CN-121979059-A - Multistage cooperative intelligent control and equipment operation and maintenance data management platform for chemical production

CN121979059ACN 121979059 ACN121979059 ACN 121979059ACN-121979059-A

Abstract

The invention relates to the technical field of industrial automation control and discloses a multistage cooperative intelligent control and equipment operation and maintenance data management platform for chemical production, which comprises a multi-source data acquisition module, a working condition identification and feature extraction module, an equipment health assessment module, an adaptive control module, a hierarchical optimization control module and a cooperative decision-making module, wherein the multi-source data acquisition module acquires multi-source heterogeneous data and performs time alignment processing and quality verification, the working condition identification and feature extraction module adopts weighted fusion and principal component analysis to obtain equipment operation state data, the equipment health assessment module calculates equipment health score and predicts degradation trend through exponential smoothing, the adaptive control module designs a multivariable coordination controller and dynamically generates operation constraint of the multivariable coordination controller according to the equipment health score, the hierarchical optimization control module establishes an interlayer feedback mechanism, and the cooperative decision-making module generates a cooperative decision-making trigger signal according to equipment health information to generate a cooperative decision-making scheme.

Inventors

GUO ANYONG
YANG HONGFU
WANG YINFENG
ZHANG XINGPENG
ZHU HUANHUAN
CUI SHUQIANG
Lao Yongliang
WANG GUOXIN

Assignees

山东滨农科技有限公司

Dates

Publication Date: 20260505
Application Date: 20260202

Claims (10)

1. Multistage cooperative intelligent control and equipment operation and maintenance data management platform towards chemical production, its characterized in that includes: the multi-source data acquisition module establishes a unified time reference based on the edge computing node, acquires multi-source heterogeneous data, performs time alignment processing and quality verification, and obtains a time-synchronous data stream; The working condition recognition and feature extraction module is used for carrying out working condition recognition by adopting a sliding window based on time-synchronous data flow, extracting equipment features by frequency domain analysis and temperature trend analysis, and obtaining equipment running state data by adopting weighted fusion and principal component analysis; the equipment health evaluation module calculates equipment health degree scores based on the equipment running state data, and the degradation trend is predicted through exponential smoothing to obtain equipment health degree information; the self-adaptive control module is used for designing a multi-variable coordination controller based on the equipment health degree information, dynamically generating the operation constraint of the multi-variable coordination controller according to the equipment health degree score, and obtaining an operation parameter set value; The hierarchical optimization control module is used for respectively executing optimization control, coordination control and PID control based on the set values of the operation parameters, establishing an interlayer feedback mechanism and obtaining a multi-level coordination control instruction; and the collaborative decision module is used for generating a collaborative decision trigger signal according to the equipment health degree information based on the equipment health degree information and the multi-level coordination control instruction and generating a final collaborative decision scheme by adopting a rule matching method.
2. The chemical production-oriented multi-stage collaborative intelligent control and equipment operation and maintenance data management platform according to claim 1, wherein the time alignment process comprises: the method comprises the steps of obtaining multi-source heterogeneous data collected by an edge computing node, establishing a data buffer area for the multi-source heterogeneous data based on a unified time reference, carrying out aggregation processing on all data with the same time stamp in the same time unit, and eliminating time deviation among data sources through the data aggregation processing to obtain a multi-source data set with unified time.
3. The chemical production-oriented multi-level collaborative intelligent control and equipment operation and maintenance data management platform of claim 1, wherein the acquiring multi-source heterogeneous data comprises: And acquiring high-frequency vibration data, process operation parameter data and equipment temperature data of chemical production equipment, wherein the process operation parameter data and the equipment temperature data are classified into corresponding time units directly according to time stamps, calculating statistical characteristic values of the high-frequency vibration data by adopting a sliding window statistical processing method, and aligning the statistical characteristic values with a time reference to form a multi-source data stream with a uniform time format.
4. The chemical production-oriented multi-stage collaborative intelligent control and equipment operation and maintenance data management platform according to claim 1, wherein the condition identification comprises: Acquiring process operation parameter data in the time-synchronous data stream, calculating the difference degree of the process operation parameter data between different working condition types based on the historical operation data, performing measurement calculation on the difference degree by adopting an analysis of variance method, and selecting the parameter with the largest difference degree as a working condition sensitive parameter according to the measurement result of the difference degree for judging the state of the subsequent working condition.
5. The chemical production-oriented multi-stage collaborative intelligent control and equipment operation and maintenance data management platform according to claim 1, wherein the adoption of a sliding window for operating condition identification comprises: Acquiring a real-time value of the working condition sensitive parameter, carrying out time sequence analysis on the working condition sensitive parameter by adopting a sliding window method, calculating a change trend of the working condition sensitive parameter in a window, calculating a slope by adopting a linear regression method to represent the change trend, judging that the working condition is switched when the absolute value of the change trend slope is larger than a preset threshold value, and outputting a working condition state identifier.
6. The chemical production-oriented multi-level collaborative intelligent control and equipment operation and maintenance data management platform according to claim 1, wherein the weighted fusion comprises: and acquiring equipment characteristics extracted by frequency domain analysis and temperature trend analysis, establishing a working condition characteristic weight mapping table based on a working condition recognition result, inquiring corresponding characteristic weight coefficients from the working condition characteristic weight mapping table according to the current working condition type, multiplying each component of the equipment characteristics by the corresponding weight coefficients respectively, and obtaining a weighted comprehensive state characteristic vector through weight fusion processing.
7. The chemical production-oriented multi-level collaborative intelligent control and equipment operation and maintenance data management platform according to claim 1, wherein the generating of the equipment health information comprises: The method comprises the steps of obtaining normal operation data of equipment under different working condition types in a historical operation database, calculating statistical characteristic parameters of a characteristic vector sample set of equipment state under the working condition for each working condition type, taking the statistical characteristic parameters as characteristic baselines of normal states of the equipment under the working condition, and establishing a working condition baseline mapping library to store the characteristic baselines for equipment health degree scoring calculation.
8. The chemical production-oriented multi-stage collaborative intelligent control and equipment operation and maintenance data management platform according to claim 1, wherein the multi-variable coordination controller comprises: Obtaining the equipment health grade obtained by calculating the equipment health grade score, determining an equipment load rate constraint range based on the equipment health grade, setting a wider load rate constraint range when the health grade is higher so as to improve the production efficiency, and setting a tighter load rate constraint range when the health grade is lower so as to protect the equipment safety, thereby obtaining dynamic equipment state constraint parameters.
9. The chemical production-oriented multi-stage collaborative intelligent control and equipment operation and maintenance data management platform according to claim 1, further comprising: And the cloud edge end cooperative data management module is used for carrying out cloud edge end cooperative data management based on a final cooperative decision scheme, and realizing data management and model updating through data acquisition, edge processing, cloud storage, offline model training and model deployment.
10. A computer readable storage medium for storing computer readable instructions which, when read by a computer, are capable of running the chemical production oriented multi-level collaborative intelligent control and equipment operation and maintenance data management platform of any one of claims 1-9.

