{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T20:27:03Z","timestamp":1783110423612,"version":"3.54.6"},"reference-count":92,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100004377","name":"Hong Kong Polytechnic University","doi-asserted-by":"publisher","award":["P0057944"],"award-info":[{"award-number":["P0057944"]}],"id":[{"id":"10.13039\/501100004377","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Advanced Engineering Informatics"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.aei.2026.104794","type":"journal-article","created":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T09:07:06Z","timestamp":1778490426000},"page":"104794","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PC","title":["LightLLM4FDD: Domain-specific lightweight large language models for fault detection and diagnosis in building HVAC systems"],"prefix":"10.1016","volume":"74","author":[{"given":"Jian","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng (Eva)","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6005-1051","authenticated-orcid":false,"given":"Chaobo","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yizhi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.aei.2026.104794_b0005","doi-asserted-by":"crossref","DOI":"10.1016\/j.apenergy.2021.117139","article-title":"Problem of data imbalance in building energy load prediction: Concept, influence, and solution","volume":"297","author":"Zhang","year":"2021","journal-title":"Appl. Energy"},{"key":"10.1016\/j.aei.2026.104794_b0010","article-title":"A building information modelling study of carbon emissions in the construction industry based on life cycle assessment","volume":"1","author":"Yang","year":"2025","journal-title":"Energy Environ Nexus"},{"key":"10.1016\/j.aei.2026.104794_b0015","doi-asserted-by":"crossref","first-page":"525","DOI":"10.1016\/j.enbenv.2021.05.006","article-title":"Optimization of group control strategy and analysis of energy saving in refrigeration plant","volume":"3","author":"Tu","year":"2022","journal-title":"Energy Built Environ."},{"key":"10.1016\/j.aei.2026.104794_b0020","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/j.rser.2019.04.021","article-title":"Artificial intelligence-based fault detection and diagnosis methods for building energy systems: Advantages, challenges and the future","volume":"109","author":"Zhao","year":"2019","journal-title":"Renew. Sustain. Energy Rev."},{"key":"10.1016\/j.aei.2026.104794_b0025","doi-asserted-by":"crossref","DOI":"10.1016\/j.apenergy.2025.127056","article-title":"A few-shot learning framework for HVAC fault diagnosis in data centers with minimal data required","volume":"402","author":"Yan","year":"2026","journal-title":"Appl. Energy"},{"key":"10.1016\/j.aei.2026.104794_b0030","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1080\/10789669.2005.10391123","article-title":"Methods for fault detection, diagnostics, and prognostics for building systems\u2014a review, part I","volume":"11","author":"Katipamula","year":"2005","journal-title":"HVAC&R Res"},{"key":"10.1016\/j.aei.2026.104794_b0035","doi-asserted-by":"crossref","DOI":"10.1016\/j.apenergy.2025.127076","article-title":"Large language models meet energy systems: Opportunities, challenges, and future perspectives","volume":"403","author":"Zhang","year":"2026","journal-title":"Appl. Energy"},{"key":"10.1016\/j.aei.2026.104794_b0040","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1007\/s12273-025-1235-9","article-title":"Large language models for building energy applications: Opportunities and challenges","volume":"18","author":"Liu","year":"2025","journal-title":"Build. Simul."},{"key":"10.1016\/j.aei.2026.104794_b0045","doi-asserted-by":"crossref","first-page":"2875","DOI":"10.1007\/s12273-025-1324-9","article-title":"Pre-training large language models based on transformer architecture for building industry application: a review","volume":"18","author":"Liang","year":"2025","journal-title":"Build. Simul."