Intelligent control method and system for periodically switching devices

Abstract

This invention belongs to the field of intelligent control technology, and provides an intelligent control method and system for periodically switching equipment. The method includes: determining the initial effective processing capacity of the periodically switching equipment according to a set calculation scheme; calculating the actual effective processing capacity and measured attenuation rate after each use or regeneration based on the initial effective processing capacity, and establishing an attenuation rate database; determining the predicted attenuation rate after each subsequent use or regeneration based on the attenuation rate database; calculating the maximum operating time of the equipment core layer after multiple uses or regenerations based on the actual effective processing capacity and the predicted attenuation rate; and dynamically adjusting the operating status of the periodically switching equipment based on the maximum operating time of the equipment core layer and in conjunction with pre-set switching and regeneration time thresholds. This solution extends the service life of the equipment, reduces maintenance and production costs, and better meets the needs of modern chemical production for high efficiency, stability, and intelligence.

Description

Technical Field

[0001] This invention relates to the field of intelligent control technology, and in particular to an intelligent control method and system for periodically switching equipment. Background Technology

[0002] In the chemical production field, intermittent operation equipment such as raw material adsorbers and molecular sieve dryers are typical periodic switching devices, and their operational stability directly determines the continuity of the production process, product quality, and production efficiency. These devices require a cyclical switching process of operation-regeneration-reoperation to achieve impurity adsorption and raw material purification. Precise control of the switching timing is crucial to ensuring production effectiveness. Traditional switching methods rely primarily on manual operation, depending on operator experience and fixed schedules to manually adjust valves and operating parameters. This not only consumes significant labor costs but also demands extremely high levels of expertise. Fatigue, negligence, or misjudgment can easily lead to switching timing deviations, resulting in serious problems such as material leakage, reaction interruption, and product quality fluctuations.

[0003] With the expansion of chemical production scale and the initial application of automation technology, some enterprises have adopted automated control systems based on preset time programs or simple logic. Although this reduces human intervention, it is still difficult to adapt to the high complexity and dynamic changes of the production process. Chemical production is affected by multiple factors such as raw material properties, ambient temperature, and pressure. Parameters such as impurity concentration and flow rate in raw materials often experience sudden fluctuations. Fixed switching times and logic cannot respond to these changes in real time, which may lead to impurities penetrating the adsorption layer and causing product quality degradation, or the equipment being switched before fully utilizing its adsorption performance, resulting in material waste, increased energy consumption, and other problems. At the same time, frequent and ineffective switching can also damage the adsorbent structure, shorten equipment lifespan, and increase maintenance costs.

[0004] It is evident that the existing switching control methods for periodic switching equipment suffer from technical problems such as insufficient accuracy, poor dynamic adaptability, and low operating efficiency. Summary of the Invention

[0005] This invention provides an intelligent control method and system for periodic switching equipment, which solves the defects of existing periodic switching equipment in terms of insufficient accuracy, poor dynamic adaptability and low operating efficiency.

[0006] On one hand, the present invention provides an intelligent control method for a periodically switching device, comprising: The initial effective processing capacity of the periodically switching equipment is determined according to the established calculation scheme. Based on the initial effective processing capacity, the actual effective processing capacity and measured attenuation rate after each use or regeneration are calculated, and an attenuation rate database is established. Based on the attenuation rate database, the predicted attenuation rate is determined for each subsequent use or regeneration. Based on the actual effective processing capacity and the predicted attenuation rate, the maximum operating time of the core layer of the equipment after multiple uses or regenerations is calculated. Based on the maximum operating time of the core layer of the device, and in conjunction with the preset switching and regeneration time thresholds, the operating status of the periodically switching device is dynamically adjusted.

[0007] According to the intelligent control method for periodic switching equipment provided by the present invention, the core layer of the equipment includes a main bed layer and a protective bed layer; Based on the initial effective processing capacity, the actual effective processing capacity and measured attenuation rate after each use or regeneration are calculated, including: After each use or regeneration, obtain the current feed flow rate, the current impurity concentration in the feed, and the time when the impurities in the main bed exceed the standard. Based on the inflow rate, the impurity concentration, and the time the impurities exceeded the standard, the effective treatment capacity of the main bed and the effective treatment capacity of the protective bed are calculated. The effective treatment capacity of the main bed layer and the effective treatment capacity of the protective bed layer are summed to calculate the actual effective treatment capacity after each use or regeneration. Based on the initial effective processing capacity and the actual effective processing capacity after each use or regeneration, the measured value of the attenuation rate after each use or regeneration is calculated.

[0008] According to the intelligent control method for the periodic switching device provided by the present invention, the effective processing capacity of the main bed and the effective processing capacity of the guard bed are calculated based on the inflow rate, the impurity concentration, and the time the impurities exceed the standard, including: The effective processing capacity of the main bed is calculated by multiplying the inflow rate, the impurity concentration, and the time the impurities exceeded the standard. The effective processing capacity of the main bed layer is calculated by multiplying it by the pre-obtained filling ratio of the main bed layer and the protective bed layer.

[0009] According to the intelligent control method for periodically switching devices provided by the present invention, based on the attenuation rate database, the method determines the predicted attenuation rate value after each subsequent use or regeneration, including: Retrieve the measured attenuation rate values ​​after each use or regeneration from the attenuation rate database; The difference in attenuation rate is calculated by subtracting the corresponding measured values ​​of attenuation rate from two consecutive values. Assuming that the attenuation rate difference between all two consecutive values ​​is equal, the predicted attenuation rate after each subsequent use or regeneration is calculated based on the attenuation rate difference and the last measured attenuation rate value in the attenuation rate database.

