A review of machine learning for the optimization of production processes

Weichert, Dorina; Link, Patrick; Stoll, Anke; Rüping, Stefan; Ihlenfeldt, Steffen; Wrobel, Stefan

doi:10.1007/s00170-019-03988-5

Cited by 223 publications

(107 citation statements)

References 115 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The study in Reference [27] examined several works on ML-based optimization in the areas of product quality and process improvement. The interdependencies among the used data, the amount of data, the ML algorithms, the adopted optimisers and the specific production problems were discussed, concluding that often, their correlation is not carefully investigated, thus leading to highly complex models, being trained with insufficient amounts of data, exhibiting overfitting and low interpretability.…”

Section: Previous Survey Workmentioning

confidence: 99%

Tackling Faults in the Industry 4.0 Era—A Survey of Machine-Learning Solutions and Key Aspects

Angelopoulos

Michailidis

Νομικός

et al. 2019

Sensors

220

View full text Add to dashboard Cite

The recent advancements in the fields of artificial intelligence (AI) and machine learning (ML) have affected several research fields, leading to improvements that could not have been possible with conventional optimization techniques. Among the sectors where AI/ML enables a plethora of opportunities, industrial manufacturing can expect significant gains from the increased process automation. At the same time, the introduction of the Industrial Internet of Things (IIoT), providing improved wireless connectivity for real-time manufacturing data collection and processing, has resulted in the culmination of the fourth industrial revolution, also known as Industry 4.0. In this survey, we focus on the vital processes of fault detection, prediction and prevention in Industry 4.0 and present recent developments in ML-based solutions. We start by examining various proposed cloud/fog/edge architectures, highlighting their importance for acquiring manufacturing data in order to train the ML algorithms. In addition, as faults might also occur from sources beyond machine degradation, the potential of ML in safeguarding cyber-security is thoroughly discussed. Moreover, a major concern in the Industry 4.0 ecosystem is the role of human operators and workers. Towards this end, a detailed overview of ML-based human–machine interaction techniques is provided, allowing humans to be in-the-loop of the manufacturing processes in a symbiotic manner with minimal errors. Finally, open issues in these relevant fields are given, stimulating further research.

show abstract

Section: Previous Survey Workmentioning

confidence: 99%

Tackling Faults in the Industry 4.0 Era—A Survey of Machine-Learning Solutions and Key Aspects

Angelopoulos

Michailidis

Νομικός

et al. 2019

Sensors

220

View full text Add to dashboard Cite

show abstract

“…The effectiveness in predicting dynamic behaviour of systems is a key driver of lean based operations capable of reducing wastes and overall operational cost. Machining is a vital engineering operation across the globe that seeks to attain a zero error margin between the predicted and experimental datasets especially in mission critical systems and artificial intelligence based systems Weichert et al. (2019) with a high degree of intolerance for measurement discrepancy.…”

Section: Introductionmentioning

confidence: 99%

Surface roughness prediction using a hybrid scheme of difference analysis and adaptive feedback weights

Ayomoh

Abou-El-Hossein

2021

Heliyon

View full text Add to dashboard Cite

This research has presented an optimum model for surface roughness prediction in a shop floor machining operation. The proposed solution is premised on difference analysis enhanced with a feedback control model capable of generating transient adaptive weights until a converging set point is attained. The surface roughness results utilized herein were adopted from two prior experiments in the literature. The design of experiment herein is premised on three cutting parameters in both experimental scenarios viz: feed rate, cutting speed and depth of cut for experimental dataset one and cutting speed, feed rate and flow rate for experimental dataset two. Three experimental levels were considered in both scenarios resulting in twenty-seven outcomes each. The simulation trial anchored on Matlab software was divided into two sub-categories viz: prediction of surface roughness for cutting combinations with vector points off the edges of the mesh referred to as off-edge cutting combinations (Off-ECC) and recovery of cutting combinations with positions on the edges of the mesh referred to as on-edge cutting combinations (On-ECC). The proposed hybrid scheme of difference analysis with feedback control premised on the use of dynamic weights produced an accurate output in comparison with the abductive, regression analysis and artificial neural network techniques as earlier utilized in the literature. The novelty of the proposed hybrid model lies in its high degree of prediction and recovery of existing datasets with an error margin approximately zero. This predictive efficacy is premised on the use of set points and transient dynamic weights for feedback iterations. The proposed solution technique in this research is quite consistent with its outputs and capable of working with very small to complex datasets.

show abstract

“…Recently, machine learning (ML) has been applied to the optimization of processes. Optimization through ML results in improved product quality in terms of the cost, time, consumption of resources, and specific optimization [ 19 ]. Hart-Rawung et al [ 20 ] proposed a prediction model for the phase fraction in a hot stamping simulation using ML to reduce the total calculation time.…”

Section: Introductionmentioning

confidence: 99%

Effect of a Multiple Reduction Die on the Residual Stress of Drawn Materials

et al. 2021

View full text Add to dashboard Cite

Residual stress may influence the mechanical behavior and durability of drawn materials. Thus, this study develops a multiple reduction die (MRD) that can reduce residual stress during the drawing process. The MRD set consists of several die tips, die cases, and lubricating equipment. All the die tips of the MRD were disposed of simultaneously. Finite element analysis of the drawing process was performed according to the reduction ratio of each die tip, and the variables in drawing process with the MRD were optimized using a deep neural network to minimize the residual stress. Experiments on the drawing process with the conventional die and MRD were performed to evaluate the residual stress and verify the effectiveness of the MRD. The results of X-ray diffraction measurements indicated that the axial and hoop residual stresses on the surface were dramatically reduced.

show abstract

A review of machine learning for the optimization of production processes

Cited by 223 publications

References 115 publications

Tackling Faults in the Industry 4.0 Era—A Survey of Machine-Learning Solutions and Key Aspects

Tackling Faults in the Industry 4.0 Era—A Survey of Machine-Learning Solutions and Key Aspects

Surface roughness prediction using a hybrid scheme of difference analysis and adaptive feedback weights

Effect of a Multiple Reduction Die on the Residual Stress of Drawn Materials

Contact Info

Product

Resources

About