Real-time online monitoring and early warning equipment, method and system for methane gas concentration and medium

Abstract

The invention provides a methane gas concentration real-time online monitoring and early warning device, method, system and medium, the method comprises the following steps: acquiring environmental data, the environmental data comprising a methane concentration apparent value and other sensor data; performing data conversion on the methane concentration apparent value to obtain a methane concentration true value; inputting a methane concentration true value and other sensor data into the trained prediction model for prediction to obtain a prediction result; and performing threshold judgment based on the prediction result to output an early warning signal, wherein the early warning signal comprises a first-level early warning, a second-level early warning and a third-level early warning. The real value of the methane concentration is determined through the conversion coefficient, the abnormal change of the methane concentration can be effectively sensed in advance in combination with the prediction model, the accuracy and timeliness of early warning are improved, meanwhile, the real-time online monitoring and early warning equipment has the characteristics of high protection, high sensitivity, low energy consumption and the like, and the method is suitable for large-scale municipal drainage pipeline network deployment. And municipal public safety is guaranteed.

Description

Technical Field

[0001] The present invention belongs to the technical field of environmental monitoring and urban public safety, and in particular relates to a real-time online monitoring and early warning device, method, system and medium for methane gas concentration. Background Art

[0002] With the continuous acceleration of urbanization, the discharge of municipal sewage continues to grow. During the long-term operation of municipal sewage pipes, due to the decomposition of organic matter, hydraulic disturbance and anaerobic fermentation of microorganisms, combustible gases mainly composed of CH4 are easily accumulated in local spaces inside the pipes. When the methane concentration reaches the explosion limit (5% to 15%), it is very easy to cause an explosion accident, which seriously threatens public safety and the lives of workers.

[0003] Currently, methane gas leakage or accumulation in municipal drainage pipes is the main factor leading to explosion accidents. Among them, traditional methane detection methods mostly rely on single-point alarms, which have delayed responses and untimely warnings. Most existing equipment fails to combine real-time trend predictions for intelligent warnings, and equipment deployment and maintenance are complex.

[0004] Existing technologies are limited to data monitoring of combustible gases, lacking targeted monitoring of methane gas and related generation trend prediction, and the environmental parameters are relatively simple. Some studies focus on real-time monitoring of harmful gas concentrations in municipal sewage pipes, which lacks specificity and has weak ability to perceive the generation patterns and concentration change trends of monitored gases in advance, and lacks an effective time series prediction mechanism.

[0005] At the same time, in the complex and changeable hydraulic conditions and pipeline environment of municipal sewage pipes, the generation process of methane gas is affected by the coupling of multiple environmental parameters (such as temperature, humidity, water level, wind speed, etc.). How to monitor and warn of methane concentration based on multiple environmental parameters has become a research direction and needs to be solved urgently. Summary of the Invention

[0006] In view of the shortcomings of the prior art described above, the purpose of the present invention is to provide a real-time online monitoring and early warning device, method, system and medium for methane gas concentration, which is used to solve the problem of real-time monitoring and early warning of methane concentration in municipal drainage pipes in the above-mentioned prior art.

[0007] In a first aspect, the present invention provides a real-time online monitoring and early warning device for methane gas concentration, comprising: The device body is equipped with a sensor group, a controller and a power supply, wherein: The sensor group includes a methane sensor, a temperature and humidity sensor, a liquid level sensor, and a wind speed sensor, which are used to collect environmental data in the pipeline; The controller includes a processing unit and a communication unit, wherein the processing unit is used to receive environmental data and process it to generate an early warning signal, and the communication unit is used to communicate the early warning signal to the outside; The power supply includes a power supply, a power supply compartment and a power connection line, and the power supply is used to supply power to the sensor group and the controller.

[0008] In a possible implementation of the present application, the equipment body is placed on a support plate and is limited by at least two fixed plates, wherein the support plate and the fixed plate are both fixed to a fixed rod through a fixed ring, and the fixed rod is fixedly connected to the well ring of the pipeline inspection well, wherein the material of the support plate, the fixed plate and the fixed rod includes metal.

[0009] In a possible implementation of the present application, the device body includes a box having an openable and closable lid, and a handle is installed on one side of the box, wherein the material of the box includes engineering plastic.

[0010] In a second aspect, the present invention provides a real-time online monitoring and early warning method for methane gas concentration, which is applied to any of the real-time online monitoring and early warning devices for methane gas concentration described above, wherein the method comprises: Acquiring environmental data, including apparent methane concentration values and other sensor data; Performing data conversion on the apparent value of methane concentration to obtain the true value of methane concentration; Based on the actual value of the methane concentration and the other sensor data, the data is input into the trained prediction model to perform prediction to obtain a prediction result; A threshold value judgment is performed based on the prediction result to output an early warning signal, and the early warning signal includes a first-level early warning, a second-level early warning and a third-level early warning.

