Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture最新文献_第2页

A tool wear monitoring approach based on triplet long short-term memory neural networks 基于三重长短期记忆神经网络的工具磨损监测方法

IF 2.6 3区工程技术

Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture Pub Date : 2023-11-25 DOI: 10.1177/09544054231206589

Bo Qin, Yongqing Wang, Kuo Liu, Shi Qiao, Mengmeng Niu, Yeming Jiang

{"title":"A tool wear monitoring approach based on triplet long short-term memory neural networks","authors":"Bo Qin, Yongqing Wang, Kuo Liu, Shi Qiao, Mengmeng Niu, Yeming Jiang","doi":"10.1177/09544054231206589","DOIUrl":"https://doi.org/10.1177/09544054231206589","url":null,"abstract":"Advancements in artificial intelligence have significantly improved the monitoring of tool wear in machining processes, thereby enhancing the overall quality of machining. However, the scarcity of tool wear samples poses a challenge to the enhancement of model precision. This necessitates the exploration of monitoring techniques that are effective even with small sample sizes. A method involving a triplet long short-term memory (LSTM) neural network is introduced, which offers the potential for superior accuracy even with limited training data. During the machining process, spindle vibrations are captured using a triaxial accelerometer. The raw data is processed by a triplet network, which uses an LSTM as the base model, thereby facilitating the aggregation within classes and separation between classes. A soft-max classification layer is subsequently integrated into the model, which enables the precise determination of tool wear states. The base model is optimized using a Genetic Algorithm to ensure model efficiency and accuracy before it is expanded into a triplet network. Experimental results from a vertical machining center confirm that the triplet LSTM network offers superior accuracy compared to a standard LSTM network, even when the sample size is small.","PeriodicalId":20663,"journal":{"name":"Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture","volume":"120 1","pages":""},"PeriodicalIF":2.6,"publicationDate":"2023-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139236557","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Determination of optimal sample thickness and positions of transducer for the effective Higher Order Mode Cluster-guided wave generation 确定有效高阶模式簇导波生成的最佳样品厚度和换能器位置

IF 2.6 3区工程技术

Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture Pub Date : 2023-11-25 DOI: 10.1177/09544054231210014

Che-Hua Yang, Van Nguyen Le, M. Saravana Kumar

{"title":"Determination of optimal sample thickness and positions of transducer for the effective Higher Order Mode Cluster-guided wave generation","authors":"Che-Hua Yang, Van Nguyen Le, M. Saravana Kumar","doi":"10.1177/09544054231210014","DOIUrl":"https://doi.org/10.1177/09544054231210014","url":null,"abstract":"Higher Order Mode Cluster (HOMC) guided waves (GW) have recently been proposed for ultrasonic testing of plates and pipes. The incident wave through the plastic wedge generates the HOMC-GW. A propagated distance, namely the HOMC formation field, is necessary to create the wave signal. Unfortunately, the HOMC wave is unstable in the formation region, which needs a longer distance for stability. This research examines the effect of sample thickness on the HOMC generation process. ABAQUS CAE simulated the HOMC generation in various samples with different thicknesses, such as 6, 7, 10, 15, and 20 mm. The results show that HOMC stability was achieved at a shorter distance in the smaller sample (6 mm) compared to the larger sample (20 mm). Moreover, the ABAQUS-Explicit 2D-FEA model was used for notch detection in a mild steel sample based on the HOMC status. The result shows that the transducer’s strength decreases along the formation regions, and the reflected amplitude becomes more robust when it reaches the stable region. When it travels further, the amplitude gets weaker due to the reduction in its energy. The experimental study was conducted similarly to the 2D-FEA model to compare the simulation and experimental results. The empirical findings show good agreement with the simulation results throughout notch detection. The precise distance required for the HOMC wave to become stable was determined via this work, optimizing the selection and employment of single modes.","PeriodicalId":20663,"journal":{"name":"Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture","volume":"95 31","pages":""},"PeriodicalIF":2.6,"publicationDate":"2023-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139238197","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Toward understanding the drilling performance of thermoplastic CF/PEEK and thermoset CF/epoxy composites using special drills 探讨热塑性CF/PEEK和热固性CF/环氧复合材料在特殊钻头上的钻削性能

3区工程技术

Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture Pub Date : 2023-11-14 DOI: 10.1177/09544054231209791

