{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T15:57:55Z","timestamp":1774540675045,"version":"3.50.1"},"reference-count":52,"publisher":"MDPI AG","issue":"13","license":[{"start":{"date-parts":[[2022,6,30]],"date-time":"2022-06-30T00:00:00Z","timestamp":1656547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"the National Science and Technology Major Project of China","award":["Y2019-VII-0018-0160"],"award-info":[{"award-number":["Y2019-VII-0018-0160"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>For data-driven intelligent manufacturing, many important in-process parameters should be estimated simultaneously to control the machining precision of the parts. However, as two of the most important in-process parameters, there is a lack of multi-task learning (MTL) model for simultaneous estimation of surface roughness and tool wear. To address the problem, a new MTL model with shared layers and two task-specific layers was proposed. A novel parallel-stacked auto-encoder (PSAE) network based on stacked denoising auto-encoder (SDAE) and stacked contractive auto-encoder (SCAE) was designed as the shared layers to learn deep features from cutting force signals. To enhance the performance of the MTL model, the scaled exponential linear unit (SELU) was introduced as the activation function of SDAE. Moreover, a dynamic weight averaging (DWA) strategy was implemented to dynamically adjust the learning rate of different tasks. Then, the time-domain features were extracted from raw cutting signals and low-frequency reconstructed wavelet packet coefficients. Frequency-domain features were extracted from the power spectrum obtained by the Fourier transform. After that, all features were combined as the input vectors of the proposed MTL model. Finally, surface roughness and tool wear were simultaneously predicted by the trained MTL model. To verify the superiority and effectiveness of the proposed MTL model, nickel-based superalloy Haynes 230 was machined under different cutting parameter combinations and tool wear levels. Some other intelligent algorithms were also implemented to predict surface roughness and tool wear. The results showed that compared with the support vector regression (SVR), kernel extreme learning machine (KELM), MTL with SDAE (MTL_SDAE), MTL with SCAE (MTL_SCAE), and single-task learning with PSAE (STL_PSAE), the estimation accuracy of surface roughness was improved by 30.82%, 16.67%, 14.06%, 26.17%, and 16.67%, respectively. Meanwhile, the prediction accuracy of tool wear was improved by 46.74%, 39.57%, 41.51%, 38.68%, and 39.57%, respectively. For practical engineering application, the dimensional deviation and surface quality of the machined parts can be controlled through the established MTL model.<\/jats:p>","DOI":"10.3390\/s22134943","type":"journal-article","created":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T01:40:36Z","timestamp":1656639636000},"page":"4943","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["A Novel Multi-Task Learning Model with PSAE Network for Simultaneous Estimation of Surface Quality and Tool Wear in Milling of Nickel-Based Superalloy Haynes 230"],"prefix":"10.3390","volume":"22","author":[{"given":"Minghui","family":"Cheng","sequence":"first","affiliation":[{"name":"School of Mechanical Engineering, Beijing Institute of Technology, No. 5 Zhongguancun South Street, Haidian District, Beijing 100081, China"}]},{"given":"Li","family":"Jiao","sequence":"additional","affiliation":[{"name":"Key Laboratory of Fundamental Science for Advanced Machining, Beijing Institute of Technology, No. 5 Zhongguancun South Street, Haidian District, Beijing 100081, China"}]},{"given":"Pei","family":"Yan","sequence":"additional","affiliation":[{"name":"Key Laboratory of Fundamental Science for Advanced Machining, Beijing Institute of Technology, No. 5 Zhongguancun South Street, Haidian District, Beijing 100081, China"}]},{"given":"Huiqing","family":"Gu","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Beijing Institute of Technology, No. 5 Zhongguancun South Street, Haidian District, Beijing 100081, China"}]},{"given":"Jie","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Beijing Institute of Technology, No. 5 Zhongguancun South Street, Haidian District, Beijing 100081, China"}]},{"given":"Tianyang","family":"Qiu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Fundamental Science for Advanced Machining, Beijing Institute of Technology, No. 5 Zhongguancun South Street, Haidian District, Beijing 100081, China"}]},{"given":"Xibin","family":"Wang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Fundamental Science for Advanced Machining, Beijing Institute of Technology, No. 5 Zhongguancun South Street, Haidian District, Beijing 100081, China"}]}],"member":"1968","published-online":{"date-parts":[[2022,6,30]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Wang, Y., Wang, Y., Zheng, L., and Zhou, J. (2022). Online Surface Roughness Prediction for Assembly Interfaces of Vertical Tail Integrating Tool Wear under Variable Cutting Parameters. Sensors, 22.","DOI":"10.3390\/s22051991"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"106575","DOI":"10.1016\/j.triboint.2020.106575","article-title":"Effect of machined surface texture on fretting crack nucleation under radial loading in conformal contact","volume":"153","author":"Gu","year":"2021","journal-title":"Tribol. Int."