Total production time (TPT) is typically an essential component for calculating the total production cost (TPC) in production operations. In job shop facilities, the precise classical calculations of the TPT of a single workpiece or a small batch are too complicated and expensive because of the large variations. The typical solution of this problem is to rely on experts estimations. In this paper, a new estimation method based on an artificial neural network (ANN) is introduced for the assessment of the TPT. This estimator relies on feeding the ANN with a set of workpiece and cutting operation parameters. The TPT outputs from the estimator are compared with collected experts’ estimations, both with reference to the referential accurate operations sheet values. The results of the proposed approach are found to be closer to the referential values by a significant percentage. The developed model is versatile, simple and has shorter execution time.

总生产时间 (TPT) 通常是计算生产操作中的总生产成本 (TPC) 的重要组成部分。在加工车间设施中，单个工件或小批量的 TPT 的精确经典计算过于复杂和昂贵，因为变化很大。这个问题的典型解决方案是依靠专家估计。在本文中，引入了一种基于人工神经网络 (ANN) 的新估计方法来评估 TPT。该估算器依赖于向 ANN 提供一组工件和切割操作参数。估计器的 TPT 输出与收集的专家估计值进行比较，两者均参考参考准确操作表值。发现所提出方法的结果在很大程度上更接近于参考值。开发的模型通用、简单且执行时间更短。