},{"key":"10.1016\/j.aei.2026.104794_b0050","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1016\/j.enbenv.2023.06.005","article-title":"Generative pre-trained transformers (GPT)-based automated data mining for building energy management: Advantages, limitations and the future","volume":"5","author":"Zhang","year":"2024","journal-title":"Energy Built Environ."},{"key":"10.1016\/j.aei.2026.104794_b0055","series-title":"Energy Informatics","first-page":"49","article-title":"Large language models for fault detection in buildings\u2019 HVAC systems","author":"Langer","year":"2025"},{"key":"10.1016\/j.aei.2026.104794_b0060","article-title":"Domain-specific large language models for fault diagnosis of heating, ventilation, and air conditioning systems by labeled-data-supervised fine-tuning","volume":"377","author":"Zhang","year":"2025","journal-title":"Appl. Energy"},{"key":"10.1016\/j.aei.2026.104794_b0065","doi-asserted-by":"crossref","DOI":"10.1016\/j.apenergy.2023.121030","article-title":"A review of data-driven fault detection and diagnostics for building HVAC systems","volume":"339","author":"Chen","year":"2023","journal-title":"Appl. Energy"},{"key":"10.1016\/j.aei.2026.104794_b0070","doi-asserted-by":"crossref","DOI":"10.1016\/j.apenergy.2022.120050","article-title":"Using discrete Bayesian networks for diagnosing and isolating cross-level faults in HVAC systems","volume":"327","author":"Chen","year":"2022","journal-title":"Appl. Energy"},{"key":"10.1016\/j.aei.2026.104794_b0075","doi-asserted-by":"crossref","DOI":"10.1016\/j.apenergy.2024.125059","article-title":"Deep generative models in energy system applications: Review, challenges, and future directions","volume":"380","author":"Zhang","year":"2025","journal-title":"Appl. Energy"},{"key":"10.1016\/j.aei.2026.104794_b0080","doi-asserted-by":"crossref","DOI":"10.1016\/j.cose.2021.102527","article-title":"Security of building automation and control systems: Survey and future research directions","volume":"112","author":"Graveto","year":"2022","journal-title":"Comput. Secur."},{"key":"10.1016\/j.aei.2026.104794_b0085","doi-asserted-by":"crossref","unstructured":"Mundt T, Wickboldt P. Security in building automation systems - a first analysis. In: Proceedings of the 2016 International Conference On Cyber Security And Protection Of Digital Services (Cyber Security), 2016, p. 1\u20138. https:\/\/doi.org\/10.1109\/CyberSecPODS.2016.7502336.","DOI":"10.1109\/CyberSecPODS.2016.7502336"},{"key":"10.1016\/j.aei.2026.104794_b0090","doi-asserted-by":"crossref","DOI":"10.1016\/j.energy.2025.137405","article-title":"A generic framework and strategies for integrating AI into building automation systems for field-level optimization of HVAC systems","volume":"333","author":"Xie","year":"2025","journal-title":"Energy"},{"key":"10.1016\/j.aei.2026.104794_b0095","unstructured":"Touvron H, Lavril T, Izacard G, Martinet X, Lachaux M-A, Lacroix T, et al. LLaMA: open and efficient foundation language models. arXiv preprint 2023. https:\/\/doi.org\/10.48550\/arXiv.2302.13971."},{"key":"10.1016\/j.aei.2026.104794_b0100","unstructured":"Jiang AQ, Sablayrolles A, Mensch A, Bamford C, Chaplot DS, Casas D de las, et al. Mistral 7B. arXiv preprint 2023. https:\/\/doi.org\/10.48550\/arxiv.2310.06825."},{"key":"10.1016\/j.aei.2026.104794_b0105","unstructured":"Almazrouei E, Alobeidli H, Alshamsi A, Cappelli A, Cojocaru R, Debbah M, et al. The falcon series of open language models. arXiv preprint 2023. https:\/\/doi.org\/10.48550\/arXiv.2311.16867."},{"key":"10.1016\/j.aei.2026.104794_b0110","doi-asserted-by":"crossref","DOI":"10.1016\/j.aei.2025.103909","article-title":"Applications of multimodal large language models in construction industry","volume":"69","author":"Erfani","year":"2026","journal-title":"Adv. Eng. Inf."