Trigger mechanism detection method and system for fire extinguishing equipment
By constructing an environmental feature map model and Bayesian network evaluation, combined with formal verification, the problem of difficult verification of response speed and accuracy of traditional fire extinguishing equipment testing methods in complex fire scenarios is solved, and the automatic triggering mechanism of fire extinguishing equipment is improved. Reliability and effectiveness in the environment.
Patent Information
- Application Number
- CN202411229499.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-03
- Publication Date
- 2024-11-05
- Estimated Expiration
- 2044-09-03
AI Technical Summary
The traditional fire extinguishing equipment trigger mechanism testing methods lack sufficient simulation and comprehensive performance evaluation of real environmental variability, making it difficult to effectively verify response speed, sensitivity and accuracy in complex or non-standard fire scenarios, resulting in unforeseen risks.
By building an environmental feature map model, dynamically generate multiple fire situations, simulate the automatic triggering mechanism of fire extinguishing equipment, record response data, optimize performance, use Bayesian network to evaluate accuracy, and identify and correct logical errors and designs through formal verification defect.
It improves the comprehensiveness and practicality of the test, enhances the reliability and effectiveness of the trigger mechanism, and significantly reduces personal injury and property losses caused by untimely or inaccurate responses.
Smart Images

Figure CN118743835B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of automatic trigger mechanism testing, and in particular to a trigger mechanism detection method and system for fire extinguishing equipment. Background Art
[0002] The field of automatic trigger mechanism testing technology focuses on developing, optimizing and verifying the performance of trigger mechanisms in various automated systems and equipment. Especially in safety and emergency response equipment, the reliability of automatic trigger mechanisms is crucial. The field includes the evaluation of the reaction speed, sensitivity, accuracy of the trigger mechanism and its stability under different environmental conditions. By continuously exploring new test methods, we can ensure that the automatic trigger system can be activated quickly and accurately in an emergency, thereby minimizing personal injury and property loss.
[0003] Among them, the fire extinguishing equipment trigger mechanism detection method is a set of test procedures and technologies designed to evaluate the performance of the automatic trigger mechanism in the fire extinguishing equipment. The main purpose of this method is to ensure that the fire extinguishing equipment can be automatically and immediately activated when a fire is detected, so as to achieve rapid fire extinguishing, thereby effectively controlling the fire and reducing the damage caused by the fire. The test method simulates various fire scenarios to evaluate the response time, sensitivity and reliability of the trigger mechanism to ensure that it can work effectively in real fire situations.
[0004] Traditional trigger mechanism testing methods lack sufficient simulation of the variability of real environments and comprehensive performance evaluation when evaluating and verifying the performance of automatic trigger mechanisms. When faced with complex or non-standard fire scenarios, the response speed, sensitivity and accuracy of the trigger mechanism are difficult to be effectively verified. Traditional methods rely on experience and judgment to identify logical errors and design defects, and lack systematic analysis and verification tools, resulting in unforeseen risks in the actual application of the trigger mechanism. Summary of the invention
[0005] The purpose of the present invention is to solve the shortcomings in the prior art and to propose a trigger mechanism detection method and system for fire extinguishing equipment.
[0006] In order to achieve the above object, the present invention adopts the following technical solution: a method for detecting a trigger mechanism of a fire extinguishing device comprises the following steps:
[0007] S1: Based on the real environment scene and material data, an environment model is constructed, each node is used to represent the environment feature, and the edge represents the interaction between features. The key environment features are identified by traversal to obtain the environment feature graph model;
[0008] S2: Based on the environmental feature graph model, dynamically generate environmental scenes representing various fire situations, adjust scene parameters, optimize simulation effects, and obtain a set of simulated fire scenes;
[0009] S3: deploying an automatic trigger mechanism for fire extinguishing equipment according to the simulated fire scenario set, simulating conditions encountered in actual operation, and recording trigger mechanism response data to obtain a trigger mechanism performance evaluation result;
[0010] S4: Based on the performance evaluation results of the trigger mechanism, the fire scenario generation logic is optimized, and the parameter settings are adjusted according to the performance feedback to obtain a performance optimization strategy;
[0011] S5: According to the performance optimization strategy, a Bayesian network model is used to define factors that affect the accuracy of the trigger mechanism, perform Bayesian inference to update the network state, and calculate the probability of trigger accuracy based on the data to obtain a Bayesian accuracy evaluation result;
[0012] S6: Based on the Bayesian accuracy evaluation results, a formal verification method is used to analyze the logical rules of the automatic triggering mechanism, perform a formal proof process, identify logical errors and design defects, and formulate corrective measures to obtain a logical verification and correction plan.
[0013] The improvements of the present invention are that the environmental characteristic graph model includes characteristic nodes of temperature level, humidity range and combustible type, the simulated fire scene set includes closed space fire scene, open area fire scene and electrical fire scene, the trigger mechanism performance evaluation result includes response speed, accuracy score, false triggering frequency, the performance optimization strategy includes trigger threshold adjustment measures, response speed improvement strategy, false triggering suppression measures, the Bayesian accuracy evaluation result includes sensor responsiveness, external environmental impact information, equipment status reliability information, and the logic verification and correction scheme includes rule conflict resolution strategy, performance optimization path, and safety threshold setting.
[0014] The present invention has the following improvements: according to the real environment scene and material data, an environment model is constructed, each node is used to represent the environment feature, the edge represents the interaction between the features, and the key environment features are identified by traversal, and the specific steps of obtaining the environment feature graph model are as follows:
[0015] S101: According to the real environment scene and material data, collect temperature, humidity, and combustible type information, and summarize and organize the information to obtain a basic environmental characteristic data set;
[0016] S102: Based on the basic environmental characteristic data set, each characteristic is classified and encoded, including classifying temperature into three categories: low, medium, and high, and classifying humidity into dry, normal, and humid, to obtain a classified and encoded environmental characteristic data set;
[0017] S103: Based on the classified and coded environmental characteristic data set, using the mutual relationship between environmental characteristics, including the association between temperature and combustible type, a connection relationship diagram between environmental characteristics is constructed to obtain an environmental characteristic diagram model.
