Semantic mining is an essential part in knowledgebase and decision support systems where it enables the extraction of useful knowledge form available databases with the ultimate goal of supporting the decision making process. In process systems engineering, decisions are made throughout plant / process / product life cycles. The provision of smart semantic mining techniques will improve the decision making process for all life cycle activities. In particular, safety and environmental related decisions are highly dependent on process internal and external conditions and dynamics with respect to equipment geometry and plant layout. This chapter discusses practical methods for semantic mining using systematic knowledge representation as integrated with process modeling and domain knowledge. POOM or plant/process object oriented modeling methodology is explained and used as a basis to implement semantic mining as applied on process systems engineering. Case studies are illustrated for biological process engineering, in particular MoFlo systems focusing on process safety and operation design support.
TopIntroduction
The recent challenges of industrial, medical, and social systems are focused on how to provide intelligent learning systems that can deal with increasing complexity and multidimensional knowledge structures. The problem became worse when dealing with different scales of domain knowledge in multimedia formats. Researchers and professionals from industry are seeking practical approaches to extract useful knowledge to support decisions throughout process / system life cycle. Recent advances in semantic mining motivated researchers and industry in different system disciplines to adopt and apply semantic mining techniques for traditional and multimedia databases and knowledgebase systems. This chapter will discuss problems and solutions related to application of advanced semantic mining using formal representation of domain knowledge for process systems. The proposed approach can be divided into the following major stages:
- •
Model construction of process systems
- •
Knowledge structuring and representation of process models
- •
Construction of formal meta-language and language to represent domain knowledge and activities of process models
- •
Knowledge acquisition and validation (qualitative and quantitative)
- •
Semantic mining for decision support of process life cycle activities
The management of these stages requires robust modeling methodology, which facilitated the integration between nano, micro, and macro process levels. Each process level is abstracted using building blocks in three basic views: static, dynamic, and operation (Gabbar et al., 2001; 2003; 2004). In view of the proposed modeling and simulation methodology, control layer is used to support the design and operation of the underlying system as integrated with simulation environment. The proposed system engineering approach supports change management, HSE (health, safety, and environment), recycling, energy, and sustainability. Planning and scheduling are analyzed and managed for the different hierarchical levels i.e. nano, micro, and macro. For example, process of reconstruction of human cell functions includes MoFlo cell sorter systems.
Figure 1.
Process engineering framework
TopOverview Of Semantic Mining For Process Engineering
Almost all efforts made in semantic mining was directed towards discovering new knowledge or search for important knowledge within large number of data elements, databases, or knowledgebases in any form, e.g. html pages, multimedia, text, etc. Semantic mining is always associated with process where primitive data is collected, updated, and manipulated. Such process involves organizational and behavioral changes. For example, semantic mining for biological processes is associated with basic biological data, e.g., samples, and phenomena linked with such biological data such as cell separation, transformation, or demolishing. In order to effectively apply and benefit from knowledge obtained from semantic mining, it is essential to define clearly how the knowledge is created, maintained, and managed with respect to process model in terms of structure, behavior, and operation. The concept of process based semantic mining is the ultimate approach for successful semantic mining. In other words, the construction of database / knowledgebase is considered as part of the semantic mining where meta-data are constructed about domain knowledge that supports semantic mining process. There are several approaches that have been done in the area of semantic mining for process engineering. Among these approaches are those that have been directed towards operating procedures representation, synthesis, and verification.