Detection method, system and device of gas alarm and gas alarm

Abstract

The invention relates to the technical field of fuel gas alarms, and discloses a fuel gas alarm detection method, system and device and a fuel gas alarm.The method comprises the steps that in a simulation environment, operation parameters of a fuel gas alarm are obtained, and the operation parameters comprise the temperature, the pressure and the fuel gas concentration; calculating according to the operating parameters to obtain a theoretical change value of the gas concentration; acquiring historical fault data, and performing fault feature extraction on the historical fault data to obtain a fault feature library; inputting the theoretical change value into a pre-trained machine learning evaluation model to obtain an evaluation value; when the evaluation value does not meet a preset qualified range, it is judged that an alarm fault exists, the evaluation value is compared with the fault feature library, and the fault position in the gas alarm is determined. According to the method, the problems of unreasonable evaluation and low detection accuracy caused by the fact that the operation environment is complex and the quality problem cannot be accurately detected only by using the simulation leakage test function are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of gas alarms, and in particular to a detection method, system, device and gas alarm for a gas alarm. Background Art

[0002] A gas alarm is a device designed specifically to monitor the leakage of flammable gases and is widely used in domestic and industrial environments. This device can effectively detect many types of flammable gases, such as natural gas, artificial gas, and liquefied petroleum gas. When these gases leak in the pipelines of gas cookers, boilers or other industrial equipment, the gas alarm will quickly sound an alarm, thereby reminding the staff on site to take necessary safety measures to prevent accidents such as fire or explosion caused by gas accumulation. Safety is one of the most important considerations in industrial and domestic environments. The existence of gas alarms greatly reduces the risk of property loss and casualties caused by gas leaks. Therefore, in order to ensure the normal operation and accuracy of gas alarms, regular inspection and maintenance are particularly important. This not only ensures that the equipment can detect potential gas leaks in time, but also prolongs its service life. Through regular inspections of gas alarms, any problems that may affect their performance can be discovered and repaired in time, ensuring that they can respond at critical moments.

[0003] In the prior art, the detection of gas alarms is generally done by professionals regularly checking the pipelines, detectors and horns of the gas alarms to ensure that they can work properly. For example, the simulated leak test function of the gas alarm can be turned on to observe whether it can work properly. In addition, professionals will also check the temperature and humidity of the equipment, and perform maintenance and repairs based on the above parameters to ensure the stability and reliability of the equipment.

[0004] In the current gas alarm detection method, due to the complexity of the actual operating environment, only using the simulated leakage test function cannot accurately detect its quality problems, and the evaluation is not reasonable, resulting in low detection accuracy. Summary of the invention

[0005] The present invention provides a gas alarm detection method, system, device and gas alarm to solve the problem that due to the complex operating environment, only the simulated leakage test function cannot accurately detect its quality problems, resulting in unreasonable evaluation and low detection accuracy.

[0006] In a first aspect, in order to solve the above technical problems, the present invention provides a method for detecting a gas alarm, comprising: In a simulated environment, obtaining operating parameters of the gas alarm, the operating parameters including temperature, pressure and gas concentration; Calculating according to the operating parameters to obtain a theoretical change value of the gas concentration; Acquire historical fault data, extract fault features from the historical fault data, and obtain a fault feature library; Inputting the theoretical change value into a pre-trained machine learning evaluation model to obtain an evaluation value; When the evaluation value does not meet the preset qualified range, it is determined that an alarm fault exists, and the evaluation value is compared with the fault feature library to determine the fault location in the gas alarm; wherein the fault feature library includes a mapping relationship between the evaluation value and the fault location.

[0007] In an optional implementation, obtaining the operating parameters of the gas alarm in a simulated environment includes: Set up a simulation environment; in the simulation environment, use the sensor module to collect the temperature, pressure and gas concentration of the gas alarm in the simulation environment.

[0008] In an optional implementation, the theoretical change value of the gas concentration is obtained by calculating according to the operating parameters, including: The theoretical change in gas concentration is calculated using the following formula: in, It is The theoretical change value of the gas concentration of the group, It is The standard value of the gas concentration is is the coefficient of gas concentration variation with temperature, is the current temperature, is the standard temperature, n satisfies 1≤n≤N, and N is the number of actual detection groups.

[0009] In an optional embodiment, the method further includes: Calculate the first Standard values ​​of group gas concentration: = k1 k2 ( k3 Tn) + e Among them, k1 is the concentration value change coefficient caused by the change of the corresponding temperature parameter, k2 is the concentration value change coefficient caused by the corresponding pressure change, and k3 is the coefficient corresponding to the change of the theoretical change value with the change of the temperature parameter. Tn is the difference between the actual temperature and the standard temperature in the nth detection, and e is the error parameter.

