Gas emission monitoring system and method based on spectral analysis

Abstract

The invention discloses a gas emission monitoring system and method based on spectral analysis, and belongs to the technical field of artificial intelligence. The method comprises the following steps: starting a sampling pump, extracting a gas sample from a to-be-detected environment, removing impurities, and conveying the gas sample to a gas sample pool; generating a spectrogram, and identifying gas components and gas concentration by using the spectrogram; when a plurality of gas components are identified in the spectrogram, establishing a hazardous gas combinatorial library by using a support vector machine algorithm and a random forest algorithm; detecting the gas composition and concentration in the current environment in real time, comparing the gas composition and concentration with the dangerous reaction library, and generating an alarm signal if the detected gas combination accords with the dangerous combination and the concentration reaches or exceeds a critical value; when an alarm is triggered, specific information is displayed on a control panel, the alarm is given, emergency operation guidance is displayed, a ventilation system is automatically started or added, and an isolation device is automatically started; and after the alarm is automatically released, data are recorded, and fault conditions of corresponding equipment are analyzed.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a gas emission monitoring system and method based on spectral analysis. Background Art

[0002] With the continuous advancement of industrialization and urbanization, the problem of gas emissions generated in the industrial production process is becoming increasingly serious. These waste gases usually contain a variety of harmful components, such as sulfur dioxide, carbon monoxide, nitrogen oxides, volatile organic compounds, etc. If they are not controlled, they will not only cause irreversible pollution to the environment around the factory, but also pose a serious threat to the health of people inside the factory and nearby areas. Therefore, the application of gas emission monitoring technology in industrial production has become extremely important. Whether the emission of harmful gases can be monitored and controlled in a timely and accurate manner is directly related to environmental protection and personnel safety.

[0003] Traditional gas monitoring methods often rely on chemical reagents or simple sensors. These methods have low accuracy and sensitivity when detecting multiple gas components and are prone to errors. Many existing monitoring systems cannot achieve real-time monitoring, and there is a lag in data transmission and processing, which cannot reflect changes in gas concentration in a timely manner, resulting in potential dangers that cannot be discovered and handled in a timely manner. Existing systems usually rely on manual operation and analysis, with a low degree of automation, making it difficult to achieve continuous and stable gas monitoring and control. The manual operation process is not only time-consuming and labor-intensive, but also prone to errors in data collection and processing due to human factors. Many monitoring systems lack a complete emergency response mechanism and are unable to quickly take effective emergency measures when the concentration of dangerous gases exceeds the standard. This defect makes it difficult for the system to respond in a timely manner when faced with sudden dangers, and it is unable to effectively protect the safety of the environment and personnel. Summary of the invention

[0004] The object of the present invention is to provide a gas emission monitoring system and method based on spectral analysis to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: A gas emission monitoring method based on spectral analysis, the method comprising the following steps: S100, start the sampling pump, extract gas samples from the environment to be tested, remove impurities through the sampling pipeline and filter, and transport them to the gas sample pool. The gas flow in the sample pool is regulated by the flow controller; the gas flows through the air inlet and outlet at both ends of the sample pool, and the gas in the sample pool is evenly distributed. The light beam emitted by the light source passes through the sample pool, and the spectrometer performs spectral measurement to generate a spectrum diagram, and the spectrum diagram is used to identify the gas composition and gas concentration; S200, when the spectrum graph identifies several gas components, using the support vector machine algorithm and the random forest algorithm to establish a dangerous gas combination library, the dangerous gas combination library lists the gas combinations that may cause dangerous reactions and their critical concentrations; real-time detection of the gas components and concentrations in the current environment, and comparison with the dangerous reaction library, if the detected gas combination meets the dangerous combination and the concentration reaches or exceeds the critical value, an alarm signal is generated; S300, when the alarm is triggered, the specific dangerous gas combination, corresponding concentration information and potential hazards are displayed on the control panel, an alarm is sounded through an audible and visual alarm, emergency operation instructions are displayed, the ventilation system is automatically started or increased, and the isolation device is automatically started; S400 monitors the gas concentration in the sample pool in real time, automatically cancels the alarm when the concentration of all hazardous gases has dropped below the safety threshold, linearly adjusts the operation of the ventilation system, closes the isolation device, records detailed data of hazardous events, and uses the random forest algorithm to analyze the failure of the corresponding equipment.

[0006] According to step S100, a flow controller is installed on the air inlet pipeline of the gas sample pool or on the pipeline close to the sampling pump, and the flow controller is a mass flow controller; before the system is started, the flow controller is calibrated to set the target flow range; the flow range is determined according to the characteristics of the gas to be tested and the sample pool; When determining the flow range, it is necessary to obtain the physical properties of the gas to be tested, such as the type, density, viscosity, and diffusion coefficient. These parameters will affect the flow of the gas in the pipeline and the distribution in the sample pool. If there are highly chemically reactive components in the gas to be tested, it is necessary to consider the behavior of these components under high or low flow conditions to prevent possible chemical reactions. According to the volume of the sample pool, determine the flow range of the gas sample so that the gas can be fully distributed in the sample pool to ensure that the light source beam can accurately reflect the gas concentration when passing through the sample pool. The path length of the light source beam through the sample pool determines the detection sensitivity of the gas component. A longer optical path length requires a lower gas flow rate to ensure that the light beam has sufficient absorption and reflection in the gas. Before starting the system, calibrate the mass flow controller and set the target flow range of the flow controller, usually in the range of 0.1-10 L / min.

