Self-adaptive catalyst bed pressure difference monitoring method and system based on multi-channel dynamic calibration

Abstract

The invention provides a self-adaptive catalyst bed pressure difference monitoring method and system based on multi-channel dynamic calibration, and is applied to the technical field of data processing. According to the method, the maintenance specification information is processed based on the fault diagnosis information, and the equipment exception processing parameter information is generated; based on the technical document reference information and the version number information corresponding to the technical document reference information, processing the measuring instrument operation process information to generate an operation optimization factor; processing the real-time measurement information and the version number information corresponding to the real-time measurement information based on the operation optimization factor, and generating measurement state classification information and processing priority information of the real-time measurement information; and inputting the measurement specification index, the measurement state classification information of the real-time measurement information, the processing priority information and the equipment exception processing parameter information into the target adaptive differential pressure monitoring model for processing, and generating differential pressure monitoring optimization result information.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method and system for monitoring the pressure difference of an adaptive catalyst bed based on multi-channel dynamic calibration. Background Art

[0002] In practice, measuring instruments lack unified and precise standards for system initialization, channel selection, parameter setting, data collection, and export. Different operators may use different settings, compromising the accuracy and reliability of measurement results. For example, the various initialization modes and arbitrary data collection frequencies and communication interface parameters of measuring instruments make it difficult to compare measured data under different conditions, making it difficult to ensure the accuracy of differential pressure monitoring and providing a reliable basis for chemical production.

[0003] Existing equipment maintenance specifications and troubleshooting methods are relatively fragmented. Fault diagnosis relies heavily on simple fault code prompts, lacking in-depth analysis and comprehensive evaluation. For example, when a measuring instrument fails, only superficial fault information can be obtained, and the type and severity of the fault cannot be accurately determined, making it difficult to perform targeted maintenance. Moreover, maintenance items and cycles are often set based on fixed time intervals, without fully integrating the actual operating conditions and fault history of the equipment. This results in low maintenance efficiency, a high equipment failure rate, and an increased risk of production interruptions. In the face of equipment failures or changes in operating conditions, the monitoring strategy cannot be adjusted in a timely manner, resulting in a decrease in the reliability and accuracy of the monitoring results, and an inability to meet the chemical production demand for high-precision, high-reliability differential pressure monitoring.

[0004] 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

[0005] The present application aims to provide an adaptive catalyst bed pressure differential monitoring method and system based on multi-channel dynamic calibration, which, at least to a certain extent, overcomes the problems of the prior art. The method processes technical document reference information to generate measurement specification parameter information to assess the impact of each operational step on the accuracy of pressure differential monitoring. Furthermore, maintenance specification information is processed based on fault diagnosis information to obtain equipment abnormality handling parameter information, which is used to characterize abnormal conditions associated with equipment failures. Next, the measuring instrument operation process information is processed in conjunction with the technical document reference information and version number to generate an operation optimization factor to measure the impact of deviations from standard requirements on monitoring operations. The operation optimization factor is used to process real-time measurement information to classify measurement states and determine processing priorities. Measurement specification indicators, classification and priority information for real-time measurement information, and equipment abnormality handling parameters are input into the model to generate an associated evaluation value for pressure differential monitoring effectiveness. The evaluation value optimizes the internal decision vector of the model to obtain a resource allocation deviation vector. After analytical transformation, the pressure differential monitoring optimization result information is ultimately generated. This provides a scientific basis and optimization guidance for catalyst bed pressure differential monitoring in actual production, contributing to efficient and stable operation of chemical production.

[0006] 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.

[0007] According to one aspect of the present application, an adaptive catalyst bed pressure difference monitoring method based on multi-channel dynamic calibration is provided, including: obtaining measuring instrument system initialization information, channel selection information, parameter setting information, data acquisition information, data export information, fault diagnosis information, maintenance specification information and technical document reference information; processing the measuring instrument system initialization information, channel selection information, parameter setting information, data acquisition information, data export information based on the technical document reference information to generate measurement specification parameter information; processing the maintenance specification information based on the fault diagnosis information to generate equipment abnormality processing parameter information; processing the measuring instrument operation process information based on the technical document reference information and the version number information corresponding to the technical document reference information to generate an operation optimization factor; processing the real-time measurement information and the version number information corresponding to the real-time measurement information based on the operation optimization factor to generate measurement status classification information and processing priority information of the real-time measurement information, wherein the real-time measurement information is used to characterize measurement-related attribute information such as the measurement status, pressure value, flow value, etc. of each channel; inputting the measurement specification indicators, the measurement status classification information and processing priority information of the real-time measurement information and the equipment abnormality processing parameter information into the target adaptive pressure difference monitoring model for processing to generate pressure difference monitoring optimization result information.

[0008] Another aspect of the present application is an adaptive catalyst bed pressure difference monitoring device based on multi-channel dynamic calibration, characterized in that it includes: an acquisition module for acquiring measuring instrument system initialization information, channel selection information, parameter setting information, data acquisition information, data export information, fault diagnosis information, maintenance specification information and technical document reference information; a processing module for processing the measuring instrument system initialization information, channel selection information, parameter setting information, data acquisition information and data export information based on the technical document reference information to generate measurement specification parameter information; processing the maintenance specification information based on the fault diagnosis information to generate equipment abnormality processing parameter information; based on the technical document reference information, a processing module for ... The measuring instrument operation process information is processed based on the technical document reference information and the version number information corresponding to the technical document reference information to generate an operation optimization factor; the real-time measurement information and the version number information corresponding to the real-time measurement information are processed based on the operation optimization factor to generate measurement status classification information and processing priority information of the real-time measurement information, wherein the real-time measurement information is used to characterize measurement-related attribute information such as the measurement status, pressure value, flow value, etc. of each channel; the measurement specification indicators, the measurement status classification information and processing priority information of the real-time measurement information and the equipment abnormality processing parameter information are input into the target adaptive pressure difference monitoring model for processing to generate pressure difference monitoring optimization result information.

[0009] According to another aspect of the present application, an electronic device is characterized in that it includes: a first processor; and a memory for storing executable instructions of the first processor; wherein the first processor is configured to execute the above-mentioned adaptive catalyst bed pressure difference monitoring method based on multi-channel dynamic calibration by executing the executable instructions.

[0010] 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 method for adaptive catalyst bed pressure difference monitoring based on multi-channel dynamic calibration is implemented.

