Abnormity diagnosis and reliability evaluation method and system for combustible gas monitoring equipment

Abstract

The invention relates to the technical field of urban gas safety monitoring, in particular to a combustible gas monitoring equipment abnormity diagnosis and reliability evaluation method and system. The combustible gas monitoring equipment abnormity diagnosis method comprises the following steps: firstly, based on a working principle of combustible gas monitoring equipment, constructing an abnormity type of the equipment; constructing an equipment exception identification model corresponding to each exception type; then, labels of the equipment on all the exception types are judged through an equipment exception recognition model; when the labels of all the abnormal types are normal, judging that the equipment is normal; on the contrary, if the label of any abnormal type is abnormal, judging that the equipment is abnormal, and marking the abnormal type. According to the combustible gas monitoring equipment abnormity diagnosis method, the operation state of the combustible gas monitoring equipment is researched, a comprehensive equipment abnormity identification model is established, the operation state of the equipment is judged by collecting the operation parameters and the monitoring data of the combustible gas monitoring equipment and inputting the collected data into the data set training model, and the equipment abnormity diagnosis accuracy is improved. And automatic diagnosis of the operation state of the combustible gas monitoring equipment can be rapidly carried out.

Description

Technical Field

[0001] The present invention relates to the technical field of urban gas safety monitoring, and in particular to a method and system for abnormal diagnosis and reliability assessment of combustible gas monitoring equipment. Background Art

[0002] In recent years, with the continuous development of urbanization, city gas has been widely used in urban life. At the same time, the challenges brought by gas safety cannot be ignored. Using combustible gas monitoring equipment to perceive the combustible gas concentration in real time to evaluate the safe operation of the city gas pipeline network has become a new monitoring method. However, due to the harsh service conditions of the monitoring equipment, various equipment abnormalities such as communication anomalies, sensor anomalies, pump speed anomalies, and voltage anomalies are prone to occur during operation, affecting the integrity of urban gas safety monitoring. How to quickly detect whether the equipment is abnormal has become an important issue facing the field of urban gas safety monitoring. At the same time, various types of combustible gas monitoring equipment on the market are of varying quality. Choosing a reliable monitoring equipment is critical for real-time perception of the safe operation of the city. Therefore, it is necessary to establish a method and system for rapid forecasting of abnormal diagnosis and reliability evaluation of combustible gas monitoring equipment. Summary of the invention

[0003] In order to overcome the defects of the above-mentioned prior art that the combustible gas monitoring equipment is of varying quality, the present invention proposes a method for abnormal diagnosis of combustible gas monitoring equipment, which can realize equipment status monitoring and abnormal judgment to ensure dynamic perception of the operating status of the urban gas pipeline network and ensure the reliability of the combustible gas monitoring data.

[0004] The present invention proposes a method for diagnosing abnormalities of combustible gas monitoring equipment, comprising the following steps: firstly, based on the working principle of the combustible gas monitoring equipment, constructing abnormality types of the equipment; constructing equipment abnormality recognition models corresponding to each abnormality type; then judging the labels of the equipment on each abnormality type through the equipment abnormality recognition model; when all labels of the abnormality type are normal, judging the equipment is normal; otherwise, if any label of the abnormality type is abnormal, judging the equipment is abnormal, and marking the abnormality type;

[0005] The abnormal types of the equipment include: one or more of communication abnormality, pump speed abnormality, voltage abnormality, laser sensor abnormality and temperature and humidity sensor abnormality.

[0006] Preferably, the device anomaly model corresponding to the communication anomaly is a threshold judgment rule; first, the execution time range corresponding to normal communication is defined based on the known communication anomaly and normal communication labels, and the execution time is the difference between the abnormal monitoring execution time and the latest data collection time of the monitoring device; the execution time is calculated at each monitoring cycle node, and if the execution time falls within the execution time range, the communication is judged to be normal; otherwise, the communication is judged to be abnormal.

[0007] Preferably, the equipment anomaly recognition model includes a feature extraction module and an anomaly determination module; the anomaly extraction module is used to extract data features of the input object, and the anomaly determination module determines whether the input object is abnormal based on the data features and outputs the determination result; the input objects are pump speed data, voltage data, combustible gas concentration data collected by the laser sensor, and temperature data and humidity data collected by the temperature and humidity sensor;

[0008] The equipment anomaly recognition model adopts a fixed feature extraction module and trains the anomaly determination module on the corresponding data set.

