Arsine reactor pressure control method and device, equipment, storage medium

Abstract

The application provides a hydrogen arsenide reaction kettle pressure control method and device, equipment and a storage medium, and belongs to the technical field of equipment pressure control. The method comprises the following steps: determining whether to perform pressure control based on a target pressure and a standard pressure; different reaction periods of substances in the hydrogen arsenide reaction kettle correspond to different standard pressures; in response to performing pressure control, determining a target pressure adjustment device based on a target reaction period; the target pressure adjustment device is at least one pressure adjustment device; determining a target pressure adjustment parameter based on a target difference, the target reaction period and the target pressure adjustment device; the target difference is a difference between the target pressure and the standard pressure; the pressure adjustment parameter corresponds to the pressure adjustment device one by one; for each pressure adjustment device, the pressure adjustment device is controlled based on the pressure adjustment parameter corresponding to the pressure adjustment device, so as to control the pressure of the current hydrogen arsenide reaction kettle. The application can improve the accuracy of hydrogen arsenide reaction kettle pressure control.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of device pressure control, and more particularly relates to a method and device for controlling the pressure of an arsine reaction kettle, equipment and a storage medium. BACKGROUND

[0002] Arsine is a highly toxic and flammable gas. The control of pressure during the synthesis of arsine is a core link for ensuring the safety of the reaction, improving the quality of the product and optimizing the process efficiency.

[0003] Traditional methods for controlling the pressure of an arsine reaction kettle mostly rely on a plurality of relatively fixed pressure thresholds. When the pressure in the arsine reaction kettle exceeds the maximum pressure threshold among the plurality of pressure thresholds or is lower than the minimum pressure threshold among the plurality of pressure thresholds, a pressure regulating valve or other device is controlled to adjust the pressure. However, the control precision and accuracy of the pressure adjustment by relying only on the relatively fixed pressure thresholds and the pressure adjustment equipment are low. For example, when the pressure of the arsine reaction kettle is in an abnormal pressure range, i.e., the pressure in the arsine reaction kettle exceeds the maximum pressure threshold among the plurality of pressure thresholds or is lower than the minimum pressure threshold among the plurality of pressure thresholds, the adjustment degree is not clear and the adjustment is stopped immediately when the pressure returns to the normal pressure range during the adjustment process. Therefore, the pressure after the adjustment is often at the edge of the normal pressure range, and with the progress of the reaction, the pressure of the arsine reaction kettle is easily raised or lowered to the abnormal pressure range in a short time, thereby triggering a new round of pressure adjustment. The adjustment frequency is high, and the control precision and accuracy are low.

[0004] Therefore, there is a need for a high-precision and accurate method for controlling the pressure of an arsine reaction kettle. SUMMARY

[0005] The application aims to provide a method and device for controlling the pressure of an arsine reaction kettle, equipment and a storage medium to improve the control precision and accuracy of the pressure of the arsine reaction kettle.

[0006] In a first aspect, the application provides a method for controlling the pressure of an arsine reaction kettle, comprising:

[0007] determining whether to perform pressure control based on a target pressure and a standard pressure; the target pressure is the pressure in the current arsine reaction kettle, and the standard pressure is determined based on a target reaction period; the target reaction period is the reaction period of the substance in the current arsine reaction kettle; different reaction periods of the substance in the arsine reaction kettle correspond to different standard pressures;

[0008] determining a target pressure adjustment device based on the target reaction period in response to performing pressure control; the target pressure adjustment device is at least one pressure adjustment device;

[0009] determining a target pressure adjustment parameter based on the target difference, the target reaction period and the target pressure adjustment device; the target difference is a difference between the target pressure and the standard pressure; the target pressure adjustment parameter includes at least one pressure adjustment parameter; the pressure adjustment parameter corresponds to the pressure adjustment device one by one;

[0010] For each pressure adjustment device, the pressure adjustment device is controlled based on the pressure adjustment parameter corresponding to the pressure adjustment device, so as to control the pressure of the current arsine reaction kettle.

[0011] In a second aspect, the embodiment of the present application provides a pressure control device for an arsine reaction kettle, which comprises:

[0012] The judgment module is configured to determine whether to perform pressure control based on a target pressure and a standard pressure; the target pressure is a pressure in a current arsine reaction kettle; the standard pressure is determined based on a target reaction period; the target reaction period is a reaction period of a substance in the current arsine reaction kettle; different reaction periods of the substance in the arsine reaction kettle correspond to different standard pressures.

[0013] The device determination module is configured to determine a target pressure adjustment device based on the target reaction period in response to performing pressure control; the target pressure adjustment device is at least one pressure adjustment device.

[0014] The adjustment parameter determination module is configured to determine a target pressure adjustment parameter based on the target difference, the target reaction period and the target pressure adjustment device; the target difference is a difference between the target pressure and the standard pressure; the target pressure adjustment parameter includes at least one pressure adjustment parameter; the pressure adjustment parameter corresponds to the pressure adjustment device one by one.

[0015] The control module is configured to control, for each pressure adjustment device, the pressure adjustment device based on the pressure adjustment parameter corresponding to the pressure adjustment device, so as to control the pressure of the current arsine reaction kettle.

[0016] In a third aspect, the embodiment of the present application provides an electronic device, which comprises a memory, a processor and a computer program stored in the memory and running on the processor; when the processor executes the computer program, the steps of the pressure control method for the arsine reaction kettle are implemented.

[0017] In a fourth aspect, the embodiment of the present application provides a computer readable storage medium, which stores a computer program; when the computer program is executed by a processor, the steps of the pressure control method for the arsine reaction kettle are implemented.

[0018] The pressure control method and device for the arsine reaction kettle, the equipment and the storage medium provided by the embodiment of the present application have the following beneficial effects:

[0019] The traditional method relies on a relatively fixed pressure threshold, and when the pressure is in the abnormal interval, the adjustment degree is not clear and the pressure returns to the normal interval immediately to stop adjusting, which causes the pressure to easily rise or fall to the abnormal interval in a short time during the reaction, the adjustment frequency is high, and the control precision and accuracy are low. The embodiments of the present application determine the standard pressure based on the target reaction period, and different reaction periods correspond to different standard pressures, which can more accurately fit the actual pressure demand of arsine reaction at different stages. At the same time, the target pressure adjustment parameter is determined according to the difference between the target pressure and the standard pressure, the target reaction period and the target pressure adjustment device, and the pressure adjustment device is finely controlled, avoiding the blindness of the traditional method adjustment, and improving the precision and accuracy of pressure control. The embodiments of the present application determine the appropriate pressure adjustment parameter according to the reaction period and the pressure difference, so that the pressure adjustment process is more scientific. When the pressure is abnormal, accurate adjustment can be carried out according to the determined parameter, avoiding the problems caused by the unclear adjustment degree and the immediate stop of the adjustment when the pressure returns to the normal interval in the traditional method, reducing the possibility of repeated rise or fall of the pressure to the abnormal interval in a short time, thereby reducing the frequency of pressure adjustment and improving the precision and accuracy of the pressure control of the arsine reaction kettle. BRIEF DESCRIPTION OF DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creating any creative labor.

