A multi-channel catalyst uniform loading method and system based on modular diversion matrix and intelligent control

Abstract

The present invention provides a multi-channel catalyst uniform loading method and system based on a modular shunt matrix and intelligent control, which is applied to the field of data processing technology. The present application processes 10-way tubular reactor information and catalyst information based on equipment component information to generate equipment adaptation parameter information; processes operation process information based on fault diagnosis and maintenance information to generate fault prevention parameter information; processes pre-loading preparation information based on equipment component information to generate loading preparation adjustment factors; processes operation process information and step number information corresponding to the operation process information based on the loading preparation adjustment factors to generate step classification information and execution sequence information of the operation process; inputs the equipment adaptation index, step classification information and execution sequence information of the operation process, and fault prevention parameter information into the target catalyst loading operation model for processing to generate catalyst loading execution result information.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a multi-channel catalyst uniform filling method and system based on a modular shunt matrix and intelligent control. Background Art

[0002] In the field of multi-channel catalyst loading technology, current methods present a series of critical issues that urgently need to be addressed. First, it is difficult to ensure uniform catalyst loading in a 10-channel shell-and-tube reactor. Catalysts of different shapes (such as strips, cloverleafs, and honeycombs) and particle sizes (3-8mm) vary significantly in their flowability and packing properties. Existing technologies cannot precisely control this, resulting in uneven distribution of catalyst within each tube, seriously affecting reaction efficiency and product quality stability.

[0003] Secondly, there is a lack of assessment of the compatibility of the equipment with the reactor and catalyst. This lack of comprehensive consideration of the compatibility of equipment components (such as the grid-distributed bin and the toothed plate control module) with different reactor specifications (tube diameter 25mm, center-to-center tolerance ±1.5mm) and catalyst characteristics makes it difficult to determine optimal operating parameters, resulting in inadequate equipment performance and potentially increased equipment wear and catalyst waste.

[0004] Furthermore, the operational process lacks fault prevention capabilities. Common faults such as single-channel metering deviations and multi-channel synchronization errors lack effective monitoring and early warning. Handling often relies on post-event experience, failing to fundamentally address the issues. This results in prolonged equipment downtime and reduced production efficiency. Precise adjustments to pre-loading preparations are also difficult. The impact of tube cleanliness, deformation, and equipment parameter deviations on loading performance cannot be accurately assessed, making it difficult to optimize the operational process.

[0005] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute prior art known to ordinary technicians in the field. Summary of the Invention

[0006] The purpose of this application is to provide a multi-channel catalyst uniform loading method and system based on a modular diversion matrix and intelligent control, which, at least to a certain extent, overcomes the problems existing in the prior art. By processing reactor and catalyst information based on equipment component information, equipment adaptation parameters are obtained and the compatibility of the equipment with the loading task is evaluated. Fault diagnosis and maintenance information is used to process operational process information to generate fault prevention parameters to help prevent faults in advance. Pre-loading preparation information is processed in combination with equipment components and technical standards to derive a loading preparation adjustment factor for calibrating pre-loading preparation work.

[0007] Next, the operational process is optimized based on the loading preparation adjustment factor, clarifying the step classification and execution sequence. Equipment adaptation indicators, operational process information, and fault prevention parameters are input into the model to first obtain a correlation evaluation value for the loading effect. This is then used to optimize the loading strategy decision vector. After analytical transformation, execution result information, including equipment resource allocation and loading quality quantitative indicators, is generated. This allows for comprehensive control of the catalyst loading process, improving loading quality and efficiency, and providing strong technical support for related industrial production.

[0008] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by practice of the invention.

[0009] According to one aspect of the present application, a multi-channel catalyst uniform loading method based on a modular diversion matrix and intelligent control is provided, including: obtaining 10-way shell-and-tube reactor information, catalyst information, equipment component information, pre-loading preparation information, operation process information, and fault diagnosis and maintenance information; processing the 10-way shell-and-tube reactor information and catalyst information based on the equipment component information to generate equipment adaptation parameter information; processing the operation process information based on the fault diagnosis and maintenance information to generate fault prevention parameter information; processing the pre-loading preparation information based on the equipment component information and the technical standard information corresponding to the equipment component information to generate a loading preparation adjustment factor; processing the operation process information and the step numbering information corresponding to the operation process information based on the loading preparation adjustment factor to generate step classification information and execution sequence information of the operation process; inputting the equipment adaptation index, the step classification information and execution sequence information of the operation process and the fault prevention parameter information into the target catalyst loading operation model for processing to generate catalyst loading execution result information.

[0010] Another aspect of the present application provides a multi-channel catalyst uniform loading device based on a modular diversion matrix and intelligent control, including: an acquisition module for acquiring 10-way shell and tube reactor information, catalyst information, equipment component information, pre-loading preparation information, operation process information, fault diagnosis and maintenance information; a processing module for processing the 10-way shell and tube reactor information and catalyst information based on the equipment component information to generate equipment adaptation parameter information; processing the operation process information based on the fault diagnosis and maintenance information to generate fault prevention parameter information; processing the pre-loading preparation information based on the equipment component information and the technical standard information corresponding to the equipment component information to generate a loading preparation adjustment factor; processing the operation process information and the step number information corresponding to the operation process information based on the loading preparation adjustment factor to generate step classification information and execution sequence information of the operation process; inputting the equipment adaptation index, the step classification information and execution sequence information of the operation process and the fault prevention parameter information into the target catalyst loading operation model for processing to generate catalyst loading execution result information.

[0011] According to another aspect of the present application, an electronic device is provided, comprising: a first processor; and a memory for storing executable instructions of the first processor; wherein the first processor is configured to execute the executable instructions to implement the above-mentioned multi-channel catalyst uniform loading method based on modular diversion matrix and intelligent control.

[0012] According to another aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a second processor, the multi-channel catalyst uniform loading method based on the modular diversion matrix and intelligent control is implemented.

[0013] This application provides a multi-channel catalyst uniform loading method and system based on a modular diversion matrix and intelligent control. Based on equipment component information, reactor and catalyst information is processed to obtain equipment adaptation parameters and assess the compatibility of the equipment with the loading task. Fault diagnosis and maintenance information is used to process operational process information and generate fault prevention parameters to help prevent failures in advance. Pre-loading preparation information is processed in conjunction with equipment components and technical standards to derive a loading preparation adjustment factor for calibrating pre-loading preparations.

[0014] Next, the operational process is optimized based on the loading preparation adjustment factor, clarifying the step classification and execution sequence. To obtain the target catalyst loading operation model, the model is determined through sample collection, grouping, and training. Finally, the equipment adaptation index, operational process information, and fault prevention parameters are input into the model. The model first obtains the associated evaluation value of the loading effect, which is then used to optimize the loading strategy decision vector. After analytical transformation, the execution result information, including equipment resource allocation and loading quality quantitative indicators, is generated. This allows for comprehensive control of the catalyst loading process, improves loading quality and efficiency, and provides strong technical support for related industrial production.

[0015] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A flow chart showing a multi-channel catalyst uniform loading method based on a modular diversion matrix and intelligent control provided by one embodiment of the present application is shown;

[0017] Figure 2 A schematic structural diagram of a multi-channel catalyst uniform loading device based on a modular diversion matrix and intelligent control provided by an embodiment of the present application is shown. DETAILED DESCRIPTION

[0018] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0019] The following combination Figure 1 The following describes a method for uniformly loading a multi-channel catalyst based on a modular diversion matrix and intelligent control according to an exemplary embodiment of the present application. It should be noted that the following application scenarios are provided solely to facilitate understanding of the spirit and principles of the present application, and the embodiments of the present application are not limited in this respect. Rather, the embodiments of the present application are applicable to any applicable scenario.

[0020] In one embodiment, the present application also proposes a multi-channel catalyst uniform loading method and system based on a modular diversion matrix and intelligent control. Figure 1 The following schematically shows a flow chart of a multi-channel catalyst uniform loading method based on a modular diversion matrix and intelligent control according to an embodiment of the present application. Figure 1 As shown, the method is applied to the server and includes:

[0021] S101, obtaining 10-way shell-and-tube reactor information, catalyst information, equipment component information, pre-loading preparation information, operation process information, fault diagnosis and maintenance information.

