Search results

The purpose of this investigation was to study the function mechanisms of a corrosion inhibitor package used for martensitic stainless steel tubulars in acid solution at high temperatures.

The inhibition performance was evaluated by means of an acid corrosion test at high temperature and high pressure, and the functional mechanism of the inhibitor package at different temperatures was investigated using polarization curve and electrochemical impedance spectroscopy measurements.

The results showed that the corrosion inhibitor package chosen for high-temperature and high-pressure gas well applications was very suitable for use with 13Cr super martensitic stainless steel. At lower temperatures, the function mechanism of the corrosion inhibitor package was characterized as a type of negative catalytic effect. As the temperature was increased, the effect of the intensifier in the package became more significant and the function mechanism changed to be the geometric covering effect type.

This study has the important practical value for guiding the oil field to conduct reasonable screening and using the acidizing corrosion inhibitor for martensite stainless steel tubulars.

This paper aims to automatically plan sequence for complex assembly products and improve assembly efficiency.

An assembly sequence planning system for workpieces (ASPW) based on deep reinforcement learning is proposed in this paper. However, there exist enormous challenges for using DRL to this problem due to the sparse reward and the lack of training environment. In this paper, a novel ASPW-DQN algorithm is proposed and a training platform is built to overcome these challenges.

The system can get a good decision-making result and a generalized model suitable for other assembly problems. The experiments conducted in Gazebo show good results and great potential of this approach.

The proposed ASPW-DQN unites the curriculum learning and parameter transfer, which can avoid the explosive growth of assembly relations and improve system efficiency. It is combined with realistic physics simulation engine Gazebo to provide required training environment. Additionally with the effect of deep neural networks, the result can be easily applied to other similar tasks.