[0010] In an optional implementation, the training process of the machine learning evaluation model includes: An initial machine learning model is constructed based on the sample change value and the initial weight parameters, and the initial machine learning model is trained; when the training times of the initial machine learning model are greater than the preset training times or the loss function value of the initial machine learning model is less than the preset loss threshold, the training is determined to be completed, and a machine learning evaluation model is obtained.

[0011] In an optional embodiment, the method further includes: When the evaluation value meets the preset qualified range, the gas alarm is determined to be qualified.

[0012] In a second aspect, the present invention provides a gas alarm detection system, comprising: The sensor module is used to obtain the operating parameters of the gas alarm under a simulated environment, wherein the operating parameters include temperature, pressure and gas concentration; A data processing module, used to calculate according to the operating parameters to obtain a theoretical change value of the gas concentration; A data query module is used to obtain historical fault data, extract fault features from the historical fault data, and obtain a fault feature library; A data evaluation module, used for inputting the theoretical change value into a pre-trained machine learning evaluation model to obtain an evaluation value; A data comparison module is used to determine the presence of an alarm fault when the evaluation value does not meet a preset qualified range, compare the evaluation value with the fault feature library, and determine the fault location in the gas alarm; wherein the fault feature library includes a mapping relationship between the evaluation value and the fault location.

[0013] In a third aspect, the present invention further provides an electronic device comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements any one of the above-described gas alarm detection methods when executing the computer program.

[0014] In a fourth aspect, the present invention further provides a gas alarm, which is used to communicate with the detection system of the gas alarm described above, and the detection system of the gas alarm is used to determine the fault location in the gas alarm.

[0015] In a fifth aspect, the present invention also provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the gas alarm detection methods described above.

[0016] Compared with the prior art, the present invention has the following beneficial effects: The present invention discloses a method for detecting a gas alarm. Under simulated conditions, the operating parameters of the gas alarm are obtained, and the gas alarm is evaluated by combining a formula and a machine learning model to perform data processing. Under simulated conditions, data is collected in real time to accurately evaluate the quality of the gas alarm. Different parameters are set for the simulated environment, and the operating quality of the gas alarm is evaluated by combining multiple sets of data. The gas alarm is tested multiple times, different operating parameters are set, and a data model is established by combining formulas and parameter values. According to the model data and formula, the evaluation value is accurately obtained, and a fault feature library can be constructed for the evaluation value. According to the fault feature library, the fault position of the gas alarm is accurately detected. Compared with the existing detection method, it is necessary for professionals to regularly check the pipeline, the detector and the horn of the gas alarm, check the temperature and humidity of the equipment, and perform maintenance and repair according to the above parameters to ensure the stability and reliability of the equipment. The present invention constructs a simulation environment in which the detection environment is controllable and close to the actual environment, constructs multiple groups of different simulation environments, collects data, and combines machine learning models to establish a data model and a fault feature library to evaluate the gas alarm, thereby realizing the intelligentization and precision of the quality evaluation of the gas alarm. Therefore, the present invention can solve the problem that the operating environment is complex and only the simulated leakage test function cannot accurately detect its quality problems, resulting in unreasonable evaluation and low detection accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a flow chart of a detection method of a gas alarm provided by a first embodiment of the present invention; Figure 2 It is a schematic diagram of the system structure for collecting the operating parameters of the gas alarm provided by the present invention; Figure 3 It is a schematic structural diagram of an embodiment of a detection system for a gas alarm provided by the present invention; Figure 4 It is a structural schematic diagram of an embodiment of a sensor module of a detection system of a gas alarm provided by the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] A gas alarm is a device designed specifically to monitor the leakage of flammable gases and is widely used in domestic and industrial environments. This device can effectively detect many types of flammable gases, such as natural gas, artificial gas, and liquefied petroleum gas. When these gases leak in the pipelines of gas cookers, boilers or other industrial equipment, the gas alarm will quickly sound an alarm, thereby reminding the staff on site to take necessary safety measures to prevent accidents such as fire or explosion caused by gas accumulation. Safety is one of the most important considerations in industrial and domestic environments. The existence of gas alarms greatly reduces the risk of property loss and casualties caused by gas leaks. Therefore, in order to ensure the normal operation and accuracy of gas alarms, regular inspection and maintenance are particularly important. This not only ensures that the equipment can detect potential gas leaks in time, but also prolongs its service life. Through regular inspections of gas alarms, any problems that may affect their performance can be discovered and repaired in time, ensuring that they can respond at critical moments.