[0011] The present application provides an adaptive catalyst bed pressure difference monitoring method and system based on multi-channel dynamic calibration, which obtains multi-source information such as measuring instrument system initialization, channel selection, and parameter setting. The above information is processed based on the technical document reference information to generate measurement specification parameter information to evaluate the impact of each operation link on the accuracy of pressure difference monitoring. At the same time, the maintenance specification information is processed based on the fault diagnosis information to obtain equipment abnormality processing parameter information for characterizing abnormal conditions related to equipment failures. Then, the measuring instrument operation process information is processed in combination with the technical document reference information and version number to generate an operation optimization factor to measure the impact of the deviation of the operation process from the standard requirements on the monitoring operation. The operation optimization factor is used to process real-time measurement information to achieve measurement status classification and determination of processing priority.

[0012] The model inputs measurement specifications, the classification and priority of real-time measurement information, and equipment anomaly handling parameters to generate an associated assessment value for differential pressure monitoring effectiveness. Based on this assessment value, the model's internal decision vector is optimized to derive a resource allocation deviation vector. After analytical transformation, this ultimately generates differential pressure monitoring optimization results. This provides a scientific basis and optimization guidance for catalyst bed differential pressure monitoring in actual production, contributing to efficient and stable chemical production.

[0013] 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

[0014] Figure 1 A flow chart showing an adaptive catalyst bed pressure difference monitoring method based on multi-channel dynamic calibration provided by an embodiment of the present application is shown;

[0015] Figure 2 A schematic structural diagram of an adaptive catalyst bed pressure difference monitoring device based on multi-channel dynamic calibration provided in one embodiment of the present application is shown. DETAILED DESCRIPTION

[0016] 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.

[0017] The following combination Figure 1 The following describes an adaptive catalyst bed pressure differential monitoring method based on multi-channel dynamic calibration 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.

[0018] In one embodiment, the present application also proposes an adaptive catalyst bed pressure difference monitoring method and system based on multi-channel dynamic calibration. Figure 1 The following schematically shows a flow chart of a method for adaptive catalyst bed pressure difference monitoring based on multi-channel dynamic calibration according to an embodiment of the present application. Figure 1 As shown, the method is applied to the server and includes:

[0019] S101, obtaining measuring instrument system initialization information, channel selection information, parameter setting information, data acquisition information, data export information, fault diagnosis information, maintenance specification information and technical document reference information.

[0020] In one embodiment, when the measuring instrument is started, the default measurement mode is set to "continuous measurement", the data acquisition frequency is set to 1 time per second, the communication interface of the measuring instrument is initialized to an Ethernet interface compatible with the factory automation system, and the baud rate is set to 100Mbps. These parameters constitute the initialization information of the measuring instrument system and provide basic settings for subsequent measurement work. The company's catalyst bed has 10 different positions that need to monitor the pressure difference. The operator selected channels 1, 3, 5, 7, and 9 for real-time measurement according to the needs. These selected channel numbers and related selection operation records are the channel selection information, which determines the specific object of the measurement. In order to accurately measure the pressure difference, the operator sets the pressure measurement range of the measuring instrument to 0-10MPa, the accuracy requirement to ±0.01MPa, and the flow measurement range to 0-50m3 / h according to the design parameters and process requirements of the catalyst bed. These specific parameter settings for the measurement indicators are the parameter setting information.

[0021] During the measurement process, the measuring instrument collects real-time pressure and flow data from each channel according to the set parameters and channel selection. For example, at a certain moment, channel 1 collected a pressure value of 2.5 MPa and a flow value of 15 m³ / h; channel 3 collected a pressure value of 2.3 MPa and a flow value of 13 m³ / h, and so on. This real-time data is called data acquisition information. The company needs to transmit the measurement data to a data analysis system for further processing and storage. Therefore, the data export format is set to CSV file, the export path is to the specific folder " / data / catalyst_pressure" on the factory server, and the export interval is set to once every hour. This information, including the data export method and frequency, is called data export information. During the measurement process, the measuring instrument malfunctioned. The fault diagnosis system displayed the fault code "E001," indicating "pressure sensor malfunction." This fault may be due to sensor aging, resulting in inaccurate measurement data. This set of information, including the fault code and meaning, is the fault diagnosis information, which indicates the equipment problem.

[0022] According to the measuring instrument's manual and the company's maintenance procedures, daily inspections include checking the instrument's exterior for damage and ensuring proper connection lines. Quarterly maintenance requires sensor calibration and cleaning. Annual maintenance covers a comprehensive inspection of the instrument's internal circuitry and replacement of wearing parts. This information, which specifies maintenance tasks at different time intervals, constitutes maintenance specifications. The company uses version 2.0 of the measuring instrument's technical documentation, which details the instrument's functions, operating procedures, parameter setting ranges, and maintenance requirements. For example, the documentation specifies the normal operating range of the pressure measurement range and the optimal application scenarios for different channels. The relevant content in these technical documents constitutes technical document reference information, providing a standard basis for measuring instrument operation and maintenance.

[0023] S102 : Processing measuring instrument system initialization information, channel selection information, parameter setting information, data acquisition information, and data export information based on technical document reference information to generate measurement specification parameter information.

[0024] In one embodiment, feature extraction processing is performed on the measuring instrument system initialization information, channel selection information, parameter setting information, data acquisition information, and data export information to generate initialization setting features, channel selection features, parameter setting features, data acquisition mode features, and data export method features. When the measuring instrument is started, the default measurement mode is set to "timed measurement", the data acquisition interval is 5 minutes, the communication interface is initialized to RS485, and the baud rate is 9600bps. The initialization setting features extracted from this information are: measurement mode is "timed measurement", acquisition interval is 5 minutes, communication interface type is RS485, and baud rate is 9600bps. The operator selected channels 2, 4, and 6 of the measuring instrument to monitor the pressure difference at different positions of the catalyst bed. The channel selection features thus obtained are: the selected channels are numbered 2, 4, and 6.

[0025] According to process requirements, the pressure measurement range is set to 0-8 MPa with an accuracy requirement of ±0.02 MPa, and the flow measurement range is set to 0-30 m³ / h. The extracted parameter setting features are: pressure measurement range 0-8 MPa, pressure accuracy ±0.02 MPa, and flow measurement range 0-30 m³ / h. Over a period of time, channel 2 collected pressure values of 3.2 MPa, 3.1 MPa, and so on, and flow values of 12 m³ / h, 11.5 m³ / h, and so on. Channels 4 and 6 also collected corresponding real-time data. Data acquisition pattern features extracted from this data include the temporal sequence of data acquisition (e.g., timed acquisition) and the fluctuation range of the acquired data. The data export format is set to Excel, the export path is "D:\catalyst_data\," and the export interval is set to 1:00 AM daily. The extracted data export method features are: export format Excel, export path "D:\catalyst_data\," and export interval is 1:00 AM daily.