[0007] After starting the sampling pump, the flow controller starts working and monitors the flow of the gas sample in real time. The sensor inside the controller detects the flow signal and compares it with the set value. If the actual flow deviates from the set value, the controller automatically adjusts the valve opening or the pump speed to ensure that the flow is stable within the target range. The flow controller is equipped with a closed-loop control system to adjust the flow through real-time feedback. The monitoring interface displays the current flow value, and the operator can monitor and adjust it manually in real time.

[0008] According to step S100, a xenon lamp is selected as a light source, the spectrum of the light source covers the absorption wavelength range of the target gas, the light source is introduced into the optical path system through a collimating lens and an optical fiber to form a parallel light beam, and the gas sample pool is designed with quartz glass; the light beam enters from one end of the sample pool, passes through the gas sample, and then exits from the other end. The gas molecules have an absorption effect on light of a specific wavelength. When the light beam passes through the sample pool, the intensity and wavelength of the light beam change; The light beam entering the spectrometer is decomposed into spectra of different wavelengths by a grating or prism. The decomposed spectrum is projected onto the detector, which generates electrical signals according to the light intensity of different wavelengths. The detector converts these electrical signals into digital signals. The light intensity data of different wavelengths are plotted into a spectrum graph, which shows the absorption of each wavelength of light by the gas sample, and the gas composition and gas concentration are identified by the position and intensity of the absorption peak.

[0009] According to step S200, spectral data of historical gas samples are collected, each sample includes several gas components and their concentrations, and each sample is marked whether a dangerous reaction will occur, and the marked sample labels are: 1 for dangerous and -1 for safe; features are extracted from the spectral data, and the features include absorption peak position, absorption intensity, peak area, half-peak width, baseline shift and peak shape; The support vector machine is used to identify dangerous gas combinations. Its goal is to find a hyperplane to separate samples of different categories, including dangerous and safe. The spectral data feature vectors and corresponding labels form a first training data set, which is used for training. The objective function is defined as follows: ; Among them, w is the weight vector, which indicates the direction of the hyperplane, and b is the bias term, which indicates the displacement of the hyperplane; For each training sample, the constraints that need to be satisfied are defined as follows: ; in, is the sample label of the i-th sample, is the feature vector extracted from the spectral data of the i-th sample.

[0010] Construct the Lagrangian function through Lagrangian multipliers and solve the dual problem: ; in, is the Lagrange multiplier, used for the dual solution of the optimization problem, represents the slack variable of the constraint condition, and n is the number of training samples; Solve the Lagrangian function, take the derivative of w and b, and set the derivative to zero, and we get the dual problem: ; The constraints of the dual problem are: ; Use the gradient descent algorithm to solve the dual problem and get the optimal ; Use the best Calculate the weight vector w and bias term b as follows: ; in, are the labels of the support vectors, is the eigenvector of the support vector; The classification decision function of the trained support vector machine model is: ; in, is a classification decision function used to determine whether a gas combination is dangerous.

[0011] According to step S200, according to the hazardous gas combination obtained by the support vector machine algorithm, the spectral data of the gas samples of the corresponding hazardous gas combination are collected; the spectral data feature vectors of the gas samples of the hazardous gas combination and the critical concentration of the hazardous gas combination are combined into a second training data set, and several subsets are generated by random sampling from the second training data set, and each subset is used to train a decision tree; decision tree training is performed on each subset to establish a regression model; the feature vector of the new sample is input into each decision tree for prediction, and the average of the prediction results of all decision trees is taken as the final critical concentration prediction value.

[0012] According to step S200, for each decision tree , using a subset of the training data Conduct training, including is the spectral data feature vector of the gas sample of the dangerous gas combination, is the critical concentration of the dangerous gas combination; for the characteristic vector of the dangerous gas combination , each decision tree The prediction result is , which means the i-th decision tree is The prediction results output the critical concentration of dangerous gas combination; Random forest gives the final prediction value by combining the prediction results of all decision trees : ; in, is the number of decision trees; The dangerous gas combination library is established by combining the critical concentrations of the dangerous gas combination obtained by the support vector machine algorithm and the dangerous gas combination obtained by the decision tree algorithm.

[0013] According to step S300, the control panel will display the type of gas detected, the concentration of each gas, the danger level and the potential hazard description, and display emergency operation instructions on the control panel and the staff's mobile device; the emergency operation instructions include how to wear personal protective equipment, the specific routes and steps for evacuating personnel and the steps for starting the ventilation system; automatically start or increase the operation of the ventilation system to reduce the concentration of dangerous gases, and automatically adjust the wind speed and air volume of the ventilation system according to the gas concentration and combination; when the gas sensor detects that the concentration of dangerous gases exceeds the standard, it automatically triggers the isolation device; when a fault is found in the isolation device, an automatic isolation device fault alarm is issued, and troubleshooting instructions are provided.

