ADVANCED MATERIALS & PROCESSES | JULY/AUGUST 2025 48 iTSSe TSS iTSSe TSS A MACHINE LEARNING APPROACH FOR ANALYZING RESIDUAL STRESS DISTRIBUTION IN COLD SPRAY COATINGS Rosa Huaraca Aparco, Fidelia Tapia-Tadeo, Yajhayda Bellido Ascarza, Alexis León Ramírez, Yersi-Luis HuamánRomaní, and Calixto Cañari Otero This study establishes a machine learning (ML) model utilizing the expectation-maximization approach to predict maximum residual stresses, encompassing both tensile and compressive states, in the cold spraying process across various substrates. The main feature of the ML algorithm lies in its two-step iterative process, where the Expectation (E step) refines latent variable estimates, and the Maximization (M step) optimizes the model’s parameters, aligning them with the data. (Fig. 1) The Journal of Thermal Spray Technology (JTST), the official journal of the ASM Thermal Spray Society, publishes contributions on all aspects— fundamental and practical— of thermal spray science, including processes, feedstock manufacture, testing, and characterization. As the primary vehicle for thermal spray information transfer, its mission is to synergize the rapidly advancing thermal spray industry and related industries by presenting research and development efforts leading to advancements in implementable engineering applications of the technology. The highlighted papers below, hand-picked by Editorin-Chief André McDonald, FASM, spotlight the development of intelligent coating processes that are shaping the future of thermal spray technology. JTST is available online through springerlink.com. TSS members receive free online access to JTST. For more information, visit asminternational.org/tss. Fig. 1 — Example depicting 3D arrangement of multiple particles within the FE simulation. ThermalSprayDirectory.com Simplify Your Search for Vendors Find the right solutions for your business. Search for products, research companies, connect with suppliers, and make confident purchasing decisions all in one place. JTST HIGHLIGHTS 14
RkJQdWJsaXNoZXIy MTYyMzk3NQ==