[0021] Figure 1 The flowchart of the arsine reaction kettle pressure control method provided by an embodiment of the present application is shown in the figure.

[0022] Figure 2 The structural block diagram of the arsine reaction kettle pressure control device provided by an embodiment of the present application is shown in the figure.

[0023] Figure 3 The schematic block diagram of the electronic device provided by an embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0024] In the following description, specific details such as specific system structures, techniques, etc. are presented in order to thoroughly understand the embodiments of the present application. However, it should be clear to those skilled in the art that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits and methods are omitted to avoid unnecessary details that hinder the description of the present application.

[0025] For the purposes of the present application, the technical solutions and advantages will be made clearer in the following combined with the drawings through specific embodiments.

[0026] Please refer to Figure 1 , Figure 1 The flowchart of the pressure control method of the arsenic hydride reaction kettle provided by an embodiment of the present application can be executed by an electronic device, and the method can include S101-S104.

[0027] S101: determining whether to perform pressure control based on a target pressure and a standard pressure; the target pressure is the pressure in the current arsenic hydride reaction kettle, and the standard pressure is determined based on a target reaction period, the target reaction period being the reaction period of the substance in the current arsenic hydride reaction kettle; different reaction periods of the substance in the arsenic hydride reaction kettle correspond to different standard pressures.

[0028] In the embodiment, the target pressure refers to the actual pressure value inside the current arsenic hydride reaction kettle, i.e., the real-time pressure, which is used as a reference for pressure control to determine whether the current pressure state of the reaction kettle needs to be adjusted. The target pressure can be obtained by a pressure sensor arranged in the arsenic hydride reaction kettle. The standard pressure is a pressure standard value, i.e., the ideal pressure, which is set in advance for the target reaction period of the substance in the reaction kettle. Since the generation reaction of arsenic hydride has different characteristics (such as reaction rate, heat release / absorption intensity, etc.) at different reaction periods (such as the beginning of the reaction, the most intense reaction, and the approach to the end of the reaction), different pressure environments are needed to ensure the reaction efficiency and safety, so different reaction periods correspond to different standard pressures. The target reaction period refers to the reaction period of the substance in the current reaction kettle, which can be divided into the initial reaction period, the middle reaction period, and the final reaction period, etc.

[0029] In the embodiment, whether the pressure needs to be adjusted can be determined by comparing the target pressure and the standard pressure. For example, if the difference between the target pressure and the standard pressure is within a preset error range, no control is performed, otherwise, if the difference exceeds the preset error range, the pressure control process is started to adjust the actual pressure to the standard pressure or a certain range around the standard pressure. The preset error range can be set based on experience.

[0030] S102: in response to performing pressure control, determining a target pressure adjustment device based on the target reaction period; the target pressure adjustment device is at least one pressure adjustment device.

[0031] In the embodiment, if the subsequent pressure control action is triggered after the judgment, the target pressure adjustment device is determined based on the pre-determined mapping relationship and the target reaction period. The mapping relationship refers to the mapping relationship between the target reaction period and the target pressure adjustment device. The target pressure adjustment device refers to the device selected to adjust the pressure of the arsine reaction kettle at the current reaction period, which can be one device or a combination of multiple devices. The target pressure adjustment device can be a device that directly or indirectly adjusts the pressure. The device that directly adjusts the pressure can be an exhaust valve and a nitrogen inlet valve. The device that indirectly adjusts the pressure can be a feed valve and a reaction kettle outer jacket medium flow valve, etc. Among them, the feed valve can indirectly affect the reaction rate by adjusting the feed rate, thereby determining the gas generation amount and the pressure in the reaction kettle (the pressure in the reaction kettle can be understood as the gas pressure). Secondly, the gas pressure is positively correlated with the temperature, so the reaction kettle outer jacket medium flow valve can indirectly adjust the pressure by adjusting the temperature and flow of the medium in the reaction kettle outer jacket, that is, by the volume effect to indirectly control the pressure. In response to not performing pressure control, no action is performed.

[0032] S103: determining a target pressure adjustment parameter based on the target difference, the target reaction period and the target pressure adjustment device; the target difference is the difference between the target pressure and the standard pressure; at least one pressure adjustment parameter exists in the target pressure adjustment parameter; the pressure adjustment parameter corresponds to the pressure adjustment device one by one.

[0033] In the embodiment, the target difference should have a positive or negative sign, otherwise when the pressure adjustment parameter is determined, the adjustment direction cannot be determined. When the target difference is positive, it means that the target pressure is greater than the standard pressure, that is, the pressure of the current arsine reaction kettle is larger, so at this time the pressure adjustment device should be adjusted in the direction of reducing the pressure of the arsine reaction kettle; on the contrary, when the target difference is negative, it means that the target pressure is less than the standard pressure, that is, the pressure of the current arsine reaction kettle is smaller, so at this time the pressure adjustment device should be adjusted in the direction of increasing the pressure of the arsine reaction kettle. The target pressure adjustment parameter refers to the specific parameters and parameter values of the parameters that need to be set for each pressure adjustment device to make the pressure of the reaction kettle reach the standard pressure. For example, if the target device is an exhaust valve, the parameter can be to adjust the opening by 20%.

[0034] In the embodiment, the final target pressure adjustment parameter can be determined based on the target difference, the target reaction period and the target pressure adjustment device and by using a particle swarm algorithm, or other algorithm models such as a neural network model, a random forest model or a support vector machine model can be used. If the particle swarm algorithm is selected, its essence is a kind of optimization algorithm model, and its core is to find the optimal solution through the cooperation and iterative search of particles in the group.

[0035] S104: For each pressure adjusting device, control the pressure adjusting device based on the pressure adjusting parameter corresponding to the pressure adjusting device, to control the pressure of the current arsine reaction kettle.

[0036] In the embodiment, each pressure adjusting device refers to each independent device in the target pressure adjusting device. The pressure adjusting device is controlled according to the pressure adjusting parameter corresponding to the pressure adjusting device. It should be noted that the pressure adjusting device is controlled by the electronic device shown in the foregoing, for example, the exhaust valve is essentially an electromagnetic valve, rather than a manual valve. The various pressure adjusting devices can directly or indirectly control the pressure of the arsine reaction kettle, so that the pressure adjusting device is controlled based on the pressure adjusting parameter corresponding to the pressure adjusting device, so as to achieve the effect of controlling the pressure of the current arsine reaction kettle.

[0037] From the above, it can be seen that the conventional method relies on a relatively fixed pressure threshold. When the pressure is in the abnormal interval, the adjustment degree is not clear, and the adjustment is stopped immediately when the pressure returns to the normal interval, which causes the pressure to easily rise or fall to the abnormal interval in a short time during the reaction, the adjustment frequency is high, and the control precision and accuracy are low. The application embodiment determines the standard pressure based on the target reaction period, and different reaction periods correspond to different standard pressures, which can more accurately fit the actual pressure demand of the arsine reaction in different reaction periods. At the same time, the target pressure adjusting parameter is determined according to the difference between the target pressure and the standard pressure, the target reaction period, and the target pressure adjusting device, and the pressure adjusting device is finely controlled, avoiding the blindness of the adjustment of the conventional method, and improving the precision and accuracy of the pressure control. The application embodiment determines the appropriate pressure adjusting parameter according to the reaction period and the pressure difference, so that the pressure adjusting process is more scientific. When the pressure is abnormal, accurate adjustment can be performed according to the determined parameter, avoiding the problems caused by the unclear adjustment degree and the immediate stop of the adjustment when the pressure returns to the normal interval in the conventional method, reducing the possibility of repeated rise or fall of the pressure to the abnormal interval in a short time, thereby reducing the frequency of pressure adjustment and improving the precision and accuracy of the pressure control of the arsine reaction kettle.

