In many environments, product yield is heavily influenced by equipment condition. Despite this fact, previous research has either focused on the issue of maintenance, ignoring the effect of equipment condition on yield, or has focused on the issue of production, omitting the possibility of actively changing the machine state. We formulate two MIP models that use of Markov chain for producing parameters need to process model of a single-stage multi parallel machines production system in which demand is supple have up and down bounds. We address a general lot-sizing problem with pricing. The objective is to maximise profit. The problem extends the general lot-sizing problem (GLSP). Model one is based on Myer GLT model and model two is based on Almada-lobo GLSP model. We extend almada-lobo GLSP model to involve non triangular setup condition. Both models are non cyclical and value-optimized maintenance planning and have maintenance micro periods. Models don’t interfere unemployment in depreciation. In this study, we propose that maintenance has intrinsic value and argue that existing cost-centric models ignore an important dimension of maintenance, namely its value, and in so doing, they can lead to sub-optimal maintenance strategies. The product yield depends on the equipment condition, which deteriorates over time. The objective is to choose simultaneously the equipment maintenance schedule as well as the demand and quantity to produce in a way that minimizes the sum of expected production, backorder, and holding costs. In this study introduced particle swarm optimization, simulated annealing and a heuristic-metaheuristic combined method as three meta-heuristics to solve the Integrated non cyclical maintenance planning and production planning in sensible time. Computational result annonce model two is better than model one in one machine problems. But in two or three machines problems model one was better than model two. In meta-heuristics, particle swarm optimization was not succeeded but simulated annealing and heuristic-metaheuristic combined method have good results, but heuristic-metaheuristic combined method have lower variance and solution time in compare by simulated annealing algorithm