[0018] The present invention is improved in that, based on the environmental characteristic graph model, environmental scenes representing various fire situations are dynamically generated, and scene parameters are adjusted to optimize the simulation effect. The specific steps of obtaining a simulated fire scene set are as follows:
[0019] S201: Based on the environmental characteristic graph model, dynamically generate environmental scenes representing various fire situations, formulate environmental parameter combinations under various fire scenes, adjust the combustible reaction rate under the wet scene, and obtain an environmental parameter combination data set;
[0020] S202: Based on the environmental parameter combination data set, simulate environmental changes under differentiated fire scenarios, and adjust temperature and humidity values to simulate the impact of fire sources to obtain a simulated environmental change data set;
[0021] S203: Based on the simulated environmental change data set, adjust the parameters under the differentiated scenarios, adjust the temperature change rate according to the fire spread speed, refine the differentiated fire scenarios, and obtain a simulated fire scenario set.
[0022] The present invention is improved in that, according to the simulated fire scene set, the automatic trigger mechanism of the fire extinguishing equipment is deployed, the conditions encountered in actual operation are simulated, and the trigger mechanism response data is recorded. The specific steps of obtaining the trigger mechanism performance evaluation result are as follows:
[0023] S301: According to the simulated fire scene, target environmental parameters are selected to deploy an automatic trigger mechanism for fire extinguishing equipment, actual operation simulation is performed, and trigger time and reaction sensitivity are recorded to obtain trigger data records;
[0024] S302: Based on the trigger data record, analyze the performance of the trigger mechanism in the differentiated scenarios, evaluate the response time and accuracy, identify the performance bottleneck, and obtain the performance bottleneck analysis result;
[0025] S303: According to the performance bottleneck analysis result, the trigger sensitivity and response parameters of the trigger mechanism of the fire extinguishing equipment are adjusted, and the simulation test is re-performed to verify the performance improvement after the adjustment, and the performance evaluation result of the trigger mechanism is obtained.
[0026] The present invention is improved in that, based on the performance evaluation result of the trigger mechanism, the fire scenario generation logic is optimized, and the parameter setting is adjusted according to the performance feedback, and the specific steps of obtaining the performance optimization strategy are as follows:
[0027] S401: According to the trigger mechanism performance evaluation result, identifying environmental parameters that affect the trigger mechanism performance, and adjusting the fire scenario to generate a new test scenario to obtain an adjusted test scenario set;
[0028] S402: Based on the adjusted test scenario set, perform simulation testing, collect trigger mechanism response data, analyze response efficiency and accuracy improvements, and obtain a refined performance data set;
[0029] S403: Based on the refined performance data set, parameter optimization is performed to adjust the sensitivity and response speed of the trigger mechanism of the fire extinguishing equipment, optimize the performance of the fire extinguishing equipment in various environments, and obtain a performance optimization strategy.
[0030] The present invention is improved in that, according to the performance optimization strategy, a Bayesian network model is adopted to define factors affecting the accuracy of the trigger mechanism, Bayesian inference is performed to update the network state, and the probability of trigger accuracy is calculated based on the data. The specific steps of obtaining the Bayesian accuracy evaluation result are as follows:
[0031] S501: According to the performance optimization strategy, identify key factors that affect the accuracy of the trigger mechanism, including temperature sensing accuracy and smoke recognition capability, organize the factors as input nodes of the Bayesian network, and obtain a factor definition list;
[0032] S502: constructing a Bayesian network model according to the factor definition list, assigning an initial probability value to each factor node according to historical data and expert experience, and obtaining a basic Bayesian network;
[0033] S503: Based on the basic Bayesian network, combined with the collected trigger mechanism operation data, the probability value in the Bayesian network is updated, and Bayesian inference is performed to optimize the network state, calculate the trigger accuracy probability, and obtain the Bayesian accuracy evaluation result;
[0034] The Bayesian inference is through the formula:
[0035]
[0036] Calculate the trigger accuracy probability and obtain the Bayesian accuracy evaluation result, where: Assume that the trigger mechanism is accurate. To trigger the mechanism to manipulate the data, is the environmental stability parameter, is the device response time parameter, Assumptions for environmental and equipment factors The weight coefficient of influence.
[0037] The present invention is improved in that, based on the Bayesian accuracy evaluation result, a formal verification method is adopted to analyze the logic rules of the automatic trigger mechanism, perform a formal proof process, identify logic errors and design defects, and formulate correction measures. The specific steps of obtaining the logic verification and correction plan are as follows:
[0038] S601: Based on the Bayesian accuracy evaluation result, identify the logic rules of the automatic trigger mechanism, including the trigger conditions and execution sequence, and generate a logic rule set;
[0039] S602: According to the logic rule set, a formal verification method is applied to analyze the logic rules, perform a proof process, identify logic errors and design defects, and record the problem points to obtain a logic error record;
[0040] The formal verification method is based on the formula:
[0041]
[0042] Calculate the state transition and get the logical error record, where:
[0043] represents the automatic trigger mechanism model, is a set of test scene parameters. Represents a set of performance indicator parameters, is a logical expression conversion function, Model checking function for automatic triggering mechanism;
[0044] S603: Based on the logic error record, formulate matching correction measures, including modifying the logic expression and adding missing conditions, to obtain a logic verification and correction plan.
