Deep learning-driven particle swarm optimisation for additive manufacturing energy optimisation

Abstract

The additive manufacturing (AM) process is characterised as a high energy-consuming process, which has a significant impact on the environment and sustainability. The topic of AM energy consumption modelling, prediction, and optimisation has then become a research focus in both industry and academia. This issue involves many relevant features, such as material condition, process operation, part and process design, working environment, and so on. While existing studies reveal that AM energy consumption modelling largely depends on the design-relevant features in practice, it has not been given sufficient attention. Therefore, in this study, design-relevant features are firstly examined with respect to energy modelling. These features are typically determined by part designers and process operators before production. The AM energy consumption knowledge, hidden in the design-relevant features, is exploited for prediction modelling through a design-relevant data analytics approach. Based on the new modelling approach, a novel deep learning-driven particle swarm optimisation (DLD-PSO) method is proposed to optimise the energy utility. Deep learning is introduced to address several issues, in terms of increasing the search speed and enhancing the global best of PSO. Finally, using the design-relevant data collected from a real-world AM system in production, a case study is presented to validate the proposed modelling approach, and the results reveal its merits. Meanwhile, optimisation has also been carried out to guide part designers and process operators to revise their designs and decisions in order to reduce the energy consumption of the designated AM system under study.

Feature-level Data Fusion for Energy Consumption Analytics in Additive Manufacturing

“…This reveals that the attributes of the working environment, e.g., chamber temperature and gas flow, are closely correlated with the thermal history of the substrate and AM energy consumption. In the scope of big data and IoT applications, Qin et al [10] proposed a data analytics model for predicting AM energy consumption based on artificial neural networks. The prediction model integrates data from design-relevant, process operation, working environment, and material, which tended to cover the entire data generation stages during an AM process.…”

“…Most researchers have been focusing on investigations of the relationships between processing attributes, material properties, and energy consumption, while the impacts of design-relevant and working environmental attributes have not been paid enough attention to. Several factors related to design models and working environment, such as the volume of part envelopes [8], part geometry [9], platform temperature [10], have been identified to have strong relationships with energy consumption in AM processes. However, to comprehensively analyze and understand the impacts of these correlated factors is still challenging.…”

Autonomous resource allocation of smart workshop for cloud machining orders

“…Di and Wang (2013) proposed a fully distributed, VM-multiplexing resource allocation scheme to manage decentralized resources. Qin et al (2020) proposed a novel deep learningdriven particle swarm optimization (DLD-PSO) method to optimize the energy utility. Kumar and Saxena (2015) proposed a demand-based preferential resource allocation technique that designed a market-driven auction mechanism to identify users for resource allocation based on their payment capacities.…”

Event-Driven Interoperable Manufacturing Ecosystem for Energy Consumption Monitoring

“…The results are quite promising, even though the scenarios have only been done offline, i.e., separately from the running system. Using learning techniques, an approach to reduce energy consumption in additive manufacturing is presented in [18]. This approach focuses essentially on optimizing the product's design to reduce consumption during its production.…”