[0038] In an embodiment of the application, the target pressure adjusting parameter is determined based on the target difference, the target reaction period, and the target pressure adjusting device, including:

[0039] Determine the particle dimension of the particle swarm algorithm based on the target pressure adjusting device;

[0040] Determine the hyperparameter of the particle swarm algorithm based on the target reaction period;

[0041] The fitness function of the particle swarm algorithm is determined based on the pressure adjustment difference value and the safety risk index; wherein the pressure adjustment difference value is determined based on the target pressure adjustment value and the target difference value; the target pressure adjustment value refers to the pressure change value of the arsenic hydride reaction kettle when the current population optimal position of the particle swarm algorithm is used as the target pressure adjustment parameter to control the target pressure adjustment device; the safety risk index is used to represent the leakage risk of the arsenic hydride reaction kettle when the current population optimal position of the particle swarm algorithm is used as the target pressure adjustment parameter to control the target pressure adjustment device; the weight corresponding to the pressure adjustment difference value and the weight corresponding to the safety risk index in the fitness function are determined based on the target reaction period;

[0042] The iterative calculation is performed based on the particle dimension, the hyperparameter and the fitness function until the fitness function meets the preset iteration condition or the iteration number reaches the preset iteration threshold, and the target population optimal position is obtained. The particle position corresponding to the target population optimal position is determined as the target pressure adjustment parameter.

[0043] In the present embodiment, the particle dimension can be understood as the number of coordinate axes of the solution space, corresponding to the number of parameters to be optimized, and each pressure adjustment device corresponds to a parameter dimension. For example, if the target device is an intake valve and an exhaust valve, two parameters, intake valve opening degree and exhaust valve opening degree, need to be optimized, and the particle dimension = 2. In addition to the specific numerical value described above, the particle dimension can also include specific parameters, such as the intake valve opening degree and the exhaust valve opening degree described above, that is, the particle dimension is 2 and the particle dimension can represent [intake valve opening degree, exhaust valve opening degree]. The mathematical representation of each particle position is, for example, represented as a vector x = [x1, x2], wherein x1 is the intake valve opening degree and x2 is the exhaust valve opening degree.

[0044] In the embodiment, the hyperparameters refer to parameters for controlling the search behavior of the algorithm, which can include inertia weight, individual learning factor, and group learning factor, etc. Different reaction periods can correspond to different hyperparameters based on their own characteristics. For example, the reaction speed in the middle period of the reaction is the fastest and the reaction is violent, so when the material reaction of the arsine reactor is in the middle period of the reaction, the iteration result should be determined more quickly. At this time, the inertia weight in the particle swarm algorithm can be appropriately set to a smaller value compared with the inertia weight in the early period of the reaction and the inertia weight in the late period of the reaction. The inertia weight is a key parameter in the particle velocity update formula, which determines the degree of retention of the particle's historical speed. When the inertia weight is large, the particle will retain more historical speed and tend to wander in the solution space, and the global exploration ability is enhanced, so the process of focusing on the optimal solution will be slower. Conversely, when the inertia weight is small, the particle's retention of historical speed is weak, and it relies more on the optimal solution of itself and the group for adjustment. A smaller inertia weight can accelerate the convergence of the particle to the optimal solution, and the convergence speed is faster. The hyperparameter values corresponding to different reaction periods can be determined based on a preset mapping table. The mapping table is used to represent different reaction periods and corresponding hyperparameter values. The specific parameter values in the mapping table can be set based on commonly used parameter values, but need to meet the aforementioned limiting conditions (the inertia weight corresponding to the middle period of the reaction is less than the inertia weight corresponding to the early period of the reaction and the inertia weight corresponding to the late period of the reaction). The mapping table can contain part of the hyperparameters or all of the hyperparameters. When the mapping table contains part of the hyperparameters, the remaining hyperparameters not embodied in the mapping table can be set to the default value of the particle swarm algorithm.

[0045] In the embodiment, the fitness function refers to a mathematical expression for evaluating the pros and cons of parameter combinations. In the embodiment, it can be wherein, represents the fitness function, represents the pressure adjustment difference value, represents the safety risk index, represents the weight corresponding to the pressure adjustment difference value, represents the weight corresponding to the safety risk index. Wherein, , represents the target difference value, represents the target pressure adjustment value, that is, the pressure change value of the arsine reactor when the current population optimal position of the particle swarm algorithm is used as the target pressure adjustment parameter to control the target pressure adjustment device. It should be noted that the calculation process of should contain numerical values and signs, and there is no unit in the calculation process.

[0046] In the embodiment, the pressure adjustment amount of each pressure adjustment device corresponding to the parameter adjustment when the parameter adjustment is performed should be determined in advance, and then the corresponding relationship between the parameter adjustment amount of each pressure adjustment device and the pressure adjustment amount of the reactor is obtained. For example, a plurality of experiments and data statistics are performed in a period when other pressure adjustment device parameters are unchanged and the pressure in the reactor is stable (for example, at the end of the reaction or directly taking the empty reactor without the reaction process as the experimental object), and it is obtained that the valve opening degree of the exhaust valve is opened by 1 degree, and the pressure (measured after the pressure is stable) of the arsine reactor is decreased by N MPa. The corresponding relationship between the parameter adjustment amount of each pressure adjustment device and the pressure adjustment amount of the reactor can be obtained through a limited number of experiments, and the corresponding relationship can be linear or nonlinear. Finally, the first mapping table is formed, and the first mapping table is used to represent the corresponding relationship between the parameter adjustment amount of each pressure adjustment device and the pressure adjustment amount of the arsine reactor. In the embodiment, the output of the particle swarm algorithm after iteration is the target pressure adjustment parameter, and the essence is also the parameter adjustment amount. Therefore, the target pressure adjustment parameter and the first mapping table described above can be used to determine the parameter adjustment amount of each pressure adjustment device in the embodiment. .

[0047] In the embodiment, the leakage risk of the arsine reactor corresponding to the parameter adjustment of each pressure adjustment device when the parameter adjustment is performed should also be set in advance, which can be set based on experience. For example, when the valve opening degree of the exhaust valve is too large, the sealing failure can be caused; the opening degree changes too fast, and the pipeline vibration can be caused. The importance of each pressure adjustment device when the pressure is controlled and the corresponding risk can be determined based on experience by a person skilled in the art, and the second mapping table is set in advance. The second mapping table is used to represent the corresponding relationship between the parameter adjustment amount of each pressure adjustment device and the leakage risk of the arsine reactor. The second mapping table is not described in detail in the embodiment. Therefore, the target pressure adjustment parameter and the second mapping table described above can be used to determine the parameter adjustment amount of each pressure adjustment device in the embodiment. , is a dimensionless parameter. The larger the value is, the greater the corresponding leakage risk is, that is, the leakage risk and the safety risk index are positively correlated.