[0045] A trigger mechanism detection system for fire extinguishing equipment, the system comprising:
[0046] The environmental analysis module collects temperature, humidity, and combustible type information based on real-world environmental scenarios and material data, and summarizes and processes the information to obtain an environmental characteristic data set;
[0047] The scene simulation module dynamically constructs environmental scenes representing various fire situations based on the environmental characteristic data set, optimizes the simulation effect by adjusting scene parameters, and obtains a simulated fire scene set;
[0048] The trigger performance test module deploys the automatic trigger mechanism of the fire extinguishing equipment based on the simulated fire scene set, simulates the actual operating conditions, records the response data of the trigger mechanism, and obtains the trigger performance data;
[0049] The performance evaluation module analyzes the performance of the trigger mechanism based on the trigger performance data, evaluates the response time and accuracy, identifies performance bottlenecks, and generates performance evaluation results;
[0050] The parameter adjustment module optimizes the fire scenario generation based on the performance evaluation results, adjusts the trigger threshold, response speed and false trigger suppression measures of the fire extinguishing equipment trigger mechanism, and obtains the adjusted parameter settings;
[0051] The accuracy analysis module applies the Bayesian network model based on the adjusted parameter settings, defines the factors that affect the accuracy of the trigger mechanism, performs Bayesian inference to update the network state, calculates the probability of trigger accuracy, and obtains the Bayesian accuracy evaluation result;
[0052] Based on the Bayesian accuracy evaluation results, the logic correction module adopts formal verification technology to analyze the logic rules of the automatic triggering mechanism, execute the proof process, identify and record logical errors and design defects, formulate correction measures, and obtain a logic verification and correction plan.
[0053] Compared with the prior art, the advantages and positive effects of the present invention are:
[0054] In the present invention, by constructing a variety of fire scenarios, in-depth analysis and simulation of actual fire environments, the comprehensiveness and practicality of the test are improved. In the performance evaluation and optimization strategy link, the Bayesian network model and formal verification method are used to enhance the quantitative evaluation capability of the accuracy of the trigger mechanism, and the formal proof of logical rules is introduced to effectively identify and correct logical errors and design defects, thereby ensuring the reliability and effectiveness of the automatic trigger mechanism in complex and changeable real environments, and significantly reducing personal injury and property loss caused by untimely or inaccurate response. BRIEF DESCRIPTION OF THE DRAWINGS
[0055] Figure 1 A flow chart of a method for detecting a trigger mechanism of a fire extinguishing device proposed by the present invention;
[0056] Figure 2 A schematic diagram of a detailed flow chart of step S1 in the method for detecting the trigger mechanism of a fire extinguishing device proposed in the present invention;
[0057] Figure 3 A detailed flow chart of step S2 in the method for detecting the trigger mechanism of a fire extinguishing device proposed by the present invention;
[0058] Figure 4 A detailed flow chart of step S3 in the method for detecting the trigger mechanism of a fire extinguishing device proposed by the present invention;
[0059] Figure 5 A detailed flow chart of step S4 in the method for detecting the trigger mechanism of a fire extinguishing device proposed by the present invention;
[0060] Figure 6 A detailed flow chart of step S5 in the method for detecting the trigger mechanism of a fire extinguishing device proposed by the present invention;
[0061] Figure 7 A detailed flow chart of step S6 in the method for detecting the trigger mechanism of a fire extinguishing device proposed by the present invention;
[0062] Figure 8 The present invention provides a module diagram of the trigger mechanism detection system of the fire extinguishing equipment. DETAILED DESCRIPTION
[0063] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.
[0064] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating positions or positional relationships, are based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined. Example
[0065] See also Figure 1 The present invention provides a technical solution: a method for detecting a trigger mechanism of a fire extinguishing device, comprising the following steps:
[0066] S1: Based on the real environment scene and material data, an environment model is constructed, each node is used to represent the environment feature, and the edge represents the interaction between features. The key environment features are identified by traversal to obtain the environment feature graph model;
[0067] S2: Based on the environmental feature graph model, dynamically generate environmental scenes representing various fire situations, adjust scene parameters, optimize simulation effects, and obtain a set of simulated fire scenes;
[0068] S3: Based on the simulated fire scenario set, deploy the automatic trigger mechanism of the fire extinguishing equipment, simulate the conditions encountered in actual operation, and record the trigger mechanism response data to obtain the trigger mechanism performance evaluation results;
[0069] S4: Based on the performance evaluation results of the trigger mechanism, the fire scenario generation logic is optimized, and the parameter settings are adjusted according to the performance feedback to obtain the performance optimization strategy;
[0070] S5: Based on the performance optimization strategy, the Bayesian network model is used to define the factors that affect the accuracy of the trigger mechanism, perform Bayesian inference to update the network state, and calculate the probability of trigger accuracy based on the data to obtain the Bayesian accuracy evaluation result;
[0071] S6: Based on the Bayesian accuracy evaluation results, a formal verification method is used to analyze the logical rules of the automatic trigger mechanism, perform a formal proof process, identify logical errors and design defects, and formulate corrective measures to obtain a logical verification and correction plan.
[0072] The environmental characteristic graph model includes characteristic nodes of temperature level, humidity range and combustible type. The simulated fire scenario set includes enclosed space fire scenario, open area fire scenario and electrical fire scenario. The trigger mechanism performance evaluation results include response speed, accuracy score and false trigger frequency. The performance optimization strategy includes trigger threshold adjustment measures, response speed improvement strategy and false trigger suppression measures. The Bayesian accuracy evaluation results include sensor responsiveness, external environmental impact information and equipment status reliability information. The logic verification and correction scheme includes rule conflict resolution strategy, performance optimization path and safety threshold setting.
