Han Pang

The significant fluctuations in the liquid level of the two-stage tandem separators on FPSOs result in low oil and gas separation efficiency. To address this issue, an improved adaptive smoothing factor weight deep deterministic policy gradient (ASFW-DDPG) control algorithm is proposed to mitigate the separator liquid level fluctuations. The adaptive smoothing factor weight function and the reward function are meticulously designed to improve convergence speed and stability. A two-stage tandem separator liquid level control network, based on the ASFW-DDPG online control algorithm, is developed. Simulation experiments with the ASFW-DDPG algorithm are carried out using monitoring data from the separators on FPSOs. These simulations demonstrate that the learning efficiency of the ASFW-DDPG algorithm is 200% higher than that of the traditional DDPG algorithm. The primary and secondary separator liquid levels stabilize at the set values within 2.4 seconds and 1.8 seconds, while the PID and traditional DDPG algorithms exhibit slight fluctuations in liquid level. The results suggest that the ASFW-DDPG algorithm exhibits superior convergence speed and stability.

With the offshore oil–gas fields entering a decline phase, the high-efficiency separation of oil–gas–water mixtures becomes a significant challenge. As essential equipment for separation, the three-phase separators play a key role in offshore oil–gas production. However, level control is critical in the operation of three-phase gravity separators on offshore facilities, as it directly affects the efficacy and safety of the separation process. This paper introduces an advanced deep deterministic policy gradient with the adaptive learning rate weights (ALRW-DDPG) control algorithm, which improves the convergence and stability of the conventional DDPG algorithm. An adaptive learning rate weight function has been meticulously designed, and an ALRW-DDPG algorithm network has been constructed to simulate three-phase separator liquid level control. The effectiveness of the ALRW-DDPG algorithm is subsequently validated through simulation experiments. The results show that the ALRW-DDPG algorithm achieves a 15.38% improvement in convergence rate compared to the traditional DDPG algorithm, and the control error is significantly smaller than that of PID and DDPG algorithms.

With the offshore oil-gas fields entering decline phase, high-efficiency separation of oil-gas-water mixtures becomes a significant challenge. As essential equipment for separation, the three-phase separators play a key role in Offshore Oil-Gas production. However, level control is critical in the operation of three-phase gravity separators on offshore facilities, as it directly affects the efficacy and safety of the separation process. This paper introduces an advanced deep deterministic policy gradient with adaptive learning rate weights (ALRW-DDPG) control algorithm, which improves the convergence and stability of the conventional DDPG algorithm. An adaptive learning rate weight function is meticulously designed, and an ALRW-DDPG algorithm network is constructed for simulating three-phase separator liquid level control. The effectiveness of the ALRW-DDPG algorithm is subsequently validated through simulation experiments. The results show that the ALRW-DDPG algorithm achieves a 15.38% improvement in convergence rate compared to the traditional DDPG algorithm, and the control error is significantly smaller than that of PID and DDPG algorithms.

Fracturing truck is an important part of all electric drive shale gas stimulation system. As the main bearing structure of fracturing truck, the frame bears complex loads, and its fatigue life determines reliability of the system. Taking the frame of 7000hp full electric drive fracturing truck as the research object, this paper establishes the finite element simulation model of the frame, determines the load spectrum of the frame, analyzes the transient stress of the frame, and then calculates the fatigue life of the frame by using S-N curve analysis method and fatigue cumulative damage theory.

Purpose: – One of the major shortcomings in the data process of the traditional wheel force transducers (WFTs) is the theoretical errors of initial value determination. A new method to identify the initial values of the WFT for the solution of this problem is proposed in this paper. The paper aims to discuss these issues. Design/methodology/approach: – With this method, the initial values can be obtained by equations which are established based on multiple stops on horizontal road. Findings: – The calibration and contrast tests on the MTS calibration platform illustrate the better performance with the new method. Moreover, the real vehicle test confirms the effectiveness in practice. Originality/value: – The test results show that the new method of initial calibration has an advanced performance compared to the traditional one. In addition, it is effective in the brake test with a real vehicle.