Indoor hydrogen-doped natural gas leakage monitoring and disposal method, system, equipment and medium

Abstract

The invention relates to the technical field of natural gas leakage monitoring, and particularly discloses an indoor hydrogen-doped natural gas leakage monitoring and handling method, system and device and a medium. Acquiring a gas concentration sequence of the indoor area in the first time period and failure state data of disposal equipment arranged in the indoor area in the first time period; based on the gas concentration sequence and the collection position of the indoor area in the first time period and the failure state data of the first time period, a first treatment measure parameter of the first time period and failure state prediction data of the treatment equipment in the second time period are obtained by utilizing a treatment measure prediction model, and the gas concentration of the indoor area is obtained according to the first treatment measure parameter of the first time period and the failure state prediction data of the treatment equipment. And obtaining target disposal measure parameters in the first time period, determining target disposal equipment, and controlling the target disposal equipment to perform disposal according to the target disposal measure parameters. The indoor hydrogen-doped natural gas leakage monitoring and handling capacity can be improved, the potential gas leakage risk is effectively prevented, and the safety of the indoor environment is ensured.

Description

Background Art

[0002] With the acceleration of urbanization, the use of indoor gas has become increasingly popular, bringing convenience to residents' lives. In the context of achieving the dual carbon goals, the use of hydrogen-blended natural gas is of great significance. As a secondary energy source with abundant sources, green and low carbon, hydrogen energy plays an important role in building a clean, low-carbon, safe and efficient energy system and achieving the goals of carbon peak and carbon neutrality. Hydrogen-blended natural gas technology can not only realize the large-scale storage of hydrogen energy, but also transport hydrogen efficiently and at low cost, realizing "hydrogen into thousands of homes". It is an effective way to reduce the carbon emission intensity of natural gas utilization and ensure the safety of gas supply.

[0003] Since indoor spaces are relatively closed, the diffusion and dilution speed of gas leaks is slow. Once a leak occurs, it is very easy to cause a serious accident. Therefore, it is particularly important to quickly detect and effectively deal with indoor gas leaks. In particular, the use of hydrogen-blended natural gas, due to the addition of hydrogen, its combustion characteristics and leakage and diffusion behavior are different from those of pure natural gas, making the potential risk after leakage greater. The leakage and diffusion characteristics of hydrogen-blended natural gas are different from those of pure natural gas, and its post-leakage disposal method also needs to be adjusted accordingly.

[0004] Existing indoor gas leak monitoring and disposal methods mainly rely on gas concentration sensors, which can monitor the indoor gas concentration in real time. Once a leak is detected, preset disposal measures are usually taken, such as starting the ventilation system or closing the gas valve. Although existing indoor gas leak monitoring and disposal technologies have improved safety to a certain extent, they still face the following major limitations in practical applications:

[0005] 1) Limited real-time data analysis capabilities: Many existing systems lack sufficient computing power and advanced algorithm support when processing real-time data, resulting in an inability to quickly and accurately analyze leaks and make the best decisions in a timely manner.

[0006] 2) Lack of real-time updated disposal strategies: Once a leak is detected, the system usually only executes the preset disposal procedures and cannot make dynamic adjustments based on the actual situation of the leak.

[0007] 3) Insufficient consideration of failure situations: In actual applications, disposal measures may fail due to equipment failure, such as fan or shut-off valve failure, and existing systems often lack monitoring and early warning mechanisms for such situations. This increases the uncertainty and risk of accident handling.

[0008] Therefore, it is urgent to provide a technical solution to solve the above problems. Summary of the invention

[0009] In order to solve the above technical problems, the present invention provides a method, system, equipment and medium for monitoring and handling indoor hydrogen-blended natural gas leakage.

[0010] In the first aspect, the present invention provides a method for monitoring and treating indoor hydrogen-doped natural gas leakage, and the technical solution of the method is as follows:

[0011] When the gas concentration value in the target indoor area is monitored to be greater than the corresponding preset value at the target time, the gas concentration sequence of the target indoor area in the first time period and the failure state data of the disposal equipment set in the target indoor area in the first time period are obtained; wherein the starting time of the first time period is the target time; the gas concentration value is: hydrogen concentration value or methane concentration value;

[0012] Based on the gas concentration sequence and the collection position of the gas concentration sequence in the target indoor area in the first time period, and the failure state data of the disposal equipment in the first time period, and using the target disposal measure prediction model, the first disposal measure parameters corresponding to the first time period and the failure state prediction data of the disposal equipment in the second time period are obtained; wherein the second time period is located after the first time period;

[0013] According to the first treatment measure parameters corresponding to the first time period and the failure state prediction data of the treatment equipment in the second time period, the target treatment measure parameters corresponding to the first time period are obtained and the target treatment equipment corresponding to the target treatment measure parameters is determined, and the target treatment equipment is controlled to perform treatment according to the target treatment measure parameters corresponding to the first time period.

[0014] The beneficial effects of the indoor hydrogen-blended natural gas leakage monitoring and disposal method of the present invention are as follows:

[0015] The method of the present invention can improve the monitoring and treatment capabilities of indoor hydrogen-blended natural gas leakage, effectively prevent potential gas leakage risks, and ensure the safety of the indoor environment.

[0016] On the basis of the above scheme, the indoor hydrogen-blended natural gas leakage monitoring and disposal method of the present invention can also be improved as follows.

[0017] In an optional manner, at least one leakage monitoring sensor is arranged in the target indoor area, and each leakage monitoring sensor obtains the gas concentration value at the corresponding collection position; any leakage monitoring sensor is: a methane concentration sensor or a hydrogen concentration sensor;

[0018] When any leakage monitoring sensor is a methane concentration sensor, the leakage monitoring sensor obtains the methane concentration value at the collection position; when any leakage monitoring sensor is a hydrogen concentration sensor, the leakage monitoring sensor obtains the hydrogen concentration value at the collection position.

[0019] In an optional manner, the target treatment measure parameters include: the start / stop state and the operating speed of the target treatment equipment.

[0020] In an optional manner, the disposal equipment includes: at least one gas valve, at least one exhaust fan and at least one supply fan; the target disposal equipment includes: at least one exhaust fan among all exhaust fans and at least one supply fan among all supply fans.

[0021] In an optional manner, when the gas concentration value in the target indoor area is monitored to be greater than the corresponding preset value at the target time, the method further includes:

[0022] Close any gas valves that have not failed.

[0023] In an optional manner, the method further includes:

[0024] Based on the actual layout of the target indoor area, construct an indoor space simulation model of the target indoor area, and respectively set a leakage monitoring sensor model at multiple preset positions in the indoor space simulation model;

[0025] Based on the optimal leakage treatment parameters under different leakage simulation conditions, the failure status data of the treatment equipment, the preset position corresponding to each leakage monitoring sensor model and the collected gas concentration sequence, the preset treatment measure prediction model is trained to obtain the target treatment measure prediction model.

