault data through blockchain, fine-tune the adjusted multi-dimensional clustering risk factor center, and obtain the latest multi-dimensional clustering risk factor analysis result;

[0122] Specifically, using blockchain technology to extract historical fault data not only ensures the security of the data, but also provides the most authentic and reliable data support for fine-tuning the clustering risk factors. Through this method, the trust problem in traditional data storage can be eliminated, ensuring the accuracy and reliability of fault prediction. At the same time, the distributed storage of blockchain makes data access more flexible and efficient, helping to process large-scale equipment state data in real time.

[0123] Based on the latest multi-dimensional clustering risk factor analysis result, list the hidden dangers existing in the switchgear corresponding to each dimension of the clustering risk factor and the probability of the occurrence of the hidden dangers, and generate a detailed fault prediction report.

[0124] It should be noted that the automatically generated fault prediction report has high operability, which can help equipment maintenance personnel quickly identify potential hidden dangers and take targeted preventive measures. Through the probability analysis in the report, the operation and maintenance personnel can prioritize the handling of high-risk faults according to the specific risk level, thereby effectively reducing the equipment failure rate and maintenance cost. This method not only improves the accuracy of fault prediction, but also enhances the operation and maintenance efficiency and the scientificity of decision-making.

[0125] This embodiment also provides a state perception and hidden danger assessment system based on switchgear, including: a data acquisition module, a data transmission module, a data storage module, an anomaly detection module, a risk assessment module, a clustering modeling module, and a prediction report module; the data acquisition module is used to collect switchgear state data in real time; the data transmission module transmits the switchgear state data to the cloud server through the Internet of Things; the data storage module, after the cloud server receives the switchgear state data, uses the blockchain method to perform distributed encrypted storage on the switchgear state data; the anomaly detection module uses a bio-inspired swarm intelligence algorithm to adaptively optimize the distributed encrypted storage switchgear state data and identify abnormal states; the risk assessment module conducts multi-dimensional assessments on the abnormal states, quantifies the impact of switchgear state data in different dimensions on the fault risk through multiple regression analysis, and outputs fault risk factors; the clustering modeling module constructs multi-dimensional clustering risk factors based on the fault risk factors through a multi-dimensional clustering algorithm; the prediction report module predicts the hidden dangers existing in the switchgear through the multi-dimensional clustering risk factors and generates a fault prediction report.

[0126] This embodiment also provides a computer device applicable to the situation of the state perception and hidden danger assessment method based on switchgear, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the state perception and hidden danger assessment method based on switchgear proposed in the above embodiment.

[0127] This computer device can be a terminal, and this computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Among them, the processor of this computer device is used to provide computing and control capabilities. The memory of this computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of this computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a carrier network, NFC (Near Field Communication), or other technologies. The display screen of this computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of this computer device can be a touch layer covered on the display screen, or a button, a trackball, or a touchpad set on the computer device shell, or an external keyboard, touchpad, or mouse, etc.

[0128] This embodiment also provides a storage medium, on which a computer program is stored. When the program is executed by a processor, it implements the method for realizing state perception and hidden danger assessment based on switchgear cabinets as proposed in the above embodiment; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, abbreviated as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, abbreviated as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, abbreviated as EPROM), programmable read-only memory (Programmable Red-Only Memory, abbreviated as PROM), read-only memory (Read-Only Memory, abbreviated as ROM), magnetic memory, flash memory, magnetic disk or optical disc.

[0129] In summary, the present invention combines Internet of Things, blockchain technology and bio-inspired swarm intelligence algorithm to provide an efficient solution for state data acquisition, encrypted storage and anomaly recognition of switchgear cabinets. The data is transmitted through the Internet of Things and the blockchain is used to ensure data security and immutability, avoiding the risk of single point of failure. The bio-inspired algorithm optimizes data to identify abnormal states and improves the accuracy of fault prediction. Based on multi-dimensional fault risk factor assessment and clustering analysis, it can accurately evaluate the impact of each dimension on the risk, generate accurate fault prediction reports, thereby enhancing the intelligence and security of the system and reducing the operation risk of the power system.

[0130] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

Claims

1. A state perception and hidden danger assessment method based on a switch cabinet, characterized in that: include, Real-time collection of switch cabinet status data; Transmit switch cabinet status data to cloud servers via the Internet of Things; After receiving the switch cabinet status data, the cloud server uses the blockchain method to perform distributed encrypted storage of the switch cabinet status data; Adopting biologically inspired swarm intelligence algorithm, adaptively optimizing the distributed encrypted storage of switch cabinet status data and identifying abnormal status; Conduct multi-dimensional evaluation of abnormal status, quantify the impact of switchgear status data in different dimensions on fault risk through multivariate regression analysis, and output fault risk factors; Based on the failure risk factors, a multi-dimensional clustering risk factor is constructed through a multi-dimensional clustering algorithm; The hidden dangers in the switch cabinet are predicted through multi-dimensional clustering risk factors, and a fault prediction report is generated.

2. The switch cabinet-based state perception and hidden danger assessment method according to claim 1, characterized in that: The switch cabinet status data includes temperature data, humidity data, and voltage data; The specific steps of transmitting the switch cabinet status data to the cloud server through the Internet of Things are as follows: Use edge computing to calibrate, denoise and timestamp switch cabinet status data to generate standard status data; A distributed encryption mechanism is used to encrypt the standard state data in pieces, and each piece of encrypted standard state data is associated through a hash chain and encapsulated into a structured data packet; Dynamically aggregate structured data packets through the IoT gateway to form aggregated data blocks; The aggregated data blocks are transmitted to the cloud server via the MQTT protocol.

