Natural gas unmanned station reliability quantitative evaluation method, device, equipment and medium

Abstract

The invention relates to the field of natural gas unmanned stations, discloses a natural gas unmanned station reliability quantitative evaluation method, device, equipment and medium, and can determine a plurality of key equipment types in a natural gas unmanned station and the number of equipment corresponding to each key equipment type according to a process flow diagram of the natural gas unmanned station. Generating a fault tree model based on the plurality of key device types and the corresponding device number; wherein the fault tree model comprises a station failure top event, a middle event group and a bottom event group which are connected through a logic gate. And determining a plurality of event states of a bottom event group in the fault tree model and corresponding event state probability distribution. And constructing a plurality of bottom event state groups based on a plurality of event states and event state probability distributions of the bottom event groups. And determining the reliability of the natural gas unmanned station according to the plurality of bottom event state groups, the station failure top event in the fault tree model, the intermediate event group and the logic gate, thereby effectively realizing quantitative evaluation of the reliability of the natural gas unmanned station.

Description

Technical Field

[0001] The present invention relates to the field of unmanned natural gas stations, and in particular to a reliability quantitative evaluation method, device, equipment and medium for an unmanned natural gas station. Background Art

[0002] An unmanned natural gas station refers to an automated and unmanned station that uses automated equipment and monitoring systems to carry out processing such as natural gas collection, transportation and storage.

[0003] Among them, the advancement of automation technology has enabled unmanned natural gas stations to have the potential to operate efficiently, but it has also brought new challenges to the reliability of unmanned natural gas stations.

[0004] At present, how to conduct reliability evaluation on unmanned natural gas stations has become an important issue that needs to be solved urgently. Summary of the invention

[0005] The present invention provides a reliability quantitative evaluation method, device, equipment and medium for a natural gas unmanned station, which are used to implement reliability evaluation for the natural gas unmanned station.

[0006] In a first aspect, the present invention provides a method for quantitatively evaluating the reliability of an unmanned natural gas station, comprising: According to the process flow chart of the natural gas unmanned station, determining multiple key equipment types in the natural gas unmanned station and the number of equipment corresponding to each key equipment type; Based on the multiple key equipment types and the corresponding equipment quantities, a fault tree model is generated; wherein the fault tree model includes a site failure top event, an intermediate event group, and a bottom event group connected by logic gates; Determine multiple event states of the bottom event group in the fault tree model and corresponding event state probability distributions; Based on the multiple event states of the bottom event group and the event state probability distribution, construct a plurality of bottom event state groups; The reliability of the natural gas unmanned station is determined according to the multiple bottom event status groups, the station failure top event in the fault tree model, the intermediate event group and the logic gate.

[0007] Optionally, the bottom event group of the fault tree model includes multiple bottom events; The determining of the multiple event states and corresponding event state probability distributions of the bottom event group in the fault tree model includes: For any of the bottom events in the bottom event group, multiple event states of the bottom event and corresponding event state probability distributions are determined.

[0008] Optionally, constructing multiple bottom event state groups based on the multiple event states of the bottom event group and the event state probability distribution includes: For any of the base events, among the multiple event states of the base event, state sampling is performed according to the corresponding event state probability distribution to obtain a corresponding target event state; Determine the target event state of each of the bottom events as the bottom event state group; Return to executing the step of performing state sampling according to the corresponding event state probability distribution among the multiple event states of any of the bottom events to obtain the corresponding target event state, until the multiple bottom event state groups are obtained.

[0009] Optionally, determining the reliability of the natural gas unmanned station according to the multiple bottom event status groups, the station failure top event in the fault tree model, the intermediate event group and the logic gate includes: For any of the bottom event status groups, the bottom event status group is input into the fault tree model, so that the fault tree model performs an accident simulation based on the bottom event status group, the intermediate event group, the station failure top event and the logic gate, and obtains a corresponding top event occurrence result; The total number of accident simulations is determined, and the reliability of the unmanned natural gas station is determined according to the total number of accident simulations and the occurrence result of the top event corresponding to each of the bottom event state groups.