[0026] In a second aspect, the present invention provides an indoor hydrogen-blended natural gas leakage monitoring and disposal system, the technical solution of which is as follows:

[0027] An indoor hydrogen-blended natural gas leakage monitoring and disposal system, comprising: a monitoring module, a prediction module and a disposal module;

[0028] The monitoring module is used to: when the gas concentration value in the target indoor area is monitored to be greater than the corresponding preset value at the target time, obtain the gas concentration sequence of the target indoor area in the first time period and the failure state data of the disposal equipment set in the target indoor area in the first time period; wherein the starting time of the first time period is the target time; the gas concentration value is: hydrogen concentration value or methane concentration value;

[0029] The prediction module is used to obtain, based on the gas concentration sequence and the acquisition position of the gas concentration sequence of the target indoor area in the first time period, and the failure state data of the disposal equipment in the first time period, and by using the target disposal measure prediction model, the first disposal measure parameter corresponding to the first time period and the failure state prediction data of the disposal equipment in the second time period; wherein the second time period is located after the first time period;

[0030] The treatment module is used to: obtain the target treatment measure parameters corresponding to the first time period and determine the target treatment equipment corresponding to the target treatment measure parameters based on the first treatment measure parameters corresponding to the first time period and the failure state prediction data of the treatment equipment in the second time period, and control the target treatment equipment to perform treatment according to the target treatment measure parameters corresponding to the first time period.

[0031] The beneficial effects of the indoor hydrogen-blended natural gas leakage monitoring and disposal system of the present invention are as follows:

[0032] The system of the present invention can improve the monitoring and treatment capabilities of indoor hydrogen-blended natural gas leakage, effectively prevent potential gas leakage risks, and ensure the safety of the indoor environment.

[0033] On the basis of the above scheme, the indoor hydrogen-blended natural gas leakage monitoring and disposal system of the present invention can also be improved as follows.

[0034] In an optional manner, at least one leakage monitoring sensor is arranged in the target indoor area, and each leakage monitoring sensor obtains the gas concentration value at the corresponding collection position; any leakage monitoring sensor is: a methane concentration sensor or a hydrogen concentration sensor;

[0035] When any leakage monitoring sensor is a methane concentration sensor, the leakage monitoring sensor obtains the methane concentration value at the collection position; when any leakage monitoring sensor is a hydrogen concentration sensor, the leakage monitoring sensor obtains the hydrogen concentration value at the collection position.

[0036] In a third aspect, a technical solution of an electronic device of the present invention is as follows:

[0037] The invention comprises a memory, a processor and a program stored in the memory and running on the processor. When the processor executes the program, the steps of the indoor hydrogen-blended natural gas leakage monitoring and disposal method of the present invention are realized.

[0038] In a fourth aspect, the present invention provides a computer-readable storage medium having the following technical solution:

[0039] Instructions are stored in the computer-readable storage medium. When the computer-readable storage medium reads the instructions, the computer-readable storage medium executes the steps of the indoor hydrogen-blended natural gas leakage monitoring and disposal method of the present invention.

[0040] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The accompanying drawings are only used to illustrate the embodiments and are not to be considered as limiting the present invention. In addition, the same reference symbols are used to represent the same components throughout the accompanying drawings. In the accompanying drawings:

[0042] Figure 1 It is a schematic flow chart of an embodiment of a method for monitoring and treating indoor hydrogen-blended natural gas leakage of the present invention;

[0043] Figure 2 A schematic diagram of the structure of a preset treatment measure prediction model;

[0044] Figure 3 This is a schematic diagram of the indoor space simulation model;

[0045] Figure 4 This is a schematic diagram of the simulation results of indoor hydrogen-blended natural gas leakage and diffusion;

[0046] Figure 5 This is a schematic diagram of the distribution of leakage monitoring sensors;

[0047] Figure 6 It is a structural schematic diagram of an embodiment of an indoor hydrogen-blended natural gas leakage monitoring and disposal system of the present invention;

[0048] Figure 7 The figure is a schematic structural diagram of an embodiment of an electronic device of the present invention. DETAILED DESCRIPTION

[0049] Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be limited to the embodiments set forth herein.

[0050] Figure 1A flow chart of an embodiment of a method for monitoring and handling indoor hydrogen-blended natural gas leaks provided by the present invention is shown. The method for monitoring and handling indoor hydrogen-blended natural gas leaks can be executed by electronic devices such as terminal devices or servers. The terminal device can be any fixed or mobile terminal such as user equipment (UE), mobile device, user terminal, terminal, cellular phone, cordless phone, personal digital assistant (PDA), handheld device, computing device, vehicle-mounted device, wearable device, etc. The server can be a single server or a server cluster composed of multiple servers. Any electronic device can implement the method for monitoring and handling indoor hydrogen-blended natural gas leaks by calling computer-readable instructions stored in a memory through a processor. Figure 1 As shown, the following steps are included:

[0051] S1. When the gas concentration value in the target indoor area is monitored to be greater than the corresponding preset value at the target time, the gas concentration sequence of the target indoor area in the first time period and the failure status data of the disposal equipment installed in the target indoor area in the first time period are obtained.

[0052] Among them, the target indoor area is the indoor area to be monitored and treated for natural gas leaks in this embodiment, and the gas used in this indoor area is hydrogen-blended natural gas. The gas concentration value is a hydrogen concentration value or a methane concentration value. At least one leak monitoring sensor is arranged in the target indoor area, and each leak monitoring sensor obtains the gas concentration value at the corresponding collection position. The leak monitoring sensor is: a methane concentration sensor or a hydrogen concentration sensor. When the leak monitoring sensor is a methane concentration sensor, the leak monitoring sensor obtains the methane concentration value at the collection position; when the leak monitoring sensor is a hydrogen concentration sensor, the leak monitoring sensor obtains the hydrogen concentration value at the collection position. The preset value corresponding to the methane concentration sensor is different from the preset value corresponding to the hydrogen concentration sensor, and can be set according to the gas concentration standard respectively.

[0053] The starting time of the first period is the target time, and the duration of the first period is 10s by default, which can also be set according to actual needs. There is no limit here. The number of gas concentration values ​​in the gas concentration sequence is determined according to the collection frequency of the leakage monitoring sensor. For example, if the collection is once per second, the number of gas concentration values ​​in the gas concentration sequence is 10.

[0054] Among them, the disposal equipment includes: at least one gas valve, at least one exhaust fan and at least one supply fan. The specific location of the gas valve, exhaust fan and supply fan can be determined according to the actual layout and characteristics of the target indoor area, and there is no restriction here.

[0055] It should be noted that the methane concentration sensor and the hydrogen concentration sensor in the present embodiment are in real-time operation (such as collecting data once per second). When any sensor detects that the gas concentration value (methane concentration value or hydrogen concentration value) in the target indoor area is greater than the corresponding preset value at any time, the moment is determined as the target moment, and the steps of obtaining the gas concentration sequence of the target indoor area in the first time period and the failure status data of the disposal equipment installed in the target indoor area in the first time period are executed.

[0056] S2. Based on the gas concentration sequence and the collection position of the gas concentration sequence in the target indoor area in the first time period, as well as the failure status data of the disposal equipment in the first time period, and using the target disposal measure prediction model, obtain the first disposal measure parameters corresponding to the first time period and the failure status prediction data of the disposal equipment in the second time period.