},{"key":"10.1016\/j.aei.2026.104794_b0115","doi-asserted-by":"crossref","DOI":"10.1016\/j.aei.2025.104035","article-title":"Toward construction-specialized, small language models: the interplay of domain adaptation, model scale and data volume","volume":"69","author":"Wang","year":"2026","journal-title":"Adv. Eng. Inf."},{"key":"10.1016\/j.aei.2026.104794_b0120","unstructured":"Grattafiori A, Dubey A, Jauhri A, Pandey A, Kadian A, Al-Dahle A, et al. The llama 3 herd of models. arXiv preprint 2024. https:\/\/doi.org\/10.48550\/arXiv.2407.21783."},{"key":"10.1016\/j.aei.2026.104794_b0125","doi-asserted-by":"crossref","DOI":"10.1016\/j.aei.2025.103208","article-title":"FD-LLM: Large language model for fault diagnosis of complex equipment","volume":"65","author":"Lin","year":"2025","journal-title":"Adv. Eng. Inf."},{"key":"10.1016\/j.aei.2026.104794_b0130","doi-asserted-by":"crossref","first-page":"30675","DOI":"10.1038\/s41598-024-75331-2","article-title":"Distilling the knowledge from large-language model for health event prediction","volume":"14","author":"Ding","year":"2024","journal-title":"Sci. Rep."},{"key":"10.1016\/j.aei.2026.104794_b0135","doi-asserted-by":"crossref","unstructured":"Chen H, Saha A, Hoi S, Joty S. Personalised distillation: empowering open-sourced LLMs with adaptive learning for code generation. arXiv preprint 2023. https:\/\/doi.org\/10.48550\/arXiv.2310.18628.","DOI":"10.18653\/v1\/2023.emnlp-main.417"},{"key":"10.1016\/j.aei.2026.104794_b0140","unstructured":"Narayanan SM, Braza JD, Griffiths R-R, Bou A, Wellawatte G, Ramos MC, et al. Training a scientific reasoning model for chemistry. arXiv preprint 2025. https:\/\/doi.org\/10.48550\/arXiv.2506.17238."},{"key":"10.1016\/j.aei.2026.104794_b0145","doi-asserted-by":"crossref","unstructured":"Na H, Hua Y, Wang Z, Shen T, Yu B, Wang L, et al. A survey of large language models in psychotherapy: current landscape and future directions. arXiv preprint 2025. https:\/\/doi.org\/10.48550\/arXiv.2502.11095.","DOI":"10.18653\/v1\/2025.findings-acl.385"},{"key":"10.1016\/j.aei.2026.104794_b0150","doi-asserted-by":"crossref","DOI":"10.1016\/j.aei.2025.104089","article-title":"Building regulation question-answering system using retrieval-augmented generation with dual-stage fine-tuned large language model","volume":"69","author":"Jiang","year":"2026","journal-title":"Adv. Eng. Inf."},{"key":"10.1016\/j.aei.2026.104794_b0155","unstructured":"Xu X, Li M, Tao C, Shen T, Cheng R, Li J, et al. A survey on knowledge distillation of large language models. arXiv preprint 2024. https:\/\/doi.org\/10.48550\/arXiv.2402.13116."},{"key":"10.1016\/j.aei.2026.104794_b0160","doi-asserted-by":"crossref","first-page":"2629","DOI":"10.1007\/s10439-023-03272-4","article-title":"Prompt engineering with ChatGPT: a guide for academic writers","volume":"51","author":"Giray","year":"2023","journal-title":"Ann. Biomed. Eng."},{"key":"10.1016\/j.aei.2026.104794_b0165","doi-asserted-by":"crossref","unstructured":"Lee K, Ippolito D, Nystrom A, Zhang C, Eck D, Callison-Burch C, et al. Deduplicating training data makes language models better. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics, 2022, p. 8424\u201345. https:\/\/doi.org\/10.18653\/v1\/2022.acl-long.577.","DOI":"10.18653\/v1\/2022.acl-long.577"},{"key":"10.1016\/j.aei.2026.104794_b0170","doi-asserted-by":"crossref","unstructured":"Charikar MS. Similarity estimation techniques from rounding algorithms. In: Proceedings of the thiry-fourth annual ACM symposium on Theory of computing, 2002, p. 380\u20138. https:\/\/doi.org\/10.1145\/509907.509965.","DOI":"10.1145\/509907.509965"},{"key":"10.1016\/j.aei.2026.104794_b0175","unstructured":"Dahlgaard S, Knudsen MBT, Thorup M. Practical hash functions for similarity estimation and dimensionality reduction. arXiv preprint 2017. https:\/\/doi.org\/10.48550\/arXiv.1711.08797."