Long-term Faults Research Articles

Machine Learning-Based Automated Fault Detection and Diagnostics in Building Systems

Automated fault detection and diagnostics analysis in commercial building systems using machine learning (ML) can improve the building’s efficiency and conserve energy costs from inefficient equipment operation. However, ML can be challenging to implement in existing systems due to a lack of common data standards and because of a lack of building operators trained in ML techniques. Additionally, results from ML procedures can be complicated for untrained users to interpret. Boolean rule-based analysis is standard in current automated fault detection and diagnostics (AFDD) solutions but limits analysis to the rules defined and calibrated by energy engineers. Boolean rule-based analysis and ML can be combined to create an effective fault detection and diagnostics (FDD) tool. Three examples of ML’s advantages over rule-based analysis are explored by analyzing functional building equipment. ML can detect long-term faults in the system caused by a lack of system maintenance. It can also detect faults in system components with incomplete sets of sensors by modeling expected system operations and by making comparisons to actual system operations. An example of ML detecting a failure in a building is shown along with a demonstration of the soft decision boundaries of ML-based FDD compared to Boolean rule-based FDD analysis. The results from the three examples are used to demonstrate the strengths and weaknesses of using ML for AFDD analysis.

Methodology for the Identification of Dust Accumulation Levels in Photovoltaic Panels Based in Heuristic-Statistical Techniques

The use of renewable energies is increasing around the world in order to deal with the environmental and economic problems related with conventional generation. In this sense, photovoltaic generation is one of the most promising technologies because of the high availability of sunlight, the easiness of maintenance, and the reduction in the costs of installation and production. However, photovoltaic panels are elements that must be located outside in order to receive the sun radiation and transform it into electricity. Therefore, they are exposed to the weather conditions and many environmental factors that can negatively affect the output delivered by the system. One of the most common issues related to the outside location is the dust accumulation in the surface of the panels. The dust particles obstruct the passage of the sunlight, reducing the efficiency of the generation process and making the system prone to experimental long-term faults. Thus, it is necessary to develop techniques that allow us to assess the level of dust accumulation in the panel surface in order to schedule a proper maintenance and avoid losses associated with the reduction of the delivered power and unexpected faults. In this work, we propose a methodology that uses a machine learning approach to estimate different levels of dust accumulation in photovoltaic panels. The developed method takes the voltage, current, temperature, and sun radiance as inputs to perform a statistical feature extraction that describes the behavior of the photovoltaic system under different dust conditions. In order to retain only the relevant information, a genetic algorithm works along with the principal component analysis technique to perform an optimal feature selection. Next, the linear discrimination analysis is carried out using the optimized dataset to reduce the problem dimensionality, and a multi-layer perceptron neural network is implemented as a classifier for discriminating among three different conditions: clean surface, slight dust accumulation, and severe dust accumulation. The proposed methodology is implemented using real signals from a photovoltaic installation, proving to be effective not only to determine if a dust accumulation condition is present but also when maintenance actions must be performed. Moreover, the results demonstrate that the accuracy of the proposed method is always above 94%.

Analysis on the Control of Faults on the Formation of P-1 Reservoir in Syncline Area of X Oilfield

Hydrocarbon occurrence in Putaohua Formation of Xujiaweizi Syncline area is largely controlled by three types of faults. The long-term faults were the conduit of hydrocarbon from source rock Q1 to Putaohua reservoir. These long-term faults could cause new accumulation and leakage of accumulated hydrocarbon simultaneously during their active time. The middle-term and short-term faults are the sealing faults to enforce the entrapment of hydrocarbon in the fault-block traps. The relationship of fault conduits with the related traps is the main controlling factor for the hydrocarbon distribution in the faulted blocks around the center of Xujiaweizi Syncline. This hypothesis can well explain why the central portion of the syncline is with poorer accumulation than the surrounding horst blocks in which the accumulation are rich in their anticline structure traps.

