From bearings to substations: Transfer Learning for fault detection in district heating

Metamorphoses of cogeneration-based district heating in Romania: A case study

This report summarizes a comprehensive literature review for the selected sensor suites used in building controls and fault detection and diagnostics (FDD), which is a Q2 deliverable of the Sensor Impact Evaluation and Verification project. The project’s overarching goal is to develop a framework for investigating the impact of sensor deployment and configuration for building energy optimization, fault detection and diagnosis (FDD), occupants’ thermal comfort, and potential grid efficiency. While the first phase of the literature review performed in Q1 reviewed the current methods of various sensor selection and placements and their impact, this report focuses on high impactful potential use cases for the selected sensor suites in building control and FDD. The use cases identified in this literature review will be further investigated and be included in the final sensor impact evaluation framework. For the review, the multi-laboratory team reviewed 241 research papers, technical reports, and books to identify existing technologies, the potential impact on energy savings and thermal comfort, and future research opportunities for the selected use cases in building controls and FDD. Along with the literature review, the team conducted a series of interviews with experts in sensors and controls area to identify the state-of-art sensor technologies, and the most impactful use cases in controls and FDD areas. The interview results will also be incorporated with the findings from the literature review in the next quarter, and the final use cases to be evaluated will be selected.

Comparative Analysis Between District Heating and Geothermal Heat Pump System

This paper presents a methodology for satellite sensors' fault detection and diagnosis (FDD) in a fault-tolerant attitude determination system using a nonlinear interacting-multiple-model approach (IMM). Moreover, the fault-tolerant attitude determination system utilizes the IMM approach in the presence of sensors' total fault to estimate faulty sensors and attitude states. This methodology relies on the most conventional satellite attitude sensors including magnetometer, sun sensor, and gyroscope measurements. The presented scheme leads to a significant computational time-saving method due to considering a pre-filter Kalman for fault detection, hence, the proposed FDD approach consists of two stages. In the first stage, the pre-filter Kalman detects any sensor fault and attitude states. In contrast, in the next stage, fault diagnosis and optimal attitude estimation are obtained through the IMM approach. Therefore, the IMM algorithm will be activated to extract the optimal estimation and identify faulty sensor(s). A Monte Carlo type approach is used to verify this technique for various initial conditions. Through numerical and Monte Carlo simulations, it is shown that the proposed scheme is robust against sensors' total fault, and the system is capable of detecting and isolating accurately the faulty sensor. Hardware in the loop tests using satellite dynamics simulator are also used to validate the presented system performance.

Techno-economic model for district heating systems

Hybrid modeling based double-granularity fault detection and diagnosis for quadrotor helicopter

Electric Vehicles (EVs) are emerging as the preferred mode of transportation owing to various advantages and to reach the Sustainable Development Goals (SDGs). However, the commercial usage of EVs is in its initial stage, due to multiple factors, among which faults caused by the operational environment and component failures are one. Furthermore, early diagnosis of such faults is necessary to protect from severe damage and catastrophic failures. This paper presents various fault modes in EV components, their impact on EV performance, and Fault Detection and Diagnosis (FDD) practices. Later sections of the paper focus on the use of Artificial Intelligence (AI) and Machine Learning (ML) techniques in FDD. Also, it provides a comparative analysis of model-based, signal-based, data-driven, and hybrid FDD approaches. Additionally, the paper explores component-specific FDD techniques, modelling of drive faults, current research trends, and suggestions on the selection of feature extraction techniques. Furthermore, the paper highlights the need to develop a hybrid FDD method to enhance the accuracy, reliability, and speed of FDD in EVs. The future scope of EV FDD techniques, considering various aspects, is also presented.