[0073] See also Figure 2 ,According to the real environment scene and material data, the environment model is constructed, each node is used to represent the environment feature, the edge represents the interaction between the features, and the key environment features are identified by traversal. The specific steps to obtain the environment feature graph model are as follows:
[0074] S101: According to the real environment scene and material data, collect temperature, humidity, and combustible type information, and summarize and organize the information to obtain the basic environmental characteristic data set. The specific process is as follows;
[0075] In sub-step S101, based on real-world environmental scenarios and material data, a data collection method is adopted to automatically extract temperature, humidity, and combustible type information from multiple data sources using Python scripts. The Pandas library is used to organize the data, including removing duplicate values and processing missing data, to ensure the integrity and consistency of the information, and to generate a basic environmental characteristic data set.
[0076] S102: Based on the basic environmental characteristic data set, each characteristic is classified and encoded, including classifying temperature into three categories: low, medium, and high, and classifying humidity into dry, normal, and humid. The specific process of obtaining the classified and encoded environmental characteristic data set is as follows;
[0077] In sub-step S102, based on the basic environmental characteristic dataset, data classification and encoding technology is adopted, and the LabelEncoder and custom threshold division in Python's sklearn.preprocessing module are used to divide the temperature into three categories of low, medium, and high according to the set threshold, and the humidity is divided into dry, normal, and humid according to the similar threshold. A clear category label is given to each environmental characteristic to ensure that the characteristic data is operational, and a classified and encoded environmental characteristic dataset is generated.
[0078] S103: Based on the classified coded environmental characteristic data set, the relationship between environmental characteristics, including the relationship between temperature and combustible type, is used to construct a connection relationship diagram between environmental characteristics. The specific process of obtaining the environmental characteristic diagram model is as follows;
[0079] In sub-step S103, based on the classified coded environmental characteristic dataset, a graph theory algorithm is adopted, and the NetworkX library of Python is used to define nodes to represent environmental characteristics, such as temperature level, humidity range and combustible type, and edges to represent the interaction between characteristics, such as the association between temperature and combustible type. The graph construction process is executed, which includes setting the weights of nodes and edges to indicate the strength of the interaction between characteristics, accurately expressing the complex relationship between environmental characteristics, and generating an environmental characteristic graph model.
[0080] See also Figure 3 ,Based on the environmental feature graph model, the specific steps of dynamically generating environmental scenes representing various fire situations,adjusting the scene parameters, optimizing the simulation effect, and obtaining the simulated fire scene set are as follows:
[0081] S201: Based on the environmental feature graph model, dynamically generate environmental scenes representing various fire scenarios, formulate environmental parameter combinations under various fire scenarios, adjust the combustible reaction rate under the wet scene, and obtain the specific process of the environmental parameter combination data set as follows;
[0082] In sub-step S201, based on the environmental characteristic graph model, a scenario generation algorithm is adopted, and Python's NumPy library is used to randomly generate environmental parameters representing different fire scenarios, such as temperature, humidity, and combustible reaction rate. By setting different parameter ranges and distributions, the environmental characteristics under various fire scenarios are simulated, and the combustible reaction rate under temperature and humidity conditions is adjusted to ensure that the generated environmental parameters can cover a wide range of fire scenarios, and generate an environmental parameter combination data set.
[0083] S202: Based on the environmental parameter combination data set, simulate the environmental changes under the differentiated fire scenario, adjust the temperature and humidity values, simulate the impact of the fire source, and obtain the simulated environmental change data set. The specific process is as follows;
[0084] In sub-step S202, based on the environmental parameter combination data set, simulation technology is adopted, and the Simulink environment in MATLAB software is used to simulate the environmental changes under differentiated fire scenarios. By adjusting the temperature and humidity parameters in the Simulink model, the influence of the fire source is simulated, accurately reflecting the dynamic changes of environmental parameters under different fire scenarios, and generating a simulated environmental change data set.
[0085] S203: Based on the simulated environmental change data set, the parameters under the differentiated scenarios are adjusted, the temperature change rate is adjusted according to the fire spread speed, and the differentiated fire scenarios are refined to obtain the simulated fire scenario set. The specific process is as follows;
[0086] In sub-step S203, based on the simulated environmental change data set, the parameter adjustment method is adopted, and the Python script is used to carefully adjust the parameters in the differentiated scenarios. The temperature change rate is adjusted according to the preset fire spread model. The spread speed and diffusion range of the fire are simulated by adjusting the parameters to ensure the real-time adaptability and accuracy of the parameters in the differentiated fire scenarios, and generate a set of simulated fire scenarios.
[0087] See also Figure 4 ,According to the simulated fire scenario set, the automatic trigger mechanism of the fire extinguishing equipment is deployed, the conditions encountered in actual operation are simulated, and the trigger mechanism response data is recorded. The specific steps to obtain the performance evaluation results of the trigger mechanism are as follows:
[0088] S301: According to the simulated fire scene, target environmental parameters are selected to deploy the automatic trigger mechanism of the fire extinguishing equipment, actual operation simulation is performed, and the trigger time and reaction sensitivity are recorded. The specific process of obtaining the trigger data record is as follows;
[0089] In sub-step S301, based on the simulated fire scenario, scenario simulation technology is adopted, using MATLAB software and Simulink environment, and according to the selected target environmental parameters, a simulation model of the automatic triggering mechanism of the fire extinguishing equipment is deployed to perform actual operation simulation. Through the data recording module in the Simulink environment, the triggering time and reaction sensitivity are recorded to ensure that the acquired data reflects the performance of the automatic triggering mechanism of the fire extinguishing equipment under different fire scenarios, and to generate trigger data records.
