Addressing Uncertainty in Tool Wear Prediction with Dropout-Based Neural Network
Data-driven algorithms have been widely applied in predicting tool wear because of the high prediction performance of the algorithms, availability of data sets, and advancements in computing capabilities in recent years. Although most algorithms are supposed to generate outcomes with high precision...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Computers |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-431X/12/9/187 |
| _version_ | 1797580664585846784 |
|---|---|
| author | Arup Dey Nita Yodo Om P. Yadav Ragavanantham Shanmugam Monsuru Ramoni |
| author_facet | Arup Dey Nita Yodo Om P. Yadav Ragavanantham Shanmugam Monsuru Ramoni |
| author_sort | Arup Dey |
| collection | DOAJ |
| description | Data-driven algorithms have been widely applied in predicting tool wear because of the high prediction performance of the algorithms, availability of data sets, and advancements in computing capabilities in recent years. Although most algorithms are supposed to generate outcomes with high precision and accuracy, this is not always true in practice. Uncertainty exists in distinct phases of applying data-driven algorithms due to noises and randomness in data, the presence of redundant and irrelevant features, and model assumptions. Uncertainty due to noise and missing data is known as data uncertainty. On the other hand, model assumptions and imperfection are reasons for model uncertainty. In this paper, both types of uncertainty are considered in the tool wear prediction. Empirical mode decomposition is applied to reduce uncertainty from raw data. Additionally, the Monte Carlo dropout technique is used in training a neural network algorithm to incorporate model uncertainty. The unique feature of the proposed method is that it estimates tool wear as an interval, and the interval range represents the degree of uncertainty. Different performance measurement matrices are used to compare the proposed method. It is shown that the proposed approach can predict tool wear with higher accuracy. |
| first_indexed | 2024-03-10T22:54:07Z |
| format | Article |
| id | doaj.art-50f3fff483504bc08b256554b70a6ab0 |
| institution | Directory Open Access Journal |
| issn | 2073-431X |
| language | English |
| last_indexed | 2024-03-10T22:54:07Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Computers |
| spelling | doaj.art-50f3fff483504bc08b256554b70a6ab02023-11-19T10:07:35ZengMDPI AGComputers2073-431X2023-09-0112918710.3390/computers12090187Addressing Uncertainty in Tool Wear Prediction with Dropout-Based Neural NetworkArup Dey0Nita Yodo1Om P. Yadav2Ragavanantham Shanmugam3Monsuru Ramoni4School of Engineering, Math, and Technology, Navajo Technical University, Crownpoint, NM 87313, USADepartment of Industrial and Manufacturing Engineering, North Dakota State University, Fargo, ND 58102, USADepartment of Industrial & Systems Engineering, North Carolina Agricultural and Technical State University, Greensboro, NC 27411, USADepartment of Engineering Technology, Fairmont State University, Fairmont, WV 26554, USASchool of Engineering, Math, and Technology, Navajo Technical University, Crownpoint, NM 87313, USAData-driven algorithms have been widely applied in predicting tool wear because of the high prediction performance of the algorithms, availability of data sets, and advancements in computing capabilities in recent years. Although most algorithms are supposed to generate outcomes with high precision and accuracy, this is not always true in practice. Uncertainty exists in distinct phases of applying data-driven algorithms due to noises and randomness in data, the presence of redundant and irrelevant features, and model assumptions. Uncertainty due to noise and missing data is known as data uncertainty. On the other hand, model assumptions and imperfection are reasons for model uncertainty. In this paper, both types of uncertainty are considered in the tool wear prediction. Empirical mode decomposition is applied to reduce uncertainty from raw data. Additionally, the Monte Carlo dropout technique is used in training a neural network algorithm to incorporate model uncertainty. The unique feature of the proposed method is that it estimates tool wear as an interval, and the interval range represents the degree of uncertainty. Different performance measurement matrices are used to compare the proposed method. It is shown that the proposed approach can predict tool wear with higher accuracy.https://www.mdpi.com/2073-431X/12/9/187Monte Carlo dropoutuncertaintytool wearprincipal component analysisinterval prediction |
| spellingShingle | Arup Dey Nita Yodo Om P. Yadav Ragavanantham Shanmugam Monsuru Ramoni Addressing Uncertainty in Tool Wear Prediction with Dropout-Based Neural Network Computers Monte Carlo dropout uncertainty tool wear principal component analysis interval prediction |
| title | Addressing Uncertainty in Tool Wear Prediction with Dropout-Based Neural Network |
| title_full | Addressing Uncertainty in Tool Wear Prediction with Dropout-Based Neural Network |
| title_fullStr | Addressing Uncertainty in Tool Wear Prediction with Dropout-Based Neural Network |
| title_full_unstemmed | Addressing Uncertainty in Tool Wear Prediction with Dropout-Based Neural Network |
| title_short | Addressing Uncertainty in Tool Wear Prediction with Dropout-Based Neural Network |
| title_sort | addressing uncertainty in tool wear prediction with dropout based neural network |
| topic | Monte Carlo dropout uncertainty tool wear principal component analysis interval prediction |
| url | https://www.mdpi.com/2073-431X/12/9/187 |
| work_keys_str_mv | AT arupdey addressinguncertaintyintoolwearpredictionwithdropoutbasedneuralnetwork AT nitayodo addressinguncertaintyintoolwearpredictionwithdropoutbasedneuralnetwork AT ompyadav addressinguncertaintyintoolwearpredictionwithdropoutbasedneuralnetwork AT ragavananthamshanmugam addressinguncertaintyintoolwearpredictionwithdropoutbasedneuralnetwork AT monsururamoni addressinguncertaintyintoolwearpredictionwithdropoutbasedneuralnetwork |