[0010] Optionally, the occurrence result of the top event is the occurrence of the site failure top event, or the non-occurrence of the site failure top event; Determining the reliability of the natural gas unmanned station according to the total number of accident simulations and the occurrence result of the top event corresponding to each of the bottom event state groups includes: In the top event occurrence result corresponding to each bottom event status group, a total number of failures is counted, where the total number of failures is the number of the top event occurrence results of which are the site failure top events; Calculating a ratio of the total number of failures to the total number of accident simulations, and subtracting the ratio from 1 to obtain a target difference; The target difference is determined as the reliability of the unmanned natural gas station.

[0011] Optionally, the determining, according to the process flow chart of the unmanned natural gas station, multiple key equipment types in the unmanned natural gas station and the number of equipment corresponding to each key equipment type includes: Inputting the process flow chart of the natural gas unmanned station into the trained multi-target detection model to perform key equipment detection to determine the multiple key equipment types in the natural gas unmanned station and the number of equipment corresponding to each key equipment type; The multi-target detection model is obtained by training a pre-trained detection model using a sample process flow chart.

[0012] Optionally, generating a fault tree model based on the multiple key equipment types and the corresponding equipment quantities includes: Determining a plurality of key devices according to the plurality of key device types and the corresponding number of devices; Acquire the logical connection relationship between the multiple key devices; The multiple key equipment types, the corresponding equipment quantities and the logical connection relationships are input into a trained intelligent pattern matching model for model construction to generate the fault tree model.

[0013] In a second aspect, the present invention provides a reliability quantitative evaluation device for an unmanned natural gas station, comprising: A first determination unit is used to determine a plurality of key equipment types in the unmanned natural gas station and the number of equipment corresponding to each key equipment type according to a process flow chart of the unmanned natural gas station; A generating unit, configured to generate a fault tree model based on the multiple key equipment types and the corresponding equipment quantities; wherein the fault tree model includes a site failure top event, an intermediate event group, and a bottom event group connected by logic gates; A second determining unit, configured to determine a plurality of event states of the bottom event group in the fault tree model and corresponding event state probability distributions; A construction unit, used to determine multiple event states of the bottom event group in the fault tree model and corresponding event state probability distributions; The third determination unit is used to determine the reliability of the natural gas unmanned station according to the multiple bottom event status groups, the station failure top event in the fault tree model, the intermediate event group and the logic gate.

[0014] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the method for quantitatively evaluating the reliability of an unmanned natural gas station according to the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0015] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the method for quantitatively evaluating the reliability of an unmanned natural gas station according to the first aspect or any corresponding embodiment thereof.

[0016] The method, device, equipment and medium for quantitatively evaluating the reliability of an unmanned natural gas station provided by the present invention can determine multiple key equipment types and the number of equipment corresponding to each key equipment type in the unmanned natural gas station according to the process flow chart of the unmanned natural gas station. A fault tree model is generated based on multiple key equipment types and corresponding equipment numbers; wherein the fault tree model includes a station failure top event, an intermediate event group and a bottom event group connected by logic gates. Multiple event states and corresponding event state probability distributions of the bottom event group in the fault tree model are determined. Based on the multiple event states and event state probability distributions of the bottom event group, multiple bottom event state groups are constructed. The reliability of the unmanned natural gas station is determined based on multiple bottom event state groups, the station failure top event, the intermediate event group and the logic gates in the fault tree model. The present invention can effectively realize the quantitative evaluation of the reliability of an unmanned natural gas station. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 A flow chart of a method for quantitatively evaluating the reliability of an unmanned natural gas station provided by an embodiment of the present invention; Figure 2 A key equipment graphic symbol in a process flow diagram of a natural gas unmanned station provided by an embodiment of the present invention; Figure 3 A schematic diagram of the structure of a natural gas unmanned station fault tree model provided by an embodiment of the present invention; Figure 4 A schematic diagram of the structure of a reliability quantitative evaluation device for an unmanned natural gas station provided by an embodiment of the present invention; Figure 5 A schematic diagram of the structure of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are 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.

[0020] Combine the following Figure 1-Figure 3 The reliability quantitative evaluation method of the natural gas unmanned station of the present invention is described.

[0021] like Figure 1 As shown, this embodiment proposes a first method for quantitatively evaluating the reliability of an unmanned natural gas station, which may include the following steps: S101. According to a process flow chart of the natural gas unmanned station, determine multiple key equipment types in the natural gas unmanned station and the number of equipment corresponding to each key equipment type.