[0048] In the embodiment, the iteration calculation can be performed based on the aforementioned particle dimension, hyperparameters and fitness function, other parameters in the particle swarm algorithm can be determined as the default values of the particle swarm algorithm, the solution space can be set based on the limitations of each pressure adjustment device, for example, the dimension of the opening of the valve, the upper limit of which can be 80%. The stop condition of iteration can be that the fitness function meets the preset iteration stop condition or the number of iterations reaches the preset iteration threshold. The preset iteration stop condition can be that the fitness function value is less than the preset fitness threshold for M times continuously after N times of continuous iteration, and the preset fitness threshold can be a value determined based on experience. N and M can be set as default values or other values determined based on experience. The preset iteration threshold can be 200 times. The fitness function value refers to a value calculated based on the fitness function and the population optimal position of the current particle swarm algorithm.

[0049] From the above, it can be concluded that the embodiments of the present application can determine the hyperparameters of the particle swarm algorithm, such as the inertia weight, according to the target reaction period. Different reaction periods have different characteristics, such as fast and violent reaction speed in the middle of the reaction. At this time, a smaller inertia weight is appropriately set, which can accelerate the convergence of particles to the optimal solution, quickly determine the iteration result, and enable the algorithm to efficiently search for the optimal parameters in different reaction periods, thereby further improving the accuracy of the pressure adjustment parameters. The embodiments of the present application can determine the fitness function based on the pressure adjustment difference and the safety risk index, and the weight corresponding to the pressure adjustment difference and the weight corresponding to the safety risk index are determined based on the target reaction period. The pressure adjustment difference reflects the deviation degree of the pressure adjustment value of the reaction kettle when the current parameters are controlled from the target difference, and the larger the deviation degree, the larger the range shown in the foregoing. The safety risk index characterizes the leakage risk in the control process. The embodiments of the present application comprehensively consider these two factors and their weights, the fitness function can comprehensively evaluate the advantages and disadvantages of the parameter combination, guide the particle swarm algorithm to search in the direction of meeting the pressure adjustment requirement and reducing the safety risk, and finally obtain more scientific and reasonable target pressure adjustment parameters, thereby improving the precision of pressure control.

[0050] In an embodiment of the present application, the determination method of the weight corresponding to the pressure adjustment difference and the weight corresponding to the safety risk index in the fitness function comprises:

[0051] In response to the target reaction period being the initial stage of the reaction, the weight corresponding to the pressure adjustment difference is determined as a first value, and the weight corresponding to the safety risk index is determined as a second value;

[0052] In response to the target reaction period being the middle stage of the reaction, the weight corresponding to the pressure adjustment difference is determined as a third value, and the weight corresponding to the safety risk index is determined as a fourth value;

[0053] In response to the target reaction period being the end of the reaction, the weight corresponding to the pressure adjustment difference value is determined as a fifth numerical value, and the weight corresponding to the safety risk index is determined as a sixth numerical value;

[0054] The reaction initial stage is a reaction period with a target time as a first starting time and a time after a first time length from the first starting time as a first ending time. The target time is the time when arsine starts to be generated. The reaction middle stage is a reaction period with the first ending time as a second starting time and a time after a second time length from the second starting time as a second ending time. The reaction end stage is a reaction period with the second ending time as a third starting time and a time after a third time length from the third starting time as a third ending time. The first numerical value and the fifth numerical value are both greater than the third numerical value. The second numerical value and the sixth numerical value are both less than the fourth numerical value.

[0055] In the embodiment, when the target reaction period is the reaction middle stage, the reaction in the arsine reaction kettle is intense, the pressure changes quickly, and the risk of safety hazards is relatively large. Therefore, in the reaction middle stage, the weight corresponding to the safety risk index in the fitness function should be larger than when the target reaction period is the reaction initial stage or the reaction end stage. Therefore, the second numerical value and the sixth numerical value are both less than the fourth numerical value. Since the sum of the weight corresponding to the pressure adjustment difference value and the weight corresponding to the safety risk index is 1, the first numerical value and the fifth numerical value are both greater than the third numerical value. In the embodiment, the first time length, the second time length, and the third time length can be set based on experience. The first numerical value, the second numerical value, the third numerical value, the fourth numerical value, the fifth numerical value, and the sixth numerical value can be determined based on experience or multiple experiments.

[0056] From the above, the embodiment of the application considers that when the target reaction period is the reaction middle stage, the reaction in the arsine reaction kettle is intense, the pressure changes quickly, and the risk of safety hazards is relatively large. At this time, the weight corresponding to the safety risk index is determined as the larger fourth numerical value, and the weight corresponding to the pressure adjustment difference value is determined as the smaller third numerical value. When the algorithm optimizes the parameters, more attention is paid to the safety risk in the control process. By balancing the pressure adjustment and the safety risk, the reaction in the middle stage is ensured to be stable under the premise of safety, the probability of accidents is reduced, and the reliability of the entire reaction process is ensured.

[0057] In an embodiment of the application, the target pressure adjustment device corresponding to each reaction period is pre-set. If the target pressure adjustment device corresponding to the reaction initial stage is consistent with the target pressure adjustment device corresponding to the reaction middle stage;

[0058] Then, iterative calculation is performed based on the particle dimension, the hyperparameter, and the fitness function until the fitness function meets a preset iteration condition or the number of iterations reaches a preset iteration threshold, including:

[0059] If the target reaction period is the middle reaction period, and overpressure control is performed in the initial reaction period of the same reaction process, the historical population optimal position is called;

[0060] The target solution space is determined based on the historical population optimal position; the target solution space is used to limit the range of the target pressure adjustment parameter;

[0061] Iterative calculation is performed based on the particle dimension, the hyperparameter, the target solution space, and the fitness function until the fitness function meets the preset iteration condition or the number of iterations reaches the preset iteration threshold.

[0062] In this embodiment, the present application considers that if the target pressure adjustment device corresponding to the initial reaction period is consistent with the target pressure adjustment device corresponding to the middle reaction period and the target reaction period is the middle reaction period, and overpressure control is performed in the initial reaction period of the same reaction process, the historical population optimal position is called, the target solution space can be determined based on the historical population optimal position of the particle swarm optimization algorithm in the initial reaction period of the same reaction process. The reason is that for the same reaction process, if the same device is used in the initial period and the middle period, the optimal parameters usually have correlation (for example, the reasonable range of the valve opening is similar). Therefore, the middle period optimization can refer to the initial period result. The same reaction process refers to the process in which the reaction is not interrupted or the termination time of the reaction end period is not reached.