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"106669","DOI":"10.1016\/j.ijfatigue.2021.106669","article-title":"Effect of milling surface topography and texture direction on fatigue behavior of ZK61M magnesium alloy","volume":"156","author":"Chen","year":"2022","journal-title":"Int. J. Fatigue"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"556","DOI":"10.1016\/j.ymssp.2017.11.021","article-title":"Gaussian process regression for tool wear prediction","volume":"104","author":"Kong","year":"2018","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"943","DOI":"10.1007\/s10845-020-01698-4","article-title":"Surface roughness stabilization method based on digital twin-driven machining parameters self-adaption adjustment: A case study in five-axis machining","volume":"33","author":"Zhao","year":"2020","journal-title":"J. Intell. Manuf."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"799","DOI":"10.1016\/j.ymssp.2017.11.016","article-title":"Machinery health prognostics: A systematic review from data acquisition to RUL prediction","volume":"104","author":"Lei","year":"2018","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1923","DOI":"10.1007\/s10845-017-1361-z","article-title":"Development of a Grey online modeling surface roughness monitoring system in end milling operations","volume":"30","author":"Huang","year":"2019","journal-title":"J. Intell. Manuf."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"206","DOI":"10.1007\/s40436-021-00345-2","article-title":"Prediction of product roughness, profile, and roundness using machine learning techniques for a hard turning process","volume":"9","author":"Du","year":"2021","journal-title":"Adv. Manuf."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1016\/j.jmsy.2021.10.013","article-title":"Physics-informed meta learning for machining tool wear prediction","volume":"62","author":"Li","year":"2022","journal-title":"J. Manuf Syst."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Qiao, H., Wang, T., Wang, P., Qiao, S., and Zhang, L. (2018). A Time-Distributed Spatiotemporal Feature Learning Method for Machine Health Monitoring with Multi-Sensor Time Series. Sensors, 18.","DOI":"10.3390\/s18092932"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"80006","DOI":"10.1109\/ACCESS.2021.3084617","article-title":"An Effective PSO-LSSVM-Based Approach for Surface Roughness Prediction in High-Speed Precision Milling","volume":"9","author":"Li","year":"2021","journal-title":"IEEE Access"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"6393","DOI":"10.3390\/s140406393","article-title":"Surface Roughness Model Based on Force Sensors for the Prediction of the Tool Wear","volume":"14","author":"Rubio","year":"2014","journal-title":"Sensors"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1045","DOI":"10.1007\/s10845-017-1381-8","article-title":"Artificial intelligence for automatic prediction of required surface roughness by monitoring wear on face mill teeth","volume":"29","author":"Pimenov","year":"2018","journal-title":"J. Intell. Manuf."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1580","DOI":"10.1177\/0954405420935787","article-title":"An intelligent prediction model of the tool wear based on machine learning in turning high strength steel. Proceedings of the Institution of Mechanical Engineers, Part B","volume":"234","author":"Cheng","year":"2020","journal-title":"J. Eng. Manuf."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1357","DOI":"10.1007\/s00170-021-07522-4","article-title":"Application of machine vision method in tool wear monitoring","volume":"116","author":"Peng","year":"2021","journal-title":"Int. J. Adv. Manuf. Technol."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1423","DOI":"10.1007\/s10845-017-1334-2","article-title":"A novel integrated tool condition monitoring system","volume":"30","author":"Jain","year":"2019","journal-title":"J. Intell. Manuf."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"118","DOI":"10.1016\/j.measurement.2019.05.062","article-title":"Analytical modeling of tool health monitoring system using multiple sensor data fusion approach in hard machining","volume":"145","author":"Kene","year":"2019","journal-title":"Measurement"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"268","DOI":"10.1016\/j.jmapro.2017.09.016","article-title":"A comprehensive study on the effects of tool wear on surface roughness, dimensional integrity and residual stress in turning IN718 hard-to-machine alloy","volume":"30","author":"Mears","year":"2017","journal-title":"J. Manuf. Process."