[0009] Preferably, the data characteristics of the pump speed data include maximum value, minimum value and slope; the data characteristics of the voltage data include maximum value and minimum value; the data characteristics of the combustible gas concentration data include slope and fluctuation rate; the data characteristics of the temperature data include maximum value, minimum value and change rate; the data characteristics of the humidity data include maximum value and change rate.

[0010] The present invention proposes a reliability evaluation method for abnormal diagnosis of combustible gas monitoring equipment. First, based on the abnormal type of the equipment and in combination with the working principle of the equipment, the key components of the equipment are determined; then the reliability score and influence degree of each key component are calculated, and then the influence degree is used as the weight to perform weighted summation of the reliability scores of each key component as the reliability score of the entire equipment;

[0011] The reliability score of a component is the product of the failure probability, the abnormality frequency, and the abnormality repair time;

[0012] The impact of a component is calculated using the following formula:

[0013]

[0014] Among them, Num i represents the number of devices with the i-th key component failure predicted by the corresponding device anomaly recognition model; n i It indicates the number of devices where the i-th key component actually fails among the devices where the i-th key component failure is predicted by the corresponding device anomaly recognition model;

[0015] Num j represents the number of devices with the jth key component failure predicted by the corresponding device anomaly recognition model; n j It represents the number of devices with the jth key component failure actually occurring among the devices predicted by the corresponding equipment anomaly identification model; I is the number of key components.

[0016] Preferably, the failure probability B of the i-th key component is i =Num i / Num,Numi It indicates the number of devices with the i-th key component failure predicted by the corresponding device anomaly recognition model; Num indicates the total number of devices.

[0017] Preferably, the calculation formula for the abnormal frequency of the i-th key component is as follows:

[0018]

[0019] Among them, C k,i It indicates the predicted number of failures of the i-th key component in the k-th equipment during the monitoring period; Num indicates the total number of equipment.

[0020] Preferably, the key components correspond to the abnormality types, and the key components include: signal antenna, air pump, battery, laser sensor and temperature and humidity sensor.

[0021] The present invention proposes a system for evaluating the reliability of abnormal diagnosis of combustible gas monitoring equipment, which includes a memory and a processor. The memory stores a computer program. The processor is connected to the memory. The processor is used to execute the computer program to implement the method for evaluating the reliability of abnormal diagnosis of combustible gas monitoring equipment.

[0022] The present invention provides a storage medium storing a computer program, which is used to implement the abnormal diagnosis reliability assessment method of combustible gas monitoring equipment when executed.

[0023] (1) The abnormality diagnosis method for combustible gas monitoring equipment proposed in the present invention studies the operating status of the combustible gas monitoring equipment and establishes a relatively comprehensive equipment abnormality recognition model. By collecting the operating parameters and monitoring data of the combustible gas monitoring equipment, the collected data is input into the data set training model to judge the operating status of the equipment, and quickly carry out automatic diagnosis of the operating status of the combustible gas monitoring equipment.

[0024] (2) The present invention also provides a method for obtaining a device abnormality identification model corresponding to each abnormality type, and identifies the device abnormality type through the device abnormality identification model corresponding to each abnormality type, outputs the device fault category, determines the weak components of the device, and provides a basis for equipment upgrade and iteration.

[0025] (3) In the present invention, data features are specifically extracted from different working data to perform abnormality judgment, thereby ensuring the accuracy of various types of abnormality judgments, thereby improving the reliability of equipment fault judgment.

[0026] (4) The present invention proposes a method for evaluating the reliability of abnormal diagnosis of combustible gas monitoring equipment, establishes a reliability evaluation index P for combustible gas monitoring equipment, visualizes the reliability of the equipment, and provides a basis for equipment selection and reliability evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 It is a flow chart of a method for diagnosing abnormality of combustible gas monitoring equipment;

[0028] Figure 2 A schematic diagram of a flow chart of an abnormality diagnosis method for combustible gas monitoring equipment;

[0029] Figure 3 A flow chart of a reliability evaluation method for abnormal diagnosis of combustible gas monitoring equipment;

[0030] Figure 4 The results of reliability evaluation of abnormal diagnosis of a combustible gas monitoring device are statistically analyzed. DETAILED DESCRIPTION

[0031] 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.

