start-ver=1.4 cd-journal=joma no-vol=19 cd-vols= no-issue=1 article-no= start-page=JAMDSM0001 end-page= dt-received= dt-revised= dt-accepted= dt-pub-year=2025 dt-pub=2025 dt-online= en-article= kn-article= en-subject= kn-subject= en-title= kn-title=Development of tool life prediction system for square end-mills based on database of servo motor current value en-subtitle= kn-subtitle= en-abstract= kn-abstract=Accurate prediction of tool life is crucial for reducing production costs and enhancing quality in the machining process. However, such predictions often rely on empirical knowledge, which may limit inexperienced engineers to reliably obtain accurate predictions. This study explores a method to predict the tool life of a cutting machine using servo motor current data collected during the initial stages of tool wear, which is a cost-effective approach. The LightGBM model was identified as suitable for predicting tool life from current data, given the challenges associated with predicting from the average variation of current values. By identifying and utilizing the top 50 features from the current data for prediction, the accuracy of tool life prediction in the early wear stage improved. As this prediction method was developed based on current data obtained during the very early wear stage in experiments with square end-mills, it was tested on extrapolated data using different end-mill diameters. The findings revealed average accuracy rates of 71.2% and 69.4% when using maximum machining time and maximum removal volume as thresholds, respectively. en-copyright= kn-copyright= en-aut-name=KODAMAHiroyuki en-aut-sei=KODAMA en-aut-mei=Hiroyuki kn-aut-name= kn-aut-sei= kn-aut-mei= aut-affil-num=1 ORCID= en-aut-name=SUZUKIMakoto en-aut-sei=SUZUKI en-aut-mei=Makoto kn-aut-name= kn-aut-sei= kn-aut-mei= aut-affil-num=2 ORCID= en-aut-name=OHASHIKazuhito en-aut-sei=OHASHI en-aut-mei=Kazuhito kn-aut-name= kn-aut-sei= kn-aut-mei= aut-affil-num=3 ORCID= affil-num=1 en-affil=Faculty of Environmental, Life, Natural Science and Technology, Okayama University kn-affil= affil-num=2 en-affil=Graduate school of Environmental, Life, Natural Science and Technology, Okayama University kn-affil= affil-num=3 en-affil=Faculty of Environmental, Life, Natural Science and Technology, Okayama University kn-affil= en-keyword=Milling kn-keyword=Milling en-keyword=LightGBM kn-keyword=LightGBM en-keyword=Tool life prediction kn-keyword=Tool life prediction en-keyword=Square end-mill kn-keyword=Square end-mill en-keyword=Servo motor current kn-keyword=Servo motor current END start-ver=1.4 cd-journal=joma no-vol=11 cd-vols= no-issue=6 article-no= start-page=24-00129 end-page= dt-received= dt-revised= dt-accepted= dt-pub-year=2024 dt-pub=2024 dt-online= en-article= kn-article= en-subject= kn-subject= en-title= kn-title=Effect of artificial defect on tensile properties of thin titanium alloy wire en-subtitle= kn-subtitle= en-abstract= kn-abstract=This study investigated the effects of artificial defects, introduced via focused ion beam (FIB) processing, on the tensile properties of thin titanium alloy wires (Ti-6Al-4V). Results indicated that the defective wires fractured when the net-section nominal stress reached the ultimate tensile strength of the smooth wires, probably because of localized stress concentrations relaxing due to plastic deformation around the defects. The effect of defects on tensile properties was classified into three regions based on the size of the defect area. In the case of small defects, wires fractured at the smooth area away from the defects where the cross-sectional strength was lower. In this case, the defects minimally affected the tensile properties. This is attributable to variations in the cross-sectional strength of the wire, which resulted in some sections with lower strength as compared with the defect area. In the case of medium-sized defects, the fracture strain decreased gradually as the defect area increased. Finally, in the case of large defects, the fracture strain was extremely small. The boundary between the medium-sized and large defects indicates the transition from plastic deformation to no plastic deformation in the smooth area. en-copyright= kn-copyright= en-aut-name=SAKAMOTOJunji en-aut-sei=SAKAMOTO en-aut-mei=Junji kn-aut-name= kn-aut-sei= kn-aut-mei= aut-affil-num=1 ORCID= en-aut-name=TADANaoya en-aut-sei=TADA en-aut-mei=Naoya kn-aut-name= kn-aut-sei= kn-aut-mei= aut-affil-num=2 ORCID= en-aut-name=UEMORITakeshi en-aut-sei=UEMORI en-aut-mei=Takeshi kn-aut-name= kn-aut-sei= kn-aut-mei= aut-affil-num=3 ORCID= en-aut-name=OISHIKoyo en-aut-sei=OISHI en-aut-mei=Koyo kn-aut-name= kn-aut-sei= kn-aut-mei= aut-affil-num=4 ORCID= affil-num=1 en-affil=Okayama University kn-affil= affil-num=2 en-affil=Okayama University kn-affil= affil-num=3 en-affil=Okayama University kn-affil= affil-num=4 en-affil=Okayama University kn-affil= en-keyword=Ti-6Al-4V kn-keyword=Ti-6Al-4V en-keyword=Thin wire kn-keyword=Thin wire en-keyword=Tensile properties kn-keyword=Tensile properties en-keyword=Defect kn-keyword=Defect en-keyword=Focused ion beam kn-keyword=Focused ion beam en-keyword=Net-section nominal stress kn-keyword=Net-section nominal stress en-keyword=Fracture surface kn-keyword=Fracture surface