[0011] In a possible implementation of the present application, converting the apparent value of the methane concentration into a true value of the methane concentration specifically includes: Generate an experimental matrix, wherein the experimental matrix includes numerical factors and categorical factors; Perform response surface analysis based on different factors in the experimental matrix to obtain conversion coefficients; The apparent value of the methane concentration is multiplied by the conversion coefficient to complete data conversion to obtain the true value of the methane concentration.

[0012] In one possible implementation of the present application, the training process of the prediction model includes: Acquire historical data and perform data preprocessing to obtain training samples, and divide the training samples into a training set and a validation set according to a preset ratio; The initial LSTM network model is trained based on the training set, and the validation set is used to verify the results of each training. The training phase also includes a gradient clipping mechanism. A root mean square error evaluation is performed on the predicted concentration value sequence and the actual methane concentration in the validation set to complete model training and obtain the prediction model.

[0013] In a possible implementation of the present application, the threshold value judgment is performed based on the prediction result to output a warning signal, and the warning signal includes a first-level warning, a second-level warning, and a third-level warning, specifically including: Obtaining a preset concentration threshold, where the preset concentration threshold includes a first threshold range, a second threshold range, and a third threshold range; The methane concentration value is compared based on the prediction result and the preset concentration threshold, wherein: If the methane concentration value of the predicted result is within the first threshold range, a first-level warning is output, including a yellow warning signal; If the methane concentration value of the predicted result is within the second threshold range, a second-level warning is output, including an orange warning signal; If the methane concentration value of the prediction result is within the third threshold range, a third-level warning is output, including a red reminder signal.

[0014] In a third aspect, the present invention provides a real-time online monitoring and early warning system for methane gas concentration, the system comprising: An acquisition module, configured to acquire environmental data, including an apparent value of methane concentration and other sensor data; A conversion module, configured to convert the apparent value of methane concentration into a true value of methane concentration; A prediction module, configured to input the actual value of the methane concentration and the other sensor data into a trained prediction model to perform prediction and obtain a prediction result; The output module is used to perform threshold judgment based on the prediction result to output an early warning signal, and the early warning signal includes a first-level early warning, a second-level early warning and a third-level early warning.

[0015] In a fourth aspect, the present invention provides an electronic device, comprising: a processor and a memory; The memory is used to store computer programs; The processor is used to execute the computer program stored in the memory, so that the electronic device executes the above-mentioned real-time online monitoring and early warning method for methane gas concentration.

[0016] In a fifth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by an electronic device, implements the above-mentioned real-time online monitoring and early warning method for methane gas concentration.

[0017] As described above, the real-time online monitoring and early warning equipment, method, system and medium for methane gas concentration described in the present invention can continuously perform real-time monitoring, integrate multi-parameter correction, trend prediction and intelligent response of methane gas monitoring and early warning, introduce multiple environmental parameter variables to correct experimental data, effectively improve the accuracy of the true value of methane, and combined with the prediction model, can effectively perceive abnormal changes in methane concentration in advance, improve the accuracy and timeliness of early warning, and at the same time, the real-time online monitoring and early warning equipment has the characteristics of high protection, high sensitivity, low energy consumption, etc., which is suitable for large-scale municipal drainage pipeline network deployment to ensure municipal public safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 Shown is a schematic structural diagram of a real-time online monitoring and early warning device for methane gas concentration according to an embodiment of the present invention; Figure 2 Shown is a schematic diagram of the installation of a real-time online monitoring and early warning device for methane gas concentration according to one embodiment of the present invention; Figure 3 Shown is a schematic diagram of the steps of an embodiment of the real-time online monitoring and early warning method for methane gas concentration of the present invention; Figure 4 Shown is a flow chart of a method for real-time online monitoring and early warning of methane gas concentration according to one embodiment of the present invention; Figure 5 Shown is a schematic diagram of the process of outputting a warning signal in an embodiment of the real-time online monitoring and warning method for methane gas concentration of the present invention; Figure 6 Shown is a structural schematic diagram of a real-time online monitoring and early warning system for methane gas concentration in one embodiment of the present invention; Figure 7 FIG. 1 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.

[0019] Component number description 12 Equipment body 121 handle 122 Openable lid 13 Methane Sensor 131 Methane sensor chamber 14 Temperature and humidity sensors 141 Temperature and humidity sensor probe 15 Liquid level sensor 151 Ultrasonic Transmitter Probe 16 Wind speed sensor 161 Wind speed sensor components 17 Power supply compartment 18 Controller 19 Power cable 20 Well Circle 21 Manhole Cover 22 Fixing rod 23 fixing ring 24 Fixed plate 25 support plate DETAILED DESCRIPTION

[0020] The following describes the embodiments of the present invention through specific examples. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments. The details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments can be combined with each other unless they conflict.

