Concerning the problem of storage location assignment in automated warehouse, combined with the operational characteristics and security requirements of warehouse, a multi-objective model for automated stereoscopic warehouse storage location assignment was constructed, and an adaptive improved Simulated Annealing Genetic Algorithm (SAGA) based on Sigmoid curve for solving the model was proposed. Firstly, aiming at reducing the loading and unloading time of items, the distance between items in same group and the gravity center of shelf, a storage location optimization model was established. Then, in order to overcome the shortcomings of poor local search ability and being easily fall into local optimum of Genetic Algorithm (GA), the adaptive cross mutation operation based on Sigmoid curve and the reversed operation were introduced and fused with SAGA. Finally, the optimization, stability and convergence of the improved genetic SAGA were tested. The experimental results show that compared with Simulated Annealing (SA) algorithm, the proposed algorithm has the optimization degree of loading and unloading time of items increased by 37.7949 percentage points, the optimization degree of distance between items in same group improved by 58.4630 percentage points, and optimization degree of gravity center of shelf increased by 25.9275 percentage points, meanwhile the algorithm has better stability and convergence. It proves the effectiveness of the improved genetic SAGA to solve the problem. The algorithm can provide a decision method for automated warehouse storage location assignment optimization.

In order to solve the problem of slow convergence speed of reinforcement learning tasks with large state space, a priority-based parallel reinforcement learning task scheduling strategy was proposed. Firstly, the convergence of Q-learning in asynchronous parallel computing mode was proved. Secondly, complex problems were divided according to state spaces, then sub-problems and computing nodes were matched at the scheduling center, and each computing node completed the reinforcement learning tasks of sub-problems and gave feedback to the center to realize parallel reinforcement learning in the computer cluster. Finally, the experimental environment was built based on CloudSim, the parameters such as optimal step length, discount rate and sub-problem size were solved and the performance of the proposed strategy with different computing nodes was proved by solving practical problems. With 64 computing nodes, compared with round-robin scheduling and random scheduling, the efficiency of the proposed strategy was improved by 61% and 86% respectively. Experimental results show that the proposed scheduling strategy can effectively speed up the convergence under parallel computing, and it takes about 1.6×10 ⁵ s to get the optimal strategy for the control probelm with 1 million state space.

In order to improve the speed of data processing and the efficiency of software development, a temperature real-time monitoring system was devised based on Matlab Graphical User Interface (GUI). Serial port tool box in Matlab and Modbus communication protocol were used to link up SHIMADEN SRS13A thermostat to PC, and the real-time monitoring of the metal surface temperature in heating process was implemented. The interface of the system software was simple and the software had convenient operation with smaller memory footprint. Variety operating modes could be achieved by setting different parameters. The test results show that, the system runs rapidly and stably, and the temperature response curves with different parameter configuration settings were plotted promptly and accurately. The system's sampling interval was 1s and the temperature measurement accuracy was 0.1℃.