[0057] Among them, the number of gas concentration sequences is the same as the number of leakage monitoring sensors in the target indoor area and corresponds one to one. The collection location of the gas concentration sequence is: the layout location of the leakage monitoring sensor that collects the gas concentration sequence. The failure status data of the disposal equipment includes: gas valve closing failure (not failed), exhaust fan operation failure (not failed) and supply fan operation failure (not failed). The failure status data is the status data of the disposal equipment obtained by real detection. The first disposal measure parameter is the disposal measure parameter corresponding to the first time period. The disposal measure parameter includes the corresponding disposal equipment and the corresponding opening and closing state and speed of the disposal equipment.

[0058] The second time period is located after the first time period, and the start time of the second time period can be the end time of the first time period, or a time after the first time period, without limitation. For example, if the first time period is 0s-10s (the target time is 0s), then the second time period is 10s-20s or 15s-25s (the interval between the two time periods is 5s). The failure state prediction data is the state data of the disposal equipment predicted by the target disposal measure prediction model.

[0059] The target disposal measure prediction model is a model obtained by training the preset disposal measure prediction model. The input data of the preset disposal measure prediction model are: the gas concentration sequence collected by each leakage monitoring sensor, the collection position (layout position) of each leakage monitoring sensor, and the failure state data of the disposal equipment; the output data of the preset disposal measure prediction model are: disposal measure parameters and the failure state prediction data of the disposal equipment.

[0060] Among them, the preset treatment measure prediction model is composed of a multi-layer neural network deep learning model. The preset treatment measure prediction model includes but is not limited to: a fully connected network, a long short-term memory network, a convolutional neural network, and additional neural networks. It should be noted that before the data is input into the model, the input data needs to be normalized, and after the model outputs the data, the output data also needs to be denormalized. In this embodiment, the input data of the preset treatment measure prediction model is converted into: a tensor with a dimension of [N1, N2, N3] and a tensor with a dimension of [N4]; the output data of the preset treatment measure prediction model is converted into: a tensor with a dimension of [N5, N6] and a tensor with a dimension of [N7]. Among them, the tensor with dimension N1 represents the number of leakage monitoring sensors, the tensor with dimension N2 represents the length of the gas concentration sequence, the tensor with dimension N3 represents the horizontal and vertical coordinates corresponding to the layout position of the leakage monitoring sensor and the corresponding gas concentration value, the tensor with dimension N4 represents the failure state data of the disposal equipment, the tensor with dimension N5 represents the disposal equipment corresponding to the disposal measure parameters, and the tensor with dimension N6 represents the state and speed of the disposal equipment corresponding to the disposal measure parameters. The tensor with dimension N7 represents the failure state prediction data of the disposal equipment. Figure 2 The detailed architecture diagram of the preset treatment measure prediction model is shown. The input data is a tensor of dimension [2, 10, 3] and a tensor of dimension [3], and the output data is a tensor of dimension [2, 2] and a tensor of dimension [3].

[0061] like Figure 2 As shown, the preset treatment measure prediction model includes: the first input layer, the reshaping layer, the first long short-term memory network (LSTM) layer, the second long short-term memory network layer and the flattening layer are connected in sequence, the second input layer, the first fully connected layer, the second fully connected layer, the third fully connected layer and the fourth fully connected layer are connected in sequence, the flattening layer and the fourth fully connected layer are respectively connected to the random loss layer, the random loss layer is connected to the fifth fully connected layer, and the fifth fully connected layer is respectively connected to the sixth fully connected layer and the seventh fully connected layer; the sixth fully connected layer, the first batch normalization layer, the eighth fully connected layer, the second batch normalization layer, the ninth fully connected layer, the third batch normalization layer, the tenth fully connected layer, the fourth batch normalization layer and the first output layer are connected in sequence, and the seventh fully connected layer, the fifth batch normalization layer, the eleventh fully connected layer, the sixth batch normalization layer, the twelfth fully connected layer and the second output layer are connected in sequence. Specifically:

[0062] ① The first input layer receives a tensor of dimension [2, 10, 3] and sends it to the reshape layer to change the shape of the tensor, obtaining the first feature with a tensor shape of [10, 6]. The first feature then passes through the first long short-term memory network layer and the second long short-term memory network layer in turn to extract time series features, and outputs the second feature with a dimension of [10, 16]. The second feature passes through the flattening layer to change the shape of the tensor, and outputs the third feature with a dimension of

[160] .

[0063] ② The second input layer receives a tensor of dimension [3] and sends it to the first fully connected layer, and is processed by the second fully connected layer, the third fully connected layer, and the fourth fully connected layer in turn to obtain the fourth feature. The number of hidden units in the first fully connected layer, the second fully connected layer, the third fully connected layer, and the fourth fully connected layer are 8, 16, 16, and 32, respectively.

[0064] ③ The third feature and the fourth feature are combined to obtain a tensor of dimension

[192] and input to the random dropout layer (dropout rate is 0.1) for processing, the fifth feature is obtained and input to the fifth fully connected layer (the number of hidden units is 64) for processing, and the sixth feature is obtained and input to the sixth and seventh fully connected layers respectively. The sixth feature passes through the sixth fully connected layer (the number of hidden units is 32), the first batch normalization layer, the eighth fully connected layer (the number of hidden units is 16), the second batch normalization layer, the ninth fully connected layer (the number of hidden units is 8), the third batch normalization layer, the tenth fully connected layer (the number of hidden units is 4), and the fourth batch normalization layer in sequence, and finally outputs a tensor of dimension [2, 2] through the first output layer. The first [2] in the tensor of dimension [2, 2] indicates that the number of treatment equipment corresponding to the treatment measure parameters is two (one supply fan and one exhaust fan), and the second [2] in the tensor of dimension [2, 2] indicates the on / off state and speed of the treatment equipment. In addition, the sixth feature also passes through the seventh fully connected layer (the number of hidden units is 32), the fifth batch normalization layer, the eleventh fully connected layer (the number of hidden units is 16), the sixth batch normalization layer, the twelfth fully connected layer (the number of hidden units is 3), and finally outputs a tensor of dimension [3] through the second output layer. The [3] in the tensor of dimension [3] represents the failure state prediction data of the disposal equipment (gas valve, exhaust fan and supply fan).

[0065] It should be noted that the last layers of the two fully connected networks (the tenth fully connected layer and the twelfth fully connected layer) use the Sigmoid activation function to ensure that the output value is in the range of 0 to 1; the other fully connected layers use the tanh activation function.

[0066] S3. According to the first treatment measure parameters corresponding to the first time period and the failure state prediction data of the treatment equipment in the second time period, the target treatment measure parameters corresponding to the first time period are obtained and the target treatment equipment corresponding to the target treatment measure parameters is determined, and the target treatment equipment is controlled to perform treatment according to the target treatment measure parameters corresponding to the first time period.

[0067] Among them, the target disposal measure parameters include: the start and stop status and operating speed of the target disposal equipment. The target disposal equipment is: the disposal equipment corresponding to the target disposal measure parameters, including at least one exhaust fan among all exhaust fans and at least one supply fan among all supply fans, which is set according to the actual situation and is not restricted here. The first disposal measure parameters include the corresponding disposal equipment and the start and stop status and operating speed corresponding to the disposal equipment. If the failure state prediction data of the disposal equipment included in the first disposal measure parameters in the second time period is a failure state, a new disposal measure parameter is regenerated, namely: the target disposal measure parameter. For example, the first disposal measure parameter includes: the exhaust fan is started and the exhaust fan speed is 1400, but at this time the exhaust fan is in a failure state in the failure state prediction data, then a new disposal measure parameter is regenerated to obtain the target disposal measure parameter.

