An integrated ANN-EMO approach to reduce the risk of occupational health hazards

Workers in labor-intensive units, in general, maximize their earnings by subjecting themselves to high risk of occupational health hazards (RoOHH) due to economic reasons. We present an intelligent system integrating artificial neural network (ANN) and evolutionary multiobjective optimisation (EMO) to tackle this problem, which has received scant attention in the literature. A brick manufacturing unit in India is chosen as case study to demonstrate the working of proposed system. Firing is assessed to be the most severe job among others using an interview method. A job-combination approach is devised which allows firing workers to perform another job (loading/covering/molding) along with firing. The second job not only reduces their exposure to high temperature zone but also helps to compensate for reduced earnings. RoOHH is measured using a risk assessment score (RAS). ANN models the psychological responses of workers in terms of RAS, and facilitates the evaluation of a fitness function of EMO. EMO searches for optimal work schedules in a job-combination to minimize RAS and maximize earnings simultaneously. 1 Introduction Brick manufacturing (BM) in India is labor intensive and comprises the following major jobs − molding the raw bricks, loading molded bricks to kiln using a pushcart or a pony-cart, stacking molded bricks into the kiln in a particular way, spreading clay sand over the stacks uniformly for superior baking of bricks, firing the kiln that includes pouring the coal into the kiln from the covered holes at the top of the kiln at required intervals and monitoring the fire, and finally unloading the baked bricks from the kiln; we term these processes respectively as molding, loading, stacking, covering, firing and unloading, for ready references in this paper.