Equipment security management system and method based on data analysis

Abstract

The invention discloses an equipment safety management system and method based on data analysis, and belongs to the technical field of data analysis, and the method comprises the steps: obtaining basic theory information which comprises related theories of research risk assessment, early warning and big data analysis; acquiring equipment operation data, wherein the equipment operation data comprises real-time voltage, real-time current and an equipment real-time state; performing data preprocessing on the equipment operation data for removing abnormal values, processing missing data and performing standardization processing; extracting key feature data from the preprocessed data, wherein the key feature data comprises voltage fluctuation, current change and equipment load; performing model training according to basic theory information, and evaluating model performance through cross validation; adjusting and optimizing the model according to a verification result; and applying the trained model to equipment operation data, and outputting a possible fault prediction result of the equipment. According to the invention, the real-time monitoring and early warning effects of the equipment are realized.

Description

Technical Field

[0001] The present application relates to the technical field of data analysis, and in particular to a device safety management system and method based on data analysis. Background Art

[0002] With the rapid development of science and technology, the number of equipment in factories has increased significantly, and the complexity of the equipment is also increasing. The increase in the number of equipment and the increase in complexity have made the security threats faced by the equipment increasingly diverse. Technical data analysis refers to the technology of quickly and efficiently analyzing and processing large-scale and complex data sets to extract valuable information and insights. With the rapid development of big data technology, data analysis technology has been widely used in various fields, including equipment safety management.

[0003] Traditional security management methods usually focus on the defense against known threats, but lack effective countermeasures for unknown threats; they are often unable to deal with new security threats faced by current devices. In addition, traditional methods also make it difficult to achieve real-time monitoring and early warning of devices, and it is difficult to detect and deal with security threats in a timely manner. Summary of the invention

[0004] In order to achieve real-time monitoring and early warning of equipment, the present application provides an equipment safety management system and method based on data analysis.

[0005] The present application provides a data analysis-based equipment safety management system and method thereof using the following technical solutions: In a first aspect, the present application provides a device security management method based on data analysis, comprising the following steps: Obtaining basic theoretical information, including research risk assessment, early warning and big data analysis related theories; Acquire equipment operation data, wherein the equipment operation data includes real-time voltage, real-time current, and real-time status of the equipment; Performing data preprocessing on the equipment operation data to remove outliers, process missing data, and perform standardization; Extract key feature data from the preprocessed data, wherein the key feature data includes voltage fluctuation, current change, and equipment load; Based on the basic theoretical information, model training is performed and model performance is evaluated through cross-validation; Adjust and optimize the model based on the validation results; The trained model is applied to the equipment operation data to output the prediction results of possible equipment failures.

[0006] Furthermore, the step of applying the trained model to the equipment operation data and outputting the prediction result of possible equipment failures specifically includes: Querying normal operating data from a preset database, wherein the normal operating data includes a normal voltage range, a normal current range, and a normal device status; Comparing the key feature data with the normal operating data to identify potential risk data, wherein the potential risk data includes abnormal voltage, abnormal current, and abnormal equipment status; Querying risk accident information corresponding to the potential risk data from a preset database; The potential risk data and risk accident information are pushed to the user's smart terminal.

[0007] Furthermore, after the step of pushing the potential risk data and risk accident information to the user's smart terminal, it also includes: Compare the potential risk data with the normal operating data, and calculate abnormal voltage difference, abnormal current difference, and abnormal equipment status; Query risk determination rules from a preset database; According to the abnormal voltage difference, abnormal current difference, abnormal equipment status and risk determination rules, potential risk factors and risk sources of the accident are identified; Assess the severity and probability of risk based on the potential risk factors and risk sources of the accident; Generating a risk priority table according to the risk severity and the risk occurrence probability, wherein the risk priority table is used to rank the multiple risks; The risk priority form is pushed to the user's smart terminal.

[0008] Furthermore, the steps of assessing the severity of the risk and the probability of the risk occurring specifically include: According to the potential risk factors and risk sources of the accident, all possible minimum path sets are retrieved; the structural importance is calculated, and the structural importance is used to reflect the influence of different potential risk factors of the accident on the probability of risk occurrence. The specific calculation formula is as follows: ; in, is the structural importance; k j is the minimum path set containing basic event i; n j k j The number of elementary events in ; According to the structural importance, the step of evaluating the risk severity and the risk occurrence probability is performed.

