scholarly journals Improved Fault Diagnosis in Hydraulic Systems with Gated Convolutional Autoencoder and Partially Simulated Data

Sensors ◽  
2021 ◽  
Vol 21 (13) ◽  
pp. 4410
Author(s):  
Albert Gareev ◽  
Vladimir Protsenko ◽  
Dmitriy Stadnik ◽  
Pavel Greshniakov ◽  
Yuriy Yuzifovich ◽  
...  
Keyword(s):  
Neural Network ◽  
Fault Detection ◽  
Network Architecture ◽  
Hydraulic System ◽  
Test Bench ◽  
Simulated Data ◽  
Hydraulic Systems ◽  
Detection Model ◽  
Convolutional Autoencoder ◽  
System States

This paper examines the effectiveness of neural network algorithms for hydraulic system fault detection and a novel neural network architecture is suggested. The proposed gated convolutional autoencoder was trained on a simulated training set augmented with just 0.2% data from the real test bench, dramatically reducing the time needed to spend with the actual hardware to build a high-quality fault detection model. Our fault detection model was validated on a test bench and showed accuracy of more than 99% of correctly recognized hydraulic system states with a 10-s sampling window. This model can be also leveraged to examine the decision boundaries of the classifier in the two-dimensional embedding space.

Adaptive Neural Network in Compensation the Dynamics and Position Control of a Servo-Hydraulic System With a Flexible Load

2005 ◽  
Author(s):  
Hassan Yousefi ◽  
Heikki Handroos
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Hydraulic System ◽  
Position Control ◽  
Reference Model ◽  
Differential Evolution Algorithm ◽  
Nonlinear Behavior ◽  
System Stability ◽  
Hydraulic Systems ◽  
Highly Nonlinear

Asymmetrical servo-hydraulic systems are commonly used in industry. These kinds of systems are nonlinear in nature and generally difficult to control. Because of changing system parameters, using the same gain will cause overshoot or even loss of system stability. The highly nonlinear behavior of these devises makes them idea subjects for applying different types of sophisticated controllers. This paper is concerned with using two artificial neural networks in compensation the dynamics and position tracking of a second order model reference in a flexible servo-hydraulic system. In present study, a neural network as an acceleration feedforward and another one as a gain scheduling of a proportional controller are proposed. Differential evolution algorithm is used to find the weights and biases to avoid the local minima. The proposed controller was verified with a commonly used p-controller. The results suggest that if the neural networks choose and train well, they improve all performance evaluation criteria such as stability, fast response, and accurate reference model tracking in servo-hydraulic systems.

A hybrid fault diagnosis scheme for railway point machines by motor current signal analysis

2021 ◽  
pp. 095440972110619
Author(s):  
Khadem Hossaini Narges ◽  
Mirabadi Ahmad ◽  
Gholami Manesh Fereydoun
Keyword(s):  
Neural Network ◽  
Fault Detection ◽  
Decision Tree ◽  
Network Architecture ◽  
Failure Modes ◽  
Support Vector ◽  
Current Signal ◽  
Neural Network Architecture ◽  
Mechanical Faults ◽  
Neural Network Algorithm

Proper analysis of point machine current signal provides pervasive information of health status of their internal components. Point machines are subjected to several failure modes during their operation. “Gearbox,” “ball bearing,” “lead screw,” and “sliding chair” faults are among common mechanical failure modes. In this article, a two-stage prediction innovative process is proposed using Fault Detection based Decision Tree strategy (FDDT) where the healthy and faulty modes are first determined, followed by classifying the types of mechanical faults based on Parallel Neural Network Architecture and Fuzzy System (PNNFS). To differentiate between faulty and healthy point machines, some relevant features are extracted from the motors’ current signals which are used as input data for the proposed FDDT_PNNFS method. Feature selection has been performed using the ReliefF to select the dominant predictors in the point machine. Firstly, the Decision Tree (DT) algorithm is used to obtain a classifier model based on the offline training method for fault detection. The performance of DT is compared with the support vector machine algorithm. In the second stage, faulty data is fed to a bank of Neural Networks, designed in Parallel Neural Network Architecture (PNNA), which is used for identifying the type of failures. Each Neural Network Algorithm (NNA) is responsible for detecting only one type of failure and assessment of the NNA outputs shows the final failure of the point machine. If there is a discrepancy between the outputs of the NNAs, fuzzy logic plays the role of modifier and judges among outputs of NNAs and determines the more probable fault type.

