scholarly journals Fault Propagation Inference Based on a Graph Neural Network for Steam Turbine Systems

Energies ◽  
2021 ◽  
Vol 14 (2) ◽  
pp. 309
Author(s):  
Yi-Jing Zhang ◽  
Li-Sheng Hu
Keyword(s):  
Neural Network ◽  
Steam Turbine ◽  
Link Prediction ◽  
Graph Model ◽  
Normal Operation ◽  
Prediction Methods ◽  
Industrial System ◽  
Fault Propagation ◽  
Graph Topology ◽  
System A

A fault propagates along physical paths until it reaches the boundary of the equipment or system, which shows as a functional failure. Hence, inferring the fault propagation helps to ensure the normal operation of the industrial system. To infer the fault propagation in the steam turbine system, a graph model is developed. Firstly, a process graph topology is constructed according to the system mechanism, whose nodes and edges represent the equipment and mutual relationships. Meanwhile, a fault graph topology is built, in which nodes indicate potential faults and edges are inferred propagation paths. Then, the representations of fault nodes are realized through a graph neural network. Lastly, link prediction methods based on nodes’ representations are conducted, along with the paths inference results. Consequently, the accuracy of fault propagation inference for the steam turbine system is over 86%.

scholarly journals Edge-Nodes Representation Neural Machine for Link Prediction

Algorithms ◽  
2019 ◽  
Vol 12 (1) ◽  
pp. 12 ◽  
Author(s):  
Guangluan Xu ◽  
Xiaoke Wang ◽  
Yang Wang ◽  
Daoyu Lin ◽  
Xian Sun ◽  
...  
Keyword(s):  
Neural Network ◽  
Formation Mechanism ◽  
Link Prediction ◽  
State Of The Art ◽  
Prediction Methods ◽  
Topological Features ◽  
Novel Method ◽  
Fully Connected ◽  
Two Sides

Link prediction is a task predicting whether there is a link between two nodes in a network. Traditional link prediction methods that assume handcrafted features (such as common neighbors) as the link’s formation mechanism are not universal. Other popular methods tend to learn the link’s representation, but they cannot represent the link fully. In this paper, we propose Edge-Nodes Representation Neural Machine (ENRNM), a novel method which can learn abundant topological features from the network as the link’s representation to promote the formation of the link. The ENRNM learns the link’s formation mechanism by combining the representation of edge and the representations of nodes on the two sides of the edge as link’s full representation. To predict the link’s existence, we train a fully connected neural network which can learn meaningful and abundant patterns. We prove that the features of edge and two nodes have the same importance in link’s formation. Comprehensive experiments are conducted on eight networks, experiment results demonstrate that the method ENRNM not only exceeds plenty of state-of-the-art link prediction methods but also performs very well on diverse networks with different structures and characteristics.

Improved ART1 Neural Network Based Condenser Fault Diagnosis

2012 ◽  
Vol 588-589 ◽  
pp. 1091-1094
Author(s):  
Qing Yang Xu ◽  
Ying Liang
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Steam Turbine ◽  
Bp Neural Network ◽  
Original Training ◽  
Industrial System ◽  
Training Algorithm ◽  
Adaptive Resonance ◽  
Fault Features ◽  
Network Studies

Condenser is an essential equipment of steam turbine. It is valuable to diagnose the fault when monitor the condenser system. To overcome shortcomings of BP neural network in fault diagnosis, ART1 (adaptive resonance architecture 1) is used to diagnose the condenser fault. The ART1 Neural network studies the typical fault features data, and realizes fault diagnosis. The results indicate the improved ART1 neural network can diagnose the condenser system fault correctly, and overcome the shortcoming of the original training algorithm. Although this is an application based on condenser, the algorithm can be used to further industrial system.

scholarly journals Relationship Prediction Based on Graph Model for Steam Turbine Control Valve

Actuators ◽  
2021 ◽  
Vol 10 (5) ◽  
pp. 91
Author(s):  
Yi-Jing Zhang ◽  
Li-Sheng Hu
Keyword(s):  
Steam Turbine ◽  
Link Prediction ◽  
Dead Zone ◽  
Graph Model ◽  
Score Function ◽  
Control Valve ◽  
Test Accuracy ◽  
Industrial Systems ◽  
The Relationship ◽  
Graph Nodes

The control valve is an important piece of equipment in the steam turbine, which frequently suffers from the fault of the dead zone. The graph model is a promising method for dead zone detection, yet establishing an accurate and completed graph topology is not an easy task due to limited mechanism knowledge. Hence, a graph model is proposed to predict the links in the graph and estimate the relationship between variables of related equipment of the control valve. The graph convolution is conducted on the uncompleted graph to learn the low-level representations of the graph nodes, and the score function is used to evaluate the probability of the existence of links between a pair of graph nodes. Results demonstrate a test accuracy of 99.2% for the link prediction, and follow the principles of thermodynamics in the steam turbine. Consequently, the proposed graph model is capable of estimating the relationships for the steam turbine control valve, and other inter-connected industrial systems.