[0090] S302: Based on the trigger data records, analyze the performance of the trigger mechanism in the differentiated scenarios, evaluate the response time and accuracy, identify the performance bottleneck, and obtain the specific process of the performance bottleneck analysis result as follows;
[0091] In sub-step S302, based on the trigger data records, data analysis technology is adopted, using Python's Pandas library and Matplotlib library to analyze the performance of the trigger mechanism in differentiated scenarios. By calculating and visualizing the response time and accuracy, the performance bottlenecks of the trigger mechanism in specific scenarios are identified, such as long response time or insufficient accuracy. This allows an in-depth understanding of the limitations that the trigger mechanism may encounter in actual applications, and generates performance bottleneck analysis results.
[0092] S303: According to the performance bottleneck analysis results, the trigger sensitivity and response parameters of the fire extinguishing equipment trigger mechanism are adjusted, and the simulation test is re-performed to verify the performance improvement after the adjustment. The specific process of obtaining the trigger mechanism performance evaluation results is as follows;
[0093] In sub-step S303, based on the results of performance bottleneck analysis, performance adjustment technology is adopted, and MATLAB software and Simulink environment are used to accurately adjust the trigger sensitivity and response parameters of the automatic trigger mechanism of the fire extinguishing equipment. According to the specific situation of the performance bottleneck, the parameters are fine-tuned to improve the performance of the trigger mechanism. The simulation test is re-performed, and the effectiveness of the adjustment measures is verified by comparing the performance data before and after the adjustment to ensure that the trigger mechanism can maintain optimal performance in various environments, and the performance evaluation results of the trigger mechanism are obtained.
[0094] See also Figure 5 ,Based on the performance evaluation results of the trigger mechanism, the fire scenario generation logic is optimized, and the parameter settings are adjusted according to the performance feedback.,The specific steps of the performance optimization strategy are as follows:
[0095] S401: According to the trigger mechanism performance evaluation result, the environmental parameters that affect the trigger mechanism performance are identified, and the fire scenario is adjusted to generate a new test scenario. The specific process of obtaining the adjusted test scenario set is as follows;
[0096] In sub-step S401, based on the performance evaluation results of the trigger mechanism, the environmental parameter analysis method is adopted, and the response data is analyzed using a Python script to identify the key environmental parameters that affect the performance of the trigger mechanism, such as temperature, humidity, and type of combustibles. The fire scenario parameters are adjusted according to the analysis results, and a new test scenario is generated using Python's NumPy library to ensure that the test scenario covers all key environmental conditions that limit the performance of the trigger mechanism, and an adjusted test scenario set is generated.
[0097] S402: Based on the adjusted test scenario set, a simulation test is performed, trigger mechanism response data is collected, and response efficiency and accuracy improvement are analyzed to obtain a detailed performance data set. The specific process is as follows;
[0098] In sub-step S402, based on the adjusted test scenario set, simulation testing technology is adopted, and simulation testing is performed again using MATLAB software and Simulink environment. The automatic triggering mechanism model of the fire extinguishing equipment is run through the set environmental parameters, and a new round of triggering mechanism response data is collected. The built-in data analysis tools in MATLAB are used to analyze the improvement of response efficiency and accuracy, and the specific impact of adjusting environmental parameters on the performance of the triggering mechanism is carefully understood, and a detailed performance data set is generated.
[0099] S403: Based on the refined performance data set, parameter optimization is performed to adjust the sensitivity and response speed of the trigger mechanism of the fire extinguishing equipment, optimize the performance of the fire extinguishing equipment in various environments, and the specific process of obtaining the performance optimization strategy is as follows;
[0100] In sub-step S403, based on the refined performance data set, performance optimization techniques are adopted, and the parameters of the automatic triggering mechanism of the fire extinguishing equipment, such as trigger sensitivity and response speed, are adjusted using the MATLAB and Simulink environments. According to the analysis results in the refined performance data set, the parameters are precisely fine-tuned to ensure the optimal performance of the fire extinguishing equipment in various test scenarios. Through repeated simulation tests and parameter adjustment cycles, the performance of the fire extinguishing equipment in various environments is optimized, and a performance optimization strategy is obtained.
[0101] See also Figure 6 ,According to the performance optimization strategy, the Bayesian network model is adopted, the factors affecting the accuracy of the trigger mechanism are defined, the Bayesian inference is performed to update the network state, and the probability of trigger accuracy is calculated based on the data. The specific steps to obtain the Bayesian accuracy evaluation results are as follows:
[0102] S501: According to the performance optimization strategy, identify the key factors that affect the accuracy of the trigger mechanism, including temperature sensing accuracy and smoke recognition ability, sort out the factors as input nodes of the Bayesian network, and obtain the specific process of the factor definition list as follows;
[0103] In sub-step S501, based on the performance optimization strategy, the key factor analysis method is adopted, and Python scripts are used to analyze the factors that affect the accuracy of the trigger mechanism, such as temperature sensing accuracy and smoke recognition ability. Through data collation and expert consultation, the factors are determined as the input nodes of the Bayesian network to ensure that the factors cover the key influencing points of the trigger mechanism performance and generate a factor definition list.
[0104] S502: According to the factor definition list, a Bayesian network model is constructed, and an initial probability value is assigned to each factor node according to historical data and expert experience. The specific process of obtaining the basic Bayesian network is as follows;
[0105] In sub-step S502, based on the factor definition list, the Bayesian network construction technology is adopted, and Python's PyMC3 library is used to assign initial probability values to each factor node according to historical data and expert experience. In this way, the framework and node probability of the basic Bayesian network are established to ensure that the network model can reflect the actual performance of the automatic triggering mechanism of the fire extinguishing equipment and obtain the basic Bayesian network.
[0106] S503: Based on the basic Bayesian network, combined with the collected trigger mechanism operation data, the probability value in the Bayesian network is updated, and Bayesian inference is performed to optimize the network state, calculate the trigger accuracy probability, and obtain the specific process of the Bayesian accuracy evaluation result as follows;
[0107] In sub-step S503, based on the basic Bayesian network, the Bayesian inference optimization method is adopted, combined with the collected trigger mechanism operation data, and the PyMC3 library is used to perform Bayesian inference, update the probability values in the network, optimize the state of the Bayesian network, and more accurately calculate the accuracy probability of the trigger mechanism. This ensures that the evaluation results can accurately reflect the performance of the trigger mechanism under different conditions and obtain Bayesian accuracy evaluation results.
[0108] Bayesian inference, through the formula:
[0109]
[0110] Calculate the trigger accuracy probability and obtain the Bayesian accuracy evaluation result, where: Assume that the trigger mechanism is accurate. To trigger the mechanism to manipulate the data, is the environmental stability parameter, is the device response time parameter, Assumptions for environmental and equipment factors The weight coefficient of influence, Indicates that in a given operation data And environmental stability parameters and device response time parameters Under the condition of The probability of being true, For the assumption True and considering the environmental stability and device response time, the data is observed The probability of It means that under the conditions of considering environmental stability and device response time, assuming The probability of being true, is the unconditional data probability under given conditions of environmental stability and device response time.
[0111] The specific implementation process of the improved formula is as follows:
[0112] By analyzing historical data and Determination of correlation with trigger success rate The specific value of As well as environmental stability parameter E and device response time parameter , update the probability values in the Bayesian network, perform Bayesian inference, optimize the network status, calculate the accuracy probability of the trigger mechanism, and ensure that the evaluation results can accurately reflect the performance of the trigger mechanism under different conditions.
[0113] See also Figure 7 ,Based on the Bayesian accuracy evaluation results, a formal verification method is used to analyze the logical rules of the automatic trigger mechanism, perform a formal proof process, identify logical errors and design defects, and formulate correction measures. The specific steps of the logic verification and correction plan are as follows:
[0114] S601: Based on the Bayesian accuracy evaluation result, the logic rules of the automatic trigger mechanism are identified, including the trigger conditions and the execution sequence. The specific process of generating the logic rule set is as follows;
[0115] In sub-step S601, based on the Bayesian accuracy evaluation results, logical rule analysis technology is adopted, and Python scripts are used to analyze the accuracy data of the trigger mechanism, identify the core logical rules of the automatic trigger mechanism, including trigger conditions and execution sequences, and extract logical rules through programmatic methods to ensure that the rule set covers all key operations of the automatic trigger mechanism of the fire extinguishing equipment and generate logical rules.
[0116] S602: According to the logic rule set, apply the formal verification method, analyze the logic rules, perform the proof process, identify the logic errors and design defects, and record the problem points. The specific process of obtaining the logic error record is as follows;
[0117] In sub-step S602, based on the logic rule set, formal verification technology is adopted, using Model Checking tools and logic analysis software such as SPIN or NuSMV, to strictly analyze the logic rules, execute the proof process, systematically identify logic errors and design defects, record all problem points found, ensure the logical integrity and accuracy of the trigger mechanism, and obtain logic error records.
[0118] Formal verification method, according to the formula:
[0119]
[0120] Calculate the state transition and get the logical error record, where:
[0121] Represents the automatic trigger mechanism model, which is a mathematical or logical representation of the behavior, state transition, and event triggering mechanism of the automatic trigger mechanism being tested. A set of test scenario parameters that define specific environmental conditions or operating scenarios encountered by the automatic trigger mechanism, such as temperature changes, pressure conditions, or different states of the automatic trigger mechanism configuration. Represents a set of performance indicator parameters, including performance indicators that need to be verified on the automatic trigger mechanism model, such as response time, throughput or error rate, etc. For logical expression conversion functions, according to the test scenario and performance indicators Generate applicable logical expressions to convert specific test conditions and performance requirements into a logical form that model checking tools can understand and process. The function checks the automatic trigger mechanism model, which traverses all possible states of the automatic trigger mechanism model through an algorithm and checks whether a given logical property is true on all possible execution paths.
[0122] The specific implementation process of the improved formula is as follows:
[0123] By defining the automatic trigger mechanism model , describe in detail the behavior and state transitions of the automatic trigger mechanism model, and determine the test scenario parameter set according to specific test requirements , the parameters reflect the different conditions encountered when the automatic trigger mechanism is running, and define the performance indicator parameter set , clarify the performance criteria that the automatic trigger mechanism needs to meet, use the conversion function ,according to and Generate targeted logical expressions that specifically reflect the test scenario conditions and performance indicator requirements. Function, using and by The generated logical expressions are formally verified to systematically analyze whether the automatic triggering mechanism model satisfies the logical properties on all execution paths.
[0124] S603: Based on the logic error record, formulate matching correction measures, including modifying the logic expression and adding missing conditions, and obtain the specific process of logic verification and correction plan as follows;
[0125] In sub-step S603, based on the logic error records, a logic correction strategy is adopted, and specialized logic design software, such as MATLAB Stateflow or similar tools, is used to correct the identified logic errors, including modifying unreasonable logic expressions and adding missing conditions. Through this precise adjustment, it is ensured that the automatic triggering mechanism of the fire extinguishing equipment can be accurately and effectively executed in various situations, and a logic verification and correction plan is obtained.