[0009] Furthermore, the steps of assessing the severity of the risk and the probability of the risk occurring specifically include: According to the basic theoretical information, the equipment failure frequency is obtained ; According to the equipment failure frequency , calculate the device health status S i , the equipment health status S i It is used as a quantitative indicator to evaluate the health status of the equipment. The formula is as follows: ; Where i is the number of devices, a i is the scale factor, b i is the curvature coefficient, c i is a constant; Calculate the maximum failure rate f max , minimum failure rate f min and the average equipment failure rate f av , the relevant equation is as follows: ; Where S min , S av and S max Represents the worst, average, and best condition ratings of the equipment, respectively; According to the current health status of the device S i and its corresponding failure rate f (Si) , calculate the actual risk probability of the equipment.

[0010] Furthermore, the steps of assessing the severity of the risk and the probability of the risk occurring specifically include: According to the potential risk factors and risk sources of the accident, the risk probability P and the potential risk factor C of the accident are quantitatively evaluated to obtain the risk level R of the risk source. The calculation formula is as follows: R = P·C; Among them, P is the risk probability level of accidents or dangerous events, C is the impact level caused by accidents or dangerous events, including casualties, property losses, and environmental impacts; R is the calculated score of the operating condition risk level, that is, the risk level; According to the risk level R, the priority of risk management is determined, and dangerous and harmful factors with higher risk levels are dealt with first.

[0011] In a second aspect, the present application provides a device safety management system based on data analysis, comprising: A basic theoretical information acquisition module is used to acquire basic theoretical information, including theories related to research risk assessment, early warning and big data analysis; The equipment operation data acquisition module is used to acquire equipment operation data, wherein the equipment operation data includes real-time voltage, real-time current, and real-time status of the equipment; A data preprocessing module is used to preprocess the equipment operation data to remove outliers, process missing data, and perform standardization; A key feature data extraction module is used to extract key feature data from the preprocessed data, wherein the key feature data includes voltage fluctuation, current change, and equipment load; A model training module, used to perform model training based on the basic theoretical information and evaluate model performance through cross-validation; Adjustment and optimization module, used to adjust and optimize the model according to the verification results; The fault prediction module is used to apply the trained model to the equipment operation data and output the prediction results of possible faults of the equipment.

[0012] In a third aspect, the present application provides an intelligent terminal, comprising a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and execute the above-mentioned device security management method based on data analysis.

[0013] In a fourth aspect, the present application provides a computer-readable storage medium storing a computer program that can be loaded by a processor and execute the above-mentioned device security management method based on data analysis.

[0014] In summary, compared with the prior art, the above technical solution has the following beneficial effects: The equipment safety management system and method based on data analysis described in this application can significantly improve the accuracy of equipment failure prediction through scientific data processing and feature extraction, as well as model training and optimization based on big data analysis. Through real-time monitoring and analysis of equipment operation data, it is possible to issue an early warning before the equipment fails, providing a valuable time window for timely maintenance and replacement of the equipment. Through accurate fault prediction and early warning, it helps to reduce unplanned downtime of equipment, reduce maintenance costs, improve equipment utilization and production efficiency, enhance the overall safety management level of the enterprise, and reduce safety risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a flow chart of a device safety management method based on data analysis in an embodiment of the present application.

[0016] Figure 2 It is a flowchart of querying risk accident information corresponding to the potential risk data from a preset database in an embodiment of the present application.

[0017] Figure 3It is a flowchart of querying risk determination rules from a preset database in an embodiment of the present application. DETAILED DESCRIPTION

[0018] The present application is further described in detail below in conjunction with all the accompanying drawings.

[0019] The present application discloses a device safety management system and method based on data analysis, referring to Figure 1 , a device safety management method based on data analysis includes: S101. Obtain basic theoretical information.

[0020] Specifically, the safety management system acquires basic theoretical information, including relevant theories of risk assessment, early warning and big data analysis; the safety management system deeply studies risk assessment methods, including risk identification, assessment, monitoring and response measures, understands the basic principles of the early warning system, such as the setting of early warning thresholds, the triggering of early warning signals, etc., and learns relevant theories of big data analysis, such as data mining, machine learning algorithms, etc., to provide a theoretical basis for model training. This provides a solid theoretical basis for subsequent data analysis and model training, ensuring the scientificity and accuracy of safety management methods.