[0026] Initialization settings and channel selection features are quantitatively analyzed to generate a system base quantization factor. The measurement mode "periodic measurement" is quantized as 1 (continuous measurement is quantized as 2), and the acquisition interval of 5 minutes is quantized as 5. The RS485 communication interface type is quantized as 8 (out of 10) based on its transmission stability and versatility, and the baud rate of 9600 bps is quantized as 6 (out of 10). The number of selected channels, 3, is quantized as 3. These quantization values are combined and a specific algorithm (such as weighted averaging) is used to generate a system base quantization factor. Assuming the weights are 0.2 for measurement mode, 0.1 for acquisition interval, 0.3 for communication interface, 0.2 for baud rate, and 0.2 for number of selected channels, the system base quantization factor is calculated as 1 × 0.2 + 5 × 0.1 + 8 × 0.3 + 6 × 0.2 + 3 × 0.2 = 4.9.

[0027] The parameter setting characteristics, data acquisition mode characteristics, and data export method characteristics are quantitatively analyzed and processed to generate the measurement operation quantitative factors. The pressure measurement range of 0-8MPa is quantified as 7 (out of 10) based on the degree of matching with the ideal measurement range, the pressure accuracy of ±0.02MPa is quantified as 8, and the flow measurement range of 0-30m

[0028] / h was quantified as 7; the data acquisition mode was quantified as 8 based on its stability and accuracy; the versatility of the data export format Excel was quantified as 9, the rationality of the export path was quantified as 8, and the suitability of the export time interval was quantified as 7. Similarly, the measurement operation quantification factor was generated using the weighted average algorithm. Assuming the corresponding weights are 0.3, 0.3, 0.2, 0.1, and 0.1, the measurement operation quantification factor is calculated as 7 × 0.3 + 8 × 0.3 + 7 × 0.2 + 8 × 0.1 + 9 × 0.1 = 7.6.

[0029] Based on the technical documentation reference information, the system foundation quantization factor and measurement operation quantization factor are processed to generate measurement specification evaluation information and corresponding weight calculation results. The technical documentation reference information specifies the standard parameters and standard procedures for various measurement instrument operations. The system foundation quantization factor of 4.9 and the measurement operation quantization factor of 7.6 are compared with the technical documentation. For example, the technical documentation sets a weight of 0.4 for initialization-related operations and a weight of 0.6 for measurement operations. Based on these weights, the measurement specification evaluation information is calculated. Assume that the evaluation value corresponding to the system foundation quantization factor is 4.9 × 0.4 = 1.96, and the evaluation value corresponding to the measurement operation quantization factor is 7.6 × 0.6 = 4.56. The resulting measurement specification evaluation information is [1.96, 4.56], and the corresponding weight calculation results are [0.4, 0.6]. This indicates that in the current measurement instrument operation, the initialization phase contributes 1.96 to the overall standardization level, and the measurement operation phase contributes 4.56. Furthermore, the initialization phase accounts for 40% of the importance of the measurement standardization level, while the measurement operation phase accounts for 60%.

[0030] The measurement specification evaluation information and the corresponding weight calculation results are processed to generate measurement specification parameter information. The measurement specification parameter information characterizes the degree to which the instrument's operational compliance during system initialization, channel selection, parameter setting, data acquisition, and data exporting, among other steps, impacts differential pressure monitoring accuracy. The weighted sum of each evaluation value yields the following: measurement specification parameter information = 1.96 × 0.4 + 4.56 × 0.6 = 3.544. This value indicates that, considering the instrument's operational compliance during these steps, the degree to which operational compliance impacts differential pressure monitoring accuracy is 3.544 (assuming a maximum score of 10, higher values indicate a greater positive impact on differential pressure monitoring accuracy and closer alignment with standard operation). A value close to the maximum indicates that the instrument's operation complies with standards across all steps, contributing to accurate differential pressure monitoring. A lower value indicates that non-standard operation exists in certain steps, potentially impacting differential pressure monitoring accuracy and requiring adjustments and optimization to improve overall measurement performance.

[0031] S103: Process the maintenance specification information based on the fault diagnosis information to generate equipment abnormality processing parameter information.

[0032] In one embodiment, fault diagnosis information and maintenance specification information are extracted and classified to generate information about fault codes, fault meanings, fault handling methods, daily inspection items, quarterly maintenance items, and annual maintenance items. The fault diagnosis system for the measuring instrument displays the fault code "F003," indicating "abnormal flow sensor signal," and the fault handling method is "check the flow sensor connection wiring; if the wiring is normal, replace the sensor." According to the maintenance specification information for the measuring instrument, daily inspection items include checking the instrument's exterior for damage and loose connections; quarterly maintenance items include calibrating the sensor; and annual maintenance items include a comprehensive inspection of the measuring instrument's internal circuitry and replacement of wearing parts. Therefore, by extracting and classifying the fault diagnosis information and maintenance specification information, we obtain the following: fault code information: F003; fault meaning information: abnormal flow sensor signal; fault handling method information: check the flow sensor connection line, and replace the sensor if the line is normal; daily inspection item information: check whether the instrument appearance is damaged and whether the connection lines of the measuring instrument are loose; quarterly maintenance item information: calibrate the sensor; annual maintenance item information: conduct a comprehensive inspection of the internal circuit of the measuring instrument and replace wearing parts.

[0033] Based on the fault diagnosis information, the fault-related content in the maintenance specification information is processed to generate fault type determination information and fault severity assessment information. Based on the fault diagnosis information "F003 - Flow sensor signal abnormality," the fault type is determined to be a sensor fault. Further assessment of the fault severity reveals that the abnormal flow sensor signal may lead to inaccurate flow data, affecting the assessment of catalyst bed reaction conditions. If not promptly addressed, it may cause a production accident. Therefore, it is assessed as a high-severity fault, resulting in: Fault Type Determination Information: Sensor Fault Fault Severity Assessment Information: High Severity.

[0034] Based on the fault type determination and fault severity assessment information, target data within the maintenance specification information is marked and filtered to generate abnormal maintenance data screening results. Maintenance data related to flow sensors is marked. For example, in daily inspections, information related to checking the flow sensor connection wiring is marked; in quarterly maintenance, information related to sensor calibration is marked; and in annual maintenance, information related to the inspection and replacement of consumable parts in the flow sensor circuit is marked. This fault-related target data is filtered out to generate abnormal maintenance data screening results. For example, data related to "inspecting the flow sensor connection wiring," "calibrating the flow sensor," and "inspecting and replacing consumable parts in the flow sensor circuit" are filtered out.

