The analysis of offshore fishing capacity is of great significance and practical value to the sustainable utilization and conservation of marine fishery resources. Based on the 2004–2020 China Fishery Statistical Yearbook, data envelopment analysis (DEA) was applied for measuring fishing capacity using a number of fishing vessels, total power, total tonnage, and the number of professional fishermen as the input measures and the annual catch as the output measure. Capacity utilization had a calculated range from 80.7 to 100%, and its average is 93.5%. In the first four years of 2003–2007, the excess investment rate of fishing vessels, total tonnage, total power, and fishermen was low (<5%). There was a consistent sharp upward trend in 2007, a gradual downward trend from 2007 to 2015, and an upward trend after reaching a low point in 2015, with the highest gross tonnage of fishing vessels reaching 25.5%. Four regression models that incorporate machine learning algorithms are used, including Lasso, Ridge, KNN, and Polynomial Features. The goodness of fit for the four models was used as the evaluation index, and the offshore annual catch based on the evaluation index was proposed. The forecasting annual catch of the polynomial model can reach 0.98. Furthermore, a comparative simulation of the DEA incorporating the polynomial model was carried out. The results show that DEA can evaluate input factors under the conditions of a given range, and the polynomial model has more advantages in forecasting annual catches. Furthermore, the combined application of DEA and polynomial model was used to analyze and discuss the management policies of China’s offshore fishery, which can provide help and reference for future management.

Due to unpredictable global competition and high-frequency market changes, to stay competitive, manufacturers must possess some new and advanced manufacturing systems with reconfigurability in order to meet all these changes rapidly and cost-effectively. These manufacturing systems should adjust their production functionality and capacity in time by changing system configurations; hence, it is very important to analyze the impact of different configuration on manufacturing system performance. A systematic analysis method is needed to evaluate overall performance based on system hierarchy process. By using manufacturing system engineering theory, Boolean algebra, probability statistics theory, stream of variation methodology and so on, the impact of system configuration on performance is studied with respect to reliability, scalability, convertibility, quality, productivity and cost. A case study shows some preliminary conclusions for the performance analysis of different configurations of manufacturing system. These performance factors have been developed an integrated performance evaluation model as the criterion to select manufacturing system configuration, the elementary flow frame of this model is presented.