[0126] See also Figure 8 , a trigger mechanism detection system for fire extinguishing equipment, the system includes:
[0127] The environmental analysis module collects temperature, humidity, and combustible type information based on real-world environmental scenarios and material data, and summarizes and processes the information to obtain an environmental characteristic data set;
[0128] The scenario simulation module dynamically constructs environmental scenarios representing various fire scenarios based on the environmental characteristic data set, optimizes the simulation effect by adjusting the scenario parameters, and obtains a set of simulated fire scenarios;
[0129] The trigger performance test module deploys the automatic trigger mechanism of the fire extinguishing equipment based on the simulated fire scene set, simulates the actual operating conditions, records the response data of the trigger mechanism, and obtains the trigger performance data;
[0130] The performance evaluation module analyzes the performance of the trigger mechanism based on the trigger performance data, evaluates the response time and accuracy, identifies performance bottlenecks, and generates performance evaluation results;
[0131] The parameter adjustment module optimizes the fire scenario generation based on the performance evaluation results, adjusts the trigger threshold, response speed and false trigger suppression measures of the fire extinguishing equipment trigger mechanism, and obtains the adjusted parameter settings;
[0132] The accuracy analysis module applies the Bayesian network model based on the adjusted parameter settings, defines the factors that affect the accuracy of the trigger mechanism, performs Bayesian inference to update the network state, calculates the probability of trigger accuracy, and obtains the Bayesian accuracy evaluation result;
[0133] The logic correction module is based on the Bayesian accuracy evaluation results and adopts formal verification technology to analyze the logic rules of the automatic trigger mechanism, execute the proof process, identify and record logical errors and design defects, formulate correction measures, and obtain a logic verification and correction plan.
[0134] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.
Claims
1. A method for detecting a trigger mechanism of a fire extinguishing device, characterized in that: The following steps are involved: According to the real environment scene and material data, the environment model is constructed, each node is used to represent the environment feature, the edge represents the interaction between the features, and the key environment features are identified by traversal to obtain the environment feature graph model; Based on the environmental characteristic graph model, dynamically generate environmental scenes representing various fire situations, adjust scene parameters, optimize simulation effects, and obtain a set of simulated fire scenes; According to the simulated fire scenario set, deploy the automatic trigger mechanism of the fire extinguishing equipment, simulate the conditions encountered in actual operation, and record the trigger mechanism response data to obtain the trigger mechanism performance evaluation result; Based on the performance evaluation results of the trigger mechanism, the fire scenario generation logic is optimized, and the parameter settings are adjusted according to the performance feedback to obtain the performance optimization strategy; According to the performance optimization strategy, a Bayesian network model is used to define factors that affect the accuracy of the trigger mechanism, perform Bayesian inference to update the network state, and calculate the probability of trigger accuracy based on the data to obtain a Bayesian accuracy evaluation result; Based on the Bayesian accuracy evaluation results, a formal verification method is used to analyze the logic rules of the automatic trigger mechanism, perform a formal proof process, identify logical errors and design defects, and formulate corrective measures to obtain a logic verification and correction plan; The environmental characteristic graph model includes characteristic nodes of temperature level, humidity range and combustible type; the simulated fire scenario set includes enclosed space fire scenario, open area fire scenario and electrical fire scenario; the trigger mechanism performance evaluation results include response speed, accuracy score and false triggering frequency; the performance optimization strategy includes trigger threshold adjustment measures, response speed improvement strategy and false triggering suppression measures; the Bayesian accuracy evaluation results include sensor responsiveness, external environmental impact information and equipment status reliability information; the logic verification and correction scheme includes rule conflict resolution strategy, performance optimization path and safety threshold setting.
2. The method for detecting the trigger mechanism of a fire extinguishing device according to claim 1, characterized in that: According to the real environment scene and material data, the environment model is constructed, each node is used to represent the environment feature, the edge represents the interaction between the features, and the key environment features are identified by traversal. The specific steps to obtain the environment feature graph model are as follows: According to the real environment scene and material data, collect temperature, humidity, and combustible type information, and summarize and organize the information to obtain the basic environmental characteristics data set; Based on the basic environmental characteristic data set, each characteristic is classified and encoded, including classifying temperature into three categories of low, medium and high, and classifying humidity into dry, normal and humid, to obtain a classified and encoded environmental characteristic data set; Based on the classified and coded environmental characteristic data set, the relationship between environmental characteristics, including the relationship between temperature and combustible type, is utilized to construct a connection relationship diagram between environmental characteristics, thereby obtaining an environmental characteristic diagram model.
3. The method for detecting the trigger mechanism of a fire extinguishing device according to claim 1, characterized in that: Based on the environmental feature graph model, environmental scenes representing various fire situations are dynamically generated, and scene parameters are adjusted to optimize the simulation effect. The specific steps for obtaining a simulated fire scene set are as follows: Based on the environmental characteristic graph model, environmental scenes representing various fire situations are dynamically generated, environmental parameter combinations under various fire scenes are formulated, and the combustible reaction rate under the wet scene is adjusted to obtain an environmental parameter combination data set; Based on the environmental parameter combination data set, simulate environmental changes under differentiated fire scenarios, and adjust temperature and humidity values to simulate the impact of fire sources to obtain a simulated environmental change data set; Based on the simulated environmental change data set, the parameters under the differentiated scenarios are adjusted, the temperature change rate is adjusted according to the fire spread speed, the differentiated fire scenarios are refined, and a simulated fire scenario set is obtained.
4. The method for detecting the trigger mechanism of a fire extinguishing device according to claim 1, characterized in that: According to the simulated fire scenario set, the automatic trigger mechanism of the fire extinguishing equipment is deployed to simulate the conditions encountered in actual operation, and the trigger mechanism response data is recorded to obtain the specific steps of the trigger mechanism performance evaluation result as follows: According to the simulated fire scenario, target environmental parameters are selected to deploy the automatic trigger mechanism of the fire extinguishing equipment, actual operation simulation is performed, and the trigger time and reaction sensitivity are recorded to obtain trigger data records; Based on the trigger data records, analyze the performance of the trigger mechanism in different scenarios, evaluate the response time and accuracy, identify performance bottlenecks, and obtain performance bottleneck analysis results; According to the performance bottleneck analysis results, the trigger sensitivity and response parameters of the fire extinguishing equipment trigger mechanism are adjusted, and the simulation test is re-performed to verify the performance improvement after the adjustment and obtain the trigger mechanism performance evaluation results.