[0020] In the prior art, the detection of gas alarms is generally done by professionals regularly checking pipelines, gas alarm detectors and speakers to ensure that they can work properly. For example, the simulated leak test function of the gas alarm can be turned on to observe whether it can work properly. In addition, professionals will also check the temperature and humidity of the equipment, and perform maintenance and inspections based on the above parameters to ensure the stability and reliability of the equipment. In the current gas alarm detection method, due to the complexity of the actual operating environment, only using the simulated leak test function cannot accurately detect its quality problems, and the evaluation is not reasonable, resulting in low detection accuracy.

[0021] To solve the above problems, refer to Figure 1 The first embodiment of the present invention provides a method for detecting a gas alarm, comprising the following steps: S1, obtaining operating parameters of the gas alarm in a simulated environment, wherein the operating parameters include temperature, pressure and gas concentration; S2, calculating according to the operating parameters to obtain a theoretical change value of the gas concentration; S3, acquiring historical fault data, extracting fault features from the historical fault data, and obtaining a fault feature library; S4, inputting the theoretical change value into the pre-trained machine learning evaluation model to obtain an evaluation value S5, when the evaluation value does not meet the preset qualified range, it is determined that an alarm fault exists, and the evaluation value is compared with the fault feature library to determine the fault location in the gas alarm; wherein the fault feature library includes a mapping relationship between the evaluation value and the fault location.

[0022] Compared with the existing detection methods, professionals are required to regularly check the pipelines, detectors and speakers of the gas alarm, check the temperature and humidity of the equipment, and perform maintenance and inspections based on the above parameters to ensure the stability and reliability of the equipment. The present invention constructs a simulation environment in which the detection environment is controllable and close to the actual environment, constructs multiple groups of different simulation environments, collects data, combines machine learning models, establishes data models and fault feature libraries, and evaluates the gas alarm to achieve intelligent and precise quality evaluation of the gas alarm. Therefore, the present invention can solve the problem that the operating environment is complex and the quality problem cannot be accurately detected by only using the simulated leak test function, resulting in unreasonable evaluation and low detection accuracy.

[0023] In step S1, operating parameters of the gas alarm are obtained in a simulated environment.

[0024] In one implementation, obtaining the operating parameters of the gas alarm in a simulated environment includes: Set up the simulation environment; In the simulated environment, the sensor module is used to collect the temperature, pressure and gas concentration of the gas alarm in the simulated environment.

[0025] The settings of the simulation environment include: the temperature range of the simulation environment is between 15°C and 25°C, the pressure requirement of the simulation environment is standard atmospheric pressure ±20kPa, and the gas concentration is set to 1%×Nm3, where N is a natural number. The above-mentioned simulated environmental parameters are used to simulate the use environment of the gas alarm. After the simulated environment is set up, the sensor module is used to collect the operating parameters of the gas alarm in the simulated environment, and finally a set of operating parameters of the gas alarm is obtained, wherein the operating parameters include temperature, pressure and gas concentration; in the simulated environment, the temperature parameters of the simulated environment are detected by the temperature sensing module, and the temperature changes of the current simulated environment are monitored in real time to ensure that the detected temperature is stable within the set range, wherein the set range is between -10°C and 40°C; the pressure parameters of the simulated environment are determined by the pressure sensing module, and the pressure changes of the simulated environment are measured to ensure that the detected pressure meets the expected standard, wherein the expected standard is in the range of 0.5kPa to 3kPa under standard atmospheric pressure; the gas concentration parameters of the simulated environment are measured by the gas concentration sensing module, and the changes in the gas concentration level of the gas alarm are detected, and the detection capability and reaction speed of the gas alarm under different concentration conditions are measured by the changes in the gas concentration level.

[0026] By setting up a simulated environment, all tests are conducted under the same conditions, eliminating the interference of external variables. This standardized test can ensure the comparability of test results, so that data from different groups can be effectively compared and analyzed. Setting parameters such as temperature, pressure and gas concentration in a simulated environment can effectively reproduce the working conditions of the gas alarm in actual use. The simulated environment setting close to the real environment can effectively obtain more accurate and reliable test results, discover potential problems and make targeted adjustments.

[0027] In step S2, calculation is performed according to the operating parameters to obtain a theoretical change value of the gas concentration.

[0028] In one implementation, the operating parameters are calculated to obtain a theoretical change value of the gas concentration. The theoretical change value of the gas concentration can be calculated by the following formula: in, It is The theoretical change value of the gas concentration of the group, It is The standard value of the gas concentration is is the coefficient of gas concentration variation with temperature, is the current ambient temperature, is the standard ambient temperature, which is usually 20°C, n satisfies 1≤n≤N, and N is the number of actual detection groups.

[0029] It should be noted that for The calculation of the standard value of the gas concentration can be calculated by the following formula: = k1 k2 ( k3 Tn) + e Among them, k1 is the concentration value change coefficient caused by the change of the corresponding temperature parameter, k2 is the concentration value change coefficient caused by the corresponding pressure change, and k3 is the coefficient corresponding to the change of the theoretical change value with the change of the temperature parameter. Tn is the difference between the actual temperature and the standard temperature in the nth detection, e is the error parameter, and e satisfies -0.01≤e≤0.01.