Yu Du, Tao Yang, Chang Liu, Sinan Liu

{"title":"Toward understanding the drilling performance of thermoplastic CF/PEEK and thermoset CF/epoxy composites using special drills","authors":"Yu Du, Tao Yang, Chang Liu, Sinan Liu","doi":"10.1177/09544054231209791","DOIUrl":"https://doi.org/10.1177/09544054231209791","url":null,"abstract":"Thermoplastic carbon fiber reinforced polyetheretherkrtone (CF/PEEK) and thermoset carbon fiber reinforced epoxy (CF/epoxy) composites are being widely applied in aviation and aerospace fields for their excellent performance. To compare the drilling characteristics of two typical carbon fiber reinforced composites under varying feed speeds, drilling experiments were carried out using three different special drills involving twist, brad, and dagger drills. The drilling performance of CF/epoxy and CF/PEEK composites was analyzed in terms of chip morphology, drilling temperature, thrust force, delamination damage, and surface morphology. The results show that CF/PEEK composites produced continuous chips, so that CF/PEEK composites generated higher drilling temperature and thrust force than that of CF/epoxy composites. CF/epoxy composites showed larger delamination damage and poorer machined surface than CF/PEEK composite due to its poor interlaminar toughness. Burrs produced agglomeration and crimping at the hole edges of the CF/PEEK composites due to PEEK resin is softened by heat, matrix plastic deformation. Brad drill revealed fewer burrs and merely a tearing damage at the exit. Dagger drill showed more burrs. The hole wall damage is minimal for brad drill. The results provide guidance for drilling of high quality thermoset and thermoplastic composites.","PeriodicalId":20663,"journal":{"name":"Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture","volume":"21 6","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134954053","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Study on tool wear and optimization of machining parameters in laser-assisted fast tool servo machining of glass-ceramic 激光辅助玻璃陶瓷快速刀具伺服加工中刀具磨损及加工参数优化研究

3区工程技术

Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture Pub Date : 2023-11-14 DOI: 10.1177/09544054231209798

Mingxu Fan, Xiaoqin Zhou, Jinzhou Song, Shan Jiang, Ke Gao, Shunfa Chen

{"title":"Study on tool wear and optimization of machining parameters in laser-assisted fast tool servo machining of glass-ceramic","authors":"Mingxu Fan, Xiaoqin Zhou, Jinzhou Song, Shan Jiang, Ke Gao, Shunfa Chen","doi":"10.1177/09544054231209798","DOIUrl":"https://doi.org/10.1177/09544054231209798","url":null,"abstract":"Glass-ceramic is difficult to be ultra precision machined due to its high hardness and brittleness. Laser-assisted fast tool servo machining (LAFTSM) of glass-ceramic optical free-form surface was carried out with tool wear as the characteristic value to study the machining quality of glass-ceramic. Orthogonal experiments on LAFTSM were conducted using the Taguchi method (TM). The range of tool wear reduction obtained by comparing laser-assisted machining (LAM) with fast tool servo (FTS) machining is 48.83%–64.12%. The order of contribution of each machining parameter obtained through variance analysis to the reduction of tool wear is: spindle speed > laser power > feed rate > piezoelectric frequency. The optimal combination of machining parameters that can minimize tool wear obtained through signal-to-noise ratio (S/N) analysis is: spindle speed 55 rpm, feed rate 0.01 mm/rev, piezoelectric frequency 8 Hz, laser power 75 W. Artificial neural network (ANN) and genetic algorithm (GA) were used to fit and optimize the machining parameters and experimental results in TM orthogonal experiments. The fitting values of ANN are highly consistent with the orthogonal experimental results. The optimal combination of machining parameters obtained after GA optimization analysis is: spindle speed 50 rpm, feed rate 0.015 mm/rev, piezoelectric frequency 4 Hz, laser power 75 W. Experiments were conducted using the optimal combination of machining parameters of TM and ANN, the results showed that ANN performs better than TM in predicting minimum tool wear and optimizing machining parameters. This study provides a reference for LAFTSM and the research methods of tool wear.","PeriodicalId":20663,"journal":{"name":"Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture","volume":"40 14","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134954250","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Modeling and compensation of the axial thermal error of electric spindles based on HHO-GRU method 基于HHO-GRU方法的电主轴轴向热误差建模与补偿

3区工程技术

Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture Pub Date : 2023-11-14 DOI: 10.1177/09544054231209786