[0068] It should be noted that the target treatment measure parameter corresponding to the first period does not mean that the actual treatment operation is performed in the first period, but that the treatment is started at a certain time after the first period, and the specific setting of the treatment time is not restricted here. In addition, neither the target treatment equipment nor the treatment equipment corresponding to the first treatment measure parameter includes a gas valve, that is, the start and stop of the gas valve are not predicted and controlled.

[0069] In an optional manner, when the gas concentration value in the target indoor area is monitored to be greater than the corresponding preset value at the target time, the method further includes:

[0070] Close any gas valves that have not failed.

[0071] Among them, when any gas concentration value (methane concentration value or hydrogen concentration value) in the target indoor area is monitored to be greater than the corresponding preset value at any time (such as: target time), the gas valve that has not failed at that moment is closed, and then the subsequent steps are executed.

[0072] In an optional manner, the method further includes:

[0073] Based on the actual layout of the target indoor area, an indoor space simulation model of the target indoor area is constructed, and a leakage monitoring sensor model is respectively set at multiple preset positions in the indoor space simulation model.

[0074] The indoor space simulation model is a three-dimensional model constructed according to the actual layout of the target indoor area. The preset position can be set according to the needs, and there is no restriction here. A leakage monitoring sensor is set at each preset position, and the leakage monitoring sensor can be a methane concentration sensor or a hydrogen concentration sensor.

[0075] Based on the optimal leakage treatment parameters under different leakage simulation conditions, the failure status data of the treatment equipment, the preset position corresponding to each leakage monitoring sensor model and the collected gas concentration sequence, the preset treatment measure prediction model is trained to obtain the target treatment measure prediction model.

[0076] According to different key leakage parameters (gas leakage size and other parameters) and treatment measure parameters set in the indoor space simulation model, the simulated gas concentration sequence under different leakage simulation conditions (leakage diffusion conditions, treatment measure parameters and treatment equipment failure status data) is simulated by the computational fluid simulation method, and a coordinate system is established in the indoor space simulation model. According to the leakage monitoring sensor model coordinates set in the indoor space simulation model, the gas concentration sequence (methane concentration sequence or hydrogen concentration sequence) collected at the preset position corresponding to each leakage monitoring sensor model is extracted from all simulated gas concentration sequences, and the indoor hydrogen-blended natural gas explosive volume sequence in the indoor space simulation model is recorded. The collected leakage monitoring sensor model coordinates, the gas concentration sequence at the preset position corresponding to the leakage monitoring sensor model, the indoor hydrogen-blended natural gas explosive volume sequence, the treatment measure parameters, and the treatment equipment failure status data are processed to obtain the best treatment measure parameters in each treatment (preset) period, and these data are constructed into a data set. Each sample data in the data set includes: input sample data and output sample data. The input sample data includes: the gas concentration sequence and the collection position of the gas concentration sequence in the training period, and the failure status data of the treatment equipment in the training period. The output sample data includes: the treatment measure parameters corresponding to the training period and the failure state prediction data of the treatment equipment in the next period of the training period. The sample data in the data set is processed into a training set, a validation set and a test set for the preset treatment measure prediction model training, and the preset treatment measure prediction model is trained, verified and tested to obtain the target treatment measure prediction model.

[0077] It should be noted that:

[0078] 1) By performing multiple numerical simulations with different gas leakage treatment measures and different treatment equipment failure status data under the same leakage simulation conditions, the volume value of the indoor gas explosive volume greater than the lower limit of the explosive volume under each treatment measure parameter and treatment equipment failure status data is obtained, and the treatment measure parameter with the largest volume value reduction after treatment is used as the optimal treatment measure parameter to be taken at this stage. The continuous treatment time required to calculate the reduction in volume value after treatment can be defined in the model by yourself, and there is no limit here.

[0079] 2) During the model training process, the Adam optimizer is used, and the mean square error (MSE) is used as the loss function. The sample data in the data set is input into the treatment measure prediction model and trained for 2000 epochs to obtain a trained target treatment measure prediction model, which can provide treatment measures for the current indoor gas diffusion state and predict the failure of the current treatment equipment.

[0080] 3) Within a specific time range from the start of indoor hydrogen-blended natural gas leakage monitoring, if the target disposal measure prediction model detects that the disposal equipment has failed, an early warning of disposal equipment failure may not be issued (no failure status prediction data is output), and in subsequent disposal measure updates, the input conditions of the disposal measure prediction model do not include failure status data (all disposal equipment is valid by default). The above time range for not judging the failure of disposal equipment can be customized and is not restricted here.

[0081] In order to better illustrate the technical solution of this embodiment, the following examples are used for illustration:

[0082] S10, perform fluid numerical simulation on the target indoor area to obtain the gas concentration sequence and explosive volume sequence collected by each leakage monitoring sensor model under different leakage simulation conditions. Specifically:

[0083] S101, using fluid numerical simulation to obtain a data set containing multiple training data, using computational fluid dynamics software to build an indoor space simulation model of the target indoor area, the indoor space simulation model is as follows: Figure 3 As shown. The target indoor area is 11m long, 4.5m wide and 3m high. There is one natural ventilation outlet, one mechanical air supply outlet controlled by a supply fan, and one mechanical exhaust outlet controlled by an exhaust fan. The gas leak is located 0.1m above the ground and is vertically upward. Different leakage simulation conditions have different leak diameters, including but not limited to: 1mm, 3mm, 5mm, 7mm and 9mm.

[0084] S102. The natural ventilation of the target indoor area is the pressure outlet boundary condition, and the pressure is equal to the atmospheric pressure. The mechanical air supply outlet of the target indoor area is the wall surface when the mechanical air supply is not started, and the velocity inlet is when the mechanical air supply is started, and the component is air. The mechanical exhaust outlet of the target indoor area is the wall surface when the mechanical exhaust is not started, and the velocity inlet is when the mechanical exhaust is started (the velocity is a negative value). The gas leak port is the velocity inlet boundary condition when there is a gas leak and the gas valve fails to close. The component is natural gas with a hydrogen blending ratio of 0.2. When the gas valve is effectively opened, the gas leak port is the wall surface.

[0085] S103, establishing an xyz coordinate system in the indoor space simulation model of the target indoor area, with the z value at the ground being 0 m.

[0086] S104. The leakage rate of hydrogen-blended natural gas starts from 5m / s, and increases by 5m / s gradually until it reaches 50m / s. There are five diameters of the leakage port, namely 1mm, 3mm, 5mm, 7mm and 9mm. A total of 50 leakage simulation conditions are set as the conditions for initial gas leakage. A transient simulation is performed for 50s, and the calculation results are saved every 1s. Finally, 50 gas concentration sequences (hydrogen concentration sequence and methane concentration sequence) and explosive volume sequences, and volume value sequences with concentrations greater than the lower limit of the explosive volume within 50s of the leakage of hydrogen-blended natural gas in the target indoor area space under the above 50 conditions can be obtained. For this initial leakage simulation condition, the equipment failure states used as model input and output are that the gas valve, air supply fan and exhaust fan are all in valid states, and the values ​​are (1, 1, 1). The methane concentration distribution of the gas at 50s on the plane x=2.25m in the target indoor area under one of the leakage simulation conditions is as follows: Figure 4 shown.

