A control method and control system for determining the concentration of methyl chloride in a storage tank

Abstract

The present application relates to a chloromethane processing technical field, the present application discloses a kind of control method and control system for determining the concentration of chloromethane in storage tank, including obtaining target chloromethane concentration, based on target chloromethane concentration and pre-constructed dry classification model generates dry mode category, the dry mode category includes large amount of atmosphere dry and small amount of atmosphere dry, large amount of atmosphere dry includes drying agent process and molecular sieve process, small amount of atmosphere dry is membrane separation process, in the present application, the concentration of chloromethane is monitored in real time, combined with the characteristics of drying agent water removal, molecular sieve water removal and membrane separation water removal, the drying process of chloromethane can be accurately controlled, considering the cost difference of different drying methods, the present application determines the most suitable drying agent process or molecular sieve process by calculating the first drying cost and the second drying cost, to ensure the efficient chloromethane drying, while avoiding unnecessary high cost.

Description

Technical Field

[0001] This invention relates to the field of chloromethane processing technology, and more specifically, to a control method and control system for determining the concentration of chloromethane in a storage tank. Background Technology

[0002] Chloromethane, commonly known as chloromethane or methyl chloride, is an important organic chemical product widely used in the preparation of methane chloride, fluorinated refrigerants, and silicone polymers. Its production process mainly involves the reaction of gaseous methanol and hydrogen chloride under the action of different catalysts to produce chloromethane and water. After washing, drying, and compression, the product chloromethane is obtained. Drying is an operation that removes moisture (water or other solvents) from wet materials to obtain dry materials. According to different dehydration principles, the drying process of chloromethane can usually be divided into desiccant dehydration, molecular sieve dehydration, and membrane separation dehydration. Current technology usually only uses one of these drying processes. Because the actual concentration of chloromethane is not considered, the efficiency of drying chloromethane is not high.

[0003] For example, patent CN102614751 B discloses a chloromethane drying device, recovery system and method, and a butyl rubber production system. This patent dries chloromethane by setting up a drying tower and drying pipeline, and placing a desiccant inside the drying tower. Patent CN101015763A discloses a method for removing trace amounts of water from monochloromethane by steam permeation through a NaA zeolite molecular sieve membrane. This patent removes water by passing monochloromethane through a NaA zeolite molecular sieve membrane. Although both methods can remove water from monochloromethane, they both have certain problems:

[0004] Although the aforementioned patents all involve drying chloromethane, none of them monitor the concentration of chloromethane in real time. Desiccant dehydration and molecular sieve dehydration are typically used for high concentrations of chloromethane, while membrane separation dehydration is typically used for low concentrations. None of the aforementioned patents can provide real-time control based on the concentration of chloromethane. Furthermore, desiccant dehydration and molecular sieve dehydration have different drying costs. It is necessary to ensure that chloromethane can be dried efficiently while avoiding excessively high drying costs.

[0005] In view of this, the present invention proposes a control method and control system for measuring the concentration of chloromethane in a storage tank to solve the above problems. Summary of the Invention

[0006] In order to overcome the above-mentioned defects of the prior art, the present invention provides a control method and control system for measuring the concentration of chloromethane in a storage tank.

[0007] To achieve the above objectives, the present invention provides the following technical solution:

[0008] A method for controlling the concentration of chloromethane in a storage tank includes:

[0009] S10: Obtain the target chloromethane concentration, and generate a drying method category based on the target chloromethane concentration and the pre-constructed drying classification model. The drying method category includes large-volume drying and small-volume drying. Large-volume drying includes desiccant process and molecular sieve process, and small-volume drying is membrane separation process.

[0010] S20: When the drying method is large-volume drying, switch to S30; when the drying method is small-volume drying, dry chloromethane using membrane separation process.

[0011] S30: The desiccant consumption is generated based on the target chloromethane concentration, desiccant process, and a pre-built first machine learning model; the waste gas volume is generated based on the target chloromethane concentration, molecular sieve process, and a pre-built second machine learning model.

[0012] S40: Obtain the remaining amount of desiccant, obtain the first drying cost based on the desiccant consumption, obtain the second drying cost based on the waste gas volume, and determine whether to use a desiccant process or a molecular sieve process to dry chloromethane based on the remaining amount of desiccant, the first drying cost, and the second drying cost.

[0013] Furthermore, methods for obtaining the target concentration of monochloromethane include:

[0014] The real-time concentration of monochloromethane in the storage tank is obtained. Based on the real-time monochloromethane concentration, the concentration change rate of real-time monochloromethane per unit time is generated. It is determined whether the concentration change rate is less than the change rate threshold. If it is less, the real-time monochloromethane concentration is determined as the target monochloromethane concentration.