[0010] According to the intelligent control method for periodically switching devices provided by the present invention, based on the attenuation rate database, the method determines the predicted attenuation rate value after each subsequent use or regeneration, including: A regression prediction model is established with the decay rate as the dependent variable and time or number of uses as the independent variable. Based on the regression prediction model and at least some measured attenuation rates in the attenuation rate database, the predicted attenuation rate is determined for each subsequent use or regeneration.

[0011] According to the intelligent control method for periodically switching equipment provided by the present invention, based on the actual effective processing capacity and the predicted attenuation rate, the maximum operating time of the core layer of the equipment after multiple uses or regenerations is calculated, including: Based on the actual effective processing capacity and the predicted attenuation rate, the predicted effective processing capacity after each subsequent use or regeneration is determined. The inflow rate and impurity concentration of the subsequent raw materials are obtained, and the maximum operating time of the main bed and the maximum operating time of the protective bed are calculated based on the inflow rate and impurity concentration of the subsequent raw materials and the predicted effective processing capacity. The maximum operating time of the main bed layer and the maximum operating time of the protective bed layer are taken as the maximum operating time of the core layer of the equipment after multiple uses or regeneration.

[0012] According to the intelligent control method for periodic switching devices provided by the present invention, the switching and regeneration time thresholds include the minimum necessary time for switching and the minimum necessary time for regeneration; Based on the maximum operating time of the core layer of the device, and in conjunction with pre-set switching and regeneration time thresholds, the operating status of the periodically switching device is dynamically adjusted, including: The maximum operating time of the protective bed is compared with the minimum necessary switching time to obtain the first comparison result; The maximum operating time of the main bed layer is added to the maximum operating time of the protective bed layer to calculate the sum of the maximum operating times. The sum of the maximum running time is compared with the minimum necessary time for regeneration to obtain a second comparison result; Based on the first comparison result and the second comparison result, the operating status of the periodically switching equipment is dynamically adjusted.

[0013] The intelligent control method for a periodically switching device provided by the present invention further includes: Collect data on the decay rate and the corresponding number of runs to establish a data sample set; Construct a frequency prediction model, and train the frequency prediction model using the data sample set to obtain a trained frequency prediction model; Based on the aforementioned frequency prediction model, the maximum number of runs corresponding to the actual effective processing capacity dropping to the minimum allowable value is determined.

[0014] The intelligent control method for a periodically switching device provided by the present invention further includes: Determine the actual number of times the periodically switching equipment is operated; If the actual number of runs reaches a set percentage of the maximum number of runs, a maintenance and repair task will be triggered.

[0015] On the other hand, the present invention also provides an intelligent control system for a periodically switching device, comprising: The calculation module is used to determine the initial effective processing capacity of the periodically switching equipment according to the set calculation scheme; A module is established to calculate the actual effective processing capacity and measured attenuation rate after each use or regeneration based on the initial effective processing capacity, and to establish an attenuation rate database. The prediction module is used to determine the predicted value of the attenuation rate after each subsequent use or regeneration based on the attenuation rate database. The calculation module is used to calculate the maximum operating time of the core layer of the device after multiple uses or regenerations, based on the actual effective processing capacity and the predicted attenuation rate. The control module is used to dynamically adjust the operating status of the periodically switching device based on the maximum operating time of the core layer of the device and in combination with the preset switching and regeneration time thresholds.

[0016] The intelligent control method and system for periodic switching equipment provided by this invention can dynamically and accurately calculate the maximum operating time of the core layer of the equipment by accurately measuring the initial effective processing capacity, accumulating attenuation rate data in real time, and predicting the subsequent attenuation trend. Combined with preset thresholds, it can realize intelligent dynamic adjustment of the operating status. This avoids the errors of traditional manual operation and the limitations of simple automated fixed logic, fully utilizes the adsorption performance of the equipment to reduce material waste and energy consumption, and can predict the attenuation status and service life of the equipment in advance. This effectively improves product quality and equipment operation stability, extends equipment service life, reduces maintenance and production costs, and better meets the needs of modern chemical production for high efficiency, stability, and intelligence. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0018] Figure 1 This is a flowchart illustrating the intelligent control method for periodically switching devices provided in an embodiment of the present invention. Figure 2 This is a schematic diagram of the structure of the adsorber in an embodiment of the present invention; Figure 3 This is a schematic diagram of the linear regression model for the attenuation rate prediction stage in this embodiment of the invention; Figure 4 This is a schematic diagram of the structure of the intelligent control system for the periodic switching device provided in an embodiment of the present invention. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0020] The following is combined Figures 1 to 4 The present invention describes the detailed scheme of the intelligent control method and system for the periodic switching device.

[0021] like Figure 1 As shown, the intelligent control method for periodically switching devices provided in this embodiment of the invention mainly includes the following steps: Step 110: Determine the initial effective processing capacity of the periodically switching equipment according to the set calculation scheme.

[0022] In practical applications, two methods can be used to set up a measurement scheme: direct method and indirect method, such as... Figure 2 As shown, taking the periodically switching device as an adsorber as an example, in the process of directly measuring the initial total adsorption (i.e. the initial effective treatment capacity), we can first count the initial loading amount of the adsorbent in the adsorber, and then query or determine the adsorption capacity of the adsorbent through experiments. The initial total adsorption can be calculated by multiplying the initial loading amount by the adsorption capacity.

[0023] For example, for a certain type of adsorber, the initial adsorbent loading is 100 kg, and the designed adsorption capacity of the adsorbent is known to be 0.055 kg impurities / kg adsorbent. Therefore, by direct calculation, the initial total adsorption amount is 5.5 kg.

