Safety performance detection method and system of intelligent protective helmet

Abstract

The invention provides a safety performance detection method and system for an intelligent protective helmet, and relates to the technical field of performance detection.The method comprises the steps that a helmet assembly set of a target protective helmet is obtained, safety performance influence index mining is conducted on Y helmet assemblies according to preset influence index feature constraints, helmet safety influence evaluation is conducted, and the safety performance of the target protective helmet is obtained; y safety influence coefficients are obtained and proportion calculation is carried out, performance detection analysis is carried out based on a helmet heterogeneous safety verification algorithm, data fusion is carried out on the safety value coefficient and a safety performance detection result, a comprehensive detection result is generated, and finally a safety performance detection report is generated. Through the helmet safety performance detection method and device, the technical problems that in the prior art, index mining cannot be deeply carried out on each assembly, the independent safety performance of each assembly cannot be considered, and consequently the evaluation result is incomplete and inaccurate can be solved, and according to the comprehensive detection result and the detection result of each assembly, a detailed helmet safety performance detection report can be generated.

Description

Technical Field

[0001] The present application relates to the technical field of performance testing, and in particular to a method and system for testing the safety performance of an intelligent protective helmet. Background Art

[0002] As an important personal protective equipment, smart protective helmets are widely used in various fields such as construction, industry, mining, firefighting, and transportation to protect the wearer's head safety. With the continuous advancement of science and technology, the functions of smart protective helmets are becoming more and more abundant. In addition to the basic protection functions, smart sensors and communication modules are also added to achieve more intelligent safety monitoring and early warning. However, whether the safety performance of smart protective helmets is reliable is directly related to the safety of the wearer. Therefore, it is particularly important to test and evaluate the safety performance of smart protective helmets.

[0003] At present, the existing helmet safety performance testing mainly relies on physical impact testing and manual evaluation. Although this method can evaluate the protective effect of the helmet to a certain extent, it has limitations such as long testing cycle, inaccurate data, and strong subjectivity in evaluation.

[0004] In summary, the existing technology cannot deeply mine indicators of each component and cannot take into account the independent security performance of each component, resulting in technical problems such as incomplete and inaccurate evaluation results. Summary of the invention

[0005] The purpose of this application is to provide a safety performance detection method and system for an intelligent protective helmet, so as to solve the technical problem that the prior art cannot deeply mine the indicators of each component and cannot take into account the independent safety performance of each component, resulting in incomplete and inaccurate evaluation results.

[0006] In view of the above problems, the present application provides a method and system for detecting the safety performance of an intelligent protective helmet.

[0007] In a first aspect, the present application provides a method for detecting the safety performance of an intelligent protective helmet, the method being implemented by a safety performance detection system for an intelligent protective helmet, wherein the method comprises: obtaining a helmet component set of a target protective helmet, wherein the helmet component set comprises Y helmet components of the target protective helmet, wherein Y is the total number of components of the target protective helmet; performing safety performance influencing indicator mining on the Y helmet components according to predetermined influencing indicator feature constraints, and obtaining Y component safety performance influencing indicator sources, wherein the predetermined influencing indicator feature constraints comprise predetermined indicator safety association constraints and predetermined indicator coupling constraint values; performing head mining on the Y helmet components, respectively. A helmet safety impact assessment is performed to obtain safety impact coefficients of Y components, and a proportion calculation is performed based on the safety impact coefficients of the Y components to obtain safety value coefficients of the Y components; based on a helmet heterogeneous safety verification algorithm, according to the safety value coefficients of the Y components and the safety performance impact indicator sources of the Y components, safety performance detection and analysis are performed on the Y helmet components respectively to obtain safety performance detection results of the Y components; based on the safety value coefficients of the Y components, data fusion is performed on the safety performance detection results of the Y components to generate a comprehensive safety performance detection result of the helmet; based on the comprehensive safety performance detection result of the helmet and the safety performance detection results of the Y components, a helmet safety performance detection report is generated.

[0008] In a second aspect, the present application also provides a safety performance detection system for an intelligent protective helmet, which is used to execute a safety performance detection method for an intelligent protective helmet as described in the first aspect, wherein the system includes: a helmet component set acquisition module, the helmet component set acquisition module is used to obtain a helmet component set of a target protective helmet, wherein the helmet component set includes Y helmet components of the target protective helmet, wherein Y is the total number of components of the target protective helmet; a performance impact indicator source acquisition module, the performance impact indicator source acquisition module is used to mine safety performance impact indicators of the Y helmet components according to predetermined impact indicator feature constraints, and obtain Y component safety performance impact indicator sources, wherein the predetermined impact indicator feature constraints include predetermined indicator safety association constraints and predetermined indicator coupling constraint values; a safety impact coefficient acquisition module, the safety impact coefficient acquisition module is used to mine the safety performance impact indicators of the Y helmet components respectively according to predetermined impact indicator feature constraints, and obtain Y component safety performance impact indicator sources, wherein the predetermined impact indicator feature constraints include predetermined indicator safety association constraints and predetermined indicator coupling constraint values; a safety impact coefficient acquisition module A helmet safety impact assessment is performed on the Y helmet components to obtain safety impact coefficients of Y components, and a proportion calculation is performed based on the safety impact coefficients of the Y components to obtain safety value coefficients of the Y components; a performance test result acquisition module is used to perform safety performance test and analysis on the Y helmet components based on the helmet heterogeneous safety verification algorithm, according to the safety value coefficients of the Y components and the safety performance impact indicator sources of the Y components, to obtain safety performance test results of the Y components; a data fusion module is used to perform data fusion on the safety performance test results of the Y components based on the safety value coefficients of the Y components to generate a comprehensive test result of the safety performance of the helmet; a performance test report generation module is used to generate a helmet safety performance test report based on the comprehensive test result of the helmet safety performance and the safety performance test results of the Y components.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages: By obtaining a helmet component set of a target protective helmet, wherein the helmet component set includes Y helmet components of the target protective helmet, wherein Y is the total number of components of the target protective helmet; performing safety performance influencing indicator mining on the Y helmet components according to predetermined influencing indicator feature constraints, and obtaining Y component safety performance influencing indicator sources, wherein the predetermined influencing indicator feature constraints include predetermined indicator safety association constraints and predetermined indicator coupling constraint values; performing helmet safety impact assessments on the Y helmet components respectively, obtaining Y component safety impact coefficients, and performing proportion calculations based on the Y component safety impact coefficients, and obtaining Y component safety value coefficients; based on a helmet heterogeneous safety verification algorithm, performing safety performance detection and analysis on the Y helmet components respectively according to the Y component safety value coefficients and the Y component safety performance influencing indicator sources, and obtaining Y component safety performance detection results; performing data fusion on the Y component safety performance detection results based on the Y component safety value coefficients, and generating a comprehensive helmet safety performance detection result; generating a helmet safety performance detection report based on the comprehensive helmet safety performance detection result and the Y component safety performance detection results. It effectively solves the technical problems that the existing technology cannot deeply mine the indicators of each component and cannot take into account the independent safety performance of each component, resulting in incomplete and inaccurate evaluation results. According to the comprehensive test results and the test results of each component, a detailed helmet safety performance test report can also be generated.