[0087] S105. Taking the indoor gas concentration distribution at 5s, 10s, 15s and 20s of leakage as the initial conditions of the initial leakage simulation of hydrogen-blended natural gas, a 10s transient simulation of the treatment measure startup condition is carried out. The leakage simulation conditions include that the gas valve is effectively cut off, and the boundary condition of the leakage port is set to the wall surface; the gas valve fails and cannot be closed, and its boundary condition is kept as the velocity inlet boundary condition; the supply fan is effectively started, and the boundary of the mechanical supply air outlet is set to the velocity inlet boundary condition, and the wind speed is based on the six supply air volumes corresponding to the supply fan speed of 400, 600, 800, 1000, 1200, and 1400 rpm; the supply fan fails or is closed, and the boundary of the mechanical supply air outlet is kept as the wall surface; the exhaust fan is effectively started, and the boundary of the mechanical exhaust air outlet is set to the velocity inlet boundary condition, the speed is a negative value, and the wind speed is based on the six supply air volumes corresponding to the supply fan speed of 400, 600, 800, 1000, 1200, and 1400 rpm; the exhaust fan fails or is closed, and the boundary of the mechanical exhaust air outlet is kept as the wall surface. Finally, under the above leakage simulation conditions, we can obtain 10 gas concentration sequences (hydrogen concentration sequence and methane concentration sequence) and explosive volume sequences within 10 seconds of starting treatment in the indoor space, volume value sequences with concentrations greater than the lower limit of the explosive volume, equipment failure status data, equipment start and stop status, and supply fan speed and exhaust fan speed.

[0088] S106. Take the measure start-up condition as the initial condition and perform a transient simulation of the subsequent 10s disposal work. For the condition where the gas valve, air supply fan, and exhaust fan fail in step S105, the failed equipment will continue to remain in the failed state in the subsequent disposal simulation. In this embodiment, only the case where at most one disposal equipment fails is considered, but the number of disposal equipment failures involved can be more than one. The subsequent 10s disposal simulation conditions include the effective cutting off of the gas valve, setting the leakage port boundary condition to the wall; the gas valve fails and cannot be closed, and its boundary condition is maintained as the velocity inlet boundary condition; the supply fan is effectively started, and the mechanical supply air outlet boundary is set to the velocity inlet boundary condition, and the wind speed is based on the six supply air volumes corresponding to the supply fan speed of 400, 600, 800, 1000, 1200, and 1400 rpm; the supply fan fails or is closed, and the mechanical supply air outlet boundary is maintained as the wall; the exhaust fan is effectively started, and the mechanical exhaust air outlet boundary is set to the velocity inlet boundary condition, the speed is a negative value, and the wind speed is based on the six supply air volumes corresponding to the supply fan speed of 400, 600, 800, 1000, 1200, and 1400 rpm; the exhaust fan fails or is closed, and the mechanical exhaust air outlet boundary is maintained as the wall. Finally, under the above working conditions, 10 gas concentration sequences (hydrogen concentration sequence and methane concentration sequence) and explosive volume sequences, volume value sequences with concentrations greater than the lower limit of the explosive volume, equipment failure status data, equipment start and stop status, and supply and exhaust fan speeds within 10 seconds of the start of treatment in the indoor space can be obtained;

[0089] S107, repeat S106, and continue to simulate the continuous treatment conditions 20s, 30s, 40s, and even 200s after the treatment measures are started. Considering that the conditions that need to be simulated will increase sharply in the future, 200 conditions are randomly selected for simulation in the subsequent treatment simulation conditions every 10s. Finally, under the above conditions, 10 gas concentration sequences (hydrogen concentration sequence and methane concentration sequence) and explosive volume sequences within 10s of the start of treatment in the indoor space, volume value sequences with concentrations greater than the lower limit of the explosive volume, equipment failure status data, equipment on / off status, and supply fan speed and exhaust fan speed can be obtained.

[0090] S20, obtaining a data set. Specifically:

[0091] S201, such as Figure 5 As shown, at a height of 2.8m of the indoor space simulation model of the target indoor area, 9 layout (collection) positions of leakage monitoring sensors are selected, and the position coordinates of the leakage monitoring sensors (coordinates of the preset positions) are (1.12m, 11.04m, 2.8m), (1.12m, 12.03m, 2.8m), (1.12m, 13.01m, 2.8m), (2.25m, 11.04m, 2.8m), (2.25m, 12.03m, 2.8m), (2.25m, 13.01m, 2.8m), (3.37m, 11.04m, 2.8m), (3.37m, 12.03m, 2.8m), (3.37, 13.01m, 2.8m). Based on all numerical simulation results of S10, the gas concentration sequences with a time series length of 10s for hydrogen and methane concentrations at the above 9 coordinate points under different treatment conditions at different treatment stages are obtained.

[0092] S202. Based on the gas concentration sequence obtained in S201, for the operating conditions with the same initial conditions and the operating conditions with different treatment measures, the treatment measure parameter with the largest reduction in hydrogen and methane concentrations within 10 seconds of the operating condition is taken as the optimal treatment measure parameter of the operating condition at this stage, and the on / off status of the supply fan (0 is off, 1 is on), the speed value of the supply fan, the on / off status of the exhaust fan (0 is off, 1 is on), and the speed value of the exhaust fan are recorded in the optimal treatment measure parameters of the operating condition.

[0093] S203, construct a data set for model training, the data set consists of multiple sample data. Each sample data includes: input sample data and output sample data. The input sample data includes: the gas concentration sequence and the acquisition position of the gas concentration sequence in the training period, and the failure state data of the treatment equipment in the training period. The output sample data includes: the treatment measure parameters corresponding to the training period and the failure state prediction data of the treatment equipment in the next period of the training period.

[0094] S204. For the two input tensors of sample data, the dimensions are [N, 2, 10, 4] and [N, 3]. For the tensor with the dimension [N, 2, 10, 4], the 10s sequence of hydrogen and methane concentration values ​​collected at the sensor coordinates and the sensor coordinate values ​​are recorded. N represents the total number of samples, 2 represents the number of enabled sensors is 2, 10 represents the time sequence of 10s, and 4 represents the x, y coordinates of the sensor and the collected hydrogen and methane concentration values, respectively. For the tensor with the dimension [N, 3], the failure status value of the disposal equipment in the previous stage is recorded. N represents the total number of samples, and 3 represents the failure status of the gas valve, supply fan and exhaust fan (0 represents failure, 1 represents non-failure).

