CN111984692A - Chemical data analysis system based on industrial big data - Google Patents
Chemical data analysis system based on industrial big data Download PDFInfo
- Publication number
- CN111984692A CN111984692A CN202010127933.2A CN202010127933A CN111984692A CN 111984692 A CN111984692 A CN 111984692A CN 202010127933 A CN202010127933 A CN 202010127933A CN 111984692 A CN111984692 A CN 111984692A
- Authority
- CN
- China
- Prior art keywords
- data
- module
- cloud
- industrial big
- service
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 239000000126 substance Substances 0.000 title claims abstract description 33
- 238000007405 data analysis Methods 0.000 title claims abstract description 31
- 238000012545 processing Methods 0.000 claims abstract description 16
- 238000013500 data storage Methods 0.000 claims abstract description 6
- 238000012544 monitoring process Methods 0.000 claims abstract description 3
- 238000003908 quality control method Methods 0.000 claims abstract description 3
- 238000000034 method Methods 0.000 claims description 62
- 238000004519 manufacturing process Methods 0.000 claims description 44
- QGZKDVFQNNGYKY-UHFFFAOYSA-N Ammonia Chemical compound N QGZKDVFQNNGYKY-UHFFFAOYSA-N 0.000 claims description 43
- 230000008569 process Effects 0.000 claims description 41
- 238000004422 calculation algorithm Methods 0.000 claims description 30
- 238000001035 drying Methods 0.000 claims description 19
- 239000000428 dust Substances 0.000 claims description 18
- 238000004458 analytical method Methods 0.000 claims description 17
- 238000005457 optimization Methods 0.000 claims description 17
- 238000005469 granulation Methods 0.000 claims description 14
- 230000003179 granulation Effects 0.000 claims description 14
- 238000005406 washing Methods 0.000 claims description 13
- 229910021529 ammonia Inorganic materials 0.000 claims description 12
- 238000006243 chemical reaction Methods 0.000 claims description 12
- 238000010586 diagram Methods 0.000 claims description 12
- 238000001816 cooling Methods 0.000 claims description 11
- 238000012824 chemical production Methods 0.000 claims description 8
- 238000004140 cleaning Methods 0.000 claims description 8
- 238000012216 screening Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000003066 decision tree Methods 0.000 claims description 4
- 238000002474 experimental method Methods 0.000 claims description 4
- 238000012795 verification Methods 0.000 claims description 4
- 238000010219 correlation analysis Methods 0.000 claims description 3
- 238000009826 distribution Methods 0.000 claims description 3
- 230000008676 import Effects 0.000 claims description 3
- 239000003337 fertilizer Substances 0.000 description 31
- 150000001875 compounds Chemical class 0.000 description 26
- 239000000463 material Substances 0.000 description 25
- QAOWNCQODCNURD-UHFFFAOYSA-N Sulfuric acid Chemical compound OS(O)(=O)=O QAOWNCQODCNURD-UHFFFAOYSA-N 0.000 description 18
- NBIIXXVUZAFLBC-UHFFFAOYSA-N Phosphoric acid Chemical compound OP(O)(O)=O NBIIXXVUZAFLBC-UHFFFAOYSA-N 0.000 description 16
- 239000008186 active pharmaceutical agent Substances 0.000 description 15
- 239000000047 product Substances 0.000 description 15
- 210000004556 brain Anatomy 0.000 description 12
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 12
- 239000007789 gas Substances 0.000 description 10
- 229910000147 aluminium phosphate Inorganic materials 0.000 description 8
- 235000015097 nutrients Nutrition 0.000 description 8
- 230000000694 effects Effects 0.000 description 7
- 238000011049 filling Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 7
- 239000002253 acid Substances 0.000 description 6
- 239000007788 liquid Substances 0.000 description 6
- 239000003345 natural gas Substances 0.000 description 6
- 238000007781 pre-processing Methods 0.000 description 6
- 239000002994 raw material Substances 0.000 description 6
- 229910052921 ammonium sulfate Inorganic materials 0.000 description 5
- 230000008859 change Effects 0.000 description 5
- 238000013506 data mapping Methods 0.000 description 5
- 238000007726 management method Methods 0.000 description 5
- 239000002245 particle Substances 0.000 description 5
- 238000007637 random forest analysis Methods 0.000 description 5
- BFNBIHQBYMNNAN-UHFFFAOYSA-N ammonium sulfate Chemical compound N.N.OS(O)(=O)=O BFNBIHQBYMNNAN-UHFFFAOYSA-N 0.000 description 4
- 235000011130 ammonium sulphate Nutrition 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 239000013072 incoming material Substances 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 239000002699 waste material Substances 0.000 description 3
- NLXLAEXVIDQMFP-UHFFFAOYSA-N Ammonia chloride Chemical compound [NH4+].[Cl-] NLXLAEXVIDQMFP-UHFFFAOYSA-N 0.000 description 2
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 description 2
- WCUXLLCKKVVCTQ-UHFFFAOYSA-M Potassium chloride Chemical compound [Cl-].[K+] WCUXLLCKKVVCTQ-UHFFFAOYSA-M 0.000 description 2
- 238000011001 backwashing Methods 0.000 description 2
- 238000007599 discharging Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000000513 principal component analysis Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000010187 selection method Methods 0.000 description 2
- 239000002002 slurry Substances 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 238000005303 weighing Methods 0.000 description 2
- XSQUKJJJFZCRTK-UHFFFAOYSA-N Urea Chemical compound NC(N)=O XSQUKJJJFZCRTK-UHFFFAOYSA-N 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 235000019270 ammonium chloride Nutrition 0.000 description 1
- LFVGISIMTYGQHF-UHFFFAOYSA-N ammonium dihydrogen phosphate Chemical compound [NH4+].OP(O)([O-])=O LFVGISIMTYGQHF-UHFFFAOYSA-N 0.000 description 1
- 229910000387 ammonium dihydrogen phosphate Inorganic materials 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- PASHVRUKOFIRIK-UHFFFAOYSA-L calcium sulfate dihydrate Chemical compound O.O.[Ca+2].[O-]S([O-])(=O)=O PASHVRUKOFIRIK-UHFFFAOYSA-L 0.000 description 1
- 239000004202 carbamide Substances 0.000 description 1
- 235000013877 carbamide Nutrition 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000003344 environmental pollutant Substances 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 239000012467 final product Substances 0.000 description 1
- 239000008187 granular material Substances 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 235000019837 monoammonium phosphate Nutrition 0.000 description 1
- 239000006012 monoammonium phosphate Substances 0.000 description 1
- 238000006386 neutralization reaction Methods 0.000 description 1
- 229910052757 nitrogen Inorganic materials 0.000 description 1
- 235000021049 nutrient content Nutrition 0.000 description 1
- 238000005453 pelletization Methods 0.000 description 1
- 231100000719 pollutant Toxicity 0.000 description 1
- 239000001103 potassium chloride Substances 0.000 description 1
- 235000011164 potassium chloride Nutrition 0.000 description 1
- OTYBMLCTZGSZBG-UHFFFAOYSA-L potassium sulfate Chemical compound [K+].[K+].[O-]S([O-])(=O)=O OTYBMLCTZGSZBG-UHFFFAOYSA-L 0.000 description 1
- 229910052939 potassium sulfate Inorganic materials 0.000 description 1
- 235000011151 potassium sulphates Nutrition 0.000 description 1
- 239000000843 powder Substances 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000004886 process control Methods 0.000 description 1
- 230000006798 recombination Effects 0.000 description 1
- 238000005215 recombination Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2462—Approximate or statistical queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2455—Query execution
- G06F16/24568—Data stream processing; Continuous queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2474—Sequence data queries, e.g. querying versioned data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/248—Presentation of query results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/067—Enterprise or organisation modelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- Quality & Reliability (AREA)
- Computational Linguistics (AREA)
- Game Theory and Decision Science (AREA)
- Probability & Statistics with Applications (AREA)
- Operations Research (AREA)
- Educational Administration (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Manufacturing & Machinery (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a chemical data analysis system based on industrial big data, which comprises a cloud service platform for receiving and storing industrial big data information; the system comprises a data acquisition unit arranged in a chemical plant area, wherein the data acquisition unit is provided with a data statistics module; the industrial big data processing unit comprises a monitoring and early warning module, a product quality control module, a data analysis module, a modeling module and a report module; the cloud service platform is linked with an industrial big data processing unit and comprises a resource unit on the cloud and a local resource unit, the local resource unit transmits data of a chemical industry (factory area) intranet to a data acquisition extranet interface server of the resource unit on the cloud, and the resource unit on the cloud comprises a data service API gateway module, a data bus DataHub module and a big data storage computing service MaxCommute module.