[0010] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0012] Figure 1 A schematic diagram of a safety performance testing method for an intelligent protective helmet for this application; Figure 2 This is a schematic diagram of the structure of a safety performance detection system for an intelligent protective helmet according to the present application.

[0013] Description of reference numerals: Helmet component set acquisition module 11, performance impact indicator source acquisition module 12, safety impact coefficient acquisition module 13, performance test result acquisition module 14, data fusion module 15, performance test report generation module 16. DETAILED DESCRIPTION

[0014] This application solves the technical problems that the prior art cannot deeply mine indicators of each component and cannot take into account the independent safety performance of each component, resulting in incomplete and inaccurate evaluation results, by providing a method and system for testing the safety performance of an intelligent protective helmet. A detailed helmet safety performance test report can also be generated based on the comprehensive test results and the test results of each component.

[0015] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0016] Embodiment 1 Please refer to the attached Figure 1 The present application provides a method for detecting the safety performance of an intelligent protective helmet, wherein the method is applied to a safety performance detection system for an intelligent protective helmet, and the method specifically comprises the following steps: Step 1: obtaining a helmet component set of a target protective helmet, wherein the helmet component set includes Y helmet components of the target protective helmet, wherein Y is the total number of components of the target protective helmet; Specifically, the components of the helmet include the outer shell, lining, straps, adjustment devices, protective plates, sensors, communication modules, and all other parts that make up the helmet and affect its performance. Under the premise of safety and non-destructive testing, the helmet is disassembled into individual components. During the disassembly process, the type, quantity, location, and function of each component are recorded in detail. All identified helmet components are classified and sorted to form a complete helmet component set. This set should include all components of the helmet and be able to clearly display the structure and function of the helmet. Finally, the number of each component in the helmet component set is counted to determine the number of each component and the total number Y. Among them, Y is a positive integer.

[0017] Step 2: mining the safety performance influencing indicators of the Y helmet components respectively according to the predetermined influencing indicator feature constraints to obtain the safety performance influencing indicator sources of the Y components, wherein the predetermined influencing indicator feature constraints include predetermined indicator safety association constraints and predetermined indicator coupling constraint values; Specifically, the influencing index characteristic constraints can be set by personnel in this field, including predetermined index safety association constraints and predetermined index coupling constraint values. The predetermined index safety association constraints define the correlation between each helmet component and safety performance. For example, the material and thickness of the shell may be directly related to the impact resistance, while the adjustment device of the strap may be related to the wearing stability. The predetermined index coupling constraint value takes into account the interaction and influence between components. For example, the data transmission efficiency between the sensor and the communication module may affect the intelligent function performance of the helmet. For each component, analyze its correlation factors with safety performance according to its functional and structural characteristics. This can be done through experimental testing and simulation analysis. Quantify the degree of influence of each component on safety performance. This can be achieved by establishing a mathematical model, using sensor data for real-time monitoring and analysis, and other methods. Analyze whether there is a coupling relationship between the influencing indicators of different components, that is, whether the performance change of one component will affect the performance of other components.

[0018] Step 3: Conduct helmet safety impact assessments on the Y helmet components respectively to obtain safety impact coefficients of the Y components, and perform ratio calculations based on the safety impact coefficients of the Y components to obtain safety value coefficients of the Y components; Specifically, for each helmet component, the degree of its impact on the safety performance of the helmet is evaluated according to its function, structure, material and role in the overall helmet. The evaluation can be carried out by simulation analysis or industry standards. For example, for the shell, its impact resistance, puncture resistance and other properties can be considered; for the strap, its stability, comfort and adjustment ability can be considered. The evaluation result is a quantitative indicator, namely the safety impact coefficient. This coefficient reflects the contribution of the component to the overall safety performance of the helmet. According to the evaluation results, a safety impact coefficient is assigned to each helmet component. This coefficient can be a value between 0 and 1, where 0 indicates no impact and 1 indicates the maximum impact. The size of the coefficient should be determined based on the importance of the component and its actual contribution to safety performance. For example, key components such as shells and sensors may have higher coefficients, while auxiliary components such as decorative parts may have lower coefficients. Once the safety impact coefficient of each component is obtained, a proportion calculation can be performed. The proportion calculation is to determine the relative importance of each component in the overall safety performance. The proportion can be calculated by dividing the safety impact coefficient of each component by the sum of the safety impact coefficients of all components. In this way, the proportion of each component represents its weight in the overall safety performance of the helmet. Based on the proportion, the safety value coefficient can be further calculated. The safety value coefficient can be a direct reflection of the proportion, and this coefficient is used to quantify the relative value of each component in the safety performance of the helmet.

[0019] Step 4: Based on the helmet heterogeneous safety verification algorithm, according to the safety value coefficients of the Y components and the safety performance influencing indicator sources of the Y components, respectively perform safety performance detection and analysis on the Y helmet components to obtain safety performance detection results of the Y components; Specifically, ensure that the helmet heterogeneous safety verification algorithm is ready and suitable for detecting and analyzing the safety performance of helmet components. This algorithm should be able to handle different types of components and their corresponding safety performance indicators. Preferably, the helmet heterogeneous safety verification algorithm can be a deep learning algorithm, an integrated learning method, a multi-criteria decision analysis method, etc. The safety value coefficients and safety performance impact indicator sources of Y components are provided as input data to the helmet heterogeneous safety verification algorithm. The safety value coefficient reflects the relative importance of the component in the overall safety performance of the helmet. Run the helmet heterogeneous safety verification algorithm to detect and analyze the safety performance of each component. The algorithm will comprehensively consider the safety value coefficients and safety performance impact indicator sources of the components, as well as other safety performance-related factors that may exist. The helmet heterogeneous safety verification algorithm will output the safety performance test results of Y components. These results may be presented in numerical values, grades, charts, or other forms.