[0035] The results of abnormal maintenance data screening are integrated and quantified to generate equipment abnormality handling parameter information. This information is used to characterize the abnormal conditions and severity of faults that occur during the maintenance process. During quantification, a quantification rule can be set. For example, for fault type, a sensor fault is assigned a value of 5 (assuming the total fault type score is 1-10, with larger values indicating more severe fault types). For fault severity, a higher severity is assigned a value of 8 (out of 10). For daily inspections, quarterly maintenance, and annual maintenance, fault-related operations are quantified based on their difficulty and importance. For example, checking the flow sensor connection line is quantified as 3, flow sensor calibration operations are quantified as 4, and inspection and replacement of wearing parts in the circuit where the flow sensor is located are quantified as 6. The device abnormality handling parameter information is calculated using a weighted average (assuming the weights are 0.4 for fault type, 0.4 for fault severity, 0.1 for daily inspection-related operations, 0.05 for quarterly maintenance-related operations, and 0.05 for annual maintenance-related operations): 5 × 0.4 + 8 × 0.4 + 3 × 0.1 + 4 × 0.05 + 6 × 0.05 = 6. This device abnormality handling parameter information, "6" (assuming a full score of 10), represents the abnormality and severity of the fault during maintenance. A higher value indicates a more severe abnormality, a greater impact on the normal operation of the measuring instrument, and the need for more timely and in-depth maintenance.

[0036] S104 : Processing the measuring instrument operation procedure information based on the technical document reference information and the version number information corresponding to the technical document reference information to generate an operation optimization factor.

[0037] In one embodiment, the measuring instrument operation process information, technical document reference information and the corresponding version number information are extracted and classified to generate operation step difference information, parameter setting deviation information, version compatibility difference information, and technical document compliance difference information. A multi-channel catalyst bed pressure difference measuring instrument of model XYZ-100 is used, and its technical document reference information version number is V3.0. The measuring instrument operation process information shows that when starting the measurement, the operator first selects the channel, then sets the parameters, and then starts data collection. However, the standard operation process specified in the technical document V3.0 is to set the parameters first, then select the channel, and finally start data collection. This generates operation step difference information: the order of channel selection and parameter setting steps in the actual operation process is inconsistent with the technical document.

[0038] Regarding parameter settings, the pressure measurement range in the operational process information was set to 0-12 MPa, while the applicable pressure measurement range for this type of measuring instrument specified in Technical Documentation V3.0 is 0-10 MPa. This resulted in parameter setting deviation information: the pressure measurement range setting exceeded the range specified in the technical documentation. Because the company used measuring instrument software version V2.5, which did not fully match the software version requirements corresponding to Technical Documentation V3.0, some functional compatibility issues arose, resulting in version compatibility discrepancy information: measuring instrument software version V2.5 has compatibility issues with the software version required by Technical Documentation V3.0. Comparison revealed that some operations in the operational process did not fully comply with the technical documentation regarding the basis for setting the data collection frequency, resulting in technical document compliance discrepancy information: the data collection frequency setting did not fully comply with the technical documentation.

[0039] Based on technical document reference information, information on operational procedure discrepancies, parameter setting deviations, version compatibility discrepancies, and technical document compliance discrepancies is processed to generate discrepancy type and severity assessment information. Operational procedure discrepancies are classified as "operational process sequence error"; parameter setting deviations are classified as "parameter setting error"; version compatibility discrepancies are classified as "software version incompatibility"; and technical document compliance discrepancies are classified as "non-compliance with operating specifications." While the operational procedure discrepancies are incorrect in sequence, they do not immediately lead to measurement errors; they may only affect operational efficiency and are therefore assessed as mild severity. Parameter settings outside the specified range may lead to inaccurate measurement results, significantly impacting differential pressure monitoring accuracy and are therefore assessed as moderate severity. Software version incompatibility may cause unknown issues and affect instrument stability and is therefore assessed as moderate severity. Non-compliance with operating specifications has a limited impact on the standardization and accuracy of the overall measurement operation and is therefore assessed as mild severity. The resulting discrepancy type is [operational process sequence error, parameter setting error, software version incompatibility, non-compliance with operating specifications], and the discrepancy severity assessment is [mild, moderate, moderate, mild].

[0040] Based on the discrepancy type and severity assessment information, target data within the measuring instrument's operational process information is marked and filtered to generate discrepancy data screening results. Operation records involving channel selection and parameter setting order, pressure measurement range setting data, software version data, and data collection frequency setting data are marked. These discrepancy-related target data are filtered out to form discrepancy data screening results, such as "operation records of first selecting channels and then setting parameters," "data indicating the pressure measurement range is set to 0-12 MPa," "information regarding software version V2.5," and "records indicating that the data collection frequency setting does not follow the technical documentation."

[0041] The discrepancy data screening results are integrated and quantified to generate an operation optimization factor. This factor characterizes the deviation of the measuring instrument's operating procedures from the technical documentation standards and the degree of impact on the accuracy, stability, and efficiency of differential pressure monitoring operations. A quantitative rule is established: for example, a minor impact value of 2 (out of 10) is assigned to an incorrect operating procedure sequence; a moderate impact value of 5 is assigned to an incorrect parameter setting; a moderate impact value of 5 is assigned to an incompatible software version; and a minor impact value of 2 is assigned to a non-compliant operating specification. Assuming the weights are 0.2 for incorrect operating procedure sequence, 0.4 for incorrect parameter setting, 0.3 for incompatible software version, and 0.1 for non-compliant operating specifications, the operation optimization factor is calculated using the weighted average: (2 × 0.2 + 5 × 0.4 + 5 × 0.3 + 2 × 0.1) = 3.9. This operation optimization factor of 3.9 (out of 10) characterizes the deviation of the measuring instrument's operating procedures from the technical documentation standards and the degree of impact on the accuracy, stability, and efficiency of differential pressure monitoring operations. The higher the value, the greater the deviation, and the greater the negative impact on the differential pressure monitoring operation. The operating process needs to be optimized accordingly to improve the measurement effect.

[0042] S105 : Process the real-time measurement information and the version number information corresponding to the real-time measurement information based on the operation optimization factor to generate measurement state classification information and processing priority information of the real-time measurement information.