[0014] The type of gas detected, the concentration of each gas, the danger level and the potential hazard description are displayed in real time on the control panel and the staff's mobile device. Specific instructions on how to wear personal protective equipment, including what type of protective clothing, masks, gloves, etc. are used. Based on the detected gas concentration and wind direction, a specific evacuation route map is displayed on the control panel, and the navigation function is used to guide personnel to evacuate safely. Detailed steps are listed, such as: shutting down work equipment, quickly evacuating to a safe area, counting the number of people, etc. The steps for starting the ventilation system are displayed on the control panel, including the location of the manual start button, the conditions for automatic start, etc.

[0015] When the gas sensor detects that the isolation device is not working properly, the system will automatically alarm and display the fault information on the control panel. Provide detailed troubleshooting instructions, such as checking the power supply, restarting the device, replacing the faulty parts, etc. Through the system's built-in fault diagnosis algorithm, automatically analyze the cause of the fault and provide corresponding maintenance suggestions.

[0016] According to step S400, the gas concentration in the sample pool is continuously monitored by the sensor, and when the concentration of all dangerous gases drops below the safety threshold, the alarm is automatically lifted; according to the real-time monitored gas concentration data, the system automatically adjusts the wind speed and air volume of the ventilation system; the automatic control system shuts down the isolation device that was previously activated and restores the normal operation of the isolated area; and automatically records the time of the dangerous event, the type of gas detected, the concentration change, and the emergency measures taken; Use the random forest algorithm to perform fault analysis. Input the preprocessed equipment operation data into the random forest model, randomly select feature subsets, build several decision trees, use the training data to build multiple decision trees, each tree is trained independently, and predict the new data. Take the average prediction result of all decision trees as the equipment's fault condition analysis data and record it into the hazardous gas combination library.

[0017] A gas emission monitoring system based on spectral analysis, comprising: Sampling and filtering module: including: gas sampling unit, gas filtering unit and flow control unit; wherein, the gas sampling unit is responsible for starting the sampling pump and extracting gas samples from the environment to be tested through the sampling probe, the gas filtering unit is responsible for controlling the gas sample to pass through the sampling pipeline and filter, remove impurities and then be transported to the gas sample pool, and the flow control unit is responsible for adjusting the flow of the gas sample through the flow controller; Spectral measurement module: including: sample pool control unit, light source control unit and spectrometer control unit; wherein, the sample pool control unit is responsible for controlling the air inlet and outlet at both ends of the sample pool to flow when the gas sample enters the sample pool, so that the gas in the sample pool is evenly distributed, the light source control unit is responsible for controlling the light beam emitted by the light source to pass through the sample pool, and the spectrometer control unit is responsible for controlling the spectrometer to perform spectral measurement, generate a spectrum graph, and use the spectrum graph to identify gas composition and gas concentration; Data analysis and alarm module: including: a dangerous gas combination library establishment unit and a real-time detection unit; wherein, the dangerous gas combination library establishment unit is responsible for establishing a dangerous gas combination library using a support vector machine algorithm and a random forest algorithm when the spectrum map identifies several gas components, and the dangerous gas combination library lists gas combinations that may cause dangerous reactions and their critical concentrations; the real-time detection unit is responsible for real-time detection of the current gas composition and concentration, and compares them with the dangerous reaction library. If a dangerous gas combination is detected and the concentration reaches a critical value, an alarm signal is generated; Emergency response module: including: display unit, notification unit and emergency control unit; among them, the display unit will display the specific dangerous gas combination, corresponding concentration information and potential hazards on the control panel when an alarm occurs, the notification unit is responsible for sounding the alarm through the sound and light alarm, and displaying the emergency operation instructions on the control panel and the mobile devices of the staff, and the emergency control unit is responsible for automatically starting or increasing the ventilation system and automatically starting the isolation device; Data recording and analysis module: including: alarm release unit, emergency control release unit, data recording unit and random forest analysis unit; among them, the alarm release unit is responsible for real-time monitoring of the gas concentration in the sample pool, and automatically releases the alarm when the concentration of all dangerous gases has dropped below the safety threshold. The emergency control release unit is responsible for linearly adjusting the ventilation system and closing the isolation device. The data recording unit is responsible for recording detailed data of dangerous events. The random forest analysis unit uses the random forest algorithm to analyze the failure of the corresponding equipment.

[0018] Compared with the prior art, the beneficial effects achieved by the present invention are: The present invention can collect and analyze gas samples in real time, quickly generate spectrograms, and detect gas composition and concentration in real time through machine learning algorithms, promptly discover potential dangerous gas combinations, and issue alarms.

[0019] The present invention adopts automatic sampling, filtering, flow control, data processing and alarm mechanism, reduces manual intervention and improves the continuity and stability of monitoring.