[0020] Step 5: Based on the safety value coefficients of the Y components, data fusion is performed on the safety performance test results of the Y components to generate a comprehensive test result of the helmet safety performance; Specifically, according to the specific application scenarios and requirements, select the appropriate data fusion method. You can choose weighted average, fuzzy comprehensive evaluation, neural network fusion, etc. For example, use weighted average for data fusion, use the safety value coefficient of each component as the weight, and perform weighted average on its safety performance test results. Multiply the safety performance test result of each component by its corresponding safety value coefficient, and then add the weighted results of all components to obtain the comprehensive safety performance score of the helmet.

[0021] Step 6: Generate a helmet safety performance test report based on the comprehensive test results of the helmet safety performance and the safety performance test results of the Y components.

[0022] Specifically, explain what the report covers, including the overall safety performance evaluation of the helmet and the safety performance testing of each component. Present a comprehensive score or rating for the helmet's safety performance, which is calculated based on the safety value coefficient of each component and the safety performance test results through weighted average and other methods. Interpret the comprehensive score and analyze whether the overall safety performance of the helmet meets design requirements, industry standards or user needs. List all Y components of the helmet, including the name, functional description and corresponding safety value coefficient of each component. Display the safety performance test results of each component, which may include numerical scores, pass / fail judgments, performance indicators, etc. Analyze the safety performance test results of each component, point out areas of good performance and areas that need improvement, and provide a basis for subsequent optimization or repairs.

[0023] Furthermore, step 2 of this application also includes: Traversing the Y helmet components and extracting the first helmet component; Loading a first component performance indicator set corresponding to the first helmet component, wherein the first component performance indicator set includes a plurality of performance indicators corresponding to the first helmet component; Performing helmet safety association identification on each performance indicator in the first component performance indicator set respectively to obtain multiple indicator safety association identification results; Based on the multiple indicator security association identification results, the first component performance indicator set is screened according to the predetermined indicator security association constraint to obtain multiple screened performance indicators that meet the predetermined indicator security association constraint; Based on the predetermined indicator coupling constraint value, an indicator coupling screening analysis is performed on the multiple screening performance indicators to generate a first component safety performance impact indicator source, and the first component safety performance impact indicator source is added to the Y component safety performance impact indicator sources.

[0024] Specifically, initialize a counter variable, such as index, and set it to 0. Use a loop structure such as a for loop to traverse all Y components of the helmet. In each loop, check whether index is equal to the index of the target component. If index is equal to the target index, extract the component as the first helmet component and jump out of the loop. If index is not equal to the target index, increment index and continue the next loop. After determining the first helmet component, load the first component performance indicator set corresponding to the component. Load these performance indicators into memory for subsequent processing. Initialize an empty list or array to store the indicator safety association identification results. Traverse each performance indicator in the first component performance indicator set. For each performance indicator, perform helmet safety association identification. Including comparing and analyzing the indicator with the standard, threshold or model of helmet safety. Add the safety association identification results of each performance indicator, such as safe, unsafe, need further inspection, etc., to the result list. After completing the safety association identification of all performance indicators, the result list is output as the safety association identification results of multiple indicators. Review the safety association identification results of the multiple indicators to determine which performance indicators meet the predetermined indicator safety association constraints. The predetermined indicator safety association constraints may include standards such as the minimum safety threshold and the maximum risk tolerance. The performance indicators that meet the predetermined indicator safety association constraints are screened out to form a plurality of screened performance indicators. The predetermined indicator coupling constraint values ​​are used to perform further indicator coupling screening analysis on the screened multiple performance indicators. Indicator coupling may include interactions and influences between different indicators. Analyze the coupling relationship between each screened performance indicator to determine how they jointly affect the safety performance of the helmet. Define the set of performance indicators that have been screened and analyzed as the safety performance impact indicator source of the first component. Ensure that the safety performance impact indicator source of the first component contains all key safety performance indicators and that these indicators have been properly screened and coupled analyzed. Add the generated first component safety performance impact indicator source to the list of Y component safety performance impact indicator sources.

[0025] Furthermore, the present application also includes: Traversing the plurality of screening performance indicators to perform pairwise coupling analysis to obtain a plurality of indicator coupling coefficients; Based on the predetermined indicator coupling constraint value, the plurality of indicator coupling coefficients are classified into two categories to obtain a first indicator coupling coefficient set that is less than the predetermined indicator coupling constraint value, and a second indicator coupling coefficient set that is greater than / equal to the predetermined indicator coupling constraint value; Based on the multiple screening performance indicators, matching the independent screening performance indicator set corresponding to the first indicator coupling coefficient set and the coupled screening performance indicator set corresponding to the second indicator coupling coefficient set; Based on the second indicator coupling coefficient set, the coupled screening performance indicator set is subjected to indicator fusion to obtain a decoupled screening performance indicator set; The independent screening performance indicator set and the decoupled screening performance indicator set are added to the first component safety performance impact indicator source.

[0026] Specifically, the plurality of screening performance indicators are traversed, and a pairwise coupling degree analysis is performed for each pair of indicators. The coupling degree analysis aims to quantify the degree of interaction between two indicators. The coupling coefficient between each pair of indicators is calculated using appropriate mathematical methods or algorithms such as correlation coefficient, covariance analysis, mutual information, etc. This coefficient will reflect the degree of mutual dependence between the two indicators when they change. The calculated plurality of indicator coupling coefficients are stored for subsequent processing. According to the predetermined indicator coupling constraint value, the calculated plurality of indicator coupling coefficients are classified into two categories. The predetermined indicator coupling constraint value is a threshold value for distinguishing between low-coupling and high-coupling indicator pairs. It can be set by a person skilled in the art to classify coupling coefficients less than the predetermined indicator coupling constraint value into a first indicator coupling coefficient set, and the indicator pairs corresponding to these coefficients are considered to be relatively independent. The coupling coefficients greater than or equal to the predetermined indicator coupling constraint value are classified into a second indicator coupling coefficient set, and the indicator pairs corresponding to these coefficients are considered to be highly coupled. According to the classified indicator coupling coefficient set, return to the original plurality of screening performance indicators, and match an independent screening performance indicator set corresponding to the first indicator coupling coefficient set. These indicators have a low degree of mutual dependence when they change and can be considered separately. Similarly, a coupling screening performance indicator set corresponding to the second indicator coupling coefficient set is matched. These indicators are highly interdependent when they change, and need to be further processed to reduce redundancy and complexity. For the highly coupled indicator pairs in the second indicator coupling coefficient set, appropriate indicator fusion methods such as principal component analysis and factor analysis are used for processing. These highly coupled indicators are fused into a few new decoupled indicators that can retain most of the information of the original indicators while reducing the degree of coupling between them. After the indicator fusion process, a decoupled screening performance indicator set is obtained. The indicators in this set reduce mutual dependence and complexity while retaining the original information. The independent screening performance indicator set and the decoupled screening performance indicator set are merged to form an updated first component safety performance impact indicator source. This indicator source contains both relatively independent indicators and new indicators after decoupling processing.