[0043] In one embodiment, real-time measurement information is extracted and processed to generate channel measurement status information, pressure value information, flow rate value information, and other measurement-related attribute information. At a certain moment, the measuring instrument measures multiple channels. The real-time measurement information shows that the measurement status of channel 1 is "normal measurement", the pressure value is 3.5 MPa, and the flow rate is 20 m³ / h. It also includes other measurement-related attribute information, such as the measurement time is "October 10, 2024, 10:00:00" and the sensor temperature is 30°C. Data extraction and processing of this real-time measurement information yields the following: channel measurement status information: Channel 1: Normal measurement; pressure value information: 3.5 MPa; flow rate information: 20 m³ / h; other measurement-related attribute information: measurement time is "October 10, 2024, 10:00:00" and the sensor temperature is 30°C.

[0044] Based on the version number information corresponding to the real-time measurement information, the channel measurement status information, pressure value information, flow value information, and other measurement-related attribute information are standardized and integrated to generate a standardized measurement information set. Assume that the version number corresponding to the current measuring instrument's real-time measurement information is V1.2. The technical documentation for this version specifies the standard data format and units. Based on this version requirement, the extracted information is standardized and integrated. For example, the pressure value is standardized to kPa (1 MPa = 1000 kPa), which is 3500 kPa; the flow value is standardized to m³ / h without conversion; the measurement time is standardized according to the standard format "YYYY-MM-DDHH:MM:SS"; and the sensor temperature unit does not require conversion. After this standardization and integration process, the standardized measurement information set is generated: {Channel 1: Normal measurement, Pressure value: 3500 kPa, Flow value: 20 m³ / h, Measurement time: 2024-10-10 10:00:00, Sensor temperature: 30°C}.

[0045] Based on the operational optimization factor, the standardized measurement information set is evaluated and filtered for importance. This generates a weighted importance for each piece of information in measurement status classification and processing priority determination. The operational optimization factor, previously derived from comparing the instrument's operating procedures with technical documentation, is 4.0 (out of 10). This indicates that the operating procedures have some deviation, impacting measurement accuracy, stability, and efficiency. Based on this operational optimization factor, the standardized measurement information set is evaluated and filtered for importance. Channel measurement status information, because it directly reflects whether the measurement is operating properly, is crucial for determining the reliability of measurement results. Given the current operational procedure deviation, it is assigned a higher importance weight, assuming a value of 0.4. Pressure information is crucial for assessing the reaction state of the catalyst bed and is assigned an importance weight of 0.3. Flow rate information is also crucial for understanding the reaction process and is assigned an importance weight of 0.2. Among other measurement-related attribute information, measurement time is significant for the timeliness of data analysis and is assigned a weight of 0.05. Sensor temperature, which may have a certain impact on measurement results, is also assigned a weight of 0.05. This generates the importance weight of each information in the measurement status classification and processing priority judgment: {channel measurement status information: 0.4, pressure value information: 0.3, flow value information: 0.2, measurement time: 0.05, sensor temperature: 0.05}.

[0046] The importance weights of each piece of information in measurement status classification and processing priority determination are processed to generate measurement status classification and processing priority information for real-time measurement information. Based on the importance weights of each piece of information, the measurement status is categorized into three categories: "important," "less important," and "general." The sum of the weights of channel measurement status and pressure information is 0.4 + 0.3 = 0.7, which is greater than 0.6, placing it in the "important" category. The weight of flow rate information is 0.2, placing it in the "less important" category. The sum of the weights of measurement time and sensor temperature information is 0.05 + 0.05 = 0.1, placing it in the "general" category. In terms of processing priority, information in the "important" category requires priority processing and attention, as it is the most critical for determining measurement results and analyzing catalyst bed conditions. Information in the "less important" category takes second place, and information in the "general" category is processed as resources permit. The resulting processing priority information is: channel measurement status and pressure information are processed first, followed by flow rate information, and finally measurement time and sensor temperature information.

[0047] S106 , inputting the measurement specification indicators, the measurement status classification information and the processing priority information of the real-time measurement information, and the equipment abnormality processing parameter information into the target adaptive pressure difference monitoring model for processing to generate pressure difference monitoring optimization result information.

[0048] In one embodiment, a sample set of historical measurement data of the measuring instrument and a preset adaptive pressure difference monitoring model are obtained. The chemical company has accumulated a large amount of historical measurement data of the measuring instrument in the past year. This data covers information such as pressure difference, pressure, and flow rate of the catalyst bed under different operating conditions, constituting the sample set of historical measurement data of the measuring instrument. The preset adaptive pressure difference monitoring model uses a multi-layer perceptron (MLP) neural network model. The model has an input layer, two hidden layers, and an output layer. The number of input layer nodes is determined according to the number of input data features. Assuming that the input data contains 10 features such as pressure value, flow value, measurement time, and catalyst bed temperature, the number of input layer nodes is 10; the first hidden layer is set with 30 nodes, and the second hidden layer is set with 20 nodes to learn the complex relationships in the data; the number of output layer nodes is 1, which is used to output the pressure difference monitoring effect evaluation value. The activation function of the model selects the ReLU function to increase the nonlinear expression ability of the model. The optimizer selects the Adam optimizer, and the learning rate is set to 0.001.

[0049] The number of each type of data feature in the historical measurement data sample set of the measuring instrument is counted, and the sampling ratio is generated based on the balance of feature distribution. For example, the pressure value feature has 1000 different values, the flow value feature has 800 different values, and the measurement time feature has 365 different dates. The sampling ratio is generated based on the balance of these feature distributions. Assuming that the pressure value has a significant impact on the pressure difference monitoring effect during the entire measurement process, but its number in the sample set is relatively small, in order to ensure that the model can fully learn the information of the pressure value feature and improve its sampling ratio, after calculation and adjustment, the final sampling ratio of the pressure value is determined to be 0.3, the sampling ratio of the flow value is 0.25, and the sampling ratio of the measurement time is 0.15. The corresponding sampling ratios of other features are also determined according to their importance and distribution. The sum of all feature sampling ratios is 1.

[0050] Based on the sampling ratio, a multimodal stratified sampling process is performed on the historical measurement data sample set of the measuring instrument to generate a preset number of sampling feature combinations. The data is divided according to different characteristic modes such as pressure value, flow value, and measurement time. Data is selected from each mode according to the corresponding sampling ratio to generate a preset number of sampling feature combinations (assuming 100). For example, in one sampling, specific pressure value data is selected from the pressure value mode at a sampling ratio of 0.3, and corresponding data is selected from the flow value mode, etc., to form a sampling feature combination that contains the key characteristics of each mode. Each sampling feature combination represents a specific measurement condition.