Description
Technical Field
The invention relates to application of an industrial brain, in particular to a chemical data analysis system based on industrial big data.
Background
The purpose of the industrial brain is to connect artificial intelligence and big data technology into the traditional production line, help the production enterprises to realize the cooperation of data flow, production flow and control flow, improve the production efficiency, reduce the production cost and realize the autonomous controllable intelligent manufacturing by an autonomous controllable path. The ET industry brain (i.e., the aricloud ET industry brain) enables the machine to sense, communicate and self-diagnose problems, and optimizes the output of the machine and reduces waste costs by analyzing data collected in industrial production. Through inexpensive sensors, intelligent algorithms and powerful computing power, the deployment principle of the ET industry brain can be divided into the following four steps:
1. data acquisition: multi-party industrial enterprise data such as enterprise system data, factory equipment data, sensor data, personnel management data and the like are collected.
2. Data preprocessing: the method comprises the steps of filtering dirty data and noise, solving the multi-source heterogeneity of the data, retrieving lost data, correcting wrong data and the like. Meanwhile, data are segmented, decomposed and classified according to purposes, and preparation is made for next algorithm modeling.
3. Modeling an algorithm: and rapidly modeling the collected and preprocessed historical data through an algorithm engine built in the ET industrial brain AI authoring room or an algorithm provided by an algorithm market, wherein the model can be a description model, a prediction model or an optimization model.
4. Application of the model: and releasing the established algorithm model into a service, integrating the service into a production system, and acting the service to complete the closed loop of the intelligent data application.
In order to realize continuous cloud-up of incremental real-time data of a chemical intelligent manufacturing big data project and meet the requirements of possible real-time data display, real-time data calculation, partial data copying and shunting and the like, a set of high-performance chemical data analysis system with cloud-up data needs to be constructed. Namely, according to the information planning and the service planning of the chemical enterprise system, a chemical industry foundation and environment big data platform for optimizing production, management and service is built by combining big data. If the method is positioned in a chemical enterprise system, an industrial foundation and environment big data platform for the production, management and service of the existing compound fertilizer is established to optimize the nutrient content of the compound fertilizer, reduce the emission of dust and ammonia gas, enhance the data insight capability and promote the data driving decision through connecting people and equipment, construct the rapid business response capability and comprehensively accelerate the digital transformation of the chemical enterprise. Two values can be brought mainly through digital transformation, 1) the production process of the compound fertilizer is optimized, so that indexes such as nutrients meet the industrial standard, and meanwhile, the uncertainty is reduced, and the purpose of reducing the material cost is achieved; 2) by optimizing the process parameters, the influence of measures such as emission reduction and the like on production is reduced, and the utilization rate of raw materials is improved. The specific aim is to optimize parameters of the compound fertilizer production process, and provide optimization suggestions of process parameters and material quantity in each link by analyzing and modeling historical data. Regarding a compound fertilizer production line, the main goal of environmental protection optimization is to reduce the emission of dust and ammonia gas, thereby achieving the dual purposes of reducing emission and reducing material cost.
Disclosure of Invention
The invention aims to provide a chemical industry data analysis system based on industrial big data, and a chemical industry foundation and environment for optimizing production, management and service.
In order to achieve the above purpose, the invention adopts the technical scheme that: a chemical industry data analysis system based on industrial big data comprises a cloud service platform for receiving and storing industrial big data information; the system comprises a data acquisition unit arranged in a chemical plant area, wherein the data acquisition unit is provided with a data statistics module; the industrial big data processing unit comprises a monitoring and early warning module, a product quality control module, a data analysis module, a modeling module and a report module;
the cloud service platform is linked with an industrial big data processing unit and comprises a resource unit on the cloud and a local resource unit, the local resource unit transmits data of a chemical industry (factory area) intranet to a data acquisition extranet interface server of the resource unit on the cloud, and the resource unit on the cloud comprises a data service API gateway module, a data bus DataHub module and a big data storage computing service MaxCommute module;
the data acquisition unit acquires service system data, wherein the service system data comprises DCS data in a chemical production process and chemical production class plan production report data; the DCS data comprises parameters corresponding to each process in chemical production, and comprises flow data, pressure data, temperature data, air volume data, current data and optimization target data, the optimization target data comprises finished product content, tail gas dust content and tail gas ammonia content data, the DCS data is exported and then is used for screening the basic conditions of the obtained data, data which do not belong to the corresponding parameter range in the chemical production process are removed, and the screened data are transmitted to the data statistics module;
the data of the data statistics module is transmitted to a data analysis module of the industrial big data processing unit, the data analysis module carries out statistics on the distribution condition of each data by drawing a time sequence curve of each item of data on the data of the data statistics module, and the data is subjected to modeling by the modeling module through data scatter diagram analysis or linear correlation analysis; the modeling module comprises a data cleaning submodule and a data association submodule, and the data cleaning submodule cleans unreasonable data and fills missing values; and the industrial big data processing unit carries out algorithm modeling after data modeling by using a modeling module.
