A predictive maintenance approach based on real-time internal parameter monitoring

Park, Chulsoon; Moon, Dug-Hee; Do, Namchul; Bae, Sung-Moon

doi:10.1007/s00170-015-7981-6

Cited by 38 publications

(16 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the first task, usually techniques from the fields of forecasting [5] and prognostics [6], [7] are applied, which can either rely on process parameter settings (static case) or process values recorded over time (dynamic case). Supervision of process parameters were proposed in [8] (there for a phone camera lens injection molding machine) and in [9] (there for plastic injection moulding). Both approaches rely on linear models and static mappings which do not integrate the time component (for respecting varying delays in input variables) and which cannot be (self-)adapted over time to address significant system dynamics properly.…”

Section: Motivation and State-of-the-artmentioning

confidence: 99%

Autonomous supervision and optimization of product quality in a multi-stage manufacturing process based on self-adaptive prediction models

Lughofer

Zăvoianu

Pollak

et al. 2019

Journal of Process Control

View full text Add to dashboard Cite

T. 2019. Autonomous supervision and optimization of product quality in a multi-stage manufacturing process based on self-adaptive prediction models. Journal of process control [online], 76, pages 27-45. Available from: https://doi. AbstractIn modern manufacturing facilities, there are basically two essential phases for assuring high production quality with low (or even zero) defects and waste in order to save costs for companies. The first phase concerns the early recognition of potentially arising problems in product quality, the second phase concerns proper reactions upon the recognition of such problems. In this paper, we address a holistic approach for handling both issues consecutively within a predictive maintenance framework at an on-line production system. Thereby, we address multi-stage functionality based on i)data-driven forecast models for (measure-able) product quality criteria (QCs) at a latter stage, which are established and executed through process values (and their time series trends) recorded at an early stage of production (describing its progress), and ii) process optimization cycles whose outputs are suggestions for proper reactions at an earlier stage in the case of forecasted downtrends or exceeds of allowed boundaries in product quality. The data-driven forecast models are established through a high-dimensional batch time-series modeling problem. In this, we employ a non-linear version of PLSR (partial least squares regression) by coupling PLS with generalized Takagi-Sugeno fuzzy systems (termed as PLS-Fuzzy). The models are able to self-adapt over time based on recursive parameters adaptation and rule evolution functionalities. Two concepts for increased flexibility during model updates are proposed, i.) a dynamic outweighing strategy of older samples with an adaptive update of the forgetting factor (steering forgetting intensity) and ii.) an incremental update of the latent variable space spanned by the directions (loading vectors) achieved through PLS; the whole model update approach is termed as SAFM-IF (Self-Adaptive Forecast Models with Increased Flexibility). Process optimization is achieved through multi-objective optimization using evolutionary techniques, where the (trained and updated) forecast models serve as surrogate models to guide the optimization process to Pareto fronts (containing solution candidates) with high quality. A new influence analysis between process values and QCsis suggested based on the PLS-fuzzy forecast models in order to reduce the dimensionality of the optimization space and thus to guarantee high(er) quality of solutions within a reasonable amount of time (→ better usage in on-line mode). The methodologies have been comprehensively evaluated on real on-line process data from a (micro-fluidic)chip production system, where the early stage comprises the injection molding process and the latter stage the bonding process. The results show remarkable performance in terms of low prediction errors of the PLS-Fuzzy forecast models (showing mostly lower errors t...

show abstract

Section: Motivation and State-of-the-artmentioning

confidence: 99%

Autonomous supervision and optimization of product quality in a multi-stage manufacturing process based on self-adaptive prediction models

Lughofer

Zăvoianu

Pollak

et al. 2019

Journal of Process Control

View full text Add to dashboard Cite

show abstract

“…Therefore, the practice of PdM strategies can result in an increase in global competitiveness through the elimination of unplanned maintenance operations, since PdM techniques help to identify and to determine the conditions of assets before they fail [22]. Further, PdM helps to monitor the condition of selected physical parameters within an operating machine by performing periodic or continuous real-time data collection [22] [23]. Thus, the collected data can be used to discover, with the help of PdM models, current or future deterioration of components and machines [25] [37].…”

Section: E Condition-based Maintenance (Cbm)mentioning

confidence: 99%

“…Within such architectures/ frameworks, the main idea of CBM is to detect the degradation level of machine components by collecting periodic or continuous real-time data with sensor technologies whereas. CBM strategies may involve Predictive Maintenance (PdM), wherein the current state of monitored equipment, along with historical data and relevant domain knowledge and models is employed to predict through statistical or machine learning models trends, behaviour patterns and correlations [11] [22] [23], and anticipate pending failures in advance to enhance the decision-making process for the maintenance activity [24]- [26]. PdM is becoming more and more a crucial approach among modern smart manufacturing industries, since global competitiveness is becoming everyday more challenging.…”

Section: Introductionmentioning

confidence: 99%

An Industry 4.0-Enabled Low Cost Predictive Maintenance Approach for SMEs

Sezer

Romero

Guedea-Elizalde

et al. 2018

2018 IEEE International Conference on Engineering, Technology and Innovation (ICE/ITMC)

View full text Add to dashboard Cite

This paper outlines the base concepts, materials and methods used to develop an Industry 4.0 architecture focused on predictive maintenance, while relying on low-cost principles to be affordable by Small Manufacturing Enterprises. The result of this research work was a low-cost, easy-to-develop cyber-physical system architecture that measures the temperature and vibration variables of a machining process in a Haas CNC turning centre, while storing such data in the cloud where Recursive Partitioning and Regression Tree model technique is run for predicting the rejection of machined parts based on a quality threshold. Machining quality is predicted based on temperature and/or vibration machining data and evaluated against average surface roughness of each machined part, demonstrating promising predictive accuracy.

show abstract

“…• Availability improvement -Predictive Maintenance [12], [13], [14] -Prognostics and Health Management [13], [15] • Performance improvement -Predictive Production Planning [16] -Predictive Manufacturing Control [17] • Quality improvement -Predictive Quality Control [18] -Control Chart Pattern Recognition [19], [20] These concepts provide theoretical foundations and require additional specifications for direct applicability. For this purpose, we propose a specified process model focusing on improving availability, since the costs for keeping a high availability represent 15 -60 % of total costs in manufacturing [21].…”

Section: Kdd In Manufacturingmentioning

confidence: 99%

How to Discover Knowledge for Improving Availability in the Manufacturing Domain?

Utz¹,

Neumann²,

Omid³

2018

Proceedings of the 51st Hawaii International Conference on System Sciences

View full text Add to dashboard Cite

This paper presents a specific process model for Knowledge Discovery in Databases (KDD) projects aiming at availability improvement in manufacturing. For this purpose, Overall Equipment Efficiency (OEE) is analyzed and used, since it is an approved approach to monitor and improve the degree of availability in manufacturing. To define the specific process model, we use the generic CRISP-DM reference model and conduct a mapping for availability improvement. We prove the applicability of our model in the context of a specific KDD project in a large enterprise in the manufacturing industry.

show abstract

A predictive maintenance approach based on real-time internal parameter monitoring

Cited by 38 publications

References 14 publications

Autonomous supervision and optimization of product quality in a multi-stage manufacturing process based on self-adaptive prediction models

Autonomous supervision and optimization of product quality in a multi-stage manufacturing process based on self-adaptive prediction models

An Industry 4.0-Enabled Low Cost Predictive Maintenance Approach for SMEs

How to Discover Knowledge for Improving Availability in the Manufacturing Domain?

Contact Info

Product

Resources

About