[0030] The formula in step S2 sets a simulated environment close to the actual environment according to the simulated environment parameters. For each actual detection, the detected value of the gas concentration is the gas pressure value recorded in the nth detection. According to the formula, the theoretical change value is obtained. , combined with the formula, the actual gas alarm at the time of the nth detection is obtained, and the detection value of the gas concentration in the actual gas alarm is deduced.

[0031] The theoretical change value calculated by the formula in step S2, in actual application, the change of gas concentration is affected by many factors, including temperature and pressure. By calculating the theoretical change value, the change of the gas alarm under different environmental conditions can be more accurately evaluated. This precise measurement enables the gas alarm to adjust its reaction threshold in time according to the temperature and pressure changes of the simulated environment, predict the risks that may exist under specific conditions in advance, and ensure that the gas alarm sounds an alarm before the gas concentration reaches a dangerous level, wherein the specific conditions are the simulated environment that is infinitely close to the actual environment under the multiple sets of different operating parameters set in step S1.

[0032] Among them, the theoretical change value refers to the change in gas concentration relative to its standard value under specific simulated environmental conditions. By calculating the theoretical change value, the performance of the equipment can be evaluated and whether it is in normal working condition. The theoretical change value is used to monitor and adjust the reaction threshold of the gas alarm. The standard value of gas concentration is a reference value set under ideal environmental conditions for comparison with the actual detection value. The temperature change coefficient k1 represents the degree of influence of temperature change on gas concentration. It can quantify the impact of temperature rise or fall on gas concentration, so that the concentration change under various temperature conditions can be more accurately simulated during the calculation process. The pressure change coefficient k2 represents the magnitude of the influence of pressure change on gas concentration. Different pressure conditions will have a direct impact on the density and therefore the concentration of the gas. The pressure change coefficient k2 can help adjust the standard value under different pressure environments. The coefficient k3 of the theoretical change value with temperature is used to describe how the theoretical change value changes with temperature changes. It acts as a regulator in the model to ensure that the prediction of gas concentration can be appropriately adjusted when the temperature changes. Tn is the difference between the actual ambient temperature (Tn) and the standard ambient temperature (usually 20°C) in the nth detection, which can directly affect the calculation of the standard value of the gas concentration. By comparing the actual environment with the standard environment, we can better understand how environmental factors affect the gas concentration. The error parameter e is a small constant used to correct the concentration fluctuation caused by inaccurate equipment measurement or external interference. It allows small changes between -0.01 and 0.01, which can improve the reliability of the standard value and ensure that the calculation result is closer to the actual situation.

[0033] In step S3, historical fault data is acquired, and fault features are extracted from the historical fault data to obtain a fault feature library.

[0034] In one implementation, historical fault data is obtained by repeatedly testing different types of gas alarms under a variety of different simulated environmental parameters. Each gas alarm may exhibit different failure modes under different simulated environments, where the failure mode is the specific way in which the gas alarm exhibits abnormal behavior or performance degradation under a specific simulated environment or operating state. It describes the working condition of the equipment when the fault occurs, which may include: the gas alarm fails to sound an alarm; the gas alarm mistakenly sounds an alarm when there is no gas leak; the gas alarm fails to sound an alarm in time after the gas concentration reaches a dangerous level; the gas alarm remains in an alarm state even after returning to a safe state. Through multiple tests in a specific simulation environment, a large amount of historical fault data is obtained. These historical fault data cover the frequency, occurrence conditions and influencing factors of various faults, providing important information for in-depth understanding of the working performance of the gas alarm. The fault frequency is the number of times a specific type of fault occurs within a certain period of time or number of tests, usually expressed as the proportion of faults per thousand or ten thousand tests. By analyzing the fault frequency with historical data, potential problems can be accurately identified, and fault warning and maintenance plans can be formulated to help judge the reliability and stability of the gas alarm. The lower the fault frequency, the better the equipment performance. The occurrence conditions are the environmental conditions and operating conditions when a specific fault occurs, including various parameters such as temperature, humidity, pressure, power supply fluctuations, and gas concentration. Different working environments (such as high temperature, high humidity, low temperature, etc.), the working mode of the gas alarm (normal operation, standby, alarm, etc.), and whether it has been regularly maintained and calibrated may affect the performance of the gas alarm. Influencing factors refer to various external and internal conditions that may affect the performance of gas alarms. These influencing factors include not only the above-mentioned occurrence conditions, but also many other variables, including internal factors: the quality, aging and contamination of the sensor will have a direct impact on its detection performance, and power instability, power failure or voltage fluctuations may cause the alarm to not work properly. And external factors: if the alarm is installed in an improper position, such as too far away from the leak source, it may cause detection delays or missed reports, and electromagnetic interference from surrounding equipment, airflow changes, etc. may affect the normal detection function of the sensor.