[0095] S205. The output tensor for the data set samples has dimensions of [N, 2, 2] and [N, 3]. The tensor with dimensions of [N, 2, 2] records the current optimal treatment measure parameters, N represents the total number of samples, the second dimension 2 represents the supply fan and the exhaust fan, and the third dimension 2 represents the fan start and stop decisions in the treatment measures (0 is closed and 1 is open), and the speed values ​​of the fans (exhaust fans and supply fans) set in the treatment measures. The tensor with dimensions of [N, 3] records the failure status values ​​of the current treatment equipment, N represents the total number of samples, and 3 represents the failure status of the gas valve, the supply fan, and the exhaust fan;

[0096] S206, constructing a data set according to steps S204 and S205. For the two leakage monitoring sensors in the data set, 36 sensor combinations are obtained by combining two of the nine sensor coordinate points determined in step S201.

[0097] S207. In the data set, for the sample at the beginning of the treatment, the failure state value of the treatment equipment in the previous stage in the input tensor [N, 3] is that the gas valve, the supply air fan, and the exhaust air fan are all not failed.

[0098] S208, normalizing the data set, and dividing it into a training set accounting for 80%, a validation set accounting for 10%, and a test set accounting for 10% according to the number of working conditions.

[0099] S30, constructing a preset treatment measure prediction model and training it to obtain a target treatment measure prediction model. Specifically:

[0100] S301. The preset treatment measure prediction model is composed of a preset multi-layer neural network deep learning model. The input data is a tensor of dimension [2, 10, 3] and a tensor of dimension [3]. The tensor of dimension [2, 10, 3] represents the number of sensors, time series length, sensor coordinates and concentration data collected by the sensor. The tensor of dimension [3] represents the failure state values ​​of the gas valve, supply fan and exhaust fan in the previous stage. The output data is a tensor of dimension [2, 2] and a tensor of dimension [3]. The tensor of dimension [2, 2] represents the supply fan and exhaust fan, the on / off state of the fan and the fan speed. The tensor of dimension [3] represents the failure state values ​​of the current gas valve, supply fan and exhaust fan.

[0101] S302. Input data has a dimension of [2, 10, 3], where the third dimension 3 represents the sensor x-coordinate, the sensor y-coordinate and a concentration value of hydrogen and methane concentrations. In this embodiment, the methane concentration value is used.

[0102] S303. The preset treatment measure prediction model includes but is not limited to the following components: fully connected network, long short-term memory network, convolutional neural network and additional neural network, etc. The architecture, depth and hyperparameters of the model can be adjusted and optimized accordingly according to specific data sets and business requirements.

[0103] S304, the model receives input tensors of dimensions [2, 10, 3] and [3]. The input tensor of dimension [2, 10, 3] first changes the shape of the tensor through a reshape layer, and outputs features of dimension [10, 6]. It then passes through two long short-term memory (LSTM) layers to extract temporal features, and the output dimension is [10, 16]. It also passes through a flattening layer to change the shape of the tensor, and outputs features of dimension

[160] . The input tensor of dimension [3] passes through four fully connected layers in succession, and the number of hidden units in the four fully connected layers is 8, 16, 16, and 32 respectively. It is then merged with the tensor of dimension

[160] whose shape is changed through the flattening layer into a tensor of dimension

[192] . The merged feature tensor passes through a random dropout layer with a dropout rate of 0.1 and a fully connected layer with 64 hidden units, and is then sent to two sets of fully connected networks. The first group of fully connected networks consists of 4 fully connected layers and one reshape layer, which form a tensor with a final output dimension of [2, 2], representing the predicted supply fan and exhaust fan, the fan on / off status and the fan speed, where the number of hidden units in the 4 fully connected layers is 32, 16, 16, and 4, respectively. The second group of fully connected networks consists of 3 fully connected layers, which form a tensor with a final output dimension of [3], representing the predicted failure status of the current gas valve, supply fan, and exhaust fan, where the number of hidden units in the 3 fully connected layers is 32, 16, and 3, respectively.

[0104] S305. At the end of the preset treatment measure prediction model, the last layers of the two sets of fully connected networks use the Sigmoid activation function to ensure that the output value is within the range of 0 to 1. The other fully connected network layers in the preset treatment measure prediction model continue to use the tanh activation function.

[0105] S306. During the training of the preset treatment measure prediction model, the Adam optimizer is used, and the mean square error (MSE) is used as the loss function.

[0106] S307, input the training data set into the preset disposal measure prediction model, and perform training for 2000 epochs to obtain a trained model, which can provide disposal measures for the current indoor gas diffusion state and predict the failure of the current disposal equipment.

[0107] S308. For the trained target treatment measure prediction model, its prediction result will be subjected to a denormalization process to obtain a final prediction result of the treatment fan operating speed.

[0108] S40. When the gas concentration value in the target indoor area is monitored to be greater than the corresponding preset value at the target time, the gas valve is closed, and the gas concentration sequence of the target indoor area in the first time period and the failure state data of the disposal equipment installed in the target indoor area in the first time period are obtained; based on the gas concentration sequence of the target indoor area in the first time period and the acquisition position of the gas concentration sequence, as well as the failure state data of the disposal equipment in the first time period, and using the target disposal measure prediction model, the first disposal measure parameters corresponding to the first time period and the failure state prediction data of the disposal equipment in the second time period are obtained; according to the first disposal measure parameters corresponding to the first time period and the failure state prediction data of the disposal equipment in the second time period, the target disposal measure parameters corresponding to the first time period are obtained and the target disposal equipment corresponding to the target disposal measure parameters are determined. Specifically:

[0109] S401. Select two locations from the nine sensor installation locations in the target indoor area as the final layout locations (collection locations) of the leakage monitoring sensors, install two methane concentration sensors, and continuously collect indoor methane concentration sequences.

[0110] S402: When the methane volume concentration in the collected methane concentration sequence is monitored to be higher than the preset alarm disposal concentration (the default is 0.01), a leakage alarm is issued and a cut-off instruction is issued to the gas shut-off to shut off the gas valve.

[0111] S403. At the same time, the methane concentration sequence lasting 10 seconds collected by the two leakage monitoring sensors until the current moment is normalized and input into the target leakage treatment measure prediction model. When the treatment starts, the tensor value with dimension [3] representing the failure state value of the gas valve, supply air fan and exhaust air fan in the previous stage input into the target leakage treatment measure prediction model is [1, 1, 1].

[0112] S404. The target leakage disposal measure prediction model predicts the currently required supply air fan and exhaust air fan, the fan on / off status and the fan speed based on the input data, and predicts the failure state value of the gas valve, supply air fan and exhaust air fan.

[0113] S405. Based on the prediction results of the target leakage treatment measure prediction model for the supply fan and the exhaust fan, the on / off status of the fan and the fan speed, relevant operation instructions are issued to the supply fan and the exhaust fan, and the supply fan and the exhaust fan perform actions according to the instructions.

[0114] S406. After the treatment measures are executed for 10 seconds, the current methane concentration sequence lasting 10 seconds and the previous model's predicted values ​​of the failure status of the gas valve, supply air fan, and exhaust air fan are normalized and input into the target leakage treatment measures prediction model, and then the operations of S404-S406 are executed.