[0063] In this embodiment, the historical population optimal position refers to the optimal parameter combination found by the particle swarm optimization algorithm when performing pressure control in the initial reaction period, that is, a set of device parameter values that can minimize the fitness function. The target solution space refers to the solution space when the particle swarm optimization algorithm is solved at present (that is, when the target reaction period is the middle reaction period), which is the limited range of parameter search. The target solution space is smaller than the initial solution space, and the initial solution space refers to the solution space corresponding to the iteration of the particle swarm optimization algorithm in the initial reaction period of the same reaction process.

[0064] It should be noted that the target pressure adjustment device corresponding to the initial reaction period is consistent with the target pressure adjustment device corresponding to the middle reaction period, specifically referring to the number and type of the target pressure adjustment device being completely consistent, that is, the particle dimension is completely consistent.

[0065] In this embodiment, after the solution space is reduced, the search efficiency of the particle swarm optimization algorithm can be improved, secondly, the historical optimal solution is used as the starting point, which reduces the risk of falling into local optimum, and is suitable for periods with intense reaction and frequent pressure change.

[0066] In the embodiment, if the target pressure adjustment device corresponding to the initial reaction stage is inconsistent with the target pressure adjustment device corresponding to the middle reaction stage, the target solution space of the particle swarm algorithm in the middle reaction stage cannot be determined based on the historical optimal population position in the initial reaction stage of the same reaction process. In this case, the solution space of the particle swarm algorithm in the initial reaction stage of the same reaction process can be iterated, that is, a default or pre-set value.

[0067] In the embodiment, the target solution space is determined based on the historical optimal population position, including:

[0068] determining positions of each sub-optimal solution particle, the position of the sub-optimal solution particle being a position of the sub-optimal solution particle in the solution space of the particle swarm algorithm when the historical optimal population position is determined, the sub-optimal solution particle being a particle in the particle swarm algorithm having a distance less than a pre-set distance from the particle in the historical optimal population position;

[0069] determining a target fluctuation based on the positions of each sub-optimal solution particle, the target fluctuation being used to quantify a fluctuation range of a solution parameter of the particle swarm algorithm in an iteration process, the solution parameter being a dimension of a particle of the particle swarm algorithm;

[0070] determining the target solution space based on the historical optimal population position and the target fluctuation.

[0071] In the embodiment, the position of the sub-optimal solution particle refers to a parameter combination corresponding to a particle having a relatively close distance from the historical optimal population position (that is, an optimal parameter found in the initial reaction stage) in the particle swarm optimization in the initial reaction stage, that is, a position coordinate. That is, a particle in the particle swarm algorithm having a distance less than a pre-set distance from the historical optimal particle.

[0072] The target fluctuation is a parameter variation range calculated based on a distribution feature of the position of the sub-optimal solution particle, quantifying a dispersion degree of the sub-optimal solution particle relative to the historical optimal position, and reflecting a normal fluctuation boundary of the parameter. For example, the maximum parameter value and the minimum parameter value of the sub-optimal solution particle can be counted for each parameter dimension such as an opening degree and a power, and the fluctuation range = the maximum value - the minimum value. Or the standard deviation of the sub-optimal solution particle in the dimension can be calculated, and the fluctuation range = 2 x the standard deviation (covering 95% of reasonable values). In the formula, the multiplication by 2 indicates the up and down fluctuation. If the opening degree of the sub-optimal solution particle is distributed in 38% to 42%, the target fluctuation of the opening degree is “± 2%”. If the power is distributed in 48 to 52 kW, the target fluctuation of the power is “± 2 kW”.

[0073] The limited range of the target solution space reaction mid-term parameter search is a parameter interval with the historical population optimal position as the center and the target fluctuation as the boundary. It is used to limit the search range of the particle swarm optimization algorithm, avoid parameters exceeding the reasonable interval (such as the maximum opening allowed by the device, the safety threshold), and reduce invalid search. For example, combined with the historical optimal position [40%, 50kW] and the target fluctuation [±2%, ±2kW], the target solution space is: exhaust valve opening: 38%~42%, pump power: 48kW~52kW. The historical optimal position is the effective solution verified in the early stage, and the target fluctuation is the safety boundary close to the optimal solution. The solution space formed by the combination of the two can not only guarantee the effectiveness of the parameters, but also narrow the search range and reduce the calculation amount of the algorithm.

[0074] From the above, it can be concluded that in the case of using the same target pressure adjustment device in the reaction initial stage and the reaction mid-stage, when the target reaction period is the reaction mid-stage and the overpressure control is performed in the reaction initial stage, the target solution space is determined by calling the historical population optimal position. The target solution space is smaller than the initial solution space, so that the particles do not need to blindly explore in a too large range during the search process, reducing unnecessary calculation and iteration times, thereby improving the search efficiency of the algorithm and speeding up the process of converging to the optimal solution. The historical population optimal position is used as the starting point of the particle swarm optimization algorithm search in the reaction mid-stage, providing valuable prior information for the algorithm. In the reaction process, when the same device is used in the initial stage and the mid-stage, the optimal parameters usually have correlation, and the historical optimal solution provides a good starting point for parameter optimization in the mid-stage. The particles start searching from this point, which can move faster in a better direction, avoiding the blind exploration process that may occur when starting from a random initial point, further improving the search efficiency of the algorithm, so that the algorithm can find the optimal parameter combination that meets the requirements of the fitness function faster. When determining the target solution space, not only the historical population optimal position is considered, but also the position information of the suboptimal solution particles. The suboptimal solution particles are particles that are close to the historical optimal particles, and their position distribution reflects the reasonable fluctuation range of the parameters in the particle swarm optimization algorithm search process in the reaction initial stage.

[0075] In an embodiment of the present application, the hyperparameters of the particle swarm optimization algorithm include:

[0076] Determining the hyperparameters of the particle swarm optimization algorithm based on the target reaction period includes:

[0077] In response to the target reaction period being the reaction initial stage, the inertia weight is set to a seventh value;

[0078] In response to the target reaction period being the reaction mid-stage, the inertia weight is set to an eighth value;

[0079] In response to the target reaction period being the reaction final stage, the inertia weight is set to a ninth value; the seventh value and the ninth value are both greater than the eighth value.

[0080] In the embodiment, the reaction speed is the fastest and the reaction is the most violent in the middle period of the reaction, so the iteration result should be determined more quickly when the substance in the arsenic hydride reaction kettle is in the middle period of the reaction. The inertia weight can adjust the time for the particle swarm algorithm to solve the optimal solution to a certain extent. When the inertia weight is larger, the process of focusing on the optimal solution will be slower, that is, the solving time will be longer. When the inertia weight is smaller, the particles can converge to the optimal solution faster, that is, the solving time will be shorter. Therefore, the seventh value and the ninth value are both larger than the eighth value. The seventh value, the eighth value and the ninth value can be determined based on experience.

[0081] It should be noted that although a smaller inertia weight may cause the particles to fall into a local optimal solution, when the arsenic hydride reaction kettle is currently in the middle period of the reaction, the primary goal is to ensure rapid output and make corresponding adjustments, and the local optimal solution can also meet the optimization target in the fitness function to a certain extent, but it is not the optimal solution, and it will not cause serious deviation from the optimization target. In the embodiment, when the target reaction period is in the middle period of the reaction, the preset iteration threshold of the particle swarm algorithm can also be reduced based on the first iteration number. The first iteration number can be set based on experience or preference, for example, 50 times.