[0022] It should be noted that the process flow chart of the unmanned natural gas station is composed of equipment symbols of various key equipment connected together.

[0023] Among them, the key equipment type can be the specific equipment type to which the key equipment in the natural gas unmanned station belongs, such as a regulating valve, a shut-off valve, an air pump and a gas tank.

[0024] Specifically, the number of devices corresponding to the key device type is the number of devices of a certain key device. For example, when the key device type is an air pump, the number of devices corresponding to the key device type is the number of air pumps.

[0025] Optionally, step S101 may include: Input the process flow chart of the natural gas unmanned station into the trained multi-target detection model to perform key equipment detection to determine multiple key equipment types in the natural gas unmanned station and the number of equipment corresponding to each key equipment type; Among them, the multi-target detection model is obtained by training the pre-trained detection model using the sample process flow chart.

[0026] It should be noted that this embodiment can realize target detection of key components of the process flow chart of natural gas stations, especially unmanned remanufacturing stations, based on end-to-end target detection technology of computer vision.

[0027] Among them, this embodiment can establish a data set of equipment units as a training object based on the natural gas unmanned station process flow chart, such as Figure 2The key equipment graphic symbols shown are the boosting facilities in the compressor station, the storage facilities in the distribution station, the flowmeters in the metering station and the related valves. This embodiment can use the end-to-end target detection algorithm to realize the recognition of the equipment units of the station process flow chart with multiple types of labels. Based on the original data set, data enhancement can be performed by flipping, rotating, scaling, cropping and other methods, which can greatly increase the data volume of the training data set and increase the robustness of the model prediction.

[0028] Specifically, in the process of training the pre-trained detection model using the sample process flow chart, this embodiment can collect image data including the process flow chart of the natural gas unmanned station, ensure the diversity and representativeness of the data, and accurately annotate the target objects (such as equipment, pipelines and valves, etc.) in the image, including bounding boxes and category information. The image is pre-processed such as scaling and normalization to meet the requirements of the model input for image quality and format. The v10 algorithm in the YOLO series of algorithms is used as the basic model to ensure that it has high detection accuracy and efficiency. A consistent dual allocation method is introduced in the algorithm, and label allocation is performed in combination with one-to-many and one-to-one strategies to ensure the consistency of training and reasoning. The non-maximum suppression (NMS) step is removed to reduce reasoning latency and achieve end-to-end deployment. A lightweight classification head is designed to reduce computational redundancy. The spatial-channel separation downsampling technology is used to optimize the feature extraction process. The overall architecture is simplified and computational efficiency is improved by using rank-based module design. Large kernel convolution is introduced to enhance the model's ability to capture detailed features. Some self-attention modules are added to improve detection accuracy. Use the preprocessed data to train the constructed end-to-end object detection model, using appropriate loss functions and optimization algorithms. Evaluate the trained model on the validation set, including accuracy, recall, F1 score and other indicators. Adjust the model hyperparameters such as learning rate, batch size, etc. based on the validation results to obtain the best performance.

[0029] Among them, this embodiment is based on the YOLO series of algorithms, and through a series of optimization measures, it can achieve the goal of reducing computational overhead while maintaining high-accuracy recognition. Among them, this embodiment can focus on the balance between efficiency and accuracy in object detection, and is suitable for edge device deployment with limited resources. Specifically, this embodiment can improve the model performance of the target detection model through data enhancement. Among them, this embodiment can effectively increase the diversity of the data set and enhance the model's recognition ability for different equipment units through data enhancement, such as rotation, scaling, and cropping. By constructing a data set with a rich sample size and high quality, the model can learn and generalize better, so that when facing practical applications, it can more accurately identify equipment units in natural gas unmanned stations, provide a solid foundation for model training, and significantly improve the recognition accuracy and stability of the model.

[0030] Specifically, data labeling and model training are important processes in model development and training. This embodiment can ensure the high quality of training data by accurately labeling the equipment units in the process flow diagram, which can directly affect the final recognition effect of the model. Based on the labeled data, through sufficient training, the model can learn the characteristics of different equipment units, thereby achieving high-precision recognition of unseen data. The quality of the labeled data directly affects the learning effect of the model, and sufficient training ensures that the model can capture the key patterns and laws in the data.

