Automatic generation method of process knowledge based on P-graph

doi:10.11949/j.issn.0438-1157.20181353

Abstract

Abstract:

Knowledge generation is the basis of industrial knowledge automation. Process industry knowledge is usually generated by directed tasks, such as optimization scheduling, optimization operation, fault diagnosis, etc. The solution generation requires not only understanding the operation mechanism and production data, but also relying on domain expert experience. Such forms of knowledge representation are difficult to unify, poorly ported, and inconvenient to share and reuse. Aiming at the problem of resource scheduling optimization of ethylene cracking furnace group, the P-graph method is used to construct the superstructure model of the solution, which is designed to represent the knowledge of P-graph ontology and database mapping into knowledge rules, and automatically generate RDF (resource description framework) represents the solution knowledge and builds a knowledge repository. Finally, the actual production data of the ethylene production plant was used to verify the feasibility and practicability of the proposed method.

Key words: algorithm, integration, optimization, P-graph, superstructure, ontology

摘要：

知识生成是工业知识自动化的基础，流程工业知识通常由定向任务驱动生成，如优化调度、优化操作、故障诊断等，其解决方案生成除需要了解运行机理及生产数据外，同时更依赖领域专家经验，此类知识表示形式难统一，移植性差，不便于共享及重用。针对乙烯裂解炉炉群资源调度优化问题，采用P-图求解方法，构建解决方案的超结构模型，设计用于表示知识的P-图本体以及数据库映射为知识的规则，自动生成RDF(resource description framework)表示的解决方案知识，建立知识库。最后利用乙烯生产厂的实际生产数据，验证了提出方法的可行性与实用性。

关键词: 算法, 集成, 优化, P-图, 超结构, 本体

CLC Number:

TP 391.1

Jian CAO, Peng MU, Xiangbai GU, Qunxiong ZHU. Automatic generation method of process knowledge based on P-graph[J]. CIESC Journal, 2019, 70(2): 467-474.

曹健, 牟鹏, 顾祥柏, 朱群雄. 基于P-图的流程知识自动生成方法[J]. 化工学报, 2019, 70(2): 467-474.