Fault Diagnosis of Rolling Bearings in Rail Train Based on Exponential Smoothing Predictive Segmentation and Improved Ensemble Learning Algorithm

The rolling bearing is a key component of the bogie of the rail train. The working environment is complex, and it is easy to cause cracks and other faults. Effective rolling bearing fault diagnosis can provide an important guarantee for the safe operation of the track while improving the resource utilization of the rolling bearing and greatly reducing the cost of operation. Aiming at the problem that the characteristics of the vibration data of the rolling bearing components of the railway train and the vibration mechanism model are difficult to establish, a method for long-term faults diagnosis of the rolling bearing of rail trains based on Exponential Smoothing Predictive Segmentation and Improved Ensemble Learning Algorithm is proposed. Firstly, the sliding time window segmentation algorithm of exponential smoothing is used to segment the rolling bearing vibration data, and then the segmentation points are used to construct the localized features of the data. Finally, an Improved AdaBoost Algorithm (IAA) is proposed to enhance the anti-noise ability. IAA, Back Propagation (BP) neural network, Support Vector Machine (SVM), and AdaBoost are used to classify the same dataset, and the evaluation indexes show that the IAA has the best classification effect. The article selects the raw data of the bearing experiment platform provided by the State Key Laboratory of Rail Traffic Control and Safety of Beijing Jiaotong University and the standard dataset of the American Case Western Reserve University for the experiment. Theoretical analysis and experimental results show the effectiveness and practicability of the proposed method.

Transient Stability Analysis for Offshore Wind Power Plant Integration Planning Studies—Part I: Short-Term Faults

Power system planning is the process of forecasting load demand and ensuring sufficient generation and reserve capacities over some planning horizon. This process includes investigation of steady-state and dynamic operations of the power system of interest. This paper addresses the transient stability (also known as large-signal stability) analysis of power systems for offshore wind power plant integration planning studies. In particular, this study develops a comprehensive practical methodology to assess the transient stability of power systems, including rotor angle stability, voltage stability, and frequency response for large scale power systems. This methodology considers variability of the offshore wind power plants as well as the type of any faulted system's components present. Additionally, this methodology is applicable to the study of both short-term and long-term faults, though only short-term faults are considered here (long-term faults are treated sequentially in a companion paper). This paper considers the integration of offshore wind power plants into existing power systems and demonstrates the utility of this methodology through the examination of the specific case of integrating 1000 MW of offshore wind power into the FirstEnergy/PJM service territory using a realistic model of 63k-bus test system that represents the U.S. Eastern Interconnection.

Off-fault long-term damage: A condition to account for generic, triangular earthquake slip profiles

Natural earthquake slip profiles have a generic triangular shape which the available rupture dynamics models fail to reproduce. Long-term faults are embedded in long-damaged crustal material, and the properties of the long-term damage vary both across and along the faults. We examine the effects of the predamaged state of the medium on the earthquake slip distributions. We simulate long-term damage by the decrease in the elastic modulus of the medium around the fault. We model the dynamic crack-like rupture of a slip-weakening planar, right-lateral strike-slip fault, and search which geometries and elastic properties of the long-term damage produce a triangular slip profile on the rupture. We find that such a profile is produced only when a laterally heterogeneous preexisting damage zone surrounds the ruptured fault. The highest on-fault slip develops in the most compliant region of the damage zone, and not necessarily above the earthquake hypocenter. The coseismic slip decreases in zones of stiffer damage. The amount of coseismic slip dissipated in the damage zone is large, at least 25–40% of maximum on-fault slip, and can occur over large distances from the fault. Our study thus emphasizes that off-fault preexisting damage should be considered for an accurate description of earthquake ruptures. It also motivates a reformulation of the available earthquake source inversion models since most of them do not include the inelastic deformations that occur in the near field of the earthquake ruptures.

Characteristics of Fault and its Controlling to Hydrocarbon Accumulation in the Yumin Area Northern, Songliao Basin

By using seismic, logging, test oil data, based on the analysis about development characteristics and movement stages of faults, and their control to the deposition of Fuyu oil layer, this paper studied the control of fault belts to hydrocarbon accumulation and characteristics of hydrocarbon migration and accumulation in different fault belts. Study shows that the faults of Fuyu oil layer are made up of middle and long-term faults, which are mainly formed or active in the early deposition of Qingshankou Formation, in a plane the faults are dense to be in belt by the control of basement fault. The distribution of sand bodies and strike of distributary channel of Fuyu oil layer is controlled by basement fault and long-term growth fault, there are three spatial combinations between fault belts and distributary channel:Low-angle intersection, High-angle intersection, and distributary channels long-distance extension along the fault belt in the upside of the boundary fault. The spatial combinations between fault belts and sand bodies determine hydrocarbon migration way and its accumulation in the fault belts: in the eastern hydrocarbon is transported by transporting fault-sand mode, the traps within and besides the fault belt communicated by transporting passage are both accumulated by hydrocarbon, in the western hydrocarbon is transported by boundary fault-sand mode,the oiliness becomes gradually poor from both sides to the inter of fault belt.