[0022] In one embodiment, the following information is provided for a 10-channel shell-and-tube reactor. The compatible shells are 25 mm diameter tubes, with a center-to-center tolerance of ±1.5 mm. These parameters determine the layout and dimensions of the reactor's internal tubes, significantly impacting material distribution and flow paths during subsequent catalyst loading. Internal cleanliness of the tubes must be verified, with residual content ≤ 3 mg / m² (sample testing). Tube deformation must be inspected using an endoscope, with an ellipticity of less than 3‰ of the tube diameter. Tube cleanliness and deformation directly impact catalyst loading and reaction efficiency. Residual impurities within the tubes may block catalyst channels or affect catalyst activity; tube deformation can lead to uneven catalyst distribution. Applicable catalyst shapes include strips, trifoliate, and honeycomb, with particle sizes ranging from 3 to 8 mm diameter. Catalyst shape and particle size influence its flowability and distribution within the reactor. Catalysts of different shapes and particle sizes require different operating parameters and equipment settings during loading to ensure uniform loading. This involves information such as the density and bulk density of the catalyst. These characteristics will affect the calculation of the filling amount as well as the carrying capacity and operational stability of the equipment.

[0023] The equipment component information includes the following: a grid uniform distribution bin with a 10-station flow equalizer with a spacing of 38mm, which is used to preliminarily evenly distribute the catalyst so that the catalyst can be more evenly distributed before entering each channel. A tooth plate control module with 10 stations independently controls the flow rate. By adjusting the tooth plate gap, the flow rate of the catalyst in each channel can be accurately controlled, thereby achieving precise control of the filling amount and filling speed. A buffer control module prevents the catalyst from being broken due to excessive drop during the filling process, protects the integrity of the catalyst, and ensures that its catalytic performance is not affected. The conveying module, consisting of a conveyor belt and a servo motor drive system, is responsible for transporting the catalyst from the storage area to the reactor tube array. Its performance indicators such as operating speed and stability have an important impact on the filling efficiency and quality. The HMI human-machine interface is equipped with a 7-inch touch screen, which provides operators with an intuitive operating interface for convenient parameter setting, equipment monitoring, and operation instruction input. The PLC control module adopts Siemens S-200 to achieve coordinated control of various components of the equipment, ensure that the equipment operates stably according to preset programs and parameters, and improve the reliability and stability of equipment operation.

[0024] Pre-loading preparations include the following: Reactor inspection includes testing the internal cleanliness and deformation of the tubes. Cleanliness must meet a residue requirement of ≤3 mg / m², and deformation must meet an ovality requirement of <3‰ of the tube diameter. Inspection results determine whether additional cleaning or repair of the reactor is necessary to meet catalyst loading requirements. Machine start positions are set according to the tube distribution map to avoid overlapping operations, ensure orderly loading, improve efficiency, and prevent safety issues such as equipment collisions. Gradient filling parameters are set to measure and adjust machine parameters based on the filling height, enabling more accurate catalyst loading, ensuring consistent filling heights within each tube, and improving reaction uniformity. The operational process includes the following: startup steps, performing a 10-channel parallel calibration, injecting 100g of standard catalyst into each channel. If mass differences cause the catalyst synchronization to end more than 5 seconds, the tooth plate gap is adjusted. Calibration ensures accurate and synchronized catalyst injection across each channel, ensuring uniformity in subsequent loading. Filling mode is selected, with either uniform or buffered mode. In uniform mode, each channel features independent tooth plate adjustment (consistent regular clearances are recommended), suitable for general loading needs. In buffer mode, the release depth of the buffer suspension line is adjusted based on the drop size, addressing large drops that may cause catalyst breakage. Operation monitoring monitors key parameters such as inter-tube height difference and belt tension. The inter-tube height difference must be ≤10mm, and the belt tension should be maintained at 800-1200N. Real-time monitoring of these parameters allows for timely detection of equipment operating anomalies. For example, excessive inter-tube height difference may indicate uneven catalyst distribution, while abnormal belt tension may affect conveying efficiency or even cause equipment failure, allowing for timely adjustment measures.

[0025] Fault diagnosis and maintenance information include the following: single-channel metering deviation, check whether the belt tension is appropriate and whether the grid flow plate is stuck by catalyst debris. Improper belt tension will affect the stability of the catalyst delivery rate, and grid flow plate jamming may cause local flow rate abnormalities, which in turn cause single-channel metering deviation. Multi-channel synchronization out of tolerance, the correction steps include ensuring that the center of the belt has 5mm of elasticity when pressed, and using tools to clean the catalyst without damaging the belt body. These measures can be used to adjust the belt state, remove impurities that may affect metering, and restore the accuracy of multi-channel metering. Preventive maintenance checklist, during each use, clean the belt conveyor grid chute residue to ensure that there is no residue, to prevent residual catalyst from affecting the subsequent filling accuracy and equipment operation. After each use, clean the components used in the entire machine, requiring no residue and dust, etc., to extend the service life of the equipment, ensure stable equipment performance, and reduce the probability of failure.

[0026] S102 : Processing the 10-way tubular reactor information and the catalyst information based on the equipment component information to generate equipment adaptation parameter information.

[0027] In one embodiment, feature extraction processing is performed on the 10-way shell-and-tube reactor information and catalyst information to generate reactor specification features, catalyst shape features, catalyst particle size features, and reactor internal state features. The reactor specification feature is that the 10-way shell-and-tube reactor is adapted to a φ25mm shell-and-tube group, and the shell-and-tube center distance tolerance is ±1.5mm. These specification parameters directly affect the internal shell and tube layout of the reactor, determine the flow path and distribution space of the catalyst in the reactor, and are key basic data for subsequent quantitative analysis. Catalyst shape features include applicable catalyst shapes including strips, clover, and honeycomb. Catalysts of different shapes have different fluidity and stacking methods, and the requirements for equipment during the loading process are also different. For example, strip catalysts and honeycomb catalysts have different flow rates and distribution characteristics when passing through the diversion matrix system, which will affect the uniformity of loading.

[0028] Catalyst particle size characteristics include a particle size range of φ3-8mm, and the particle size affects the fluidity and bulk density of the catalyst. Catalysts with smaller particle sizes may flow more easily, but may also agglomerate during transportation; catalysts with larger particle sizes may have higher wear resistance requirements for the transportation and distribution components of the equipment. The impact of these factors on the filling effect needs to be considered during quantitative analysis. The internal state characteristics of the reactor include the need to confirm the cleanliness of the tubes, requiring residues to be ≤3mg / m² (sampling and testing); using an endoscope to detect tube deformation, and the ellipticity to be <3‰ of the tube diameter. Poor tube cleanliness may lead to catalyst poisoning or reduced activity, and tube deformation will change the flow trajectory of the catalyst, resulting in uneven filling. These two characteristics are important indicators for evaluating whether the reactor is suitable for filling.

[0029] The reactor specification characteristics are quantitatively analyzed and processed to generate the reactor adaptation quantitative factor. The tube diameter of the 10-way tube reactor is 25mm, the center distance tolerance is ±1.5mm. In quantitative analysis, the specifications of pipe diameter and center distance tolerance are first converted into specific values. The pipe diameter determines the cross-sectional area of ​​the tube, and the area formula of the circle is used to calculate the cross-sectional area of ​​the tube. (where d is the tube diameter), the cross-sectional area of ​​the tubes can be calculated, which directly affects the filling space and flow channel size of the catalyst in the tubes. The center distance tolerance reflects the relative position accuracy between the tubes, which will affect the distribution path and uniformity of the material between multiple tubes. For example, if the center distance tolerance is small, the distribution of materials between the tubes may be more uniform; if the tolerance is large, it may cause uneven distribution of materials in some tubes. The effective filling space is an important parameter for measuring the adaptability of the reactor. When calculating, it is necessary to consider the length and diameter of the tubes and possible obstacles inside the tubes (such as support structures, etc.). Assuming that the tube length is L, according to the tube cross-sectional area S calculated above, the filling space of the tube is The larger the effective loading space, the more catalysts can be loaded, and the higher the adaptability to large-scale loading tasks.