[0015] Furthermore, the methods for constructing the dryness classification model include:

[0016] Obtain i sets of data, where i is a positive integer greater than 1. The data includes the target chloromethane concentration and the drying method category. Use the target chloromethane concentration and the drying method category as a sample set. Divide the sample set into a training set and a test set. Build a classifier. Use the target chloromethane concentration in the training set as the input data and the drying method category in the training set as the output data. Train the classifier to obtain an initial classifier. Test the initial classifier using the test set. Output the classifier that meets the preset accuracy as the drying classification model.

[0017] Furthermore, the construction methods for the first machine learning model include:

[0018] A sample dataset is obtained, which includes historical target chloromethane concentration, desiccant process, and historical desiccant consumption. The sample dataset is divided into a sample training set and a sample test set. A regression network is constructed, using the historical target chloromethane concentration and desiccant process from the sample training set as input data and the historical desiccant consumption from the sample training set as output data. The regression network is trained to obtain an initial regression network for predicting real-time desiccant consumption. The initial regression network is tested using the sample test set, and the regression network that outputs a value less than a preset error value is used as the first machine learning model.

[0019] Furthermore, the construction methods for the second machine learning model include:

[0020] A sample dataset is obtained, which includes historical target chloromethane concentration, molecular sieve process, and historical waste gas volume. The sample dataset is divided into a sample training set and a sample test set. A regression network is constructed, using the historical target chloromethane concentration and molecular sieve process in the sample training set as input data and the historical waste gas volume in the sample training set as output data. The regression network is trained to obtain an initial regression network for predicting real-time waste gas volume. The initial regression network is tested using the sample test set, and the regression network that outputs a value less than a preset error value is used as the second machine learning model.

[0021] Furthermore, methods for obtaining the first drying cost based on desiccant consumption include:

[0022]

[0023] In the formula, I de is the first drying cost, Dct is the desiccant consumption, Nps is the volume of desiccant processed per cycle, u1 is the price per unit volume of desiccant, u2 is the price per cycle of desiccant processing, and u3 is the price per unit volume of desiccant transportation.

[0024] Furthermore, methods for obtaining the second drying cost based on the exhaust gas volume include:

[0025] Obtain the concentration of monochloromethane tail gas in the exhaust gas volume;

[0026] If the concentration of chloromethane tail gas is greater than the preset concentration threshold, then activated carbon adsorption is used to treat chloromethane, and the second drying cost is the cost required for activated carbon treatment of chloromethane.

[0027] If the concentration of chloromethane tail gas is less than or equal to the preset concentration threshold, then biodegradation is selected to treat chloromethane, and the second drying cost is the cost required for biodegradation treatment of chloromethane.

[0028] Furthermore, methods for drying chloromethane using desiccant processes or molecular sieve processes include:

[0029] If the remaining amount of desiccant is less than a preset remaining amount threshold, then the molecular sieve process is used to dry the chloromethane. If not, then the first drying cost is further determined to be greater than the second drying cost. If so, then the molecular sieve process is used to dry the chloromethane. If not, then the desiccant process is used to dry the chloromethane.

[0030] A control system for measuring the concentration of chloromethane in a storage tank, used to implement the aforementioned control method for measuring the concentration of chloromethane in a storage tank, includes:

[0031] Acquisition module: Acquires the target chloromethane concentration, generates a drying method category based on the target chloromethane concentration and a pre-built drying classification model, the drying method category includes large-volume drying and small-volume drying, large-volume drying includes desiccant process and molecular sieve process, and small-volume drying is membrane separation process;

[0032] Discrimination module: When the drying method is large-volume drying, the process switches to the generation module; when the drying method is small-volume drying, the chloromethane is dried using a membrane separation process.

[0033] Generation module: Generates desiccant consumption based on target chloromethane concentration, desiccant process and pre-built first machine learning model; generates waste gas volume based on target chloromethane concentration, molecular sieve process and pre-built second machine learning model.

[0034] Method determination module: Obtain the remaining amount of desiccant, obtain the first drying cost based on the desiccant consumption, obtain the second drying cost based on the waste gas volume, and determine the desiccant process or molecular sieve process for drying chloromethane based on the remaining amount of desiccant, the first drying cost, and the second drying cost.

[0035] A computer-readable storage medium storing a computer program, which, when executed, implements the above-described control method for determining the concentration of chloromethane in a storage tank.