[0020] The present invention utilizes support vector machine algorithm and random forest algorithm to establish a hazardous gas combination library, and combines with big data technology to perform in-depth analysis and mining of large amounts of complex data, providing accurate fault prediction and trend analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings: Figure 1 It is a schematic diagram of the steps of a gas emission monitoring method based on spectral analysis of the present invention; Figure 2 It is a system structure diagram of a gas emission monitoring system based on spectral analysis of the present invention. DETAILED DESCRIPTION

[0022] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0023] See also Figure 1 and Figure 2 , the present invention provides a technical solution: According to one embodiment of the present invention, Figure 1 A method for monitoring gas emissions based on spectral analysis is shown in a schematic diagram of the steps. The method for monitoring gas emissions based on spectral analysis comprises the following steps: S100, start the sampling pump, extract gas samples from the environment to be tested, remove impurities through the sampling pipeline and filter, and transport them to the gas sample pool. The gas flow in the sample pool is regulated by the flow controller; the gas flows through the air inlet and outlet at both ends of the sample pool, and the gas in the sample pool is evenly distributed. The light beam emitted by the light source passes through the sample pool, and the spectrometer performs spectral measurement to generate a spectrum diagram, and the spectrum diagram is used to identify the gas composition and gas concentration; S200, when the spectrum graph identifies several gas components, using the support vector machine algorithm and the random forest algorithm to establish a dangerous gas combination library, the dangerous gas combination library lists the gas combinations that may cause dangerous reactions and their critical concentrations; real-time detection of the gas components and concentrations in the current environment, and comparison with the dangerous reaction library, if the detected gas combination meets the dangerous combination and the concentration reaches or exceeds the critical value, an alarm signal is generated; S300, when the alarm is triggered, the specific dangerous gas combination, corresponding concentration information and potential hazards are displayed on the control panel, an alarm is sounded through an audible and visual alarm, emergency operation instructions are displayed, the ventilation system is automatically started or increased, and the isolation device is automatically started; S400 monitors the gas concentration in the sample pool in real time, automatically cancels the alarm when the concentration of all hazardous gases has dropped below the safety threshold, linearly adjusts the operation of the ventilation system, closes the isolation device, records detailed data of hazardous events, and uses the random forest algorithm to analyze the failure of the corresponding equipment.

[0024] According to step S100, a flow controller is installed on the air inlet pipeline of the gas sample pool or on the pipeline close to the sampling pump, and the flow controller is a mass flow controller; before the system is started, the flow controller is calibrated and the target flow range is set; the flow range is determined according to the characteristics of the gas to be tested and the sample pool, and the flow range in this embodiment is 5 L / min; After starting the sampling pump, the flow controller starts working and monitors the flow of the gas sample in real time. The sensor inside the controller detects the flow signal and compares it with the set value. If the actual flow deviates from the set value, the controller automatically adjusts the valve opening or the pump speed to ensure that the flow is stable within the target range. The flow controller is equipped with a closed-loop control system to adjust the flow through real-time feedback. The monitoring interface displays the current flow value, and the operator can monitor and adjust it manually in real time.

[0025] According to step S100, a xenon lamp is selected as a light source, the spectrum of the light source covers the absorption wavelength range of the target gas, the light source is introduced into the optical path system through a collimating lens and an optical fiber to form a parallel light beam, and the gas sample pool is designed with quartz glass; the light beam enters from one end of the sample pool, passes through the gas sample, and then exits from the other end. The gas molecules have an absorption effect on light of a specific wavelength. When the light beam passes through the sample pool, the intensity and wavelength of the light beam change; The light beam entering the spectrometer is decomposed into spectra of different wavelengths by a grating or prism. The decomposed spectrum is projected onto the detector, which generates electrical signals according to the light intensity of different wavelengths. The detector converts these electrical signals into digital signals. The light intensity data of different wavelengths are plotted into a spectrum graph, which shows the absorption of each wavelength of light by the gas sample, and the gas composition and gas concentration are identified by the position and intensity of the absorption peak.

[0026] According to step S200, spectral data of historical gas samples are collected, each sample includes several gas components and their concentrations, and each sample is marked whether a dangerous reaction will occur, and the marked sample labels are: 1 for dangerous and -1 for safe; features are extracted from the spectral data, and the features include absorption peak position, absorption intensity, peak area, half-peak width, baseline shift and peak shape; Part of the training data set is as follows: sample ID: 1, absorption peak position: 450, absorption intensity 0.8, peak area: 200, half peak width: 50, baseline shift: 0.1, peak shape: 1.2, label: 1; Sample ID: 2, absorption peak position: 500, absorption intensity: 0.6, peak area: 180, half peak width: 45, baseline shift: 0.15, peak shape: 1.1, label: -1; The support vector machine is used to identify dangerous gas combinations. Its goal is to find a hyperplane to separate samples of different categories, including dangerous and safe. The spectral data feature vectors and corresponding labels form a first training data set, which is used for training. The objective function is defined as follows: ; Among them, w is the weight vector, which indicates the direction of the hyperplane, and b is the bias term, which indicates the displacement of the hyperplane; For each training sample, the constraints that need to be satisfied are defined as follows: ; in, is the sample label of the i-th sample, is the feature vector extracted from the spectral data of the i-th sample.

[0027] Construct the Lagrangian function through Lagrangian multipliers and solve the dual problem: ; in, is the Lagrange multiplier, used for the dual solution of the optimization problem, represents the slack variable of the constraint condition, and n is the number of training samples; Solve the Lagrangian function, take the derivative of w and b, and set the derivative to zero, and we get the dual problem: ; The constraints of the dual problem are: ; Use the gradient descent algorithm to solve the dual problem and get the optimal ; Use the best Calculate the weight vector w and bias term b as follows: ; in, are the labels of the support vectors, is the eigenvector of the support vector; Finally get ; The classification decision function of the trained support vector machine model is: ; in, arrive They correspond to the absorption peak position, absorption intensity, peak area, half-peak width, baseline shift and peak shape, respectively. is a classification decision function used to determine whether a gas combination is dangerous.