[0032] Reference Figure 1 ,This embodiment proposes a method for diagnosing abnormalities of a combustible gas monitoring device. First, based on the working principle of the combustible gas monitoring device, the abnormality types of the device are constructed, including: communication abnormality, pump speed abnormality, voltage abnormality, laser sensor abnormality, temperature and humidity sensor abnormality, etc.;

[0033] Construct equipment anomaly recognition models corresponding to each anomaly type;

[0034] The device anomaly identification model is used to determine the device's label for each anomaly type. When all labels for all anomaly types are normal, the device is considered normal. Otherwise, if any label for any anomaly type is abnormal, the device is considered abnormal and the anomaly type is marked.

[0035] Specifically, in this implementation, the device abnormality identification model corresponds one-to-one to the device abnormality type.

[0036] Reference Figure 2In the specific implementation, the collected data is labeled, the data collection time data of abnormal communication is defined as label 11, the data collection time data of normal communication is defined as label 10, the data of abnormal operation of the gas pump is defined as label 21, the data of normal operation of the gas pump is defined as label 20, the data of abnormal operation of the battery voltage is defined as label 31, the data of normal operation of the battery voltage is defined as label 30, the data of abnormal operation of the laser sensor combustible gas concentration is defined as label 41, the data of normal operation of the laser sensor combustible gas concentration is defined as label 40, the data of abnormal operation of the temperature and humidity sensor is defined as label 51, and the data of normal operation of the temperature sensor is defined as label 50. In this way, it is convenient for subsequent data observation and statistics.

[0037] In this embodiment, the device abnormality model corresponding to the communication abnormality is actually a threshold judgment rule; first, the execution time range corresponding to the normal communication is defined according to the known communication abnormality and normal communication labels, and the execution time is the difference between the abnormal monitoring execution time and the latest data collection time of the monitoring device; if the execution time falls within the execution time range, the communication is judged to be normal; otherwise, the communication is judged to be abnormal. The execution time range can be set to (0, maximum data collection period].

[0038] In this embodiment, abnormal monitoring is implemented throughout the entire cycle of the monitoring equipment, that is, the equipment leaves the factory - is used - is repaired - is scrapped; during the entire cycle, the equipment is periodically monitored, that is, the abnormal monitoring execution time is each monitoring cycle node, and at each monitoring cycle node, monitoring judgment is performed on each abnormal type.

[0039] In this embodiment, the equipment abnormality recognition models corresponding to the pump speed abnormality, voltage abnormality, laser sensor abnormality and temperature and humidity sensor are all trained on the corresponding data sets, and the support vector machine algorithm can be used for model training.

[0040] Taking the equipment abnormality recognition model corresponding to the abnormal pump speed as an example, its training method includes the following steps:

[0041] S1. Collect the equipment pump speed data with labels to form a pump speed data set, where the labels include abnormal pump speed and normal pump speed; construct a pump speed abnormality recognition model, that is, an abnormality recognition model corresponding to the pump speed abnormality, and the pump speed abnormality recognition model includes: a feature extraction module and an abnormality determination module;

[0042] The feature extraction module is used to extract the features of the pump speed data, such as the maximum value, minimum value and slope;

[0043] The abnormality determination module determines whether the pump speed is abnormal according to the data features extracted by the feature extraction module; the abnormality determination module may specifically adopt a neural network model;

[0044] S2. The pump speed anomaly recognition model is made to learn on the pump speed data set to train the anomaly determination module until the pump speed anomaly recognition model reaches a set convergence condition.

[0045] The convergence condition can be specifically set as: the accuracy of the device anomaly recognition model reaches a set value. It is worth noting that in the device anomaly recognition model, the feature extraction module does not need to be trained and updated, only the anomaly determination module needs to be trained.

[0046] Reference Figure 3 In this embodiment, the device anomaly recognition models corresponding to voltage anomaly, laser sensor anomaly and temperature and humidity sensor are composed of a feature extraction module and an anomaly determination module, and during the training process, only the anomaly determination module needs to be trained.