[0030] The theoretical uniformity of material distribution is closely related to factors such as the tube layout, center-to-center distance tolerance, and the reactor's feed method. For example, in a 10-way tube-to-tube reactor, if a uniform feed method is used and the tube center-to-center distance tolerance is small and uniform, the material distribution across the tubes will be relatively uniform. A material flow model can be established to simulate the material flow within the reactor and calculate the material distribution ratio within each tube. For example, computational fluid dynamics (CFD) methods can be used to simulate the material's initial conditions (such as flow velocity and flow rate) and reactor geometric parameters (tube diameter, center-to-center distance), thereby simulating the material flow trajectory and distribution within the reactor. By analyzing the simulation results, the differences in material filling levels within each tube can be determined, and the magnitude of these differences can be used to quantify the theoretical uniformity of material distribution. The more uniform the material distribution, the better the reactor's suitability for catalyst loading, as uniform material distribution improves catalyst reaction efficiency and overall performance.

[0031] Taking into account the values ​​of the converted tolerances of the tube diameter and center distance, as well as the calculated effective loading space and theoretical uniformity of material distribution, the reactor adaptation quantitative factor is generated through a certain algorithm (such as the weighted average method). Assume that the weight of the effective loading space is , the weight of the theoretical uniformity of material distribution is ,and , then the reactor adaptation quantization factor ,in For the actual effective filling space, For ideal filling space, is the filling amount of the material in the i-th row of tubes, is the average filling volume of each tube array. This quantitative factor can intuitively reflect the adaptability of the reactor to different filling tasks. The higher the value, the more the reactor meets the requirements during the filling process.

[0032] The catalyst shape characteristics and catalyst particle size characteristics are quantitatively analyzed and processed to generate the catalyst adaptation quantitative factor. For catalysts with different shapes such as strips, clover leaves, honeycombs, etc., their shape coefficient is an important basis for quantitative analysis. The shape coefficient of a strip catalyst can be expressed by the ratio of its length to its diameter. For example, if the length of the strip catalyst is l and the diameter is d, the shape coefficient is The shape of the clover is relatively complex, and the shape coefficient can be determined by its equivalent diameter and shape complexity. Assume that the equivalent diameter of the clover is By measuring its perimeter and area, and using specific geometric relationships to calculate the shape complexity C, the shape coefficient The shape factor of the honeycomb catalyst can be determined by the size of its honeycomb structure (such as the honeycomb pore size). , cell wall thickness t, etc.) and the arrangement of the honeycomb, for example (N is a coefficient related to the honeycomb arrangement.) These shape coefficients reflect the geometric characteristics of catalysts of different shapes and have a significant impact on their flow and packing characteristics in the packing equipment.

[0033] The relationship between particle size, flow resistance and stacking efficiency: The catalyst particle size is within the range of φ3-8mm, and the particle size is closely related to the flow resistance and stacking efficiency. According to the principles of fluid mechanics, the smaller the particle size, the greater the friction between the catalyst particles and the fluid at the same flow rate, and the greater the flow resistance. This can be explained by Stokes' law. (where F is the resistance of the particle, The relationship between particle size and flow resistance can be analyzed using the formula (where r is the fluid viscosity, r is the particle radius, and v is the relative velocity between the particle and the fluid). During the actual loading process, flow resistance affects the speed and uniformity of catalyst delivery within the equipment. For example, smaller particle sizes may require more power to transport the same amount of catalyst, and clogging may occur during delivery. Particle size also affects the catalyst's stacking efficiency. Generally speaking, smaller catalyst particles fill more voids during stacking, resulting in a higher stacking density, but this can also lead to an unstable stacking structure. Larger catalyst particles have a lower stacking density but a more stable stacking structure.

[0034] Combined with the relationship between the shape coefficient and particle size of the catalyst and the flow resistance and stacking efficiency, the corresponding quantitative indicators are determined. For catalysts of different shapes, the effects of their shape coefficient and particle size on flow resistance and stacking efficiency are considered separately. For example, for strip catalysts, the quantitative indicators ,in is the flow resistance coefficient calculated based on the particle size, is the bulk density. For the clover catalyst, ( The specific surface area of ​​the clover-shaped structure reflects the size of its active surface area and has an impact on the reaction efficiency). For honeycomb catalysts, ( (where is the porosity of the honeycomb, which affects the contact area between the reactants and the catalyst). These quantitative indicators take into account the shape and particle size characteristics of the catalyst and can more comprehensively measure the compatibility of the catalyst with the loading equipment.

[0035] Based on the determined quantitative indicators, the catalyst adaptation quantitative factor is generated by a suitable calculation method. A weighted summation method can be used. For example, assuming that the quantitative indicator weights of strip, clover, and honeycomb catalysts are ,and , then the catalyst adaptation quantitative factor This quantitative factor can intuitively reflect the adaptability of different catalysts to the loading equipment, help select the catalyst that best suits specific loading equipment and process requirements, and improve the catalyst loading effect and reaction efficiency.

[0036] The reactor and catalyst suitability factors are processed based on equipment component information and relevant technical standards to generate equipment suitability assessment information and corresponding weighted calculation results. The equipment components include a grid distribution bin, a toothed plate control module, a buffer control module, a conveyor module, an HMI (human-machine interface), and a PLC control module. The grid distribution bin's 10-position flow equalizers have a spacing of 38 mm, which affects the initial uniformity of catalyst distribution. The toothed plate control module's 10-position independent flow rate control function adjusts the flow rate based on catalyst characteristics. These component characteristics are closely related to the suitability of the reactor and catalyst. Relevant technical standards specify the performance requirements and operating specifications of equipment components under different operating conditions. Based on the equipment component information and technical standards, the reactor and catalyst suitability factors are comprehensively processed. Based on the technical standards' requirements for flow rate and distribution uniformity for different catalyst shapes and particle sizes under specific reactor specifications, combined with the actual performance of the equipment components, the importance of each factor in assessing equipment suitability is determined, thus generating equipment suitability assessment information and corresponding weighted calculation results.

[0037] The equipment adaptation assessment information and the corresponding weight calculation result information are processed to generate equipment adaptation parameter information, wherein the equipment adaptation parameter information is used to characterize the degree of adaptation of the equipment components to the 10-way tubular reactor for loading catalysts. Each quantitative factor is weighted and calculated according to the weight, and multiple factors such as reactor specifications, catalyst characteristics, and equipment component performance are comprehensively considered to generate equipment adaptation parameter information. The equipment adaptation parameter information intuitively reflects the degree of adaptation of the equipment components to the 10-way tubular reactor for loading catalysts in the form of specific numerical values ​​or parameter combinations. This information can be used to determine whether the equipment can meet the current reactor and catalyst loading requirements, providing an important basis for subsequent equipment adjustments and operation optimization, and ensuring efficient and accurate catalyst loading.

[0038] S103: Process the operation process information based on the fault diagnosis and maintenance information to generate fault prevention parameter information.

[0039] In one embodiment, feature extraction and processing are performed on the operation process information and fault diagnosis and maintenance information to generate abnormal operation step features, fault phenomenon features, maintenance cycle features, and maintenance item features. The operation process covers the startup steps and operation monitoring and other links. In the startup step, when performing 10-way parallel calibration, if the mass difference of 100g standard catalyst injected into each channel causes the synchronization end time to be greater than 5 seconds, this delay is an abnormal operation step feature. When selecting the filling mode, if the mode cannot be switched normally or the equipment operation is abnormal after switching, it is also an abnormal operation step. During the operation monitoring stage, when the height difference between the monitored pipes exceeds ≤10mm and the belt tension is not in the range of 800-1200N, these deviations from normal parameters can be recorded as abnormal operation step features.