[0024] In the process of determining the initial total adsorption using the indirect method, it can be assumed that the periodically switching equipment is uniformly filled. By integrating the current raw material inflow rate, impurity concentration, and the time when impurities in the main bed exceed the standard, the initial total adsorption of the main bed can be calculated. The initial total adsorption of the protective bed can be calculated by multiplying the filling ratio of the main bed and the protective bed by the initial total adsorption of the main bed. By adding the initial total adsorption of the main bed and the initial total adsorption of the protective bed, the initial total adsorption of the entire adsorber can be indirectly calculated.

[0025] For example, assuming the feed flow rate is stable at 10 m³ / h and the impurity concentration is 0.05 kg / m³, monitoring shows that the impurities in the main bed exceed the standard for 10 hours. Assuming uniform packing, the initial total adsorption of the main bed can be calculated by integration. Under stable flow and concentration conditions, the initial total adsorption of the main bed is 5 kg. Given a main bed to guard bed packing ratio of 10:1, the initial total adsorption of the guard bed is 0.5 kg. Therefore, the initial total adsorption of impurities for the entire system can be indirectly calculated as 5.5 kg.

[0026] In some embodiments, the initial total adsorption amount can also be calculated based on the heat of adsorption. This involves indirectly calculating the initial total adsorption amount by utilizing the relationship between the heat of adsorption generated during the adsorption process and the amount of adsorption. Each adsorbent releases a specific heat of adsorption when adsorbing impurities. A high-precision temperature sensor installed inside the adsorber measures the temperature change during the adsorption process in real time, and combined with the known functional relationship between the adsorbent's heat of adsorption and the amount of adsorption, the total amount of adsorbed impurities is calculated.

[0027] For example, if it is known that an adsorbent releases a specific amount of heat for every kilogram of impurities adsorbed, then during the initial operation of the adsorber, the heat change caused by the temperature rise inside the adsorber during the adsorption process is measured. The initial total adsorption amount is then the ratio of the heat change to the specific heat value.

[0028] In other embodiments, a dynamic equilibrium model method can be used to calculate the initial total adsorption. Specifically, a dynamic equilibrium model describing the adsorption process within the adsorber can be constructed, taking into account factors such as the feed gas inflow rate, impurity concentration, adsorbent properties, and adsorption kinetics. By solving the model, the total adsorption in the adsorber under steady-state conditions can be obtained. Specifically, a set of equations including mass conservation equations and adsorption kinetic equations can be established, and these equations can be solved using numerical calculation methods (such as the finite element method and the finite difference method) to obtain the initial total adsorption. This method can more comprehensively consider various dynamic factors in the adsorption process, and compared to direct and indirect calculation methods, the calculation results may be closer to the actual situation. However, the calculation process is relatively complex and requires more input parameters and computational resources.

[0029] Step 120: Based on the initial effective processing capacity, calculate the actual effective processing capacity and measured attenuation rate after each use or regeneration, and establish an attenuation rate database.

[0030] Understandably, by summarizing the measured values ​​of attenuation rate after the first use or regeneration, an attenuation rate database can be established.

[0031] Step 130: Based on the attenuation rate database, determine the predicted attenuation rate for each subsequent use or regeneration.

[0032] In this embodiment, by retrieving the attenuation rate database, the attenuation rate after subsequent use or regeneration can be predicted, thereby providing effective data basis for predicting the maximum operating time.

[0033] Step 140: Based on the actual effective processing capacity and the predicted attenuation rate, calculate the maximum operating time of the core layer of the equipment after multiple uses or regenerations.

[0034] Understandably, based on the actual effective processing capacity and decay rate predictions, the maximum operating time can be further predicted.

[0035] Step 150: Based on the maximum operating time of the core layer of the equipment and in combination with the preset switching and regeneration time thresholds, dynamically adjust the operating status of the periodically switching equipment.

[0036] In one embodiment, the core layer of the device specifically includes a main bed layer and a protective bed layer.

[0037] Based on the initial effective processing capacity, the actual effective processing capacity and measured attenuation rate after each use or regeneration are calculated, including: The first step is to obtain the current feed flow rate, the current impurity concentration in the feed, and the time when the impurities in the main bed exceed the standard after each use or regeneration.

[0038] In practical applications, after the nth (n greater than or equal to 1) use or regeneration, the current raw material inflow rate can be monitored, the impurity concentration in the current raw material can be detected, and the time when the impurities in the main bed exceed the standard can be recorded.

[0039] The second step involves calculating the effective treatment capacity of the main bed and the effective treatment capacity of the protective bed based on the inflow rate, impurity concentration, and the time the impurities exceeded the standard.

[0040] In a specific implementation, the effective treatment capacity of the main bed and the effective treatment capacity of the guard bed are calculated based on the influent flow rate, impurity concentration, and impurity exceedance time. Specifically, this includes: First, the effective treatment capacity of the main bed is calculated by multiplying the inflow rate, impurity concentration, and impurity exceedance time.

[0041] In this embodiment, the adsorber is still taken as an example. The total amount of adsorption in the main bed can be calculated by calculating the inflow rate, impurity concentration and the time when the impurities in the main bed exceed the standard.

[0042] Then, the effective treatment capacity of the main bed layer is multiplied by the pre-obtained filling ratio of the main bed layer and the protective bed layer to calculate the effective treatment capacity of the protective bed layer.

[0043] In this embodiment, for the adsorber, the total adsorption amount of the main bed can be calculated by multiplying the total adsorption amount of the main bed by the filling ratio.