[0051] Based on statistical tests performed on any key feature combined with each sampling feature, the data is divided into a group with good differential pressure monitoring performance and a group with poor differential pressure monitoring performance. Each group contains a preset number of data samples, and at least one sample contains fault diagnosis information. "Pressure value" is selected as the key feature, and each sampling feature combination is statistically tested against this key feature. The data is divided into a group with good differential pressure monitoring performance and a group with poor differential pressure monitoring performance by using statistical methods such as calculating the degree of difference between the pressure value in each sampling feature combination and the normal pressure range. Each group is set to contain 50 data samples, and at least one sample in each group contains fault diagnosis information, such as a record indicating "abnormal pressure value due to pressure sensor failure." For example, if the pressure value in a sampling feature combination is within the normal range and other relevant features also indicate stable measurement status, it is classified as the group with good differential pressure monitoring performance. If the pressure value exceeds the normal range and is accompanied by flow anomalies, it is classified as the group with poor differential pressure monitoring performance.

[0052] The pre-set adaptive differential pressure monitoring model was iteratively trained based on the good and poor differential pressure monitoring performance groups, generating a trained adaptive differential pressure monitoring model and performance metrics. The pre-set multi-layer perceptron (MLP) model was iteratively trained using data from the good and poor differential pressure monitoring performance groups. During the training process, a cross-validation method was used to divide the training data into five subsets (i.e., 5-fold cross-validation), with four subsets selected each time as the training set and one subset as the validation set. The model's weights and biases were continuously adjusted using a backpropagation algorithm to minimize the model's loss function (e.g., mean squared error loss) on the training set. Simultaneously, the model's performance, such as accuracy and recall, was evaluated on the validation set to avoid overfitting. After multiple iterative training cycles, the model gradually learned the relationship between data characteristics and differential pressure monitoring performance under different operating conditions, ultimately generating a trained adaptive differential pressure monitoring model and performance metrics. For example, the trained model achieved an accuracy of 85% and a recall of 80% on the validation set.

[0053] If the fault diagnosis information in the training results is identified by the model as a key feature that affects the evaluation of the pressure differential monitoring effect, the trained model will be used as the target adaptive pressure differential monitoring model. If the fault diagnosis information in the training results (such as pressure sensor failure, flow anomaly, etc.) is identified by the model as a key feature that affects the evaluation of the pressure differential monitoring effect, it means that the model can effectively capture the impact of fault-related data features on the monitoring effect and has good fault monitoring and evaluation capabilities. At this time, the trained multi-layer perceptron (MLP) model is determined as the target adaptive pressure differential monitoring model. This model can be used for subsequent actual pressure differential monitoring work, and outputs accurate pressure differential monitoring optimization result information based on the input measurement specification indicators, measurement status classification information and processing priority information of real-time measurement information, and equipment abnormality processing parameter information. For example, when real-time measurement information at a certain moment is input, including channel measurement status, pressure value, flow value, etc., as well as measurement specification indicators and possible abnormal handling parameters of the equipment, the target model can quickly and accurately evaluate the effect of the current pressure difference monitoring, determine whether there are potential risks, and give corresponding optimization suggestions based on the evaluation results, such as adjusting measurement parameters, maintaining equipment, etc., thereby improving the reliability and accuracy of the entire catalyst bed pressure difference monitoring system and ensuring the stable operation of the chemical production process.

[0054] In another embodiment, based on the target adaptive pressure difference monitoring model, the measurement specification indicators, the measurement status classification information of the real-time measurement information, the processing priority information and the equipment abnormality processing parameter information are processed to generate a pressure difference monitoring effect correlation evaluation value. At a certain moment, the measurement specification indicators stipulate that the pressure measurement range is 0-10MPa, the accuracy is ±0.01MPa, and the flow measurement range is 0-50m3 / h. The real-time measurement information shows that the measurement status of channel 1 is normal, the pressure value is 3MPa, and the flow value is 20m3 / h. This information is classified as "important" and has a higher processing priority; the equipment abnormality processing parameter information indicates that the current device has a flow sensor signal abnormality problem, and the equipment abnormality processing parameter information quantization value is 6 (the full score is 10, and the higher the value, the more serious the abnormality).

[0055] This information is input into the target adaptive differential pressure monitoring model. Based on the internal algorithm and previously learned rules, the model comprehensively considers the measurement specification indicators, the classification and priority of real-time measurement information, and the abnormal conditions of the equipment. For example, the model will compare the degree of compliance of the real-time pressure value and flow value with the specification indicators, combined with the measurement status classification and processing priority, and the severity of the equipment abnormality. If the measured value is closer to the specification range, the more important the measurement status classification and the higher the processing priority, and the lower the degree of equipment abnormality, the higher the evaluation value. Assume that after calculation, the generated differential pressure monitoring effect correlation evaluation value is 70 (out of 100). This evaluation value reflects the effectiveness of the current differential pressure monitoring after comprehensive consideration of various factors. The higher the value, the more conducive the current measurement and equipment status are to accurate monitoring of the differential pressure.

[0056] Based on the pressure differential monitoring effect correlation evaluation value generated above, the pressure differential monitoring strategy decision vector within the target adaptive pressure differential monitoring model is optimized and adjusted to generate a pressure differential monitoring resource allocation deviation vector. Based on the pressure differential monitoring effect correlation evaluation value 70 generated above, the target adaptive pressure differential monitoring model will optimize and adjust the internal pressure differential monitoring strategy decision vector. Assume that the pressure differential monitoring strategy decision vector contains decision information on measurement frequency adjustment, equipment resource allocation (such as sensor calibration resources, data processing resources, etc.). The original decision vector sets the measurement frequency to once per minute, allocates 30% of the data processing resources for pressure data analysis, 20% for flow data analysis, and 50% for overall system coordination. Since the current evaluation value does not reach the ideal high score (assuming the ideal value is 90), the model analysis finds that the pressure value is close to the upper limit of the measurement range and there is an abnormality in the flow sensor of the equipment. In order to improve the monitoring effect, the model adjusts the decision vector. Increasing the measurement frequency to every 30 seconds increases pressure data analysis resources to 40%, flow data analysis resources to 30%, and overall system coordination resources to 30%. This generates a pressure differential monitoring resource allocation deviation vector, represented by [measurement frequency adjustment: from once per minute to every 30 seconds, pressure data analysis resource adjustment: from 30% to 40%, flow data analysis resource adjustment: from 20% to 30%, overall system coordination resource adjustment: from 50% to 30%]. This deviation vector demonstrates the direction and extent of adjustments to the original filling strategy to improve monitoring effectiveness.