[0028] According to step S200, according to the hazardous gas combination obtained by the support vector machine algorithm, the spectral data of the gas samples of the corresponding hazardous gas combination are collected; the spectral data feature vectors of the gas samples of the hazardous gas combination and the critical concentration of the hazardous gas combination are combined into a second training data set, and several subsets are generated by random sampling from the second training data set, and each subset is used to train a decision tree; decision tree training is performed on each subset to establish a regression model; the feature vector of the new sample is input into each decision tree for prediction, and the average of the prediction results of all decision trees is taken as the final critical concentration prediction value.

[0029] According to step S200, for each decision tree , using a subset of the training data Conduct training, including is the spectral data feature vector of the gas sample of the dangerous gas combination, is the critical concentration of the dangerous gas combination; for the characteristic vector of the dangerous gas combination , each decision tree The prediction result is , which means the i-th decision tree is The prediction results output the critical concentration of dangerous gas combination; Random forest gives the final prediction value by combining the prediction results of all decision trees : ; in, is the number of decision trees. In this example ; The dangerous gas combination library is established by combining the critical concentrations of the dangerous gas combination obtained by the support vector machine algorithm and the dangerous gas combination obtained by the decision tree algorithm.

[0030] The spectral feature vector of the new sample is , bring it into the SVM model for classification: ; because , the sample is classified as dangerous. Then, the random forest model is used to predict the critical concentration of the sample, and the prediction results of each decision tree are: ; The final predicted value is: ; The predicted critical concentration value for this sample is 10.95 units, which is recorded in the hazardous gas combination library.

[0031] According to step S300, the control panel will display the type of gas detected, the concentration of each gas, the danger level and the potential hazard description, and display emergency operation instructions on the control panel and the staff's mobile device; the emergency operation instructions include how to wear personal protective equipment, the specific routes and steps for evacuating personnel and the steps for starting the ventilation system; automatically start or increase the operation of the ventilation system to reduce the concentration of dangerous gases, and automatically adjust the wind speed and air volume of the ventilation system according to the gas concentration and combination; when the gas sensor detects that the concentration of dangerous gases exceeds the standard, it automatically triggers the isolation device; when a fault is found in the isolation device, an automatic isolation device fault alarm is issued, and troubleshooting instructions are provided.

[0032] The type of gas detected, the concentration of each gas, the danger level and the potential hazard description are displayed in real time on the control panel and the staff's mobile device. Specific instructions on how to wear personal protective equipment, including what type of protective clothing, masks, gloves, etc. are used. Based on the detected gas concentration and wind direction, a specific evacuation route map is displayed on the control panel, and the navigation function is used to guide personnel to evacuate safely. Detailed steps are listed, such as: shutting down work equipment, quickly evacuating to a safe area, counting the number of people, etc. The steps for starting the ventilation system are displayed on the control panel, including the location of the manual start button, the conditions for automatic start, etc.

[0033] When the gas sensor detects that the isolation device is not working properly, the system will automatically alarm and display the fault information on the control panel. Provide detailed troubleshooting instructions, such as checking the power supply, restarting the device, replacing the faulty parts, etc. Through the system's built-in fault diagnosis algorithm, automatically analyze the cause of the fault and provide corresponding maintenance suggestions.

[0034] According to step S400, the gas concentration in the sample pool is continuously monitored by the sensor, and when the concentration of all dangerous gases drops below the safety threshold, the alarm is automatically lifted; according to the real-time monitored gas concentration data, the system automatically adjusts the wind speed and air volume of the ventilation system; the automatic control system shuts down the isolation device that was previously activated and restores the normal operation of the isolated area; and automatically records the time of the dangerous event, the type of gas detected, the concentration change, and the emergency measures taken; Use the random forest algorithm to perform fault analysis. Input the preprocessed equipment operation data into the random forest model, randomly select feature subsets, build several decision trees, use the training data to build multiple decision trees, each tree is trained independently, and predict the new data. Take the average prediction result of all decision trees as the equipment's fault condition analysis data and record it into the hazardous gas combination library.

