Production trend identification and forecast for shop-floor business intelligence

Abstract

<p>The paper introduces a methodology to define production trend classes and also the results to serve with trend prognosis in a given manufacturing situation. The prognosis is valid for one, selected production measure (e.g. a quality dimension of one product, like diameters, angles, surface roughness, pressure, basis position, etc.) but the applied model takes into account the past values of many other, related production data collected typically on the shop-floor, too. Consequently, it is useful in batch or (customized) mass production environments. The proposed solution is applicable to realize production control inside the tolerance limits to proactively avoid the production process going outside from the given upper and lower tolerance limits.</p><p>The solution was developed and validated on real data collected on the shop-floor; the paper also summarizes the validated application results of the proposed methodology.</p>

Decision tree predictive model for dimensional control of side flange bearing housings

“…In [12], a manufacturing process optimization approach was demonstrated by applying a production trend prediction model. First, the developed solution collects data from the factory oor.…”

On-line anomaly detection with advanced independent component analysis of multi-variate residual signals from causal relation networks

“…In todays large-scale manufacturing systems or factories of the future, the supervision of the whole production chain for approaching zero defect manufacturing [1] and realizing predictive maintenance [2] with high performance can be established through the usage of data-driven anomaly and fault detection methods [3] [4]. Thereby, an utmost goal is to detect any possible arising fault (problem) in the system at an early stage [5] [6] based on the trend or course of the current production process [7] [8] in order to take action to avoid severe failures and/or damages. Faults can be of different nature such as downtrends in the quality of the production reaching to defective production parts/items inducing significant waste and thus costs for the company [9] and/or even annoying customers (as was the case in our use case, see Section 5), or machine/tool failures [10] reaching to system dropouts increasing risks for operators and enlarging production system down-times resulting in losses for the company [11].…”