Furthermore, the data service API gateway module provides cloud data receiving service, and the local data acquisition service calls the interface API in real time to complete real-time DCS data synchronization; the data bus DataHub module continuously collects, stores and processes a large amount of streaming data generated by various mobile devices, application software, website services and sensors, a user writes an application program or processes the streaming data written into the DataHub by using a streaming calculation engine, and various real-time data processing results are generated; the big data storage computing service MaxCommute module perfects a data import scheme and a plurality of classical distributed computing models.
Further, the step of screening the acquired data for the basic situation after the DCS data is exported is as follows: acquiring DCS historical data of multiple periods of time, exporting the data into a csv format through industrial software for analysis aiming at the DCS data, and screening the acquired data for basic conditions.
Furthermore, the local resource unit is connected with a local real-time data acquisition service, and the data acquisition service calls a cloud data service API restful interface to enable the business data to be in real-time cloud.
Still further, the DCS system data received in the data service API gateway module is pushed to the Datahub through the Datahub sdk.
Furthermore, the modeling module firstly utilizes historical data to model a recommendation algorithm module; and finally, carrying out field verification and iteration of the recommendation algorithm.
Further, the model modeled by the recommendation algorithm module is a time sequence prediction model or an optimal model.
Still further, the basic steps of the recommendation algorithm for field verification are:
1) selecting a reasonable and controllable process optimization scheme by combining decision tree optimization results according to experience to form an optimization rule for implementation;
2) selecting a node of a poor sample according to experience, identifying process parameters of a poor product, and forming an evasion rule for implementation;
3) selecting one production line to carry out a one-week experiment;
4) and selecting an AB method alternate experiment, mutually verifying, and selecting comprehensive optimal.
Further, the DCS data comprises data of a tubular reaction system, a washing system, a granulating system, a drying system, a cooling system, finished product quantity and tail gas.
The invention has the technical effects that: optimizing the chemical industry foundation and environment of production, management and service. The specific application is as follows: 1) the production process of the compound fertilizer is optimized, so that the indexes such as nutrients meet the industrial standard, and meanwhile, the uncertainty is reduced, thereby achieving the purpose of reducing the material cost; 2) by optimizing the process parameters, the influence of measures such as emission reduction and the like on production is reduced, and the utilization rate of raw materials is improved.
Drawings
FIG. 1 is a schematic diagram of the present invention;
FIG. 2 is a diagram of a data link architecture, i.e., a real-time cloud-based data architecture, according to the present invention;
FIG. 3 is a data link flow diagram of the present invention;
fig. 4-11 are drawings of the specific implementation of the invention in the field of chemical compound fertilizers, wherein:
FIG. 4 shows a conventional process for producing a compound fertilizer;
FIG. 5 is a material balance diagram of a compound fertilizer production process;
FIG. 6 is a graph showing the correlation between parameters in the time period of 3 days to 13 days in 10 months in 2018 in the embodiment;
FIG. 7 is a graph showing the correlation between the parameters in the 20 th day period from 11/month 28/12/month in 2018 in the embodiment;
FIG. 8 is a parameter chart of the correlation of reference time period data and dust;
FIG. 9 is a graph of maximum information coefficient analysis (MIC) tail gas dust content;
FIG. 10 is a plot of principal component analysis variance contribution ratio;
FIG. 11 is a flow chart of the AB process;
FIG. 12 is a predictive model to which the present invention is applied;
FIG. 13 is an optimization model to which the present invention is applied.
Detailed Description
Referring to the attached drawings, the method is based on big data analysis, and mainly achieves four functions of data cloud application, data cleaning, data mining and data display. The invention seamlessly interfaces StreamCompute to realize real-time data transmission and calculation and push the calculation result to the machine learning platform in real time. The real-time data cloud link mainly aims at high real-time data such as PLC/OPC, and service system data [ DCS (System) data, phosphoric acid workshop inspection data and phosphogypsum inspection data ] can be acquired from the cloud link. The cloud service platform 10 for receiving and storing industrial big data information comprises an on-cloud resource unit 11 and a local resource unit 12. The cloud resource unit 11 provides the required cloud resources through the cloud service platform 10 (if the corresponding resources are opened in a public cloud account number of a chemical project by using the airy cloud), mainly includes storage cloud resources such as data buses DataHub and MaxCompute, and the data service API gateway provides support for a commercial brain data factory. The local resource unit 12 only needs to deploy a set of http/https supporting services to cloud data on the local side of the chemical industry enterprise, specifically, the service is connected with a local real-time data acquisition service, and the data acquisition service realizes real-time cloud-going of business data by calling a cloud data service API restful interface.
The resource unit 11 on the cloud includes:
data service API gateway module: the data service API gateway provides high-availability and high-concurrency cloud data receiving service, and the local data acquisition service calls the interface API in real time to complete real-time DCS data synchronization cloud. Data bus DataHub module: the data bus DataHub continuously collects, stores and processes a large amount of streaming data generated by various mobile devices, application software, website services, sensors and the like. A user may write an application or use a stream computation engine to process streaming data written to the DataHub, such as a real-time web access log, an application log, various events, etc., and produce various real-time data processing results, such as real-time charts, alarm information, real-time statistics, etc. Preferably, the DCS data (pushed by the data acquisition service) received in the data service API gateway is pushed to the Datahub through the Datahub sdk, so that the time delay of cloud arrival of the data can be reduced while the pressure of the transfer database is reduced.
Big data storage computing service MaxCommute module: the big data computing service (MaxCommute, original name ODPS) is a GB/TB/PB level data warehouse which is managed rapidly and completely, namely the MaxCommute provides a perfect data import scheme and various classical distributed computing models, the problem of mass data computing can be solved more rapidly, the enterprise cost is effectively reduced, and the data security is guaranteed.
The following description is implemented by combining compound fertilizer chemical enterprises:
referring to NPK content analysis, a brief flow chart thereof: 1. the assay center gives the detection value of the raw material; 2. the control room can be operated to determine the N content, the P content and the K content of the fertilizer. The method can reduce dust and nitrogen emission through data specific recommendation, namely a control room can control the N content, the P content and the K content of a batch of fertilizers. Specifically, the system of the invention uses big data to calculate, calculates the product for producing the target nutrient according to the current raw material detection report, the product detection report of a few hours before and the data of each point of the factory, and modifies the value according to the control requirement, thus producing the fertilizer meeting the requirement. Based on the method, the data of all compound fertilizer plants are collected by the big data, and finally, the corresponding data are determined, so that the stability of the product quality is realized. For example, if the total nutrient is 51 fertilizers, namely the sum of the NPK content is 51%, the cost is wasted if the sum is more than 51%, and the cost is unqualified if the sum is less than 51%, the fertilizers must be qualified firstly, namely the total nutrient is at least 51%, the existing method is operated manually by experience, namely manual feeding of compound fertilizer factories is performed according to experience, so that the standards for producing the compound fertilizers in the plants are different, the quality of the compound fertilizers in the plants is different directly, namely the quality of all the compound fertilizers in the whole compound fertilizer industry is very unstable, the total nutrient can reach 52% or 53%, and the cost is wasted if the products are uncontrollable and the compound fertilizer factories in the whole industry are used. The system directly transmits the control room to mass production, saves cost, and is accurate and stable compared with the prior direct manual operation.
