Knowledge based performance

Performance problems may be exacerbated during unfamiliar or novel process events, for example, situations not covered in the emergency procedures or in refresher training. These events require knowledge-based information processing for which people are not very reliable. The types of errors associated with knowledge-based performance have been discussed in Chapter 2. 

Knowledge based performance - activities where we have little pre-existing skills or rules to call upon and we need to assimilate the facts from first principles using inference and judgement. 

Knowledge-based performance is a response to a totally unfamiliar situation (no skill or rule is recogfiiz-able to the individual). The person must rely on his or her prior understandingand knowledge, their perceptions of present circumstances, similarities of the present situation, and similarities to circumstances encountered before, and the scientifc principles, and fundamental theory related to the perceived situation... 

Rasmussen (1983) also adopts a human information processing point of view. His taxonomy allows to discriminate three levels of human behavior skill-, rule-, and knowledge-based performance. The figure 5.1. illustrates how different internal mechanisms are used for the same decisional function, depending upon the degree of familiarity with the work situation and task element. 

Knowledge-based errors are concerned with performance in novel or new situations. Actions have to be planned on-line and the process is intellectually demanding. The problem solver will only resort to this type of activity when he has run out of rule-based solutions. An example of knowledge-based performance is that of first learning to operate a piece of machinery. The hydraulic controls of a winch provide a good example. Experimentation will help the operator to build a mental model of how the controls can be co-ordinated to achieve the desired movements. Eventually, the operator will adopt a set of rules derived from that mental model. With practice, the task will become skill-based. Training offers the opportunity to miss out the experimentation phase by guiding the trainee to a correct model of situations, based on the experiences of others. 

Knowledge-based performance is a response to a totally unfamiliar situation (no skin or rule is recognizable to the individual) (US DOE, 2009a). At this performance level, a JEIA should be completed for each new experience with unique issues or problems to ensure controls are implemented.The overall job requirements become the parent and a portfoHo of experiences developed for future use and periodically reviewed for similarities. This experience-based knowledge provides an understanding of types of hazards that could be created and how they might combine to increase the risk severity. 

The design of training should incorporate whether the job requires skill-based, rule-base, or knowledge-based performance as discussed in Chapter 2. These types of performance should incorporate the concept noted previously. 

One of the first attempts to build a knowledge base for synthetic organic reactions was made by Gelernter s group, through inductive and deductive machine learning [1]. Important work on this topic was also performed by Funatsu and his group [2]. 

The most recent version of EROS has a clearcut separation of the system proper, which performs all the manipulations on chemical structures and reactions, from the knowledge base, which defines the scope of it.s application (Figure 10.3-7). 

The Japanese program system AlPHOS is developed by Funatsu s group at Toyo-hashi Institute of Technology [40]. AlPHOS is an interactive system which performs the retrosynthetic analysis in a stepwise manner, determining at each step the synthesis precursors from the molecules of the preceding step. AlPHOS tries to combine the merits of a knowledge-based approach with those of a logic-centered approach. 

Computer-aided process synthesis systems do not mean completely automated design systems (57). Process synthesis should be carried out by interactive systems, in which the engineer s role is to carry out synthesis and the machine s role is to analy2e the performance of synthesized systems. Computet apphcations in the future will probably deal with the knowledge-based system in appHed artificial intelligence. Consequendy, research on computer-aided process synthesis should be directed toward the realization of such systems with the collaboration of experienced process engineers. 

Eor a number of cognitive or interpretive tasks, there are alternatives to mainstream knowledge-based systems that may be more appropriate, especially if adaptive behavior and learning capabihty are important to system performance. Two approaches that embody these characteristics are neural networks (nets) and case-based reasoning. 

In Figure 2.6, the slips/mistakes distinction is further elaborated by relating it to the Rasmussen SRK classification of performance discussed earlier. Slips can be described as being due to misapplied competence because they are examples of the highly skilled, well practiced activities that are characteristic of the skill-based mode. Mistakes, on the other hand, are largely confined to the rule and knowledge-based domains. 

Perform task analysis (see Chapter 4) and identify skill, rule or knowledge-based tasks or aspects of tasks (the flow diagram in Figure 2.7 may be used to assist in this classification). 

Perform task analysis and classify skill, rule or knowledge-based behaviors involved in the scenario being evaluated. 

The practical implications of this experiment are that when evaluating the effects of shift work due to circadian effects, the type of task being carried out by the worker must be taken into account. For example, skill-based tasks would be expected to exhibit the performance changes characteristic of low memory load tasks, whereas performance variations in knowledge-based tasks would be expected to follow the pattern of high memory load tasks. Performance on rule-based tasks may depend on the degree of frequency of use of the rules, which in turn may determine the memory load. If these results were confirmed by further process plant studies, it would have implications for when different types of operation (involving different levels of memory load) should be scheduled to reduce circadian rhythm effects and minimize errors. 

Detailed procedures will only be required in unusual situations where the usual rules of thumb do not apply and the worker is likely to be in the knowledge-based mode. In Chapter 4, and case study 3 in Chapter 7, a systematic framework for developing procedures, in which their format and content is based on a detailed analysis of the tasks to be performed and the normal skill level of the person who will perform the tasks, will be described. 

The term process control is often used when machine control is actually performed. As the knowledge base of the fundamentals of the molding process continues to grow,... 

---