[0021] It should be noted that the illustrations provided in the following embodiments are merely schematic illustrations of the basic concept of the present invention. Therefore, the illustrations only show components related to the present invention and are not drawn according to the number, shape, and size of components in actual implementation. In actual implementation, the type, quantity, and proportion of each component may be changed arbitrarily, and the component layout may also be more complex.

[0022] In addition, the descriptions of "first", "second", etc. in this application are for descriptive purposes only and should not be understood as indicating or implying their relative importance or implicitly indicating the number of the technical features indicated. Therefore, the features defined as "first" or "second" may explicitly or implicitly include at least one of such features. In addition, the technical solutions between the various embodiments can be combined with each other, but this must be based on the fact that they can be implemented by ordinary technicians in this field. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0023] Specifically, the invention patent (authorization publication number: CN118038642B) discloses a digital gas parameter early warning system and method for mining based on gas analysis. The invention patent (authorization publication number: CN115019482B) discloses a dangerous gas patrol early warning method and device based on big data. The invention patent (authorization publication number: CN111311882B) discloses a leaked gas information feedback and alarm prompt early warning device that integrates data transmission with the Internet of Things. However, these patents are limited to data monitoring of combustible gases, lacking targeted monitoring of methane gas and related generation trend prediction, and their environmental parameters are relatively simple. Meng Qinglong et al. (2022) focused on real-time monitoring of harmful gas concentrations in municipal sewage pipelines, lacking specificity, and had limited ability to perceive the generation patterns and concentration trends of the monitored gases in advance, lacking an effective time series prediction mechanism.

[0024] The present application proposes a real-time online monitoring and early warning device, method, system and medium for methane gas concentration, which can be applied to municipal drainage pipes. The real-time online monitoring and early warning device is used to output the apparent value data of methane gas concentration obtained by real-time monitoring of the sensor group through the conversion coefficient determined by response surface analysis as the true value of methane concentration, and is combined with other sensor data to input into a trained long-short-term memory network prediction model to obtain a prediction result, so that real-time early warning can be carried out based on the prediction result, and the threshold distribution judgment is specifically performed to output the corresponding early warning signal, helping municipal management personnel to respond and take measures in the first time.

[0025] Specifically, the technical solutions in the embodiments of the present invention will be described in detail below with reference to the accompanying drawings in the embodiments of the present invention.

[0026] like Figure 1 As shown, in one embodiment of the invention, the real-time online monitoring and early warning device for methane gas concentration of the present invention includes: The device body is equipped with a sensor group, a controller and a power supply, wherein: The sensor group includes a methane sensor, a temperature and humidity sensor, a liquid level sensor, and a wind speed sensor, which are used to collect environmental data in the pipeline; The controller includes a processing unit and a communication unit, wherein the processing unit is used to receive environmental data and process it to generate an early warning signal, and the communication unit is used to communicate the early warning signal to the outside; The power supply includes a power supply, a power supply compartment and a power connection line, and the power supply is used to supply power to the sensor group and the controller.

[0027] It should be noted that, in this embodiment, Figure 1As shown, it is a structural schematic diagram of a real-time online monitoring and early warning device, which can be applied to municipal drainage pipes for real-time online monitoring and early warning of methane gas concentration, and can also be applied to other embodiments, such as safety management of underground sewage pipe networks, inspection wells, combined sewer pipes and other areas. Furthermore, the current real-time online monitoring and early warning device specifically includes a device body 12, a sensor group (not shown), a controller 18 and a power supply (not shown). The device body 12 includes a box with an openable and closable lid 122, and a handle 121 is installed on one side of the box. The material of the box includes engineering plastics, such as ABS plastic and polycarbonate, with a protection grade of IP68, which is suitable for humid and highly corrosive environments. When actually laid out, it is laid out at four-fifths of the vertical height of the inspection well of the municipal drainage pipe from the bottom to the top to meet the requirements of ("Gas Detection Standard for Drainage Facilities" CJ / T 307-2009).

[0028] Furthermore, in this embodiment, the sensor group includes a methane sensor 13, a temperature and humidity sensor 14, a liquid level sensor 15 and a wind speed sensor 16. Figure 1 As shown, the methane sensor 13 corresponds to a methane sensor chamber 131, the temperature and humidity sensor 14 corresponds to a temperature and humidity sensor probe 141, the liquid level sensor 15 corresponds to an ultrasonic transmitting probe 151, and the wind speed sensor 16 corresponds to a wind speed sensing component 161; specifically, the methane gas sensor supports NB-IoT communication and an I²C interface, and adopts the non-dispersive infrared (NDIR) principle to periodically detect the apparent concentration of gaseous methane in the drainage pipe every three hours. The temperature and humidity sensor 14 adopts a digital temperature and humidity sensor 14, supports NB-IoT communication and an I²C interface, has a high-precision, corrosion-resistant package, and is suitable for high-humidity and harsh environments. The ultrasonic wind speed sensor 16 is used to monitor the ventilation conditions of the pipeline, supports NB-IoT communication and an I²C interface, has a protection level of IP68, and can also work for a long time in a high-humidity environment in the pipeline. Furthermore, in this embodiment, the controller 18 includes a microcontroller unit that integrates a processing unit and a communication unit, wherein the processing unit is used to receive environmental data and process it to generate an early warning signal, and the communication unit is used to communicate the early warning signal to the outside. Specifically, the processing unit uses an STM32L series MCU (Microcontroller Unit) to read sensor data and complete data analysis and processing steps, including converting the apparent value of methane concentration into the actual value of methane concentration, mobilizing the trained prediction model to perform data prediction, and determining the execution of the early warning response step to generate an early warning signal based on the prediction result. The communication unit uses NB-IoT communication to transmit the processed early warning signal to the background management center.