[0035] Through the systematic arrangement and analysis of these historical fault data, combined with the structural characteristics of the gas alarm, the parameters of each model and the environmental characteristics of the gas alarm, a detailed fault feature library is created. The fault feature library is a systematic information collection that brings together various possible fault features, including the type of fault, related environmental conditions, and the structure and parameter characteristics of the gas alarm. By integrating this information together, it is possible to quickly refer to these known fault features, determine the fault features and fault location of the current gas alarm, and improve the efficiency of troubleshooting and problem solving. For the acquired characteristic fault library, in the actual application process, the fault characteristic library is a dynamic database that needs to be continuously updated, maintained and optimized. The fault characteristic library will be continuously updated and deleted, and the existing data will be reviewed regularly. In this process, old data that is no longer applicable, outdated fault characteristics or duplicate records will be cleaned up and deleted to keep the fault characteristic library tidy, ensuring that the information in the characteristic library is reliable and of practical value, so that the fault characteristic library can be adjusted and updated according to the changes in the fault characteristics of different gas alarms and the changes in the on-site use conditions. Specifically, when new test results or fault cases are recorded, the related data will be promptly included in the fault characteristic library, and a fault characteristic library that adapts to the new gas alarm will be constructed in real time. The real-time update mechanism can ensure that the fault characteristic library always reflects the latest fault characteristics and fault locations, and improve the monitoring capabilities and response speed of the gas alarm performance.

[0036] In step S4, the theoretical change value is input into a pre-trained machine learning evaluation model to obtain an evaluation value.

[0037] In the specific implementation, the machine learning evaluation model is trained in the following way: constructing an initial machine learning model based on the sample change value and the initial weight parameter, and training the initial machine learning model; when the number of training times of the initial machine learning model is greater than the preset number of training times or the loss function value of the initial machine learning model is less than the preset loss threshold, the training is determined to be completed, and the machine learning evaluation model is obtained. Among them, the sample change value is the change amount of a specific parameter over a period of time. It comes from data collection of real-time monitoring equipment. The sensor data obtained using these devices can constitute a rich data set, which is used to train the initial machine learning model so that it can learn how to make effective predictions under different input conditions.

[0038] In the specific implementation process, the initial weight parameters will be selected based on historical data to ensure that the initial machine learning model can cover the potential range of changes, build a preliminary machine learning model, input a large amount of data input and model adjustment, use a series of training samples to continuously adjust the parameters of the model, and continuously iterate and optimize the initial machine learning model, so that the prediction error can be reduced and the accuracy of the model can be improved. The initial machine learning model is continuously verified and optimized according to the set standards. These standards include the value of the loss function and the number of training times of the initial machine learning model. When the loss function value of the initial machine learning model does not reach the preset threshold, or the number of training times does not reach the preset upper limit, the training process will continue. On the contrary, if any condition is met, it can be considered that the training of the initial machine learning model has been completed, and finally a machine learning evaluation model is obtained. Among them, the potential range of changes is the interval between the minimum and maximum values ​​of the parameters (such as temperature, pressure, concentration, etc.) that may appear under certain time, environment or operating conditions. When collecting samples, it is necessary to ensure that as many ranges of changes as possible are covered in order to obtain a comprehensive data set. At the same time, preprocessing the collected data to remove noise and outliers can help better determine the potential range of changes. When building a machine learning model, you can choose appropriate features based on the potential range of variation. If a parameter has a large range of variation, it indicates that it may be an important feature and should be retained in the model.

[0039] In this embodiment, by setting different operating parameters for the simulation environment, the model can better adapt to actual application needs. The parameters in step S1 are combined, the formula in step S2 is used, and the trained machine learning evaluation model is used to detect the data to finally obtain the corresponding evaluation value.

[0040] Specifically, it is necessary to adjust several key parameters to ensure that various situations that may be encountered in real life can be covered. First, for the adjustment of temperature parameters, the range of temperature parameters is increased and set between -10°C and 40°C to ensure that the temperature changes that may exist under different environmental conditions, the machine learning evaluation model can provide stable evaluation results when facing various temperature fluctuations. For the adjustment of pressure parameters, the pressure parameters are increased and the pressure parameter change range is set between 0.5kPa and 3kPa, so that a variety of possible pressure changes can be covered, and the reliability and applicability of the machine learning evaluation model can be enhanced. Change the gas concentration parameter: In step S1, the gas concentration parameter is increased so that the concentration range of the gas concentration parameter is set between 1% and 10%, so that under the simulation of different concentrations, combined with the fault characteristics of the gas alarm, the machine learning evaluation model can analyze the environmental data in real time and evaluate the sensitivity and accuracy under various concentration conditions.