[0021] S102: Obtain equipment operation data.

[0022] Specifically, the safety management system obtains equipment operation data, including real-time voltage, real-time current, and real-time status of the equipment; the safety management system collects the voltage, current, and status data of the equipment in real time through sensors or monitoring systems. The data collection frequency is set according to the characteristics of the equipment and monitoring requirements to ensure the comprehensiveness and accuracy of the data. This provides rich input information, helps capture subtle changes in the equipment, and provides a reliable data source for subsequent data preprocessing and feature extraction.

[0023] S103: Preprocess the equipment operation data.

[0024] Specifically, the safety management system performs data preprocessing on the equipment operation data to remove outliers, process missing data, and perform standardization processing; the safety management system identifies and removes outliers in the data by setting reasonable thresholds or using statistical methods; uses interpolation, mean filling, or regression prediction methods to process missing data to ensure data integrity; and converts data into a unified dimension and range to improve the efficiency and accuracy of model training. This improves data quality, provides a reliable data foundation for subsequent feature extraction and model training, and reduces the negative impact of noise data on model performance.

[0025] S104: extract key feature data from the preprocessed data.

[0026] Specifically, the safety management system extracts key feature data closely related to equipment failures, such as voltage fluctuations, current changes, and equipment loads, from the preprocessed data, and uses statistical methods or machine learning algorithms to screen and optimize the features to improve the prediction accuracy of the model. Extracting key features closely related to equipment failures helps the model more accurately capture the operating status and potential failures of the equipment, and improves the prediction accuracy and generalization ability of the model.

[0027] S105. Perform model training based on the basic theoretical information and evaluate model performance through cross-validation.

[0028] Specifically, the safety management system selects appropriate machine learning algorithms for model training based on basic theoretical information and extracted key feature data, and uses cross-validation methods to evaluate the performance of the model, such as accuracy, recall, and F1 score. The model is tuned based on the cross-validation results, including adjusting algorithm parameters and optimizing feature selection, which is conducive to training a stable and accurate prediction model, and the stability and reliability of the model are ensured through cross-validation.

[0029] S106. Adjust and optimize the model according to the verification results.

[0030] Specifically, the safety management system further adjusts and optimizes the model based on the cross-validation results and actual needs. New features or algorithms are introduced to improve the prediction accuracy and generalization ability of the model, and the model is iteratively trained to gradually optimize its performance. This improves the prediction accuracy and generalization ability of the model, making the model more adaptable to the needs of actual application scenarios.

[0031] S107: Apply the trained model to the equipment operation data, and output a prediction result of possible equipment failures.

[0032] Specifically, the safety management system applies the trained model to the equipment operation data, outputs the prediction results of possible equipment failures in real time, and tracks and verifies the prediction results to evaluate the actual effect of the model. Users take corresponding maintenance measures in a timely manner based on the prediction results, such as replacing parts and adjusting parameters. It achieves accurate prediction and early warning of equipment failures, provides a valuable time window for timely maintenance and replacement of equipment, and reduces the failure rate and maintenance cost of equipment.

[0033] In another embodiment, referring to Figure 2 , S107 specifically includes the following sub-steps: S107.11. Query normal operation data from a preset database.

[0034] Specifically, the safety management system queries the normal operation data from the preset database, and the normal operation data includes the normal voltage range, normal current range, and normal equipment status; the user pre-establishes a database containing normal equipment operation parameters, and the database should cover the normal voltage range, normal current range, and normal equipment status of various equipment. When it is necessary to predict equipment failure, the safety management system first queries the normal operation data that matches the current equipment model and specifications from this database. The database provides a reference standard for the normal operation of the equipment, provides a benchmark for subsequent fault prediction, ensures the accuracy and reliability of the prediction results, and avoids misjudgment due to different equipment models or specifications.

[0035] S107.12. Compare the key feature data with the normal operation data to identify potential risk data.