[0047] The device anomaly recognition model corresponding to voltage anomaly, the data stored in all data sets during training is device voltage data, and the label is normal voltage or abnormal voltage; the voltage data features extracted by the feature extraction module are maximum and minimum values; the anomaly judgment module judges whether the battery is abnormal based on the maximum and minimum voltage values.

[0048] The equipment anomaly recognition model corresponding to the laser sensor anomaly, the data stored in all data sets during training is the equipment combustible gas concentration data, and the label is normal concentration or abnormal concentration; the combustible gas concentration data features extracted by the feature extraction module are slope and volatility; the anomaly judgment module judges whether the laser sensor is abnormal based on the slope and volatility.

[0049] The device anomaly recognition model corresponding to the temperature and humidity sensor, during training, all data sets store device temperature data and humidity data, with labels of normal temperature and humidity sensor or abnormal temperature and humidity sensor; the data features extracted by the feature extraction module include: the maximum value, minimum value and change rate of temperature data, and the maximum value and change rate of humidity data. The anomaly judgment module judges whether the temperature and humidity sensor is abnormal based on the data features extracted by the feature extraction module.

[0050] A method for evaluating the reliability of abnormal diagnosis of combustible gas monitoring equipment proposed in this embodiment first determines the key components of the equipment based on the equipment abnormality type and the equipment working principle; then calculates the overall reliability P of the equipment in accordance with the following formula;

[0051]

[0052] Among them, I is the number of key components, P i is the reliability score of the i-th key component, A i is the influence degree of the i-th key component.

[0053] It is worth noting that the larger the P value, the lower the reliability of the equipment; the reliability score P of key components i The higher it is, the lower the reliability of key components.

[0054] The impact degree of a component refers to the impact degree of a component failure on the normal operation of the equipment. In this implementation, the impact degree of a key component is defined as the ratio of the failure rate of the key component to the sum of the failure rates of all key components; that is:

[0055]

[0056] Among them, Num i represents the number of devices with the i-th key component failure predicted by the corresponding device anomaly recognition model; n i It indicates the number of devices where the i-th key component actually fails among the devices where the i-th key component failure is predicted by the corresponding device anomaly recognition model;

[0057] Num j represents the number of devices with the jth key component failure predicted by the corresponding device anomaly recognition model; n j It indicates the number of devices whose j-th key component actually fails among the devices whose j-th key component failure is predicted by the corresponding device anomaly recognition model.

[0058] The reliability score of a component is the product of the failure probability, abnormality frequency and abnormal repair time of the component; the failure probability of a component is the ratio of the number of devices with abnormal components to the total number of devices; the abnormality frequency of a component is the ratio of the total number of abnormalities of the component in each device during the monitoring period to the total number of devices; the abnormality repair time of a component is an empirical value manually marked.

[0059] The formula is:

[0060] P i =B i ×F i ×T i (3)

[0061] Among them, B i represents the failure probability of the i-th key component, F i represents the abnormal frequency of the i-th key component, T i represents the abnormal repair time of the i-th key component;

[0062] B i =Num i / Num

[0063]

[0064] Among them, C k,i It indicates the predicted number of failures of the i-th key component in the k-th equipment during the monitoring period; Num indicates the total number of equipment.

[0065] The above-mentioned abnormal diagnosis reliability assessment method of combustible gas monitoring equipment is verified in combination with specific embodiments below.

[0066] In this embodiment, the abnormality categories of the equipment include: communication abnormality, pump speed abnormality, voltage abnormality, laser sensor abnormality and temperature and humidity sensor abnormality; correspondingly, the key components are set to: signal antenna, air pump, battery, laser sensor and temperature and humidity sensor.

[0067] In this embodiment, firstly, the device anomaly recognition model corresponding to each anomaly category is trained in combination with the data in the historical database, and the anomaly determination module in each device anomaly recognition model adopts a deep neural network.

[0068] In this implementation, taking a combustible gas monitoring equipment as an example, there are three batches of equipment produced in different years. Based on the operating years, production processes and technological improvements, the third batch of equipment has higher overall stability during actual operation, while the first and second batches of equipment have lower stability, and the second batch is better than the first batch.

