A Novel CNC Milling Energy Consumption Prediction Method Based on Program Parsing and Parallel Neural Network

Cao, Jin; Xia, Xuhui; Wang, Lei; Zhang, Zelin; Liu, Xiang

doi:10.3390/su132413918

Cited by 10 publications

(7 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several models were investigated and a deviation of 7.16% was achieved for the whole machine tool system using decision trees. Cao et al also developed an ML-based prediction of energy consumption [19]. Here, in the first stage, a parser was used to group the NC code, based on which an ML model predicted the energy demand for each state group.…”

Section: State Of the Artmentioning

confidence: 99%

See 1 more Smart Citation

Time Series Prediction for Energy Consumption of Computer Numerical Control Axes Using Hybrid Machine Learning Models

Ströbel,

Probst,

Deucker

et al. 2023

Machines

View full text Add to dashboard Cite

The prediction of energy-related time series for computer numerical control (CNC) machine tool axes is an essential enabler for the shift towards autonomous and intelligent production. In particular, a precise prediction of energy consumption is needed to determine the environmental impact of a product and the optimization of its production. For this purpose, a novel approach for predicting high-frequency time series of numerically controlled axes based on the program code to be executed is presented. The method involves simulative preprocessing of the input NC code to determine each axis’s acceleration, velocity, and process force. Combined with the material removal rate, these variables are input for a machine learning (ML) model that delivers axis-specific high-frequency time series predictions. Compared to common approaches, it is thus possible to make predictions for the variable energy consumption of machine tools for any tool path or target resolution in the time domain. Experiments show that this approach achieves a high precision when a robust learning data basis is available. For the X-, Y-, and Z-axis, errors of 0.2%, −1.09%, and 0.09% for aircut and of 0.15%, −3.55%, and 0.08% for material removal can be achieved. The potentials for further improvement are identified systematically.

show abstract

Section: State Of the Artmentioning

confidence: 99%

“…As shown in [15], a combination of analytical and data-based models can be useful. In more recent developments, ML approaches [18,19] are increasingly used for block-wise prediction.…”

Section: State Of the Artmentioning

confidence: 99%

Time Series Prediction for Energy Consumption of Computer Numerical Control Axes Using Hybrid Machine Learning Models

Ströbel,

Probst,

Deucker

et al. 2023

Machines

View full text Add to dashboard Cite

show abstract

“…Using various machine learning algorithms to accurately predict the energy requirements of CNC machining operations based on real production data, Brillinger et al [18] were able to develop a prediction that deviated only 7.16% from the real value. Cao et al [19] developed a method to efficiently determine the total energy consumption of CNC machines using program parsing and parallel neural networks. The method has been verified by case studies and can determine the total energy consumption with a deviation of 5% for each NC-block.…”

Section: Energy Prediction and Optimizationmentioning

confidence: 99%

Software-Defined Workpiece Positioning for Resource-Optimized Machine Tool Utilization

Ströbel¹,

Probst²,

Hutt³

et al. 2023

Journal of Machine Engineering

View full text Add to dashboard Cite

Advancing climate change, tense world markets, and political pressure steadily increase the demand for resourceoptimized production solutions. Herby, the positioning of the raw material in the machine tool is an important factor that has received little attention. Traditionally, this is done centrally on the machine table, which leads to locally increased wear of the feed axis. Furthermore, positioning directly influences energy consumption during machining. Consequently, the longest possible component utilization through optimum wear and energy optimization creates a direct conflict of objectives. To solve this conflict, this paper presents an automated approach for software-defined workpiece positioning and NC-Code optimization regarding the axis-specific energy consumption and the spindle condition of ball screws. An approach for mapping the energy consumption and the directly measured spindle condition is presented. Both represent input variables of the cost function. Approaches for the optimization of the position as well as for the practical implementation are proposed.

show abstract

“…The use of artificial neural networks to anticipate energy consumption in milling offers several advantages. Firstly, it allows obtaining more precise and reliable estimates of energy consumption, which simplifies decision making and programming of operations and not only can energy consumption be predicted in mining but in other industries as indicated by Cao. et al, (2021).…”

Section: Introductionmentioning

confidence: 99%

Prediction of energy consumption in grinding using artificial neural networks to improve the distribution of fragmentation size [Predicción del consumo de energía en la molienda utilizando redes neuronales artificiales para mejorar la distribución del tamaño de la fragmentación]

Anticona Cueva,

Vera Encarnación,

Anticona Cueva

et al. 2024

J. energy environ. sci.

View full text Add to dashboard Cite

The study focuses on the prediction of energy consumption in grinding processes using artificial neural networks (ANN). The purpose was to develop a predictive model based on artificial neural networks to estimate energy consumption in grinding and improve the fragmentation size distribution, which is crucial for the efficiency of mining and metallurgical operations. Energy consumption in grinding represents a significant part of operating costs and directly influences the profitability of operations. The ANN was trained from a data set of 126 records, which were divided into 80% for training and 20 % for model testing. The results of this research highlight optimal performance of the predictive model with performance metrics such as Mean Absolute Error (MAE), Mean Square Error (MSE), Root Mean Square Error (RMSE) and Correlation Coefficient (R2), with values of 0.78, 1.39, 1.18 and 0.98, respectively in the estimation of energy consumption in the grinding process. Finally, these results indicate that the ANN achieved an accurate prediction of energy consumption in the grinding process, this will allow better baking in energy optimization.

show abstract

A Novel CNC Milling Energy Consumption Prediction Method Based on Program Parsing and Parallel Neural Network

Cited by 10 publications

References 37 publications

Time Series Prediction for Energy Consumption of Computer Numerical Control Axes Using Hybrid Machine Learning Models

Time Series Prediction for Energy Consumption of Computer Numerical Control Axes Using Hybrid Machine Learning Models

Software-Defined Workpiece Positioning for Resource-Optimized Machine Tool Utilization

Prediction of energy consumption in grinding using artificial neural networks to improve the distribution of fragmentation size [Predicción del consumo de energía en la molienda utilizando redes neuronales artificiales para mejorar la distribución del tamaño de la fragmentación]

Contact Info

Product

Resources

About