[0029] Furthermore, in this embodiment, the power supply includes a power supply, a power supply compartment 17 and a power connection line 19. The power supply is used to supply power to the sensor group and the controller 18. The power supply adopts multiple ER14505 lithium batteries connected in series, or other power supply batteries, without limitation. Accordingly, the power supply compartment 17 is used to place multiple power supply lithium batteries, and the power connection line 19 is used to connect the power supply compartment 17 and the batteries in series, as well as to connect the power supply and different sensors and the controller 18 for power supply.

[0030] Furthermore, in one embodiment of the invention, the equipment body 12 is placed on a support plate 25 and is limited by at least two fixed plates 24, wherein the support plate 25 and the fixed plate 24 are both fixed to the fixed rod 22 through a fixed ring 23, and the fixed rod 22 is fixedly connected to the well ring 20 of the pipeline inspection well, wherein the material of the support plate 25, the fixed plate 24 and the fixed rod 22 includes metal.

[0031] It should be noted that, in this embodiment, Figure 2 As shown in the figure, it shows the installation and application diagram of the real-time online monitoring and early warning equipment, wherein the real-time online monitoring and early warning equipment is installed in the municipal drainage pipe for monitoring and early warning, as shown in the figure. Figure 2 As shown, a fixing rod 22 is fixedly connected to the manhole ring 20 of the pipeline inspection manhole, for example, by a threaded fixed connection. Accordingly, in actual application, a manhole cover 21 is also included on the manhole ring 20. Furthermore, two fixing rings 23 are fixedly connected to one end of the fixing rod 22 away from the manhole cover 21, wherein one fixing ring 23 is fixedly connected to a support plate 25, and the other fixing ring 23 is fixedly connected to several fixing plates 24, wherein the equipment body 12 is placed on the support plate 25, and is limited by at least two fixing plates 24, so that the real-time online monitoring and early warning equipment can stably monitor and warn the methane concentration in the municipal drainage pipe, wherein the material of the support plate 25, the fixing plate 24 and the fixing rod 22 includes metal, and the surface has an anti-corrosion layer. On the premise of playing a supporting role, it can be suitable for humid and highly corrosive environments.

[0032] like Figure 3 As shown, in one embodiment of the invention, the real-time online monitoring and early warning method of methane gas concentration of the present invention is applied to any of the real-time online monitoring and early warning devices of methane gas concentration, wherein the method comprises the following steps: Step S302, obtaining environmental data, wherein the environmental data includes an apparent value of methane concentration and other sensor data; Step S304, performing data conversion on the apparent value of methane concentration to obtain the true value of methane concentration; Step S306: inputting the actual value of the methane concentration and the other sensor data into the trained prediction model to perform prediction and obtain a prediction result; Step S308: Perform threshold judgment based on the prediction result to output a warning signal, wherein the warning signal includes a first-level warning, a second-level warning, and a third-level warning.

[0033] It should be noted that in this embodiment, when applied to the application scenario of municipal drainage pipes, environmental data is first obtained through a sensor group of real-time online monitoring and early warning equipment set in the pipe, including the apparent value of methane concentration and other sensor data, among which other sensor data include, for example, temperature data, humidity data, water level data and wind speed data.

[0034] Furthermore, in this embodiment, the apparent value of the methane concentration of the methane gas obtained by real-time monitoring is converted into the true value of the methane concentration through the conversion coefficient determined by response surface analysis. The specific response surface analysis process will be described in detail in the subsequent instructions. Then, based on the true value of the methane concentration and the other sensor data, they are input into the trained prediction model to perform prediction to obtain the prediction result. Accordingly, a deep learning neural network model is constructed based on the historical monitoring data of the sensor equipment and the experimental environment data to train the trained prediction model. The specific training process will also be described in detail in the subsequent instructions.

[0035] Furthermore, in this embodiment, the prediction results of the methane gas concentration prediction are combined with the set threshold to determine whether to issue an early warning. The early warning signals corresponding to different threshold ranges are different, specifically including level one early warning, level two early warning and level three early warning. Among them, by establishing an intelligent and automated multi-level early warning response mechanism, the accuracy and efficiency of the monitoring and early warning of dangerous gases in municipal drainage pipelines can be achieved, filling the gap in the field of early warning of dangerous gases in municipal drainage pipelines.