[0036] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0037] This invention monitors the concentration of chloromethane in real time and combines the characteristics of desiccant dehydration, molecular sieve dehydration, and membrane separation dehydration to precisely control the chloromethane drying process. Considering the cost differences of different drying methods, this invention calculates the first drying cost and the second drying cost to determine the most suitable desiccant process or molecular sieve process to ensure high-efficiency chloromethane drying while avoiding unnecessary high costs. Attached Figure Description

[0038] Figure 1 This is a schematic diagram of a method for controlling the concentration of chloromethane in a storage tank according to the present invention;

[0039] Figure 2 This is a schematic diagram of a control system for measuring the concentration of chloromethane in a storage tank according to the present invention;

[0040] Figure 3 This is a schematic diagram illustrating the storage and distribution of monochloromethane to different drying processes according to the present invention;

[0041] Figure 4 This is a schematic diagram of a computer-readable storage medium according to the present invention. Detailed Implementation

[0042] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0043] Example 1

[0044] Please see Figure 1 As shown in the figure, this embodiment discloses a control method for determining the concentration of chloromethane in a storage tank, including:

[0045] S10: Obtain the target chloromethane concentration, and generate a drying method category based on the target chloromethane concentration and the pre-constructed drying classification model. The drying method category includes large-volume drying and small-volume drying. Large-volume drying includes desiccant process and molecular sieve process, and small-volume drying is membrane separation process.

[0046] It should be noted that, as Figure 3 As shown in the figure, 10 is a storage tank for storing chloromethane, 20 is an inlet pipe for introducing chloromethane into the storage tank, 30 is a solenoid valve for controlling the gas flow through the pipe, and 40, 50 and 60 are pipes connected to the desiccant process, membrane separation process and molecular sieve process, respectively. It can be clearly seen from the figure that there are multiple ways to obtain the target chloromethane concentration. For example, a gas sensor can be installed inside the storage tank 10 for acquisition. This embodiment provides a method for obtaining the target chloromethane concentration.

[0047] Methods for obtaining the target concentration of monochloromethane include:

[0048] The real-time concentration of chloromethane in the storage tank is obtained. Based on the real-time chloromethane concentration, the concentration change rate of real-time chloromethane per unit time is generated. It is determined whether the concentration change rate is less than the change rate threshold. If it is less, the real-time chloromethane concentration is determined as the target chloromethane concentration.

[0049] Understandably, in the initial stage of drying chloromethane, chloromethane needs to be supplied to the storage tank 10 through the inlet pipe 20. In the early stage of supplying, the concentration of chloromethane in the storage tank 10 changes rapidly, exhibiting strong instability. At this time, the concentration of chloromethane is not the target concentration required by this invention. Since the concentration of chloromethane is relatively small at this time, chloromethane can be directly dried using membrane separation technology. This invention does not limit this. As the supply continues, the concentration of chloromethane inside the storage tank 10 increases rapidly and then gradually stabilizes. At this time, the concentration of chloromethane inside the storage tank 10 is the target concentration of chloromethane required by this invention. By obtaining the accurate target concentration of chloromethane, errors in the subsequent generation of the drying method category based on the target concentration of chloromethane can be avoided.

[0050] The concentration change rate is used to characterize the concentration. When the concentration change rate is less than the change rate threshold, it means that the concentration of chloromethane inside the storage tank 10 is gradually stabilizing. When the concentration change rate is greater than or equal to the change rate threshold, it means that the concentration of chloromethane inside the storage tank 10 has not yet stabilized. Therefore, the real-time concentration of chloromethane inside the storage tank 10 cannot be determined as the target concentration of chloromethane. The concentration change rate can be obtained by dividing the concentration change value by the unit time.

[0051] Methods for constructing dryness classification models include:

[0052] Obtain i sets of data, where i is a positive integer greater than 1. The data includes the target chloromethane concentration and the drying method category. Use the target chloromethane concentration and the drying method category as a sample set. Divide the sample set into a training set and a test set. Construct a classifier. Use the target chloromethane concentration in the training set as the input data and the drying method category in the training set as the output data. Train the classifier to obtain an initial classifier. Test the initial classifier using the test set. Output a classifier that meets the preset accuracy as the drying classification model. The classifier is preferably one of the Naive Bayes model or the Support Vector Machine model.

[0053] It is worth noting that the drying method category includes large volume drying and small volume drying. When the target chloromethane concentration is high, the output drying method category is large volume drying, and when the target chloromethane concentration is low, the output drying method category is small volume drying. The specific setting can be determined by those skilled in the art according to the actual situation, and will not be elaborated further in this invention.

[0054] S20: When the drying method is large-volume drying, switch to S30; when the drying method is small-volume drying, dry chloromethane using membrane separation process.

[0055] In this embodiment, since desiccant dehydration and molecular sieve dehydration are typically used for high concentrations of chloromethane, while membrane separation dehydration is typically used for low concentrations of chloromethane, when the drying method category is large-volume drying, it indicates that the concentration of chloromethane to be dried is high, and therefore a desiccant process or molecular sieve process is required to dry the chloromethane. Conversely, when the drying method category is small-volume drying, it indicates that the concentration of chloromethane to be dried is low, and the chloromethane is directly dried using a membrane separation process.

[0056] S30: The desiccant consumption is generated based on the target chloromethane concentration, desiccant process, and a pre-built first machine learning model; the waste gas volume is generated based on the target chloromethane concentration, molecular sieve process, and a pre-built second machine learning model.

[0057] It should be noted that the desiccant process refers to absorbing moisture from chloromethane using desiccants such as quicklime, solid sodium hydroxide, or concentrated sulfuric acid. Its advantages are that the technology is simple, mature, and easy to implement. Its disadvantage is that the desiccant needs to be replaced, which is affected by cost factors. The molecular sieve process refers to using a pressure-switching and temperature-switching absorption system to absorb saturated moisture. Its advantages are that the process technology is mature and suitable for large-volume treatment. Its disadvantage is that a large amount of tail gas is generated during the adsorption and regeneration switching process, and the treatment of tail gas also requires high costs.

[0058] The first method for constructing a machine learning model includes:

[0059] Obtain a sample dataset, which includes historical target chloromethane concentration, desiccant process, and historical desiccant consumption. Divide the sample dataset into a sample training set and a sample test set. Construct a regression network, using the historical target chloromethane concentration and desiccant process in the sample training set as input data and the historical desiccant consumption in the sample training set as output data. Train the regression network to obtain an initial regression network for predicting real-time desiccant consumption. Test the initial regression network using the sample test set. The regression network that outputs a value less than a preset error value is used as the first machine learning model. The regression network is preferably a neural network model.

[0060] The methods for constructing the second machine learning model include:

[0061] A sample dataset is obtained, which includes historical target chloromethane concentration, molecular sieve process, and historical waste gas volume. The sample dataset is divided into a sample training set and a sample test set. A regression network is constructed, using the historical target chloromethane concentration and molecular sieve process in the sample training set as the input data of the regression network, and the historical waste gas volume in the sample training set as the output data of the regression network. The regression network is trained to obtain an initial regression network for predicting real-time waste gas volume. The initial regression network is tested using the sample test set, and the regression network that outputs a value less than a preset error value is used as the second machine learning model. The regression network is preferably a neural network model.

[0062] It is understandable that both the desiccant process and the molecular sieve process are equivalent to features used for model training. Only by inputting the desiccant process or molecular sieve process as features into the model can the model output the corresponding desiccant consumption or waste gas volume based on the target chloromethane concentration. The construction method of the second machine learning model is the same as that of the first machine learning model, except that the desiccant process in the input data of the model is replaced with the molecular sieve process, and the historical desiccant consumption in the output data of the model is replaced with the historical waste gas volume. This invention will not elaborate on this further.

[0063] S40: Obtain the remaining amount of desiccant, obtain the first drying cost based on the desiccant consumption, obtain the second drying cost based on the waste gas volume, and determine the desiccant process or molecular sieve process for drying chloromethane based on the remaining amount of desiccant, the first drying cost and the second drying cost.

[0064] It is worth noting that the remaining amount of desiccant refers to the amount of unused desiccant used to remove moisture from chloromethane in a timely manner. The desiccant is usually stored in a desiccant box. As the amount of desiccant consumed increases, the remaining amount of desiccant decreases. Therefore, it is necessary to add desiccant to the desiccant box in a timely manner. There are several ways to obtain the remaining amount of desiccant. A sensor can be installed in the desiccant box to obtain the remaining amount of desiccant.

[0065] Methods for determining the initial drying cost based on desiccant consumption include:

[0066]

[0067] In the formula, I de is the first drying cost, Dct is the desiccant consumption, Nps is the volume of desiccant processed in a single operation, u1 is the price per unit volume of desiccant, u2 is the price per single operation of desiccant, and u3 is the price for transporting a unit volume of desiccant.

[0068] Understandably, in the above, Nps represents the volume of desiccant processed in a single operation, and u2 represents the price of a single desiccant processing operation. Due to different environmental policies in each region, the volume of desiccant processed each time also varies. If the environmental policies are relatively strict, the desiccant needs to be processed urgently when it accumulates to a certain volume. The more times it is processed, the higher the cost. Therefore, the initial drying cost varies in each region. In this way, the initial drying cost can be obtained more accurately by combining the price of a single desiccant processing operation with the price of transporting a unit volume of desiccant.

[0069] Methods for determining the second drying cost based on exhaust gas volume include:

[0070] Obtain the concentration of monochloromethane tail gas in the exhaust gas volume;

[0071] If the concentration of chloromethane tail gas is greater than the preset concentration threshold, then activated carbon adsorption is used to treat chloromethane, and the second drying cost is the cost required for activated carbon treatment of chloromethane.

[0072] If the concentration of chloromethane tail gas is less than or equal to the preset concentration threshold, then the chloromethane is treated by biodegradation, and the second drying cost is the cost required for the biodegradation treatment of chloromethane.