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"455","DOI":"10.1016\/j.cirp.2019.03.007","article-title":"Heterogeneous data-driven hybrid machine learning for tool condition prognosis","volume":"68","author":"Wang","year":"2019","journal-title":"CIRP Ann."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1931","DOI":"10.1007\/s00170-021-07280-3","article-title":"Vibration-based tool condition monitoring in milling of Ti-6Al-4V using an optimization model of GM(1,N) and SVM","volume":"115","author":"Rao","year":"2021","journal-title":"Int. J. Adv. Manuf. Technol."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Huang, P., and Lee, C. (2021). Estimation of Tool Wear and Surface Roughness Development Using Deep Learning and Sensors Fusion. Sensors, 21.","DOI":"10.3390\/s21165338"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Chen, H., and Lee, C. (2021). Deep Learning Approach for Vibration Signals Applications. Sensors, 21.","DOI":"10.3390\/s21113929"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1016\/j.measurement.2014.01.024","article-title":"Prediction of cutting tool wear, surface roughness and vibration of work piece in boring of AISI 316 steel with artificial neural network","volume":"51","author":"Murthy","year":"2014","journal-title":"Measurement"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1023\/A:1007379606734","article-title":"Multitask Learning","volume":"28","author":"Caruana","year":"1997","journal-title":"Mach. Learn."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1016\/j.neucom.2020.01.051","article-title":"A multi-task learning framework for gas detection and concentration estimation","volume":"416","author":"Liu","year":"2020","journal-title":"Neurocomputing"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1016\/j.neucom.2020.05.087","article-title":"Multimodal multitask deep learning model for Alzheimer\u2019s disease progression detection based on time series data","volume":"412","author":"Abuhmed","year":"2020","journal-title":"Neurocomputing"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"2169","DOI":"10.1007\/s10845-020-01630-w","article-title":"Multitask learning for health condition identification and remaining useful life prediction: Deep convolutional neural network approach","volume":"32","author":"Kim","year":"2021","journal-title":"J. Intell. Manuf."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1016\/j.jmsy.2020.11.018","article-title":"An accurate prediction method of multiple deterioration forms of tool based on multitask learning with low rank tensor constraint","volume":"58","author":"Liu","year":"2021","journal-title":"J. Manuf. Syst."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"6023","DOI":"10.1109\/TII.2020.3040285","article-title":"A New Multitask Learning Method for Tool Wear Condition and Part Surface Quality Prediction","volume":"17","author":"Wang","year":"2021","journal-title":"IEEE T Ind. Inform."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1016\/j.ins.2021.01.064","article-title":"A new deep auto-encoder using multiscale reconstruction errors and weight update correlation","volume":"559","author":"Song","year":"2021","journal-title":"Inf. Sci."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"7043","DOI":"10.1007\/s00170-022-09286-x","article-title":"Indirect monitoring of machining characteristics via advanced sensor systems: A critical review","volume":"120","author":"Korkmaz","year":"2022","journal-title":"Int. J. Adv. Manuf. Technol."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Kunto\u011flu, M., Aslan, A., Pimenov, D.Y., Usca, \u00dc.A., Salur, E., Gupta, M.K., Mikolajczyk, T., Giasin, K., Kap\u0142onek, W., and Sharma, S. (2021). A Review of Indirect Tool Condition Monitoring Systems and Decision-Making Methods in Turning: Critical Analysis and Trends. Sensors, 21.","DOI":"10.3390\/s21010108"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Pimenov, D.Y., Bustillo, A., Wojciechowski, S., Sharma, V.S., Gupta, M.K., and Kunto\u011flu, M. (2022). Artificial intelligence systems for tool condition monitoring in machining: Analysis and critical review. J. Intell. Manuf., 1\u201343.","DOI":"10.1007\/s10845-022-01923-2"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"108639","DOI":"10.1016\/j.knosys.2022.108639","article-title":"Deep multiple auto-encoder with attention mechanism network A dynamic domain adaptation method for rotary machine fault diagnosis under different working conditions","volume":"249","author":"Yang","year":"2022","journal-title":"Knowl.-Based Syst."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"278","DOI":"10.1016\/j.ymssp.2017.09.026","article-title":"A novel method for intelligent fault diagnosis of rolling bearings using ensemble deep auto-encoders","volume":"102","author":"Shao","year":"2018","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_36","unstructured":"Klambauer, G., Unterthiner, T., Mayr, A., and Hochreiter, S. (2017). Self-Normalizing Neural Networks. arXiv."