[0036] Furthermore, in one embodiment of the invention, converting the apparent value of the methane concentration into a true value of the methane concentration specifically includes: Generate an experimental matrix, wherein the experimental matrix includes numerical factors and categorical factors; Perform response surface analysis based on different factors in the experimental matrix to obtain conversion coefficients; The apparent value of the methane concentration is multiplied by the conversion coefficient to complete data conversion to obtain the true value of the methane concentration.

[0037] It should be noted that, in this embodiment, the functional relationship between the actual value of methane concentration and the apparent value of methane concentration is: ,in, Indicates the true value of methane concentration in mg / L. It represents the apparent value of methane concentration in mg / L. The K value is the conversion coefficient between the true value of methane concentration and the apparent value of methane concentration.

[0038] Furthermore, specifically, the custom combination design (CustomDesign) method was used in Design Expert 13 software to generate an experimental matrix, in which the factors and levels were set as numerical factors: temperature (15°C, 25°C, 35°C), humidity (70%, 80%, 90%), and wind speed (0.1 m / s, 0.3 m / s, 0.5 m / s); the categorical factors were: water level (high water level > 10 cm was coded as 1, low water level ≤ 10 cm was coded as 0). After the experimental matrix was generated, the experimental data were input, and the response variable was set as the ratio of the true value of methane to the apparent value of methane. Response surface methodology (RSM) analysis was performed in the software, and the built-in variance analysis tool of the software was used to perform a statistical significance test on the model. Combined with the determination coefficient R 2 The indicator evaluates the goodness of fit of the model and further confirms the validity of the model. After confirmation, the function expression is output through "equation", where the regular expression is: , is the response variable, which corresponds to the conversion coefficient K in this embodiment. It is Impact factors; are the model coefficients; It is the experimental error. After the conversion coefficient is obtained by performing response surface analysis based on different factors in the experimental matrix, the apparent value of the methane concentration is multiplied by the conversion coefficient to complete the data conversion to obtain the true value of the methane concentration.

[0039] Furthermore, in one embodiment of the invention, the training process of the prediction model includes: Acquire historical data and perform data preprocessing to obtain training samples, and divide the training samples into a training set and a validation set according to a preset ratio; The initial LSTM network model is trained based on the training set, and the validation set is used to verify the results of each training. The training phase also includes a gradient clipping mechanism. A root mean square error evaluation is performed on the predicted concentration value sequence and the actual methane concentration in the validation set to complete model training and obtain the prediction model.

[0040] It should be noted that, in this embodiment, Figure 4As shown, historical data is obtained and preprocessed to obtain training samples. In practical applications, real-time monitoring data also needs to be preprocessed. Furthermore, in this embodiment, data preprocessing specifically involves data cleaning, outlier identification, and smoothing of the actual methane concentration and other sensor data (such as temperature, humidity, wind speed, and water level environmental parameter data) to ensure the quality of input data and the stability of model prediction results. The process specifically includes: (1) Data alignment: All types of monitoring data are aligned according to a unified time base to ensure that the apparent value of methane concentration corresponds to the environmental parameters at each sampling time; (2) Data cleaning: For abnormal change values in the monitoring data, a multi-stage cleaning strategy is used to process them, including common outliers and extreme outliers. Common outliers: For abnormal change values in the monitoring data, a multi-stage cleaning strategy is used to process them, that is, to filter out physically unacceptable outliers, such as negative methane concentration and water level exceeding the structural limit of the drainage pipe; and extreme outliers: To identify extreme outliers in terms of statistical data validity (extreme anomalies in sensor data) for cleaning, the Z-score method and the interquartile range (IQR) method are introduced for processing. Specifically, (a) For variable data (temperature, humidity) that approximately obey the normal distribution, the Z-score standardization coefficient is used for judgment, where the Z-score is defined as: ,in, is the sample value; μ is the mean of the data set; is the standard deviation of the data set; Indicates the distance between the sample value and the mean (in standard deviation). , indicating that the sample deviates from the mean by more than "3" standard deviations and is considered an outlier; for non-normally distributed or skewed data (such as wind speed, water level, and methane concentration), the IQR upper and lower limit rules are used to identify abnormal fluctuations, that is, and x is considered an outlier when , Q1 is the lower quartile of the data set, Q3 is the upper quartile of the data set, and IQR is the interquartile range, which represents the middle "50%" range of the data set.

[0041] (3) Data smoothing: Specifically, the cleaned outliers are set as missing and the data is smoothed by linear interpolation. The linear interpolation formula is: , where is the current abnormal point; is the previous normal value; is the next normal value; i is the current abnormal index; is the index of the previous normal point; The index of the next normal point.