[0044] The third step is to sum the effective treatment capacity of the main bed and the effective treatment capacity of the protective bed to calculate the actual effective treatment capacity after each use or regeneration.

[0045] In practical applications, for adsorbers, the actual total adsorption amount after each use or regeneration can be calculated by adding the total adsorption amount of the main bed layer to the total adsorption amount of the protective bed layer.

[0046] The fourth step is to calculate the measured value of the attenuation rate after each use or regeneration, based on the initial effective processing capacity and the actual effective processing capacity after each use or regeneration.

[0047] In this embodiment, the formula for calculating the measured attenuation rate is as follows: (1) in, This represents the measured attenuation rate after the nth use or regeneration. This represents the actual effective processing capacity after the (n-1)th use or regeneration. This represents the actual effective processing capacity after the nth use or regeneration.

[0048] In practical applications, an attenuation rate database can be established to record the measured attenuation rate values ​​obtained from each calculation. δ 1 、 δ 2…… δ n .

[0049] For example, when the adsorber reaches saturation, a regeneration operation can be performed. After regeneration, it can be put back into use. At this time, the feed flow rate is 11 cubic meters per hour, the impurity concentration is 0.055 kg / cubic meter, and the impurity exceedance time in the main bed is 8 hours. The total adsorption amount in the main bed is calculated to be 4.961 kg of impurities. Since the total adsorption amount in the guard bed is one-tenth of the total adsorption amount in the main bed, the actual total adsorption amount after regeneration is 5.4571 kg of impurities. Since the initial total adsorption amount is 5.5 kg of impurities, the measured attenuation rate is [(5.5-5.4571) / 5.5]×100%=0.78%.

[0050] In some embodiments, taking the adsorber as an example, the actual total adsorption can also be calculated based on the adsorption breakthrough curve calculation method. During the operation of the adsorber, the change of impurity concentration at the adsorber outlet over time is monitored in real time, and the adsorption breakthrough curve is plotted. By analyzing the adsorption breakthrough curve, the adsorption capacity of the adsorbent after one use / regeneration is determined. For example, the adsorption breakthrough curve is fitted to an ideal breakthrough curve model, and the actual total adsorption is calculated based on the fitting parameters. This method can more intuitively reflect the changes in the adsorption performance of the adsorbent during actual operation, and more information about the adsorption process, such as the movement speed of the adsorption front, can be obtained through detailed analysis of the breakthrough curve.

[0051] In other embodiments, the actual total adsorption can be calculated based on changes in the adsorbent's microstructure. Specifically, the microstructure of the adsorbent can be detected before and after adsorber regeneration. By analyzing the changes in the microstructure parameters of the adsorbent before and after regeneration, and combining the known quantitative relationship between the microstructure and the total adsorption, the actual total adsorption after each use or regeneration can be calculated. For example, assuming a linear relationship between the specific surface area S of the adsorbent and the adsorption capacity q, q = kS + b (where k and b are constants), by measuring the specific surface areas S1 and S2 of the adsorbent before and after regeneration, the actual total adsorption q1 and q2 can be calculated, thus obtaining the measured value of the attenuation rate.

[0052] In one embodiment, determining the predicted attenuation rate after each subsequent use or regeneration based on an attenuation rate database specifically includes: First, retrieve the measured attenuation rate values ​​from the attenuation rate database after each use or regeneration.

[0053] Then, the difference between the two consecutive measured attenuation rate values ​​is calculated to obtain the attenuation rate difference.

[0054] Finally, assuming that the attenuation rate difference between all two consecutive values ​​is equal, the predicted attenuation rate after each subsequent use or regeneration is calculated based on the attenuation rate difference and the last measured attenuation rate value in the attenuation rate database.

[0055] In this embodiment, the predicted attenuation rate after each subsequent use or regeneration can be obtained based on a trend derivation method. Specifically, the measured attenuation rate after the nth use or regeneration can be calculated first. The measured attenuation rate after the (n-1)th use or regeneration The difference in attenuation rate between them can be expressed as Δ. This indicates that the attenuation rate difference Δ after the (n+1)th use or regeneration is different from the attenuation rate after the nth use or regeneration. , and Δ Based on this assumption, the decay rate at the (n+1)th time can be derived. In this way, it is possible to predict the subsequent decay rate based on the changing trends of historical decay rate data.

[0056] In one embodiment, determining the predicted attenuation rate after each subsequent use or regeneration based on an attenuation rate database specifically includes: First, a regression prediction model is established with the decay rate as the dependent variable and time or number of uses as the independent variable.

[0057] Then, based on the regression prediction model and at least some of the measured decay rate values ​​in the decay rate database, the predicted decay rate value for each subsequent use or regeneration is determined.

[0058] In this embodiment, a regression model can be used to predict the decay rate. Specifically, the decay rate can be used as the dependent variable, and time or the number of uses can be used as the independent variable. For example... Figure 3 As shown, x represents the number of uses, and y represents the decay rate. Based on this, a linear regression model or a multinomial regression model can be established to obtain a regression prediction model. Then, the previously measured decay rate values ​​are substituted into the regression prediction model, and the parameters of the regression prediction model are determined through fitting to obtain a well-fitted regression model. Finally, this well-fitted regression model can be used to predict the decay rate after multiple subsequent uses or regenerations.

[0059] In one embodiment, based on the actual effective processing capacity and the predicted attenuation rate, the maximum operating time of the core layer of the device after multiple uses or regenerations is calculated, specifically including: First, based on the actual effective processing capacity and the predicted attenuation rate, the predicted effective processing capacity after each subsequent use or regeneration is determined.