The application embodiment of the system in the production process of the compound fertilizer comprises the following steps:
referring to fig. 4, the existing compound fertilizer production process, in particular to a process flow of an S-ammonium sulfate device with a three-waste discharge point: the production process of the chemical compound fertilizer relates to the following main procedures, 1) tubular reaction mainly comprises a reaction container of sulfuric acid, phosphoric acid and liquid ammonia, wherein the sulfuric acid and the liquid ammonia react to generate ammonium sulfate, the amount of the ammonia entering is that the acid is completely neutralized to generate the ammonium sulfate and generate heat, and the generated heat can improve the production temperature of the subsequent environment to achieve the effect of energy conservation, so that the cost is reduced from the dimension of energy consumption; 2) a granulation system: the method comprises the following steps that ammonia acid is generated through reaction of a tubular reactor, high-temperature low-humidity slurry is sprayed onto a granulating material bed layer of a granulating system through a nozzle, various nutrient materials and returned materials are added through a bucket elevator belt system, liquid ammonia and steam engine air are added into the granulating system at the same time, the granulating temperature is controlled, the dry and wet materials are agglomerated into granules under the rotation of a rotary drum granulator, and escaped ammonia gas in the granulating system is treated through a washing system; 3) a drying system: conveying the materials at the outlet of the granulator to a drying system, heating the air by natural gas in the drying system, and then conveying the hot air into a drying furnace for drying by an air blower, wherein more dust is generated in the process, and the generated dust is pumped to a washing system; 4) a cooling system: and the material passing through the drying system enters a cooling system for cooling, the cooled material is screened by a vibrating screen to obtain particles with the particle size meeting the standard, the nutrient measurement is carried out, unqualified products with the particle size being too large or too small are conveyed to a granulation system by a bucket lifting belt to participate in granulation reaction again, and the products with the large particle size are shaken and crushed by the vibrating screen.
Referring to fig. 5, it is a key parameter diagram of the above process flow, i.e. a material balance diagram. The figure is provided to illustrate that the granulation and drying processes in the production of the compound fertilizer directly influence the generation ratio of particles, further influence the emission of dust and ammonia gas, and whether the ammonia-acid reaction fully and directly influences the utilization rate of liquid ammonia, thereby influencing the emission of ammonia gas.
The processing process of the system of the invention comprises the following steps:
the data sources are collected by the data collection unit 20:
from the system point of view, it is necessary to reflect all the processes of production, i.e. the incoming material condition, the production process data and the production result data, as much as possible from the data. The data source acquisition situation is as follows:
| production process | Product class planning |
| DCS data | Production report |
The following is some basic information of data, namely, the main parameters of the chemical compound fertilizer production process are as follows:
the table lists the main parameters in the production process of the compound fertilizer, and each process of the production process has corresponding parameter influence and is mainly divided into the following categories: 1) the flow data mainly comprises acid, ammonia and washing liquid, such as phosphoric acid amount, sulfuric acid amount, liquid ammonia amount and washing liquid, wherein the liquid ammonia is directly accessed from brother units, so the flow is basically stable, the change is small, and the natural gas amount influences the effect of the drying system; 2) pressure type data, such as dryer inlet pressure; 3) temperature data, which mainly comprises the inlet temperature, the tail gas temperature and the outlet material temperature of the drying system; 4) the air volume data, the drying system and the cooling system can influence the emission of tail gas; 5) current data: the method mainly comprises the steps that the current of materials of a bucket elevator is directly related to the current of a belt scale, and the current is directly related to the quantity of the materials; 6) optimizing the target class, mainly comprising the finished product content, the dust content of tail gas and the ammonia content of tail gas. The parameters can be divided into process parameters and raw material quantity parameters, and the raw materials mainly comprise sulfuric acid, phosphoric acid, liquid ammonia, different materials, return materials and washing liquid; and the process control parameters mainly include control of temperature, air volume and the like.
Acquiring historical data of DCS (data communication system collected data) in multiple periods of time, exporting the data into a csv format through industrial software for analysis aiming at the DCS data, and screening the acquired data for basic conditions. If the current of the dryer is used as an index to judge whether the production is normal, the normal range of the data is seen from the analysis curve through analysis, and the data is given as the index. Actually, the data of DCS is derived at 5-minute intervals at present, most parameters are collected in real time in the actual production process, the 5-minute intervals are selected, the total data of one day is recorded into 288 pieces, the high-frequency change rule of the temperature and pressure parameters can be observed, and the characteristics of daily change can also be found.
Then, the data statistics module 21 on the data acquisition unit 20 performs data statistics:
the following is a data statistics table from 10 months, 3 days to 13 days in 2018:
the data are shown in the table from 10 months to 3 days to 13 days in 2018, partial current and frequency modulation data are not available, and the natural gas flow data are not available. The total number of records is 2808 data (with unreliable data before and after deduction), and the time span is from 10 months 3 to 10 months 13 days in 2018.
Similarly, 4478 data (with unreliable data before and after deduction) are recorded for data between the 11 th month and the 28 th month and the 12 th month in 2018 and between the 28 th month and the 12 th month and between the 20 th month in the 11 th month and the 12 th month in 2018.
Next, the time series and moving average are analyzed by the data analysis module 33:
namely, the historical data is subjected to relevant statistical analysis, and the analyzed data comprises a tubular reaction system, a granulation system, a drying system, a cooling system and a washing and discharging system. And (3) counting the distribution condition of each data by drawing a time sequence curve of each item of data, reflecting the general view of the data and preparing for data analysis and predictive modeling.
Specifically, the tubular reaction comprises liquid ammonia data: namely the flow of the inlet pipe reverse liquid ammonia, the pressure of the inlet pipe reverse liquid ammonia and the adjustment data of the inlet pipe reverse liquid ammonia adjusting valve in corresponding time periods; sulfuric acid data: namely the flow rate of the back sulfuric acid entering the pipe and the pressure of the back sulfuric acid entering the pipe in the corresponding time period; phosphoric acid data: namely the pipe inlet reverse phosphoric acid flow and the pipe inlet reverse phosphoric acid pressure in the corresponding time period; washing liquid data: namely the flow rate of the pipe inlet backwashing washing liquid and the pressure of the pipe inlet backwashing washing liquid in the corresponding time period;
the granulation system comprises material weighing data: weighing data in corresponding time periods; granulation temperature data: namely the temperature of granulation tail gas in the corresponding time period; return charge quantity current data: namely, the belt current data for the corresponding time period (L5303), (L5307) bucket current data, (L5308) bucket current data; air volume data: i.e. the corresponding time period (C5201) fan current data.