[0027] Furthermore, step 4 of this application also includes: According to the Y helmet components, extract the yth helmet component, where y is a positive integer and y belongs to Y; Based on the Y component safety value coefficients and the Y component safety performance impact index sources, matching the yth component safety value coefficient and the yth component safety performance impact index source corresponding to the yth helmet component; Based on each indicator in the safety performance impact indicator source of the yth component, indicator safety impact identification is performed to obtain multiple indicator safety impact coefficients, and the multiple indicator safety impact coefficients are calculated to obtain multiple indicator safety impact weights; Based on the safety value coefficient of the yth component and the safety impact weights of the multiple indicators, confidence detection scheme mining is performed according to the safety performance impact indicator source of the yth component to generate a yth component detection scheme set; Performing a detection destructive prediction on the yth helmet component based on the yth component detection solution set, obtaining a solution detection destructive prediction result, and constructing a detection solution execution constraint based on the solution detection destructive prediction result; Based on the detection scheme execution constraints, the yth helmet component is detected according to the yth component detection scheme set to obtain a yth component indicator detection result set; Based on the pre-built helmet heterogeneous safety analysis channel, analyze according to the yth component indicator detection result set to obtain multiple indicator safety detection coefficients; The safety detection coefficients of the multiple indicators are weightedly calculated based on the safety impact weights of the multiple indicators to generate a safety performance detection result of the yth component, and the safety performance detection result of the yth component is added to the safety performance detection results of the Y components.

[0028] Specifically, according to the Y helmet components, the information of the yth helmet component is extracted, where y is a positive integer, and y belongs to the set Y, that is, y is an element in Y. Ensure that the extracted component information is accurate. Based on the Y component safety value coefficients, find the yth component safety value coefficient corresponding to the yth helmet component. This coefficient reflects the importance of the component in the overall safety performance of the helmet. At the same time, match the yth component safety performance impact indicator source from the Y component safety performance impact indicator sources. These indicator sources will be used for subsequent safety performance analysis and detection plan formulation. Identify the indicator safety impact of each indicator in the yth component safety performance impact indicator source. Including evaluating the specific impact of each indicator on the component safety performance. Through the identification process, multiple indicator safety impact coefficients are obtained. These coefficients quantify the impact of each indicator on the safety performance. The proportion of these indicator safety impact coefficients is calculated to determine the relative importance of each indicator in the overall safety performance evaluation. Combine the yth component safety value coefficient and multiple indicator safety impact weights to mine confidence detection solutions. Through the mining process, a set of yth component detection solutions is generated. This solution set includes multiple possible detection solutions for the yth helmet component, each of which is optimized based on the safety value coefficient of the component and the safety impact weight of the indicator.

[0029] Furthermore, the present application also includes: Traversing the safety performance influencing indicator source of the yth component, and extracting the first safety performance influencing indicator of the yth helmet component; Based on the multiple indicator safety impact weights, match the first indicator safety impact weight corresponding to the first safety performance impact indicator, and calculate the first indicator safety comprehensive value coefficient in combination with the yth component safety value coefficient; Inputting the first indicator safety comprehensive value coefficient into a pre-constructed scheme mining confidence constraint table to match the first indicator scheme confidence constraint value, wherein the scheme mining confidence constraint table includes a plurality of preset indicator safety comprehensive value coefficients and a plurality of preset indicator scheme confidence constraint values; Collect sample detection solutions based on the first safety performance impact indicator to obtain a first indicator sample detection solution library; Perform support analysis based on the first indicator sample detection solution library to obtain detection solution support analysis results, and perform sample detection solution confidence calculation based on the detection solution support analysis results to obtain multiple sample solution confidences; Based on the first indicator solution confidence constraint value, the first indicator sample detection solution library is screened according to the confidence of the multiple sample solutions to obtain a first indicator confidence detection solution that is greater than the first indicator solution confidence constraint value, and the first indicator confidence detection solution is added to the yth component detection solution set.

[0030] Specifically, the yth component safety performance impact indicator source is traversed, and this indicator source contains multiple indicators that affect the safety performance of the yth helmet component. The first safety performance impact indicator is extracted from it, which can be each indicator in the yth component safety performance impact indicator source. The first indicator safety impact weight corresponding to the first safety performance impact indicator is matched. This weight reflects the importance of the indicator in the component safety performance evaluation. Combined with the yth component safety value coefficient, the first indicator safety comprehensive value coefficient is calculated. Preferably, the first indicator safety comprehensive value coefficient can be obtained by multiplying the first indicator safety impact weight by the yth component safety value coefficient. This coefficient comprehensively considers the importance of the indicator and the safety value of the component itself, and is used for subsequent solution mining and decision-making. The calculated first indicator safety comprehensive value coefficient is input into the pre-constructed solution mining confidence constraint table. This table contains multiple preset indicator safety comprehensive value coefficients and corresponding indicator solution confidence constraint values. Find the preset indicator safety comprehensive value coefficient that matches the first indicator safety comprehensive value coefficient in the table, and obtain the corresponding preset indicator solution confidence constraint value as the first indicator solution confidence constraint value. Based on the first safety performance impact indicator, the sample detection solution is collected. The collected detection schemes are organized into a first indicator sample detection scheme library. This library will contain multiple potential detection schemes, each of which may be used to evaluate the first safety performance impact indicator. Support analysis is performed on the first indicator sample detection scheme library. Support analysis aims to evaluate the feasibility and popularity of each detection scheme in practical applications. This can be achieved by analyzing historical data, user feedback, expert ratings, etc. According to the support analysis results, the confidence of each sample detection scheme is calculated. Confidence is a quantitative indicator used to measure the reliability and effectiveness of the detection scheme. Schemes with high confidence are more likely to accurately evaluate the first safety performance impact indicator. Use the first indicator scheme confidence constraint value as the screening criterion. This constraint value is matched from the scheme mining confidence constraint table according to the safety comprehensive value coefficient of the indicator in the previous step. Compare the calculated confidence of multiple sample schemes with the confidence constraint value of the first indicator scheme. Screen out sample detection schemes with confidence greater than the confidence constraint value of the first indicator scheme. Add the screened first indicator confidence detection scheme to the yth component detection scheme set. The updated set of testing solutions for the yth component will include more high-quality testing solutions targeting the first safety performance influencing indicators, thereby improving the ability to evaluate the safety performance of helmet components.