[0041] Through the comprehensive implementation of the above steps, a comprehensive dynamic evaluation mechanism can be gradually formed. Specifically, the machine learning model can continuously adjust its own evaluation criteria according to the real-time collected data to form an adaptive monitoring mechanism. When the environmental conditions change, the machine learning evaluation model can quickly evaluate and update the alarm parameters to adapt to the new state and achieve more intelligent monitoring and control. Establish a good data collection and feedback mechanism to ensure the lasting effectiveness of the machine learning evaluation model. In practical applications, data under different conditions will be recorded and stored, including but not limited to multiple parameters such as temperature, pressure and gas concentration. These parameters will become an important reference for further optimization of the machine learning evaluation model. This mechanism not only ensures that the machine learning model can adapt to the current data and conditions, but also has the ability to respond quickly to potential changes in the future. The core of this method is to improve the generalization ability of the machine learning evaluation model through systematic training and parameter adjustment, so that the machine learning evaluation model can play a greater role in practical applications.

[0042] In step S5, when the evaluation value does not meet the preset qualified range, it is determined that an alarm fault exists, and the evaluation value is compared with the fault feature library to determine the fault location in the gas alarm; wherein the fault feature library includes a mapping relationship between the evaluation value and the fault location.

[0043] In this embodiment, according to the evaluation value obtained in step S4, it is judged whether the quality of the gas alarm is qualified. If the evaluation value Z satisfies 1≤|Z|≤1.5, the quality of the gas alarm is judged to be qualified. Otherwise, the judgment result is that there is an alarm function failure, and the relevant fault characteristics are obtained according to the evaluation value. In the actual detection process, the evaluation results generated by the machine learning evaluation model will be evaluated in detail according to the measurement of the gas alarm. By matching these evaluation results with the fault feature library, the specific fault location of the alarm function failure of the gas alarm can be accurately determined, so that the efficiency of fault detection can be improved and the accuracy of judgment can be enhanced. Further explanation, in the entire detection process, the evaluation value is first formed by collecting and analyzing a variety of operating parameters. These parameters may include information such as ambient temperature, gas concentration, and the working state of the sensor. In step S4, through the comprehensive analysis of these parameters, an evaluation value Z is finally calculated. If this evaluation value falls within the predetermined qualified range, that is, 1≤|Z|≤1.5, it can be confirmed that the device is working normally and there is no fault. When the evaluation value in step S4 is out of range, more in-depth troubleshooting is required. The corresponding fault characteristics are obtained from the evaluation value obtained for the gas alarm of the type corresponding to the operating parameters collected in step S1 in the fault feature library. Based on the actual detection of the gas alarm, the evaluation results generated by the machine learning evaluation model are evaluated, matched with the fault feature library, and the location of the alarm function failure of the gas alarm is accurately determined.

[0044] Among them, each record in the fault feature library clearly identifies the mapping relationship between a specific evaluation value and a fault mode, providing a basis for subsequent fault detection and quickly locating and identifying the specific area where the equipment has problems. The mapping relationship usually exists in the fault feature library in the form of a key-value pair. The evaluation value calculated by analyzing and calculating the various operating parameters of the gas alarm is mapped one by one to the fault type or fault location associated with the specific evaluation value in the fault feature library. At the same time, the different operating parameters used in the evaluation process, such as ambient temperature, gas concentration, etc., correspond to different parameter types, so that the evaluation value is matched with a specific type of equipment. The mapping relationship will be continuously updated with the fault feature library. By continuously collecting new evaluation values ​​and fault data, the mapping relationship will be optimized to make the mapping relationship more accurate and better serve future fault detection work.

[0045] In order to facilitate the understanding of the present invention, some preferred embodiments of the present invention are further described below.

[0046] The following describes the working process of the present invention using a common scenario as an example. Figure 2 , which is Figure 1 Schematic diagram of the working scenario of the method.