The drying system comprises drying machine current data: i.e. dryer current for the corresponding time period; pressure data: i.e. the dryer inlet pressure at the corresponding time period; temperature data: namely the inlet temperature of the dryer and the outlet temperature of the dryer in corresponding time periods; and (3) natural gas quantity data: i.e. the natural gas flow rate for the corresponding period of time.
The cooling system comprises a fan current change amplitude of the cooling system: i.e., the fan current data for the corresponding time period (C5303).
The finished product quantity and the pollution emission comprise finished product quantity data; emission data: namely dust emission data and ammonia emission data in corresponding time periods.
And then according to the data, the first path:
data scatter plot analysis: the scatter diagram of the corresponding time period data analysis is relatively complex, so that the method is not attached to the application, and the inlet temperature of the dryer, the outlet material temperature of the dryer and the outlet temperature of the dryer can be actually read out from the scatter diagram, so that the correlation is relatively strong.
And (2) a second way: linear correlation analysis
Referring to fig. 6, which is a 2018 data analysis correlation thermodynamic diagram of days 3-13, months 10, the data at this time does not reflect a major and emissions correlation, which, as previously mentioned, may be a post-wash result with observed emissions, but the effect of the wash system on emissions is dominant.
Referring to fig. 7, which is a data analysis correlation thermodynamic diagram from 11/month 28 to 12/month 20/day 2018, the data part index and the emission in the period have a certain correlation, and the correlation of the short data is greater than 0.3 (moderate correlation).
Referring to fig. 9, from the analysis of MIC, there is a more obvious correlation (linear + non-linear) between the more variable and the pollutant emission, especially the correlation of the dust content of the exhaust gas. But the factors associated with ammonia emissions are only 2.
| PI_5204 | FI_5218 | |
| Parameter(s) | Pipe back pressure | Natural gas flow |
| MIC | 0.52 | 0.32 |
In fig. 10, it is seen that 8 of the 40 parameters were selected, and principal component analysis showed that the 8 contributions to variance were 67.2%. But there are some uncertain factors in general, and the contribution of 30% + comes from other scattered elements, so the whole system has strong non-linear characteristics.
Here, the applicant indicates: in the present embodiment, two time period history data are analyzed. In practical application, analysis is carried out in more time periods, and with the access of real-time data, more data are introduced into an analysis model subsequently, so that the completeness and the certainty of the analysis are ensured.
And modeling data by a modeling module (34) after the analysis, wherein the modeling module (34) comprises a data cleaning submodule and a data association submodule.
The purpose of the data cleaning submodule is to process unreasonable data existing in original data and fill missing data according to rules. And the data cleaning submodule cleans unreasonable data and fills missing values.
The unreasonable data mainly refers to error data and abnormal data, for example, when the current data of the drying machine is invalid, the data of other parameters are not used, and the data of few points with too high values caused by the bad reaction of ammonia acid in a short time are also available. For this case, the relevant few data will be excluded, thereby avoiding the extreme impact of the few data on the overall analysis of the data. Whereas missing values are empty value data present in the value data that is not recorded. The existence of the missing value causes data inconsistency and has certain influence on data analysis and processing. The missing value filling mode comprises a forward filling mode, a backward filling mode, a mean value filling mode and the like. In this embodiment, the mean value filling is performed on the control that the continuous missing value does not exceed a certain amount, and the amount of filling is mainly determined by the ratio of the missing number.
The data association submodule is used for associating data of all links, namely associating a pipe reverse process, a granulation system, a drying system, a cold area system and a washing system, with the whole process of production of the compound fertilizer as a flow type production process so as to be capable of correctly reducing and discharging, wherein the process comprises association between incoming material data, such as data of phosphoric acid, sulfuric acid, liquid ammonia and materials, and process data, such as temperature and the like.
In the production process of the compound fertilizer, various materials are input, and return materials (waste materials) are also input, wherein the materials comprise urea, monoammonium phosphate, potassium chloride, potassium sulfate, ammonium chloride and ammonium sulfate, and the amount of the return materials plays a crucial role in the final product amount, and the effect of granulation can be influenced by the reaction of the added ammonia acid and the control of temperature and humidity. From this flow, the liquid ammonia and sulfuric acid in the tubular reactor undergo a neutralization reaction, producing an ammonium sulfate slurry and an exotherm, and in the pelletizing train, the temperature affects the rate of the recombination reaction and affects the ammonia emission. The drying system mainly discharges dust, the influencing factors mainly comprise temperature and granulation effect, and if the granulation effect is not good, the dust discharge is obviously increased due to excessive powder. The subsequent screening and cooling system also affects the dust emission.
And then modeling an algorithm module:
including dust and ammonia emissions prediction: and establishing an emission prediction model by using a machine learning algorithm and utilizing the tube inverse data, the granulation system data, the drying system data and the cooling and washing system data of the compound fertilizer. The model is mainly established by depending on historical data, the historical data can be classified and divided according to time periods, products and the like, and the emission prediction of dust and ammonia gas is output by the data obtained after the algorithm data is associated and subjected to characteristic engineering. It includes: firstly, introduction of key factor principle: in the feature selection method in the data analysis process at present, random forest is a common method, measures the importance of features and selects features with higher importance. In addition to random forest methods, basic significant feature identification may compute linear and nonlinear correlations of parameters with optimization objectives, such as Maximum Information Coefficient (MIC). Secondly, feature selection: the good feature selection can improve the performance of the model and help people to understand the characteristics and the underlying structure of data, which plays an important role in further improving the model and the algorithm. Feature selection has two main functions: 1. the number of features is reduced, the dimension is reduced, the generalization capability of the model is stronger, and overfitting is reduced; 2. enhancing the understanding between features and feature values.
The feature selection can be performed in several ways:
1. removing features with small variation in value
This feature is considered to be less powerful, assuming that the feature value of a feature is only 0 and 1, and that the feature value of 95% of the instances in all input samples is 1. If 100% is, the feature has no value to the model building. This method, while simple, is not very useful. The method can be used as a pretreatment of feature selection, which removes the features with small value change, and then selects a suitable feature from the next mentioned feature selection method for further feature selection.
Pearson Correlation coefficient Pearson Correlation
The Pearson correlation coefficient is the simplest method which can help to understand the relationship between the characteristic and the response variables, and measures the linear correlation between the variables, the value range of the result is [ -1, 1], < 1 > represents the complete negative correlation (the variable decreases and then rises), +1 represents the complete positive correlation, and < 0 > represents no linear correlation. This method is also one of the analytical methods we have previously described.
3. Mutual information and Maximum Information Coefficient (MIC).
4. Random forest
The random forest has the advantages of high accuracy, good robustness, easy use and the like, so that the random forest becomes one of the most popular machine learning algorithms at present.
The production process parameters are recommended:
and after determining the key factors, further recommending the process parameters by using the screened key factors. The process parameter recommendation modeling can be carried out in a decision tree mode, the target variable is unchanged, the input variable is replaced by the first N characteristics identified by the key factors, and N is a value determined according to the model condition.