[0031] Furthermore, the present application also includes: Based on the detection scheme execution constraints, the yth helmet component is detected according to the yth component detection scheme set to obtain an index detection result data set and a detection process monitoring data set; Performing abnormal feature recognition based on the detection process monitoring data set to obtain a monitoring abnormality recognition result; Based on the monitoring anomaly identification result, an anomaly correlation analysis is performed on the indicator detection result data set to obtain a monitoring anomaly detection correlation analysis result; The indicator detection result data set is compensated based on the monitoring anomaly detection association analysis result to generate the yth component indicator detection result set.

[0032] Specifically, based on the constructed detection scheme execution constraints, the yth helmet component is tested according to the yth component detection scheme set. These constraints ensure the safety and effectiveness of the detection process while maximizing the accuracy of the detection results. During the detection process, two key data sets are collected, the indicator detection result data set and the detection process monitoring data set. The indicator detection result data set records the actual performance of the component on various safety performance indicators, while the detection process monitoring data set records various parameters and operation information during the detection process. The collected detection process monitoring data set is subjected to abnormal feature recognition. This includes using machine learning algorithms or rule engines to analyze and identify abnormal patterns or deviations from normal behavior in the data set. Monitoring anomaly recognition results are obtained, which indicate abnormal events or potential problems that occurred during the detection process. Based on the monitoring anomaly recognition results, the indicator detection result data set is subjected to abnormal association analysis. The purpose of this step is to determine whether the anomalies that occurred during the detection process have an impact on the indicator detection results, as well as the specific nature and extent of this impact. Through the abnormal association analysis, the monitoring anomaly detection association analysis results can be obtained. These results reveal the potential connection between abnormal events and indicator detection results, which helps to more accurately understand the safety performance of components. According to the monitoring anomaly detection association analysis results, the indicator detection result data set is compensated. The purpose of compensation is to adjust the indicator detection results affected by the anomaly to make them closer to the actual safety performance of the component. Compensation methods may include data interpolation, filtering, model prediction, etc., depending on the type and impact of the anomaly. After compensation processing, the yth component indicator detection result set is generated. This result set combines the performance of the component on various safety performance indicators, while taking into account the anomalies during the detection process, providing a more accurate data basis for subsequent safety performance evaluation.

[0033] Furthermore, the present application also includes: Based on each indicator in the safety performance impact indicator source of the yth component, indicator safety detection analysis record collection is performed to obtain multiple indicator safety detection analysis record data sets; Based on an integrated learning algorithm, supervised learning is performed on the multiple indicator safety detection and analysis record data sets according to preset convergence constraints to obtain multiple indicator safety detection and analysis units, wherein each indicator safety detection and analysis unit includes multiple indicator safety detection analyzers that meet the preset convergence constraints; Loading the security detection and analysis accuracy parameters corresponding to each indicator security detection and analysis unit in the multiple indicator security detection and analysis units to obtain multiple security detection and analysis accuracy sets; Calculating the proportions of the multiple safety detection analysis accuracy sets respectively, and constructing multiple safety detection output excitation units, wherein each safety detection output excitation unit includes multiple safety detection output excitation coefficients; The multiple indicator safety detection and analysis units and the multiple safety detection output excitation units are integrated and fused to generate the helmet heterogeneous safety analysis channel.

[0034] Specifically, identify key safety performance indicators from the safety performance influencing indicator sources of the yth component. These indicators may include physical strength, impact resistance, electrical safety, etc., depending on the design and usage scenario of the helmet. For each key indicator, collect historical safety test analysis records. Clean the collected raw data to remove invalid, repeated or erroneous data points. At the same time, annotate the data to clarify the indicators, test conditions, and results corresponding to each record. Organize the cleaned and annotated data into structured data sets, each of which focuses on a specific safety performance indicator. Select an ensemble learning algorithm suitable for the problem. The ensemble learning algorithm can combine the prediction results of multiple basic models to improve the overall prediction accuracy. Including bagging, boosting and stacking. The data set for each indicator is divided into a training set and a test set. The training set is used to train the model, and the test set is used to evaluate the performance of the model. Use the selected ensemble learning algorithm and training set to train the model for each indicator. During the training process, minimize the training error by adjusting the model parameters and optimizer settings. Use the test set to evaluate each trained model and calculate its performance indicators such as accuracy, recall, F1 score, etc. on unseen data. According to the evaluation results, the model with the best performance is selected as the safety detection analyzer for each indicator. The best models selected for each indicator are combined to form an indicator safety detection analysis unit. Each analysis unit contains multiple analyzers for different indicators. For each safety detection analyzer, the accuracy parameters such as accuracy and false alarm rate achieved during the training process are obtained. These parameters reflect the analyzer's detection ability for specific indicators. According to the accuracy parameters of each analyzer, its proportion in the analysis unit to which it belongs is calculated. The proportion can be allocated according to the relative size of the accuracy parameter, and the analyzer with higher accuracy will obtain a larger proportion. Based on the calculation results of the proportion, a safety detection output excitation unit is constructed for each analysis unit. The excitation coefficient in the excitation unit is calculated based on the proportion and is used to adjust the output weights of different analyzers in subsequent safety detection. The setting of the excitation coefficient should ensure the accuracy and reliability of the overall detection results. Multiple indicator safety detection analysis units are fused with the corresponding safety detection output excitation units. This means that when performing safety detection, the outputs of different analysis units will be weighted and combined according to the excitation coefficient to form a comprehensive detection result. By integrating and fusing multiple analysis units and excitation units, a helmet heterogeneous safety analysis channel is constructed. This channel can comprehensively utilize information from multiple safety performance indicators to provide comprehensive and accurate safety detection results. In practical applications, the channel can be continuously optimized and adjusted based on the feedback from the detection results to improve its performance and adaptability.