[0073] It should be noted that the molecular sieve process generates a large amount of exhaust gas during adsorption and regeneration switching. This exhaust gas mainly consists of undried chloromethane and water vapor. To avoid the environmental impact of chloromethane, any remaining chloromethane needs to be treated. For large-scale chloromethane emissions, activated carbon adsorption is generally more economical because it is a relatively low-cost and mature technology. Biodegradation may be more suitable for smaller-scale treatment. The appropriate treatment method should be determined based on the concentration of chloromethane in the exhaust gas to improve treatment efficiency. The cost of treating chloromethane can be determined by those skilled in the art based on the specific circumstances, and will not be elaborated upon further in this invention.

[0074] Methods for determining whether to use a desiccant process or a molecular sieve process to dry chloromethane include:

[0075] If the remaining amount of desiccant is less than the preset remaining amount threshold, then the molecular sieve process is used to dry the chloromethane. If not, then the first drying cost is further determined to be greater than the second drying cost. If so, then the molecular sieve process is used to dry the chloromethane. If not, then the desiccant process is used to dry the chloromethane.

[0076] It is worth noting that, due to the large amount of desiccant used, it is necessary to replenish it frequently according to the remaining amount. When the remaining amount of desiccant is less than the preset remaining amount threshold, it indicates that the desiccant needs to be replenished in time. In this case, the molecular sieve process should be used to dry the chloromethane. When the remaining amount of desiccant is greater than or equal to the preset remaining amount threshold, the molecular sieve process or the desiccant process should be selected to dry the chloromethane according to the cost.

[0077] In this embodiment, by real-time monitoring of the concentration of chloromethane and combining the characteristics of desiccant dehydration, molecular sieve dehydration, and membrane separation dehydration, the drying process of chloromethane can be precisely controlled. Considering the cost differences of different drying methods, this embodiment calculates the first drying cost and the second drying cost to determine the most suitable desiccant process or molecular sieve process to ensure high-efficiency chloromethane drying while avoiding unnecessary high costs.

[0078] Example 2

[0079] like Figure 2 As shown, this embodiment provides a control system for measuring the concentration of chloromethane in a storage tank, based on Embodiment 1, including:

[0080] Acquisition module: Acquires the target chloromethane concentration, generates a drying method category based on the target chloromethane concentration and a pre-built drying classification model, the drying method category includes large-volume drying and small-volume drying, large-volume drying includes desiccant process and molecular sieve process, and small-volume drying is membrane separation process;

[0081] It should be noted that, as Figure 3 As shown in the figure, 10 is a storage tank for storing chloromethane, 20 is an inlet pipe for introducing chloromethane into the storage tank, 30 is a solenoid valve for controlling the gas flow through the pipe, and 40, 50 and 60 are pipes connected to the desiccant process, membrane separation process and molecular sieve process, respectively. It can be clearly seen from the figure that there are multiple ways to obtain the target chloromethane concentration. For example, a gas sensor can be installed inside the storage tank 10 for acquisition. This embodiment provides a method for obtaining the target chloromethane concentration.

[0082] Methods for obtaining the target concentration of monochloromethane include:

[0083] The real-time concentration of chloromethane in the storage tank is obtained. Based on the real-time chloromethane concentration, the concentration change rate of real-time chloromethane per unit time is generated. It is determined whether the concentration change rate is less than the change rate threshold. If it is less, the real-time chloromethane concentration is determined as the target chloromethane concentration.

[0084] Understandably, in the initial stage of drying chloromethane, chloromethane needs to be supplied to the storage tank 10 through the inlet pipe 20. In the early stage of supplying, the concentration of chloromethane in the storage tank 10 changes rapidly, exhibiting strong instability. At this time, the concentration of chloromethane is not the target concentration required by this invention. Since the concentration of chloromethane is relatively small at this time, chloromethane can be directly dried using membrane separation technology. This invention does not limit this. As the supply continues, the concentration of chloromethane inside the storage tank 10 increases rapidly and then gradually stabilizes. At this time, the concentration of chloromethane inside the storage tank 10 is the target concentration of chloromethane required by this invention. By obtaining the accurate target concentration of chloromethane, errors in the subsequent generation of the drying method category based on the target concentration of chloromethane can be avoided.

[0085] The concentration change rate is used to characterize the concentration. When the concentration change rate is less than the change rate threshold, it means that the concentration of chloromethane inside the storage tank 10 is gradually stabilizing. When the concentration change rate is greater than or equal to the change rate threshold, it means that the concentration of chloromethane inside the storage tank 10 has not yet stabilized. Therefore, the real-time concentration of chloromethane inside the storage tank 10 cannot be determined as the target concentration of chloromethane. The concentration change rate can be obtained by dividing the concentration change value by the unit time.

