Generative mechanisms of AI implementation: A critical realist perspective on predictive maintenance
采用批判实在论视角和多个案例研究，识别出预测性维护实施中的五个相互依赖的生成机制（实验、知识构建与整合、数据、焦虑、灵感），并用因果回路图揭示其社会技术动态，帮助传统制造企业理解AI实施的内在原因。
Artificial intelligence (AI) promises various new opportunities to create and appropriate business value. However, many organizations – especially those in more traditional industries – struggle to seize these opportunities. To unpack the underlying reasons, we investigate how more traditional industries implement predictive maintenance, a promising application of AI in manufacturing organizations. For our analysis, we employ a multiple-case design and adopt a critical realist perspective to identify generative mechanisms of AI implementation. Overall, we find five interdependent mechanisms: experimentation; knowledge building and integration; data; anxiety; and inspiration. Using causal loop diagramming, we flesh out the socio-technical dynamics of these mechanisms and explore the organizational requirements of implementing AI. The resulting topology of generative mechanisms contributes to the research on AI management by offering rich insights into the cause-effect relationships that shape the implementation process. Moreover, it demonstrates how causal loop diagraming can improve the modeling and analysis of generative mechanisms.