[0035] In summary, the safety performance detection method of a smart protective helmet provided by this application has the following technical effects: By obtaining a helmet component set of a target protective helmet, wherein the helmet component set includes Y helmet components of the target protective helmet, wherein Y is the total number of components of the target protective helmet; performing safety performance influencing indicator mining on the Y helmet components according to predetermined influencing indicator feature constraints, and obtaining Y component safety performance influencing indicator sources, wherein the predetermined influencing indicator feature constraints include predetermined indicator safety association constraints and predetermined indicator coupling constraint values; performing helmet safety impact assessments on the Y helmet components respectively, obtaining Y component safety impact coefficients, and performing proportion calculations based on the Y component safety impact coefficients, and obtaining Y component safety value coefficients; based on a helmet heterogeneous safety verification algorithm, performing safety performance detection and analysis on the Y helmet components respectively according to the Y component safety value coefficients and the Y component safety performance influencing indicator sources, and obtaining Y component safety performance detection results; performing data fusion on the Y component safety performance detection results based on the Y component safety value coefficients, and generating a comprehensive helmet safety performance detection result; generating a helmet safety performance detection report based on the comprehensive helmet safety performance detection result and the Y component safety performance detection results. It effectively solves the technical problems that the existing technology cannot deeply mine the indicators of each component and cannot take into account the independent safety performance of each component, resulting in incomplete and inaccurate evaluation results. According to the comprehensive test results and the test results of each component, a detailed helmet safety performance test report can also be generated.

[0036] Embodiment 2 Based on the same inventive concept as the safety performance detection method of an intelligent protective helmet in the aforementioned embodiment, the present application also provides a safety performance detection system for an intelligent protective helmet, see the attached Figure 2 , the system comprising: A helmet component set acquisition module 11, wherein the helmet component set acquisition module 11 is used to obtain a helmet component set of a target protective helmet, wherein the helmet component set includes Y helmet components of the target protective helmet, wherein Y is the total number of components of the target protective helmet; A performance impact indicator source acquisition module 12, the performance impact indicator source acquisition module 12 is used to mine the safety performance impact indicators of the Y helmet components according to the predetermined impact indicator feature constraints, and obtain the safety performance impact indicator sources of the Y components, wherein the predetermined impact indicator feature constraints include predetermined indicator safety association constraints and predetermined indicator coupling constraint values; A safety impact coefficient acquisition module 13, wherein the safety impact coefficient acquisition module 13 is used to perform helmet safety impact assessments on the Y helmet components respectively, obtain safety impact coefficients of the Y components, and perform a proportion calculation based on the safety impact coefficients of the Y components to obtain safety value coefficients of the Y components; The performance test result acquisition module 14 is used to perform safety performance test analysis on the Y helmet components respectively based on the helmet heterogeneous safety verification algorithm and the Y component safety value coefficients and the Y component safety performance impact indicator sources to obtain the safety performance test results of the Y components; A data fusion module 15, the data fusion module 15 is used to perform data fusion on the safety performance test results of the Y components based on the safety value coefficients of the Y components to generate a comprehensive test result of the safety performance of the helmet; The performance test report generating module 16 is used to generate a helmet safety performance test report according to the comprehensive test results of the helmet safety performance and the safety performance test results of the Y components.

[0037] Furthermore, the performance impact indicator source acquisition module 12 in the system is also used for: Traversing the Y helmet components and extracting the first helmet component; Loading a first component performance indicator set corresponding to the first helmet component, wherein the first component performance indicator set includes a plurality of performance indicators corresponding to the first helmet component; Performing helmet safety association identification on each performance indicator in the first component performance indicator set respectively to obtain multiple indicator safety association identification results; Based on the multiple indicator security association identification results, the first component performance indicator set is screened according to the predetermined indicator security association constraint to obtain multiple screened performance indicators that meet the predetermined indicator security association constraint; Based on the predetermined indicator coupling constraint value, an indicator coupling screening analysis is performed on the multiple screening performance indicators to generate a first component safety performance impact indicator source, and the first component safety performance impact indicator source is added to the Y component safety performance impact indicator sources.

[0038] Furthermore, the system further comprises a decoupling screening performance indicator set acquisition module, wherein the decoupling screening performance indicator set acquisition module is used to: Traversing the plurality of screening performance indicators to perform pairwise coupling analysis to obtain a plurality of indicator coupling coefficients; Based on the predetermined indicator coupling constraint value, the plurality of indicator coupling coefficients are classified into two categories to obtain a first indicator coupling coefficient set that is less than the predetermined indicator coupling constraint value, and a second indicator coupling coefficient set that is greater than / equal to the predetermined indicator coupling constraint value; Based on the multiple screening performance indicators, matching the independent screening performance indicator set corresponding to the first indicator coupling coefficient set and the coupled screening performance indicator set corresponding to the second indicator coupling coefficient set; Based on the second indicator coupling coefficient set, the coupled screening performance indicator set is subjected to indicator fusion to obtain a decoupled screening performance indicator set; The independent screening performance indicator set and the decoupled screening performance indicator set are added to the first component safety performance impact indicator source.

[0039] Furthermore, the performance test result acquisition module 14 in the system is also used for: Extracting the yth helmet component according to the Y helmet components, wherein y is a positive integer and y belongs to Y; Based on the Y component safety value coefficients and the Y component safety performance impact index sources, matching the yth component safety value coefficient and the yth component safety performance impact index source corresponding to the yth helmet component; Based on each indicator in the safety performance impact indicator source of the yth component, indicator safety impact identification is performed to obtain multiple indicator safety impact coefficients, and the multiple indicator safety impact coefficients are calculated to obtain multiple indicator safety impact weights; Based on the safety value coefficient of the yth component and the safety impact weights of the multiple indicators, confidence detection scheme mining is performed according to the safety performance impact indicator source of the yth component to generate a yth component detection scheme set; Performing a detection destructive prediction on the yth helmet component based on the yth component detection solution set, obtaining a solution detection destructive prediction result, and constructing a detection solution execution constraint based on the solution detection destructive prediction result; Based on the detection scheme execution constraints, the yth helmet component is detected according to the yth component detection scheme set to obtain a yth component indicator detection result set; Based on the pre-built helmet heterogeneous safety analysis channel, analyze according to the yth component indicator detection result set to obtain multiple indicator safety detection coefficients; The safety detection coefficients of the multiple indicators are weightedly calculated based on the safety impact weights of the multiple indicators to generate a safety performance detection result of the yth component, and the safety performance detection result of the yth component is added to the safety performance detection results of the Y components.

