One of the common problems of organizations with turn-key projects is the high scrap rate. There exist such traditional methods as Lean Six Sigma (LSS) and DMAIC tools that analyze causes and suggest solutions. New emerging intelligent technologies should influence these methods and tools as they affect many areas of our life. The purpose of this paper is to present the innovative Small Mixed Batches (SMB). The standard set of LSS tools is extended by intelligent technologies such as artificial neural networks (ANN) and machine learning. The proposed method uses the data-driven quality strategy to improve the turning process at the bakery machine manufacturer. The case study shows the step-by-step DMAIC procedure of critical to quality (CTQ) characteristics improvement. Findings from the data analysis lead to a change of measurement instrument, training of operators, and lathe machine set-up correction. However, the scrap rate did not decrease significantly. Therefore the advanced mathematical model based on ANN was built. This model predicts the CTQ characteristics from the inspection certificate of the input material. The prediction model is a part of a newly designed process control scheme using machine learning algorithms to reduce the variability even for input material with different properties from new suppliers. Further research will be focused on the validation of the proposed control scheme, and acquired experiences will be used to support business sustainability.

This paper presents optimisation of a measuring probe path in inspecting the prismatic parts on a CMM. The optimisation model is based on: (i) the mathematical model that establishes an initial collision-free path presented by a set of points, and (ii) the solution of Travelling Salesman Problem (TSP) obtained with Ant Colony Optimisation (ACO). In order to solve TSP, an ACO algorithm that aims to find the shortest path of ant colony movement (i.e. the optimised path) is applied. Then, the optimised path is compared with the measuring path obtained with online programming on CMM ZEISS UMM500 and with the measuring path obtained in the CMM inspection module of Pro/ENGINEER^®software. The results of comparing the optimised path with the other two generated paths show that the optimised path is at least 20% shorter than the path obtained by on-line programming on CMM ZEISS UMM500, and at least 10% shorter than the path obtained by using the CMM module in Pro/ENGINEER^®.