Predictive Maintenance Strategies for HVAC Systems: Leveraging MPC, Dynamic Energy Performance Analysis, and ML Classification Models

References

[1] Zhao Y, Li T, Zhang X, Zhang C. Artificial intelligence-based fault detection and diagnosis methods for building energy systems: advantages, challenges and the future. Renewable Sustainable Energy Rev 2019;109:85–101.

[2] Gondalia, A., Dixit, D., Parashar, S., Raghava, V., Sengupta, A. and Sarobin, V.R., 2018. IoTbased healthcare monitoring system for war soldiers using machine learning. Procedia computer science, 133, pp.1005-1013.

[3] Anghel, I., Cioara, T., Moldovan, D., Salomie, I. and Tomus, M.M.,2018 IEEE 16th International Conference on Embedded and Ubiquitous Computing (EUC) (pp. 29-36).

[4] A. Afram, F. Janabi-Sharifi, Gray-box modeling and validation of residential HVAC system for control system design, Appl. Energy 137 (2015) 134–150.

[5] A. Afram, F. Janabi-Sharifi, Review of modeling methods for HVAC systems, Appl. Therm. Eng. 2 (2014) 507–519.

[6] W. Kim, Y. Jeon, Y. Kim, Simulation-based optimization of an integrated daylighting and HVAC system using the design of experiments method, Appl. Energy 162 (2016) 666–674.

[7] Kim, J.K., Han, Y.S. and Lee, J.S., 2017. Concurrency and Computation: Practice and Experience, 29(11), p.e4128.

[8] Liaw, Y.C., 2011. , International Conference on Image Processing, Computer Vision, and Pattern Recognition (IPCV) (p. 1).

[9] Zhou, C., Tham, C.-K., 2018. Graphel: a graph-based ensemble learning method for distributed diagnostics and prognostics in the industrial internet of things. In: 2018 IEEE 24th International Conference on Parallel and Distributed Systems (ICPADS), IEEE, pp. 903–909.

[10] Schmidt, B., Wang, L., 2018. Predictive maintenance of machine tool linear axes: a case from manufacturing industry. Proc. Manuf. 17, 118–125.

[11] Carbery, C.M., Woods, R., Marshall, A.H., 2018. A bayesian network based learning system for modelling faults in large-scale manufacturing. 2018 IEEE International Conference on Industrial Technology (ICIT), 1357–1362.

[12] Ansari, F., Glawar, R., Sihn, W., 2020. Prescriptive maintenance of cpps by integrating multimodal data with dynamic bayesian networks. In: Machine Learning for Cyber Physical Systems, Springer, pp. 1–8.

[13] Rivas, A., Fraile, J.M., Chamoso, P., González-Briones, A., Sittón, I., Corchado, J.M., 2019. A predictive maintenance model using recurrent neural networks. In: International Workshop on Soft Computing Models in Industrial and Environmental Applications, Springer, pp. 261–270.

[14] ADHIKARI, P., RAO, H.G., BUDERATH, D.-I.M., 2018. Machine Learning Based Data Driven Diagnostics & Prognostics Framework for Aircraft Predictive Maintenance.

[15] Cai W, Liu F, Zhang H, Liu P, Tuo J. Development of dynamic energy benchmark for mass production in machining systems for energy management and energy efficiency improvement. Appl Energy 2017;202:715–25.

[16] Li H, Li X. Benchmarking energy performance for cooling in large commercial buildings. Energy Build 2018;176:179–93.

[17] Attia S, Shadmanfar N, Ricci F. Developing two benchmark models for nearly zero energy schools. Appl Energy 2020;263:114614.

[18] Liu J, Chen H, Liu J, Li Z, Huang R, Xing L, et al. An energy performance evaluation methodology for individual office building with dynamic energy benchmarks using limited information. Appl Energy 2017;206:193–205.

[19] Yan C, Wang S, Xiao F, Gao D-C. A multi-level energy performance diagnosis method for energy information poor buildings. Energy 2015;83:189–203.