[0042] Furthermore, in this embodiment, the time series sample construction uses historical monitoring data within "3" months, imports the data into the library, and uses Python 3.9 software to use the sliding window mechanism to construct the input sample of the LSTM (Long Short-Term Memory) model according to the time series output data of step 2. The continuous environmental parameter data is subjected to a sliding window construction sample based on the time window length, that is, the time step T. The time window length T selects ten time steps, each time step corresponds to a sampling every three hours, and each sample corresponds to the monitoring data of the past "30" hours. Therefore, the environmental parameter data and methane concentration data of each T consecutive time steps are used as input features, and the methane concentration value corresponding to the T+1 time is used as the label output to construct the time series training sample.

[0043] Furthermore, in this embodiment, based on the constructed training samples, the first "80%" of the data set is divided into a training set, and the last "20%" is divided into a validation set, and an LSTM sequence prediction model is established, wherein the model structure includes at least one LSTM layer and an output fully connected layer, wherein the LSTM layer contains four core structures: a forget gate, an input gate, an output gate, and a memory unit. The forget gate is used to judge and control whether the current moment retains the memory state of the previous moment. The formula is: ,in, represents the output of the forget gate, is the hidden state at the previous moment, is the current input eigenvalue, is the weight matrix, is the bias term, Represents the Sigmoid activation function; the input gate determines the degree of influence of the new input information on the current memory state at the current moment, including the input gate control amount: and candidate memory states: , where is the input gate output, For candidate status, is the weight matrix, is the bias term, is a hyperbolic tangent function, which completes the nonlinear fitting of the memory state; the memory unit integrates the information update state controlled by the forget gate and the input gate, and the expression is: , where is the memory state at time t; the output gate outputs the current state, expressed as: , ,in, is the output gate output, The final hidden state. During the training process, the model automatically learns the time dependency and parameter coupling effect in the input sequence, processes the time dependency of the sequence data, and the fully connected layer is used to convert the LSTM output features into Mapped to the predicted value of methane concentration; the model uses mean square error (MSE) as the loss function, , where is the true methane concentration value at the i-th time point; is the predicted methane concentration value of the LSTM model at the i-th time point; n is the number of evaluation samples; the Adam adaptive gradient optimizer is used for parameter learning; during the training process, a validation set is introduced for model fitting and verification, and an early stopping strategy is used to avoid overfitting. If the validation error does not decrease for several consecutive rounds, training is stopped early.

[0044] Furthermore, in this embodiment, the training phase also includes a gradient clipping mechanism. That is, a gradient clipping mechanism is introduced during the LSTM model training phase. When the gradient value exceeds a set threshold (5.0) during the model backpropagation process, the gradient size is automatically limited to prevent the gradient explosion phenomenon caused by differences in different input dimensions, thereby overcoming the problem of data errors caused by the lack of normalization.

[0045] Furthermore, in this embodiment, the root mean square error evaluation is performed on the predicted concentration value sequence and the true methane concentration in the validation set to complete the model training and obtain the prediction model. That is, the trained LSTM model is used to predict the corresponding input features in the validation set to obtain a predicted concentration value sequence, which corresponds to the true methane concentration in the validation set and is evaluated by RMSE, wherein, , where is the true methane concentration value at the i-th time point; is the predicted methane concentration value of the LSTM model corresponding to the i-th time point; n is the number of evaluation samples.

[0046] Furthermore, in one embodiment of the invention, a threshold value judgment is performed based on the prediction result to output a warning signal, and the warning signal includes a first-level warning, a second-level warning, and a third-level warning, specifically including: Obtaining a preset concentration threshold, where the preset concentration threshold includes a first threshold range, a second threshold range, and a third threshold range; The methane concentration value is compared based on the prediction result and the preset concentration threshold, wherein: If the methane concentration value of the predicted result is within the first threshold range, a first-level warning is output, including a yellow warning signal; If the methane concentration value of the predicted result is within the second threshold range, a second-level warning is output, including an orange warning signal; If the methane concentration value of the prediction result is within the third threshold range, a third-level warning is output, including a red reminder signal.

[0047] It should be noted that, in this embodiment, the latest T-step environmental parameters acquired in real time are input into the trained prediction model to predict the methane concentration at time T+1, and rolling predictions are continuously performed and the prediction sequence is recorded. If the methane concentration value in the prediction result exceeds the methane safety concentration threshold (10,000 ppm), the trend warning response mechanism is triggered, and then the alarm device or control equipment is linked to intervene. Among them, the prediction model adopts a rolling prediction mechanism, which updates the input window according to the latest data every "3" hours and recalculates the future concentration, forming a continuous prediction capability.