[0082] Secondly, because the inertia weight in the initial period of the reaction is larger than that in the middle period of the reaction, the global exploration ability in the initial period of the reaction is strong, and the search range in the solution space is wider than that in the middle period of the reaction. Therefore, the positions of the population optimal position and the suboptimal solution particles found in the initial period of the reaction are more accurate, so the target solution space determined by the experience of the particle swarm algorithm iteration in the initial period of the reaction is also more accurate, which can reduce the risk of falling into a local optimal solution to a certain extent.

[0083] From the above, it can be concluded that the embodiments of the present application take into account that different reaction periods have different characteristics in the reaction process of the arsine reaction kettle. The reaction speed is the fastest and most intense in the middle of the reaction, and the demand for quickly determining the pressure adjustment parameter to stabilize the reaction is extremely urgent. The embodiments of the present application dynamically set the inertia weight of the particle swarm algorithm according to the target reaction period, and set the inertia weight to a smaller eighth value when in the middle of the reaction. Since the inertia weight is small, the particles in the particle swarm algorithm can accelerate the convergence to the optimal solution, and the convergence speed is faster, thereby greatly shortening the solution time. This enables the pressure adjustment parameter that meets the requirements of the fitness function to be obtained more quickly in the middle of the reaction, and the pressure in the reaction kettle is effectively controlled in time, ensuring that the reaction proceeds quickly in a stable environment and avoiding problems such as loss of control of the reaction due to untimely parameter adjustment. Although a smaller inertia weight may cause particles to fall into a local optimal solution in the middle of the reaction, in the scheme of the present application, on the one hand, a larger inertia weight is used in the initial stage of the reaction, so that the particle swarm algorithm has strong global exploration ability and can search widely in the solution space, thereby finding a more accurate population optimal position and suboptimal solution particle position. Through the foregoing target solution space determination method, the target solution space in the middle of the reaction is determined based on these accurate position information, providing a reasonable range and direction for the search of particles in the middle of the reaction, reducing the possibility of particles falling into a local optimal solution. On the other hand, in the middle of the reaction, the local optimal solution can meet the optimization objective in the fitness function to a certain extent, but it is not an absolute optimal solution and will not cause serious deviation in the control effect of the reaction, so a certain degree of local optimization can be accepted on the premise of ensuring the rapid output of the parameter adjustment result.

[0084] In an embodiment of the present application, the arsine reaction kettle pressure control method further comprises:

[0085] In response to the absolute value of the target difference being greater than the preset alarm threshold, an alarm information is output; the alarm information is used to represent that the pressure of the current arsine reaction kettle is out of the self-control range.

[0086] In the embodiment, the preset alarm threshold can be determined based on the maximum bearing pressure of the arsine reaction kettle, for example, can be set to a certain proportion of the maximum bearing pressure, or can be determined based on experience. The alarm information can be an alarm signal, such as an audible and visual alarm, a system pop-up window, or an SMS notification. The self-control range refers to the range in which the automatic control system can independently and effectively maintain the pressure in a reasonable interval during the pressure control process of the arsine reaction kettle.

[0087] As can be seen from the above, this embodiment of the application, by setting a preset alarm threshold and outputting alarm information in response to the absolute value of the target difference exceeding the threshold, can monitor abnormal pressure changes inside the reactor in real time and with high sensitivity. This allows operators to be aware of abnormal pressure conditions immediately, gaining valuable time to take timely countermeasures.

[0088] Corresponding to the pressure control method of the arsine reactor in the above embodiment, Figure 2 This is a structural block diagram of an arsine reactor pressure control device provided in one embodiment of this application. For ease of explanation, only the parts relevant to the embodiment of this application are shown. References Figure 2 The pressure control device 20 for the arsine reactor includes: a judgment module 21, an equipment determination module 22, an adjustment parameter determination module 23, and a control module 24.

[0089] The judgment module 21 is used to determine whether to perform pressure control based on the target pressure and the standard pressure. The target pressure is the current pressure in the arsine reactor, and the standard pressure is determined based on the target reaction period, which is the reaction period of the substances in the current arsine reactor. Different reaction periods of the substances in the arsine reactor correspond to different standard pressures.

[0090] Equipment determination module 22 is used to determine a target pressure regulating device based on a target response period in response to pressure control; the target pressure regulating device is at least one pressure regulating device;

[0091] The parameter determination module 23 is used to determine the target pressure adjustment parameters based on the target difference, the target reaction period, and the target pressure adjustment equipment; the target difference is the difference between the target pressure and the standard pressure; at least one pressure adjustment parameter exists among the target pressure adjustment parameters; and there is a one-to-one correspondence between the pressure adjustment parameters and the pressure adjustment equipment.

[0092] The control module 24 is used to control each pressure adjustment device based on the corresponding pressure adjustment parameters to control the pressure of the current arsine reactor.

[0093] In one embodiment of this application, the parameter determination module 23 is specifically used to determine the particle dimension of the particle swarm algorithm based on the target pressure adjustment device;

[0094] The hyperparameters of the particle swarm optimization algorithm are determined based on the target reaction period;

[0095] The fitness function of the particle swarm algorithm is determined based on a pressure adjustment difference value and a safety risk index, wherein the pressure adjustment difference value is determined based on a target pressure adjustment value and a target difference value; the target pressure adjustment value refers to a pressure change value of the arsenic hydride reaction kettle when the current population optimal position of the particle swarm algorithm is used as a target pressure adjustment parameter to control the target pressure adjustment device; the safety risk index is used to represent a leakage risk of the arsenic hydride reaction kettle when the current population optimal position of the particle swarm algorithm is used as the target pressure adjustment parameter to control the target pressure adjustment device; and weights corresponding to the pressure adjustment difference value and the safety risk index in the fitness function are determined based on a target reaction period.

[0096] The iterative calculation is performed based on the particle dimension, the hyperparameter and the fitness function until the fitness function meets a preset iteration condition or the number of iterations reaches a preset iteration threshold, and the target population optimal position is obtained, and the particle position corresponding to the target population optimal position is determined as the target pressure adjustment parameter.

[0097] In an embodiment of the present application, the arsenic hydride reaction kettle pressure control device 20 further comprises a weight determination module configured to determine the weight corresponding to the pressure adjustment difference value as a first value and the weight corresponding to the safety risk index as a second value in response to the target reaction period being a reaction initial period.

[0098] In response to the target reaction period being a reaction middle period, the weight corresponding to the pressure adjustment difference value is determined as a third value, and the weight corresponding to the safety risk index is determined as a fourth value.

[0099] In response to the target reaction period being a reaction final period, the weight corresponding to the pressure adjustment difference value is determined as a fifth value, and the weight corresponding to the safety risk index is determined as a sixth value.