[0036] Specifically, the safety management system compares the key feature data (such as voltage fluctuations, current changes, equipment load, etc.) extracted from the equipment operation data with the normal operation data retrieved from the database. By setting reasonable thresholds or using statistical methods, potential risk data, that is, data that exceeds the normal operating range, are identified. The potential risk data includes abnormal voltage, abnormal current, and abnormal equipment status. This enables timely detection of abnormal conditions in equipment operation, provides strong support for fault prediction, improves the accuracy and sensitivity of fault prediction, and helps take measures in advance to avoid faults.

[0037] S107.13. Query the risk accident information corresponding to the potential risk data from a preset database.

[0038] Specifically, the safety management system queries the risk accident information corresponding to the potential risk data from the preset database; the user establishes the corresponding relationship between the risk accident information and the potential risk data in the database in advance, that is, when certain key characteristic data exceeds the normal range, the risk accident type and its consequences that may be caused. After the potential risk data is identified, the corresponding risk accident information is queried from the database according to this corresponding relationship. This provides users with detailed risk accident information, helps users understand the possible consequences and impacts of the failure, and facilitates users to formulate corresponding response measures and plans based on the risk accident information to reduce the losses caused by the failure.

[0039] S107.14. Push the potential risk data and risk accident information to the user's smart terminal.

[0040] Specifically, the safety management system uses modern information technology, such as SMS, email, and APP push, to push the identified potential risk data and corresponding risk accident information to users in a timely manner. The push content should include detailed information on the potential risk data, the types of risk accidents that may be caused and their consequences, and recommended response measures. This ensures that users can understand abnormal conditions in equipment operation in a timely manner and take corresponding response measures, improves users' safety awareness and response capabilities, and helps reduce the risks and losses caused by equipment failures.

[0041] Reference Figure 3 , S107.14 and later also generate a risk priority form based on the potential risk data and normal operation data, which specifically includes the following steps: S107.21. Compare the potential risk data with the normal operating data, and calculate the abnormal voltage difference, abnormal current difference, and abnormal equipment status.

[0042] Specifically, the safety management system compares the voltage, current value, and equipment status in the potential risk data with the corresponding values ​​in the normal operation data, calculates the difference between voltage and current (i.e., abnormal voltage difference, abnormal current difference), and identifies abnormal conditions of equipment status (such as overheating, overload, etc.). It provides quantified abnormal data, which helps users to more intuitively understand the degree of deviation in equipment operation and provides basic data support for subsequent risk determination and assessment.

[0043] S107.22. Query risk determination rules from a preset database.

[0044] Specifically, the safety management system queries the risk determination rules from the preset database; users pre-establish risk determination rules in the preset database, which are based on historical data and expert experience and cover the potential risks and danger levels corresponding to different abnormal data. When the safety management system calculates the abnormal data, it queries the corresponding risk determination rules from the database. This provides a scientific basis and standard for risk determination, ensuring the accuracy and consistency of risk determination.

[0045] S107.23. Identify potential hazards and risk sources of accidents.

[0046] Specifically, the safety management system identifies potential risk factors and risk sources of accidents based on the abnormal voltage difference, abnormal current difference, abnormal equipment status and risk determination rules; identifies potential risk factors and risk sources that may cause accidents based on abnormal data and risk determination rules, and classifies and describes these factors and sources in detail so that users can understand and take corresponding preventive measures. It helps users clarify the potential safety hazards in equipment operation and provides users with targeted risk management suggestions.

[0047] S107.24. Assess risk severity and probability of risk occurrence.

[0048] Specifically, the safety management system evaluates the severity and probability of risk based on the potential risk factors and risk sources of the accident; it evaluates the severity and probability of risk by using risk assessment methods (such as risk matrix, fault tree analysis, etc.), combined with abnormal data and potential risk factors, and classifies and categorizes risks based on the assessment results. It provides quantitative information on the severity and probability of risk, which helps users understand the urgency and importance of risks and provides a decision-making basis for subsequent risk handling.

[0049] S107.25. Generate risk priority form.

[0050] Specifically, the safety management system generates a risk priority form based on the assessment results of risk severity and probability of occurrence. The form should contain information such as the risk name, description, severity level, probability of occurrence, and recommended response measures, and sort the risks in the form to highlight the risks with higher priority. Providing clear risk priority information helps users to reasonably allocate resources and energy, and improves the efficiency and effectiveness of risk management.

[0051] S107.26. Push the risk priority form to the user's smart terminal.

