工程认证与新工科双背景下AI赋能无损检测技术教学研究

Research and Exploration on AI-Enabled Non-Destructive Testing Technology Teaching under the Dual Background of Engineering Accreditation and Emerging Engineering Education

摘要: 工程教育专业认证与新工科建设是我国高等工程教育改革的核心导向，二者均以“学生中心、产出导向、持续改进”为核心理念，聚焦学生解决复杂工程问题能力的培养。无损检测技术是航空航天等高端工程领域的关键支撑技术，但其传统教学模式存在知识体系固化、实践教学受限、教学单向传导、评价机制单一等问题，难以契合产出导向教育(OBE)理念对复合型工程人才的培养要求。本文以工程教育认证与新工科建设为框架，以人工智能(AI)技术为赋能手段，从课程体系优化、智能化教学资源建设、产教融合教学方法创新、多维闭环评价体系构建四个维度完善教学改革路径，构建“一个核心理念、双向技术赋能、三层能力融合”的教学模式，旨在培育具备跨学科知识整合能力、AI技术应用能力、解决复杂工程问题能力的复合型无损检测专业人才。

Abstract: Engineering Education Professional Accreditation and the Emerging Engineering Education Initiative are the core orientations of China’s higher engineering education reform. Both adhere to the core philosophy of “Student-Centered, Outcome-Based, Continuous Improvement” and focus on cultivating students’ ability to solve complex engineering problems. Non-Destructive Testing technology serves as a critical supporting technology in high-end engineering fields represented by aerospace. Nevertheless, its traditional teaching mode is plagued by issues including a rigid knowledge system, constrained practical teaching, one-way knowledge transmission, and a simplistic evaluation mechanism, which fail to align with the training requirements of the Outcome-Based Education (OBE) concept for interdisciplinary engineering talents. Taking engineering education accreditation and emerging engineering education construction as the framework and artificial intelligence (AI) technology as the enabling means, this paper optimizes the teaching reform path from four dimensions: curriculum system optimization, intelligent teaching resource development, innovation of industry-education integrated teaching methods, and construction of a multi-dimensional closed-loop evaluation system. A teaching mode characterized by “one core philosophy, two-way technology empowerment, and three-level capability integration” is established, aiming to nurture interdisciplinary Non-Destructive Testing professionals who possess interdisciplinary knowledge integration competence, AI technology application capability, and the ability to address complex engineering problems.