[0069] In this embodiment, serial numbers 1, 2, 3, 4, and 5 represent the signal antenna, air pump, battery, laser sensor, and temperature and humidity sensor, respectively, that is, P1 represents the reliability score of the signal antenna, P2 represents the reliability score of the air pump, P3 represents the reliability score of the battery, P4 represents the reliability score of the laser sensor, and P5 represents the reliability score of the temperature and humidity sensor.

[0070] In this embodiment, the failure probability, abnormal frequency and abnormal repair time of each key component in each batch are counted respectively, and then substituted into formula (3) to obtain:

[0071] The first batch of equipment:

[0072] Signal antenna reliability score P1 = 1.271

[0073] The reliability score of the air pump is P2 = 2.194

[0074] Battery reliability score P3 = 0.050

[0075] Laser sensor reliability score P4 = 0.012

[0076] Reliability score of temperature and humidity sensor P5 = 0.002

[0077] In the second batch of equipment:

[0078] Signal antenna reliability score P1 = 0.161

[0079] The reliability score of the air pump is P2 = 2.958

[0080] Battery reliability score P3 = 0.070

[0081] Laser sensor reliability score P4 = 0.005

[0082] Reliability score of temperature and humidity sensor P5 = 0.002

[0083] In the third batch of equipment:

[0084] Signal antenna reliability score P1 = 0.361

[0085] The reliability score of the air pump is P2 = 0.076

[0086] Battery reliability score P3 = 0.057

[0087] Laser sensor reliability score P4 = 0.059

[0088] Reliability score of temperature and humidity sensor P5 = 0.099

[0089] According to the calculation results, it can be seen that in the first and second batches, the reliability of laser sensors and temperature and humidity sensors is higher, while that of the third batch is relatively lower; in the first and second batches, the reliability of the air pump is relatively low, while that of the third batch is higher; the reliability of the signal antenna is lower in the first batch, while that of the second and third batches is higher; the reliability of the batteries in the three batches is close.

[0090] In this embodiment, the number of devices that cannot work normally among the various abnormal devices is detected and predicted, so as to calculate the failure ratio of each key component, and then substitute it into formula (2) to calculate the influence of each key component on the normal operation of the equipment.

[0091] Table 1: Equipment abnormality statistics

[0092]

[0093] Combined with Table 1 above, formula (1) is executed for each batch to obtain the reliability P of each batch of equipment.

[0094] For the first batch of equipment:

[0095] P=1.271×0.09+2.194×0.10+0.050×0.58+0.012×0.14+0.002×0.09=0.36465

[0096] For the second batch of equipment:

[0097] P=0.161×0.09+2.958×0.10+0.070×0.58+0.005×0.14+0.002×0.09=0.35177

[0098] For the third batch of equipment:

[0099] P=0.361×0.09+0.076×0.10+0.057×0.58+0.059×0.14+0.099×0.09=0.09032

[0100] Figure 4 The overall reliability of the equipment in three batches is given by Figure 4 It can be seen that the third batch of equipment has the highest overall reliability; the reliability of the first and second batches of equipment is not much different, and the reliability of the second batch of equipment is relatively slightly higher. It can be seen that the evaluation results of the present invention are in line with the actual situation, proving the reliability of the equipment evaluation of the present invention.

[0101] Of course, it is obvious to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, but also includes the same or similar structures that can be implemented in other specific forms without departing from the spirit or essential features of the present invention. Therefore, no matter from which point of view, the embodiments should be regarded as exemplary and non-limiting, and the scope of the present invention is defined by the appended claims rather than the above description, and it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any reference numerals in the claims should not be regarded as limiting the claims involved.

[0102] In addition, it should be understood that although the present specification is described according to implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment may also be appropriately combined to form other implementation modes that can be understood by those skilled in the art.

[0103] The techniques, shapes, and structural parts not described in detail in the present invention are all well-known techniques.

Claims

1. A method for diagnosing abnormality of combustible gas monitoring equipment, characterized in that: The following steps are involved: First, based on the working principle of the combustible gas monitoring equipment, the abnormal types of the equipment are constructed; the equipment abnormality recognition model corresponding to each abnormal type is constructed; then the equipment abnormality recognition model is used to determine the label of the equipment on each abnormal type; when the labels of all abnormal types are normal, the equipment is judged to be normal; On the contrary, if any abnormal type of label is abnormal, the device is judged to be abnormal and the abnormal type is marked; The abnormal types of the equipment include: one or more of communication abnormality, pump speed abnormality, voltage abnormality, laser sensor abnormality and temperature and humidity sensor abnormality.