en-keyword=Fracture strain kn-keyword=Fracture strain END start-ver=1.4 cd-journal=joma no-vol=16 cd-vols= no-issue=4 article-no= start-page=JAMDSM0037 end-page= dt-received= dt-revised= dt-accepted= dt-pub-year=2022 dt-pub=2022 dt-online= en-article= kn-article= en-subject= kn-subject= en-title= kn-title=A bilevel production planning using machine learning-based customer modeling en-subtitle= kn-subtitle= en-abstract= kn-abstract=Mass customization is an important strategy to improve production systems to satisfy customersf preferences while maintaining production efficiency for mass production. Module production is one of the ways to achieve mass customization, and products are produced by combining modules. In the module production, it becomes much more important for manufacturing companies to reflect customersf preferences for selling products. The manufacturer can increase its total profit by providing customized products that satisfy customersf preferences by increasing customersf satisfaction. In conventional production planning, there are some cases where module production is conducted by the demands from customersf preferences. However, the customer decision-making model has not been employed in the production planning model. In this paper, a production planning model incorporating customersf preferences is developed. The customersf purchasing behavior is generated by using a machine learning model. Customer segmentation is conducted by clustering data that uses the purchase data of multiple customers. The resulting production planning model is a bilevel production planning problem consisting of a single company and multiple customers. Each company can sell products that combine modules that customers require in each segment. We show that the proposed model can obtain higher customersf satisfaction with greater profits than the model that does not employ the customersf purchasing model. en-copyright= kn-copyright= en-aut-name=NAKAOJun en-aut-sei=NAKAO en-aut-mei=Jun kn-aut-name= kn-aut-sei= kn-aut-mei= aut-affil-num=1 ORCID= en-aut-name=NISHITatsushi en-aut-sei=NISHI en-aut-mei=Tatsushi kn-aut-name= kn-aut-sei= kn-aut-mei= aut-affil-num=2 ORCID= affil-num=1 en-affil=Graduate School of Natural Science and Technology, Okayama University kn-affil= affil-num=2 en-affil=Graduate School of Natural Science and Technology, Okayama University kn-affil= en-keyword=Supply chain management kn-keyword=Supply chain management en-keyword=Mass customization kn-keyword=Mass customization en-keyword=Production planning kn-keyword=Production planning en-keyword=Customerfs modeling kn-keyword=Customerfs modeling en-keyword=Machine learning kn-keyword=Machine learning END start-ver=1.4 cd-journal=joma no-vol=16 cd-vols= no-issue=4 article-no= start-page=JAMDSM0035 end-page= dt-received= dt-revised= dt-accepted= dt-pub-year=2022 dt-pub=2022 dt-online= en-article= kn-article= en-subject= kn-subject= en-title= kn-title=Adaptive heterogeneous particle swarm optimization with comprehensive learning strategy en-subtitle= kn-subtitle= en-abstract= kn-abstract=This paper proposes an adaptive heterogeneous particle swarm optimization with a comprehensive learning strategy for solving single-objective constrained optimization problems. In this algorithm, particles can use an exploration strategy and an exploitation strategy to update their positions. The historical success rates of the two strategies are used to adaptively control the adoption rates of strategies in the next iteration. The search strategy in the canonical particle swarm optimization algorithm is based on elite solutions. As a result, when no particles can discover better solutions for several generations, this algorithm is likely to fall into stagnation. To respond to this challenge, a new strategy is proposed to explore the neighbors of the elite solutions in this study. Finally, a constraint handling method is equipped to the proposed algorithm to make it be able to solve constrained optimization problems. The proposed algorithm is compared with the canonical particle swarm optimization, differential evolution, and several recently proposed algorithms on the benchmark test suite. The Wilcoxon signed-rank test results show that the proposed algorithm is significantly better on most of the benchmark problems compared with the competitors. The proposed algorithm is also applied to solve two real-world mechanical engineering problems. The experimental results show that the proposed algorithm performs consistently well on these problems. en-copyright= kn-copyright= en-aut-name=LIUZiang en-aut-sei=LIU en-aut-mei=Ziang kn-aut-name= kn-aut-sei= kn-aut-mei= aut-affil-num=1 ORCID= en-aut-name=NISHITatsushi en-aut-sei=NISHI en-aut-mei=Tatsushi kn-aut-name= kn-aut-sei= kn-aut-mei= aut-affil-num=2 ORCID= affil-num=1 en-affil=Faculty of Natural Science and Technology, Okayama University kn-affil= affil-num=2 en-affil=Faculty of Natural Science and Technology, Okayama University kn-affil= en-keyword=Swarm intelligence kn-keyword=Swarm intelligence en-keyword=Particle swarm optimization kn-keyword=Particle swarm optimization en-keyword=Differential evolution kn-keyword=Differential evolution en-keyword=Comprehensive learning kn-keyword=Comprehensive learning END