[0047] In order to effectively evaluate the operating performance of the gas alarm, the gas alarm needs to be placed in a controllable simulation environment, which should have the following conditions: Temperature adjustment: Use a temperature sensor to ensure that the indoor temperature is adjustable, for example, set it to 25°C. Pressure adjustment: Use a pressure sensor to simulate normal air pressure conditions, usually 1 atm. Gas concentration adjustment: The gas concentration sensor is set to 500 ppm to simulate the gas concentration under normal working conditions, so as to better monitor and record the operating parameters of the gas alarm and simulate the normal state that may occur in daily life. At the same time, the temperature sensor, pressure sensor and gas concentration sensor are used for real-time monitoring and these parameters are continuously adjusted. In the simulation environment, the data is continuously collected and recorded by real-time monitoring of parameters such as temperature, pressure and gas concentration. These data are used to help understand the performance of the equipment under standard operating conditions, and also provide a baseline for subsequent fault analysis to observe the performance of the gas alarm under different conditions. According to the collected operating parameters, the theoretical change value of the gas concentration is calculated using the preset formula. Consult the past data records and extract the historical fault data in recent years. These data cover the evaluation values ​​under various fault conditions; the environmental conditions and time when the fault occurs; the corresponding fault mode and maintenance history. Establish a fault feature library, which contains the mapping relationship between different evaluation values ​​and fault locations. Each record in the fault feature library clearly identifies the mapping relationship between a specific evaluation value and a fault mode, thereby providing a basis for subsequent fault detection. The calculated theoretical change value is input into the trained machine learning evaluation model, and the machine learning evaluation model outputs an evaluation value, such as 0.5. Check whether the evaluation value 0.5 output by the machine learning evaluation model is within the preset qualified range. According to the defined qualified range of 1≤|Z|≤1.5, for the output evaluation value 0.5, it is found that the evaluation value does not meet this condition. Next, since the evaluation value 0.5 does not meet the qualified standard, this evaluation value is compared with the fault feature library, and the fault mode corresponding to 0.5 is found from the feature library. It is found that the evaluation value corresponds to a specific fault mode, thereby confirming the fault location and obtaining a maintenance plan. After the maintenance is completed, the performance data of the new sensor is recorded and compared with the previous fault records. By analyzing this data, potential trends or abnormalities can be identified to help better predict faults in the future. To prevent similar failures from happening in the future, a regular maintenance and inspection plan can be developed, including regular calibration of sensors, inspection of power modules, and updating of software systems, which will help improve the overall reliability and safety of the equipment.

[0048] In summary, the present invention discloses a method for detecting a gas alarm. Under simulated conditions, the operating parameters of the gas alarm are obtained, and the gas alarm is evaluated by combining formulas and machine learning models for data processing. Under simulated conditions, data is collected in real time to accurately evaluate the quality of the gas alarm. Different parameters are set for the simulated environment, and the operating quality of the gas alarm is evaluated by combining multiple sets of data. The gas alarm is tested multiple times, different operating parameters are set, and a data model is established by combining formulas and parameter values. According to the model data and formula, the evaluation value is accurately obtained, and a fault feature library can be constructed for the evaluation value. According to the fault feature library, the fault position of the gas alarm is accurately detected. Compared with the existing detection method, it is necessary for professionals to regularly check the pipeline, the detector and the horn of the gas alarm, check the temperature and humidity of the equipment, and perform maintenance and repair according to the above parameters to ensure the stability and reliability of the equipment. The present invention constructs a simulation environment in which the detection environment is controllable and close to the actual environment, constructs multiple groups of different simulation environments, collects data, and combines machine learning models to establish data models and fault feature libraries to evaluate the gas alarm, thereby realizing the intelligentization and precision of the quality evaluation of the gas alarm. Therefore, the present invention can solve the problem that the operating environment is complex and only the simulated leakage test function cannot accurately detect its quality problems, resulting in unreasonable evaluation and low detection accuracy.

[0049] Reference Figure 3 The second embodiment of the present invention provides a gas alarm detection system, comprising: The sensor module is used to obtain the operating parameters of the gas alarm under a simulated environment, wherein the operating parameters include temperature, pressure and gas concentration; A data processing module, used to calculate according to the operating parameters to obtain a theoretical change value of the gas concentration; A data query module is used to obtain historical fault data, extract fault features from the historical fault data, and obtain a fault feature library; A data evaluation module, used for inputting the theoretical change value into a pre-trained machine learning evaluation model to obtain an evaluation value; A data comparison module is used to determine the presence of an alarm fault when the evaluation value does not meet a preset qualified range, compare the evaluation value with the fault feature library, and determine the fault location in the gas alarm; wherein the fault feature library includes a mapping relationship between the evaluation value and the fault location.

[0050] Reference Figure 4 The embodiment of the present invention provides a sensor module of a detection system of a gas alarm, comprising: A temperature sensor unit, used to detect the simulated ambient temperature information; A pressure sensor unit, used to detect pressure information of a simulated environment; Gas concentration sensor unit, used to detect the gas concentration information of the simulated environment It should be noted that a gas alarm detection system provided in an embodiment of the present invention is used to execute all process steps of a gas alarm detection method in the above embodiment, and the working principles and beneficial effects of the two correspond one to one, so they will not be repeated here.

[0051] An embodiment of the present invention further provides a gas alarm, which is used to communicate with the detection system of the gas alarm described above, and the detection system of the gas alarm is used to determine the fault location in the gas alarm.