2. The method for diagnosing abnormality of combustible gas monitoring equipment according to claim 1, characterized in that: The device anomaly model corresponding to the communication anomaly is the threshold judgment rule; first, the execution time range corresponding to normal communication is defined based on the known communication anomaly and normal communication labels, and the execution time is the difference between the abnormal monitoring execution time and the latest data collection time of the monitoring device; the execution time is calculated at each monitoring cycle node, and if the execution time falls within the execution time range, the communication is judged to be normal; otherwise, the communication is judged to be abnormal.

3. The method for diagnosing abnormality of combustible gas monitoring equipment according to claim 1, characterized in that: The equipment anomaly recognition model includes a feature extraction module and an anomaly determination module; the anomaly extraction module is used to extract the data features of the input object, and the anomaly determination module determines whether the input object is abnormal based on the data features and outputs the determination result; the input objects are pump speed data, voltage data, combustible gas concentration data collected by the laser sensor, and temperature data and humidity data collected by the temperature and humidity sensor; The equipment anomaly recognition model adopts a fixed feature extraction module and trains the anomaly determination module on the corresponding data set.

4. The method for diagnosing abnormality of combustible gas monitoring equipment according to claim 3, characterized in that: The data characteristics of pump speed data include maximum value, minimum value and slope; the data characteristics of voltage data include maximum value and minimum value; the data characteristics of combustible gas concentration data include slope and fluctuation rate; the data characteristics of temperature data include maximum value, minimum value and change rate, and the data characteristics of humidity data include maximum value and change rate.

5. A method for evaluating the reliability of abnormal diagnosis of combustible gas monitoring equipment, characterized in that: First, based on the equipment abnormality type and combined with the equipment working principle, the key components of the equipment are determined; then the reliability score and impact degree of each key component are calculated, and then the impact degree is used as the weight to perform a weighted sum of the reliability scores of each key component as the overall reliability score of the equipment; The reliability score of a component is the product of the failure probability, the abnormality frequency, and the abnormality repair time; The impact of a component is calculated using the following formula: Among them, Num i represents the number of devices with the i-th key component failure predicted by the corresponding device anomaly recognition model; n i It indicates the number of devices where the i-th key component actually fails among the devices where the i-th key component failure is predicted by the corresponding device anomaly recognition model; Num j represents the number of devices with the jth key component failure predicted by the corresponding device anomaly recognition model; n j It represents the number of devices with the jth key component failure actually occurring among the devices predicted by the corresponding equipment anomaly identification model; I is the number of key components.

6. The method for evaluating the reliability of abnormal diagnosis of combustible gas monitoring equipment according to claim 5, characterized in that: The failure probability B of the i-th key component i =Num i / Num,Num i It indicates the number of devices with the i-th key component failure predicted by the corresponding device anomaly recognition model; Num indicates the total number of devices.

7. The method for evaluating the reliability of abnormal diagnosis of combustible gas monitoring equipment according to claim 5, characterized in that: The calculation formula for the abnormal frequency of the i-th key component is as follows: Among them, C k,i It indicates the predicted number of failures of the i-th key component in the k-th device during the monitoring period; Num indicates the total number of devices.

8. The method for evaluating the reliability of abnormal diagnosis of combustible gas monitoring equipment according to claim 2, characterized in that: The key components correspond to the abnormality types, and the key components include: signal antenna, air pump, battery, laser sensor, and temperature and humidity sensor.

9. A reliability assessment system for abnormal diagnosis of combustible gas monitoring equipment, characterized in that: It includes a memory and a processor, the memory stores a computer program, the processor is connected to the memory, and the processor is used to execute the computer program to implement the abnormal diagnosis reliability assessment method of combustible gas monitoring equipment as described in any one of claims 5-8.

10. A storage medium, characterized in that: A computer program is stored, and when the computer program is executed, it is used to implement the abnormal diagnosis reliability assessment method of combustible gas monitoring equipment as described in any one of claims 5-8.

Images