Figures/Tables 10

References 31

1	FriedlerF， FanL T, ImrehB. Process network synthesis: problem definition[J]. Networks, 1998, 31(2): 119-124.
2	RaymondR T, ChristinaD C, KathleenB A. P-graph approach to optimal operational adjustment in polygeneration plants under conditions of process inoperability[J]. Applied Energy, 2014, 135: 402-406.
3	刘树明，万峰，杨宇，等. 化工领域设备本体模型构建[J].华东理工大学学报， 2017, 43(3): 404-410.
	LiuS M, WanF, YangY, et al. Model of chemical domain device ontology constructing[J]. Journal of East China University of Science and Technology, 2017, 43(3): 404-410.
4	EdwardC, PieterP, HuS S, et al. A performance assessment ontology for the environmental and energy management of buildings[J]. Automation in Construction, 2015, 57: 249-259.
5	桂卫华，岳伟超，陈晓方，等. 流程工业知识自动化及其在铝电解生产中的应用[J]. 控制理论与应用， 2018, 35(7): 887-899.
	GuiW H,YueW C,ChenX F. Process industry knowledge automation and its applications in aluminum electrolysis production[J].Control Theory & Applications, 2018,35(7):887-899.
6	ZhangY Z, LuoX F, ZhaoY, et al. An ontology-based knowledge framework for engineering material selection[J].Advanced Engineering Informatics, 2015, 29: 985-1000.
7	ZhouQ, YanP, XinY. Research on a knowledge modeling methodology for fault diagnosis of machine tools based on formal semantics[J]. Advanced Engineering Informatics, 2017, 32: 92-112.
8	ZhouL, PanM, SikorskiJ J, alet . Towards an ontological infrastructure for chemical process simulation and optimization in the context of eco-industrial parks[J]. Applied Energy, 2017, 204:1284-1298.
9	ManuV, CharlesM E , JohcenT. An ontology-based analysis of the industry foundation class schema for building information model exchanges[J]. Advanced Engineering Informatics, 2015, 29: 940-957.
10	SoonjoK, BongcheolK, KyungikA, et al. Standardized exchange of plant equipment and materials data based on ISO 15926 methodology in unclear power plants[J].Annals of Nuclear Energy, 2018, 118: 185-198.
11	文亮，李娟，刘智颖，等. 基于概念层次网络的知识表示与本体建模[J]. 中文信息学报， 2018， 32(4): 66-73.
	WenL, LiJ, LiuZ Y, et al. A method of knowledge representation and ontology modeling based on hierarchical network of concepts[J]. Journal of Chinese Information Processing， 2018, 32(4): 66-73.
12	ChenY J. Development of a method for ontology-based empirical knowledge representation and reasoning[J]. Decision Support Systems, 2010, 50: 1-20.
13	ChenB C, WanJ F, ShuL, et al. Smart factory of industry 4.0: key technologies, application case, and challenges[J]. IEEE Access,2018, 6(99): 6505-6519.
14	BorjaR F, JoseL M L. Private local automation clouds builts by CPS: potential and challenges for distributed reasoning[J].Advanced Engineering Informatics, 2017, 32: 113-125.
15	JamshaidA, ElizabethC, OmarK H, et al. Ontology usage analysis in the ontology lifecycle: a state-of-the-art review[J]. Knowledge-Based Systems, 2018, 50: 34-47.
16	MeganK, MarkF. Ontologies for transportation research: a survey[J]. Transportation Research Part C, 2018, 89: 53-82.
17	MuhammadN A, MuhanmmadW, MuhanmmadU G K, et al. A survey of ontology learning techniques and applications[J]. Database, 2018, 2018: 1-24.
18	EstanislaoM, FernandoR, MartaB. A knowledge-driven approach for process supervision in chemical plants[J]. Computers and Chemical Engineering, 2013, 59: 164-177.
19	LeeY C, EastmanC M， SolihinW. An ontology-based approach for developing data exchange requirements and model views of building information modeling[J].Advanced Engineering Informatics, 2016, 30: 354-367.
20	LiuJ, ZhengB J, LuoL M, et al. Ontology representation and mapping of common fuzzy knowledge[J]. Neurocomputing, 2016, 214: 184-195.
21	NaimeR K,SasanH A. A hybrid multi-criteria recommender system using ontology and neuro-fuzzy techniques[J]. Electronic Commerce Research and Applications, 2017, 21: 50-64.
22	曹健, 牟鹏, 耿志强, 等.工业系统超结构模型应用研究进展[J].化工学报, 2017, 68(3): 801-810.
	CaoJ, MuP, GengZ Q, et al. Research progress and application of superstructure model for industrial systems[J].CIESC Journal, 2017, 68(3): 801-810.
23	KathleenB A, RaymondR T. Fuzzy P-graph for optimal synthesis of cogeneration and trigeneration systems[J]. Energy, 2018, 154:258-268.
24	许晓慧，宋海华，于兰平，等.加速分支定界算法在化工过程合成中的应用[J]. 计算机与应用化学, 2011, 28(4): 451-457.
	XuX H，SongH H，YuL P ,et al. Application of accelerated branch and bound in process synthesis of chemical engineering[J]. Computers and Applied Chemistry, 2011, 28(4): 451-457.
25	AlexandrosM S, IstvanH, FerencF, et al. An accelerated branch-and-bound algorithm for assignment problems of utility systems[J].Computers and Chemical Engineering, 2002, 26: 617-630.
26	杜小勇，李曼，王珊. 本体学习研究综述[J]. 软件学报， 2006, 17(9): 1837-1847.
	DuX Y, LiM, WangS. A survey on ontology learning research[J]. Journal of Software, 2006, 17(9): 1837-1847.
27	ZhangC, ZhouG H， LuQ， et al. Graph-based knowledge reuse for supporting knowledge-driven decision-making in new product development[J]. International Journal of Production Research, 2017, 4: 1-17.
28	刘晓慧，崔健，蔡菲. 突发地质灾害应急响应知识地理本体建模及推理[J]. 地理与地理信息科学， 2018, 34(4): 1-6.
	LiuX H, CuiJ, CaiF. Geo-ontology modeling and reasoning of geohazard emergency response knowledge[J]. Geography and Geo-Information Science, 2018, 34(4): 1-6.
29	MazenA, KhalidM M, MaqboolH. Automated ontology generation framework powered by linked biomedical ontologies for disease-drug domain[J]. Computer Methods and Programs in Biomedicine, 2018, 165: 117-128.
30	PatienceU U, EnobongM U, UdoinyangG I, et al. An ontology-based temporal scheduling and complexity reduction model for timetabling knowledge management [J]. Advances in Science, Technology and Engineering Systems Journal, 2017, 2(3): 1585-1591.
31	商保鹏. 乙烯裂解炉炉群原料调度建模与优化[D]. 上海：华东理工大学， 2014.
	ShangB P. Modeling and optimization for ethylene cracking furnace systems feed scheduling[D]. Shanghai: East China University of Science and Technology, 2014.

编号	操作单元
1	({light},{light_A})
2	({light},{light_B})
3	({light},{light_M})
4	({light_A},{Ethylene})
5	({light_B},{Ethylene})
…	……
20	({HCR_B},{ Ethylene })

编号	操作单元
1	({light},{light_A})
2	({light},{light_B})
3	({light},{light_M})
4	({light_A},{Ethylene})
5	({light_B},{Ethylene})
…	……
20	({HCR_B},{ Ethylene })