[0048] Furthermore, in this embodiment, Figure 5 As shown, it is a flow chart of outputting warning signals, wherein the prediction result is compared with the preset concentration threshold, and risk grading is performed according to the distribution of the prediction result in different threshold ranges. If the methane concentration value of the prediction result is within the first threshold range, specifically between "10,000 and 15,000 ppm (excluding 15,000 ppm)", a first-level warning is output, including a yellow reminder signal, thereby sending a yellow reminder signal to the backend management center, suggesting manual review; if the methane concentration value of the prediction result is within the second threshold range, specifically between "15,000 and 18,000 ppm (excluding 18,000 ppm)", a second-level warning is output, including an orange alarm signal, thereby sending an orange alarm signal to the backend management center; if the methane concentration value of the prediction result is within the third threshold range, specifically between "18,000 and 20,000 ppm", a third-level warning is output, including a red reminder signal, thereby sending a red alarm signal to the backend management center, reminding management personnel to respond in time.

[0049] See also Figure 6 In one embodiment, this embodiment provides a real-time online monitoring and early warning system 60 for methane gas concentration, the system comprising: An acquisition module 61 is configured to acquire environmental data, including an apparent value of methane concentration and other sensor data; A conversion module 62 is configured to convert the apparent value of the methane concentration into a true value of the methane concentration; A prediction module 63 is configured to input the actual value of the methane concentration and the other sensor data into a trained prediction model to perform prediction and obtain a prediction result; The output module 64 is used to perform threshold judgment based on the prediction result to output a warning signal, and the warning signal includes a first-level warning, a second-level warning and a third-level warning.

[0050] Since the specific implementation of this embodiment corresponds to the aforementioned method embodiment, the same details will not be repeated here, and those skilled in the art should also understand that Figure 6 The division of the various modules in the embodiment is merely a division of logical functions. In actual implementation, all or part of the modules can be integrated into one or more physical entities, and all of these modules can be implemented in the form of software called by processing elements, or all of them can be implemented in the form of hardware. Some modules can also be implemented in the form of software called by processing elements, and some modules can be implemented in the form of hardware.

[0051] In the several embodiments provided by the present invention, it should be understood that the disclosed devices or methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of modules / units is only a logical function division. In actual implementation, there may be other division methods, such as multiple modules or units can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules or units, which can be electrical, mechanical or other forms.

[0052] Modules / units described as separate components may or may not be physically separate, and components displayed as modules / units may or may not be physical modules, that is, they may be located in one place or distributed across multiple network elements. Some or all of the modules / units may be selected based on actual needs to achieve the objectives of the embodiments of the present invention. For example, the functional modules / units in various embodiments of the present invention may be integrated into a single processing module, each module / unit may exist physically separately, or two or more modules / units may be integrated into a single module / unit.

[0053] Those skilled in the art should further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the composition and steps of each example according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0054] The embodiment of the present invention further provides an electronic device, such as Figure 7 As shown, the electronic device includes a processor and a memory.

[0055] The memory is used to store computer programs.

[0056] The processor is configured to execute the computer program stored in the memory, so as to enable the electronic device to perform any of the above methods.

[0057] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices or methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of modules / units is only a logical function division. There may be other division methods in actual implementation. For example, multiple modules or units can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules or units, which can be electrical, mechanical or other forms.

[0058] The modules / units described as separate components may or may not be physically separate, and the components displayed as modules / units may or may not be physical modules, that is, they may be located in one place or distributed across multiple network elements. Some or all of the modules / units may be selected according to actual needs to achieve the purpose of the embodiments of the present application. For example, the functional modules / units in the various embodiments of the present application may be integrated into a processing module, or each module / unit may exist physically separately, or two or more modules / units may be integrated into a single module / unit.

[0059] Those skilled in the art should further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the composition and steps of each example according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0060] The present application also provides a computer-readable storage medium. Those skilled in the art will appreciate that all or part of the steps in the methods of the above embodiments can be performed by instructing a processor through a program. The program can be stored in a computer-readable storage medium, which is a non-transitory medium, such as random access memory, read-only memory, flash memory, a hard disk, a solid-state drive, magnetic tape, a floppy disk, an optical disc, or any combination thereof. The storage medium can be any available medium accessible by a computer, or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a digital video disc (DVD)), or a semiconductor medium (e.g., a solid-state drive (SSD)).

[0061] The embodiments of the present application may also provide a computer program product, which includes one or more computer instructions. When the computer instructions are loaded and executed on a computing device, the process or function described in the embodiments of the present application is generated in whole or in part. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, or data center to another website, computer, or data center via wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means.

[0062] When the computer program product is executed by a computer, the computer executes the method described in the above method embodiment. The computer program product can be a software installation package. When the above method is needed, the computer program product can be downloaded and executed on the computer.

[0063] The descriptions of the processes or structures corresponding to the above figures have different emphases. For parts that are not described in detail in a certain process or structure, please refer to the relevant descriptions of other processes or structures.