[0060] In this embodiment, the formula for calculating the predicted effective processing capacity is as follows: Q n+k = Q n+k-1 ×[1 - ( +Δ (2) in, Q n+k Indicates the first n+k Predicted effective processing capacity after first use or regeneration Q n+k-1 Indicates the first n+k -Predicted effective processing capacity after one use or regeneration Indicates the first n+k -Predicted attenuation rate after one use or regeneration, Δ Indicates the first n+k -1 is the attenuation rate difference corresponding to the previous attenuation, where k is an integer value greater than or equal to 1.

[0061] Then, the inflow rate and impurity concentration of the subsequent raw materials are obtained, and based on the inflow rate and impurity concentration of the subsequent raw materials and the predicted effective processing capacity, the maximum operating time of the main bed and the maximum operating time of the protective bed are calculated.

[0062] In this embodiment, by obtaining the inflow rate and impurity concentration of raw materials at subsequent corresponding times, and combining this with the predicted effective processing capacity, the maximum operating time of the main bed can be predicted after subsequent use or regeneration; similarly, the maximum operating time of the protective bed can be predicted after subsequent use or regeneration.

[0063] Finally, the maximum operating time of the main bed layer and the maximum operating time of the protective bed layer are taken as the maximum operating time of the core layer of the equipment after multiple uses or regeneration.

[0064] For example, assuming the adsorber has run or been regenerated for the 100th time and its overall decay rate is 39.5%, the maximum adsorption capacity of the guard bed is 0.5 kg impurities × (1 - 39.5%) = 0.3025 kg impurities. The current feed flow rate is 11 m³ / h, the impurity concentration is 0.055 kg / m³, the maximum possible operating time of the guard bed is 0.5 hours, the maximum adsorption capacity of the main bed is 5 kg impurities × (1 - 39.5%) = 3.025 kg impurities, and the maximum possible operating time of the main bed is 5 hours.

[0065] In one embodiment, the switching and regeneration time thresholds include the minimum necessary time for switching and the minimum necessary time for regeneration.

[0066] In practical applications, the minimum necessary time for switching can be set based on parameters such as equipment structure and valve response speed; and the minimum necessary time for regeneration can be set in combination with the regeneration process duration and the start-up time of standby equipment.

[0067] Furthermore, based on the maximum operating time of the core equipment layer and in conjunction with pre-set switching and regeneration time thresholds, the operating status of periodically switching equipment is dynamically adjusted, specifically including: The first step is to compare the maximum operating time of the protective bed with the minimum necessary switching time to obtain the first comparison result.

[0068] In this embodiment, if the maximum running time of the protective bed is less than the minimum necessary time for switching, the protective bed has reached its maximum service life. At this time, the running time of the main bed can be automatically shortened to ensure a smooth switching process.

[0069] The second step is to add the maximum running time of the main bed layer to the maximum running time of the protective bed layer to calculate the sum of the maximum running times.

[0070] The third step is to compare the sum of the maximum running times with the minimum necessary time for regeneration to obtain the second comparison result.

[0071] In this embodiment, if the sum of the maximum running times is less than the minimum necessary time for regeneration, it indicates that the entire periodic switching equipment has reached its maximum service life. At this point, a lifespan warning can be issued to alert staff that the equipment is nearing its maximum service life. In practical applications, after issuing a lifespan warning, adjustments can be made such as reducing the absolute content of impurities in the inlet raw material or arranging for adsorbent replacement.

[0072] The fourth step is to dynamically adjust the operating status of the periodically switching equipment based on the first and second comparison results.

[0073] For example, suppose the minimum necessary time for switching the adsorber is 0.5 hours, which is equal to the maximum possible operating time of the protective bed. When the protective bed reaches its maximum operating cycle, the system issues an early warning and needs to shorten the operating time of the main bed to meet the adsorber switching time.

[0074] If the minimum necessary time for the regeneration of the adsorber is 5.5 hours, which is consistent with the sum of the maximum possible operating time of the main bed and the maximum operating time of the protective bed, the system will issue an early warning, prompting the operator to remind the adsorber to have reached its maximum service life, and that the total amount of inlet impurities needs to be reduced, or that maintenance and replacement of the adsorbent should be arranged immediately.

[0075] In practical applications, taking the adsorber as an example, key data such as raw material flow rate, impurity concentration, and outlet impurity content of the main bed can be monitored in real time during operation. When a sudden change in one or more data points is detected, the operating cycle or inlet flow rate can be automatically adjusted to ensure sufficient adsorption of impurities.

[0076] During the adsorption process, the inflow rate of the feedstock, the impurity concentration, and the impurity content at the outlet of the main bed are continuously monitored. For example, when the inflow rate of the feedstock changes to 12 cubic meters per hour and the impurity concentration changes to 0.06 kilograms per cubic meter, the system adjusts the operating parameters of the adsorber according to a pre-set algorithm and the current adsorption state of the bed. This adjustment may include shortening the operating cycle or reducing the inflow rate to ensure that impurities are fully adsorbed. Simultaneously, the system records the time when impurities exceed the limit at the outlet of the main bed in real time, providing data support for subsequent calculations of the total adsorption volume and attenuation rate.