[0031] It should be noted that computer vision and reliability evaluation technologies in related technologies have become mature, but have not been applied to the reliability evaluation of unmanned natural gas stations. In order to improve the operating efficiency of the station and ensure that the unmanned natural gas station can operate stably under various conditions, in the reliability evaluation and optimization process of the unmanned natural gas station, this embodiment can establish the component function connection topology of the unmanned station and the fault tree model of the station, so as to understand the relationship and working mode of each component, and take into account the complex process flow of the unmanned natural gas station and the interaction between various components, to identify components more accurately and efficiently.

[0032] Compared with the image recognition method in the related art, the end-to-end target detection of this embodiment can introduce a deeper convolutional neural network architecture, enhance the feature extraction capability, and more accurately identify the tiny features (such as identifiers, connecting lines) in complex flowcharts. At the same time, by introducing a multi-scale detection strategy, the problem of difficult identification of elements of different degrees in the flowchart is effectively solved. By optimizing the calculation process in end-to-end target detection and using efficient reasoning guidance, efficient recognition can be achieved under low latency, meeting the strict real-time requirements of unmanned stations and having strong adaptability.

[0033] This embodiment can automatically and accurately identify the equipment units in the process flow diagram of the natural gas unmanned station by establishing a recognition system based on the end-to-end target detection model. The model directly processes the input process flow diagram and outputs the type and quantity of the equipment units, avoiding complex intermediate processing steps and improving recognition efficiency and accuracy. Through this end-to-end model design, manual intervention can be reduced, the robustness and adaptability of the system can be enhanced, and it is suitable for different types of process flow diagrams.

[0034] S102. Generate a fault tree model based on multiple key equipment types and corresponding equipment quantities; wherein the fault tree model includes a site failure top event, an intermediate event group, and a bottom event group connected by logic gates.

[0035] The intermediate event group may include multiple intermediate events, and the bottom event group may include multiple bottom events.

[0036] Specifically, this embodiment can construct a fault tree model based on multiple key equipment types in the determined natural gas unmanned station and the number of equipment corresponding to each key equipment type. Among them, this embodiment can generate a logical relationship diagram and a fault tree model of the station by analyzing the failure modes and failure causes of the natural gas unmanned station. Optionally, the main failure modes of the natural gas unmanned station may include initial defects, corrosion, construction defects, foundation settlement, pressure vessel and pipeline failure, deformation and fracture, etc. This embodiment can consider various failure modes and failure causes from multiple aspects such as material selection, design, installation, operation, management and maintenance of the station, and construct a fault tree model based on the key equipment of the natural gas unmanned station identified by target detection and the physical connection logical structure between them and the operation logic between the equipment.

[0037] like Figure 3 In the fault tree model shown, the gas supply failure of station A is the top event of the natural gas unmanned station A, T1 to T3 are intermediate events, X1 to X7 are bottom events, and the gas supply failure of station A is connected to the intermediate events through logic gates, and the intermediate events are connected to the bottom events through logic gates.

[0038] Optionally, step S102 may include: Determine multiple key equipment based on multiple key equipment types and corresponding equipment quantities; Obtain the logical connection relationship between multiple key devices; Multiple key equipment types, corresponding equipment quantities and logical connection relationships are input into the trained intelligent pattern matching model for model construction to generate a fault tree model.

[0039] Specifically, this embodiment can construct a fault tree model of a natural gas unmanned station based on an intelligent pattern matching model. This embodiment can introduce an intelligent pattern matching model based on the key equipment types and equipment quantities obtained by the above detection to construct a fault tree model of a natural gas unmanned station.

[0040] Specifically, this embodiment can first obtain the logical connection relationship between each key device, and then input the fault tree model construction command into the intelligent pattern matching model, which includes the key device type, the number of devices and the logical connection relationship. Through pattern matching and logical reasoning, the potential logical relationship between each device and each functional area is generated. The structured data code output by the intelligent pattern matching model is used to build a fault tree model for an unmanned station. Among them, this embodiment can pre-process the natural language prompt words of the input station fault tree model construction command by tokenization, embedding and position encoding, and convert the requirements described in natural language into numerical and tokenized multi-dimensional features, which are then accepted and understood by the intelligent pattern matching model, and a fault tree model for a natural gas unmanned station is generated.