Yang Li, Yinming Bai, Jingyao Tian, Huijie Zhang, Wanhua Zhao

{"title":"Modeling and compensation of the axial thermal error of electric spindles based on HHO-GRU method","authors":"Yang Li, Yinming Bai, Jingyao Tian, Huijie Zhang, Wanhua Zhao","doi":"10.1177/09544054231209786","DOIUrl":"https://doi.org/10.1177/09544054231209786","url":null,"abstract":"As the core component of precision CNC machine tools, a lot of heat is generated from the internal heat source of electric spindles during operation, resulting in thermal deformation and thermal errors that affect machining accuracy. Thermal error compensation is an economical method for reducing thermal errors, through which the impact of thermal errors on machining accuracy can effectively decrease. Taking a high-speed electric spindle as the research object, the temperature measurement points are selected as its front and rear bearing seat, as well as some positions far from the heat source. The temperature changes at the front and rear bearing as well as in the environment are monitored, then the thermal errors are measured using a Lion spindle rotation accuracy instrument. The optimal training parameters of the gated recurrent unit (GRU) network are optimized utilizing the global optimization ability of a Harris Hawks optimizer (HHO). Finally, the thermal error prediction model of the GRU electric spindle optimized using the Harris Hawks optimizer (HHO-GRU) is established, based on which axial thermal error compensation experiments are conducted. The results show that using the HHO-GRU prediction model for compensation, the axial thermal errors of the electric spindle can be reduced by more than 80%, which can be controlled within 5 μm.","PeriodicalId":20663,"journal":{"name":"Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134954370","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Process parameters based machine learning model for bead profile prediction in activated TIG Welding using random forest machine learning 基于工艺参数的随机森林机器学习TIG焊接焊缝轮廓预测模型

3区工程技术

Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture Pub Date : 2023-11-13 DOI: 10.1177/09544054231210018

Abhinav Arun Munghate, Shivraman Thapliyal

引用次数: 0

Fabric defect detection using AI and machine learning for lean and automated manufacturing of acoustic panels 使用人工智能和机器学习进行织物缺陷检测，用于声学面板的精益和自动化制造

3区工程技术

Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture Pub Date : 2023-11-08 DOI: 10.1177/09544054231209782

Wai Hin Cheung, Qingping Yang

{"title":"Fabric defect detection using AI and machine learning for lean and automated manufacturing of acoustic panels","authors":"Wai Hin Cheung, Qingping Yang","doi":"10.1177/09544054231209782","DOIUrl":"https://doi.org/10.1177/09544054231209782","url":null,"abstract":"Fabric defects in the conventional manufacturing of acoustic panels are detected via manual visual inspections, which are prone to problems due to human errors. Implementing an automated fabric inspection system can improve productivity and increase product quality. In this work, advanced machine learning (ML) techniques for fabric defect detection are reviewed, and two deep learning (DL) models are developed using transfer learning based on pre-trained convolutional neural network (CNN) architectures. The dataset used for this work consists of 1800 images with six different classes, made up of one class of fabric in good condition and five classes of fabric defects. The model design process involves pre-processing of the images, modification of the neural network layers, as well as selection and optimisation of the network’s hyperparameters. The average accuracies of the two CNN models developed in this work, which used the GoogLeNet and the ResNet50 architectures, are 89.84% and 95.45%, respectively, showing statistically significant results. The interpretability of the models is discussed using the Grad-CAM technique. Relevant image acquisition hardware requirements are also put forward for integration with the detection software, which can enable successful deployment of the model for the automated fabric inspection.","PeriodicalId":20663,"journal":{"name":"Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture","volume":"47 S223","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135342564","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Human–machine fusion–based operational complexity measurement approach to assembly lines for smart manufacturing 基于人机融合的智能制造装配线操作复杂性测量方法

3区工程技术

Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture Pub Date : 2023-11-07 DOI: 10.1177/09544054231209158

Guoliang Fan, Zuhua Jiang, Hao Zheng, Yicong Gao, Shanhe Lou

{"title":"Human–machine fusion–based operational complexity measurement approach to assembly lines for smart manufacturing","authors":"Guoliang Fan, Zuhua Jiang, Hao Zheng, Yicong Gao, Shanhe Lou","doi":"10.1177/09544054231209158","DOIUrl":"https://doi.org/10.1177/09544054231209158","url":null,"abstract":"Complexity is an important quantification of uncertain operation in assembly lines and the key source of invisible uncertainty problems in smart manufacturing. The purpose of this paper is to propose a complexity measurement approach to assess the complexity of assembly lines integrating humans, machines and configurations. First, the complexity models of the three states of the operation related to humans and machines are built based on information entropy and the operation time model. Then, an operational complexity model is built at the station level; it is constructed with a single station, parallel stations and sublines based on Kolmogorov entropy. The model quantitatively describes the cumulative complexity along with the material flow. Furthermore, the complexity model of the overall system is given, and the Lempel–Ziv algorithm is applied to measure the complexity flow along with the stations. The complexity equilibrium index is derived to quantify the balancing degree among the stations. The model incorporates uncertain operation into system modeling to quantify the influence of uncertainties on the state of the assembly line. An engine assembly line is used to validate that the approach can measure the complexity from operation to station to system.","PeriodicalId":20663,"journal":{"name":"Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture","volume":"213 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135476108","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Comprehensive extraction technology of key quality characteristics of meta-action unit for CNC machine tools design 数控机床设计元作用单元关键质量特征综合提取技术

3区工程技术

Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture Pub Date : 2023-11-07 DOI: 10.1177/09544054231209787

Zhongxi Zhang, Junfa Li, Chongyue Shi, Yulong Li, Genbao Zhang

{"title":"Comprehensive extraction technology of key quality characteristics of meta-action unit for CNC machine tools design","authors":"Zhongxi Zhang, Junfa Li, Chongyue Shi, Yulong Li, Genbao Zhang","doi":"10.1177/09544054231209787","DOIUrl":"https://doi.org/10.1177/09544054231209787","url":null,"abstract":"The QCs (quality characteristics) of MAU (meta-action unit) determine the quality of CNC (computer numerical control) machine tools. For improving the accuracy of MAU QCs analysis, and solving the problems that the current methods either only have subjective analysis, or only have objective analysis, or the analysis process that includes both subjective and objective analysis methods is relatively complex, a comprehensive identification method of MAU QCs according to the improved MAHP (multiplicative analytic hierarchy process) method and Shannon entropy is proposed in this paper. Firstly, the QCs of the MAU are divided into quality layer and index layer. Secondly, the expert evaluation weight is introduced to improve the MAHP, then the sub quality layer of the meta-action unit was subjectively analyzed. Thirdly, the index layer of the MAU is objectively analyzed by the Shannon entropy. Finally, the results obtained by WMAHP (weighted multiplication analytic hierarchy process) method and Shannon entropy method are synthesized, and the Pareto principle is adopted to extract the key QCs of the MAU. The proposed method combines the advantages of both subjective and objective analysis, and it can reduce the fluctuation of the analysis results caused by data changes. Meanwhile, the analysis process is relatively simple. Its applicability and superiority have also been confirmed by an experiment and comparisons with various methods. The proposed method is of great significance to improve the quality of CNC machine tools.","PeriodicalId":20663,"journal":{"name":"Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture","volume":"212 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135475956","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A generalized closed-form model of cutting energy for arbitrary-helix cylindrical milling tools and its applications 任意螺旋圆柱铣刀切削能量的广义封闭模型及其应用

3区工程技术

Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture Pub Date : 2023-11-07 DOI: 10.1177/09544054231202084

Chigbogu Ozoegwu

{"title":"A generalized closed-form model of cutting energy for arbitrary-helix cylindrical milling tools and its applications","authors":"Chigbogu Ozoegwu","doi":"10.1177/09544054231202084","DOIUrl":"https://doi.org/10.1177/09544054231202084","url":null,"abstract":"The knowledge of energy consumption of different machine tool production processes leading to products is necessary for energy labeling of machined parts in the increasingly sustainability-aware world thus the need for better machining energy modeling techniques. The milling process dynamics is complicated thus numerical and averaging techniques are hitherto usually applied in the cutting energy modeling thus limiting decision-making. This work proposes a generalized force-based closed-form model for the milling process cutting energy. To the best of the author’s knowledge, the model is the first closed-form cutting energy model for milling which not only applies to the conventional cylindrical milling tools with constant helix angle but also to cylindrical milling tools with any helix angle variation. The demonstrated applications of the proposed model include modeling of milling machine electrical energy consumption, modeling/optimization of milling project energy/efficiency and helix angle optimization for passive reduction of cutting energy. The proposed model is checked with experimentally-verified results in literature. For example, the model agrees with numerically computed cutting energy in literature by absolute error of 0.0320%–0.4025% and modeling of milling machine electrical energy consumption using the proposed model recorded the goodness-of-fit indices of 0.9980 [Formula: see text]-value and −0.1271 mean percentage error compared to a published experimental data. A parametric plot and an optimization based on genetic algorithm showed that increase of helix angle increases cutting energy due to increased influence of edge forces, and the effect is more pronounced at higher helix angles. Various potential applications of the presented model are highlighted in the concluding section.","PeriodicalId":20663,"journal":{"name":"Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture","volume":"210 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135475964","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0