Neural Network for Automatic Analysis of Motility Data

1994 ◽  
Vol 33 (01) ◽  
pp. 157-160 ◽  
Author(s):  
S. Kruse-Andersen ◽  
J. Kolberg ◽  
E. Jakobsen
Keyword(s):  
Neural Network ◽  
Muscular Activity ◽  
Recording System ◽  
Automatic Analysis ◽  
Biologically Relevant ◽  
System A ◽  
The Neural Network ◽  
Valuable Method ◽  
Motor Abnormalities ◽  
Trained Network

Abstract:Continuous recording of intraluminal pressures for extended periods of time is currently regarded as a valuable method for detection of esophageal motor abnormalities. A subsequent automatic analysis of the resulting motility data relies on strict mathematical criteria for recognition of pressure events. Due to great variation in events, this method often fails to detect biologically relevant pressure variations. We have tried to develop a new concept for recognition of pressure events based on a neural network. Pressures were recorded for over 23 hours in 29 normal volunteers by means of a portable data recording system. A number of pressure events and non-events were selected from 9 recordings and used for training the network. The performance of the trained network was then verified on recordings from the remaining 20 volunteers. The accuracy and sensitivity of the two systems were comparable. However, the neural network recognized pressure peaks clearly generated by muscular activity that had escaped detection by the conventional program. In conclusion, we believe that neu-rocomputing has potential advantages for automatic analysis of gastrointestinal motility data.

scholarly journals Selected Aspects of Indoor Climate in a Passive Office Building with a Thermally Activated Building System: A Case Study from Poland

Energies ◽  
2021 ◽  
Vol 14 (4) ◽  
pp. 860
Author(s):  
Piotr Michalak
Keyword(s):  
Air Temperature ◽  
Thermal Conditions ◽  
Office Building ◽  
Normal Operation ◽  
Indoor Climate ◽  
Thermally Activated ◽  
System A ◽  
Warm Sensation ◽  
Building System ◽  
Heating Energy Consumption

Modern buildings with new heating, ventilation and air conditioning (HVAC) systems offer possibility to fit parameters of the indoor environment to the occupants’ requirements. The present paper describes the results of measurements performed in an office room in the first Polish passive commercial office building during four months of normal operation. They were used to calculate parameters describing thermal comfort: vertical air temperature profile, floor surface temperature, predicted mean vote (PMV) and predicted percent of dissatisfied (PPD). Obtained results confirmed good thermal conditions in the analysed room. The average temperature of the floor’s surface varied from 20.6 °C to 26.2 °C. The average vertical air temperature, calculated for working days, was from 22.5 °C to 23.1 °C. The temperature difference between the floor and 5 cm below the ceiling was from −0.9 °C to 6.3 °C. The PMV index varied from 0.52 to 1.50 indicating ‘slightly warm’ sensation, in spite of ‘neutral’ reported by employees. Also measured cooling and heating energy consumption was presented. The performed measurements confirmed the ability of thermally activated building system (TABS) to keep good thermal conditions.

Fault diagnosis method of peak-load-regulation steam turbine based on improved PCA-HKNN artificial neural network

2021 ◽  
pp. 1748006X2110105
Author(s):  
Yifan Wu ◽  
Wei Li ◽  
Deren Sheng ◽  
Jianhong Chen ◽  
Zitao Yu
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Steam Turbine ◽  
Power Plants ◽  
Peak Load ◽  
Clean Energy ◽  
Steam Turbines ◽  
Peak Shaving ◽  
Diagnosis Method ◽  
Load Regulation

Clean energy is now developing rapidly, especially in the United States, China, the Britain and the European Union. To ensure the stability of power production and consumption, and to give higher priority to clean energy, it is essential for large power plants to implement peak shaving operation, which means that even the 1000 MW steam turbines in large plants will undertake peak shaving tasks for a long period of time. However, with the peak load regulation, the steam turbines operating in low capacity may be much more likely to cause faults. In this paper, aiming at peak load shaving, a fault diagnosis method of steam turbine vibration has been presented. The major models, namely hierarchy-KNN model on the basis of improved principal component analysis (Improved PCA-HKNN) has been discussed in detail. Additionally, a new fault diagnosis method has been proposed. By applying the PCA improved by information entropy, the vibration and thermal original data are decomposed and classified into a finite number of characteristic parameters and factor matrices. For the peak shaving power plants, the peak load shaving state involving their methods of operation and results of vibration would be elaborated further. Combined with the data and the operation state, the HKNN model is established to carry out the fault diagnosis. Finally, the efficiency and reliability of the improved PCA-HKNN model is discussed. It’s indicated that compared with the traditional method, especially handling the large data, this model enhances the convergence speed and the anti-interference ability of the neural network, reduces the training time and diagnosis time by more than 50%, improving the reliability of the diagnosis from 76% to 97%.