[0052] The embodiment of the present invention further provides an electronic device. The electronic device includes: a processor, a memory, and a computer program stored in the memory and executable on the processor, such as a machine learning model program. When the processor executes the computer program, the steps in the above-mentioned gas alarm detection method embodiments are implemented, such as Figure 1 Alternatively, when the processor executes the computer program, the functions of each module / unit in the above-mentioned device embodiments are realized, such as the sensor module.

[0053] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program in the electronic device.

[0054] The electronic device may be a computing device such as a desktop computer, a notebook, a PDA, and a smart tablet. The electronic device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the above components are merely examples of electronic devices and do not constitute a limitation on the electronic device. The electronic device may include more or fewer components than the above components, or a combination of certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.

[0055] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the electronic device, and uses various interfaces and lines to connect various parts of the entire electronic device.

[0056] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the electronic device by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0057] Wherein, if the module / unit integrated in the electronic device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0058] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0059] The specific embodiments described above further illustrate the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for detecting a gas alarm, It is characterized in that Executed by a computer, including: In a simulated environment, obtaining operating parameters of the gas alarm, the operating parameters including temperature, pressure and gas concentration; Calculating according to the operating parameters to obtain a theoretical change value of the gas concentration; Acquire historical fault data, extract fault features from the historical fault data, and obtain a fault feature library; Inputting the theoretical change value into a pre-trained machine learning evaluation model to obtain an evaluation value; When the evaluation value does not meet the preset qualified range, it is determined that an alarm fault exists, and the evaluation value is compared with the fault feature library to determine the fault location in the gas alarm; wherein the fault feature library includes a mapping relationship between the evaluation value and the fault location.

2. The method for detecting a gas alarm according to claim 1, It is characterized in that The step of obtaining the operating parameters of the gas alarm in a simulated environment includes: Set up the simulation environment; In the simulated environment, the sensor module is used to collect the temperature, pressure and gas concentration of the gas alarm in the simulated environment.

3. The method for detecting a gas alarm according to claim 1, It is characterized in that The theoretical change value of the gas concentration is obtained by calculating according to the operating parameters, including: The theoretical change in gas concentration is calculated using the following formula: in, It is The theoretical change value of the gas concentration of the group, It is The standard value of the gas concentration is is the coefficient of gas concentration variation with temperature, is the current temperature, is the standard temperature, n satisfies 1≤n≤N, and N is the number of actual detection groups.

4. The method for detecting a gas alarm according to claim 3, It is characterized in that The method further comprises: Calculate the first Standard values ​​of group gas concentration: = k1 k2 ( k3 Tn) + e Among them, k1 is the concentration value change coefficient caused by the change of the corresponding temperature parameter, k2 is the concentration value change coefficient caused by the corresponding pressure change, and k3 is the coefficient corresponding to the change of the theoretical change value with the change of the temperature parameter. Tn is the difference between the actual temperature and the standard temperature in the nth detection, and e is the error parameter.

5. The method for detecting a gas alarm according to claim 1, It is characterized in that The training process of the machine learning evaluation model includes: Building an initial machine learning model based on the sample change value and the initial weight parameter, and training the initial machine learning model; When the training times of the initial machine learning model are greater than the preset training times or the loss function value of the initial machine learning model is less than the preset loss threshold, the training is determined to be completed and a machine learning evaluation model is obtained.

6. The method for detecting a gas alarm according to claim 1, It is characterized in that The method further comprises: When the evaluation value meets the preset qualified range, the gas alarm is determined to be qualified.

7. A gas alarm detection system, It is characterized in that include: The sensor module is used to obtain the operating parameters of the gas alarm under a simulated environment, wherein the operating parameters include temperature, pressure and gas concentration; A data processing module, used to calculate according to the operating parameters to obtain a theoretical change value of the gas concentration; A data query module is used to obtain historical fault data, extract fault features from the historical fault data, and obtain a fault feature library; A data evaluation module, used for inputting the theoretical change value into a pre-trained machine learning evaluation model to obtain an evaluation value; A data comparison module is used to determine the presence of an alarm fault when the evaluation value does not meet a preset qualified range, compare the evaluation value with the fault feature library, and determine the fault location in the gas alarm; wherein the fault feature library includes a mapping relationship between the evaluation value and the fault location.

8. An electronic device, It is characterized in that The method comprises a processor, a memory and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the gas alarm detection method as claimed in any one of claims 1 to 6 when executing the computer program.

9. A gas alarm, It is characterized in that The gas alarm is used to communicate with the detection system of the gas alarm as claimed in claim 8, and the detection system of the gas alarm is used to determine the fault location in the gas alarm.

10. A computer-readable storage medium, It is characterized in that The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the gas alarm detection method according to any one of claims 1 to 6.

Images