[0052] Specifically, the security management system pushes the risk priority form to the user's smart terminal. Using the push function of the smart terminal, the risk priority form is pushed to the user in a timely manner, and the push content includes detailed information of the form and recommended countermeasures and action guidelines. This ensures that users can keep up to date with the latest information on risk management, provides clear guidance for user actions, and helps users quickly respond to and handle risks.

[0053] The safety management system not only provides users with potential risk data and risk accident information, but also provides users with more detailed and specific risk management information, including quantitative analysis of abnormal data, application of risk determination rules, identification of potential hazardous factors and risk sources, assessment of risk severity and probability of occurrence, and generation of risk priority forms, etc. This information helps users fully understand the risk status of equipment operation and take corresponding preventive and response measures, thereby reducing the risk and loss of equipment failure.

[0054] In another embodiment, S107.24 specifically includes the following sub-steps: According to the potential risk factors and risk sources of the accident, all possible minimum path sets are retrieved; Calculate the structural importance, which is used to reflect the impact of different potential risk factors of accidents on the probability of risk occurrence. The specific calculation formula is as follows: ; in, is the structural importance; k j is the minimum path set containing basic event i; n j k j The number of elementary events in ; According to the structural importance, the step of evaluating the risk severity and the risk occurrence probability is performed.

[0055] Specifically, the safety management system finds all the basic events related to the identified potential risk factors and risk sources in the fault tree, and uses Boolean algebra simplification or other methods to find all possible minimum path sets composed of these basic events. The specific solution method is the existing technology and will not be described here. The minimum path set is a necessary and sufficient condition for the system to avoid accidents. They represent various possible ways of system safety. By calling all possible minimum path sets, various possibilities of system safety can be comprehensively analyzed, providing a basis for subsequent structural importance calculations.

[0056] The structural importance calculation formula is used to traverse all possible minimum path sets and calculate the structural importance of each basic event. The structural importance reflects the importance of basic events in the fault tree structure, that is, the degree of their influence on the probability of occurrence of the top event. By calculating the structural importance, the basic events that have the greatest impact on system safety can be identified, that is, those potential risk factors that need the most attention and prevention.

[0057] Combined with the calculated structural importance, the potential risk factors of accidents are ranked to determine which factors have higher risks and need more attention. According to the ranking results, the severity and probability of each factor are evaluated. The severity can be determined by analyzing historical data and expert experience, and the probability of occurrence can be estimated by statistical methods or probability models. Based on the evaluation results of severity and probability of occurrence, the priority and response measures of risks are determined. The introduction of structural importance makes the evaluation of risk severity and probability of occurrence more scientific and accurate. High-risk factors and high-priority risks are identified, providing strong support for subsequent risk management and preventive measures. The efficiency and effectiveness of risk management are improved, which helps to reduce the risk and loss of equipment failure.

[0058] In summary, by retrieving all possible minimum path sets and calculating the structural importance, combined with the evaluation of severity and probability of occurrence, the risks in equipment operation can be analyzed and managed more accurately. This method provides a powerful tool and support for equipment safety management, helping to ensure the safe operation of equipment and reduce the occurrence of failures.

[0059] In another embodiment, S107.24 specifically includes the following sub-steps: According to the basic theoretical information, the equipment failure frequency is obtained ; According to the equipment failure frequency , calculate the device health status S i , the equipment health status S i It is used as a quantitative indicator to evaluate the health status of the equipment. The formula is as follows: ; Where i is the number of devices, a i is the scale factor, b i is the curvature coefficient, c i is a constant; Calculate the maximum failure rate f max , minimum failure rate f min and the average equipment failure rate f av , the relevant equation is as follows: ; Where S min , S av and S max Represents the worst, average, and best condition ratings of the equipment, respectively; According to the current health status of the device S i and its corresponding failure rate f (Si) , calculate the actual risk probability of the equipment.

[0060] Specifically, the safety management system collects historical fault data of the equipment, including the time, type, and cause of the fault. By statistically analyzing the historical fault data, the fault frequency of the equipment is calculated, that is, the number of faults that occur per unit time. The quantitative data on the frequency of equipment failures is provided, which provides a basis for subsequent equipment health status assessment and risk calculation, and helps to identify equipment failure trends and potential problems.