[0077] In some embodiments, a risk assessment model based on the decay rate can be established, comprehensively considering factors such as the operating status of the periodic switching equipment, the risk of impurity leakage, and production process requirements, thereby adjusting the operation of the periodic switching equipment. For example, the predicted decay rate value can be divided into different risk levels, with each level corresponding to a different operational adjustment strategy. When the predicted decay rate value is at a low risk level, only routine monitoring and maintenance of the periodic switching equipment are performed; when the predicted decay rate value rises to a medium risk level, the feed gas inflow rate is automatically reduced, and the operating cycle of the periodic switching equipment is appropriately extended to balance adsorption effect and production efficiency; when the predicted decay rate value reaches a high risk level, an alarm is immediately issued, requiring operators to take emergency measures, such as switching to a standby periodic switching equipment or reducing the production load, to ensure the safety and stability of the production process. This method allows for more flexible and reasonable operational adjustments based on the actual risk status of the periodic switching equipment, avoiding the problems of over-adjustment or under-adjustment that may result from adjustments based solely on time or fixed parameters.

[0078] In practical applications, intelligent optimization algorithms, such as particle swarm optimization, can be used to optimize and adjust the operating parameters of periodically switching equipment. Specifically, the decay rate, impurity adsorption effect, and production efficiency can be used as optimization objectives, with the operating time, flow rate, and temperature of the periodically switching equipment as decision variables to construct an optimization model. The intelligent optimization algorithm iteratively searches for a set of optimal operating parameters, enabling the periodically switching equipment to minimize the decay rate and extend the adsorbent's lifespan while meeting production requirements. For example, in genetic algorithms, operating parameters can be encoded into chromosomes. Through genetic operations such as selection, crossover, and mutation, the fitness value of the chromosomes (i.e., the objective function value) is gradually optimized, ultimately yielding the optimal combination of operating parameters.

[0079] In some embodiments, equipment operation control can be implemented based on fuzzy control. Fuzzy control does not require establishing a precise mathematical model; instead, it formulates a series of fuzzy control rules based on the operator's experience and knowledge. For example, the inflow rate of the raw material, the impurity concentration, and the impurity content at the main bed outlet are used as input variables for the fuzzy controller, while the operating cycle of the periodically switching equipment and the inflow rate adjustment are used as output variables. Based on the changes in the input variables, fuzzy inference is performed according to the fuzzy control rules to derive the corresponding output control quantity, thereby adjusting the operating parameters of the periodically switching equipment. For example, when the inflow rate of the raw material is large and the impurity concentration is high, the output of the fuzzy controller may be a significant reduction in the operating cycle and a significant decrease in the inflow rate. This method can effectively handle uncertainties and nonlinearities in the adsorption process, has low requirements for model accuracy, and exhibits strong robustness and adaptability.

[0080] In other embodiments, model predictive control (MMCC) can be used to control the equipment operation process. Specifically, a dynamic mathematical model of the periodically switching equipment can be established, and MMCC technology can be used to control the operation of the periodically switching equipment. MMCC continuously predicts the operating state of the periodically switching equipment over a future period and optimizes the control input at the current moment based on the prediction results and the set control objectives. For example, based on the established dynamic mathematical model, the impact of changes in raw material inflow rate and impurity concentration on the impurity content at the main bed outlet can be predicted over several time steps. Then, with the objective of minimizing the deviation between the main bed outlet impurity content and the set value, the operating parameters of the periodically switching equipment that should be adjusted at the current moment are obtained by solving an optimization problem. This method can fully utilize the model's predictive information to optimize and adjust the operation of the periodically switching equipment in advance, thereby better ensuring the adsorption effect.

[0081] In one embodiment, the intelligent control method for the periodic switching device described above may further include: First, collect the decay rate data and the corresponding number of runs for each iteration to establish a data sample set.

[0082] Then, a frequency prediction model is constructed, and the frequency prediction model is trained using a data sample set to obtain a trained frequency prediction model.

[0083] In practical applications, linear regression, curve fitting, or machine learning algorithms can be used to build frequency prediction models.

[0084] Finally, based on the frequency prediction model, the maximum number of runs corresponding to the actual effective processing capacity dropping to the minimum allowable value is determined.

[0085] In practical applications, the predicted maximum number of runs can be corrected by combining the actual operating conditions of the equipment, so as to improve the accuracy of the maximum number of runs.

[0086] In one embodiment, the intelligent control method for the periodic switching device described above may further include: First, determine the actual number of times the periodically switching equipment will be run.

[0087] Then, if the actual number of runs reaches the set percentage of the maximum number of runs, a maintenance and repair task will be triggered.

[0088] In practical applications, when the actual number of runs reaches 90%-95% of the maximum number of runs, maintenance and repair tasks can be triggered. Professional personnel can be arranged to conduct a comprehensive inspection of the periodically switching equipment. Taking the adsorber as an example, the comprehensive inspection specifically includes adsorbent activity testing, bed structure integrity inspection, etc. Based on the inspection results, the necessary adsorbent, tools, and maintenance personnel are prepared for replacement. Before the actual number of runs approaches the maximum number of runs, a detailed maintenance and adsorbent replacement schedule is formulated to avoid affecting production. In this way, adsorbent replacement or equipment maintenance can be completed according to plan, ensuring that the performance of the equipment meets the standards after restarting.

[0089] For example, by mathematically simulating the changing trends of the decay rate over time, such as using linear regression or curve fitting, the maximum number of operations the adsorber can be calculated. Assuming the simulation calculates a maximum of 100 operations, a detailed maintenance and refrigerant replacement plan can be developed in advance when the actual number of operations approaches 100. Around 95 operations, a comprehensive inspection of the adsorber can be conducted by professionals, including adsorbent activity testing and bed structure integrity checks. Based on the inspection results, the necessary materials and tools for adsorbent replacement are prepared, and the adsorbent is replaced promptly before reaching 100 operations to ensure the adsorber's performance remains consistently optimal.