},{"key":"10.1016\/j.aei.2026.104794_b0180","doi-asserted-by":"crossref","unstructured":"Gururangan S, Marasovi\u0107 A, Swayamdipta S, Lo K, Beltagy I, Downey D, et al. Don\u2019t stop pretraining: Adapt language models to domains and tasks. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 2020, p. 8342\u201360. https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.740.","DOI":"10.18653\/v1\/2020.acl-main.740"},{"key":"10.1016\/j.aei.2026.104794_b0185","unstructured":"Yang Z, Dai Z, Yang Y, Carbonell J, Salakhutdinov R, Le QV. XLNet: generalized autoregressive pretraining for language understanding. arXiv preprint 2020. https:\/\/doi.org\/10.48550\/arXiv.1906.08237."},{"key":"10.1016\/j.aei.2026.104794_b0190","unstructured":"Hu EJ, Shen Y, Wallis P, Allen-Zhu Z, Li Y, Wang S, et al. LoRA: low-rank adaptation of large language models. arXiv preprint 2021. https:\/\/doi.org\/10.48550\/arXiv.2106.09685."},{"key":"10.1016\/j.aei.2026.104794_b0195","doi-asserted-by":"crossref","DOI":"10.1016\/j.aei.2025.103997","article-title":"Deep digital twin-powered large vision-language model for multi-scenario industrial fault diagnosis","volume":"69","author":"Xu","year":"2026","journal-title":"Adv. Eng. Inf."},{"key":"10.1016\/j.aei.2026.104794_b0200","doi-asserted-by":"crossref","DOI":"10.1016\/j.aei.2025.104027","article-title":"Improving construction contract question answering through embedding optimization and semantic chunking in large language models","volume":"69","author":"Zhang","year":"2026","journal-title":"Adv. Eng. Inf."},{"key":"10.1016\/j.aei.2026.104794_b0205","unstructured":"Gao Y, Xiong Y, Gao X, Jia K, Pan J, Bi Y, et al. Retrieval-augmented generation for large language models: a survey. arXiv preprint 2023. https:\/\/doi.org\/10.48550\/arXiv.2312.10997."},{"key":"10.1016\/j.aei.2026.104794_b0210","doi-asserted-by":"crossref","DOI":"10.1016\/j.enbuild.2024.114788","article-title":"Advancing building energy modeling with large language models: Exploration and case studies","volume":"323","author":"Zhang","year":"2024","journal-title":"Energy Build."},{"key":"10.1016\/j.aei.2026.104794_b0215","unstructured":"Ning K, Pan Z, Liu Y, Jiang Y, Zhang JY, Rasul K, et al. TS-RAG: retrieval-augmented generation based time series foundation models are stronger zero-shot forecaster. arXiv preprint 2025. https:\/\/doi.org\/10.48550\/arXiv.2503.07649."},{"key":"10.1016\/j.aei.2026.104794_b0220","unstructured":"Song L, Zhang C, Zhao L, Bian J. Pre-trained large language models for industrial control. arXiv preprint 2023. https:\/\/doi.org\/10.48550\/arXiv.2308.03028."},{"key":"10.1016\/j.aei.2026.104794_b0225","doi-asserted-by":"crossref","unstructured":"Ouyang L, Wu J, Jiang X, Almeida D, Wainwright CL, Mishkin P, et al. Training language models to follow instructions with human feedback. arXiv preprint 2022. https:\/\/doi.org\/10.48550\/arXiv.2203.02155.","DOI":"10.52202\/068431-2011"},{"key":"10.1016\/j.aei.2026.104794_b0230","doi-asserted-by":"crossref","DOI":"10.1016\/j.buildenv.2022.108760","article-title":"Causal discovery and inference-based fault detection and diagnosis method for heating, ventilation and air conditioning systems","volume":"212","author":"Zhang","year":"2022","journal-title":"Build. Environ."},{"key":"10.1016\/j.aei.2026.104794_b0235","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1016\/S0306-2619(03)00107-7","article-title":"Subsystem level fault diagnosis of a building\u2019s airhandling unit using general regression neural networks","volume":"77","author":"Lee","year":"2004","journal-title":"Appl. Energy"},{"key":"10.1016\/j.aei.2026.104794_b0240","doi-asserted-by":"crossref","unstructured":"Gao G, Fu Y, Zhang H. A new fault diagnosis approach for the air handling unit under the imbalanced data environment. In: Proceedings of the 2024 China Automation Congress (CAC), 2024, p. 6480\u20135. https:\/\/doi.org\/10.1109\/CAC63892.2024.10865487.","DOI":"10.1109\/CAC63892.2024.10865487"},{"key":"10.1016\/j.aei.2026.104794_b0245","unstructured":"Paszke A, Gross S, Massa F, Lerer A, Bradbury J, Chanan G, et al. PyTorch: an imperative style, high-performance deep learning library. arXiv preprint 2019. https:\/\/doi.org\/10.48550\/arXiv.1912.01703."},{"key":"10.1016\/j.aei.2026.104794_b0250","unstructured":"Wen J, Shun L. RP-1312 - tools for evaluating fault detection and diagnostic methods for air-handling units. Atlanta: ASHRAE Inc; 2012."},{"key":"10.1016\/j.aei.2026.104794_b0255","article-title":"LBNL fault detection and diagnostics datasets","author":"Granderson","year":"2022","journal-title":"Open Energy Data Initiative."},{"key":"10.1016\/j.aei.2026.104794_b0330","unstructured":"American Society of Heating, Refrigerating and Air-Conditioning Engineers. Guideline 36-2024 -- high-performance sequences of operation for HVAC systems. Atlanta: ASHRAE Inc; 2024."},{"key":"10.1016\/j.aei.2026.104794_b0335","unstructured":"American Society of Heating, Refrigerating and Air-Conditioning Engineers. ASHRAE handbook -- HVAC systems and equipment (SI). Atlanta: ASHRAE Inc; 2024."},{"key":"10.1016\/j.aei.2026.104794_b0340","unstructured":"Hyvarinen J, Karki S. Building optimization and fault diagnosis source book (Annex 25). Espoo: VTT Technical Research Centre of Finland Ltd; 1996."},{"key":"10.1016\/j.aei.2026.104794_b0345","unstructured":"Dexter A, Pakanen J. Demonstrating Automated Fault Detection and Diagnosis Methods in Real Buildings. Espoo: VTT Technical Research Centre of Finland Ltd; 2001."},{"key":"10.1016\/j.aei.2026.104794_b0350","doi-asserted-by":"crossref","unstructured":"Kelly GE, Bushby ST. Detecting faults in building air handling units \u2013 a background study for developing intelligent agents for optimizing building HVAC systems. Maryland: Northern Ocean Ltd; 2014.","DOI":"10.6028\/NIST.TN.1831"},{"key":"10.1016\/j.aei.2026.104794_b0355","unstructured":"Daikin. RESOURCE LIBRARY - PRODUCT CATALOGS; 2026. https:\/\/www.daikinapplied.com\/resources\/product-catalogs-library\/ (accessed January 13, 2026)."},{"key":"10.1016\/j.aei.2026.104794_b0360","unstructured":"Carrier. HVAC Products & Systems; 2026. https:\/\/www.carrier.com\/residential\/en\/us\/products\/ (accessed January 13, 2026)."},{"key":"10.1016\/j.aei.2026.104794_b0365","unstructured":"TRANE. Airside Products; 2026. https:\/\/www.trane.com\/commercial\/north-america\/us\/en\/products-systems\/airside-equipment.html\/ (accessed January 13, 2026)."},{"key":"10.1016\/j.aei.2026.104794_b0370","unstructured":"YORK. Air Handling Units--Get Ultimate Flexibility without Sacrificing Quality; 2026. https:\/\/www.york.com\/commercial-equipment\/air-systems\/air-handling-units\/ (accessed January 13, 2026)."},{"key":"10.1016\/j.aei.2026.104794_b0375","unstructured":"AMERICAN VENTUS. Products; 2026. https:\/\/vtsgroup.com\/us\/products\/ (accessed January 13, 2026)."},{"key":"10.1016\/j.aei.2026.104794_b0455","unstructured":"Panasonic. Products and Systems; 2026. https:\/\/www.panasonic.com\/global\/hvac\/products.html\/ (accessed January 13, 2026)."},{"key":"10.1016\/j.aei.2026.104794_b0380","unstructured":"Petasense. Revolutionizing AHU Maintenance: Case Studies on Predictive Health Monitoring; 2026. https:\/\/petasense.com\/revolutionizing-ahu-maintenance-case-studies-predictive-health-monitoring\/ (accessed January 13, 2026)."},{"key":"#cr-split#-10.1016\/j.aei.2026.104794_b0385.1","unstructured":"Seattle Public Schools. BEX IV: Resolution 2019\/20-5: Acceptance of the Building Commissioning Report for the Loyal Heights Elementary School Modernization and Addition Project"},{"key":"#cr-split#-10.1016\/j.aei.2026.104794_b0385.2","unstructured":"2019. https:\/\/www.seattleschools.org\/wp-content\/uploads\/2021\/07\/I08_20180828_Resolution-2019-20-5-Loyal-Heights-Building-Commissioning-Report.pdf\/ (accessed January 13, 2026)."},{"key":"10.1016\/j.aei.2026.104794_b0390","unstructured":"TRANE. Air Handler Maintenance; 2026. https:\/\/www.trane.com\/residential\/en\/resources\/maintenance-tips\/air-handlers\/ (accessed January 13, 2026)."},{"key":"10.1016\/j.aei.2026.104794_b0395","unstructured":"California Energy Codes & Standards. 2022 Cycle CASE Reports; 2022. https:\/\/title24stakeholders.com\/2022-cycle-case-reports\/ (accessed January 13, 2026)."},{"key":"10.1016\/j.aei.2026.104794_b0400","unstructured":"California Energy Codes & Standards. 2025 Cycle CASE Reports; 2025. https:\/\/title24stakeholders.com\/2025-cycle-case-reports\/ (accessed January 13, 2026)."},{"key":"10.1016\/j.aei.2026.104794_b0405","unstructured":"California Energy Codes & Standards. CASE Reports from Previous Cycles; 2022. https:\/\/title24stakeholders.com\/archived-case-reports\/ (accessed January 13, 2026)."},{"key":"10.1016\/j.aei.2026.104794_b0410","unstructured":"China National Standards. GB\/T 10891-1989Safety requirements for air handling units. Beijing: The Standardization Administration of the People's Republic of China; 1989."},{"key":"10.1016\/j.aei.2026.104794_b0415","unstructured":"ASHRAE. Standard 62.1-2025 -- Ventilation and Acceptable Indoor Air Quality. Atlanta: ASHRAE Inc; 2025."},{"key":"10.1016\/j.aei.2026.104794_b0420","unstructured":"ASHARE. Standard 90.1-2022-- Energy Standard for Sites and Buildings Except Low-Rise Residential Buildings. Atlanta: ASHRAE Inc; 2022."},{"key":"10.1016\/j.aei.2026.104794_b0425","unstructured":"European Committee for Standardization. EN 13053:2019--Ventilation for buildings - Air handling units - Rating and performance for units, components and sections. Brussels: European Committee for Standardization; 2019."},{"key":"10.1016\/j.aei.2026.104794_b0430","unstructured":"Wang SK. Handbook of air conditioning and refrigeration. 2th ed. New York: McGraw-Hill Inc; 2001."},{"key":"10.1016\/j.aei.2026.104794_b0435","doi-asserted-by":"crossref","unstructured":"Chadderton D. Air conditioning: a practical introduction. 3rd ed. London: Routledge Inc; 2014.","DOI":"10.4324\/9781315794068"},{"key":"10.1016\/j.aei.2026.104794_b0440","doi-asserted-by":"crossref","unstructured":"Jones WP. Air conditioning engineering. 5th ed. London: Routledge Inc; 2007.","DOI":"10.4324\/9780080498942"},{"key":"10.1016\/j.aei.2026.104794_b0445","doi-asserted-by":"crossref","unstructured":"Jones WP. Air conditioning application and design. 2nd ed. London: Routledge Inc; 2012.","DOI":"10.4324\/9780080498935"},{"key":"10.1016\/j.aei.2026.104794_b0450","doi-asserted-by":"crossref","unstructured":"Kreider JF. Handbook of heating, ventilation, and air conditioning. 1st ed. Boca Raton: CRC Press Inc; 2000.","DOI":"10.1201\/9781420036466"},{"key":"10.1016\/j.aei.2026.104794_b0260","doi-asserted-by":"crossref","DOI":"10.1016\/j.buildenv.2022.109357","article-title":"Causal discovery-based external attention in neural networks for accurate and reliable fault detection and diagnosis of building energy systems","volume":"222","author":"Zhang","year":"2022","journal-title":"Build. Environ."},{"key":"10.1016\/j.aei.2026.104794_b0265","doi-asserted-by":"crossref","DOI":"10.1016\/j.enbuild.2025.116658","article-title":"A label-free hybrid fault detection and diagnosis approach for HVAC systems using bayesian networks","volume":"351","author":"Paolini","year":"2026","journal-title":"Energy Build."},{"key":"10.1016\/j.aei.2026.104794_b0270","unstructured":"Hurst A, Lerer A, Goucher AP, Perelman A, Ramesh A, Clark A, et al. GPT-4o system card. arXiv preprint 2024. https:\/\/doi.org\/10.48550\/arXiv.2410.21276."},{"key":"10.1016\/j.aei.2026.104794_b0275","unstructured":"Ackerman C, Panickssery N. Inspection and control of self-generated-text recognition ability in Llama3-8b-instruct. arXiv preprint 2024. https:\/\/doi.org\/10.48550\/arXiv.2410.02064."},{"key":"10.1016\/j.aei.2026.104794_b0280","doi-asserted-by":"crossref","unstructured":"Tang P, Yang C, Xing T, Xu X, Jiang R, Sezaki K. Instruction-tuning llama-3-8B excels in city-scale mobility prediction. arXiv preprint 2024. https:\/\/doi.org\/10.48550\/arXiv.2410.23692.","DOI":"10.1145\/3681771.3699908"},{"key":"10.1016\/j.aei.2026.104794_b0285","unstructured":"Liu A, Feng B, Xue B, Wang B, Wu B, Lu C, et al. DeepSeek-V3 technical report. arXiv preprint 2025. https:\/\/doi.org\/10.48550\/arXiv.2412.19437."},{"key":"10.1016\/j.aei.2026.104794_b0290","unstructured":"OPENAI. Introducing GPT-5; 2025. https:\/\/openai.com\/index\/introducing-gpt-5\/ (accessed January 12, 2026)."},{"key":"10.1016\/j.aei.2026.104794_b0295","unstructured":"ANTHROPIC. Introducing the next generation of claude; 2024. https:\/\/www.anthropic.com\/news\/claude-3-family\/ (accessed January 12, 2026)."},{"key":"10.1016\/j.aei.2026.104794_b0300","doi-asserted-by":"crossref","unstructured":"Sood S, Loguinov D. Probabilistic near-duplicate detection using simhash. In: Proceedings of the 20th ACM international conference on Information and knowledge management, 2011, p. 1117\u201326. https:\/\/doi.org\/10.1145\/2063576.2063737.","DOI":"10.1145\/2063576.2063737"},{"key":"10.1016\/j.aei.2026.104794_b0305","doi-asserted-by":"crossref","unstructured":"Zheng Y, Zhang R, Zhang J, Ye Y, Luo Z, Feng Z, et al. LlamaFactory: unified efficient fine-tuning of 100+ language models. arXiv preprint 2024. https:\/\/doi.org\/10.48550\/arXiv.2403.13372.","DOI":"10.18653\/v1\/2024.acl-demos.38"},{"key":"10.1016\/j.aei.2026.104794_b0310","doi-asserted-by":"crossref","first-page":"1412","DOI":"10.1109\/TASE.2018.2876611","article-title":"Identifying unseen faults for smart buildings by incorporating expert knowledge with data","volume":"16","author":"Li","year":"2019","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"10.1016\/j.aei.2026.104794_b0315","doi-asserted-by":"crossref","DOI":"10.1016\/j.apenergy.2024.123238","article-title":"An interpretable framework for modeling global solar radiation using tree-based ensemble machine learning and shapley additive explanations methods","volume":"364","author":"Song","year":"2024","journal-title":"Appl. Energy"},{"key":"10.1016\/j.aei.2026.104794_b0320","doi-asserted-by":"crossref","first-page":"1419","DOI":"10.1007\/s12273-024-1149-y","article-title":"End-to-end data-driven modeling framework for automated and trustworthy short-term building energy load forecasting","volume":"17","author":"Zhang","year":"2024","journal-title":"Build. Simul."},{"key":"10.1016\/j.aei.2026.104794_b0325","doi-asserted-by":"crossref","first-page":"427","DOI":"10.1016\/j.ipm.2009.03.002","article-title":"A systematic analysis of performance measures for classification tasks","volume":"45","author":"Sokolova","year":"2009","journal-title":"Inf. Process. Manage."}],"container-title":["Advanced Engineering Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1474034626004866?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1474034626004866?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T20:12:38Z","timestamp":1783109558000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1474034626004866"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":92,"alternative-id":["S1474034626004866"],"URL":"https:\/\/doi.org\/10.1016\/j.aei.2026.104794","relation":{},"ISSN":["1474-0346"],"issn-type":[{"value":"1474-0346","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"LightLLM4FDD: Domain-specific lightweight large language models for fault detection and diagnosis in building HVAC systems","name":"articletitle","label":"Article Title"},{"value":"Advanced Engineering Informatics","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.aei.2026.104794","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104794"}}