[0057] The differential pressure monitoring resource allocation deviation vector is parsed and converted to generate differential pressure monitoring optimization result information. The differential pressure monitoring resource allocation deviation vector is parsed and converted. Adjusting the measurement frequency means the equipment needs to collect data more frequently, which may require increased data transmission bandwidth and storage resources. The increase in pressure and flow data analysis resources may require allocating more computing resources to data processing, such as using more powerful processor cores or increasing memory usage. A reduction in overall system coordination resources may impact the operation of other parts of the system, but this adjustment is necessary to prioritize the analysis of critical measurement data. After parsing and conversion, the differential pressure monitoring optimization result information is generated. For example, the optimization result information may include specific equipment operation instructions, such as "Adjust the data collection frequency to every 30 seconds, allocate additional computing resources to the pressure and flow data analysis modules, and prioritize data processing tasks for these two modules; at the same time, reduce resources allocated to other less important system functions to meet the current needs of critical measurement data processing." This information can directly guide operators in adjusting the measurement equipment and system, improving the accuracy and reliability of differential pressure monitoring and ensuring the efficient and stable operation of catalyst bed differential pressure monitoring in chemical production processes.

[0058] This application obtains multi-source information such as measuring instrument system initialization, channel selection, and parameter settings from the server. The above information is processed based on the technical document reference information to generate measurement specification parameter information to evaluate the impact of each operation link on the accuracy of pressure difference monitoring. At the same time, maintenance specification information is processed based on fault diagnosis information to obtain equipment abnormality processing parameter information, which is used to characterize abnormal conditions related to equipment failures. Then, the measuring instrument operation process information is processed in combination with the technical document reference information and version number to generate an operation optimization factor to measure the impact of deviations between the operation process and standard requirements on the monitoring operation. The operation optimization factor is used to process real-time measurement information to achieve measurement status classification and processing priority determination.

[0059] Afterwards, a sample set of historical measurement data from the measuring instrument and a preset model are obtained. After sampling, grouping, and iterative training, a target adaptive differential pressure monitoring model is derived. Measurement specification indicators, the classification and priority of real-time measurement information, and equipment anomaly handling parameters are input into the model to generate an associated evaluation value for the differential pressure monitoring effect. Based on this evaluation value, the model's internal decision vector is optimized to obtain a resource allocation deviation vector. After analytical transformation, the resulting differential pressure monitoring optimization results are generated. This provides a scientific basis and optimization guidance for catalyst bed differential pressure monitoring in actual production, contributing to the efficient and stable operation of chemical production.

[0060] In one embodiment, Figure 2 As shown, the present application also provides an adaptive catalyst bed pressure difference monitoring device based on multi-channel dynamic calibration, comprising:

[0061] An acquisition module 201 is used to acquire measuring instrument system initialization information, channel selection information, parameter setting information, data acquisition information, data export information, fault diagnosis information, maintenance specification information, and technical document reference information;

[0062] The processing module 202 is used to process the measuring instrument system initialization information, channel selection information, parameter setting information, data acquisition information, and data export information based on the technical document reference information to generate measurement specification parameter information; process the maintenance specification information based on the fault diagnosis information to generate equipment abnormality processing parameter information; process the measuring instrument operation process information based on the technical document reference information and the version number information corresponding to the technical document reference information to generate an operation optimization factor; process the real-time measurement information and the version number information corresponding to the real-time measurement information based on the operation optimization factor to generate measurement status classification information and processing priority information of the real-time measurement information, wherein the real-time measurement information is used to characterize measurement-related attribute information such as the measurement status, pressure value, flow value, etc. of each channel; input the measurement specification indicators, the measurement status classification information and processing priority information of the real-time measurement information, and the equipment abnormality processing parameter information into the target adaptive pressure difference monitoring model for processing to generate pressure difference monitoring optimization result information.

[0063] The computer-readable storage medium provided in the above-mentioned embodiments of the present application and the adaptive catalyst bed pressure difference monitoring method based on multi-channel dynamic calibration 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.

[0064] Each embodiment in this application is described in a related manner. The same or similar parts between the embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments. In particular, for evaluating the embodiment of the adaptive catalyst bed pressure difference monitoring method based on multi-channel dynamic calibration, the electronic device, the electronic device, and the readable storage medium, since they are basically similar to the embodiment of the adaptive catalyst bed pressure difference monitoring method based on multi-channel dynamic calibration, the description is relatively simple. For the relevant parts, please refer to the partial description of the embodiment of the adaptive catalyst bed pressure difference monitoring method based on multi-channel dynamic calibration.

Claims

1. An adaptive catalyst bed pressure difference monitoring method based on multi-channel dynamic calibration, characterized in that: include: Obtain measuring instrument system initialization information, channel selection information, parameter setting information, data acquisition information, data export information, fault diagnosis information, maintenance specification information and technical document reference information; Process the measuring instrument system initialization information, channel selection information, parameter setting information, data acquisition information, and data export information based on technical document reference information to generate measurement specification parameter information; Process maintenance specification information based on fault diagnosis information to generate equipment abnormality processing parameter information; Processing the measuring instrument operation process information based on the technical document reference information and the version number information corresponding to the technical document reference information to generate an operation optimization factor; Based on the operation optimization factor, the real-time measurement information and the version number information corresponding to the real-time measurement information are processed to generate measurement status classification information and processing priority information of the real-time measurement information, wherein the real-time measurement information is used to represent measurement-related attribute information such as the measurement status, pressure value, flow value, etc. of each channel; The measurement specification indicators, measurement status classification information of real-time measurement information, processing priority information and equipment abnormality processing parameter information are input into the target adaptive pressure difference monitoring model for processing to generate pressure difference monitoring optimization result information.

2. The method according to claim 1, wherein Based on the technical documentation reference information, the measuring instrument system initialization information, channel selection information, parameter setting information, data acquisition information, and data export information are processed to generate measurement specification parameter information, including: Perform feature extraction on the measuring instrument system initialization information, channel selection information, parameter setting information, data acquisition information, and data export information to generate initialization setting features, channel selection features, parameter setting features, data acquisition mode features, and data export method features; Perform quantitative analysis on the initialization setting features and channel selection features to generate the system basic quantitative factors; Quantitative analysis and processing of parameter setting characteristics, data acquisition mode characteristics, and data export method characteristics are performed to generate measurement operation quantitative factors; Process the system basic quantitative factors and measurement operation quantitative factors based on the technical document reference information to generate measurement specification evaluation information and corresponding weight calculation result information; The measurement specification evaluation information and the corresponding weight calculation result information are processed to generate measurement specification parameter information, wherein the measurement specification parameter information is used to characterize the degree of influence of the standardization of the measuring instrument in system initialization, channel selection, parameter setting, data acquisition, data export and other links on the accuracy of pressure difference monitoring.