[0040] Common fault symptoms include single-channel metering deviation and multi-channel synchronization deviation. When single-channel metering deviation occurs, inspection reveals improper belt tension or the grid plate is stuck by catalyst debris. These are characteristic fault symptoms. When multi-channel synchronization deviation occurs, the belt center elasticity does not meet the 5mm standard, and impurities within the equipment that affect metering are also characteristic fault symptoms. These symptoms directly reflect problems occurring during equipment operation and are important for subsequent fault cause analysis and prevention. Maintenance intervals are determined based on equipment usage. Cleaning the belt conveyor grid chute for residues during each use indicates that timely cleaning of the chute is necessary to ensure normal operation and loading accuracy within the short period of use. Cleaning all components after each use indicates a relatively long maintenance interval. The length and frequency of maintenance intervals affect equipment stability and the probability of failure, and are key characteristics of fault prevention analysis. The preventive maintenance checklist clearly defines maintenance items. Cleaning the belt conveyor grid chute for residues during each use to ensure that it is free of residue is a characteristic maintenance item. Cleaning all machine components after each use to remove residue and dust is also a key maintenance task. Different maintenance tasks target different parts of the equipment and their operating conditions, playing a key role in improving equipment performance and preventing failures.

[0041] Quantitative analysis and processing are performed on the characteristics of abnormal operation steps and fault phenomena to generate a quantitative fault risk factor. The frequency of abnormal operation steps and the severity of the fault phenomena are quantified. If calibration anomalies in the startup step occur frequently during multiple loading operations, and each anomaly results in significant quality variations, the corresponding quantitative value will be higher, indicating a greater fault risk. For fault phenomena, frequent and significant deviations in single-channel metering, or severe multi-channel synchronization out-of-tolerance, will be assigned a higher value in the quantification. Using a specific algorithm (such as a weighted calculation, where weights are assigned based on the significance of the anomaly or phenomenon to equipment operation), these quantified characteristics of abnormal operation steps and fault phenomena are combined to generate a quantitative fault risk factor. A higher value indicates a greater risk of fault during operation. Quantitative analysis and processing are performed on the characteristics of maintenance cycles and maintenance items to generate a quantitative maintenance need factor. Quantification is performed on the characteristics of maintenance cycles and maintenance items. Short maintenance cycles and a large number of maintenance items indicate a high maintenance need, resulting in a correspondingly higher quantitative value. For example, if equipment is used frequently and requires multiple maintenance tasks each time, such as cleaning the chute and complete machine components, as well as checking the wear of key equipment parts, then when quantifying this, a higher value will be assigned based on factors such as the maintenance cycle and the complexity and importance of the maintenance items. Using a reasonable quantification method (such as converting relevant parameters of the maintenance cycle and maintenance items into numerical values ​​and performing a weighted calculation), a maintenance demand quantification factor is generated, which reflects the degree of maintenance work required by the equipment.

[0042] Based on fault diagnosis and maintenance information and relevant equipment operating standards, the fault risk quantification factor and maintenance requirement quantification factor are processed to generate fault prevention assessment information and corresponding weight calculation results. Fault diagnosis and maintenance information records various equipment faults and maintenance situations, serving as an important foundation for subsequent analysis. For example, detailed records of past single-channel metering deviations and multi-channel synchronization deviations, including the time of occurrence, operating conditions at the time, and corrective measures, provide real-world data support for assessing fault risk and maintenance needs. Relevant equipment operating standards specify the parameter ranges and operating specifications for normal equipment operation. Based on fault diagnosis and maintenance information and equipment operating standards, the fault risk quantification factor and maintenance requirement quantification factor are comprehensively processed. For example, based on the standard's provisions for parameters such as belt tension and inter-tube height difference, combined with actual deviations from these parameters during faults, the importance of the fault risk quantification factor in the fault prevention assessment is determined. Furthermore, the weight of the maintenance requirement quantification factor is determined based on the standard's requirements for equipment maintenance cycles and maintenance items. By comprehensively considering these factors, fault prevention assessment information and corresponding weight calculation results are generated.

[0043] The fault prevention assessment information and the corresponding weighted calculation results are processed to generate fault prevention parameter information. This fault prevention parameter information characterizes the key parameters and response strategies for preventing faults during the multi-channel catalyst loading process. The fault risk quantification factor and the maintenance requirement quantification factor are weighted according to their respective weights, comprehensively considering multiple factors such as fault risk and maintenance requirements. The generated fault prevention parameter information intuitively reflects the key parameters and response strategies for preventing faults during the multi-channel catalyst loading process in the form of specific values ​​or parameter combinations. For example, a high weight and large value for the fault risk quantification factor indicate a high fault risk in the current process, and enhanced monitoring and adjustment of key operational steps may be necessary. A high weight for the maintenance requirement quantification factor indicates the need for increased maintenance frequency and intensity. This information provides clear guidance to operators, helping them take proactive measures to prevent faults and ensure smooth catalyst loading.

[0044] S104 : Processing the pre-loading preparation information based on the equipment component information and the technical standard information corresponding to the equipment component information to generate a loading preparation adjustment factor.

[0045] In one embodiment, pre-loading preparation information, equipment component information, and corresponding technical standard information are extracted and classified to generate information on tube cleanliness deviation, tube deformation deviation, equipment parameter setting differences, and technical standard compliance differences. During pre-loading preparation, the internal cleanliness of the tubes must be confirmed. The standard requires a residue content of ≤3 mg / m² (sample testing). The residue content within the actual tubes is measured and compared with the standard value to obtain tube cleanliness deviation information. If the actual residue content exceeds the standard, the deviation is positive; if it is below the standard, the deviation is negative. For example, if the actual residue content of a tube is 5 mg / m², its cleanliness deviation information will be reflected as 2 mg / m² exceeding the standard, indicating that the tube cleanliness does not meet the standard, which may affect catalyst loading and subsequent reactions. Tube deformation is inspected using an endoscope. The standard stipulates that the ovality should be less than 3‰ of the tube diameter. The actual ovality of the tubes is measured and compared with the standard ovality to obtain tube deformation deviation information. If the actual ovality is greater than the standard ovality, it indicates that the tube deformation exceeds the standard, which will affect the uniformity of catalyst distribution within the tube. For example, if a tube has a diameter of 25mm and the standard ovality upper limit is 0.075mm (25×3‰), and the actual measured ovality is 0.1mm, the deformation deviation information exceeds the standard value by 0.025mm.

[0046] The equipment components include a grid-distributed bin, a tooth plate control module, a buffer control module, a conveying module, an HMI human-machine interface, and a PLC control module. Each component has its own standard parameter settings. For example, the tooth plate control module is used to precisely control the flow rate, and its standard tooth plate gap corresponds to different catalyst loading requirements. The parameter setting values ​​during actual equipment operation are compared with the standard parameter values ​​to obtain information on equipment parameter setting differences. If the actual tooth plate gap setting is inconsistent with the standard value, it may cause abnormal catalyst flow rate, affecting the loading volume and loading speed. The technical standards have clear requirements for the performance and operating specifications of equipment components under different operating conditions. The actual operation and performance of the equipment components are checked to determine whether they comply with the relevant technical standards, thereby determining the technical standard compliance difference information. For example, for the conveying module, the technical standards specify its operating speed range and stability indicators. If the actual operating speed exceeds the specified range or the stability does not meet the standard, technical standard compliance difference information will be generated, which may affect the catalyst conveying effect and loading quality.

[0047] Based on the technical standards for equipment components, information on tube cleanliness deviations, tube deformation deviations, equipment parameter setting differences, and technical standard compliance differences is processed to generate deviation type judgment information and deviation severity assessment information. Based on the technical standards for equipment components, the extracted tube cleanliness deviations, tube deformation deviations, equipment parameter setting differences, and technical standard compliance differences are analyzed and judged. If the tube cleanliness deviation is caused by a substandard cleaning process, it can be determined to be a cleaning process deviation type; tube deformation deviations may be structural deviations caused by equipment aging or improper installation; equipment parameter setting differences may be parameter setting deviations caused by human error or control system failure; and technical standard compliance differences are determined based on the specific non-compliant standard clauses, such as non-compliance with electrical safety standards or mechanical performance standards. Clarifying the deviation type facilitates targeted resolution.

