Sensors (May 2023)

Optimization Experiment of Production Processes Using a Dynamic Decision Support Method: A Solution to Complex Problems in Industrial Manufacturing for Small and Medium-Sized Enterprises

  • Simona Skėrė,
  • Aušra Žvironienė,
  • Kazimieras Juzėnas,
  • Stasė Petraitienė

DOI
https://doi.org/10.3390/s23094498
Journal volume & issue
Vol. 23, no. 9
p. 4498

Abstract

Read online

In the industrial sector, production processes are continuously evolving, but issues and delays in production are still commonplace. Complex problems often require input from production managers or experts even though Industry 4.0 provides advanced technological solutions. Small and medium-sized enterprises (SMEs) normally rely more on expert opinion since they face difficulties implementing the newest and most advanced Industry 4.0 technologies. This reliance on human expertise can cause delays in the production processes, ultimately, impacting the efficiency and profitability of the enterprise. As SMEs are mostly niche markets and produce small batches, dynamics in production operations and the need for quick responses cannot be avoided. To address these issues, a decision support method for dynamic production planning (DSM DPP) was developed to optimize the production processes. This method involves the use of algorithms and programming in Matlab to create a decision support module that provides solutions to complex problems in real-time. The aim of this method is to combine not only technical but also human factors to efficiently optimize dynamic production planning. It is hardly noticeable in other methods the involvement of human factors such as skills of operations, speed of working, or salary size. The method itself is based on real-time data so examples of the required I 4.0 technologies for production sites are described in this article—Industrial Internet of Things, blockchains, sensors, etc. Each technology is presented with examples of usage and the requirement for it. Moreover, to confirm the effectiveness of this method, tests were made with real data that were acquired from a metal processing company in Lithuania. The method was tested with existing production orders, and found to be universal, making it adaptable to different production settings. This study presents a practical solution to complex problems in industrial settings and demonstrates the potential for DSM DPP to improve production processes while checking the latest data from production sites that are conducted through cloud systems, sensors, IoT, etc. The implementation of this method in SMEs could result in significant improvements in production efficiency, ultimately, leading to increased profitability.

Keywords