[0040] Furthermore, the system further comprises a sample detection scheme library acquisition module, wherein the sample detection scheme library acquisition module is used to: Traversing the safety performance influencing indicator source of the yth component, and extracting the first safety performance influencing indicator of the yth helmet component; Based on the multiple indicator safety impact weights, match the first indicator safety impact weight corresponding to the first safety performance impact indicator, and calculate the first indicator safety comprehensive value coefficient in combination with the yth component safety value coefficient; Inputting the first indicator safety comprehensive value coefficient into a pre-constructed scheme mining confidence constraint table to match the first indicator scheme confidence constraint value, wherein the scheme mining confidence constraint table includes a plurality of preset indicator safety comprehensive value coefficients and a plurality of preset indicator scheme confidence constraint values; Collect sample detection solutions based on the first safety performance impact indicator to obtain a first indicator sample detection solution library; Perform support analysis based on the first indicator sample detection solution library to obtain detection solution support analysis results, and perform sample detection solution confidence calculation based on the detection solution support analysis results to obtain multiple sample solution confidences; Based on the first indicator solution confidence constraint value, the first indicator sample detection solution library is screened according to the confidence of the multiple sample solutions to obtain a first indicator confidence detection solution that is greater than the first indicator solution confidence constraint value, and the first indicator confidence detection solution is added to the yth component detection solution set.

[0041] Furthermore, the system further comprises an abnormality detection association analysis result acquisition module, wherein the abnormality detection association analysis result acquisition module is used to: Based on the detection scheme execution constraints, the yth helmet component is detected according to the yth component detection scheme set to obtain an index detection result data set and a detection process monitoring data set; Performing abnormal feature recognition based on the detection process monitoring data set to obtain a monitoring abnormality recognition result; Based on the monitoring anomaly identification result, an anomaly correlation analysis is performed on the indicator detection result data set to obtain a monitoring anomaly detection correlation analysis result; The indicator detection result data set is compensated based on the monitoring anomaly detection association analysis result to generate the yth component indicator detection result set.

[0042] Furthermore, the system further includes a heterogeneous security analysis channel acquisition module, and the heterogeneous security analysis channel acquisition module is used to: Based on each indicator in the safety performance impact indicator source of the yth component, indicator safety detection analysis record collection is performed to obtain multiple indicator safety detection analysis record data sets; Based on an integrated learning algorithm, supervised learning is performed on the multiple indicator safety detection and analysis record data sets according to preset convergence constraints to obtain multiple indicator safety detection and analysis units, wherein each indicator safety detection and analysis unit includes multiple indicator safety detection analyzers that meet the preset convergence constraints; Loading the security detection and analysis accuracy parameters corresponding to each indicator security detection and analysis unit in the multiple indicator security detection and analysis units to obtain multiple security detection and analysis accuracy sets; Calculating the proportions of the multiple safety detection analysis accuracy sets respectively, and constructing multiple safety detection output excitation units, wherein each safety detection output excitation unit includes multiple safety detection output excitation coefficients; The multiple indicator safety detection and analysis units and the multiple safety detection output excitation units are integrated and fused to generate the helmet heterogeneous safety analysis channel.

[0043] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. Figure 1 The safety performance detection method and specific examples of a smart protective helmet in the first embodiment are also applicable to the safety performance detection system of a smart protective helmet in the present embodiment. Through the above detailed description of the safety performance detection method of a smart protective helmet, those skilled in the art can clearly know the safety performance detection system of a smart protective helmet in the present embodiment, so for the sake of brevity of the specification, it will not be described in detail here. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method part.

[0044] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0045] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. A method for detecting the safety performance of an intelligent protective helmet, characterized in that: The method comprises: Obtaining a helmet component set of a target protective helmet, wherein the helmet component set includes Y helmet components of the target protective helmet, wherein Y is the total number of components of the target protective helmet; According to the predetermined influencing indicator feature constraints, the safety performance influencing indicators of the Y helmet components are mined respectively to obtain the safety performance influencing indicator sources of the Y components, wherein the predetermined influencing indicator feature constraints include predetermined indicator safety association constraints and predetermined indicator coupling constraint values; Conducting helmet safety impact assessments on the Y helmet components respectively to obtain safety impact coefficients of the Y components, and performing ratio calculations based on the safety impact coefficients of the Y components to obtain safety value coefficients of the Y components; Based on the helmet heterogeneous safety verification algorithm, according to the safety value coefficients of the Y components and the safety performance influencing indicator sources of the Y components, the safety performance detection and analysis of the Y helmet components are respectively performed to obtain the safety performance detection results of the Y components; Based on the safety value coefficients of the Y components, data fusion is performed on the safety performance test results of the Y components to generate a comprehensive test result of the safety performance of the helmet; A helmet safety performance test report is generated based on the comprehensive test results of the helmet safety performance and the safety performance test results of the Y components.

2. The method according to claim 1, characterized in that According to the predetermined influencing index feature constraints, the Y helmet components are respectively mined for safety performance influencing indexes to obtain Y component safety performance influencing index sources, including: Traversing the Y helmet components and extracting the first helmet component; Loading a first component performance indicator set corresponding to the first helmet component, wherein the first component performance indicator set includes a plurality of performance indicators corresponding to the first helmet component; Performing helmet safety association identification on each performance indicator in the first component performance indicator set respectively to obtain multiple indicator safety association identification results; Based on the multiple indicator security association identification results, the first component performance indicator set is screened according to the predetermined indicator security association constraint to obtain multiple screened performance indicators that meet the predetermined indicator security association constraint; Based on the predetermined indicator coupling constraint value, an indicator coupling screening analysis is performed on the multiple screening performance indicators to generate a first component safety performance impact indicator source, and the first component safety performance impact indicator source is added to the Y component safety performance impact indicator sources.

3. The method according to claim 2, characterized in that Performing an indicator coupling screening analysis on the plurality of screening performance indicators based on the predetermined indicator coupling constraint value to generate a first component safety performance impact indicator source includes: Traversing the plurality of screening performance indicators to perform pairwise coupling analysis to obtain a plurality of indicator coupling coefficients; Based on the predetermined indicator coupling constraint value, the plurality of indicator coupling coefficients are classified into two categories to obtain a first indicator coupling coefficient set that is less than the predetermined indicator coupling constraint value, and a second indicator coupling coefficient set that is greater than / equal to the predetermined indicator coupling constraint value; Based on the multiple screening performance indicators, matching the independent screening performance indicator set corresponding to the first indicator coupling coefficient set and the coupled screening performance indicator set corresponding to the second indicator coupling coefficient set; Based on the second indicator coupling coefficient set, the coupled screening performance indicator set is subjected to indicator fusion to obtain a decoupled screening performance indicator set; The independent screening performance indicator set and the decoupled screening performance indicator set are added to the first component safety performance impact indicator source.

