3 results about "Batch process control" patented technology

The embodiment of the invention discloses a quality data evaluation method for a multi-variety small-batch manufacturing process, and the method comprises the steps: 1, employing a tolerance coefficient method as a data conversion algorithm, and obtaining a tolerance utilization rate of a single monitoring characteristic; step 2, performing process capability evaluation on each monitoring characteristic, combining standardized data of multiple monitoring characteristics for single monitoring characteristics capable of accumulating the total sample number N and single monitoring characteristics incapable of accumulating the total sample number N so as to perform control process capability evaluation, and performing process control in an auxiliary single-value monitoring mode; and step 3, evaluating the control process capability in the step 2, and formulating a quality state evaluation criterion of multi-variety small-batch process control. According to the technical scheme provided by the embodiment of the invention, the problems of low accuracy of quality evaluation, difficulty in establishing an effective control model and control limit and the like of a quality control mode of multi-variety and small-batch products are solved.

The application discloses a kind of reinforcement learning batch process control methods based on improved AC algorithm, it is related to the field of deep reinforcement learning and batch process control field.The method will be based on reinforcement learning method The batch process control is modeled as an optimal control problem on the basis of Markov decision process;Control action constraint is introduced in the reward function of reinforcement learning controller, the number of effective reward samples is increased to improve the learning rate of reinforcement learning controller, and the control cycle is shortened.Priority sampling method is introduced in the Actor-Critic algorithm of deep reinforcement learning, and a soft actor-critic algorithm with priority sampling is proposed to improve the sampling efficiency in the experience replay pool.The present application does not depend on prior knowledge and process model, and can realize model-free control of batch process.

To make it possible to realize batch process control that can achieve the target control performance.SOLUTION: A control support device according to one aspect of the present disclosure is a control support device that supports control of an object that executes a batch process, and includes: an acquisition unit that acquires a control quantity output from the object and a target value for the control quantity; a prediction unit that calculates a first control quantity prediction time series that represents a time series of a future control quantity later than the control quantity, based on the control quantity, a model that represents a relation between an operation quantity and a control quantity of the object, and an operation pattern that represents the time series of the operation quantity; a selection unit that selects a best operation pattern from the plurality of operation patterns, based on the first control quantity prediction time series and the target value; and a correction unit that selects a best corrected operation pattern from among one or more corrected operation patterns obtained by correcting the best operation pattern by one or more correction methods, based on the target value.SELECTED DRAWING: Figure 2