[0041] S103, determining multiple event states of the bottom event group in the fault tree model and corresponding event state probability distributions.

[0042] The bottom event group includes multiple bottom events, and the multiple event states of the bottom event group are the multiple event states of each bottom event. It is understandable that each bottom event has multiple event states, such as normal, partial failure and complete failure.

[0043] Specifically, the event state probability distribution is the probability distribution of multiple event states of the base event. For example, when the base event has two event states A and B, the event state probability distribution may include the occurrence probability of A and the occurrence probability of B.

[0044] Optionally, in other natural gas unmanned station reliability quantitative evaluation methods proposed in this embodiment, the bottom event group of the fault tree model includes multiple bottom events. In this case, step S103 may include: For any bottom event in the bottom event group, multiple event states of the bottom event and corresponding event state probability distributions are determined.

[0045] Specifically, in this embodiment, a technician may determine the event state of each base event and assign an occurrence probability to each event state.

[0046] S104: Construct multiple bottom event state groups based on the multiple event states and event state probability distributions of the bottom event groups.

[0047] Specifically, this embodiment can construct multiple bottom event state groups for triggering the operation of the fault tree model and accident simulation according to the event state and event state probability distribution of each bottom event in the bottom event group.

[0048] Optionally, step S104 may include: For any base event, among the multiple event states of the base event, state sampling is performed according to the corresponding event state probability distribution to obtain the corresponding target event state; Determine the target event state of each bottom event as a bottom event state group as a whole; Return to executing the step of sampling the state according to the corresponding event state probability distribution among the multiple event states of any bottom event to obtain the corresponding target event state, until multiple bottom event state groups are obtained.

[0049] Specifically, this embodiment may uniformly sample the event status of each bottom event, and combine the sampled event statuses into a bottom event status group.

[0050] Specifically, this embodiment can sample, for any bottom event, the multiple event states of the bottom event according to the event state probability distribution of the multiple event states of the bottom event, obtain the sampled event state and use it as the target event state. This embodiment can determine the target event state of each bottom event as a bottom event state group as a whole.

[0051] It should be noted that, after obtaining a bottom event state group, this embodiment can uniformly sample the event state of each bottom event again to construct a new bottom event state group, until a certain number of bottom event state groups are constructed.

[0052] S105. Determine the reliability of the unmanned natural gas station according to multiple bottom event status groups, the top event of station failure in the fault tree model, the intermediate event group and the logic gate.

[0053] Specifically, this embodiment can perform a reliability quantitative evaluation on the natural gas unmanned station based on the constructed multiple bottom event state groups, as well as the site failure top event, intermediate event group and logic gate in the fault tree model to obtain the reliability of the natural gas unmanned station.

[0054] Optionally, step S105 may include: For any bottom event state group, the bottom event state group is input into the fault tree model, so that the fault tree model performs an accident simulation based on the bottom event state group, the intermediate event group, the station failure top event and the logic gate, and obtains a corresponding top event occurrence result; The total number of accident simulations is determined, and the reliability of the unmanned natural gas station is determined based on the total number of accident simulations and the top event occurrence results corresponding to each bottom event state group.

[0055] Among them, the total number of accident simulations is the total number of accident simulations performed by the fault tree model.

[0056] It is understandable that the total number of accident simulations is equal to the total number of bottom event state groups. It should be noted that the total number of bottom event state groups and the total number of accident simulations can be preset in this embodiment.

[0057] Optionally, in other reliability quantitative evaluation methods for natural gas unmanned stations proposed in this embodiment, the top event occurrence result is the occurrence of a station failure top event, or the absence of a station failure top event. In this case, the reliability of the natural gas unmanned station is determined based on the total number of accident simulations and the top event occurrence result corresponding to each bottom event state group, and may include: In the top event occurrence result corresponding to each bottom event status group, the total number of failures is counted, and the total number of failures is the number of top events whose top event occurrence result is the occurrence of site failure top events; Calculate the ratio of the total number of failures to the total number of accident simulations, and subtract the ratio from 1 to obtain the target difference; The target difference is determined as the reliability of the unmanned natural gas station.