[20] Wang H, Xu P, Lu X, Yuan D. Methodology of comprehensive building energy performance diagnosis for large commercial buildings at multiple levels. Appl Energy 2016;169:14–27.

[21] Indian Dataset for Ambient Water and Energy (IAWE 2013), Nipun Batra, IIITD

[22] M. Ning, M. Zaheeruddin, Neuro-optimal operation of a variable air volume HVAC&R system, Appl. Therm. Eng. 30 (2010) 385–399

[23] B.C. Ng, I.Z.M. Darus, H. Jamaluddin, H.M. Kamar, Application of adaptive neural predictive control for an automotive air conditioning system, Appl. Therm. Eng. 73 (2014) 1244–1254

[24] A. Kusiak, G. Xu, Z. Zhang, Minimization of energy consumption in HVAC systems with data-driven models and an interior-point method, Energy Convers. Manag. 85 (2014) 146–153.

[25] X. He, Z. Zhang, A. Kusiak, Performance optimization of HVAC systems with computational intelligence algorithms, Energy Build. 81 (2014) 371–380.

[26] P. Ferreira, A. Ruano, S. Silva, E.Z.E. Conceic¸ ão, Neural networks based predictive control for thermal comfort and energy savings in public buildings, Energy Build. 55 (2012) 238–251.

[27] X. Wei, A. Kusiak, M. Li, F. Tang, Y. Zeng, Multi-objective optimization of the HVAC (heating, ventilation, and air conditioning) system performance, Energy 83 (2015) 294–306.

[28] Y. Zeng, Z. Zhang, A. Kusiak, Predictive modeling and optimization of a multi-zone HVAC system with data mining and firefly algorithms, Energy 86 (2015) 393–402.

[29] L. Maciej, Computationally Efficient Model Predictive Control Algorithms, Springer, 2014.

@article{1705111,
      author = {Divyansh Singh, Mohd. Arshad, Bhaumik Tyagi, Garv Kalia},
      title = {Predictive Maintenance Strategies for HVAC Systems: Leveraging MPC, Dynamic Energy Performance Analysis, and ML Classification Models},
      journal = {Iconic Research And Engineering Journals},
      year = {2023},
      volume = {7},
      number = {4},
      pages = {98-108},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1705111.pdf},
      abstract = {This research explores the multifaceted challenges that can affect ventilation, air conditioning systems, and heating appliances, leading to reduced operational efficiency, heightened energy consumption, and increased maintenance expenses. Predictive maintenance, a progressive approach, is investigated as a pivotal strategy, complementing traditional HVAC equipment maintenance paradigms, including breakdown maintenance and preventative machine learning. Utilizing a diverse set of predictive models infused with machine learning techniques, this study employs the 'Semiconductor Manufacturing Process (SECOM) dataset' to simulate the manufacturing processes of HVAC systems, aligning with characteristics akin to semiconductor-based devices. The research undertakes a comparative analysis, contrasting the predictive capabilities of the Random Forest (RF) algorithm with the Support Vector Machine (SVM) in areas such as problem detection, diagnostics, and load monitoring. Notably, the RF model demonstrates superior prediction accuracy. The research aims to proactively detect potential HVAC system or component issues, discerning the nature of impending failures at their earliest stages to enable proactive maintenance strategies. Evaluation metrics such as the Receiver Operating Characteristic (ROC) curve and accuracy are employed for rigorous comparative analysis across various predictive machine learning classification models. Furthermore, a comprehensive 'dynamic energy performance benchmark' framework is meticulously developed for HVAC systems, facilitating real-time operational performance assessment and the identification of irregularities in power utilization at different operational stages. Additionally, Artificial Neural Network (ANN) models are employed to establish an administrative Model Predictive Control (MPC) system tailored for residential HVAC applications.},
      keywords = {Predictive maintenance, supervised machine learning, MPC, Random Forest, Fault detection & diagnosis.},
      month = {October},
  }