[0048] The severity of various deviations is also evaluated based on the technical standards of equipment components. For the deviation of tube cleanliness, if the residue content is only slightly higher than the standard value, the effect on the catalyst activity is small and it can be evaluated as a mild deviation; if the residue content is too high, it may cause catalyst poisoning and inactivation, and it is evaluated as a severe deviation. In terms of tube deformation deviation, the ellipticity exceeds the standard value slightly, and the effect on the catalyst distribution is limited, which is a mild deviation; if the ellipticity seriously exceeds the standard, it may cause the catalyst to be seriously unevenly distributed in the tube, affecting the reaction efficiency, and it is evaluated as a severe deviation. Differences in equipment parameter settings and differences in technical standard compliance are also evaluated in a similar way, according to the degree of impact on equipment operation and catalyst loading, and are divided into different levels such as mild, moderate, and severe.

[0049] Based on the deviation type judgment information and deviation severity assessment information, the target data in the pre-loading preparation information is marked and screened to generate deviation data screening results. For tubes with serious tube cleanliness deviations, their relevant data, such as tube number, location, cleanliness test data, etc., are marked; for components with large differences in equipment parameter settings, their parameter setting values, standard values, and difference amounts are marked. By marking, problematic data can be quickly identified, facilitating subsequent screening and processing, such as screening the marked data from high to low deviation severity and priority of deviation type. Data with severe deviations are screened out first, because the problems reflected by these data have a greater impact on catalyst loading and require special attention and processing. For example, the tube data with tube deformation that seriously exceeds the standard and the equipment component data with serious substandard technical standards are first screened out to provide key basis for subsequent adjustments and optimizations.

[0050] The deviation data screening results are integrated and quantified to generate a loading preparation adjustment factor, where the loading preparation adjustment factor is used to characterize the deviation from the standard requirements in the pre-loading preparation work and the degree of impact on the subsequent loading operation. The screened deviation data are integrated, and different types of deviation data are summarized and analyzed. For example, data such as the deviation of tube cleanliness, the deviation of tube deformation, the difference in equipment parameter settings, and the difference in compliance with technical standards are combined to fully understand the problems existing in the pre-loading preparation work. Through integration, the correlation and mutual influence between different deviations can be found, providing a more comprehensive data basis for quantitative processing. Using appropriate quantitative methods, such as weighted calculation, weights are set according to the degree of impact of different deviation types and severity on the loading operation, and the integrated deviation data are quantified to generate a loading preparation adjustment factor. Assume that the weight of the tube cleanliness deviation is , the tube deformation deviation weight is , the equipment parameter setting difference weight is , the weight of the difference in technical standard compliance is ,and The loading preparation adjustment factor is calculated by multiplying the quantified value of each deviation (such as the multiple of cleanliness deviation exceeding the standard, the specific value of deformation deviation, etc.) by the corresponding weight, and then summing the results. This factor represents the deviation of pre-loading preparation work from the standard requirements in the form of a specific value. The larger the value, the more serious the deviation, and the greater the impact on subsequent loading operations. Operators can adjust the loading operation process and equipment parameters accordingly to ensure smooth catalyst loading.

[0051] S105 , processing the operation flow information and the step number information corresponding to the operation flow information based on the loading preparation adjustment factor to generate step classification information and execution sequence information of the operation flow.

[0052] In one embodiment, operational process information, loading preparation adjustment factors, and corresponding step number information are extracted and classified to generate step execution difference information, adjustment factor association information, and operational effect deviation information. The operational process includes startup steps (such as 10-channel parallel calibration and filling mode selection) and operation monitoring. When comparing the actual operational process with the standard process, if the quality differences in the standard catalyst injected into each channel during the 10-channel parallel calibration result in a synchronization end time greater than 5 seconds, or if the actual mode switching operation during filling mode selection is inconsistent with the expected one, these are considered step execution difference information. This information reflects the differences in step execution between the actual operation and the standard process and serves as the basis for subsequent analysis. The loading preparation adjustment factor is generated based on pre-loading preparation information, equipment component information, and technical standard information. The relationship between this adjustment factor and each operational process step is analyzed. For example, deviations in tube cleanliness may affect the flow rate of catalyst during transport, which in turn is associated with the flow rate adjustment step of the toothed plate control module; deviations in tube deformation may be related to adjustments to the reactor's feed method. Determining the manner and extent of the impact of the adjustment factor on each operational step and generating adjustment factor association information helps clarify the path of the adjustment factor in the operational process. Operational performance is assessed by monitoring key parameters in the operating process, such as inter-tube height difference and belt tension. A height difference of ≤10mm or a belt tension outside the 800-1200N range indicates a deviation in operational performance. This deviation data, known as operational performance deviation information, intuitively demonstrates the gap between the actual performance of equipment operation and catalyst loading under the current operating process and the ideal state.

[0053] Based on the rules governing the loading preparation adjustment factor, a comprehensive analysis of step execution discrepancies, adjustment factor correlations, and operational performance deviations is performed to determine the type of adjustment required. If the catalyst flow rate is abnormal due to tube cleanliness deviations, parameter adjustments to the conveyor module's operating speed or the plate-gear control module's clearance may be necessary. Large tube deformation deviations may necessitate replanning the feed path or repairing the reactor, representing a process change. Clarifying the type of adjustment facilitates targeted adjustment strategy development. Similarly, based on the rules governing the loading preparation adjustment factor, the degree of adjustment is assessed. For parameter adjustments, if the tube cleanliness deviation is minor, a minor adjustment to the plate-gear clearance may be sufficient; if the deviation is significant, a significant adjustment to the conveyor module speed may be necessary. For process changes, if the tube deformation exceeds the standard only slightly, a partial adjustment to the feed method may be sufficient; if it exceeds the standard significantly, the entire loading process may require redesign. Assessing the degree of adjustment helps determine the magnitude and scope of the adjustment, avoiding over- or under-adjustments.

[0054] Based on the adjustment type determination and adjustment degree assessment information, target data in the operation process information is marked and filtered to generate adjustment data screening results. Target data in the operation process information is marked based on the adjustment type determination and adjustment degree assessment information. If the chute plate gap is determined to require adjustment, relevant data from the chute plate control module is marked, including the current chute plate gap value, the target value, and the adjustment direction. If the feed path is determined to require replanning, data related to feed-related equipment components (such as the grid distribution bin and conveying module) and the reactor tube layout data are marked. This marking allows for quick identification of data requiring adjustment, preparing for subsequent screening. The marked data is then screened according to specific criteria. Data related to severe deviations is prioritized. For example, if tube deformation significantly exceeds the standard, data related to the tube and related feed and conveying components is prioritized. Data that is difficult to adjust or critical to loading performance is also prioritized. This screening process allows focus on data with the greatest impact on the operation process, improving adjustment efficiency.

[0055] The adjustment data screening results are integrated and quantified to generate step classification information and execution sequence information of the operation process, wherein the step classification information and execution sequence information of the operation process are used to characterize the reasonable classification and correct execution sequence of the operation process under the influence of the loading preparation adjustment factor. The screened adjustment data are integrated, and different types of adjustment data (such as parameter adjustment data and process change data) are summarized and analyzed. For example, the tooth plate gap adjustment data, the conveying module speed adjustment data, and the feed path change data are combined to fully understand the various aspects that need to be adjusted in the operation process. The integrated data can discover the correlation and mutual influence between different adjustments, and provide a more comprehensive data basis for quantitative processing. Quantitative processing generates information: Use appropriate quantitative methods, such as weighted calculations, to set weights according to the degree of influence of the adjustment type and degree on the operation process, quantify the integrated adjustment data, and generate step classification information and execution sequence information of the operation process. Assume that the parameter adjustment weight is , the process change adjustment weight is ,and . The quantitative value of each adjustment data (such as the adjustment range of the tooth plate gap, the quantitative value of the complexity of the feed path change, etc.) is multiplied by the corresponding weight, and then the sum is calculated to determine the priority and classification of each operation step. For example, urgent and important adjustment steps are classified as high priority categories, and general adjustment steps are classified as low priority categories. The final generated step classification information and execution sequence information can clearly demonstrate the reasonable classification and execution sequence of the operation process under the influence of the loading preparation adjustment factor, guide the operator to adjust the operation process in an orderly manner, and ensure the smooth progress of the catalyst loading work.