[0100] The reaction initial period is a reaction period with a target time as a first starting time and a time after a first time length from the first starting time as a first ending time; the target time is a time when arsenic hydride starts to be generated; the reaction middle period is a reaction period with the first ending time as a second starting time and a time after a second time length from the second starting time as a second ending time; the reaction final period is a reaction period with the second ending time as a third starting time and a time after a third time length from the third starting time as a third ending time; the first value and the fifth value are both greater than the third value; and the second value and the sixth value are both less than the fourth value.

[0101] In an embodiment of the present application, the target pressure adjustment device corresponding to each reaction period is pre-set, and if the target pressure adjustment device corresponding to the reaction initial period is consistent with the target pressure adjustment device corresponding to the reaction middle period.

[0102] The adjustment parameter determination module 23 is further configured to, if the target reaction period is the middle reaction period and the overpressure control is performed in the initial reaction period of the same reaction process, retrieve the historical population optimal position; the historical population optimal position is the population optimal position when the overpressure control is performed in the initial reaction period of the same reaction process.

[0103] The target solution space is determined based on the historical population optimal position; the target solution space is used to limit the range of the target pressure adjustment parameter.

[0104] The iterative calculation is performed based on the particle dimension, the hyperparameter, the target solution space and the fitness function until the fitness function meets the preset iteration condition or the iteration number reaches the preset iteration threshold.

[0105] In an embodiment of the present application, the adjustment parameter determination module 23 is further configured to determine each suboptimal solution particle position; the suboptimal solution particle position is the position of the suboptimal solution particle in the solution space of the particle swarm algorithm when the historical population optimal position is determined; the suboptimal solution particle is a particle in the particle swarm algorithm whose distance to the particle in the historical population optimal position is less than a preset distance;

[0106] The target fluctuation is determined based on each suboptimal solution particle position; the target fluctuation is used to quantify the fluctuation range of the solution parameter of the particle swarm algorithm in the iteration process; the solution parameter is the particle dimension of the particle swarm algorithm.

[0107] The target solution space is determined based on the historical population optimal position and the target fluctuation.

[0108] In an embodiment of the present application, the hyperparameter of the particle swarm algorithm includes: an inertia weight.

[0109] The adjustment parameter determination module 23 is further configured to, in response to the target reaction period being the initial reaction period, set the inertia weight to a seventh numerical value;

[0110] In response to the target reaction period being the middle reaction period, the inertia weight is set to an eighth numerical value;

[0111] In response to the target reaction period being the final reaction period, the inertia weight is set to a ninth numerical value; the seventh numerical value and the ninth numerical value are both greater than the eighth numerical value.

[0112] In an embodiment of the present application, the arsine reactor pressure control device 20 further comprises: an alarm module configured to, in response to the absolute value of the target difference being greater than a preset alarm threshold, output an alarm information; the alarm information is used to indicate that the pressure of the current arsine reactor is out of the self-control range.

[0113] Referring to Figure 3 , Figure 3 The electronic device provided in an embodiment of the present application is shown in a schematic block diagram. As shown inFigure 3 The electronic device 300 in the embodiment shown can include one or more processors 301, one or more input devices 302, one or more output devices 303, and one or more memories 304. The above-mentioned processors 301, input devices 302, output devices 303, and memories 304 complete communication with each other through a communication bus 305. The memory 304 is configured to store a computer program, and the computer program includes program instructions. The processor 301 is configured to execute the program instructions stored in the memory 304. The processor 301 is configured to invoke the program instructions to execute the functions of each module / unit in the above-mentioned device embodiments, for example Figure 2 The functions of the determination module 21, the device determination module 22, the adjustment parameter determination module 23, and the control module 24 are shown.

[0114] It should be understood that, in the embodiments of the present application, the processor 301 can be a central processing unit (CPU), and the processor can also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0115] The input device 302 can include a touchpad, a fingerprint collection sensor (used to collect fingerprint information and direction information of a fingerprint of a user), a microphone, etc., and the output device 303 can include a display (LCD, etc.), a loudspeaker, etc.

[0116] The memory 304 can include read-only memory and random access memory, and provide instructions and data for the processor 301. A portion of the memory 304 can also include non-volatile random access memory. For example, the memory 304 can also store device type information.

[0117] In specific implementations, the processor 301, the input device 302, and the output device 303 described in the embodiments of the present application can execute the implementation manners described in the arsenic hydride reaction kettle pressure control method provided by the embodiments of the present application, and can also execute the implementation manners of the electronic device described in the embodiments of the present application, which will not be described here.

[0118] In another embodiment of the present application, a computer readable storage medium is provided, which stores a computer program. The computer program includes program instructions, which, when executed by a processor, implement all or part of the processes of the above-mentioned embodiment methods. The computer program can also instruct related hardware to complete the implementation. The computer program can be stored in a computer readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or some intermediate form. The computer readable medium can include any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0119] The computer readable storage medium can be an internal storage unit of the electronic device of any of the preceding embodiments, such as a hard disk or a memory of the electronic device. The computer readable storage medium can also be an external storage device of the electronic device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Further, the computer readable storage medium can include both the internal storage unit and the external storage device of the electronic device. The computer readable storage medium is used to store the computer program and other programs and data required by the electronic device. The computer readable storage medium can also be used to temporarily store data that has been output or will be output.

[0120] Those skilled in the art can appreciate that the modules / units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. In order to clearly illustrate the interchangeability of hardware and software, the components and steps of the examples have been described in general terms in the above description. Whether the functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. A person skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0121] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the electronic device and the units described above can refer to the corresponding processes in the above-mentioned method embodiments, which will not be described here.

[0122] In several embodiments provided in the present application, it should be understood that the disclosed electronic device and method can be implemented in other manners. For example, the division of the above-described apparatus embodiments is merely an example, and there can be other division manners. For example, multiple modules or units can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections can be indirect couplings or communication connections through some interfaces, or can be in electrical, mechanical or other forms.

[0123] The modules or units illustrated as separate parts can or can not be physically separate, and the parts illustrated as modules or units can or can not be physical modules or units, i.e., can be located in one place, or can be distributed on multiple network modules or units. Some or all of the modules or units can be selected according to actual needs to achieve the purposes of the embodiments of the present application.

[0124] In addition, each functional module / unit in each embodiment of the present application can be integrated into a processing module / unit, or each module / unit can exist physically separately, or two or more modules / units can be integrated into one module / unit. The integrated module / unit can be implemented in the form of hardware or in the form of a software functional module / unit.