[0061] According to the equipment failure frequency and other relevant parameters (such as equipment operation time, maintenance records, etc.), the equipment health status S is calculated using the formula i , where i represents the number or serial number of the device, a i , b i 、c iIt is a constant or coefficient determined based on factors such as equipment type and operating environment. It represents a certain performance parameter or status indicator of the equipment, which can be understood here as a quantitative representation related to the frequency of equipment failure.

[0062] It should be noted that a in the formula i , b i 、c i as well as The specific form and value should be determined and adjusted according to the actual situation so that the equipment health status S i Can accurately reflect the actual health status of the equipment. Equipment health status S i As a quantitative indicator, it can directly reflect the health of the equipment, which helps to manage the equipment in a hierarchical manner and give priority to the equipment with poor health status.

[0063] In this embodiment, adjust a i It can change the difference in health status between different devices or different parts of the same device. If the failure rate of a certain type of equipment or component is generally high, its a i value, so that it has a greater weight in the health status assessment. Curvature coefficient b i Determines the health status S i The rate at which the fault frequency changes. If the health status of the device is sensitive to changes in the fault frequency, you can reduce b i On the contrary, if the change is relatively gentle, increase b i Value. Constant c i Used to adjust health status S i If the overall equipment health level is high, c can be appropriately increased. i values ​​to improve the baseline of health status.

[0064] For example, there are a number of equipment on the production line in the factory. When the equipment is first used, the initial setting of a i , b i 、c i The values ​​are 1, 0.5, and 10 respectively. After a period of operation, it is found that the health status S of a certain device i The calculated value deviates greatly from the actual observed state. After analysis, it is found that the failure rate of the equipment increases rapidly with the increase of running time. Therefore, b should be reduced. i value to more sensitively reflect the changes in the health status of the device. i The value is reduced to 0.3, and the S i The value is closer to the actual state. At the same time, according to the adjusted S i Value and failure rate f (Si), the calculated probability of risk occurrence is also more accurate.

[0065] According to the equipment health status S i The rating of the fault rate (such as worst, average, best, etc.) is used to determine the corresponding failure rate range. Calculate the maximum failure rate f max (corresponding to the worst equipment status rating S min )、Minimum failure rate f min (theoretical minimum failure rate, which may be zero or close to zero) and the average device failure rate f av (corresponding to the average equipment status rating S av ). The relevant equations need to be constructed and adjusted according to the actual situation, but the basic idea is to use the equipment health status S i and failure rate f (Si) It provides a quantitative range of equipment failure rate, helps to understand the failure distribution and potential risks of equipment, and provides important reference data for subsequent risk calculations.

[0066] According to the current health status of the device S i and its corresponding failure rate f (Si) , combined with risk assessment models or methods (such as fault tree analysis, event tree analysis, etc.), calculate the actual risk probability of the equipment. Consider the possible consequences and impacts of equipment failure (such as economic losses, casualties, etc.), and modify and weight the risk probability. It provides quantitative data on the actual risk probability of the equipment, which is helpful for risk management and decision-making, and comprehensively considers the possible consequences and impacts of equipment failure, making risk assessment more comprehensive and accurate.

[0067] In summary, by obtaining the equipment failure frequency and calculating the equipment health status S i , determine the range of failure rates, and calculate the actual risk probability, etc., can more accurately assess the risk severity and risk probability of equipment. This method provides strong support for equipment safety management and helps reduce the risk and loss of equipment failure.

[0068] In another embodiment, S107.24 specifically includes the following sub-steps: According to the potential risk factors and risk sources of the accident, the risk probability P and the potential risk factor C of the accident are quantitatively evaluated to obtain the risk level R of the risk source. The calculation formula is as follows: R = P·C; Among them, P is the risk probability level of accidents or dangerous events, C is the impact level caused by accidents or dangerous events, including casualties, property losses, and environmental impacts; R is the calculated score of the operating condition risk level, that is, the risk level; According to the risk level R, the priority of risk management is determined, and dangerous and harmful factors with higher risk levels are dealt with first.

[0069] Specifically, the safety management system evaluates the probability P of risk occurrence: collects historical data to review the frequency, conditions and environment of similar accidents or dangerous events in the past; analyzes potential factors to identify various potential factors that may lead to accidents, such as equipment failure, human error, environmental factors, etc.; uses probabilistic statistical methods, such as Bayesian networks, Markov chains, etc., to calculate the probability level P of risk occurrence.