By means of the decision tree, the optimal node which meets the requirement of a certain sample size under the current incoming material condition can be found, and therefore the corresponding process recommendation parameters are determined. Here, in order to make the recommended parameters have a certain universality, it is required to cover at least 15% of the sample size.
And the control parameters are recommended:
in order to better execute the recommended process parameters, it is necessary that the operators in the stations, especially the central control room, can accurately adjust the process indexes to be within the target value range. But the method is limited by the experience of operators and the correlation of all variables, and the target process parameters are often difficult to accurately regulate and control.
In this embodiment, a control optimization model is established for different control parameters. And (4) constructing a control model by learning the relation between historical control variables and target variables. When the control is applied, the current process parameter value and the target process parameter value are input, and a recommended control parameter set value interval is given.
Fig. 12 and 13 show algorithms of a time sequence prediction model or an optimal model:
FIG. 12 shows a time-series prediction model XT＝(x1T,...,xnT)；
FIG. 13 is an optimization model.
Further, the applicant shows: based on the deployment principle of the ET industrial brain given in the background art, the chemical industry can create and apply the ET industrial brain console to the actual production environment through the following steps:
1. preparing cloud resources: before using the ET industrial brain, cloud resources for storing data are added to prepare for data access.
2. Creating a corresponding module: and creating a corresponding module in the ET industrial brain console. If the data type is time series data, the corresponding module-time series data is adopted. E.g. the data type is image data, corresponding module-image data.
3. Setting a knowledge graph unit: and configuring a business process, a data dictionary and a business rule submodule on the knowledge map page.
4. Setting a data link unit: a series of configurations from data access, data preprocessing, data mapping and then algorithm are completed through a data link configuration function. The data link-timing data is configured, e.g., the data type is timing data. The data link is configured with image data, for example, the data type is image data.
5. Setting a data access unit: and equipment data, database data or local file data are accessed into the industrial brain platform through a data access configuration function, so that data cloud application is realized. And configuring data access if the data type is time sequence data. And uploading the image if the data type is image data.
6. Setting a data preprocessing unit: and filling missing values of the equipment data through a data preprocessing function. And configuring data preprocessing if the data type is time sequence data. If the data type is image data, no data preprocessing is required.
7. Setting a data mapping unit: and associating the equipment data with the corresponding equipment attributes through a data mapping function of the knowledge graph unit to serve as an input source or an output source of the algorithm component. And configuring data mapping if the data type is time sequence data. If the data type is image data, the data mapping configuration is not needed, but the image is required to be labeled by using an external labeling tool.
8. Configuring an AI algorithm unit: and configuring input and output of the algorithm component to realize the functions of model training and online prediction. If the data type is time series data, the algorithm component is configured. If the data type is image data, the algorithm is trained.
9. Calling an API: after the algorithm is operated, a corresponding API is generated, and the corresponding API is called by configuring the serviceId corresponding to the API and downloading the SDK development kit.
Claims (9)
1. A chemical industry data analysis system based on industrial big data comprises a cloud service platform (10) for receiving and storing industrial big data information; the system comprises a data acquisition unit (20) arranged in a chemical plant area, wherein a data statistics module (21) is arranged on the data acquisition unit (20); the industrial big data processing unit (30), the industrial big data processing unit (30) comprises a monitoring early warning module (31), a product quality control module (32), a data analysis module (33), a modeling module (34) and a report module (35); the method is characterized in that:
the cloud service platform (10) is linked with an industrial big data processing unit (30), the cloud service platform (10) comprises a resource unit (11) on the cloud and a local resource unit (12), the local resource unit (12) transmits chemical industry intranet data to a data acquisition extranet interface server of the resource unit (11) on the cloud, and the resource unit (11) on the cloud comprises a data service API gateway module, a data bus DataHub module and a big data storage computing service MaxCommute module;
the data acquisition unit (20) acquires service system data, wherein the service system data comprises DCS data in a chemical production process and chemical production class plan production report data; the DCS data comprises parameters corresponding to each process in chemical production, and comprises flow data, pressure data, temperature data, air volume data, current data and optimization target data, the optimization target data comprises finished product content, tail gas dust content and tail gas ammonia content data, the DCS data is exported and then is used for screening the obtained data for basic conditions, data which do not belong to the corresponding parameter range in the chemical production process are removed, and the screened data are transmitted to a data statistics module (21);
the data of the data statistics module (21) is transmitted to a data analysis module (33) of the industrial big data processing unit (30), the data analysis module (33) performs statistics on the distribution condition of each data by drawing a time sequence curve of each item of data on the data of the data statistics module (21), and then performs modeling on the data by the modeling module (34) through data scatter diagram analysis or linear correlation analysis; the modeling module (34) comprises a data cleaning submodule and a data correlation submodule, and the data cleaning submodule cleans unreasonable data and fills missing values; the industrial big data processing unit (30) carries out algorithm modeling after data modeling by using a modeling module (34).
2. The industrial big data-based chemical industry data analysis system according to claim 1, wherein: the data service API gateway module provides cloud data receiving service, and the local data acquisition service calls the interface API in real time to complete real-time DCS data synchronization and cloud uploading; the data bus DataHub module continuously collects, stores and processes a large amount of streaming data generated by various mobile devices, application software, website services and sensors, a user writes an application program or processes the streaming data written into the DataHub by using a streaming calculation engine, and various real-time data processing results are generated; the big data storage computing service MaxCommute module perfects a data import scheme and a plurality of classical distributed computing models.
3. The industrial big data-based chemical industry data analysis system according to claim 1, wherein: the method for screening the acquired data for the basic situation after the DCS data is exported comprises the following steps: acquiring DCS historical data of multiple periods of time, exporting the data into a csv format through industrial software for analysis aiming at the DCS data, and screening the acquired data for basic conditions.
4. The industrial big data-based chemical industry data analysis system according to claim 1, wherein: the local resource unit (12) is connected with a local real-time data acquisition service, and the data acquisition service calls a cloud data service API restful interface to enable the business data to be in real-time cloud.
5. The industrial big data-based chemical industry data analysis system according to claim 2, wherein: and pushing the DCS system data received in the data service API gateway module into the DataHub through the DataHub sdk.
6. The industrial big data-based chemical industry data analysis system according to any one of claims 1, 2, 3, 4 and 5, wherein: the modeling module (33) firstly utilizes historical data to model a recommendation algorithm module; and finally, carrying out field verification and iteration of the recommendation algorithm.
7. The industrial big data-based chemical industry data analysis system according to claim 6, wherein: and the model modeled by the recommendation algorithm module is a time sequence prediction model or an optimal model.
