The estimation of machining cost is one of the most important factors in the industry of metal products machining. Many approaches exist for the pre-calculation of the cost of machining for metal made products; but these approaches vary in complexity, requirements and therefore in their own cost. In recent years, the need for a cost effective methodology that intend to estimate the cost of machining of a given product has become more and more obvious; especially when the product is produced in small quantities where the cost of the study has to be kept to a minimum. In job shop facilities, precise classical cost calculation is too difficult due to the varieties infiniteness of workpieces in terms of features and of dimensions. A common practice is to calculate the manufacturing cost of the workpiece as a function in the machining time; however, machining time calculation itself is a costly and lengthy operation. More recently, the parametric estimation method has been adapted as a shorter way for estimation machining cost and / or time. This method needs much experience within the field of manufacturing, which lays in the human factor namely the expert. The experts judgments involve two drawbacks, first, it requires a good deal of acquired information; second the judgments are subject to evolution with the experts development. In this paper, a new estimator based on the artificial neural network (ANN) is developed to replace both methods that relied either on the expert engineer or on the detailed process sheet for the assessment of machining time. The proposed tool uses the ANN to estimate the machining time using training cases, which are collected from real machining operations. The ANN input is a set of parameters related to the workpiece under consideration and to the specific cutting operation variables. The developed and trained ANN proved to be acceptably accurate in estimating the machining time of various case studies.

This study explores the long-run relationship among the environmental footprint (EnF), renewable energy consumption, energy use, industrial growth, and urbanization in Saudi Arabia from 1990 to 2023, employing the Autoregressive Distributed Lag (ARDL) model, alongside Fully Modified Ordinary Least Squares (FMOLS), Dynamic Ordinary Least Squares (DOLS), and Canonical Cointegrating Regression (CCR) for robustness checks. Results indicate a significant long-term relationship among the variables, with renewable energy adoption emerging as a crucial factor in reducing carbon emissions. The ARDL bounds test confirms the existence of cointegration, revealing the dynamic interplay among renewable energy, economic growth, and environmental sustainability. The findings show that renewable energy consumption significantly reduces the environmental footprint (CO₂ emissions), supporting Saudi Arabia’s Vision 2030 goals for economic diversification and sustainable development. However, industrial expansion, while critical for economic growth, still contributes to increased emissions, underscoring the need for further investment in clean technologies. The study also highlights the role of urbanization, which, while essential for development, poses challenges for environmental sustainability. Short-term dynamics, represented by the Error Correction Model, indicate a fast adjustment speed toward equilibrium, with deviations corrected by approximately 52% each period. The study offers valuable insights for policymakers aiming to balance industrial growth with environmental protection, emphasizing the need for strategic investments in renewable energy and energy efficiency. This research contributes to the understanding of energy–economy–environment interactions in oil-rich economies, providing a foundation for future studies to explore the impact of advanced technologies and policy interventions on sustainable development