[0056] S106 , inputting the equipment adaptation index, the step classification information and execution sequence information of the operation process and the fault prevention parameter information into the target catalyst loading operation model for processing to generate catalyst loading execution result information.

[0057] In one embodiment, an operational sample set and a preset catalyst loading operation model are obtained. The operational sample set includes information on the 10-way shell-and-tube reactor (such as tube diameter, center-to-center distance tolerance, internal cleanliness, and deformation), catalyst information (shape, particle size, density, etc.), equipment component information (parameters of components such as the grid distribution bin and the toothed plate control module), pre-loading preparation information (reactor inspection results, machine starting position setting, etc.), operational process information (startup steps, filling mode selection, operation monitoring parameters, etc.), and fault diagnosis and maintenance information (common faults and treatment measures, maintenance cycles and items, etc.). This multi-source information comprehensively records the actual catalyst loading situation under different operating conditions, providing a rich data foundation for model training. The preset catalyst loading operation model can use a neural network model from deep learning, such as a multi-layer perceptron (MLP). It consists of an input layer, multiple hidden layers, and an output layer. The number of nodes in the input layer is determined by the number of features in the input data. Assuming the input data contains n features of the aforementioned information, the number of input layer nodes is n. Two or three hidden layers can be set to learn complex relationships in the data. The number of nodes in each layer can be determined based on experience or experimentation, generally ranging from tens to hundreds. For example, the first hidden layer can be set to 128 nodes and the second to 64 nodes. The number of nodes in the output layer is determined by the output requirements of the model. If the output is an evaluation indicator related to the filling effect (such as filling uniformity, equipment resource allocation, etc.), assuming there are m indicators, the number of output layer nodes is m. The ReLU function can be used as the model's activation function to increase the model's nonlinear expression capabilities and improve the model's fit to complex data.

[0058] The number of features in each modal data set within the operational sample set is counted, and a sampling ratio is generated based on the balance of feature distribution. Different modal data include reactor-related features, catalyst features, and equipment component features. The sampling ratio is determined based on this balance to ensure that all features are appropriately represented during sampling and to prevent certain features from being overlooked during training due to their low number. For example, if data related to reactor internal cleanliness is relatively rare in the sample set, but it significantly impacts loading performance, its sampling ratio should be increased. By analyzing the distribution of features across modal data, the probability of each feature being selected during sampling is calculated to form a sampling ratio. Based on the sampling ratio, multimodal stratified sampling is performed on the training sample set to generate a preset number of sampling feature combinations. Based on the different modalities of the data (e.g., reactor information as one modality and catalyst information as another), features are selected from each layer according to the sampling ratio to generate a preset number of sampling feature combinations. Each sampling feature combination contains a subset of key features from different modalities, representing different loading conditions. These combinations are used for subsequent model training and analysis, enabling the model to learn data characteristics under various operating conditions.

[0059] Statistical tests are performed based on any key feature combined with each sampling feature, dividing the data into a good loading effect group and a poor loading effect group. Each group contains a preset number of data samples, and at least one sample contains fault identification information. Statistical tests are performed based on any key feature (such as the reactor adaptation quantification factor in the equipment adaptation parameter information or the fault risk quantification factor in the fault prevention parameter information) combined with each sampling feature. Taking the reactor adaptation quantification factor as an example, the relationship between it and each sampling feature combination is analyzed. Using statistical tests (such as hypothesis testing), the data is divided into a good loading effect group and a poor loading effect group. Each group contains a preset number of data samples, and at least one sample contains fault identification information (such as single-channel metering deviation, multi-channel synchronization deviation, and other fault-related information). This grouping helps compare the differences in data features under different loading effects, providing more targeted data for model training, enabling the model to learn the relationship between fault occurrence and loading effect.

[0060] A pre-set catalyst loading operation model is iteratively trained based on groups with good and poor loading results. Cross-validation is used to optimize model parameters, generating a trained model and performance metrics. Cross-validation is used to optimize model parameters during training. Cross-validation involves partitioning the sample set into multiple subsets (e.g., k-fold cross-validation, typically with a k value of 5 or 10), alternating between using one subset as the training set and another as the validation set. During each training session, the model weights and biases are adjusted using a backpropagation algorithm to minimize the model's loss function (e.g., mean squared error, which measures the difference between the model's predicted values ​​and the true values) on the training set. Simultaneously, model performance is evaluated on the validation set to avoid overfitting. After multiple training iterations, the model gradually learns patterns in the data, generating a trained model and performance metrics (e.g., loading accuracy and fault prediction accuracy). These performance metrics are used to evaluate the model's performance on different tasks. Loading accuracy is measured by calculating the similarity between the model's predicted loading results and the actual ideal loading results, while fault prediction accuracy is determined by the proportion of fault identification information correctly predicted by the model.

[0061] If the fault identification information in the training results is identified by the model as a key feature that affects the evaluation of the loading effect, the trained model will be used as the target catalyst loading operation model. If the fault identification information in the training results is identified by the model as a key feature that affects the evaluation of the loading effect, this indicates that the model can effectively capture important factors that may cause loading problems and has good fault prediction and loading effect evaluation capabilities. The trained model is determined as the target catalyst loading operation model. This model can be used for catalyst loading operations. Based on the input equipment adaptation indicators, step classification information and execution sequence information of the operation process, and fault prevention parameter information, accurate catalyst loading execution result information is generated to improve loading quality and efficiency.

[0062] In another embodiment, the equipment adaptation index, the step classification information and execution sequence information of the operation process and the fault prevention parameter information are processed based on the target catalyst loading operation model to generate a loading effect correlation evaluation value. The target catalyst loading operation model will refer to the reactor adaptation quantitative factor generated by the equipment component information and the reactor specification characteristics. For example, the diameter of the tube of a 10-way shell and tube reactor is The model calculates the cross-sectional area of ​​the tubes based on these parameters, which in turn determines the catalyst filling space and flow channel size within the tubes. The effective filling space is also calculated by considering the impact of possible obstructions (such as support structures) within the tubes. A large effective filling space and high theoretical uniformity of material distribution (derived by using computational fluid dynamics (CFD) to simulate the flow trajectory and distribution of materials within the reactor) indicate that the reactor is well suited for catalyst loading, which will be given a higher weight in the evaluation calculation.

[0063] For the shape and particle size characteristics of the catalyst, the model will analyze its compatibility with the equipment components. Catalysts of different shapes (strips, clover, honeycomb) have different shape coefficients. For example, the shape coefficient of a strip catalyst can be expressed by the ratio of its length to its diameter. The particle size is in the range of φ3-8mm, and the particle size affects the flow resistance and stacking efficiency of the catalyst. The model determines quantitative indicators based on these factors. For example, for strip catalysts, the quantitative indicators take into account the shape coefficient, the flow resistance coefficient calculated based on the particle size, and the stacking density. The quantitative indicators of catalysts of different shapes are combined to evaluate the degree of compatibility between the catalyst and the loading equipment. If the catalyst adaptation quantitative factor is high, it means that the catalyst can be better uniformly loaded in the current equipment, and has a positive contribution to the evaluation value associated with the loading effect.