[0058] It is understandable that the ratio of the total number of failures to the total number of accident simulations is the failure probability of the top event. The reliability corresponds to the failure probability of the top event, and in this embodiment, the reliability can be calculated by subtracting the failure probability from 1.

[0059] Among them, the greater the reliability of the natural gas unmanned station, the higher the reliability. The smaller the reliability of the natural gas unmanned station, the lower the reliability.

[0060] It should be noted that this embodiment can identify key components in the process flow chart of the natural gas unmanned station to ensure the accuracy and completeness of the identification. This embodiment can extract the features of the process flow chart, and build a real-time process component identification model based on deep learning to identify the key components of the process flow chart of the natural gas unmanned station, so as to achieve real-time identification and tracking of the process components. Further based on the identified process components, the functional connection topology of the unmanned station field components is established, and a fault tree model is constructed. Finally, based on the constructed natural gas unmanned station fault tree model, a natural gas "unmanned station" reliability evaluation and optimization method based on Monte Carlo simulation is further constructed to continuously improve the operating efficiency and reliability of the natural gas "unmanned station" to achieve a larger range and deeper level of intelligent operation.

[0061] It should also be noted that this embodiment can establish a natural gas unmanned station process flow chart equipment unit recognition model based on an end-to-end target detection model, use data enhancement methods to increase the quantity and quality of data sets, construct a "unmanned station" process flow chart data set with rich sample volume and high quality, and annotate and train it, and finally achieve high-precision recognition of key components of the natural gas "unmanned station" process flow chart. Then, through the recognition results, that is, the types and quantities of station equipment components, and the functional connection topology of key equipment, a fault tree model of the natural gas unmanned station is established, and finally, the established fault tree model can be used to achieve efficient and accurate evaluation of the operational reliability of the natural gas unmanned station equipment unit.

[0062] The reliability quantitative evaluation method of the natural gas unmanned station proposed in this embodiment can determine multiple key equipment types and the number of equipment corresponding to each key equipment type in the natural gas unmanned station according to the process flow chart of the natural gas unmanned station. Based on multiple key equipment types and corresponding equipment numbers, a fault tree model is generated; wherein the fault tree model includes a station failure top event, an intermediate event group, and a bottom event group connected by logic gates. Determine the multiple event states of the bottom event group in the fault tree model and the corresponding event state probability distribution. Based on the multiple event states and event state probability distribution of the bottom event group, construct multiple bottom event state groups. According to multiple bottom event state groups, the station failure top event, the intermediate event group, and the logic gates in the fault tree model, determine the reliability of the natural gas unmanned station. This embodiment can effectively realize the quantitative evaluation of the reliability of the natural gas unmanned station.

[0063] like Figure 4 As shown, this embodiment proposes a reliability quantitative evaluation device for an unmanned natural gas station, which may include: The first determination unit 401 is used to determine multiple key equipment types in the unmanned natural gas station and the number of equipment corresponding to each key equipment type according to the process flow chart of the unmanned natural gas station; A generating unit 402 is used to generate a fault tree model based on multiple key equipment types and corresponding equipment quantities; wherein the fault tree model includes a site failure top event, an intermediate event group, and a bottom event group connected by logic gates; The second determining unit 403 is used to determine multiple event states and corresponding event state probability distributions of the bottom event group in the fault tree model; A construction unit 404 is used to determine multiple event states of the bottom event group in the fault tree model and corresponding event state probability distributions; The third determination unit 405 is used to determine the reliability of the unmanned natural gas station according to a plurality of bottom event status groups, the top event of station failure in the fault tree model, the intermediate event group and the logic gate.

[0064] It should be noted that the processing of the first determining unit 401, the generating unit 402, the second determining unit 403, the constructing unit 404 and the third determining unit 405 and the beneficial effects thereof can be respectively referred to in Figure 1 Steps S101 to S105 in the above are not described in detail.

[0065] Optionally, the bottom event group of the fault tree model includes multiple bottom events; The second determining unit 403 is further configured to: For any bottom event in the bottom event group, multiple event states of the bottom event and corresponding event state probability distributions are determined.