[0070] The safety management system evaluates the potential risk factors C of accidents: determine the scope of impact, that is, the areas, personnel, equipment, etc. that may be affected once an accident occurs; analyze the impact level, and analyze the severity of the consequences such as casualties, property losses, and environmental impacts that may be caused by the accident based on historical data and expert experience; quantify the impact level and quantify the impact level into specific levels, such as minor, general, serious, and extremely serious. Through quantitative evaluation, we can more accurately understand the possibility of risk occurrence and the severity of potential risk factors. It provides reliable data support for subsequent risk level calculation and risk management.

[0071] The formula R = P·C is used for calculation, where R is the calculated score of the operating condition risk level, i.e., the risk level; P is the risk probability level of an accident or dangerous event; and C is the impact level caused by an accident or dangerous event. According to the calculation results, the risk level R is divided into different intervals, such as low, medium, high, and very high, so as to understand the risk level more intuitively. By calculating the risk level R, the possibility of risk occurrence and the severity of potential dangerous factors can be comprehensively considered, thereby obtaining a comprehensive risk assessment. The division of risk levels helps to manage different risks in a hierarchical manner and improve the pertinence and efficiency of risk management.

[0072] Determine the priority of risk management according to the risk level R. Prioritize dangerous and harmful factors with higher risk levels, and formulate targeted risk management measures and emergency plans. For factors with lower risk levels, conventional management measures can be taken to monitor and prevent them. By determining the priority of risk management, resources can be reasonably allocated to ensure that high-risk factors are dealt with in a timely and effective manner, improve the overall effect of risk management, and reduce the possibility of accidents and potential losses.

[0073] In summary, quantitatively assessing the probability of risk occurrence P and the potential risk factors C of accidents, calculating the risk level R, and determining the priority of risk management based on this is a scientific, effective and practical risk management method. This method can provide enterprises with clear risk management ideas and practical guidance, which helps to ensure the safe production and sustainable development of enterprises.

[0074] Based on the above method, the embodiment of the present application also discloses a device safety management system based on data analysis. A device safety management system based on data analysis includes: A basic theoretical information acquisition module is used to acquire basic theoretical information, including theories related to research risk assessment, early warning and big data analysis; The equipment operation data acquisition module is used to acquire equipment operation data, and the equipment operation data includes real-time voltage, real-time current, and real-time status of the equipment; A data preprocessing module, which is used to preprocess the equipment operation data, remove outliers, process missing data, and perform standardization; A key feature data extraction module, which is used to extract key feature data from the preprocessed data, wherein the key feature data includes voltage fluctuation, current change, and equipment load; A model training module, which is used to perform model training based on the basic theoretical information and evaluate model performance through cross-validation; An adjustment and optimization module is used to adjust and optimize the model according to the verification results; The fault prediction module is used to apply the trained model to the equipment operation data and output the prediction results of possible faults of the equipment.

[0075] An embodiment of the present application further discloses an intelligent terminal, which includes a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and executes a device security management method based on data analysis as described above.

[0076] The embodiment of the present application also discloses a computer-readable storage medium. The computer-readable storage medium stores a computer program that can be loaded by a processor and executes a device security management method based on data analysis as described above. The computer-readable storage medium includes, for example, a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0077] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the scope of protection of the invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on these embodiments, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in this field can still combine, add, delete or make other adjustments to the features in the various embodiments of the present invention according to the circumstances without conflict, without making creative work, so as to obtain different other technical solutions that do not deviate from the concept of the present invention in essence, and these technical solutions also belong to the scope of protection of the present invention.

Claims

1. A device safety management method based on data analysis, characterized in that: The following steps are involved: Obtaining basic theoretical information, including research risk assessment, early warning and big data analysis related theories; Acquire equipment operation data, wherein the equipment operation data includes real-time voltage, real-time current, and real-time status of the equipment; Performing data preprocessing on the equipment operation data to remove outliers, process missing data, and perform standardization; Extract key feature data from the preprocessed data, wherein the key feature data includes voltage fluctuation, current change, and equipment load; Based on the basic theoretical information, model training is performed and model performance is evaluated through cross-validation; Adjust and optimize the model based on the validation results; The trained model is applied to the equipment operation data to output the prediction results of possible equipment failures.

