Polymer electrolyte membrane fuel cells (PEMFC) are a promising technology for economic and environmentally friendly energy production. However, they haven’t reached their full potential in the market yet as only few reliable PEMFC systems have successfully passed the prototyping face. A drawback of the current diagnostic tools is that only a select few are of high genericity, reliability and can perform efficiently on-line at the same time. Furthermore, there is only limited research identifying both PEMFC stack faults and ancillary system faults simultaneously. While none of the existing tools can be interrogated by the end-user. In this research, we develop novel artificial intelligence-based technologies to overcome these existing barriers, i.e., (i) a semantically enriched integrating schema (ontology) of the overall operation and structure of the PEMFC that allows automatic inference engines to automatically deduce fault detection; (ii) a knowledge-based, light-weight, on-line fuel cell system diagnosis (FuCSyDi) platform. FuCSyDi detects and provides the location of failures by considering only the data from the reliable sensors. Additionally, it provides the reasons underpinning any forthcoming failures and enables the end-user to interrogate the platform for further information regarding its operation and structure. Our platform is validated by performing tests against common automotive stress conditions. This innovative approach enhances the reliability of the fuel cell system diagnosis and, hence, its lifetime performance.

聚合物电解质膜燃料电池（PEMFC）是一种经济有效且环保的能源生产技术。但是，由于只有少数可靠的PEMFC系统成功通过了原型设计，因此它们尚未在市场上发挥出全部潜力。当前的诊断工具的缺点在于，只有少数具有高通用性，可靠性并且可以同时有效地在线执行。此外，只有有限的研究同时识别PEMFC堆栈故障和辅助系统故障。最终用户无法查询任何现有工具。在这项研究中，我们开发了新颖的基于人工智能的技术来克服这些现有的障碍，即 （i）PEMFC整体操作和结构的语义丰富的集成模式（本体），该模式允许自动推理引擎自动推断故障检测；（ii）基于知识的轻量级在线燃料电池系统诊断（FuCSyDi）平台。FuCSyDi通过仅考虑来自可靠传感器的数据来检测并提供故障位置。此外，它提供了支持任何即将发生的故障的原因，并使最终用户可以询问该平台以获取有关其操作和结构的更多信息。我们的平台已通过针对常见的汽车压力条件进行测试而得到验证。这种创新的方法提高了燃料电池系统诊断的可靠性，从而提高了其使用寿命。