An enhanced principal component analysis method with Savitzky–Golay filter and clustering algorithm for sensor fault detection and diagnosis

Applied Energy, Journal Year: 2023, Volume and Issue: 337, P. 120862 - 120862

Published: Feb. 27, 2023

Language: Английский

---

Cause analysis of hot work accidents based on text mining and deep learning

Journal of Loss Prevention in the Process Industries, Journal Year: 2022, Volume and Issue: 76, P. 104747 - 104747

Published: Feb. 7, 2022

Language: Английский

---

Deep learning GAN-based data generation and fault diagnosis in the data center HVAC system

Energy and Buildings, Journal Year: 2023, Volume and Issue: 289, P. 113072 - 113072

Published: April 12, 2023

Language: Английский

---

Data‐driven fault diagnosis approaches for industrial equipment: A review

Expert Systems, Journal Year: 2023, Volume and Issue: 41(2)

Published: May 30, 2023

Abstract Undetected and unpredicted faults in heavy industrial machines/equipment can lead to unwanted failures. Therefore, prediction of puts paramount importance on maintaining the reliability availability capital‐intensive equipment. Due large number interconnected interdependent mechanical electrical components machines, fault analysis becomes a complex challenging task. Under these circumstances, data‐driven diagnosis (DDFD) is one most powerful, reliable cost‐effective artificial intelligence tools detect, isolate, identify classify occurrence faults. This article aims make comprehensive literature survey various DDFD approaches used for analysing machines/equipment; summarizing strengths, limitations, possible applications existing methods. Analysing synthesizing 190 research works conducted last two decades revealed three types approaches: supervised‐learning, semi‐supervised‐learning unsupervised‐learning‐based diagnosis. The supervised‐learning predominantly applied contributing 82% works. this special emphasis supervised‐learning‐based diagnosis: (i) classification‐based neural network approach, (ii) inference‐based Bayesian approach. Finally, have been briefly discussed with effectiveness models their inclusion future applications.

Language: Английский

---

Experimental study on performance assessments of HVAC cross-domain fault diagnosis methods oriented to incomplete data problems

Building and Environment, Journal Year: 2023, Volume and Issue: 236, P. 110264 - 110264

Published: April 5, 2023

Language: Английский

---

Credit risk prediction based on causal machine learning: Bayesian network learning, default inference, and interpretation

Journal of Forecasting, Journal Year: 2024, Volume and Issue: 43(5), P. 1625 - 1660

Published: Feb. 27, 2024

Abstract The predictive and interpretable power of models is crucial for financial risk management. purpose this study was to perform credit prediction in a structured causal network with four stages—data processing, structural learning, parameter interpretation inferences—and use six real datasets conduct empirical research on the proposed model. Compared traditional machine learning algorithms, we comprehensively explain results default through forward reverse reasoning. We also compared our model post hoc local model‐agnostic explanations (LIME) shapley additive (SHAP) verify interpretability Bayesian networks. experimental show that performance networks superior similar ensemble models. Furthermore, offer valuable insights into interplay features by considering their relationships enable an assessment how individual influence outcome. In study, what‐if analysis performed assess probabilities under various conditions. This provides decision‐makers necessary tools make informed judgments about profile borrowers. Consequently, consider as viable tool terms interpretability.

Language: Английский

---

Causal discovery-based external attention in neural networks for accurate and reliable fault detection and diagnosis of building energy systems

Building and Environment, Journal Year: 2022, Volume and Issue: 222, P. 109357 - 109357

Published: July 2, 2022

Language: Английский

---

Three-model-driven fault diagnosis method for complex hydraulic control system: Subsea blowout preventer system as a case study

Expert Systems with Applications, Journal Year: 2024, Volume and Issue: 247, P. 123297 - 123297

Published: Jan. 23, 2024

Language: Английский

---

An interpretable graph convolutional neural network based fault diagnosis method for building energy systems

Building Simulation, Journal Year: 2024, Volume and Issue: 17(7), P. 1113 - 1136

Published: June 20, 2024

Language: Английский

---

A study on transfer learning in enhancing performance of building energy system fault diagnosis with extremely limited labeled data

Building and Environment, Journal Year: 2022, Volume and Issue: 225, P. 109641 - 109641

Published: Sept. 28, 2022

Language: Английский

---