[0090] In some embodiments, reliability analysis can be used to estimate the number of operations and formulate maintenance plans. Specifically, reliability engineering methods are applied to estimate the number of operations of the periodic switching equipment and formulate corresponding maintenance plans. A reliability model for the periodic switching equipment is established by statistically analyzing historical operating data, failure data, and adsorbent performance degradation data. For example, reliability models such as the Weibull distribution are used to describe the variation of the failure probability of the periodic switching equipment with operating time or number of operations. Based on the reliability model, the maximum number of operations of the periodic switching equipment under different reliability requirements is calculated.

[0091] In terms of maintenance planning, the maintenance measures to be taken at different operational stages can be determined based on the results of reliability analysis. For example, in the initial stage of operation of periodic switching equipment, due to the low probability of failure, regular inspections and preventative maintenance measures can be taken. As the number of operations increases, the probability of failure gradually rises, and the inspection frequency should be increased, with maintenance resources such as replacement adsorbents prepared in advance. When approaching the maximum number of operations, real-time monitoring of the periodic switching equipment can be strengthened, and any abnormalities should be repaired or replaced immediately. This method, from a reliability perspective, can more scientifically estimate the number of operations of the periodic switching equipment and formulate a reasonable maintenance plan to ensure the reliable operation of the periodic switching equipment throughout its entire service life.

[0092] In other embodiments, machine learning can be used to predict the number of runs and formulate maintenance plans. Specifically, machine learning algorithms are used to predict the number of runs of the periodic switching equipment and formulate maintenance plans. A large amount of data related to the operation of the periodic switching equipment is collected, including feed gas properties, operating parameters, adsorbent performance indicators, and the number of runs. This data is used as training samples to train a machine learning model, such as a neural network or support vector machine. Using the trained model, the remaining number of runs of the periodic switching equipment is predicted based on its current operating status and related parameters.

[0093] In terms of maintenance planning, personalized maintenance plans can be developed based on forecast results and actual production conditions. For example, when the remaining number of operations for periodically switching equipment is predicted to be low, maintenance personnel can be trained in advance, and necessary spare parts and tools can be prepared to ensure a rapid response when maintenance is needed, minimizing downtime. This approach fully leverages the advantages of data-driven approaches, uncovering potential patterns in the data and improving the accuracy of operation count forecasts, thereby providing stronger support for maintenance planning.

[0094] In summary, the intelligent control method for periodically switching devices provided in this embodiment of the invention has at least the following advantages compared with existing solutions: First, it improves equipment operating efficiency. Based on dynamic decay rate simulation calculations and maximum operating time prediction, it can accurately predict the maximum operating time of the main bed and protective bed after multiple uses or regeneration cycles. This helps to rationally schedule equipment operation, fully utilize the adsorption capacity of the bed, avoid wasting time and energy due to premature or delayed regeneration, and significantly improve equipment operating efficiency.

[0095] Second, improve product quality. When it is detected that the protective bed may have reached its maximum service life, the main bed's operating time can be adjusted and shortened in a timely manner to meet the time required for adsorber switching, thus avoiding damage to product quality due to protective bed failure. Similarly, when it is determined that the equipment may have reached its maximum service life, measures can be taken in advance, such as reducing the absolute content of inlet impurities or replacing the adsorbent, to prevent the equipment from operating beyond its limits and affecting product quality.

[0096] Third, it extends the service life of the equipment. By mathematically simulating the changing trends of the decay rate over time, the maximum number of operations for the entire equipment can be calculated, providing scientific data support for the rational scheduling of maintenance and replacement of chemicals.

[0097] Fourth, it reduces production costs. Based on accurate understanding of equipment operating status and calculation of maximum operating cycles, a reasonable maintenance and adsorbent replacement plan can be formulated, avoiding unnecessary frequent maintenance and premature adsorbent replacement, thus reducing maintenance costs. At the same time, extending equipment lifespan also reduces equipment replacement costs, resulting in an overall reduction in production costs.

[0098] Based on the same general inventive concept, this invention also protects an intelligent control system for a periodic switching device. The intelligent control system for the periodic switching device provided by this invention will be described below. The intelligent control system for the periodic switching device described below and the intelligent control method for the periodic switching device described above can be referred to in correspondence.

[0099] like Figure 4 As shown, the intelligent control system for the periodic switching device provided in this embodiment of the invention specifically includes: The calculation module 210 is used to determine the initial effective processing capacity of the periodically switching equipment according to the set calculation scheme; Module 220 is established to calculate the actual effective processing capacity and measured attenuation rate after each use or regeneration based on the initial effective processing capacity, and to establish an attenuation rate database. The prediction module 230 is used to determine the predicted value of the decay rate after each subsequent use or regeneration based on the decay rate database. Calculation module 240 is used to calculate the maximum operating time of the core layer of the equipment after multiple uses or regenerations, based on the actual effective processing capacity and the predicted attenuation rate. The control module 250 is used to dynamically adjust the operating status of the periodically switching equipment based on the maximum operating time of the core layer of the equipment and in combination with the preset switching and regeneration time thresholds.

[0100] Regarding the system in the above embodiments, the specific ways in which each module performs operations have been described in detail in the embodiments of the relevant methods, and will not be elaborated further here.

[0101] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An intelligent control method for a periodically switching device, characterized in that, include: The initial effective processing capacity of the periodically switching equipment is determined according to the established calculation scheme. Based on the initial effective processing capacity, the actual effective processing capacity and measured attenuation rate after each use or regeneration are calculated, and an attenuation rate database is established. Based on the attenuation rate database, the predicted attenuation rate is determined for each subsequent use or regeneration. Based on the actual effective processing capacity and the predicted attenuation rate, the maximum operating time of the core layer of the equipment after multiple uses or regenerations is calculated. Based on the maximum operating time of the core layer of the device, and in conjunction with the preset switching and regeneration time thresholds, the operating status of the periodically switching device is dynamically adjusted.