2. The device safety management method based on data analysis according to claim 1 is characterized in that: The step of applying the trained model to the equipment operation data and outputting the prediction result of possible equipment failures specifically includes: Querying normal operating data from a preset database, wherein the normal operating data includes a normal voltage range, a normal current range, and a normal device status; Comparing the key feature data with the normal operating data to identify potential risk data, wherein the potential risk data includes abnormal voltage, abnormal current, and abnormal equipment status; Querying risk accident information corresponding to the potential risk data from a preset database; The potential risk data and risk accident information are pushed to the user's smart terminal.

3. The device safety management method based on data analysis according to claim 2 is characterized in that: After the step of pushing the potential risk data and risk accident information to the user's smart terminal, the method further includes: Compare the potential risk data with the normal operating data, and calculate abnormal voltage difference, abnormal current difference, and abnormal equipment status; Query risk determination rules from a preset database; According to the abnormal voltage difference, abnormal current difference, abnormal equipment status and risk determination rules, potential risk factors and risk sources of the accident are identified; Assess the severity and probability of risk based on the potential risk factors and risk sources of the accident; Generating a risk priority table according to the risk severity and the risk occurrence probability, wherein the risk priority table is used to rank the multiple risks; The risk priority form is pushed to the user's smart terminal.

4. The device safety management method based on data analysis according to claim 3 is characterized in that: The steps of assessing risk severity and risk probability include: According to the potential risk factors and risk sources of the accident, all possible minimum path sets are retrieved; Calculate the structural importance, which is used to reflect the impact of different potential risk factors of accidents on the probability of risk occurrence. The specific calculation formula is as follows: ； in, is the structural importance; k j is the minimum path set containing basic event i; n j k j The number of elementary events in ; According to the structural importance, the step of evaluating the risk severity and the risk occurrence probability is performed.

5. The device safety management method based on data analysis according to claim 3 is characterized in that: The steps of assessing risk severity and risk probability include: According to the basic theoretical information, the equipment failure frequency is obtained ; According to the equipment failure frequency , calculate the device health status S i , the equipment health status S i It is used as a quantitative indicator to evaluate the health status of the equipment. The formula is as follows: ； Where i is the number of devices, a i is the scale factor, b i is the curvature coefficient, c i is a constant; Calculate the maximum failure rate f max , minimum failure rate f min and the average equipment failure rate f av , the relevant equation is as follows: ； Where S min , S av and S max Represents the worst, average, and best condition ratings of the equipment, respectively; According to the current health status of the device S i and its corresponding failure rate f (Si) , calculate the actual risk probability of the equipment.

6. The device safety management method based on data analysis according to claim 3 is characterized in that: The steps of assessing risk severity and risk probability include: According to the potential risk factors and risk sources of the accident, the risk probability P and the potential risk factor C of the accident are quantitatively evaluated to obtain the risk level R of the risk source. The calculation formula is as follows: R = P·C; Among them, P is the risk probability level of accidents or dangerous events, C is the impact level caused by accidents or dangerous events, including casualties, property losses, and environmental impacts; R is the calculated score of the operating condition risk level, that is, the risk level; According to the risk level R, the priority of risk management is determined, and dangerous and harmful factors with higher risk levels are dealt with first.

7. A device safety management system based on data analysis, characterized in that: include: A basic theoretical information acquisition module is used to acquire basic theoretical information, including theories related to research risk assessment, early warning and big data analysis; The equipment operation data acquisition module is used to acquire equipment operation data, wherein the equipment operation data includes real-time voltage, real-time current, and real-time status of the equipment; A data preprocessing module is used to preprocess the equipment operation data to remove outliers, process missing data, and perform standardization; A key feature data extraction module is used to extract key feature data from the preprocessed data, wherein the key feature data includes voltage fluctuation, current change, and equipment load; A model training module, used to perform model training based on the basic theoretical information and evaluate model performance through cross-validation; Adjustment and optimization module, used to adjust and optimize the model according to the verification results; The fault prediction module is used to apply the trained model to the equipment operation data and output the prediction results of possible faults of the equipment.

Images