Deni Gustiawan

Bio-Inspired Computing-Based Multi-Objective Optimization For Sustainable Manufacturing In The Industry 4.0 Era

Introduction

Bio-inspired computing-based multi-objective optimization for sustainable manufacturing in the industry 4.0 era. Explore bio-inspired computing's role in sustainable manufacturing for Industry 4.0. Discover strong links between algorithms like PSO and energy efficiency, production, and environmental sustainability.

Abstract

This study aims to evaluate the contribution of bio-inspired computing towards the sustainability of manufacturing systems in the context of Industry 4.0. Using quantitative and design approaches, data were collected from 100 professional respondents in the manufacturing sector through questionnaires and structured interviews. Statistical analysis was performed using Pearson correlation, linear regression, t-test, and ANOVA with the help of SPSS software. The results showed a very strong and significant relationship between the use of bio-inspired algorithms, such as Particle Swarm Optimization (PSO), with energy efficiency (r = 0.872), production level (r = 0.723), and environmental sustainability (r = 0.790). Linear regression showed that the use of the technology explained 76.1% of the variability in energy efficiency (R² = 0.761; p < 0.001). The ANOVA results also showed significant differences between groups of technology users in terms of efficiency achievements. These findings indicate that bio-inspired computing can be an important strategy in digital transformation and more sustainable decision-making. This study contributes to developing multi-objective optimization theory and provides practical implications for industrial management in implementing adaptive and environmentally friendly technologies.

Review

This study presents a timely and relevant investigation into the transformative potential of bio-inspired computing for sustainable manufacturing within the context of Industry 4.0. The paper's aim to evaluate this contribution using a mixed-methods approach, combining quantitative surveys and structured interviews with 100 manufacturing professionals, is commendable. The reported statistical findings, indicating very strong and significant relationships between bio-inspired algorithms (e.g., PSO) and energy efficiency (r = 0.872), production level (r = 0.723), and environmental sustainability (r = 0.790), are particularly striking. The demonstration that this technology explains a substantial 76.1% of variability in energy efficiency (R² = 0.761; p < 0.001) suggests a profound impact, reinforcing the study's core message that bio-inspired computing is a critical enabler for digital transformation and sustainable decision-making. The research's strengths lie in its clear articulation of theoretical and practical contributions. Theoretically, it aims to advance multi-objective optimization theory, which is vital for complex industrial systems seeking to balance conflicting goals. Practically, the study offers significant implications for industrial management, advocating for the adoption of adaptive and environmentally friendly technologies. The robust statistical evidence, including high correlation coefficients and a strong R-squared value, lends credibility to the claims regarding the positive influence of bio-inspired computing. The explicit mention of specific algorithms like Particle Swarm Optimization grounds the conceptual framework in tangible technological applications, enhancing the study's relevance for practitioners. While the findings are compelling, the abstract leaves several methodological aspects requiring further clarification. The description of "quantitative and design approaches" is somewhat vague; a more precise characterization of the "design approach" would be beneficial. Crucially, the abstract needs to elaborate on how the "use" of complex bio-inspired algorithms was effectively measured through questionnaires and interviews with "professional respondents." Understanding if respondents were reporting actual system deployments, their perception of potential, or their knowledge of these technologies is vital for interpreting the strength of the reported relationships. Furthermore, details on the composition of the "100 professional respondents" (e.g., roles, expertise, industry sectors) and the definition of "groups of technology users" for the ANOVA analysis would enhance the study's generalizability and internal validity. Addressing these points would strengthen the overall rigor and impact of the research.

Full Text

Comments

You need to be logged in to post a comment.