[0125] The above is merely specific embodiments of the present application, and the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A pressure control method for an arsine reactor, characterized by, The method comprises the following steps: determining whether to perform pressure control based on a difference between a target pressure and a standard pressure; the target pressure is the pressure in the current arsine reactor, and the standard pressure is determined based on a target reaction period, the target reaction period being the reaction period of the substance in the current arsine reactor; different reaction periods of the substance in the arsine reactor correspond to different standard pressures; the reaction period comprises a reaction initial period, a reaction middle period and a reaction final period; in response to performing pressure control, determining a target pressure adjustment device based on the target reaction period; the target pressure adjustment device is at least one pressure adjustment device; determining the particle dimension of the particle swarm algorithm based on the target pressure adjustment device; determining the hyperparameter of the particle swarm algorithm based on the target reaction period; determining the fitness function of the particle swarm algorithm based on a pressure adjustment difference and a safety risk index; the pressure adjustment difference is determined based on a target pressure adjustment value and a target difference; the safety risk index is used to represent the leakage risk of the arsine reactor when the current population optimal position of the particle swarm algorithm is taken as the target pressure adjustment parameter to control the target pressure adjustment device; the weight corresponding to the pressure adjustment difference and the weight corresponding to the safety risk index in the fitness function are determined based on the target reaction period; performing iterative calculation based on the particle dimension, the hyperparameter and the fitness function until the fitness function meets a preset iteration condition or the iteration number reaches a preset iteration threshold, obtaining a target population optimal position, and determining the particle position corresponding to the target population optimal position as the target pressure adjustment parameter; the target difference is the difference between the target pressure and the standard pressure; at least one pressure adjustment parameter exists in the target pressure adjustment parameter; the pressure adjustment parameter corresponds to the pressure adjustment device one by one; for each pressure adjustment device, controlling the pressure adjustment device based on the pressure adjustment parameter corresponding to the pressure adjustment device to control the pressure of the current arsine reactor and adjust the actual pressure in the arsine reactor to the standard pressure.

2. The arsine reactor pressure control method of claim 1, wherein, The target pressure adjustment value refers to the pressure change value of the arsine reactor when the current population optimal position of the particle swarm algorithm is taken as the target pressure adjustment parameter to control the target pressure adjustment device.

3. The arsine reactor pressure control method of claim 2, wherein, The determination method of the weight corresponding to the pressure adjustment difference and the weight corresponding to the safety risk index in the fitness function comprises: in response to the target reaction period being the reaction initial period, determining the weight corresponding to the pressure adjustment difference as a first value and determining the weight corresponding to the safety risk index as a second value; in response to the target reaction period being the reaction middle period, determining the weight corresponding to the pressure adjustment difference as a third value and determining the weight corresponding to the safety risk index as a fourth value; in response to the target reaction period being the reaction final period, determining the weight corresponding to the pressure adjustment difference as a fifth value and determining the weight corresponding to the safety risk index as a sixth value; The reaction initial stage is a reaction period with a target time as a first starting time and a time after a first time length from the first starting time as a first ending time; the target time is a time when arsine starts to be generated; the reaction middle stage is a reaction period with the first ending time as a second starting time and a time after a second time length from the second starting time as a second ending time; the reaction final stage is a reaction period with the second ending time as a third starting time and a time after a third time length from the third starting time as a third ending time; the first value and the fifth value are both greater than the third value; the second value and the sixth value are both less than the fourth value.

4. The arsine reactor pressure control method of claim 3, wherein, The target pressure adjustment device corresponding to each reaction period is preset, and if the target pressure adjustment device corresponding to the reaction initial stage is consistent with the target pressure adjustment device corresponding to the reaction middle stage; The iterative calculation based on the particle dimension, the hyperparameter and the fitness function until the fitness function meets a preset iteration condition or the iteration number reaches a preset iteration threshold comprises: If the target reaction period is the reaction middle stage and overpressure control is performed in the reaction initial stage of the same reaction process, the historical population optimal position is called; the historical population optimal position is the population optimal position when overpressure control is performed in the reaction initial stage of the same reaction process; The target solution space is determined based on the historical population optimal position; the target solution space is used to limit the range of the target pressure adjustment parameter; The iterative calculation based on the particle dimension, the hyperparameter, the target solution space and the fitness function until the fitness function meets a preset iteration condition or the iteration number reaches a preset iteration threshold.

5. The arsine reactor pressure control method of claim 4, wherein, The target solution space is determined based on the historical population optimal position, comprising: The suboptimal solution particle position is determined; the suboptimal solution particle position is the position of the suboptimal solution particle in the solution space of the particle swarm algorithm when the historical population optimal position is determined; the suboptimal solution particle is a particle in the particle swarm algorithm and the distance between the particle and the particle in the historical population optimal position is less than a preset distance; The target fluctuation is determined based on the suboptimal solution particle position; the target fluctuation is used to quantify the fluctuation range of the solution parameter of the particle swarm algorithm in the iteration process; the solution parameter is the particle dimension of the particle swarm algorithm; The target solution space is determined based on the historical population optimal position and the target fluctuation.

6. The arsine reactor pressure control method of any one of claims 2-5, wherein, The hyperparameter of the particle swarm algorithm comprises an inertia weight; The hyperparameter of the particle swarm algorithm is determined based on the target reaction period, comprising: In response to the target reaction period being the reaction initial stage, the inertia weight is set to a seventh value; In response to the target reaction period being the reaction middle stage, the inertia weight is set to an eighth value; In response to the target reaction period being the reaction final stage, the inertia weight is set to a ninth value; the seventh value and the ninth value are both greater than the eighth value.

7. The arsine reactor pressure control method of claim 1 wherein, Further comprising: In response to the absolute value of the target difference being greater than a preset alarm threshold, an alarm information is outputted; The alarm information is used to represent that the pressure of the current arsine reaction kettle exceeds the self-control range.

8. A pressure control device for an arsine reaction vessel, characterized in that, Comprising: The judgment module is configured to determine whether to perform pressure control based on a difference between the target pressure and a standard pressure. The target pressure is a pressure in a current arsine reactor, and the standard pressure is determined based on a target reaction period of substances in the current arsine reactor. Different reaction periods of the substances in the arsine reactor correspond to different standard pressures. The reaction period includes a reaction initial period, a reaction middle period, and a reaction final period. The device determination module is configured to determine a target pressure adjustment device based on the target reaction period in response to performing the pressure control. The target pressure adjustment device is at least one pressure adjustment device. The adjustment parameter determination module is configured to determine a particle dimension of a particle swarm optimization algorithm based on the target pressure adjustment device. The super parameter of the particle swarm optimization algorithm is determined based on the target reaction period. The fitness function of the particle swarm optimization algorithm is determined based on a pressure adjustment difference and a safety risk index. The pressure adjustment difference is determined based on a target pressure adjustment value and a target difference. The safety risk index is used to represent a leakage risk of the arsine reactor when a current population optimal position of the particle swarm optimization algorithm is used as a target pressure adjustment parameter to control the target pressure adjustment device. The weight corresponding to the pressure adjustment difference and the weight corresponding to the safety risk index in the fitness function are determined based on the target reaction period. The particle dimension, the super parameter, and the fitness function are used for iterative calculation until the fitness function meets a preset iteration condition or an iteration number reaches a preset iteration threshold, so as to obtain a target population optimal position. A particle position corresponding to the target population optimal position is determined as the target pressure adjustment parameter. The target difference is a difference between the target pressure and the standard pressure. At least one pressure adjustment parameter exists in the target pressure adjustment parameter. The pressure adjustment parameter and the pressure adjustment device are in one-to-one correspondence. The control module is configured to control each pressure adjustment device based on a pressure adjustment parameter corresponding to the pressure adjustment device, so as to control the pressure of the current arsine reactor and adjust an actual pressure in the arsine reactor to the standard pressure.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1-9. The computer program is executed by the processor to implement the steps of the method according to any one of claims 1 to 7.

Images