[0115] S407. During the preset treatment time of ignoring the treatment equipment failure prediction result (the default is 40s, which can also be set according to the actual situation), even if the target leakage treatment measure prediction model fails to predict the failure state of the treatment equipment, the failure result can be ignored and the state value of the treatment equipment that has not failed can be input into the target leakage treatment measure prediction model. The preset time can be defined by yourself. If it is set to 0s, the above operation will not be performed. When the treatment time is longer than the preset prediction result of ignoring the treatment equipment failure, if the target leakage treatment measure prediction model determines that the treatment equipment has failed, it will issue a treatment equipment failure alarm, and the current methane concentration sequence lasting 10s and the previous target leakage treatment measure prediction model's prediction value of the failure state of the gas shut-off valve, air supply fan, and exhaust fan are normalized and input into the target leakage treatment measure prediction model, and then the operations of S404-S407 are performed.

[0116] It should be noted that, for the verification process of the preset leakage disposal measure prediction model, a sample data in the verification set is selected. Tables 1 and 2 show that the sample contains input data collected by two leakage monitoring sensors within 10 seconds.

[0117] Table 1:

[0118]

[0119] Table 2:

[0120] Gas valve failure status Air supply fan failure status Exhaust fan failure status 1 1 1

[0121] The input data is normalized and then input into the trained target leakage treatment measures prediction model to obtain the prediction results. The prediction results of the target leakage treatment measures prediction model are denormalized to obtain the following prediction results: supply fan start-up state: 1, supply fan speed: 1400, exhaust fan start-up state: 1, exhaust fan speed: 1385, gas shut-off valve failure state: 1, supply fan failure state: 1, exhaust fan failure state: 1; actual optimal supply fan start-up state: 1, actual optimal supply fan speed: 1400, actual optimal exhaust fan start-up state: 1, actual optimal exhaust fan speed: 1400, actual gas shut-off valve failure state: 1, actual supply fan failure state: 1, actual exhaust fan failure state: 1.

[0122] The technical solution of this embodiment can improve the monitoring and disposal capabilities of indoor hydrogen-blended natural gas leaks, effectively prevent potential gas leakage risks, and ensure the safety of the indoor environment. This embodiment can be widely used in gas leak detection and disposal in various places, including residential, public, commercial and industrial indoor gas environments, and can effectively prevent potential gas leakage risks and ensure the safety of personnel and property.

[0123] Figure 6 FIG. 2 shows a schematic diagram of an embodiment of an indoor hydrogen-blended natural gas leakage monitoring and disposal system 200 provided by the present invention. Figure 6 As shown, the system 200 includes: a monitoring module 210, a prediction module 220 and a treatment module 230;

[0124] The monitoring module 210 is used to: when the gas concentration value in the target indoor area is greater than the corresponding preset value at the target time, obtain the gas concentration sequence of the target indoor area in the first time period and the failure state data of the disposal equipment set in the target indoor area in the first time period; wherein the starting time of the first time period is the target time; the gas concentration value is: hydrogen concentration value or methane concentration value;

[0125] The prediction module 220 is used to obtain the first treatment measure parameters corresponding to the first time period and the failure state prediction data of the treatment equipment in the second time period based on the gas concentration sequence and the collection position of the gas concentration sequence in the target indoor area in the first time period, and the failure state data of the treatment equipment in the first time period, and using the target treatment measure prediction model; wherein the second time period is located after the first time period;

[0126] The treatment module 230 is used to: obtain the target treatment measure parameters corresponding to the first time period and determine the target treatment equipment corresponding to the target treatment measure parameters based on the first treatment measure parameters corresponding to the first time period and the failure state prediction data of the treatment equipment in the second time period, and control the target treatment equipment to perform treatment according to the target treatment measure parameters corresponding to the first time period.

[0127] In an optional manner, at least one leakage monitoring sensor is arranged in the target indoor area, and each leakage monitoring sensor obtains the gas concentration value at the corresponding collection position; any leakage monitoring sensor is: a methane concentration sensor or a hydrogen concentration sensor;

[0128] When any leakage monitoring sensor is a methane concentration sensor, the leakage monitoring sensor obtains the methane concentration value at the collection position; when any leakage monitoring sensor is a hydrogen concentration sensor, the leakage monitoring sensor obtains the hydrogen concentration value at the collection position.

[0129] In an optional manner, the target treatment measure parameters include: the start / stop state and the operating speed of the target treatment equipment.

[0130] In an optional manner, the disposal equipment includes: at least one gas valve, at least one exhaust fan and at least one supply fan; the target disposal equipment includes: at least one exhaust fan among all exhaust fans and at least one supply fan among all supply fans.

[0131] In an optional manner, when the gas concentration value in the target indoor area is monitored to be greater than the corresponding preset value at the target time, the system 200 further includes: a control module;

[0132] The control module is used to close the gas valves that have not failed.

[0133] In an optional manner, the method further includes: a training module; the training module is used to:

[0134] Based on the actual layout of the target indoor area, an indoor space simulation model of the target indoor area is constructed, and a leakage monitoring sensor model is respectively set at multiple preset positions in the indoor space simulation model;

[0135] Based on the optimal leakage treatment parameters under different leakage simulation conditions, the failure status data of the treatment equipment, the preset position corresponding to each leakage monitoring sensor model and the collected gas concentration sequence, the preset treatment measure prediction model is trained to obtain the target treatment measure prediction model.

[0136] It should be noted that the beneficial effects of the indoor hydrogen-blended natural gas leakage monitoring and disposal system provided in the above-mentioned embodiment are the same as the beneficial effects of the indoor hydrogen-blended natural gas leakage monitoring and disposal method, which will not be repeated here. In addition, when the system provided in the above-mentioned embodiment realizes its functions, it only uses the division of the above-mentioned functional modules as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the system can be divided into different functional modules according to actual conditions to complete all or part of the functions described above. In addition, the system and method embodiments provided in the above-mentioned embodiments belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0137] Among them, the indoor hydrogen-blended natural gas leak monitoring and disposal system of the present invention can be a computer program (including program code) running in a computer device. For example, the indoor hydrogen-blended natural gas leak monitoring and disposal system of the present invention is an application software that can be used to execute the corresponding steps in the indoor hydrogen-blended natural gas leak monitoring and disposal method of the present invention.

[0138] In some embodiments, the indoor hydrogen-blended natural gas leakage monitoring and disposal system of the present invention can be implemented by a combination of software and hardware. As an example, the indoor hydrogen-blended natural gas leakage monitoring and disposal system of the present invention can be a processor in the form of a hardware decoding processor, which is programmed to execute the indoor hydrogen-blended natural gas leakage monitoring and disposal method of the present invention. For example, the processor in the form of a hardware decoding processor can adopt one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field programmable gate arrays (FPGAs) or other electronic components.

[0139] The modules involved in the embodiments of the present invention may be implemented in software or hardware. The name of a module does not limit the module itself in some cases.

