Machining cycle time prediction: Data-driven modelling of machine tool feedrate behavior with neural networks

Sun, Chao; Dominguez-Caballero, Javier; Ward, Robert; Soberanis, Sabino Ayvar; Curtis, David

doi:10.1016/j.rcim.2021.102293

Cited by 14 publications

(3 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is due to the vital role cycle times play in various aspects of production planning and scheduling (as discussed above), as well as in efficiency and optimization in manufacturing settings. This rationale aligns with the availability of research addressing cycle time estimation in other manufacturing settings (e.g., [21][22][23]). Moreover, three related research areas warrant further exploration in the context of cycle time estimation in offsite construction, as explained in the following subsection.…”

Section: Process Time Estimation Methodsmentioning

confidence: 64%

Data- and Knowledge-Driven Cycle Time Estimation in Offsite Construction

Alsakka,

Yu,

Hamzeh

et al. 2023

Preprint

View full text Add to dashboard Cite

Cycle times at workstations in offsite construction factories fluctuate widely due to various influencing factors. Consequently, relying on average rates, such as length per unit of time, for estimating cycle times proves to be inaccurate, often leading to significant deviations between production schedules and actual operations. To address this issue, this study proposes an estimation system that leverages machine-learning-based prediction, statistical methods, 3D simulation, and computer vision to predict cycle times at the workstation level. Testing of the system on a semi-automated wood-wall framing workstation in a panelized construction factory shows that it reduces the mean absolute error and sum of errors by approximately 36% and 68%, respectively, compared to the fixed rate method. The results also highlight the efficacy of using computer vision data for training machine-learning models for cycle time estimation, the importance of identifying and understanding the factors influencing cycle times, and the impact of random delays on the accuracy of cycle time estimation systems.

show abstract

Section: Process Time Estimation Methodsmentioning

confidence: 64%

Data- and Knowledge-Driven Cycle Time Estimation in Offsite Construction

Alsakka,

Yu,

Hamzeh

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…A machine‐learning‐based architecture for general sensor‐fault detection, isolation, and accommodation (SFDIA) was proposed 9 . A neural network based method was developed for machining time prediction 10 . In these methods, the physical systems or processes were regarded as a black box and data‐driven methods can be used to find the relationship between system input and output.…”

Section: Introductionmentioning

confidence: 99%

“…9 A neural network based method was developed for machining time prediction. 10 In these methods, the physical systems or processes were regarded as a black box and data-driven methods can be used to find the relationship between system input and output. Feed-forward neural networks are capable of approximating a function and its derivatives to arbitrary accurate.…”

mentioning

confidence: 99%

PhysiNet: A combination of physics‐based model and neural network model for digital twins

Sun

Shi

2021

Int J of Intelligent Sys

Self Cite

View full text Add to dashboard Cite

As the real-time digital counterpart of a physical system or process, digital twins are utilized for system simulation and optimization. Neural networks are one way to build a digital twins model by using data especially when a physics-based model is not accurate or even not available. However, for a newly designed system, it takes time to accumulate enough data for neural network moded and only an approximate physics-based model is available. To take advantage of both models, this paper proposed a model that combines the physics-based model and the neural network model to improve the prediction accuracy for the whole life cycle of a system. The proposed hybrid model (PhysiNet) was able to automatically combine the models and boost their prediction performance.Experiments showed that the PhysiNet outperformed both the physics-based model and the neural network model.

show abstract