4. The method according to claim 1, characterized in that Based on the helmet heterogeneous safety verification algorithm, according to the safety value coefficients of the Y components and the safety performance influencing indicator sources of the Y components, the safety performance detection and analysis of the Y helmet components are performed respectively to obtain the safety performance detection results of the Y components, including: Extracting the yth helmet component according to the Y helmet components, wherein y is a positive integer and y belongs to Y; Based on the Y component safety value coefficients and the Y component safety performance impact index sources, matching the yth component safety value coefficient and the yth component safety performance impact index source corresponding to the yth helmet component; Based on each indicator in the safety performance impact indicator source of the yth component, indicator safety impact identification is performed to obtain multiple indicator safety impact coefficients, and the multiple indicator safety impact coefficients are calculated to obtain multiple indicator safety impact weights; Based on the safety value coefficient of the yth component and the safety impact weights of the multiple indicators, confidence detection scheme mining is performed according to the safety performance impact indicator source of the yth component to generate a yth component detection scheme set; Performing a detection destructive prediction on the yth helmet component based on the yth component detection solution set, obtaining a solution detection destructive prediction result, and constructing a detection solution execution constraint based on the solution detection destructive prediction result; Based on the detection scheme execution constraints, the yth helmet component is detected according to the yth component detection scheme set to obtain a yth component indicator detection result set; Based on the pre-built helmet heterogeneous safety analysis channel, analyze according to the yth component indicator detection result set to obtain multiple indicator safety detection coefficients; The safety detection coefficients of the multiple indicators are weightedly calculated based on the safety impact weights of the multiple indicators to generate a safety performance detection result of the yth component, and the safety performance detection result of the yth component is added to the safety performance detection results of the Y components.

5. The method according to claim 4, characterized in that Based on the safety value coefficient of the yth component and the safety impact weights of the multiple indicators, a confidence detection scheme mining is performed according to the safety performance impact indicator source of the yth component to generate a yth component detection scheme set, including: Traversing the safety performance influencing indicator source of the yth component, and extracting the first safety performance influencing indicator of the yth helmet component; Based on the multiple indicator safety impact weights, match the first indicator safety impact weight corresponding to the first safety performance impact indicator, and calculate the first indicator safety comprehensive value coefficient in combination with the yth component safety value coefficient; Inputting the first indicator safety comprehensive value coefficient into a pre-constructed scheme mining confidence constraint table to match the first indicator scheme confidence constraint value, wherein the scheme mining confidence constraint table includes a plurality of preset indicator safety comprehensive value coefficients and a plurality of preset indicator scheme confidence constraint values; Collect sample detection solutions based on the first safety performance impact indicator to obtain a first indicator sample detection solution library; Perform support analysis based on the first indicator sample detection solution library to obtain detection solution support analysis results, and perform sample detection solution confidence calculation based on the detection solution support analysis results to obtain multiple sample solution confidences; Based on the first indicator solution confidence constraint value, the first indicator sample detection solution library is screened according to the confidence of the multiple sample solutions to obtain a first indicator confidence detection solution that is greater than the first indicator solution confidence constraint value, and the first indicator confidence detection solution is added to the yth component detection solution set.

6. The method according to claim 4, characterized in that Based on the detection scheme execution constraint, the yth helmet component is detected according to the yth component detection scheme set to obtain the yth component indicator detection result set, including: Based on the detection scheme execution constraints, the yth helmet component is detected according to the yth component detection scheme set to obtain an index detection result data set and a detection process monitoring data set; Performing abnormal feature recognition based on the detection process monitoring data set to obtain a monitoring abnormality recognition result; Based on the monitoring anomaly identification result, an anomaly correlation analysis is performed on the indicator detection result data set to obtain a monitoring anomaly detection correlation analysis result; The indicator detection result data set is compensated based on the monitoring anomaly detection association analysis result to generate the yth component indicator detection result set.

7. The method according to claim 4, characterized in that The method comprises: Based on each indicator in the safety performance impact indicator source of the yth component, indicator safety detection analysis record collection is performed to obtain multiple indicator safety detection analysis record data sets; Based on an integrated learning algorithm, supervised learning is performed on the multiple indicator safety detection and analysis record data sets according to preset convergence constraints to obtain multiple indicator safety detection and analysis units, wherein each indicator safety detection and analysis unit includes multiple indicator safety detection analyzers that meet the preset convergence constraints; Loading the security detection and analysis accuracy parameters corresponding to each indicator security detection and analysis unit in the multiple indicator security detection and analysis units to obtain multiple security detection and analysis accuracy sets; Calculating the proportions of the multiple safety detection analysis accuracy sets respectively, and constructing multiple safety detection output excitation units, wherein each safety detection output excitation unit includes multiple safety detection output excitation coefficients; The multiple indicator safety detection and analysis units and the multiple safety detection output excitation units are integrated and fused to generate the helmet heterogeneous safety analysis channel.

8. A safety performance detection system for an intelligent protective helmet, characterized in that: For implementing the steps of the method according to any one of claims 1 to 7, the system comprises: A helmet component set acquisition module, wherein the helmet component set acquisition module is used to obtain a helmet component set of a target protective helmet, wherein the helmet component set includes Y helmet components of the target protective helmet, wherein Y is the total number of components of the target protective helmet; A performance impact indicator source acquisition module, the performance impact indicator source acquisition module is used to mine the safety performance impact indicators of the Y helmet components according to the predetermined impact indicator feature constraints, and obtain the safety performance impact indicator sources of the Y components, wherein the predetermined impact indicator feature constraints include predetermined indicator safety association constraints and predetermined indicator coupling constraint values; A safety impact coefficient acquisition module, the safety impact coefficient acquisition module is used to perform helmet safety impact assessments on the Y helmet components respectively, obtain safety impact coefficients of the Y components, and perform a proportion calculation based on the safety impact coefficients of the Y components to obtain safety value coefficients of the Y components; A performance test result acquisition module, the performance test result acquisition module is used to perform safety performance test analysis on the Y helmet components respectively based on the helmet heterogeneous safety verification algorithm and the Y component safety value coefficients and the Y component safety performance impact indicator sources to obtain the safety performance test results of the Y components; A data fusion module, the data fusion module is used to perform data fusion on the safety performance test results of the Y components based on the safety value coefficients of the Y components to generate a comprehensive test result of the safety performance of the helmet; A performance test report generation module is used to generate a helmet safety performance test report based on the comprehensive test results of the helmet safety performance and the safety performance test results of the Y components.

Images