3. The switch cabinet-based state perception and hidden danger assessment method according to claim 2, characterized in that: After the cloud server receives the switch cabinet status data, it uses the blockchain method to perform distributed storage on the switch cabinet status data. The specific steps are as follows: Smart contracts are used to verify data blocks for tampering, and public key encryption is used for secondary encryption; The twice-encrypted data blocks, hash chains, and timestamp information are stored through the cloud server; Use the cloud server as a node in the distributed storage network to integrate and generate new blocks; When a new block is generated, the hash value of the new block is verified to be consistent with the hash value of the previous block to form a data chain; The location of the new block data chain is verified based on the POW consensus and stored in the blockchain to expand the existing data chain.

4. The switch cabinet-based state perception and hidden danger assessment method according to claim 3, characterized in that: The biologically inspired swarm intelligence algorithm is used to adaptively optimize the distributed encrypted storage of switch cabinet status data and identify abnormal states. The specific steps are as follows: Convert the data chain in distributed storage into a high-dimensional data point and build an ant colony agent to search for the optimal pattern in the data space; Introducing topology optimization, the relationship between ant colony agents is constructed with fractal network topology, and the topological structure is used to optimize the information transmission and collaboration of ant colony agents through overall analysis through self-similarity; Based on the state of ant colony agents, cluster analysis is performed using the adaptive particle swarm optimization algorithm to obtain the abnormality of the state of ant colony agents; Set the state judgment threshold to τ; If δ(t)>τ, it means that the ant colony data block is in an abnormal state; If δ(t)≤τ, it means that the ant colony data block is in a normal state.

5. The switch cabinet-based state perception and hidden danger assessment method according to claim 4, characterized in that: The multi-dimensional evaluation of the abnormal state is performed, and the influence of the switch cabinet state data of different dimensions on the fault risk is quantified through multivariate regression analysis, and the fault risk factor is output. The specific steps are as follows: The switch cabinet status data is extracted by blockchain, and Z-score standardization is adopted to normalize the switch cabinet data and abnormal status to obtain normalized status parameters; Using time series analysis tools, normalized state parameters are constructed into a multidimensional feature space; For multidimensional feature space, multiple regression analysis is used to obtain the impact of failure risk through historical failure data; The influence of the obtained failure risk is verified by multiple regression and the failure risk factor is output.

6. The switch cabinet-based state perception and hidden danger assessment method according to claim 5, characterized in that: Based on the fault risk factor, a multi-dimensional clustering risk factor is constructed by a multi-dimensional clustering algorithm. The specific steps are as follows: A hierarchical clustering algorithm is used to construct a tree diagram of the fault risk factors for cluster analysis; Based on the clustering results, Bayesian inference is used to dynamically update the clustering results, and the fault risk factor of the cluster center is adjusted according to the historical switchgear data; Based on the adjusted cluster failure risk factors, the Bayesian network is used to update the relationship between each cluster failure risk factor; According to the switch cabinet status data and the updated clustering fault factor posterior probability, the multi-dimensional clustering risk factor is dynamically adjusted.

7. The switch cabinet-based state perception and hidden danger assessment method according to claim 6, characterized in that: The method of predicting hidden dangers in the switch cabinet by multi-dimensional clustering risk factors and generating a fault prediction report has the following specific steps: Using multidimensional clustering risk factors, Bayesian network inference is used to dynamically update the multidimensional clustering centers, re-evaluate and adjust the multidimensional clustering risk factors; Through blockchain, historical switch cabinet status fault data is extracted, and the adjusted multi-dimensional clustering risk factor center is fine-tuned to obtain the latest multi-dimensional clustering risk factor analysis results; Through the latest multi-dimensional clustering risk factor analysis results, the hidden dangers of the switch cabinet corresponding to each dimensional clustering risk factor and the probability of hidden dangers occurring are listed, and a detailed fault prediction report is generated.

8. A switch cabinet-based state perception and hidden danger assessment system, based on the switch cabinet-based state perception and hidden danger assessment method according to any one of claims 1 to 7, characterized in that: Including data acquisition module, data transmission module, data storage module, anomaly detection module, risk assessment module, cluster modeling module and prediction report module; The data acquisition module collects switch cabinet status data in real time; The data transmission module transmits the switch cabinet status data to the cloud server via the Internet of Things; The data storage module, after receiving the switch cabinet status data, uses the blockchain method to perform distributed encrypted storage on the switch cabinet status data; The anomaly detection module uses a biologically inspired swarm intelligence algorithm to adaptively optimize the distributed encrypted storage of switch cabinet status data and identify abnormal states; The risk assessment module performs a multi-dimensional assessment of the abnormal state, quantifies the impact of switch cabinet state data of different dimensions on the fault risk through multivariate regression analysis, and outputs a fault risk factor; The cluster modeling module constructs a multi-dimensional cluster risk factor based on the fault risk factor through a multi-dimensional clustering algorithm; The prediction report module predicts hidden dangers in the switch cabinet by multi-dimensional clustering risk factors and generates a fault prediction report.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for state perception and hidden danger assessment based on a switch cabinet are implemented as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for state perception and hidden danger assessment based on a switch cabinet according to any one of claims 1 to 7 are implemented.

Images