Description

Multistage cooperative intelligent control and equipment operation and maintenance data management platform for chemical production Technical Field The invention relates to the technical field of industrial automation control, in particular to a multistage cooperative intelligent control and equipment operation and maintenance data management platform for chemical production. Background The chemical production process has high complexity, strong coupling and strict safety and environmental protection requirements, and provides serious challenges for production control and equipment operation and maintenance management. In the core devices such as continuous catalytic cracking of petrochemical enterprises, a complex coupling relation exists among a plurality of operation parameters of a reaction regeneration system, when working conditions change frequently, a plurality of parameter adjustment needs to be coordinated, and the traditional single-loop control is difficult to deal with. Meanwhile, key rotating equipment such as a main fan, a smoke ventilator and the like runs under the working condition of high temperature and high load for a long time, equipment vibration and bearing temperature problems frequently occur, and the unplanned shutdown of any key equipment can lead to the production stoppage of the whole device, so that huge economic loss is caused. At present, chemical enterprises commonly deploy a plurality of sets of informationized systems such as a DCS control system, an equipment vibration monitoring system, a video monitoring system, an equipment management system and the like, but the systems are independently operated to form a serious data island. When the production control system performs optimization control, only process constraint and product quality constraint are considered, and the health state of equipment is not used as an optimization constraint condition, so that the equipment is possibly required to run for a long time under a limit working condition for the optimization control, and equipment degradation is accelerated. When a maintenance planning is made by an equipment maintenance department, the production task arrangement cannot be known, the production continuity can be influenced by the maintenance activity, the production control decision and the equipment maintenance decision are mutually independent, and the decision conflict exists. The existing equipment monitoring system adopts fixed threshold value alarm, and can not adapt to frequent changes of the operation working conditions of chemical equipment. For example, when the main fan runs at full load, the vibration value is larger and belongs to a normal phenomenon, but when the main fan runs at low load, the same vibration value can mean a fault, and the fixed threshold cannot distinguish the difference, so that a large number of false alarms are generated under the high-load working condition, and the true fault can be missed under the low-load working condition. The health condition of the equipment is influenced by various factors such as process operation parameters, vibration monitoring data, temperature data, lubricating oil analysis data, historical maintenance records and the like, and the existing system dispersedly stores the data, lacks deep fusion analysis and is difficult to comprehensively and accurately evaluate the health condition of the equipment. Therefore, a technical scheme for realizing deep integration of a control system and an operation and maintenance system, multi-level cooperative control and equipment health management based on working condition self-adaption is needed to comprehensively improve the intelligent level of chemical production. Disclosure of Invention The invention provides a multistage cooperative intelligent control and equipment operation and maintenance data management platform for chemical production, which solves the technical problems of poor cooperativity between a control system and an operation and maintenance system and inaccurate equipment health assessment in the chemical production in the related technology. The invention provides a multistage cooperative intelligent control and equipment operation and maintenance data management platform oriented to chemical production, which comprises the following steps: the multi-source data acquisition module establishes a unified time reference based on the edge computing node, acquires multi-source heterogeneous data, performs time alignment processing and quality verification, and obtains a time-synchronous data stream; The working condition recognition and feature extraction module is used for carrying out working condition recognition by adopting a sliding window based on time-synchronous data flow, extracting equipment features by frequency domain analysis and temperature trend analysis, and obtaining equipment running state data by adopting weighted fusion and principal component analysis; the equipment health e