5. The method for detecting the trigger mechanism of a fire extinguishing device according to claim 1, characterized in that: Based on the performance evaluation results of the trigger mechanism, the fire scenario generation logic is optimized, and the parameter settings are adjusted according to the performance feedback. The specific steps of obtaining the performance optimization strategy are as follows: According to the performance evaluation result of the trigger mechanism, the environmental parameters that affect the performance of the trigger mechanism are identified, and the fire scenario is adjusted to generate a new test scenario to obtain an adjusted test scenario set; Based on the adjusted test scenario set, perform simulation tests, collect trigger mechanism response data, analyze response efficiency and accuracy improvements, and obtain a refined performance data set; Based on the refined performance data set, parameter optimization is performed to adjust the sensitivity and response speed of the trigger mechanism of the fire extinguishing equipment, optimize the performance of the fire extinguishing equipment in various environments, and obtain a performance optimization strategy.
6. The method for detecting the trigger mechanism of a fire extinguishing device according to claim 1, characterized in that: According to the performance optimization strategy, the Bayesian network model is used to define the factors that affect the accuracy of the trigger mechanism, perform Bayesian inference to update the network state, and calculate the probability of trigger accuracy based on the data. The specific steps to obtain the Bayesian accuracy evaluation result are as follows: According to the performance optimization strategy, key factors affecting the accuracy of the trigger mechanism are identified, including temperature sensing accuracy and smoke recognition capability, and the factors are sorted as input nodes of the Bayesian network to obtain a factor definition list; According to the factor definition list, a Bayesian network model is constructed, and an initial probability value is assigned to each factor node according to historical data and expert experience to obtain a basic Bayesian network; According to the basic Bayesian network, combined with the collection of trigger mechanism operation data, the probability value in the Bayesian network is updated, and Bayesian inference is performed to optimize the network state, calculate the probability of trigger accuracy, and obtain the Bayesian accuracy evaluation result; The Bayesian inference is through the formula: ; Calculate the trigger accuracy probability and obtain the Bayesian accuracy evaluation result, where: Assume that the trigger mechanism is accurate. To trigger the mechanism to manipulate the data, is the environmental stability parameter, is the device response time parameter, Assumptions for environmental and equipment factors The weight coefficient of influence.
7. The method for detecting the trigger mechanism of a fire extinguishing device according to claim 1, characterized in that: Based on the Bayesian accuracy evaluation results, a formal verification method is used to analyze the logical rules of the automatic trigger mechanism, perform a formal proof process, identify logical errors and design defects, and formulate corrective measures. The specific steps of the logic verification and correction plan are as follows: Based on the Bayesian accuracy evaluation result, identifying the logic rules of the automatic triggering mechanism, including the triggering conditions and the execution sequence, and generating a logic rule set; According to the logic rule set, a formal verification method is applied to analyze the logic rules, perform a proof process, identify logic errors and design defects, and record the problem points to obtain a logic error record; The formal verification method is based on the formula: ; Calculate the state transition and get the logical error record, where: represents the automatic trigger mechanism model, is a set of test scene parameters. Represents a set of performance indicator parameters, is a logical expression conversion function, Model checking function for automatic triggering mechanism; Based on the logic error records, matching correction measures are formulated, including modifying the logic expression and adding missing conditions, to obtain a logic verification and correction plan.
8. A trigger mechanism detection system for fire extinguishing equipment, characterized in that: According to the method for detecting the trigger mechanism of a fire extinguishing device according to any one of claims 1 to 7, the system comprises: The environmental analysis module collects temperature, humidity, and combustible type information based on real-world environmental scenarios and material data, and summarizes and processes the information to obtain an environmental characteristic data set; The scene simulation module dynamically constructs environmental scenes representing various fire situations based on the environmental characteristic data set, optimizes the simulation effect by adjusting scene parameters, and obtains a simulated fire scene set; The trigger performance test module deploys the automatic trigger mechanism of the fire extinguishing equipment based on the simulated fire scene set, simulates the actual operating conditions, records the response data of the trigger mechanism, and obtains the trigger performance data; The performance evaluation module analyzes the performance of the trigger mechanism based on the trigger performance data, evaluates the response time and accuracy, identifies performance bottlenecks, and generates performance evaluation results; The parameter adjustment module optimizes the fire scenario generation based on the performance evaluation results, adjusts the trigger threshold, response speed and false trigger suppression measures of the fire extinguishing equipment trigger mechanism, and obtains the adjusted parameter settings; The accuracy analysis module applies the Bayesian network model based on the adjusted parameter settings, defines the factors that affect the accuracy of the trigger mechanism, performs Bayesian inference to update the network state, calculates the probability of trigger accuracy, and obtains the Bayesian accuracy evaluation result; Based on the Bayesian accuracy evaluation result, the logic correction module adopts a formal verification method to analyze the logic rules of the automatic triggering mechanism, execute a formal proof process, identify and record logic errors and design defects, formulate correction measures, and obtain a logic verification and correction plan.
Citation Information
Patent Citations
Intelligent fire-fighting system based on Internet of Things
CN111383410A
Intelligent truck fire monitoring system based on Bayesian network
CN112138320A
Digital fire safety assessment and visual operation and maintenance method
CN114257791A
Ocean platform water spray fire-fighting capability assessment method
CN116415827A
Intelligent hospital safety elimination linkage control method and system based on digital twinning
CN116449679A