[0066] Optionally, the construction unit 404 is further configured to: For any base event, among the multiple event states of the base event, state sampling is performed according to the corresponding event state probability distribution to obtain the corresponding target event state; Determine the target event state of each bottom event as a bottom event state group as a whole; Return to executing the step of sampling the state according to the corresponding event state probability distribution among the multiple event states of any bottom event to obtain the corresponding target event state, until multiple bottom event state groups are obtained.

[0067] Optionally, the third determining unit 405 is further configured to: For any bottom event state group, the bottom event state group is input into the fault tree model, so that the fault tree model performs an accident simulation based on the bottom event state group, the intermediate event group, the station failure top event and the logic gate, and obtains a corresponding top event occurrence result; The total number of accident simulations is determined, and the reliability of the unmanned natural gas station is determined based on the total number of accident simulations and the top event occurrence results corresponding to each bottom event state group.

[0068] Optionally, the top event occurrence result is that a site failure top event occurs, or that a site failure top event does not occur; the third determining unit 405 is further used to: In the top event occurrence result corresponding to each bottom event status group, the total number of failures is counted, and the total number of failures is the number of top events whose top event occurrence result is the occurrence of site failure top events; Calculate the ratio of the total number of failures to the total number of accident simulations, and subtract the ratio from 1 to obtain the target difference; The target difference is determined as the reliability of the unmanned natural gas station.

[0069] Optionally, the first determining unit 401 is further configured to: Input the process flow chart of the natural gas unmanned station into the trained multi-target detection model to perform key equipment detection to determine multiple key equipment types in the natural gas unmanned station and the number of equipment corresponding to each key equipment type; Among them, the multi-target detection model is obtained by training the pre-trained detection model using the sample process flow chart.

[0070] Optionally, the generating unit 402 is further configured to: Determine multiple key equipment based on multiple key equipment types and corresponding equipment quantities; Obtain the logical connection relationship between multiple key devices; Multiple key equipment types, corresponding equipment quantities and logical connection relationships are input into the trained intelligent pattern matching model for model construction to generate a fault tree model.

[0071] The reliability quantitative evaluation device of the natural gas unmanned station proposed in this embodiment can determine multiple key equipment types and the number of equipment corresponding to each key equipment type in the natural gas unmanned station according to the process flow chart of the natural gas unmanned station. A fault tree model is generated based on multiple key equipment types and corresponding equipment numbers; wherein the fault tree model includes a station failure top event, an intermediate event group, and a bottom event group connected by logic gates. Determine the multiple event states of the bottom event group in the fault tree model and the corresponding event state probability distribution. Based on the multiple event states and event state probability distribution of the bottom event group, construct multiple bottom event state groups. Determine the reliability of the natural gas unmanned station based on multiple bottom event state groups, the station failure top event, the intermediate event group, and the logic gates in the fault tree model. The present invention can effectively realize the quantitative evaluation of the reliability of the natural gas unmanned station.

[0072] The natural gas unmanned station reliability quantitative evaluation device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0073] The embodiment of the present invention also provides a computer device having the above Figure 4 The reliability quantitative evaluation device of the unmanned natural gas station shown.

[0074] See also Figure 5, a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. The various components are connected to each other using different buses for communication, and can be installed on a common motherboard or installed in other ways as needed. The processor can process instructions executed in the computer device, including instructions stored in or on the memory to display graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides part of the necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 5 A processor 10 is taken as an example.

[0075] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0076] The memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the method shown in the above embodiment.

[0077] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function. The data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage devices. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0078] The memory 20 may include a volatile memory, such as a random access memory. The memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive. The memory 20 may also include a combination of the above-mentioned types of memory.

[0079] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0080] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0081] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A reliability quantitative evaluation method for unmanned natural gas stations, characterized in that: include: According to the process flow chart of the natural gas unmanned station, determining multiple key equipment types in the natural gas unmanned station and the number of equipment corresponding to each key equipment type; Based on the multiple key equipment types and the corresponding equipment quantities, a fault tree model is generated; wherein the fault tree model includes a site failure top event, an intermediate event group, and a bottom event group connected by logic gates; Determine multiple event states of the bottom event group in the fault tree model and corresponding event state probability distributions; Based on the multiple event states of the bottom event group and the event state probability distribution, construct a plurality of bottom event state groups; The reliability of the natural gas unmanned station is determined according to the multiple bottom event status groups, the station failure top event in the fault tree model, the intermediate event group and the logic gate.