[0140] like Figure 7As shown, an electronic device 300 according to an embodiment of the present invention includes a processor 320, the processor 320 is coupled to a memory 310, and the memory 310 stores at least one computer program 330, and the at least one computer program 330 is loaded and executed by the processor 320, so that the electronic device 300 implements any of the above-mentioned indoor hydrogen-blended natural gas leakage monitoring and disposal methods, specifically:

[0141] The electronic device 300 may have relatively large differences due to different configurations or performances, and may include one or more processors 320 (Central Processing Units, CPU) and one or more memories 310, wherein the one or more memories 310 store at least one computer program 330, and the at least one computer program 330 is loaded and executed by the one or more processors 320, so that the electronic device 300 implements any of the indoor hydrogen-blended natural gas leakage monitoring and disposal methods provided in the above embodiments. Of course, the electronic device 300 may also have components such as a wired or wireless network interface, a keyboard, and an input and output interface for input and output, and the electronic device 300 may also include other components for implementing device functions, which will not be described in detail here.

[0142] A computer-readable storage medium according to an embodiment of the present invention stores at least one computer program, and the at least one computer program is loaded and executed by a processor so that a computer implements any of the above-mentioned indoor hydrogen-blended natural gas leakage monitoring and disposal methods.

[0143] Optionally, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, and the like.

[0144] In an exemplary embodiment, a computer program product or a computer program is also provided, the computer program product or the computer program comprising computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of an electronic device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the electronic device performs any of the above-mentioned indoor hydrogen-blended natural gas leakage monitoring and disposal methods.

[0145] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects and represent the definition of a specific order or sequence. The order of use of similar objects can be interchanged where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than the order shown or described.

[0146] Those skilled in the art know that the present invention can be implemented as a system, method or computer program product. Therefore, the present disclosure can be specifically implemented in the following forms, namely: it can be complete hardware, it can be complete software (including firmware, resident software, microcode, etc.), or it can be a combination of hardware and software, which is generally referred to as "circuit", "module" or "system" herein. In addition, in some embodiments, the present invention can also be implemented in the form of a computer program product in one or more computer-readable media, and the computer-readable medium contains computer-readable program code.

[0147] Any combination of one or more computer-readable media can be used. Computer-readable media can be computer-readable signal media or computer-readable storage media. Computer-readable storage media can be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or devices, or any combination of the above. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0148] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A method for monitoring and treating indoor hydrogen-blended natural gas leakage, characterized in that: include: When the gas concentration value in the target indoor area is monitored to be greater than the corresponding preset value at the target time, the gas concentration sequence of the target indoor area in the first time period and the failure state data of the disposal equipment set in the target indoor area in the first time period are obtained; wherein the starting time of the first time period is the target time; the gas concentration value is: hydrogen concentration value or methane concentration value; Based on the gas concentration sequence and the collection position of the gas concentration sequence in the target indoor area in the first time period, and the failure state data of the disposal equipment in the first time period, and using the target disposal measure prediction model, the first disposal measure parameters corresponding to the first time period and the failure state prediction data of the disposal equipment in the second time period are obtained; wherein the second time period is located after the first time period; According to the first treatment measure parameters corresponding to the first time period and the failure state prediction data of the treatment equipment in the second time period, the target treatment measure parameters corresponding to the first time period are obtained and the target treatment equipment corresponding to the target treatment measure parameters is determined, and the target treatment equipment is controlled to perform treatment according to the target treatment measure parameters corresponding to the first time period.

2. The method for monitoring and treating indoor hydrogen-blended natural gas leakage according to claim 1, characterized in that: At least one leakage monitoring sensor is arranged in the target indoor area, and each leakage monitoring sensor obtains the gas concentration value at the corresponding collection position; any leakage monitoring sensor is: a methane concentration sensor or a hydrogen concentration sensor; When any leakage monitoring sensor is a methane concentration sensor, the leakage monitoring sensor obtains the methane concentration value at the collection position; when any leakage monitoring sensor is a hydrogen concentration sensor, the leakage monitoring sensor obtains the hydrogen concentration value at the collection position.

3. The method for monitoring and treating indoor hydrogen-blended natural gas leakage according to claim 1, characterized in that: The target treatment measure parameters include: the start / stop state and the operating speed of the target treatment equipment.

4. The method for monitoring and treating indoor hydrogen-blended natural gas leakage according to claim 3, characterized in that: The treatment equipment includes: at least one gas valve, at least one exhaust fan and at least one supply fan; the target treatment equipment includes: at least one exhaust fan among all exhaust fans and at least one supply fan among all supply fans.

5. The method for monitoring and treating indoor hydrogen-blended natural gas leakage according to claim 4, characterized in that: When the gas concentration value in the target indoor area is monitored to be greater than the corresponding preset value at the target time, the method further includes: Close any gas valves that have not failed.

6. The method for monitoring and handling indoor hydrogen-blended natural gas leakage according to any one of claims 1 to 5, characterized in that: Also includes: Based on the actual layout of the target indoor area, construct an indoor space simulation model of the target indoor area, and respectively set a leakage monitoring sensor model at multiple preset positions in the indoor space simulation model; Based on the optimal leakage treatment parameters under different leakage simulation conditions, the failure status data of the treatment equipment, the preset position corresponding to each leakage monitoring sensor model and the collected gas concentration sequence, the preset treatment measure prediction model is trained to obtain the target treatment measure prediction model.

7. An indoor hydrogen-blended natural gas leakage monitoring and disposal system, characterized in that: include: Monitoring module, prediction module and disposal module; The monitoring module is used to: when the gas concentration value in the target indoor area is monitored to be greater than the corresponding preset value at the target time, obtain the gas concentration sequence of the target indoor area in the first time period and the failure state data of the disposal equipment set in the target indoor area in the first time period; wherein the starting time of the first time period is the target time; the gas concentration value is: hydrogen concentration value or methane concentration value; The prediction module is used to obtain, based on the gas concentration sequence and the acquisition position of the gas concentration sequence of the target indoor area in the first time period, and the failure state data of the disposal equipment in the first time period, and by using the target disposal measure prediction model, the first disposal measure parameter corresponding to the first time period and the failure state prediction data of the disposal equipment in the second time period; wherein the second time period is located after the first time period; The treatment module is used to: obtain the target treatment measure parameters corresponding to the first time period and determine the target treatment equipment corresponding to the target treatment measure parameters based on the first treatment measure parameters corresponding to the first time period and the failure state prediction data of the treatment equipment in the second time period, and control the target treatment equipment to perform treatment according to the target treatment measure parameters corresponding to the first time period.

8. The indoor hydrogen-blended natural gas leakage monitoring and disposal system according to claim 7, characterized in that: At least one leakage monitoring sensor is arranged in the target indoor area, and each leakage monitoring sensor obtains the gas concentration value at the corresponding collection position; any leakage monitoring sensor is: a methane concentration sensor or a hydrogen concentration sensor; When any leakage monitoring sensor is a methane concentration sensor, the leakage monitoring sensor obtains the methane concentration value at the collection position; when any leakage monitoring sensor is a hydrogen concentration sensor, the leakage monitoring sensor obtains the hydrogen concentration value at the collection position.

9. An electronic device, characterized in that: The electronic device includes a processor, the processor is coupled to a memory, at least one computer program is stored in the memory, and the at least one computer program is loaded and executed by the processor so that the electronic device implements the indoor hydrogen-blended natural gas leakage monitoring and disposal method as described in any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores at least one computer program, and the at least one computer program is loaded and executed by the processor so that the computer-readable storage medium implements the indoor hydrogen-blended natural gas leakage monitoring and disposal method as described in any one of claims 1 to 6.

Images