[0086] Methods for constructing dryness classification models include:

[0087] Obtain i sets of data, where i is a positive integer greater than 1. The data includes the target chloromethane concentration and the drying method category. Use the target chloromethane concentration and the drying method category as a sample set. Divide the sample set into a training set and a test set. Construct a classifier. Use the target chloromethane concentration in the training set as the input data and the drying method category in the training set as the output data. Train the classifier to obtain an initial classifier. Test the initial classifier using the test set. Output a classifier that meets the preset accuracy as the drying classification model. The classifier is preferably one of the Naive Bayes model or the Support Vector Machine model.

[0088] It is worth noting that the drying method category includes large volume drying and small volume drying. When the target chloromethane concentration is high, the output drying method category is large volume drying, and when the target chloromethane concentration is low, the output drying method category is small volume drying. The specific setting can be determined by those skilled in the art according to the actual situation, and will not be elaborated further in this invention.

[0089] Discrimination module: When the drying method is large-volume drying, the process switches to the generation module; when the drying method is small-volume drying, the chloromethane is dried using a membrane separation process.

[0090] In this embodiment, since desiccant dehydration and molecular sieve dehydration are typically used for high concentrations of chloromethane, while membrane separation dehydration is typically used for low concentrations of chloromethane, when the drying method category is large-volume drying, it indicates that the concentration of chloromethane to be dried is high, and therefore a desiccant process or molecular sieve process is required to dry the chloromethane. Conversely, when the drying method category is small-volume drying, it indicates that the concentration of chloromethane to be dried is low, and the chloromethane is directly dried using a membrane separation process.

[0091] Generation module: Generates desiccant consumption based on target chloromethane concentration, desiccant process and pre-built first machine learning model; generates waste gas volume based on target chloromethane concentration, molecular sieve process and pre-built second machine learning model.

[0092] It should be noted that the desiccant process refers to absorbing moisture from chloromethane using desiccants such as quicklime, solid sodium hydroxide, or concentrated sulfuric acid. Its advantages are that the technology is simple, mature, and easy to implement. Its disadvantage is that the desiccant needs to be replaced, which is affected by cost factors. The molecular sieve process refers to using a pressure-switching and temperature-switching absorption system to absorb saturated moisture. Its advantages are that the process technology is mature and suitable for large-volume treatment. Its disadvantage is that a large amount of tail gas is generated during the adsorption and regeneration switching process, and the treatment of tail gas also requires high costs.

[0093] The first method for constructing a machine learning model includes:

[0094] Obtain a sample dataset, which includes historical target chloromethane concentration, desiccant process, and historical desiccant consumption. Divide the sample dataset into a sample training set and a sample test set. Construct a regression network, using the historical target chloromethane concentration and desiccant process in the sample training set as input data and the historical desiccant consumption in the sample training set as output data. Train the regression network to obtain an initial regression network for predicting real-time desiccant consumption. Test the initial regression network using the sample test set. The regression network that outputs a value less than a preset error value is used as the first machine learning model. The regression network is preferably a neural network model.

[0095] It is understandable that both the desiccant process and the molecular sieve process are equivalent to features used for model training. Only by inputting the desiccant process or molecular sieve process as features into the model can the model output the corresponding desiccant consumption or waste gas volume based on the target chloromethane concentration. The construction method of the second machine learning model is the same as that of the first machine learning model, except that the desiccant process in the input data of the model is replaced with the molecular sieve process, and the historical desiccant consumption in the output data of the model is replaced with the historical waste gas volume. This invention will not elaborate on this further.

[0096] Method determination module: Obtain the remaining amount of desiccant, obtain the first drying cost based on the desiccant consumption, obtain the second drying cost based on the waste gas volume, and determine the desiccant process or molecular sieve process for drying chloromethane based on the remaining amount of desiccant, the first drying cost and the second drying cost;

[0097] It is worth noting that the remaining amount of desiccant refers to the amount of unused desiccant used to remove moisture from chloromethane in a timely manner. The desiccant is usually stored in a desiccant box. As the amount of desiccant consumed increases, the remaining amount of desiccant decreases. Therefore, it is necessary to add desiccant to the desiccant box in a timely manner. There are several ways to obtain the remaining amount of desiccant. A sensor can be installed in the desiccant box to obtain the remaining amount of desiccant.

[0098] Methods for determining the initial drying cost based on desiccant consumption include:

[0099]

[0100] In the formula, I de is the first drying cost, Dct is the desiccant consumption, Nps is the volume of desiccant processed in a single operation, u1 is the price per unit volume of desiccant, u2 is the price per single operation of desiccant, and u3 is the price for transporting a unit volume of desiccant.

[0101] Understandably, in the above, Nps represents the volume of a single desiccant treatment, and u2 represents the price of a single desiccant treatment. Due to different environmental policies in each region, the volume of desiccant treated each time also varies. If the environmental policies are relatively strict, the desiccant needs to be treated urgently when it accumulates to a certain volume. The more times it is treated, the higher the cost. Therefore, the initial drying cost varies in each region. In this way, the initial drying cost can be obtained more accurately by combining the price of a single desiccant treatment with the price of transporting a unit volume of desiccant.