Reliable Analysis on Fast Valving of Ultra-Supercritical Unit Under Transient Fault Conditions

2017 ◽  
Author(s):  
Yu Cai ◽  
Wei Li ◽  
Bao Zhang ◽  
Wenjian Wu ◽  
Deren Sheng ◽  
...  
Keyword(s):  
Power System ◽  
Steam Turbine ◽  
Dynamic Model ◽  
Transient Stability ◽  
Power Grid ◽  
Load Shedding ◽  
Control Mode ◽  
Normal Operation ◽  
Transient Fault ◽  
The Stability

Fast valving of ultra-supercritical unit has great effects on over-speed prevention, load-shedding control, transient stability analysis of electrical system and other security problems. The purpose of fast valving is to maintain the stability of power system once fault or load shedding of unit occurs in the electric power system. Therefore, it is of great significance to study the reliability of fast valving for ultra-supercritical unit. In this paper, the KU ( short shedding) logic condition of SIEMENS T3000 system is analyzed as the research object of fast valving. The unit can be avoided over speed by monitoring the unit load and fast valving under faulty grid conditions based on the KU control. A series of measures will be taken after KU is triggered, for instance the governing valving will be closed quickly and the DEH (digital electro-hydraulic) control of the steam turbine will be switched to speeding control mode. On the other hand, the unit will return to normal operation if the transient fault of power grid disappears. The key contributions of this thesis include three parts: Firstly, based on the analysis of control characteristics of ultra-supercritical unit and protective logic and triggered conditions of KU function, a novel dynamic model by coupling the fast valving of steam turbine and the transient stability of generator is established by applying the PSCAD software. Then, the dynamic response process of ultra-supercritical unit is simulated and calculated by adopting the coupling dynamic model when KU function is triggered. Also the influence factors and reliability of fast valving are analyzed under transient fault conditions. Finally, two optimized measures by increasing the time delay and the speed of quantitative judgment are put forward to reduce risks and avoid the misoperation of signal distortion which may be caused by the power transmitter under transient fault conditions. The results of this study can not only help to evaluate the reliability of fast valving function scientifically in power grid transient fault, but also guide the technicians to analyze the stability of the power grid.

scholarly journals Efficiency of Using the Auxiliary Boiler for Peak Power Generation by a Steam Turbine of NPP

2021 ◽  
Vol 64 (1) ◽  
pp. 78-90
Author(s):  
V. A. Khrustalev ◽  
M. V. Garievskii
Keyword(s):  
Power Plant ◽  
Nuclear Power Plant ◽  
Steam Turbine ◽  
Nuclear Power ◽  
Power Plants ◽  
Normal Operation ◽  
Heat Output ◽  
Generation Process ◽  
System Effect ◽  
Industrial Enterprises

The article presents the technique of an estimation of efficiency of use of potential heat output of an auxiliary boiler (AB) to improve electric capacity and manoeuvrability of a steam turbine unit of a power unit of a nuclear power plant (NPP) equipped with a water-cooled water-moderated power reactor (WWER). An analysis of the technical characteristics of the AB of Balakovo NPP (of Saratov oblast) was carried out and hydrocarbon deposits near the NPP were determined. It is shown that in WWER nuclear power plants in Russia, auxiliary boilers are mainly used only until the normal operation after start-up whereas auxiliary boiler equipment is maintained in cold standby mode and does not participate in the generation process at power plants. The results of research aimed to improve the systems of regulation and power management of power units; general principles of increasing the efficiency of production, transmission and distribution of electric energy, as well as the issues of attracting the potential of energy technology sources of industrial enterprises to provide load schedules have been analyzed. The possibility of using the power complex NPP and the AB as a single object of regulation is substantiated. The authors’ priority scheme-parametric developments on the possibility of using the thermal power of the auxiliary boilers to increase the power of the steam turbine of a nuclear power plant unit equipped with WWER reactors unit during peak periods, as well as the enthalpy balance method for calculating heat flows, were applied. The surface area of the additional heater of the regeneration “deaerator – high pressure heaters” system and its cost were calculated. On the basis of calculations, it was shown that the additional power that can be obtained in the steam turbine of the NPP with a capacity of 1200 MW due to the use of heat of the modernized auxiliary boiler in the additional heat exchanger is 40.5 MW. The additional costs for the implementation of the heat recovery scheme of the auxiliary boiler at different prices for gas fuel and the resulting system effect were estimated in an enlarged way. Calculations have shown the acceptability of the payback period of the proposed modernization.

Sign in / Sign up

Export Citation Format

Share Document