[0064] The initial steps of the operation process include 10-channel parallel calibration and filling mode selection. During the 10-channel parallel calibration, if the mass difference of the 100g standard catalyst injected into each channel causes the synchronization to end in a time greater than 5 seconds, this indicates a calibration issue, affecting the uniformity of subsequent filling, and the model will assess the rationality of this operation as low. When selecting the filling mode, the choice between uniform mode and buffer mode should be determined based on the actual situation. If the selected mode does not match the characteristics of the reactor and catalyst, such as not selecting the buffer mode in the case of a large drop, the model will lower the assessment of the rationality of the operation process. During the operation monitoring phase, key parameters such as the height difference between tubes and belt tension are important criteria for assessing the rationality of the operation process. The height difference between tubes should be ≤10mm, and the belt tension should be maintained between 800-1200N. Excessive height difference between tubes means that the catalyst filling height in each tube array is inconsistent, affecting reaction uniformity. Abnormal belt tension can lead to unstable catalyst delivery and affect the accuracy of the filling amount. The model monitors these parameters in real time. If the parameters are outside the normal range, the assessment score of the rationality of the operation process will be lowered, which will in turn affect the correlation assessment value of the filling effect.

[0065] The model analyzes the characteristics of operational step anomalies and fault phenomena to generate a quantified failure risk factor. For example, if startup step calibration anomalies frequently occur during multiple loading operations, and each anomaly results in significant quality variation, or if single-channel metering deviation or multi-channel synchronization errors occur frequently, this indicates a high failure risk. The model quantifies the failure risk based on these conditions. A high failure risk quantification factor indicates a high probability of failure within the current operational process, which will reduce the effectiveness assessment of the failure prevention measures. The model also considers maintenance cycle characteristics and maintenance item characteristics. If equipment is frequently used, with short maintenance cycles and a high number of maintenance items, this indicates a high maintenance requirement. For example, cleaning the conveyor chute during each use and cleaning all components after each use can effectively reduce the probability of equipment failure. The model evaluates the effectiveness of the failure prevention measures based on the execution of maintenance measures and the degree to which maintenance requirements are met. If maintenance measures are implemented effectively and meet maintenance requirements, the model deems the failure prevention measures highly effective, positively impacting the associated assessment value of the loading performance.

[0066] The target catalyst loading operation model comprehensively calculates the above factors such as the adaptability of equipment components, the rationality of operation procedures and the effectiveness of fault prevention measures. Through the preset algorithm, a corresponding weight is assigned to each factor. For example, the weight of the adaptability of equipment components is , the weight of the rationality of the operation process is , the effectiveness weight of the fault prevention measures is ,and The quantitative evaluation value of each factor is multiplied by the corresponding weight, and then the sum is calculated to obtain the loading effect correlation evaluation value. For example, the quantitative evaluation value of the equipment component adaptation degree is A, the quantitative evaluation value of the operation process rationality is B, and the quantitative evaluation value of the effectiveness of the fault prevention measures is C. Then the loading effect correlation evaluation value is This evaluation value comprehensively reflects the expected loading effect under the current loading conditions. If the evaluation value is high, it means that with the current equipment, operating procedures and fault prevention measures, it is expected that a good catalyst loading effect can be achieved, such as uniform catalyst distribution, accurate loading amount, stable equipment operation, etc.; conversely, if the evaluation value is low, it indicates that there are some problems that need to be improved, such as adjusting equipment parameters, optimizing operating procedures or strengthening fault prevention measures, etc., to improve the loading effect and ensure the smooth progress of catalyst loading.

[0067] Based on the loading effect correlation evaluation value, the loading strategy decision vector within the target catalyst loading operation model is optimized and adjusted to generate a loading resource allocation deviation vector. The loading strategy decision vector contains the model's allocation decision information for various loading resources (such as the amount of catalyst allocated to each channel, equipment operating parameters, etc.) when loading the catalyst. If the loading effect correlation evaluation value is not ideal, the model will analyze the factors causing the difference between the evaluation value and the ideal value. For example, if it is found that the catalyst allocation amount of certain channels is unreasonable, affecting the loading effect, the model will adjust the catalyst allocation parameters of the corresponding channels in the decision vector; if the execution order of a step in the operation process is incorrect, the model will adjust the relevant execution order parameters to generate a loading resource allocation deviation vector. This vector reflects the direction and degree of adjustment that needs to be made to the original loading strategy to achieve a better loading effect.

[0068] The loading resource allocation deviation vector is parsed and converted to generate catalyst loading execution result information. This information characterizes the equipment resources allocated to the catalyst loading and provides quantitative indicators of the rationality of the loading quality. Each element in the deviation vector is parsed to understand the meaning and function of each adjustment parameter. For example, this information determines which channels require catalyst allocation increases or decreases, and which equipment operating parameters (such as conveying speed and plate clearance) should be adjusted. This parsed information is then converted into actual loading operation instructions and result data to generate catalyst loading execution result information. This information characterizes the equipment resources allocated to the catalyst loading, clarifying the specific operating status and resource allocation of each equipment component (such as the grid distribution bin and conveying module) during the loading process. Furthermore, it provides quantitative indicators of loading quality rationality, such as catalyst loading uniformity (measured by the standard deviation of the catalyst loading within each tube array; smaller standard deviations indicate higher uniformity) and the deviation rate between the loading amount and the theoretical value, to intuitively reflect the rationality of the loading quality. These indicators can help operators determine whether the loading effect meets the requirements. If not, the operating procedures and equipment parameters can be further optimized based on the result information to ensure that the catalyst loading work is carried out efficiently and accurately.

[0069] In this application, the server obtains information about the 10-way tubular reactor, catalyst, equipment components, pre-loading preparation, operating procedures, and fault diagnosis and maintenance. Based on the equipment component information, the reactor and catalyst information is processed to obtain equipment adaptation parameters and evaluate the compatibility of the equipment with the loading task. Fault diagnosis and maintenance information is used to process the operating procedure information and generate fault prevention parameters to help prevent failures in advance. Pre-loading preparation information is processed in combination with equipment components and technical standards to derive a loading preparation adjustment factor for calibrating pre-loading preparations.

[0070] Next, the operational process is optimized based on the loading preparation adjustment factor, clarifying the step classification and execution sequence. To obtain the target catalyst loading operation model, the model is determined through sample collection, grouping, and training. Finally, the equipment adaptation index, operational process information, and fault prevention parameters are input into the model. The model first obtains the associated evaluation value of the loading effect, which is then used to optimize the loading strategy decision vector. After analytical transformation, the execution result information, including equipment resource allocation and loading quality quantitative indicators, is generated. This allows for comprehensive control of the catalyst loading process, improves loading quality and efficiency, and provides strong technical support for related industrial production.

[0071] In one embodiment, Figure 2 As shown, the present application also provides a multi-channel catalyst uniform loading device based on a modular diversion matrix and intelligent control, comprising:

[0072] Acquisition module 201, for acquiring 10-way tubular reactor information, catalyst information, equipment component information, pre-loading preparation information, operation process information, fault diagnosis and maintenance information;

[0073] Processing module 202 is used to process the 10-way shell-and-tube reactor information and catalyst information based on the equipment component information to generate equipment adaptation parameter information; process the operation process information based on the fault diagnosis and maintenance information to generate fault prevention parameter information; process the pre-loading preparation information based on the equipment component information and the technical standard information corresponding to the equipment component information to generate a loading preparation adjustment factor; process the operation process information and the step number information corresponding to the operation process information based on the loading preparation adjustment factor to generate step classification information and execution sequence information of the operation process; input the equipment adaptation index, the step classification information and execution sequence information of the operation process and the fault prevention parameter information into the target catalyst loading operation model for processing to generate catalyst loading execution result information.

[0074] The computer-readable storage medium provided in the above-mentioned embodiments of the present application and the multi-channel catalyst uniform loading method based on modular diversion matrix and intelligent control provided in the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.

[0075] Each embodiment in this application is described in a related manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for evaluating the multi-channel catalyst uniform loading method based on modular shunt matrix and intelligent control, electronic device, electronic device, and readable storage medium embodiment, since it is basically similar to the above-mentioned embodiment of the multi-channel catalyst uniform loading method based on modular shunt matrix and intelligent control, the description is relatively simple, and the relevant parts can be referred to the partial description of the embodiment of the multi-channel catalyst uniform loading method based on modular shunt matrix and intelligent control.