[0102] Methods for determining the second drying cost based on exhaust gas volume include:

[0103] Obtain the concentration of monochloromethane tail gas in the exhaust gas volume;

[0104] If the concentration of chloromethane tail gas is greater than the preset concentration threshold, then activated carbon adsorption is used to treat chloromethane, and the second drying cost is the cost required for activated carbon treatment of chloromethane.

[0105] If the concentration of chloromethane tail gas is less than or equal to the preset concentration threshold, then the chloromethane is treated by biodegradation, and the second drying cost is the cost required for the biodegradation treatment of chloromethane.

[0106] It should be noted that the molecular sieve process generates a large amount of exhaust gas during adsorption and regeneration switching. This exhaust gas mainly consists of undried chloromethane and water vapor. To avoid the environmental impact of chloromethane, any remaining chloromethane needs to be treated. For large-scale chloromethane emissions, activated carbon adsorption is generally more economical because it is a relatively low-cost and mature technology. Biodegradation may be more suitable for smaller-scale treatment. The appropriate treatment method should be determined based on the concentration of chloromethane in the exhaust gas to improve treatment efficiency. The cost of treating chloromethane can be determined by those skilled in the art based on the specific circumstances, and will not be elaborated upon further in this invention.

[0107] Methods for determining whether to use a desiccant process or a molecular sieve process to dry chloromethane include:

[0108] If the remaining amount of desiccant is less than the preset remaining amount threshold, then the molecular sieve process is used to dry the chloromethane. If not, then the first drying cost is further determined to be greater than the second drying cost. If so, then the molecular sieve process is used to dry the chloromethane. If not, then the desiccant process is used to dry the chloromethane.

[0109] It is worth noting that, due to the large amount of desiccant used, it is necessary to replenish it frequently based on the remaining amount. When the remaining amount of desiccant is less than the preset remaining amount threshold, it indicates that the desiccant needs to be replenished in time. In this case, molecular sieve technology should be used to dry the chloromethane. When the remaining amount of desiccant is greater than or equal to the preset remaining amount threshold, it is necessary to choose between molecular sieve technology or desiccant technology to dry the chloromethane based on cost.

[0110] Example 3

[0111] This embodiment discloses an electronic device, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the control method for determining the concentration of chloromethane in a storage tank provided by the above methods.

[0112] Since the electronic device described in this embodiment is the electronic device used to implement the control method for measuring the concentration of chloromethane in a storage tank according to the embodiments of this application, those skilled in the art can understand the specific implementation and various variations of the electronic device in this embodiment based on the control method for measuring the concentration of chloromethane in a storage tank described in the embodiments of this application. Therefore, how the electronic device implements the method in the embodiments of this application will not be described in detail here. As long as those skilled in the art implement the electronic device used in the control method for measuring the concentration of chloromethane in a storage tank according to the embodiments of this application, it falls within the scope of protection of this application.

[0113] Example 4

[0114] like Figure 4 As shown, this embodiment discloses a computer-readable storage medium storing a computer program, which, when executed, implements the above-described method for controlling the concentration of chloromethane in a storage tank.

[0115] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters, weights, and thresholds in the formulas are set by those skilled in the art according to the actual situation.

[0116] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired or wireless network. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0117] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed in this invention can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0118] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0119] In the several embodiments provided by this invention, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only one method, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0120] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0121] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0122] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

[0123] In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for controlling the concentration of chloromethane in a storage tank, characterized in that, include: S10: Obtain the target chloromethane concentration, and generate a drying method category based on the target chloromethane concentration and the pre-constructed drying classification model. The drying method category includes large-volume drying and small-volume drying. Large-volume drying includes desiccant process and molecular sieve process, and small-volume drying is membrane separation process. S20: When the drying method is large-volume drying, switch to S30; when the drying method is small-volume drying, dry chloromethane using membrane separation process. S30: The desiccant consumption is generated based on the target chloromethane concentration, desiccant process, and a pre-built first machine learning model; the waste gas volume is generated based on the target chloromethane concentration, molecular sieve process, and a pre-built second machine learning model. S40: Obtain the remaining amount of desiccant, obtain the first drying cost based on the desiccant consumption, obtain the second drying cost based on the waste gas volume, and determine whether to use a desiccant process or a molecular sieve process to dry chloromethane based on the remaining amount of desiccant, the first drying cost, and the second drying cost.

2. The method for controlling the concentration of chloromethane in a storage tank according to claim 1, characterized in that, The method for obtaining the target concentration of chloromethane includes: The real-time concentration of monochloromethane in the storage tank is obtained. Based on the real-time monochloromethane concentration, the concentration change rate of real-time monochloromethane per unit time is generated. It is determined whether the concentration change rate is less than the change rate threshold. If it is less, the real-time monochloromethane concentration is determined as the target monochloromethane concentration.

