Answers are grounded in this paper and cite their sources.
Today, due to the exponential growth of machine learning methods and computerization, the issue of reducing the gap between the capabilities of electronic computing machines and the data generated by operation production systems is increasingly relevant. Production systems usually operate under conditions of limited labor resource management. They face the problem of adequately assessing equipment efficiency, product quality, and process reliability. Existing data collection systems in such sectors are mainly focused on cost indicators collected at different intervals and on a cumulative basis, which does not allow for a direct assessment of equipment utilization, defect rate, specific resource consumption, and other technological parameters. The article proposes a system of technological metrics that ensures the transition from fragmented cost data to the physical parameters of the production process. An observation vector is introduced that takes into account equipment operating time and downtime, output and defect volumes, raw material consumption, energy consumption, failures, and recovery time. Based on this vector, metrics are developed in six groups: system utilization, flow and time, quality, resources, reliability, and energy. The key feature of the proposed system is the introduction of six correction coefficients that take into account the specific constraints of the considered class of production systems: operational constraints, employee qualifications, staffing of production lines, logistical constraints, equipment condition, and its level of maintenance. The modified metrics make it possible to separate “pure” technological characteristics from distortions caused by personnel, operational, and maintenance factors. The developed system can be used for comparative analysis of production areas in different types of organizations and industries, as well as for developing decision support information systems aimed at predicting failures and optimizing equipment utilization.
No takes yet. Share an insight, caveat, or question.
A 2026 study studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: