Manufacturing Letters最新文献

{"title":"Predictive models for 3D inkjet material printer using automated image analysis and machine learning algorithms","authors":"Mutha Nandipati,&nbsp;Michael Ogunsanya,&nbsp;Salil Desai","doi":"10.1016/j.mfglet.2024.09.101","DOIUrl":"10.1016/j.mfglet.2024.09.101","url":null,"abstract":"<div><div>Additive manufacturing (AM) is a smart manufacturing process to fabricate components with high precision, minimal post-processing, and increased component complexity in a variety of materials. This research focuses on developing automated image analysis and predictive models for a widely used 3D material inkjet printing (IJP) process. The interplay of four input process parameters, which include frequency, voltage, temperature, and meniscus vacuum, on the output metrics of the inkjet printer was evaluated using statistical measures (ANOVA). Droplet types were classified as no drop, satellite drop, and normal drop using four machine learning classifiers, including random forest, support vector classifier, k-nearest neighbor, and decision trees. Hyperparameter tuning was performed for each model for over 486 data points. Regression predictive models were developed for both ink droplet velocity and volume with three linear models (linear, lasso, and ridge regression) and four non-linear models (random forest, decision tree, support vector regression, and k-nearest neighbor). Mean squared error and the coefficient of determination, r-squared value, were used to evaluate the performance of the predictive models. For the drop type classification models, k-fold of 5 yielded the highest accuracy for the RF, KNN, and DT models of around 98%. Similarly, for the regression based predictive models RF, DT and KNN accuracy results ranged from 97 to 99%. All the machine learning models were validated with experimental data with high prediction accuracies accuracy. This research serves as a foundation for developing design guidelines for 3D material inkjet printing with applications in biosensors, flexible electronics, and regenerative tissue engineering.</div></div>","PeriodicalId":38186,"journal":{"name":"Manufacturing Letters","volume":"41 ","pages":"Pages 810-821"},"PeriodicalIF":1.9,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142434293","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Investigating the use of 3D printed tools for electrochemical machining: Lessons learned and future improvements","authors":"Rhett Jones,&nbsp;Robert Prins,&nbsp;Jack Zhao","doi":"10.1016/j.mfglet.2024.09.062","DOIUrl":"10.1016/j.mfglet.2024.09.062","url":null,"abstract":"<div><div>This paper describes the use of 3D printing in the production of tool electrodes for use in electrochemical machining (ECM). The majority of ECM jobs require the use of a unique form tool, production of which represents a significant expense. Additive manufacturing processes such as 3D printing offer the potential to lower cost of production and allow design of more complex tool electrode geometries. The tool electrodes used in this research effort were printed in polylactic acid (PLA) and subsequently fit with a copper electrode to serve as the electrical connection terminal for the tool. The tool surface intended for use as the electrode for ECM was coated with an electrically conductive paint before being copper electroplated to form a conductive surface. These 3D printed tool electrodes were successfully demonstrated to machine hardened tool steel in a prototype ECM machine, although challenges remain. This paper describes the development of ECM tools from 3D printed tool blanks, the prototype ECM system that was constructed to demonstrate use of the tool blanks, and the results of applying the 3D printed blanks to machine hardened tool steel. Next steps including potential improvements to tool electrodes are also discussed.</div></div>","PeriodicalId":38186,"journal":{"name":"Manufacturing Letters","volume":"41 ","pages":"Pages 513-517"},"PeriodicalIF":1.9,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142434155","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"CAPP-GPT: A computer-aided process planning-generative pretrained transformer framework for smart manufacturing","authors":"Ahmed Azab ,&nbsp;Hany Osman ,&nbsp;Fazle Baki","doi":"10.1016/j.mfglet.2024.09.009","DOIUrl":"10.1016/j.mfglet.2024.09.009","url":null,"abstract":"<div><div>Smart manufacturing (SM) constitutes the backbone of Industry 4.0 (I4.0), allowing for heightened autonomy of the various interacting cyber-physical systems, making the various entities on the production floor. Connectivity, a vital enabler, plays a crucial role through state-of-the-art Digital Twinning (DT) technologies driven by underlying innovations like the industrial Internet of Things, Cloud Computing, and advancements in sensory devices. DT, which plays a vital role in the various planning functions under the production and operations management umbrella, is being used in the developed combined CAPP-GPT (Computer-Aided Process Planning-Generative Pretrained Transformer) and production scheduling approach to address disruptions on the shopfloor and in self-healing of the manufacturing processes at a micro-CAPP level by optimally adapting the process parameters and the developed toolpath on the fly based on online process signature measurements. In a leap commensurate with that which has taken place in Natural Language Processing-Large Language Models (Chat-GPT), similar efforts are currently being undertaken to parse CAD data structures and blueprints, fusing operations research and predictive analytics algorithms to carry out setup planning as well as sequencing and grouping manufacturing sub-operations. A hybridized Optimization and Machine Learning (ML) approach is employed where Logical Analysis of Data is used to solve the problem heuristically, exploiting various generative and variant methods at heart. Another extension of this macro-CAPP problem is being tackled by integrating the problem with delayed product differentiation, lot-sizing, and transfer line balance for futuristic batch-production shops employing Hybrid Manufacturing (HM) and Smart Assembly. At the micro-CAPP level, HM process parameters are optimized using a comprehensive approach employing the Taguchi loss function to assess surface roughness, internal failure costs, and other criteria, including greenhouse gas emissions and expended energy. Online measurements of the process signatures are also employed to adapt the initial set of process parameters using different automatic control schemes. ML is used to identify the process parameters carrying simulations on Simulink before the system is deployed.</div></div>","PeriodicalId":38186,"journal":{"name":"Manufacturing Letters","volume":"41 ","pages":"Pages 51-62"},"PeriodicalIF":1.9,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142434339","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Production efficiency analysis based on the RFID-collected manufacturing big data","authors":"Zhihui Chen ,&nbsp;Zeyu Xiao ,&nbsp;Yize Sun ,&nbsp;Yuhao Dong ,&nbsp;Ray Y. Zhong","doi":"10.1016/j.mfglet.2024.09.012","DOIUrl":"10.1016/j.mfglet.2024.09.012","url":null,"abstract":"<div><div>Radio Frequency Identification (RFID) technology is widely used for production data collection in manufacturing shop-floors. The RFID-collected manufacturing big data reflects detailed statuses of production processes and manufactured products, which, in turn, can be used to support a comprehensive production analysis. This paper introduces an analytical approach to conduct production efficiency analysis based on the RFID-collected manufacturing big data. The proposed method involves four key steps: data cleansing, data processing, key performance indicator (KPI) estimation, and data analytics. Specifically, speed and quality aspects of shopfloor manufacturing are investigated collectively as production efficiency to support the comprehensive production analysis. The findings highlight the influence of various factors, such as operation date, working hour, and machine failure, on production efficiency.</div></div>","PeriodicalId":38186,"journal":{"name":"Manufacturing Letters","volume":"41 ","pages":"Pages 81-90"},"PeriodicalIF":1.9,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142434342","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Smart design and additive manufacturing of bending tools to improve production flexibility","authors":"Michael Schiller ,&nbsp;Peter Frohn-Sörensen ,&nbsp;Florian Schreiber ,&nbsp;Daniel Morez ,&nbsp;Martin Manns ,&nbsp;Bernd Engel","doi":"10.1016/j.mfglet.2024.09.013","DOIUrl":"10.1016/j.mfglet.2024.09.013","url":null,"abstract":"<div><div>For the automotive industry, especially on the part of Tier 1 and Tier 2 suppliers, the future will be about maintaining sovereignty in the form of technology openness and accelerating digitization. The product portfolio, which is generally passed on by OEMs to suppliers for production, often includes body parts that cannot always be manufactured economically with the prevailing production technology. The reason for this is a high diversity of model-variants, which requires smaller batches. To this end, highly flexible large-series production cells for body sheet components that can be scaled in all dimensions are being developed and tested. For the first time, they will make it possible to redesign the process planning in series production on a component-specific basis. The aim is to reduce production costs for new, geometrically different component variants. The basic components of the flexible manufacturing system are, firstly, new flexible forming technologies which have the potential to produce typical vehicle part geometries. Secondly, a process generator develops the corresponding production plan. A digital mapping of the manufacturing processes enables the selection of cost-, efficiency-, flexibility- and resilience-optimized production chains depending on the number of parts. Established manufacturing processes to produce car body components are supplemented in the cell by flexible processes such as 3D swivel bending. As a use case for flexible manufacturing, a concept for Rapid Tooling of 3D swivel bending tools is developed. In the flexible manufacturing system to be developed, a method of a standardized process sequence to produce forming tools within 24 h has been lacking to date. For this purpose, the concept of an automated design is being developed in which a reconfigurable tool body can be sliced into sheet metal stripes The active tool surface is additively manufactured after the tool has been packaged using LMD and adapted to individual requirements. The goal in the application of Rapid Tooling is to reduce lead times and development costs through a largely automated tool design and lead time-optimized manufacturing concept.</div></div>","PeriodicalId":38186,"journal":{"name":"Manufacturing Letters","volume":"41 ","pages":"Pages 91-102"},"PeriodicalIF":1.9,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142434343","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Prediction of tool wear and surface finish using ANFIS modelling during turning of Carbon Fiber Reinforced Plastic (CFRP) composites","authors":"Anil K. Srivastava,&nbsp;Md. Mofakkirul Islam","doi":"10.1016/j.mfglet.2024.09.084","DOIUrl":"10.1016/j.mfglet.2024.09.084","url":null,"abstract":"<div><div>Carbon fiber-reinforced plastics (CFRP) are widely used in various industries due to their high strength to weight ratio, corrosion resistance, durability, and excellent thermo-mechanical properties. The machining of CFRP composites has always been a challenge for the manufacturers. In this study, CNC turning operation with coated carbide tool is used to machine a specific CFRP and the relationship between the cutting parameters (Speed, Feed, Depth of Cut) and response parameters (Vibration, Surface Finish, Cutting Force and Tool Wear) are investigated. An adaptive-network-based fuzzy inference system (ANFIS) model with two multi-input–single-output (MISO) system has been developed to predict the tool wear and surface finish. Speed, feed, depth of cut, vibration and cutting force have been used as input parameters and tool wear and surface finish have been used as output parameters. Three sets of cutting parameter have been used to gather the data points for continuous turning of CFRP composite. The model merged fuzzy inference modeling with artificial neural network learning abilities, and a set of rules is constructed directly from experimental data. This model is capable of predicting the cutting tool wear and surface finish during turning of CFRP composite. The predicted tool wear and surface finish data are compared to the experimental results. The predicted data agreed well with the actual experimental data with 98.96 % accuracy for tool wear and 99.61 % accuracy for surface finish.</div></div>","PeriodicalId":38186,"journal":{"name":"Manufacturing Letters","volume":"41 ","pages":"Pages 658-669"},"PeriodicalIF":1.9,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142434356","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A study on the gas film formation in electrochemical discharging processes by molecular dynamics simulation","authors":"Yu-Jen Chen,&nbsp;Murali Sundaram","doi":"10.1016/j.mfglet.2024.09.042","DOIUrl":"10.1016/j.mfglet.2024.09.042","url":null,"abstract":"<div><div>Molecular Dynamics (MD) simulations have emerged as a potent analytical tool for dissecting the intricate processes involved in nano gas film bubble generation. This study employs MD simulations to identify critical voltage that marks the transition from bubble saturation to gas film formation, while employing a mimic electrolysis model to expedite simulations through accelerated molecular insert rates. The simulations provide insights into underlying mechanisms, revealing the reforming and condensing dynamics of gas structures preceding gas film genesis. Experimental validation corroborates the accuracy of critical voltage predictions derived from MD simulations, with the close alignment between simulated critical points and experimental outcomes underscoring the robust predictive capability of MD simulations in elucidating electrochemical discharging (ECD) processes.</div></div>","PeriodicalId":38186,"journal":{"name":"Manufacturing Letters","volume":"41 ","pages":"Pages 351-356"},"PeriodicalIF":1.9,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142434245","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"NAMRC 52 fast-tracked research papers to Journal of Manufacturing Systems and Journal of Manufacturing Processes","authors":"Robert X. Gao (NAMRI/SME Scientific Committee Chair),&nbsp;Xun Xu (NAMRI/SME Scientific Committee Chair-Elect),&nbsp;Ihab Ragai (NAMRI/SME Scientific Committee Advisor)","doi":"10.1016/j.mfglet.2024.09.003","DOIUrl":"10.1016/j.mfglet.2024.09.003","url":null,"abstract":"","PeriodicalId":38186,"journal":{"name":"Manufacturing Letters","volume":"41 ","pages":"Pages 6-7"},"PeriodicalIF":1.9,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142434336","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Hybrid manufacturing cost models: Additive friction stir deposition, measurement, and CNC machining","authors":"Nathan Wilson ,&nbsp;Robert Patterson ,&nbsp;Elijah Charles ,&nbsp;Malachi Landis ,&nbsp;Joshua Kincaid ,&nbsp;Ryan Garcia ,&nbsp;Gregory Corson ,&nbsp;Tony Schmitz","doi":"10.1016/j.mfglet.2024.09.038","DOIUrl":"10.1016/j.mfglet.2024.09.038","url":null,"abstract":"<div><div>Based on its potential to reduce lead times, hybrid manufacturing, which often includes both additive manufacturing and machining processes, is receiving more attention from manufacturers as they seek to increase their supply chain resilience and efficiency. A new solid-state additive manufacturing, referred to as additive friction stir deposition (AFSD), has shown the potential to become an important process for hybrid manufacturing. To justify the selection of a hybrid manufacturing approach, the cost needs to be estimated for comparison to conventional approaches. Historically, hybrid manufacturing costs have been difficult to estimate due to the complexity and diversity of the manufacturing processes. This paper proposes cost models that include additive friction stir deposition, structured light scanning, milling, and turning, which can be combined in hybrid manufacturing process planning. These cost models are demonstrated in a case study and cost estimates are compared for hybrid and conventional (machining-only) manufacturing approaches. For the selected case, the hybrid manufacturing process cost was $1007.58, while the conventional milling process cost was $833.60. The results of the case study show that both labor and material costs must be considered to make an informed decision between hybrid and conventional manufacturing approaches.</div></div>","PeriodicalId":38186,"journal":{"name":"Manufacturing Letters","volume":"41 ","pages":"Pages 320-331"},"PeriodicalIF":1.9,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142434241","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Effect of materials and process parameters on machinability of stainless steels","authors":"Iqbal Shareef ,&nbsp;Durga Kumar Raja Potluri ,&nbsp;Gerry Horton","doi":"10.1016/j.mfglet.2024.09.088","DOIUrl":"10.1016/j.mfglet.2024.09.088","url":null,"abstract":"<div><div>Stainless steels, recognized for their corrosion resistance attributed to a minimum of 11 % Chromium, encompass a variety of alloys with distinctive microstructures and properties. Machinability significantly varies among these alloys. Austenitic steels such as SS303 and 304 present challenges, demonstrating poor surface finish and high power consumption. This study, employing a central composite design, investigates the machinability of AISI 303, 304, 316, AISI 416, and AISI A36. Turning tests with PVD TiAlN-coated inserts revealed optimal parameters for cutting speeds (90.5256–244.411 m/min), feed (0.0635–0.4826 mm/rev), and depth (0.00016–0.00187 m.). Surface finish analysis identified AISI 316 as the best, closely followed by AISI 303. From a power consumption standpoint, AISI 303 performed the best, and concerning fragmented chip morphology, AISI 303 also excelled. The superior performance of AISI 303 is attributed to 2 % Manganese and 0.15 % Sulfur, proving to be the most effective combination compared to the other four steels, resulting in a higher percentage of MnS₂, optimal for improving machinability. The depth of cut emerges as the most influential factor affecting dimensional accuracy. These findings hold practical significance in the selection of stainless steels and corresponding process parameters across various industries, including the manufacturing of heavy earthmoving equipment. By shedding light on the optimal composition and machining conditions, this study contributes valuable insights for enhancing performance and efficiency in stainless steel applications.</div></div>","PeriodicalId":38186,"journal":{"name":"Manufacturing Letters","volume":"41 ","pages":"Pages 696-707"},"PeriodicalIF":1.9,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142434297","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}