[0035] According to another embodiment of the present invention, Figure 2 As shown in the system structure diagram of a gas emission monitoring system based on spectral analysis, a gas emission monitoring system based on spectral analysis includes: Sampling and filtering module: including: gas sampling unit, gas filtering unit and flow control unit; wherein, the gas sampling unit is responsible for starting the sampling pump and extracting gas samples from the environment to be tested through the sampling probe, the gas filtering unit is responsible for controlling the gas sample to pass through the sampling pipeline and filter, remove impurities and then be transported to the gas sample pool, and the flow control unit is responsible for adjusting the flow of the gas sample through the flow controller; Spectral measurement module: including: sample pool control unit, light source control unit and spectrometer control unit; wherein, the sample pool control unit is responsible for controlling the air inlet and outlet at both ends of the sample pool to flow when the gas sample enters the sample pool, so that the gas in the sample pool is evenly distributed, the light source control unit is responsible for controlling the light beam emitted by the light source to pass through the sample pool, and the spectrometer control unit is responsible for controlling the spectrometer to perform spectral measurement, generate a spectrum graph, and use the spectrum graph to identify gas composition and gas concentration; Data analysis and alarm module: including: a dangerous gas combination library establishment unit and a real-time detection unit; wherein, the dangerous gas combination library establishment unit is responsible for establishing a dangerous gas combination library using a support vector machine algorithm and a random forest algorithm when the spectrum map identifies several gas components, and the dangerous gas combination library lists gas combinations that may cause dangerous reactions and their critical concentrations; the real-time detection unit is responsible for real-time detection of the current gas composition and concentration, and compares them with the dangerous reaction library. If a dangerous gas combination is detected and the concentration reaches a critical value, an alarm signal is generated; Emergency response module: including: display unit, notification unit and emergency control unit; among them, the display unit will display the specific dangerous gas combination, corresponding concentration information and potential hazards on the control panel when an alarm occurs, the notification unit is responsible for sounding the alarm through the sound and light alarm, and displaying the emergency operation instructions on the control panel and the mobile devices of the staff, and the emergency control unit is responsible for automatically starting or increasing the ventilation system and automatically starting the isolation device; Data recording and analysis module: including: alarm release unit, emergency control release unit, data recording unit and random forest analysis unit; among them, the alarm release unit is responsible for real-time monitoring of the gas concentration in the sample pool, and automatically releases the alarm when the concentration of all dangerous gases has dropped below the safety threshold. The emergency control release unit is responsible for linearly adjusting the ventilation system and closing the isolation device. The data recording unit is responsible for recording detailed data of dangerous events. The random forest analysis unit uses the random forest algorithm to analyze the failure of the corresponding equipment.

[0036] We conducted multiple experiments in a simulated factory environment. The experimental environment includes a variety of common industrial gases and simulates various possible dangerous gas combinations and concentrations exceeding the standard. The experimental equipment includes spectrometers, gas sensors, sampling pumps, flow controllers, ventilation systems, isolation devices, control panels, and mobile equipment.

[0037] At different time points and conditions, gas samples were collected and spectra were generated by the spectrometer. The spectral data characteristics of each sample were recorded, such as absorption peak position, absorption intensity, peak area, half-peak width, baseline shift and peak shape. The support vector machine and random forest model were trained using historical data to establish a dangerous gas combination library. SVM is used to identify dangerous gas combinations, and RF is used to predict the critical concentration of dangerous gas combinations. The gas concentration in the sample pool is monitored in real time, and the spectrometer continuously collects data and transmits it to the control system. The trained SVM model is used for real-time classification to determine whether there is a dangerous gas combination. When a dangerous gas combination is detected and the concentration reaches the critical value, the emergency response module is triggered.

[0038] The display unit shows detailed information on the control panel and mobile devices, including hazardous gas combinations, concentration information, hazard levels, and potential hazards. The notification unit sounds an alarm through an audible and visual alarm and displays emergency operation instructions. The emergency control unit automatically starts or increases the ventilation system, adjusts the wind speed and air volume, and activates the isolation device. Real-time monitoring and adjustment are carried out until the gas concentration drops below the safety threshold. Detailed data of hazardous events are recorded, and fault analysis is performed using the random forest algorithm to identify potential fault sources.

[0039] In this example, a dangerous combination of carbon monoxide and chlorine was detected at concentrations of 35 ppm and 10 ppm, respectively. The control panel and mobile device displayed detailed hazardous gas information and potential hazards. The sound and light alarms immediately sounded the alarm. The emergency operation instructions recommended wearing a gas mask and isolation suit, and an evacuation route map was displayed on the control panel. The ventilation system was automatically started, the wind speed was increased to 20 m / s, and the air volume was adjusted to maximum. The isolation device was automatically started to seal the contaminated area. The gas concentration was successfully reduced to a safe range, and the event lasted for 10 minutes.

[0040] A dangerous combination of ammonia and sulfur dioxide was detected at 25 ppm and 5 ppm, respectively. Detailed information was displayed and an alarm was sounded. The ventilation system started normally, but the isolation device failed to start. The system automatically alarmed and displayed a fault message on the control panel. Troubleshooting instructions were provided to check the power supply and restart the equipment. Through manual intervention and system guidance, the fault was successfully eliminated and the isolation device function was restored. The event lasted 15 minutes.

[0041] The pre-processed equipment operation data was input into the random forest model, including wind speed, air volume, gas concentration changes and other characteristics. The decision tree was trained using historical fault data to establish a fault prediction model. In the new experimental data, the random forest model successfully predicted the possible overload failure of the ventilation system and took preventive measures in advance. The results were: prediction accuracy: 89%, fault warning advance time: 5 minutes, and equipment failure rate reduction: 30%.