[0064] The above embodiments are merely illustrative of the principles and effects of this application and are not intended to limit this application. Anyone skilled in the art may modify or alter the above embodiments without departing from the spirit and scope of this application. Therefore, all equivalent modifications or alterations made by one of ordinary skill in the art without departing from the spirit and technical concepts disclosed in this application shall be covered by the claims of this application.

Claims

1. A real-time online monitoring and early warning device for methane gas concentration, characterized in that: include: The device body is equipped with a sensor group, a controller and a power supply, wherein: The sensor group includes a methane sensor, a temperature and humidity sensor, a liquid level sensor, and a wind speed sensor, which are used to collect environmental data in the pipeline; The controller includes a processing unit and a communication unit, wherein the processing unit is used to receive environmental data and process it to generate an early warning signal, and the communication unit is used to communicate the early warning signal to the outside; The power supply includes a power supply, a power supply compartment and a power connection line, and the power supply is used to supply power to the sensor group and the controller.

2. The real-time online monitoring and early warning device for methane gas concentration according to claim 1 is characterized in that: The equipment body is placed on a support plate and is limited by at least two fixed plates, wherein the support plate and the fixed plate are both fixed to a fixed rod through a fixed ring, and the fixed rod is fixedly connected to the well ring of the pipeline inspection well, wherein the material of the support plate, the fixed plate and the fixed rod includes metal.

3. The real-time online monitoring and early warning device for methane gas concentration according to claim 1 is characterized in that: The device body includes a box body with an openable and closable lid, and a handle is installed on one side of the box body, wherein the material of the box body includes engineering plastic.

4. A real-time online monitoring and early warning method for methane gas concentration, characterized in that: The method for the real-time online monitoring and early warning device for methane gas concentration according to any one of claims 1 to 3 comprises the following steps: Acquiring environmental data, including apparent methane concentration values and other sensor data; Performing data conversion on the apparent value of methane concentration to obtain the true value of methane concentration; Based on the actual value of the methane concentration and the other sensor data, the data is input into the trained prediction model to perform prediction to obtain a prediction result; A threshold value judgment is performed based on the prediction result to output an early warning signal, and the early warning signal includes a first-level early warning, a second-level early warning and a third-level early warning.

5. The method for real-time online monitoring and early warning of methane gas concentration according to claim 4 is characterized in that: The data conversion of the methane concentration apparent value to obtain the methane concentration true value specifically includes: Generate an experimental matrix, wherein the experimental matrix includes numerical factors and categorical factors; Perform response surface analysis based on different factors in the experimental matrix to obtain conversion coefficients; The apparent value of the methane concentration is multiplied by the conversion coefficient to complete data conversion to obtain the true value of the methane concentration.

6. The method for real-time online monitoring and early warning of methane gas concentration according to claim 4, characterized in that: The training process of the prediction model includes: Acquire historical data and perform data preprocessing to obtain training samples, and divide the training samples into a training set and a validation set according to a preset ratio; The initial LSTM network model is trained based on the training set, and the validation set is used to verify the results of each training. The training phase also includes a gradient clipping mechanism. A root mean square error evaluation is performed on the predicted concentration value sequence and the actual methane concentration in the validation set to complete model training and obtain the prediction model.

7. The method for real-time online monitoring and early warning of methane gas concentration according to claim 4, characterized in that: The threshold value judgment is performed based on the prediction result to output a warning signal, and the warning signal includes a first-level warning, a second-level warning and a third-level warning, specifically including: Obtaining a preset concentration threshold, where the preset concentration threshold includes a first threshold range, a second threshold range, and a third threshold range; The methane concentration value is compared based on the prediction result and the preset concentration threshold, wherein: If the methane concentration value of the predicted result is within the first threshold range, a first-level warning is output, including a yellow warning signal; If the methane concentration value of the predicted result is within the second threshold range, a second-level warning is output, including an orange warning signal; If the methane concentration value of the prediction result is within the third threshold range, a third-level warning is output, including a red reminder signal.

8. A real-time online monitoring and early warning system for methane gas concentration, characterized in that: The real-time online monitoring and early warning device for methane gas concentration according to any one of claims 1 to 3, wherein the system comprises: An acquisition module, configured to acquire environmental data, including an apparent value of methane concentration and other sensor data; A conversion module, configured to convert the apparent value of methane concentration into a true value of methane concentration; A prediction module, configured to input the actual value of the methane concentration and the other sensor data into a trained prediction model to perform prediction and obtain a prediction result; The output module is used to perform threshold judgment based on the prediction result to output an early warning signal, and the early warning signal includes a first-level early warning, a second-level early warning and a third-level early warning.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the real-time online monitoring and early warning method for methane gas concentration described in any one of claims 4 to 7 is implemented.

10. An electronic device, characterized in that: The electronic device includes: a processor and a memory; wherein the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the electronic device executes the real-time online monitoring and early warning method for methane gas concentration as described in any one of claims 4 to 7.

Images