8. The industrial big data-based chemical industry data analysis system according to claim 7, wherein: basic steps of the recommendation algorithm for field verification:
1) selecting a reasonable and controllable process optimization scheme by combining decision tree optimization results according to experience to form an optimization rule for implementation;
2) selecting a node of a poor sample according to experience, identifying process parameters of a poor product, and forming an evasion rule for implementation;
3) selecting one production line to carry out a one-week experiment;
4) and selecting an AB method alternate experiment, mutually verifying, and selecting comprehensive optimal.
9. The industrial big data-based chemical industry data analysis system according to claim 1, wherein: the DCS data comprises data of a tubular reaction system, a washing system, a granulation system, a drying system, a cooling system, finished product quantity and tail gas.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010127933.2A CN111984692B (en) | 2020-02-28 | 2020-02-28 | Chemical data analysis system based on industrial big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010127933.2A CN111984692B (en) | 2020-02-28 | 2020-02-28 | Chemical data analysis system based on industrial big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111984692A true CN111984692A (en) | 2020-11-24 |
| CN111984692B CN111984692B (en) | 2022-12-02 |
Family
ID=73441722
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010127933.2A Active CN111984692B (en) | 2020-02-28 | 2020-02-28 | Chemical data analysis system based on industrial big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111984692B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113065288A (en) * | 2021-04-19 | 2021-07-02 | 工数科技(广州)有限公司 | Nutrient optimization method for compound fertilizer production based on industrial data and process mechanism |
| CN113115241A (en) * | 2021-04-07 | 2021-07-13 | 青岛容商天下网络有限公司 | Industrial Internet system based on industrial brain |
| CN113591388A (en) * | 2021-08-09 | 2021-11-02 | 工数科技(广州)有限公司 | Steam turbine heat rate optimization method based on industrial data and process mechanism |
| CN113713536A (en) * | 2021-08-25 | 2021-11-30 | 九江一晖环保集团有限公司 | Waste gas pollution source analysis method |
| CN114817739A (en) * | 2022-05-16 | 2022-07-29 | 广东弘力控股集团有限公司 | Industrial big data processing system based on artificial intelligence algorithm |
| CN114827182A (en) * | 2021-01-21 | 2022-07-29 | 迈动云智(常熟)信息科技有限公司 | Intelligent park management platform based on ET brain |
| CN114913477A (en) * | 2022-05-06 | 2022-08-16 | 广州市城市规划勘测设计研究院 | Urban pipeline excavation prevention early warning method, device, equipment and medium |
| TWI810602B (en) * | 2021-07-07 | 2023-08-01 | 友達光電股份有限公司 | Automatic search method for key factor based on machine learning |
| CN116713709A (en) * | 2023-05-29 | 2023-09-08 | 苏州索力伊智能科技有限公司 | Control system and method for automatic connector assembly equipment |
| CN117171238A (en) * | 2023-11-02 | 2023-12-05 | 菲特（天津）检测技术有限公司 | Big data algorithm platform and data mining method |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090024359A1 (en) * | 2007-07-16 | 2009-01-22 | Rockwell Automation Technologies, Inc. | Portable modular industrial data collector and analyzer system |
| CN102903011A (en) * | 2012-09-25 | 2013-01-30 | 浙江图讯科技有限公司 | Mass data processing system used for safety production cloud service platform facing industrial and mining enterprises |
| CN102917031A (en) * | 2012-09-25 | 2013-02-06 | 浙江图讯科技有限公司 | Data computing system of safety production cloud service platform for industrial and mining enterprises |
| US20140047107A1 (en) * | 2012-08-09 | 2014-02-13 | Rockwell Automation Technologies, Inc. | Remote industrial monitoring and analytics using a cloud infrastructure |
| WO2016101638A1 (en) * | 2014-12-23 | 2016-06-30 | 国家电网公司 | Operation management method for electric power system cloud simulation platform |
| CN106161620A (en) * | 2016-06-29 | 2016-11-23 | 浙江理工大学 | A kind of cloud computing resources Internet of Things supervision and service platform |
| CN106302739A (en) * | 2016-08-16 | 2017-01-04 | 北京大邦实创节能技术服务有限公司 | A kind of Industrial Boiler monitoring and analysis aid decision cloud platform system |
| US20180210432A1 (en) * | 2015-10-12 | 2018-07-26 | Efort Intelligent Equipment Co., Ltd. | Industrial robot process cloud system and working method thereof |
| US20180285571A1 (en) * | 2017-03-28 | 2018-10-04 | International Business Machines Corporation | Automatic detection of an incomplete static analysis security assessment |
| CN109492773A (en) * | 2018-10-17 | 2019-03-19 | 南京昊瀛天成信息技术有限公司 | A kind of intelligent decision system based on industrial big data |
| CN109739922A (en) * | 2019-01-10 | 2019-05-10 | 江苏徐工信息技术股份有限公司 | A kind of industrial data intelligent analysis system |
| CN110232236A (en) * | 2019-06-11 | 2019-09-13 | 成渝钒钛科技有限公司 | A kind of steel rolling heat power engineering system efficiency optimization method |
| CN110460656A (en) * | 2019-08-01 | 2019-11-15 | 哈工大机器人（合肥）国际创新研究院 | A kind of industry environmental protection Internet of Things remotely monitors cloud platform |
| CN110457184A (en) * | 2018-05-07 | 2019-11-15 | 中国石油化工股份有限公司 | Associated chemical industry exception causality analysis and figure methods of exhibiting are fluctuated based on timing |
| CN110809017A (en) * | 2019-08-16 | 2020-02-18 | 云南电网有限责任公司玉溪供电局 | Data analysis application platform system based on cloud platform and micro-service framework |
-
2020
- 2020-02-28 CN CN202010127933.2A patent/CN111984692B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090024359A1 (en) * | 2007-07-16 | 2009-01-22 | Rockwell Automation Technologies, Inc. | Portable modular industrial data collector and analyzer system |
| US20140047107A1 (en) * | 2012-08-09 | 2014-02-13 | Rockwell Automation Technologies, Inc. | Remote industrial monitoring and analytics using a cloud infrastructure |
| CN102903011A (en) * | 2012-09-25 | 2013-01-30 | 浙江图讯科技有限公司 | Mass data processing system used for safety production cloud service platform facing industrial and mining enterprises |
| CN102917031A (en) * | 2012-09-25 | 2013-02-06 | 浙江图讯科技有限公司 | Data computing system of safety production cloud service platform for industrial and mining enterprises |
| WO2016101638A1 (en) * | 2014-12-23 | 2016-06-30 | 国家电网公司 | Operation management method for electric power system cloud simulation platform |
| US20180210432A1 (en) * | 2015-10-12 | 2018-07-26 | Efort Intelligent Equipment Co., Ltd. | Industrial robot process cloud system and working method thereof |