Claims

1. A multi-channel catalyst uniform loading method based on modular diversion matrix and intelligent control, characterized in that: include: Obtain 10-way tubular reactor information, catalyst information, equipment component information, pre-loading preparation information, operation process information, fault diagnosis and maintenance information; Based on the equipment component information, the 10-way tubular reactor information and catalyst information are processed to generate equipment adaptation parameter information. Feature extraction processing is performed on the 10-way tubular reactor information and catalyst information to generate reactor specification characteristics, catalyst shape characteristics, catalyst particle size characteristics, and reactor internal state characteristics. The reactor specification characteristics are that the 10-way tubular reactor is adapted to a φ25mm tubular group, and the tubular center distance tolerance is ±1.5mm. The reactor specification characteristics are quantitatively analyzed to generate a reactor adaptation quantitative factor. The catalyst shape characteristics and catalyst particle size characteristics are quantitatively analyzed to generate a catalyst adaptation quantitative factor. Based on equipment component information and technical standard information, the reactor adaptation quantitative factors and catalyst adaptation quantitative factors are comprehensively processed. Based on the flow rate and distribution uniformity requirements of different catalyst shapes and particle sizes under specific reactor specifications in the technical standards, combined with the actual performance of the equipment components, the importance of each quantitative factor in evaluating equipment adaptability is determined, thereby generating equipment adaptability evaluation information and corresponding weight calculation result information; Processing the equipment adaptation assessment information and the corresponding weight calculation result information to generate equipment adaptation parameter information, wherein the equipment adaptation parameter information is used to characterize the adaptability of the equipment components to the catalyst loading of the 10-channel tubular reactor; Processing operation process information based on fault diagnosis and maintenance information to generate fault prevention parameter information; Processing the pre-loading preparation information based on the equipment component information and the technical standard information corresponding to the equipment component information to generate a loading preparation adjustment factor, including: extracting and classifying the pre-loading preparation information, the equipment component information and the technical standard information corresponding thereto to generate tube cleanliness deviation information, tube deformation deviation information, equipment parameter setting difference information, and technical standard compliance difference information; processing the tube cleanliness deviation information, tube deformation deviation information, equipment parameter setting difference information, and technical standard compliance difference information based on the equipment component technical standard to generate deviation type judgment information and deviation severity assessment information; marking and screening target data in the pre-loading preparation information based on the deviation type judgment information and the deviation severity assessment information to generate deviation data screening results; integrating and quantifying the deviation data screening results to generate a loading preparation adjustment factor, wherein the loading preparation adjustment factor is used to characterize the deviation from the standard requirements in the pre-loading preparation work and the degree of influence on subsequent loading operations; Processing the operation process information and the step number information corresponding to the operation process information based on the loading preparation adjustment factor to generate step classification information and execution sequence information of the operation process; The equipment adaptation index, the step classification information and the execution sequence information of the operation process and the fault prevention parameter information are input into the target catalyst loading operation model for processing to generate catalyst loading execution result information.

2. The method according to claim 1, wherein Processing operation process information based on fault diagnosis and maintenance information to generate fault prevention parameter information, including: Perform feature extraction and processing on operation process information and fault diagnosis and maintenance information to generate operation step abnormality features, fault phenomenon features, maintenance cycle features, and maintenance item features; Quantitatively analyze and process abnormal characteristics of operating steps and fault phenomena to generate quantitative factors of fault risk; Quantitatively analyze and process maintenance cycle characteristics and maintenance project characteristics to generate maintenance demand quantitative factors; Based on the fault diagnosis and maintenance information and the relevant equipment operation standard information, the fault risk quantification factor and the maintenance demand quantification factor are processed to generate the fault prevention assessment information and the corresponding weight calculation result information; The fault prevention assessment information and the corresponding weight calculation result information are processed to generate fault prevention parameter information, wherein the fault prevention parameter information is used to characterize key parameters and response strategy information for preventing faults in the multi-channel catalyst loading operation process.

3. The method according to claim 1, wherein The operation process information and the step number information corresponding to the operation process information are processed based on the loading preparation adjustment factor to generate step classification information and execution sequence information of the operation process, including: Extract and classify the operation process information, loading preparation adjustment factors, and corresponding step number information to generate step execution difference information, adjustment factor correlation information, and operation effect deviation information; Based on the action rules of the loading preparation adjustment factor, the step execution difference information, the adjustment factor correlation information, and the operation effect deviation information are processed to generate adjustment type judgment information and adjustment degree evaluation information; Mark and filter target data in the operation process information based on the adjustment type judgment information and the adjustment degree assessment information to generate adjustment data screening results; The adjustment data screening results are integrated and quantified to generate step classification information and execution sequence information of the operation process. The step classification information and execution sequence information of the operation process are used to represent the reasonable classification and correct execution sequence of the operation process under the influence of the loading preparation adjustment factor.

4. The method according to claim 1, wherein Obtaining the target catalyst loading operation model includes: Obtaining an operation sample set and a preset catalyst loading operation model; Count the number of features of each modal data in the sample set and generate a sampling ratio based on the balance of feature distribution; Perform multimodal stratified sampling on the training sample set based on the sampling ratio to generate a preset number of sampling feature combinations; Based on a statistical test of any key feature combined with each sampling feature, the data is divided into a good filling effect group and a poor filling effect group, each group contains a preset number of data samples, and at least one sample has fault identification information; Iteratively train the preset catalyst loading operation model based on the good loading effect group and the poor loading effect group, optimize the model parameters through cross-validation, and generate the trained model and performance indicators; If the fault identification information in the training results is recognized by the model as a key feature that affects the loading effect evaluation, the trained model will be used as the target catalyst loading operation model.

5. The method according to claim 1, wherein The equipment adaptation index, the step classification information and execution sequence information of the operation process, and the fault prevention parameter information are input into the target catalyst loading operation model for processing to generate catalyst loading execution result information, including: Based on the target catalyst loading operation model, the equipment adaptation index, the step classification information and execution sequence information of the operation process, and the fault prevention parameter information are processed to generate a loading effect correlation evaluation value; Based on the loading effect correlation evaluation value, the loading strategy decision vector within the target catalyst loading operation model is optimized and adjusted to generate a loading resource allocation deviation vector; The loading resource allocation deviation vector is analyzed and converted to generate catalyst loading execution result information, wherein the catalyst loading execution result information is used to characterize the equipment resource information allocated to the catalyst loading and the rationality quantitative index of the loading quality.

6. A multi-channel catalyst uniform loading device based on modular diversion matrix and intelligent control, characterized in that: For implementing the method of claim 1, the apparatus comprises: Acquisition module, used to obtain 10-way tubular reactor information, catalyst information, equipment component information, pre-loading preparation information, operation process information, fault diagnosis and maintenance information; A processing module is used to process the 10-way shell-and-tube reactor information and catalyst information based on the equipment component information to generate equipment adaptation parameter information; process the operation process information based on the fault diagnosis and maintenance information to generate fault prevention parameter information; process the pre-loading preparation information based on the equipment component information and the technical standard information corresponding to the equipment component information to generate a loading preparation adjustment factor; process the operation process information and the step number information corresponding to the operation process information based on the loading preparation adjustment factor to generate step classification information and execution sequence information of the operation process; input the equipment adaptation index, the step classification information and execution sequence information of the operation process and the fault prevention parameter information into the target catalyst loading operation model for processing to generate catalyst loading execution result information.

7. An electronic device, characterized in that: include: a first processor; and a memory for storing executable instructions of the first processor; The first processor is configured to execute the multi-channel catalyst uniform loading method based on modular diversion matrix and intelligent control according to any one of claims 1 to 5 by executing the executable instructions.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the second processor, the multi-channel catalyst uniform loading method based on modular diversion matrix and intelligent control as described in any one of claims 1 to 5 is implemented.

Images