Real-Time Parameter Identification for Forging Machine Using Reinforcement Learning

Zhang, Dapeng; Du, Liang

doi:10.3390/pr9101848

Cited by 5 publications

(3 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, there are first activities in forging as well. Zhang et al (2021) used RL to identify optimal parameter of a mechanism model in real-time without historical data. This allows an accurate online simulation of the forging process.…”

Section: Machine Learning and Its Applications In Metal Formingmentioning

confidence: 99%

Coupling of an analytical rolling model and reinforcement learning to design pass schedules: towards properties controlled hot rolling

2023

View full text Add to dashboard Cite

Rolling is a well-established forming process employed in many industrial sectors. Although highly optimized, process disruptions can still lead to undesired final mechanical properties. This paper demonstrates advances in pass schedule design based on reinforcement learning and analytical rolling models to guarantee sound product quality. Integrating an established physical strengthening model into an analytical rolling model allows tracking the microstructure evolution throughout the process, and furthermore the prediction of the yield strength and ultimate tensile strength of the rolled sheet. The trained reinforcement learning algorithm Deep Deterministic Policy Gradient (DDPG) automatically proposes pass schedules by drawing upon established scheduling rules combined with novel rule sets to maximize the final mechanical properties. The designed pass schedule is trialed using a laboratory rolling mill while the predicted properties are confirmed using micrographs and materials testing. Due to its fast calculation time, prospectively this technique can be extended to also account for significant process disruptions such as longer inter-pass times by adapting the pass schedule online to still reach the desired mechanical properties and avoid scrapping of the material.

show abstract

Section: Machine Learning and Its Applications In Metal Formingmentioning

confidence: 99%

Coupling of an analytical rolling model and reinforcement learning to design pass schedules: towards properties controlled hot rolling

2023

View full text Add to dashboard Cite

show abstract

“…This comprises studies that measure the environmental footprint of EDM activities before and after using the integrated strategy. This area of study hopes to aid the larger mission of encouraging ecologically responsible production methods by giving proof of the positive influence on sustainability [25]. There is substantial potential in combining mathematical programming with machine learning to advance Electrical Discharge Machining.…”

Section: Theme 3: Sustainability and Environmental Impact Of Enhanced...mentioning

confidence: 99%

Integrating Machine Learning and Mathematical Programming for Optimisation of Electric Discharge of Machining Techniques

Ritu Gupta

2023

IJRITCC

View full text Add to dashboard Cite

This study explores the combination of machine guidance and several developing approaches to enhance both precision and effectiveness during Electricity-discharged Machining (EDM) business operations. The studies on quality control, energy efficiency, sustainable development, mathematical modelling within EDM optimization, and machine learning applications in EDM optimisation are all examined in this study. It highlights significant gaps in scientific knowledge, providing a pathway for the development of state-of-the-art EDM methods. The outcomes show that material decrease, energy efficiency, along EDM technique optimisation can all be enhanced. This study offers valuable information for future research within the field and contributes to the ongoing conversation about advanced manufacturing techniques. This project intends to revolutionise EDM by merging mathematical programming and machine learning. Three primary topics are investigated machining parameter optimisation, efficiency improvement using machine learning and environmental effect assessment. The goals of the study are met by using the deductive method, which gives a formal setting in which to examine hypotheses. Descriptive research designs allow for in-depth analyses of previously published works, mathematical models and automated learning programs. Finding commonalities and trends in qualitative data is the goal of the thematic data analysis technique. The results of this study provide useful resources, standards and sustainable perspectives for enhancing EDM procedures in manufacturing settings.

show abstract

“…On the other hand, among the great number of machine learning applications [9][10][11], time series analysis can be used for clustering [12,13], classification [14], query by content [15], anomaly detection, as well as forecasting [16,17], which is the branch of the current study. Moreover, given the increasing availability of data and computing power in recent years, deep learning has become a critical component of the new generation of time series forecasting models.…”

Section: Introductionmentioning

confidence: 99%

Intelligent Model for Power Cells State of Charge Forecasting in EV

et al. 2022

View full text Add to dashboard Cite

In electric vehicles and mobile electronic devices, batteries are one of the most critical components. They work by using electrochemical reactions that have been thoroughly investigated to identify their behavior and characteristics at each operating point. One of the fascinating aspects of batteries is their complicated behavior. The type of power cell reviewed in this study is a Lithium Iron Phosphate LiFePO4 (LFP). The goal of this study is to develop an intelligent model that can forecast the power cell State of Charge (SOC). The dataset used to create the model comprises all the operating points measured from an actual system during a capacity confirmation test. Regression approaches based on Deep Learning (DL), such as Long Short-Term Memory networks (LSTM), were evaluated under different model configurations and forecasting horizons.

show abstract

Real-Time Parameter Identification for Forging Machine Using Reinforcement Learning

Cited by 5 publications

References 33 publications

Coupling of an analytical rolling model and reinforcement learning to design pass schedules: towards properties controlled hot rolling

Coupling of an analytical rolling model and reinforcement learning to design pass schedules: towards properties controlled hot rolling

Integrating Machine Learning and Mathematical Programming for Optimisation of Electric Discharge of Machining Techniques

Intelligent Model for Power Cells State of Charge Forecasting in EV

Contact Info

Product

Resources

About