3. The method according to claim 1, wherein Process maintenance specification information based on fault diagnosis information to generate equipment exception handling parameter information, including: Extract and classify fault diagnosis information and maintenance specification information to generate fault code information, fault meaning information, fault handling method information, daily inspection item information, quarterly maintenance item information, and annual maintenance item information; Process the fault-related content in the maintenance specification information based on the fault diagnosis information to generate fault type judgment information and fault severity assessment information; Mark and filter target data in maintenance specification information based on fault type judgment information and fault severity assessment information to generate abnormal maintenance data screening results; The abnormal maintenance data screening results are integrated and quantified to generate equipment abnormality processing parameter information, wherein the equipment abnormality processing parameter information is used to characterize the abnormal conditions and severity of the measuring instrument caused by failures during the maintenance process.

4. The method according to claim 1, wherein The measuring instrument operation process information is processed based on the technical document reference information and the version number information corresponding to the technical document reference information to generate an operation optimization factor, including: Extract and classify the measuring instrument operation process information, technical document reference information, and corresponding version number information to generate operation step difference information, parameter setting deviation information, version compatibility difference information, and technical document compliance difference information; Based on the technical document reference information, the operation step difference information, parameter setting deviation information, version compatibility difference information, and technical document compliance difference information are processed to generate difference type judgment information and difference severity assessment information; Mark and filter target data in the measuring instrument operation process information based on the difference type judgment information and the difference severity assessment information to generate a difference data screening result; The difference data screening results are integrated and quantified to generate an operation optimization factor. The operation optimization factor is used to characterize the deviation between the operating process of the measuring instrument and the standard requirements of the technical documentation and the degree of impact on the accuracy, stability and efficiency of the differential pressure monitoring operation.

5. The method according to claim 4, wherein Based on the operation optimization factor, the real-time measurement information and the version number information corresponding to the real-time measurement information are processed to generate measurement status classification information and processing priority information of the real-time measurement information. The real-time measurement information is used to represent measurement-related attribute information such as the measurement status, pressure value, flow value, etc. of each channel, including: Perform data extraction and processing on real-time measurement information to generate channel measurement status information, pressure value information, flow value information, and other measurement-related attribute information; Based on the version number information corresponding to the real-time measurement information, the channel measurement status information, pressure value information, flow value information, and other measurement-related attribute information are standardized and integrated to generate a standardized measurement information set; Based on the operation optimization factor, the importance of the standardized measurement information set is evaluated and screened, and the importance weight of each information in the measurement status classification and processing priority judgment is generated; The importance weight of each information in the measurement status classification and processing priority judgment is processed to generate measurement status classification information and processing priority information of the real-time measurement information.

6. The method according to claim 1, wherein Obtain the target adaptive pressure difference monitoring model, including: Obtaining a sample set of historical measurement data of the measuring instrument and a preset adaptive pressure difference monitoring model; Count the number of various types of data features in the historical measurement data sample set of the measuring instrument, and generate a sampling ratio based on the balance of feature distribution; Performing multimodal stratified sampling processing on the historical measurement data sample set of the measuring instrument 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 group with good pressure differential monitoring effect and a group with poor pressure differential monitoring effect, wherein each group contains a preset number of data samples, and at least one sample contains fault diagnosis information; Iteratively train the preset adaptive pressure difference monitoring model based on the good pressure difference monitoring effect group and the poor pressure difference monitoring effect group to generate the trained adaptive pressure difference monitoring model and performance indicators; If the fault diagnosis information in the training results is identified by the model as a key feature that affects the evaluation of the pressure difference monitoring effect, the trained model will be used as the target adaptive pressure difference monitoring model.

7. The method according to claim 1, wherein The measurement specification indicators, measurement status classification information of real-time measurement information, processing priority information and equipment abnormality processing parameter information are input into the target adaptive pressure difference monitoring model for processing to generate pressure difference monitoring optimization result information, including Based on the target adaptive pressure difference monitoring model, the measurement specification indicators, measurement status classification information and processing priority information of real-time measurement information and equipment abnormality processing parameter information are processed to generate a correlation evaluation value of the pressure difference monitoring effect; Based on the pressure differential monitoring effect correlation evaluation value generated above, the pressure differential monitoring strategy decision vector within the target adaptive pressure differential monitoring model is optimized and adjusted to generate a pressure differential monitoring resource allocation deviation vector; The pressure difference monitoring resource allocation deviation vector is analyzed and converted to generate pressure difference monitoring optimization result information.

8. An adaptive catalyst bed pressure difference monitoring device based on multi-channel dynamic calibration, characterized in that: The device comprises: An acquisition module is used to obtain measuring instrument system initialization information, channel selection information, parameter setting information, data acquisition information, data export information, fault diagnosis information, maintenance specification information, and technical document reference information; The processing module is used to process the measuring instrument system initialization information, channel selection information, parameter setting information, data acquisition information, and data export information based on the technical document reference information to generate measurement specification parameter information; process the maintenance specification information based on the fault diagnosis information to generate equipment abnormality processing parameter information; process the measuring instrument operation process information based on the technical document reference information and the version number information corresponding to the technical document reference information to generate an operation optimization factor; process the real-time measurement information and the version number information corresponding to the real-time measurement information based on the operation optimization factor to generate measurement status classification information and processing priority information of the real-time measurement information, wherein the real-time measurement information is used to characterize measurement-related attribute information such as the measurement status, pressure value, flow value, etc. of each channel; input the measurement specification indicators, the measurement status classification information and processing priority information of the real-time measurement information, and the equipment abnormality processing parameter information into the target adaptive pressure difference monitoring model for processing to generate pressure difference monitoring optimization result information.

9. 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 adaptive catalyst bed pressure difference monitoring method based on multi-channel dynamic calibration according to any one of claims 1 to 7 by executing the executable instructions.

10. 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 method for adaptive catalyst bed pressure difference monitoring based on multi-channel dynamic calibration according to any one of claims 1 to 7 is implemented.

Images