The development of an ANN surface roughness prediction system of multiple materials in CNC turning

Huang, PoTsang B.; Inderawati, Maria Magdalena Wahyuni; Rohmat, Rohmat; Sukwadi, Ronald

doi:10.1007/s00170-022-10709-y

Cited by 13 publications

(6 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(1) ANNs (Huang et al [ 17 ]): This study employed artificial neural networks with a large number of interconnected neurons to search for a good fit of the root mean square error in training and validation. The best prediction of surface roughness was obtained through the development of back-propagation neural network prediction models in both single and multi-material models.…”

Section: Methodsmentioning

confidence: 99%

“…Liu et al [ 18 ] explored data-based tool wear and other roughness prediction techniques to predict roughness and an proposed an adaptive optimization method for process parameters using a digital twin. Huang et al [ 17 ] developed a back-propagation neural network prediction model for surface roughness predictions in a multi-material scenario by collecting signals as input to the prediction model through CNC and sensing techniques during the machining process. Chen et al [ 26 ] proposed a surface roughness prediction model based on a back-propagation neural network for machined workpieces, which could improve product quality and reduce machining costs simultaneously.…”

Section: Related Workmentioning

confidence: 99%

“…Data-driven methods employ statistical and machine learning models for end-to-end surface roughness predictions, enabling highly accurate predictions in scenarios without expert domain knowledge. Huang et al [ 17 ] constructed a back-propagation neural network prediction method for forecasting roughness by using the signals collected by computerized CNC turning and sensing techniques as the input to the prediction model. Liu et al [ 18 ] proposed a digital-twin-driven surface roughness prediction method to meet the real-time predictability requirements of smart manufacturing.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Milling Surface Roughness Prediction Based on Physics-Informed Machine Learning

Zeng

2023

Sensors

View full text Add to dashboard Cite

Surface roughness is a key indicator of the quality of mechanical products, which can precisely portray the fatigue strength, wear resistance, surface hardness and other properties of the products. The convergence of current machine-learning-based surface roughness prediction methods to local minima may lead to poor model generalization or results that violate existing physical laws. Therefore, this paper combined physical knowledge with deep learning to propose a physics-informed deep learning method (PIDL) for milling surface roughness predictions under the constraints of physical laws. This method introduced physical knowledge in the input phase and training phase of deep learning. Data augmentation was performed on the limited experimental data by constructing surface roughness mechanism models with tolerable accuracy prior to training. In the training, a physically guided loss function was constructed to guide the training process of the model with physical knowledge. Considering the excellent feature extraction capability of convolutional neural networks (CNNs) and gated recurrent units (GRUs) in the spatial and temporal scales, a CNN–GRU model was adopted as the main model for milling surface roughness predictions. Meanwhile, a bi-directional gated recurrent unit and a multi-headed self-attentive mechanism were introduced to enhance data correlation. In this paper, surface roughness prediction experiments were conducted on the open-source datasets S45C and GAMHE 5.0. In comparison with the results of state-of-the-art methods, the proposed model has the highest prediction accuracy on both datasets, and the mean absolute percentage error on the test set was reduced by 3.029% on average compared to the best comparison method. Physical-model-guided machine learning prediction methods may be a future pathway for machine learning evolution.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Milling Surface Roughness Prediction Based on Physics-Informed Machine Learning

Zeng

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…The enhancement of machining operations efficiency is crucial in contemporary manufacturing as it directly impacts cost-effectiveness, heightened productivity and improved product quality (Das et al 2022; Nguyen et al 2022; Huang et al 2023). The fundamental process of machining, known as turning, plays a crucial role in the formation of various materials, encompassing metals and composites.…”

Section: Introductionmentioning

confidence: 99%

Adaptive Surface Roughness Prediction in Turning Processes with Dynamic Lubrication using Fish Swarm-Intelligent Modified Xgboost Approach

2024

nano-ntp

View full text Add to dashboard Cite

Accurately anticipating Surface Roughness (SR) throughout turning operations is a continuous difficulty for the machining industry, particularly under variable lubrication circumstances. Surface finish quality is sometimes subpar because of standard models' low responsiveness to changes in lubrication conditions and machining settings. The present research introduced a novel Artificial Fish Swarm-Intelligent Modified XGBoost (AFSI-MX) methodology to tackle this problem by combining the XGBoost technique's potent prediction powers with the collective thinking of fish swarm behavior. First, the dataset is collected to assess the suggested AFSI-MX technique in relation to SR prediction. This study is carried out using the AFSI-MX approach on the Matlab platform. The suggested AFSI-MX technique is effective in forecasting SR in turning procedures over variable lubrication, as demonstrated by expserimental findings. The suggested AFSI-MX technique outperforms conventional methods in comparison when it comes to managing the complexity and unpredictability present in machining situations

show abstract

“…The ratio between product cost and quality at each production stage is important. Measuring surface roughness is crucial in several engineering applications [1].…”

Section: Introductionmentioning

confidence: 99%