An economic expert system on the personal computer to support sow replacement decisions.

Abstract An expert system (ES) was designed on the personal computer for the economic optimization of sow replacement decisions. The system focuses on the qualitative characteristics of a sow, including lameness and leg weakness, mothering characteristics and mammary quality. The ES is coupled with an existing stochastic dynamic programming model (DP model), which determines the economically optimal replacement policy based on productive and reproductive sow performance. The reasoning process of the ES is focused on three major elements: (1) clinical sow deviations; (2) deviations in the number of pigs weaned per litter, in relation to (3) deviations in the uniformity of the litter. Deviations of the first type always result in advice to replace the sow with a replacement gilt. After deviations of the second and/or third type have been found, they are weighted economically by the ES. Using the results of the DP model, the ES calculates an economic index which makes it possible to rank sows within the herd on future profitability. Therefore, the index can be used as a management guide in culling decisions. The method of acquiring the knowledge (rules of thumb, heuristics) for the ES involved direct interviews with a domain expert, in which real and example problems have been used. Formal validation results indicate a high correspondence between the system's ranking of 30 blind test scenarios with the rankings provided by both the domain expert and a second expert.