[0042] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0043] Finally, it should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A gas emission monitoring method based on spectral analysis, characterized in that: The method comprises the following steps: S100, start the sampling pump, extract gas samples from the environment to be tested, remove impurities through the sampling pipeline and filter, and transport them to the gas sample pool. The gas flow in the sample pool is regulated by the flow controller; the gas flows through the air inlet and outlet at both ends of the sample pool, and the gas in the sample pool is evenly distributed. The light beam emitted by the light source passes through the sample pool, and the spectrometer performs spectral measurement to generate a spectrum diagram, and the spectrum diagram is used to identify the gas composition and gas concentration; S200, when the spectrum graph identifies several gas components, using the support vector machine algorithm and the random forest algorithm to establish a dangerous gas combination library, the dangerous gas combination library lists the gas combinations that may cause dangerous reactions and their critical concentrations; real-time detection of the gas components and concentrations in the current environment, and comparison with the dangerous reaction library, if the detected gas combination meets the dangerous combination and the concentration reaches or exceeds the critical value, an alarm signal is generated; S300, when the alarm is triggered, the specific dangerous gas combination, corresponding concentration information and potential hazards are displayed on the control panel, an alarm is sounded through an audible and visual alarm, emergency operation instructions are displayed, the ventilation system is automatically started or increased, and the isolation device is automatically started; S400 monitors the gas concentration in the sample pool in real time, automatically cancels the alarm when the concentration of all hazardous gases has dropped below the safety threshold, linearly adjusts the operation of the ventilation system, closes the isolation device, records detailed data of hazardous events, and uses the random forest algorithm to analyze the failure of the corresponding equipment.

2. The method for monitoring gas emissions based on spectral analysis according to claim 1, characterized in that: According to step S100, a flow controller is installed on the air inlet pipeline of the gas sample pool or on the pipeline close to the sampling pump, and the flow controller is a mass flow controller; before the system is started, the flow controller is calibrated to set the target flow range; the flow range is determined according to the characteristics of the gas to be tested and the sample pool; After starting the sampling pump, the flow controller starts working and monitors the flow of the gas sample in real time. The sensor inside the controller detects the flow signal and compares it with the set value. If the actual flow deviates from the set value, the controller automatically adjusts the valve opening or the pump speed to ensure that the flow is stable within the target range. The flow controller is equipped with a closed-loop control system to adjust the flow through real-time feedback. The monitoring interface displays the current flow value, and the operator can monitor and adjust it manually in real time.

3. The gas emission monitoring method based on spectral analysis according to claim 1 is characterized in that: According to step S100, a xenon lamp is selected as a light source, the spectrum of the light source covers the absorption wavelength range of the target gas, the light source is introduced into the optical path system through a collimating lens and an optical fiber to form a parallel light beam, and the gas sample pool is designed with quartz glass; the light beam enters from one end of the sample pool, passes through the gas sample, and then exits from the other end. The gas molecules have an absorption effect on light of a specific wavelength. When the light beam passes through the sample pool, the intensity and wavelength of the light beam change; The light beam entering the spectrometer is decomposed into spectra of different wavelengths by a grating or prism. The decomposed spectrum is projected onto the detector, which generates electrical signals according to the light intensity of different wavelengths. The detector converts these electrical signals into digital signals. The light intensity data of different wavelengths are plotted into a spectrum graph, which shows the absorption of each wavelength of light by the gas sample, and the gas composition and gas concentration are identified by the position and intensity of the absorption peak.

4. The method for monitoring gas emissions based on spectral analysis according to claim 1, characterized in that: According to step S200, spectral data of historical gas samples are collected, each sample includes several gas components and their concentrations, and each sample is marked whether a dangerous reaction will occur, and the marked sample labels are: 1 for dangerous and -1 for safe; features are extracted from the spectral data, and the features include absorption peak position, absorption intensity, peak area, half-peak width, baseline shift and peak shape; The support vector machine is used to identify dangerous gas combinations. Its goal is to find a hyperplane to separate samples of different categories, including dangerous and safe. The spectral data feature vectors and corresponding labels form a first training data set, which is used for training. The objective function is defined as follows: ； Among them, w is the weight vector, which indicates the direction of the hyperplane, and b is the bias term, which indicates the displacement of the hyperplane; For each training sample, the constraints that need to be satisfied are defined as follows: ； in, is the sample label of the i-th sample, is the feature vector extracted from the spectral data of the i-th sample.

5. A gas emission monitoring method based on spectral analysis according to claim 4, characterized in that: Construct the Lagrangian function through Lagrangian multipliers and solve the dual problem: ； in, is the Lagrange multiplier, used for the dual solution of the optimization problem, represents the slack variable of the constraint condition, and n is the number of training samples; Solve the Lagrangian function, take the derivative of w and b, and set the derivative to zero, and we get the dual problem: ； The constraints of the dual problem are: ； Use the gradient descent algorithm to solve the dual problem and get the optimal ; Use the best Calculate the weight vector w and bias term b as follows: ； in, are the labels of the support vectors, is the eigenvector of the support vector; The classification decision function of the trained support vector machine model is: ； in, is a classification decision function used to determine whether a gas combination is dangerous.

6. A method for monitoring gas emissions based on spectral analysis according to claim 5, characterized in that: According to step S200, according to the hazardous gas combination obtained by the support vector machine algorithm, the spectral data of the gas samples of the corresponding hazardous gas combination are collected; the spectral data feature vectors of the gas samples of the hazardous gas combination and the critical concentration of the hazardous gas combination are combined into a second training data set, and several subsets are generated by random sampling from the second training data set, and each subset is used to train a decision tree; decision tree training is performed on each subset to establish a regression model; the feature vector of the new sample is input into each decision tree for prediction, and the average of the prediction results of all decision trees is taken as the final critical concentration prediction value.