3. The method for controlling the concentration of chloromethane in a storage tank according to claim 2, characterized in that, The method for constructing the dryness classification model includes: Obtain i sets of data, where i is a positive integer greater than 1. The data includes the target chloromethane concentration and the drying method category. Use the target chloromethane concentration and the drying method category as a sample set. Divide the sample set into a training set and a test set. Build a classifier. Use the target chloromethane concentration in the training set as the input data and the drying method category in the training set as the output data. Train the classifier to obtain an initial classifier. Test the initial classifier using the test set. Output the classifier that meets the preset accuracy as the drying classification model.

4. The method for controlling the concentration of chloromethane in a storage tank according to claim 1, characterized in that, The method for constructing the first machine learning model includes: A sample dataset is obtained, which includes historical target chloromethane concentration, desiccant process, and historical desiccant consumption. The sample dataset is divided into a sample training set and a sample test set. A regression network is constructed, using the historical target chloromethane concentration and desiccant process from the sample training set as input data and the historical desiccant consumption from the sample training set as output data. The regression network is trained to obtain an initial regression network for predicting real-time desiccant consumption. The initial regression network is tested using the sample test set, and the regression network that outputs a value less than a preset error value is used as the first machine learning model.

5. The method for controlling the concentration of chloromethane in a storage tank according to claim 1, characterized in that, The construction method of the second machine learning model includes: A sample dataset is obtained, which includes historical target chloromethane concentration, molecular sieve process, and historical waste gas volume. The sample dataset is divided into a sample training set and a sample test set. A regression network is constructed, using the historical target chloromethane concentration and molecular sieve process in the sample training set as input data and the historical waste gas volume in the sample training set as output data. The regression network is trained to obtain an initial regression network for predicting real-time waste gas volume. The initial regression network is tested using the sample test set, and the regression network that outputs a value less than a preset error value is used as the second machine learning model.

6. The method for controlling the concentration of chloromethane in a storage tank according to claim 1, characterized in that, The method for obtaining the first drying cost based on the desiccant consumption includes: In the formula, Ide is the first drying cost, Dct is the desiccant consumption, Nps is the volume of desiccant processed per cycle, u1 is the price per unit volume of desiccant, u2 is the price per cycle of desiccant processing, and u3 is the price for transporting a unit volume of desiccant.

7. The method for controlling the concentration of chloromethane in a storage tank according to claim 1, characterized in that, The method for obtaining the second drying cost based on the waste gas volume includes: Obtain the concentration of monochloromethane tail gas in the exhaust gas volume; If the concentration of chloromethane tail gas is greater than the preset concentration threshold, then activated carbon adsorption is used to treat chloromethane, and the second drying cost is the cost required for activated carbon treatment of chloromethane. If the concentration of chloromethane tail gas is less than or equal to the preset concentration threshold, then biodegradation is selected to treat chloromethane, and the second drying cost is the cost required for biodegradation treatment of chloromethane.

8. The method for controlling the concentration of chloromethane in a storage tank according to claim 7, characterized in that, The method for drying chloromethane using the desiccant process or molecular sieve process includes: If the remaining amount of desiccant is less than a preset remaining amount threshold, then the molecular sieve process is used to dry the chloromethane. If not, then the first drying cost is further determined to be greater than the second drying cost. If so, then the molecular sieve process is used to dry the chloromethane. If not, then the desiccant process is used to dry the chloromethane.

9. A control system for measuring the concentration of chloromethane in a storage tank, used to implement the control method for measuring the concentration of chloromethane in a storage tank according to any one of claims 1-8, characterized in that, include: Acquisition module: Acquires the target chloromethane concentration, generates a drying method category based on the target chloromethane concentration and a pre-built drying classification model, the drying method category includes large-volume drying and small-volume drying, large-volume drying includes desiccant process and molecular sieve process, and small-volume drying is membrane separation process; Discrimination module: When the drying method is large-volume drying, the process switches to the generation module; when the drying method is small-volume drying, the chloromethane is dried using a membrane separation process. Generation module: Generates desiccant consumption based on target chloromethane concentration, desiccant process and pre-built first machine learning model; generates waste gas volume based on target chloromethane concentration, molecular sieve process and pre-built second machine learning model. Method determination module: Obtain the remaining amount of desiccant, obtain the first drying cost based on the desiccant consumption, obtain the second drying cost based on the waste gas volume, and determine the desiccant process or molecular sieve process for drying chloromethane based on the remaining amount of desiccant, the first drying cost, and the second drying cost.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed, implements a control method for determining the concentration of chloromethane in a storage tank according to any one of claims 1 to 8.

Images