2. The intelligent control method for periodic switching equipment according to claim 1, characterized in that, The core layer of the equipment includes a main bed layer and a protective bed layer; Based on the initial effective processing capacity, the actual effective processing capacity and measured attenuation rate after each use or regeneration are calculated, including: After each use or regeneration, obtain the current feed flow rate, the current impurity concentration in the feed, and the time when the impurities in the main bed exceed the standard. Based on the inflow rate, the impurity concentration, and the time the impurities exceeded the standard, the effective treatment capacity of the main bed and the effective treatment capacity of the protective bed are calculated. The effective treatment capacity of the main bed layer and the effective treatment capacity of the protective bed layer are summed to calculate the actual effective treatment capacity after each use or regeneration. Based on the initial effective processing capacity and the actual effective processing capacity after each use or regeneration, the measured value of the attenuation rate after each use or regeneration is calculated.

3. The intelligent control method for periodic switching equipment according to claim 2, characterized in that, Based on the inflow rate, the impurity concentration, and the time the impurities exceeded the standard, the effective treatment capacity of the main bed and the effective treatment capacity of the guard bed are calculated, including: The effective processing capacity of the main bed is calculated by multiplying the inflow rate, the impurity concentration, and the time the impurities exceeded the standard. The effective processing capacity of the main bed layer is calculated by multiplying it by the pre-obtained filling ratio of the main bed layer and the protective bed layer.

4. The intelligent control method for periodic switching equipment according to claim 1, characterized in that, Based on the attenuation rate database, determine the predicted attenuation rate after each subsequent use or regeneration, including: Retrieve the measured attenuation rate values ​​after each use or regeneration from the attenuation rate database; The difference in attenuation rate is calculated by subtracting the corresponding measured values ​​of attenuation rate from two consecutive values. Assuming that the attenuation rate difference between all two consecutive values ​​is equal, the predicted attenuation rate after each subsequent use or regeneration is calculated based on the attenuation rate difference and the last measured attenuation rate value in the attenuation rate database.

5. The intelligent control method for periodic switching equipment according to claim 1, characterized in that, Based on the attenuation rate database, determine the predicted attenuation rate after each subsequent use or regeneration, including: A regression prediction model is established with the decay rate as the dependent variable and time or number of uses as the independent variable. Based on the regression prediction model and at least some measured attenuation rates in the attenuation rate database, the predicted attenuation rate is determined for each subsequent use or regeneration.

6. The intelligent control method for periodically switching equipment according to claim 1, characterized in that, Based on the actual effective processing capacity and the predicted attenuation rate, the maximum operating time of the core layer of the equipment after multiple uses or regenerations is calculated, including: Based on the actual effective processing capacity and the predicted attenuation rate, the predicted effective processing capacity after each subsequent use or regeneration is determined. The inflow rate and impurity concentration of the subsequent raw materials are obtained, and the maximum operating time of the main bed and the maximum operating time of the protective bed are calculated based on the inflow rate and impurity concentration of the subsequent raw materials and the predicted effective processing capacity. The maximum operating time of the main bed layer and the maximum operating time of the protective bed layer are taken as the maximum operating time of the core layer of the equipment after multiple uses or regeneration.

7. The intelligent control method for periodic switching equipment according to claim 6, characterized in that, The switching and regeneration time thresholds include the minimum necessary time for switching and the minimum necessary time for regeneration; Based on the maximum operating time of the core layer of the device, and in conjunction with pre-set switching and regeneration time thresholds, the operating status of the periodically switching device is dynamically adjusted, including: The maximum operating time of the protective bed is compared with the minimum necessary switching time to obtain the first comparison result; The maximum operating time of the main bed layer is added to the maximum operating time of the protective bed layer to calculate the sum of the maximum operating times. The sum of the maximum running time is compared with the minimum necessary time for regeneration to obtain a second comparison result; Based on the first comparison result and the second comparison result, the operating status of the periodically switching equipment is dynamically adjusted.

8. The intelligent control method for periodically switching equipment according to claim 1, characterized in that, The method further includes: Collect data on the decay rate and the corresponding number of runs to establish a data sample set; Construct a frequency prediction model, and train the frequency prediction model using the data sample set to obtain a trained frequency prediction model; Based on the aforementioned frequency prediction model, the maximum number of runs corresponding to the actual effective processing capacity being reduced to the minimum allowable value is determined.

9. The intelligent control method for a periodic switching device according to claim 8, characterized in that, The method further includes: Determine the actual number of times the periodically switching equipment is operated; If the actual number of runs reaches a set percentage of the maximum number of runs, a maintenance and repair task will be triggered.

10. An intelligent control system for a periodically switching device, characterized in that, include: The calculation module is used to determine the initial effective processing capacity of the periodically switching equipment according to the set calculation scheme; A module is established to calculate the actual effective processing capacity and measured attenuation rate after each use or regeneration based on the initial effective processing capacity, and to establish an attenuation rate database. The prediction module is used to determine the predicted value of the decay rate after each subsequent use or regeneration based on the decay rate database. The calculation module is used to calculate the maximum operating time of the core layer of the device after multiple uses or regenerations, based on the actual effective processing capacity and the predicted attenuation rate. The control module is used to dynamically adjust the operating status of the periodically switching device based on the maximum operating time of the core layer of the device and in combination with the preset switching and regeneration time thresholds.

Images