| CN106161620A (en) * | 2016-06-29 | 2016-11-23 | 浙江理工大学 | A kind of cloud computing resources Internet of Things supervision and service platform |
| CN106302739A (en) * | 2016-08-16 | 2017-01-04 | 北京大邦实创节能技术服务有限公司 | A kind of Industrial Boiler monitoring and analysis aid decision cloud platform system |
| US20180285571A1 (en) * | 2017-03-28 | 2018-10-04 | International Business Machines Corporation | Automatic detection of an incomplete static analysis security assessment |
| CN110457184A (en) * | 2018-05-07 | 2019-11-15 | 中国石油化工股份有限公司 | Associated chemical industry exception causality analysis and figure methods of exhibiting are fluctuated based on timing |
| CN109492773A (en) * | 2018-10-17 | 2019-03-19 | 南京昊瀛天成信息技术有限公司 | A kind of intelligent decision system based on industrial big data |
| CN109739922A (en) * | 2019-01-10 | 2019-05-10 | 江苏徐工信息技术股份有限公司 | A kind of industrial data intelligent analysis system |
| CN110232236A (en) * | 2019-06-11 | 2019-09-13 | 成渝钒钛科技有限公司 | A kind of steel rolling heat power engineering system efficiency optimization method |
| CN110460656A (en) * | 2019-08-01 | 2019-11-15 | 哈工大机器人（合肥）国际创新研究院 | A kind of industry environmental protection Internet of Things remotely monitors cloud platform |
| CN110809017A (en) * | 2019-08-16 | 2020-02-18 | 云南电网有限责任公司玉溪供电局 | Data analysis application platform system based on cloud platform and micro-service framework |
Non-Patent Citations (4)
| Title |
|---|
| YANPENG WANG ET AL.: "A USB data acquisition system in chemical laboratory", 《2010 INTERNATIONAL CONFERENCE ON COMPUTER DESIGN AND APPLICATIONS》 * |
| 孙为军等: "智能工厂工业大数据云平台的设计与实现", 《广东工业大学学报》 * |
| 杨继伟: "基于云点播生产平台的智能分析系统", 《科技创新导报》 * |
| 王小艳: "化工物性数据库系统软件开发", 《中国优秀硕士学位论文全文数据库 工程科技Ⅰ辑》 * |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114827182A (en) * | 2021-01-21 | 2022-07-29 | 迈动云智(常熟)信息科技有限公司 | Intelligent park management platform based on ET brain |
| CN113115241B (en) * | 2021-04-07 | 2022-11-15 | 青岛容商天下网络有限公司 | Industrial Internet system based on industrial brain |
| CN113115241A (en) * | 2021-04-07 | 2021-07-13 | 青岛容商天下网络有限公司 | Industrial Internet system based on industrial brain |
| CN113065288A (en) * | 2021-04-19 | 2021-07-02 | 工数科技(广州)有限公司 | Nutrient optimization method for compound fertilizer production based on industrial data and process mechanism |
| TWI810602B (en) * | 2021-07-07 | 2023-08-01 | 友達光電股份有限公司 | Automatic search method for key factor based on machine learning |
| CN113591388A (en) * | 2021-08-09 | 2021-11-02 | 工数科技(广州)有限公司 | Steam turbine heat rate optimization method based on industrial data and process mechanism |
| CN113713536A (en) * | 2021-08-25 | 2021-11-30 | 九江一晖环保集团有限公司 | Waste gas pollution source analysis method |
| CN114913477A (en) * | 2022-05-06 | 2022-08-16 | 广州市城市规划勘测设计研究院 | Urban pipeline excavation prevention early warning method, device, equipment and medium |
| CN114817739B (en) * | 2022-05-16 | 2023-03-28 | 深圳海力德油田技术开发有限公司 | Industrial big data processing system based on artificial intelligence algorithm |
| CN114817739A (en) * | 2022-05-16 | 2022-07-29 | 广东弘力控股集团有限公司 | Industrial big data processing system based on artificial intelligence algorithm |
| CN116713709A (en) * | 2023-05-29 | 2023-09-08 | 苏州索力伊智能科技有限公司 | Control system and method for automatic connector assembly equipment |
| CN116713709B (en) * | 2023-05-29 | 2023-12-19 | 苏州索力伊智能科技有限公司 | Control system and method for automatic connector assembly equipment |
| CN117171238A (en) * | 2023-11-02 | 2023-12-05 | 菲特（天津）检测技术有限公司 | Big data algorithm platform and data mining method |
| CN117171238B (en) * | 2023-11-02 | 2024-02-23 | 菲特（天津）检测技术有限公司 | Big data algorithm platform and data mining method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111984692B (en) | 2022-12-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111984692B (en) | Chemical data analysis system based on industrial big data | |
| CN111338302B (en) | Chemical process modeling processing system based on industrial big data and industrial Internet of things | |
| Chouhan et al. | Sustainable planning and decision-making model for sugarcane mills considering environmental issues | |
| CN105004542A (en) | Online monitoring and fault diagnosing method for mixing and flavouring process of cigarette filament production based on principal component analysis | |
| Thompson et al. | An integrated approach for modeling uncertainty in aggregate production planning | |
| CN114169574A (en) | Method for predicting atmospheric pollution through industrial operation power index | |
| CN115860529A (en) | Supply chain carbon accounting system based on industrial internet | |
| CN106355268A (en) | Optimization method for urban industrial structure based on environmental carrying capacity | |
| CN106779259A (en) | A kind of thermal power plant's fuel overall process intelligent management system | |
| CN107942873A (en) | A kind of intelligent accounting of the operation cost of Furniture manufacture production line and monitoring method | |
| Ungureanu et al. | Industrial load forecasting using machine learning in the context of smart grid | |
| CN116109089A (en) | Digital monitoring management method for low-carbon transformation of steel mill | |
| CN111222733A (en) | Industrial intelligent decision system and working method thereof | |
| Sharara et al. | Addressing nutrient imbalances in animal agriculture systems | |
| Tao et al. | Optimization Analysis of Power Coal-Blending Model and Its Control System Based on Intelligent Sensor Network and Genetic Algorithm. | |
| CN114125001B (en) | Edge micro-platform equipment for kitchen waste treatment anaerobic system | |
| CN103488089A (en) | System and method for controlling emission of noxious substances of pesticide waste liquid incinerator to reach standards in self-adaptation mode | |
| Liu et al. | Time series forecasting fusion network model based on prophet and improved LSTM | |
| Chuentawat et al. | The forecast of PM10 pollutant by using a hybrid model | |
| Boguhn | Forecasting power consumption of manufacturing industries using neural networks | |
| CN103558762B (en) | The implementation method of the immune genetic PID controller based on graphical configuration technology | |
| Zhou et al. | Simulation based analysis for selection and evaluation of green manufacturing strategies | |
| CN110132623A (en) | A kind of mobile terminal agricultural monitoring method for early warning | |
| CN115222153B (en) | Low-carbon scheduling optimizing method and system for thermal power enterprises | |
| CN107479479A (en) | A kind of Energy Sources Equilibrium network monitoring system based on the conservation of energy |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |