Optimizing zinc electrowinning processes with current switching via Deep Deterministic Policy Gradient learning

Predicting cobalt ion concentration in hydrometallurgy zinc process using data decomposition and machine learning

Solid waste is one of the primary contributors to environmental pollution currently, it is crucial to enhance the prevention and control of solid waste pollution in environmental management. The effectiveness of the second stage of purification in the industrial zinc hydrometallurgy is determined by the concentration of cobalt ion. Manual testing and monitoring of cobalt ion concentration are time consuming and costly, and prone to delays, which can result in discharge of cobalt ion concentration that does not meet the standards, leading to water pollution. Additionally, over-addition of zinc powder leads to a waste of resources, increasing the production cost of the company. Here, this work proposes a hybrid prediction model that combines the advantages of data decomposition and machine learning algorithms to predict the metal cobalt ion concentration in the effluent solution of a section of zinc hydrometallurgy refining purification in factory A. According to the different types of experiments, ablation experiments and contrast experiments are designed in this work under the same training and test data were used in the modeling process. Analytic and experimental results show that the proposed hybrid prediction model has the smallest error and the best fit between the actual and predicted values of cobalt ion concentration, and the appropriate graphs were finally selected for quantitative metrics analysis. The root mean square error was reduced by 4.2 %-73.9 %, the mean absolute error by 7.1 %-93.4 %, the mean percentage error by 7.7 %-86.7 % and the coefficient of determination by 1.3 %-134.6 %. The hybrid prediction model not only avoided the pollution of water resources by the cobalt ion concentration discharged in the purification, which is also of practical significance for the technicians to control the input quantity of zinc powder according to the prediction data in time and reduce the waste of resources.

Boosting effect of ultrasonication on the oxygen evolution reaction during zinc electrowinning

In this study, the electrochemical and anodic behaviors of Pb-Ag anodes during ultrasound-assisted zinc electrowinning were meticulously examined. The oxygen evolution reaction (OER) occurring at the Pb-Ag anodes in a 150 g L-1 aqueous H2SO4 solution was studied in the absence (silent) and presence of ultrasonication (40 kHz, 100 % acoustic amplitude). Electrochemical impedance spectroscopy (EIS), cyclic voltammetry (CV), linear sweep voltammetry (LSV), and zinc electrowinning tests were conducted to analyze the electrochemical behavior of the Pb-Ag anodes during zinc electrowinning. Compared with that under silent conditions, the OER was greatly enhanced under ultrasonic conditions, and the overpotential reduction was found to be 108 mV at 35 °C at a current density of 50 mA cm-2. A significant reduction in the bath voltage was achieved during ultrasound-assisted prolonged zinc electrowinning, with a difference of approximately 50 mV compared with that of the control. The integration of ultrasonic technology into the realm of zinc electrowinning leverages the physical and chemical effects of ultrasonication to significantly improve the efficiency and kinetics of the OER. Smaller PbO2 grains and a larger silver exposure area appeared on the Pb-Ag plate surface during ultrasonic-assisted electrowinning, which is beneficial for the OER chemically. The generated oxygen bubbles merged more rapidly and detached from the electrode surface with greater alacrity under ultrasonication conditions, which reinforced the OER in terms of mass transfer kinetics. Furthermore, more fine zinc products can be obtained during ultrasound-assisted zinc electrowinning. By harnessing the power of ultrasonic technology, more sustainable and cost-effective zinc electrowinning can be achieved.

Integrated Optimal Control for Electrolyte Temperature With Temporal Causal Network and Reinforcement Learning

The electrowinning process is a critical operation in nonferrous hydrometallurgy and consumes large quantities of power consumption. Current efficiency is an important process index related to power consumption, and it is vital to operate the electrolyte temperature close to the optimum point to ensure high current efficiency. However, the optimal control of electrolyte temperature faces the following challenges. First, the temporal causal relationship between process variables and current efficiency makes it difficult to estimate the current efficiency accurately and set the optimal electrolyte temperature. Second, the substantial fluctuation of influencing variables of electrolyte temperature leads to difficulty in maintaining the electrolyte temperature close to the optimum point. Third, due to the complex mechanism, building a dynamic electrowinning process model is intractable. Hence, it is a problem of index optimal control in the multivariable fluctuation scenario without process modeling. To get around this issue, an integrated optimal control method based on temporal causal network and reinforcement learning (RL) is proposed. First, the working conditions are divided and the temporal causal network is used to estimate current efficiency accurately to solve the optimal electrolyte temperature under multiple working conditions. Then, an RL controller is established under each working condition, and the optimal electrolyte temperature is placed into the controller's reward function to assist in control strategy learning. An experiment case study of the zinc electrowinning process is provided to verify the effectiveness of the proposed method and to show that it can stabilize the electrolyte temperature within the optimal range without modeling.

An enhanced deep deterministic policy gradient algorithm for intelligent control of robotic arms

Aiming at the poor robustness and adaptability of traditional control methods for different situations, the deep deterministic policy gradient (DDPG) algorithm is improved by designing a hybrid function that includes different rewards superimposed on each other. In addition, the experience replay mechanism of DDPG is also improved by combining priority sampling and uniform sampling to accelerate the DDPG's convergence. Finally, it is verified in the simulation environment that the improved DDPG algorithm can achieve accurate control of the robot arm motion. The experimental results show that the improved DDPG algorithm can converge in a shorter time, and the average success rate in the robotic arm end-reaching task is as high as 91.27%. Compared with the original DDPG algorithm, it has more robust environmental adaptability.

The Multi-Objective Optimization of Powertrain Design and Energy Management Strategy for Fuel Cell–Battery Electric Vehicle

Considering the limited driving range and inconvenient energy replenishment way of battery electric vehicle, fuel cell electric vehicles (FC EVs) are taken as a promising way to meet the requirements for long-distance low-carbon driving. However, due to the limitation of FC power ability, a battery is usually adopted as the supplement power source to fill the gap between the requirement of driving and the serviceability of FC. In consequence, energy management is essential and crucial to an efficient power flow to the wheel. In this paper, a self-optimizing power matching strategy is proposed, considering the energy efficiency and battery degradation, via implementing a deep deterministic policy gradient. Based on the proposed strategy, less energy consumption and longer FC and battery life can be expected in FC EV powertrain with optimal hybridization degree.