7. A method for monitoring gas emissions based on spectral analysis according to claim 6, characterized in that: According to step S200, for each decision tree , using a subset of the training data Conduct training, including is the spectral data feature vector of the gas sample of the dangerous gas combination, is the critical concentration of the dangerous gas combination; for the characteristic vector of the dangerous gas combination , each decision tree The prediction result is , which means the i-th decision tree is The prediction results output the critical concentration of dangerous gas combination; Random forest gives the final prediction value by combining the prediction results of all decision trees : ； in, is the number of decision trees; The dangerous gas combination library is established by combining the critical concentrations of the dangerous gas combination obtained by the support vector machine algorithm and the dangerous gas combination obtained by the decision tree algorithm.

8. The method for monitoring gas emissions based on spectral analysis according to claim 1, characterized in that: According to step S300, the control panel will display the type of gas detected, the concentration of each gas, the danger level and the potential hazard description, and display emergency operation instructions on the control panel and the staff's mobile device; the emergency operation instructions include how to wear personal protective equipment, the specific routes and steps for evacuating personnel and the steps for starting the ventilation system; automatically start or increase the operation of the ventilation system to reduce the concentration of dangerous gases, and automatically adjust the wind speed and air volume of the ventilation system according to the gas concentration and combination; when the gas sensor detects that the concentration of dangerous gases exceeds the standard, it automatically triggers the isolation device; when a fault is found in the isolation device, an automatic isolation device fault alarm is issued, and troubleshooting instructions are provided.

9. The method for monitoring gas emissions based on spectral analysis according to claim 1, characterized in that: According to step S400, the gas concentration in the sample pool is continuously monitored by the sensor, and when the concentration of all dangerous gases drops below the safety threshold, the alarm is automatically lifted; according to the real-time monitored gas concentration data, the system automatically adjusts the wind speed and air volume of the ventilation system; the automatic control system shuts down the isolation device that was previously activated and restores the normal operation of the isolated area; and automatically records the time of the dangerous event, the type of gas detected, the concentration change, and the emergency measures taken; Use the random forest algorithm to perform fault analysis. Input the preprocessed equipment operation data into the random forest model, randomly select feature subsets, build several decision trees, use the training data to build multiple decision trees, each tree is trained independently, and predict the new data. Take the average prediction result of all decision trees as the equipment's fault condition analysis data and record it into the hazardous gas combination library.

10. A gas emission monitoring system based on spectral analysis, using a gas emission monitoring method based on spectral analysis according to any one of claims 1 to 9, characterized in that: include: Sampling and filtering module: including: gas sampling unit, gas filtering unit and flow control unit; wherein, the gas sampling unit is responsible for starting the sampling pump and extracting gas samples from the environment to be tested through the sampling probe, the gas filtering unit is responsible for controlling the gas sample to pass through the sampling pipeline and filter, remove impurities and then be transported to the gas sample pool, and the flow control unit is responsible for adjusting the flow of the gas sample through the flow controller; Spectral measurement module: including: sample pool control unit, light source control unit and spectrometer control unit; wherein, the sample pool control unit is responsible for controlling the air inlet and outlet at both ends of the sample pool to flow when the gas sample enters the sample pool, so that the gas in the sample pool is evenly distributed, the light source control unit is responsible for controlling the light beam emitted by the light source to pass through the sample pool, and the spectrometer control unit is responsible for controlling the spectrometer to perform spectral measurement, generate a spectrum graph, and use the spectrum graph to identify gas composition and gas concentration; Data analysis and alarm module: including: a dangerous gas combination library establishment unit and a real-time detection unit; wherein, the dangerous gas combination library establishment unit is responsible for establishing a dangerous gas combination library using a support vector machine algorithm and a random forest algorithm when the spectrum map identifies several gas components, and the dangerous gas combination library lists gas combinations that may cause dangerous reactions and their critical concentrations; the real-time detection unit is responsible for real-time detection of the current gas composition and concentration, and compares them with the dangerous reaction library. If a dangerous gas combination is detected and the concentration reaches a critical value, an alarm signal is generated; Emergency response module: including: display unit, notification unit and emergency control unit; among them, the display unit will display the specific dangerous gas combination, corresponding concentration information and potential hazards on the control panel when an alarm occurs, the notification unit is responsible for sounding the alarm through the sound and light alarm, and displaying the emergency operation instructions on the control panel and the mobile devices of the staff, and the emergency control unit is responsible for automatically starting or increasing the ventilation system and automatically starting the isolation device; Data recording and analysis module: including: alarm release unit, emergency control release unit, data recording unit and random forest analysis unit; among them, the alarm release unit is responsible for real-time monitoring of the gas concentration in the sample pool, and automatically releases the alarm when the concentration of all dangerous gases has dropped below the safety threshold. The emergency control release unit is responsible for linearly adjusting the ventilation system and closing the isolation device. The data recording unit is responsible for recording detailed data of dangerous events. The random forest analysis unit uses the random forest algorithm to analyze the failure of the corresponding equipment.

Images