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"107232","DOI":"10.1016\/j.measurement.2019.107232","article-title":"Intelligent fault diagnosis of rotating machinery using a new ensemble deep auto-encoder method","volume":"151","author":"Zhang","year":"2020","journal-title":"Measurement"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"6069","DOI":"10.1109\/TII.2020.2967556","article-title":"A Deep Learning Model for Smart Manufacturing Using Convolutional LSTM Neural Network Autoencoders","volume":"16","author":"Essien","year":"2020","journal-title":"IEEE T Ind. Inform."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Liu, S., Johns, E., and Davison, A.J. (2018). End-to-End Multi-Task Learning with Attention. arXiv.","DOI":"10.1109\/CVPR.2019.00197"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"170","DOI":"10.1016\/j.procir.2015.08.058","article-title":"Novel Spatial Cutting Tool-wear Measurement System Development and its Evaluation","volume":"37","author":"Cerce","year":"2015","journal-title":"Procedia CIRP"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1016\/j.triboint.2019.02.049","article-title":"Investigation of surface topography and its deterioration resulting from tool wear evolution when dry turning of titanium alloy Ti-6Al-4V","volume":"135","author":"Liang","year":"2019","journal-title":"Tribol. Int."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"3123","DOI":"10.1177\/1077546314520830","article-title":"A multiscale permutation entropy based approach to select wavelet for fault diagnosis of ball bearings","volume":"21","author":"Vakharia","year":"2015","journal-title":"J. Vib. Control"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1007\/s10845-020-01663-1","article-title":"Tool wear condition monitoring based on a two-layer angle kernel extreme learning machine using sound sensor for milling process","volume":"33","author":"Zhou","year":"2020","journal-title":"J. Intell. Manuf."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"109333","DOI":"10.1016\/j.measurement.2021.109333","article-title":"Prediction of surface residual stress in end milling with Gaussian process regression","volume":"178","author":"Cheng","year":"2021","journal-title":"Measurement"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"634","DOI":"10.1016\/j.ymssp.2017.05.006","article-title":"Analysis of cutting force signals by wavelet packet transform for surface roughness monitoring in CNC turning","volume":"98","year":"2018","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"308","DOI":"10.1016\/j.isatra.2020.05.041","article-title":"Intelligent fault diagnosis among different rotating machines using novel stacked transfer auto-encoder optimized by PSO","volume":"105","author":"Haidong","year":"2020","journal-title":"ISA Trans."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"106779","DOI":"10.1016\/j.compag.2022.106779","article-title":"FWDGAN-based data augmentation for tomato leaf disease identification","volume":"194","author":"Li","year":"2022","journal-title":"Comput. Electron. Agric."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"3317","DOI":"10.1007\/s00170-016-9664-3","article-title":"Investigations on mother wavelet selection for health assessment of lathe bearings","volume":"90","author":"Kulkarni","year":"2016","journal-title":"Int. J. Adv. Manuf. Technol."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"109225","DOI":"10.1016\/j.ymssp.2022.109225","article-title":"Milling chatter detection with WPD and power entropy for Ti-6Al-4V thin-walled parts based on multi-source signals fusion","volume":"177","author":"Hao","year":"2022","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1016\/j.advengsoft.2016.01.008","article-title":"The Whale Optimization Algorithm","volume":"95","author":"Mirjalili","year":"2016","journal-title":"Adv. Eng. Softw."},{"key":"ref_51","unstructured":"Ruder, S. (2017). An Overview of Multi-Task Learning in Deep Neural Networks. arXiv."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"311","DOI":"10.1016\/j.jmsy.2021.09.001","article-title":"Model-based tool condition prognosis using power consumption and scarce surface roughness measurements","volume":"61","year":"2021","journal-title":"J. Manuf. Syst."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/13\/4943\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T23:40:57Z","timestamp":1760139657000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/13\/4943"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,30]]},"references-count":52,"journal-issue":{"issue":"13","published-online":{"date-parts":[[2022,7]]}},"alternative-id":["s22134943"],"URL":"https:\/\/doi.org\/10.3390\/s22134943","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,6,30]]}}}