步骤	P 集合	M 集合	δ[m] 集合	备注
1	Ethylene	?	?	initial
2	light_A	Ethylene	{Ethylene},{4}
3	?	Ethylene, light_A	{Ethylene},{4} +{light_A},{1}	solution 1
4	light_B	Ethylene	{Ethylene},{5}
5	?	Eethylene, light_B	{Ethylene},{5}+ {light_B},{2}	solution 2
6	light_A, light_B	Ethylene	{Ethylene},{4,5}
7	light_B	Ethylene, light_A	{Ethylene},{4,5}+ {light_A},{1}
8	?	Ethylene, light_A, light_B	{Ethylene},{4,5}+ {light_A},{1}+ {light_B},{2}	solution 3
9	C₅_A	Ethylene	{Ethylene},{9}
10	?	C₅_A, Ethylene	{Ethylene},{9}+ {C₅_A},{6}	solution 4
11	light_A, C₅_A	Ethylene	{Ethylene},{4,9}
12	C₅_A	Ethylene, light_A	{Ethylene},{4,9}+ {light_A},{1}
13	?	C₅_A，Ethylene，light_A	{Ethylene},{4,9}+{light_A},{1}+{C₅_A},{6}	solution 5
?	?	?	?	?
1278	HCR_A, HCR_B	C₅_A, C₅_B, Ethylene，light_A，light_B，NAP_A，NAP_B	{Ethylene},{4,5,9,10,14,15,19,20}+{light_A},{1}+{light_B},{2}+{C₅_A},{6}+{C₅_B},{7}+{NAP_A},{11}+{NAP_B},{12}
1279	HCR_B	C₅_A，C₅_B，Ethylene，HCR_A，light_A，light_B，NAP_A，NAP_B	{Ethylene},{4,5,9,10,14,15,19,20}+{light_A},{1}+{light_B},{2}+{C₅_A},{6}+{C₅_B},{7}+{NAP_A},{11}+{NAP_B},{12}+{HCR_A},{16}
1280	?	C₅_A, C₅_B, Ethylene, HCR_A, HCR_B, light_A, light_B, NAP_A, NAP_B	{Ethylene},{4,5,9,10,14,15,19,20}+{light_A},{1}+{light_B},{2}+{C₅_A},{6}+{C₅_B},{7}+{NAP_A},{11}+{NAP_B},{12}+{HCR_A},{16}+{HCR_B},{17}	solution 255

步骤	P 集合	M 集合	δ[m] 集合	备注
1	Ethylene	?	?	initial
2	light_A	Ethylene	{Ethylene},{4}
3	?	Ethylene, light_A	{Ethylene},{4} +{light_A},{1}	solution 1
4	light_B	Ethylene	{Ethylene},{5}
5	?	Eethylene, light_B	{Ethylene},{5}+ {light_B},{2}	solution 2
6	light_A, light_B	Ethylene	{Ethylene},{4,5}
7	light_B	Ethylene, light_A	{Ethylene},{4,5}+ {light_A},{1}
8	?	Ethylene, light_A, light_B	{Ethylene},{4,5}+ {light_A},{1}+ {light_B},{2}	solution 3
9	C₅_A	Ethylene	{Ethylene},{9}
10	?	C₅_A, Ethylene	{Ethylene},{9}+ {C₅_A},{6}	solution 4
11	light_A, C₅_A	Ethylene	{Ethylene},{4,9}
12	C₅_A	Ethylene, light_A	{Ethylene},{4,9}+ {light_A},{1}
13	?	C₅_A，Ethylene，light_A	{Ethylene},{4,9}+{light_A},{1}+{C₅_A},{6}	solution 5
?	?	?	?	?
1278	HCR_A, HCR_B	C₅_A, C₅_B, Ethylene，light_A，light_B，NAP_A，NAP_B	{Ethylene},{4,5,9,10,14,15,19,20}+{light_A},{1}+{light_B},{2}+{C₅_A},{6}+{C₅_B},{7}+{NAP_A},{11}+{NAP_B},{12}
1279	HCR_B	C₅_A，C₅_B，Ethylene，HCR_A，light_A，light_B，NAP_A，NAP_B	{Ethylene},{4,5,9,10,14,15,19,20}+{light_A},{1}+{light_B},{2}+{C₅_A},{6}+{C₅_B},{7}+{NAP_A},{11}+{NAP_B},{12}+{HCR_A},{16}
1280	?	C₅_A, C₅_B, Ethylene, HCR_A, HCR_B, light_A, light_B, NAP_A, NAP_B	{Ethylene},{4,5,9,10,14,15,19,20}+{light_A},{1}+{light_B},{2}+{C₅_A},{6}+{C₅_B},{7}+{NAP_A},{11}+{NAP_B},{12}+{HCR_A},{16}+{HCR_B},{17}	solution 255

编号	操作单元	处理能力/t	能耗/(GJ?t^-1)	比率
1	({light},{light_A})	20299.2	0.879551748	1∶0.06223
2	({light},{light_B})	107050.8	6.904969808	1∶0.47795
3	({C₅},{C₅_A})	50378	3.055076397	1∶0.46465
4	({C₅},{C₅_B})	66504	3.729234242	1∶0.19722
5	({NAP},{NAP_A})	144769.2	8.790563062	1:∶0.35801
6	({NAP},{NAP_B})	95888.4	13.87380214	1∶0.47678
7	{HCR},{HCR_A})	60744	8.222360538	1∶0.34411
8	({HCR},{HCR_B})	66984	1.177027079	1∶0.05094