Promoting efficient district heating in Estonia

Fault detection and diagnosis based on transfer learning for multimode chemical processes

This study presents a comprehensive methodology for developing a Fault Detection and Diagnosis (FDD) system for an industrial distillation column using advanced machine learning algorithms. Steady state and dynamic simulations in Aspen Plus® generate extensive datasets under normal and faulty conditions. Feature engineering, using the Minimum Redundancy Maximum Relevance (MRMR) algorithm, selects the most relevant features for fault detection. Various machine learning models, including Decision Trees, Support Vector Machines, k-nearest Neighbours, and Neural Networks, were trained and evaluated based on performance metrics such as accuracy, recall, precision, and F1 score. The top models were integrated into a stacked classifier system with a voting mechanism to enhance fault detection reliability. Explainable Artificial Intelligence (XAI) techniques, such as Local Interpretable Model-agnostic Explanations (LIME) and Shapley Additive Explanations (SHAP), were incorporated to improve model interpretability, allowing engineers to understand and validate the FDD system's decision-making process. Simulation results confirm that the proposed methodology accurately identifies and classifies faults. By integrating dynamic simulations, advanced machine learning, and XAI techniques, a robust and scalable solution is achieved for fault detection in distillation columns, improving operational reliability, safety, and reducing downtime. Future work could extend this approach to other industrial processes and explore additional machine learning algorithms to further enhance performance.

The problem of fault detection and diagnosis (FDD) in dynamic systems has received considerable attention in last decades due to the growing complexity of modern engineering systems and ever increasing demand for fault tolerance, cost efficiency, and reliability (Willsky, 1976; Basseville, 1988). Existing FDD approaches can be roughly divided into two major categories including model-based and knowledge-based approaches (Venkatasubramanian et al., 2003a; Venkatasubramanian et al., 2003b). Model-based approaches make use of the quantitative analytical model of a physical system. Knowledgebased approaches do not need full analytical modeling and allow one to use qualitative models based on the available information and knowledge of a physical system. Whenever the mathematical models describing the system are available, analytical model-based methods are preferred because they are more amenable to performance analysis. Generally, there are two steps in the procedure of model-based FDD. First, on the basis of the available observations and a mathematical model of the system, the state variable x and test statistics are required to be obtained. Then, based on the generated test statistics, it is required to decide on the potential occurrence of a fault. For linear and Gaussian systems, the Kalman filter (KF) is known to be optimal and employed for state estimation. The innovations from the KF are used as the test statistics, based on which hypothesis tests can be carried out for fault detection (Belcastro & Weinstein, 2002). In reality, however, the models representing the evolution of the system and the noise in observations typically exhibit complex nonlinearity and non-Gaussian distributions, thus precluding analytical solution. One popular strategy for estimating the state of such a system as a set of observations becomes available online is to use sequential Monte-Carlo (SMC) methods, also known as particle filters (PFs) (Doucet et al., 2001). These methods allow for a complete representation of the posterior probability distribution function (PDF) of the states by particles (Guo & Wang, 2004; Li & Kadirkamanathan, 2001). The aforementioned FDD strategies are single-model-based. However, a single-model-based FDD approach is not adequate to handle complex failure scenarios. One way to treat this

In this paper, a fault detection and diagnosis (FDD) scheme is presented for general stochastic dynamic systems with time delays. Originated from some practical processes, it is supposed that the measured information is the probability density function (PDF) of the system output rather than its actual value, which is different from the classical FDD problem. A B-spline expansion technique is applied so that the output PDF can be formulated in terms of the dynamic weights of the B-spline expansion. This leads to a dynamic model between the input and the weights where nonlinearities, uncertainties and time delays are included. As a result, the concerned FDD problem is transformed into a classic nonlinear FDD problem subject to an uncertain nonlinear system with time delays. Feasible criteria to detect the system fault are obtained and an adaptive fault diagnosis method is further presented to produce an estimate of the size of fault. Simple simulations are given to demonstrate the efficiency of the proposed approach.

Knowledge-Enhanced Spatiotemporal Analysis for Anomaly Detection in Process Manufacturing

Machine-learning-based multi-step heat demand forecasting in a district heating system

Physics theory integrated machine learning models enhance the interpretability and performance of artificial intelligence (AI) techniques to real-world industrial applications, such as the fault detection and diagnosis (FDD) of air handling units (AHU). Traditional machine learning-based automated FDD model demonstrates a high classification accuracy with sufficient training data samples, however, suffers from physical interpretation of the machine learning models. In this article, a physical model integrated Wasserstain generative adversarial network (WGAN) model is presented for AHU FDD with a scenario of insufficient training data samples. The proposed solution tackles the real-world problem of AHU FDD and enhances the model interpretability significantly. A transformer-WGAN model is designed to further improve the proposed FDD framework. Experimental results show that the proposed method outperforms existing AHU FDD methods with imbalanced real-world training data samples.