An integrated approach to improving manufacturing KPIs using lean tools, multi-criteria decision-making, and neural network analysis

Lean manufacturing principles are extensively adopted by organizations seeking a competitive advantage. Selecting the appropriate lean tools tailored to specific manufacturing environments is crucial. However, current selection models often focus on objective criteria, which may not fully reflect the specific needs of industries. This paper aims to develop an integrated model for lean tool selection to improve key manufacturing performance indicators, including process time (C1), cost efficiency (C2), defect reduction (C3), safety (C4), and quality enhancement (C5). The proposed approach integrates three methodologies: Weighted Aggregated Sum Product Assessment (WASPAS), Technique for Order Performance by Similarity to the Ideal Solution (TOPSIS), and Multi-Objective Optimization by Ratio Analysis (MOORA). Decision-maker input within the organization guides the ranking of lean tools. The BORDA method is applied for collective score evaluation to address inconsistencies in decision-maker rating scales. Furthermore, artificial neural networks (ANNs) are employed to improve computational efficiency. These ANNs are designed, trained, and simulated using MATLAB software, effectively resolving the challenges posed by manual calculations. The resulting model significantly advances lean tool selection, providing a more tailored and computationally efficient approach for enhancing manufacturing performance.