2. The method according to claim 1, characterized in that The bottom event group of the fault tree model includes a plurality of bottom events; The determining of the multiple event states and corresponding event state probability distributions of the bottom event group in the fault tree model includes: For any of the bottom events in the bottom event group, multiple event states of the bottom event and corresponding event state probability distributions are determined.

3. The method according to claim 2, characterized in that The constructing of multiple bottom event state groups based on the multiple event states of the bottom event group and the event state probability distribution includes: For any of the base events, among the multiple event states of the base event, state sampling is performed according to the corresponding event state probability distribution to obtain a corresponding target event state; Determine the target event state of each of the bottom events as the bottom event state group; Return to executing the step of performing state sampling according to the corresponding event state probability distribution among the multiple event states of any of the bottom events to obtain the corresponding target event state, until the multiple bottom event state groups are obtained.

4. The method according to claim 1, characterized in that The step of determining the reliability of the natural gas unmanned station according to the multiple bottom event status groups, the station failure top event in the fault tree model, the intermediate event group and the logic gate includes: For any of the bottom event status groups, the bottom event status group is input into the fault tree model, so that the fault tree model performs an accident simulation based on the bottom event status group, the intermediate event group, the station failure top event and the logic gate, and obtains a corresponding top event occurrence result; The total number of accident simulations is determined, and the reliability of the unmanned natural gas station is determined according to the total number of accident simulations and the occurrence result of the top event corresponding to each of the bottom event state groups.

5. The method according to claim 4, characterized in that The occurrence result of the top event is the occurrence of the site failure top event, or the non-occurrence of the site failure top event; Determining the reliability of the natural gas unmanned station according to the total number of accident simulations and the occurrence result of the top event corresponding to each of the bottom event state groups includes: In the top event occurrence result corresponding to each bottom event status group, a total number of failures is counted, where the total number of failures is the number of the top event occurrence results of which are the site failure top events; Calculating a ratio of the total number of failures to the total number of accident simulations, and subtracting the ratio from 1 to obtain a target difference; The target difference is determined as the reliability of the unmanned natural gas station.

6. The method according to claim 1, characterized in that Determining multiple key equipment types in the natural gas unmanned station and the number of equipment corresponding to each key equipment type according to the process flow chart of the natural gas unmanned station includes: Inputting the process flow chart of the natural gas unmanned station into the trained multi-target detection model to perform key equipment detection to determine the multiple key equipment types in the natural gas unmanned station and the number of equipment corresponding to each key equipment type; The multi-target detection model is obtained by training a pre-trained detection model using a sample process flow chart.

7. The method according to claim 1, characterized in that The generating a fault tree model based on the multiple key equipment types and the corresponding equipment quantities includes: Determining a plurality of key devices according to the plurality of key device types and the corresponding number of devices; Acquire the logical connection relationship between the multiple key devices; The multiple key equipment types, the corresponding equipment quantities and the logical connection relationships are input into a trained intelligent pattern matching model for model construction to generate the fault tree model.

8. A reliability quantitative evaluation device for an unmanned natural gas station, characterized in that: include: A first determination unit is used to determine a plurality of key equipment types in the unmanned natural gas station and the number of equipment corresponding to each key equipment type according to a process flow chart of the unmanned natural gas station; A generating unit, configured to generate a fault tree model based on the multiple key equipment types and the corresponding equipment quantities; wherein the fault tree model includes a site failure top event, an intermediate event group, and a bottom event group connected by logic gates; A second determining unit, configured to determine a plurality of event states of the bottom event group in the fault tree model and corresponding event state probability distributions; A construction unit, used to determine multiple event states of the bottom event group in the fault tree model and corresponding event state probability distributions; The third determination unit is used to determine the reliability of the natural gas unmanned station according to the multiple bottom event status groups, the station failure top event in the fault tree model, the intermediate event group and the logic gate.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the natural gas unmanned station reliability quantitative evaluation method according to any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the reliability quantitative evaluation method for an unmanned natural gas station according to any one of claims 1 to 7.

Images