Abstract: Aiming at the capacitated Lot-sizing and scheduling problem (CLSP) with limited ability in the job shop environment, a hybrid optimization algorithm based on the improved honey badger algorithm (IHBA) and neural network is proposed to cope with the uncertainty of demand and processing time. Firstly, considering demand and processing time are affected by uncertainty, a deterministic model based on satisfiability modulo theories is constructed, two elastic parameters of safety stock and safety relaxation are introduced, build a robust optimization model under uncertain requirements. Secondly, a hybrid algorithm based on IHBA and neural network is proposed, which uses chaos theory to generate pseudo-random values, estimate the nominal value and change amplitude of safety parameters, and improve the algorithm speed. Finally, an example is carried out, and the results show that the algorithm proposed in this paper can optimize the scheduling criterion, reduce the optimality gap, effectively solve the problem of extended order permission, and reduce the average shortage cost.