Fault Detection of Excavator’s Hydraulic System Using Dynamic General Regression Neural Network

2011 ◽  
Vol 48-49 ◽  
pp. 511-514 ◽  
Author(s):  
Xiang Yu He ◽  
Shang Hong He
Keyword(s):  
Neural Network ◽  
Fault Detection ◽  
Hydraulic System ◽  
Nonlinear Process ◽  
Training Data ◽  
General Regression Neural Network ◽  
System A ◽  
Detection Approach ◽  
General Regression ◽  
Improve Reliability

In order to improve reliability of excavator’s hydraulic system, a fault detection approach based upon dynamic general regression neural network (GRNN) approach was proposed. Dynamic GRNN is an extension of GRNN, which could effectively caputure the dynamic behavior of the nonlinear process. With this approach, normal samples were used as training data to develop a dynamic GRNN model in the first step. Secondly, this dynamic GRNN model performed as a fault determinant of the test fault. Experimental faults were used to validate the approach. Experimental results show that the proposed fault detection approach could effectively applied to the excavator’s hydraulic system.

scholarly journals Automated Valve Fault Detection Based on Acoustic Emission Parameters and Artificial Neural Network

2019 ◽  
Vol 255 ◽  
pp. 02013
Author(s):  
M. Ali Al-Obaidi Salah ◽  
K.H. Hui ◽  
L.M. Hee ◽  
M. Salman Leong ◽  
Ali Abdul-Hussain Mahdi ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Acoustic Emission ◽  
Fault Detection ◽  
Reciprocating Compressor ◽  
Operational Conditions ◽  
Detection Model ◽  
Machinery Condition Monitoring ◽  
Artificial Neural ◽  
Popular Classes

Reciprocating compressor is one of the most popular classes of machines use with wide applications in the industry. However, valve failures in this machine often results unplanned shutdown. Therefore, the effective valve fault detection technique is very necessary to ensure safe operation and to reduce the unplanned shutdown. This paper propose an artificial intelligence (AI) model to detect valve condition in reciprocating compressor based on acoustic emission (AE) parameters measurement and artificial neural network (ANN). A set of experiments were conducted on an industrial reciprocating air compressor with several operational conditions including good valve and faulty valve to acquire AE signal. A fault detection model was then developed from the combination of healthy-faulty data using ANN tool box available in MATLAB. The results of the model validation demonstrated accuracy of valves condition classification exceeding 97%. Eventually, the authors intend to do more efforts for programming this model in smart portable device which can be one of the innovative engineering technologies in the field of machinery condition monitoring in the near future.

Development of a Novel Convolutional Neural Network Architecture Named RoadweatherNet for Trajectory-Level Weather Detection using SHRP2 Naturalistic Driving Data

2021 ◽  
pp. 036119812110054
Author(s):  
Md Nasim Khan ◽  
Mohamed M. Ahmed
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Real Time ◽  
Network Architecture ◽  
Video Data ◽  
Safe Driving ◽  
Detection Model ◽  
Weather Information ◽  
Adverse Weather ◽  
Naturalistic Driving

Driver performances could be significantly impaired in adverse weather because of poor visibility and slippery roadways. Therefore, providing drivers with accurate weather information in real time is vital for safe driving. The state-of-practice of collecting roadway weather information is based on weather stations, which are expensive and cannot provide trajectory-level weather information. Therefore, the primary objective of this study was to develop an affordable detection system capable of providing trajectory-level weather information at the road surface level in real-time. This study utilized the Strategic Highway Research Program 2 Naturalistic Driving Study video data combined with a promising machine learning technique, called convolutional neural network (CNN), to develop a weather detection model with seven weather categories: clear, light rain, heavy rain, light snow, heavy snow, distant fog, and near fog. A novel CNN architecture, named RoadweatherNet, was carefully crafted to achieve the weather detection task. The evaluation results based on a test dataset revealed that RoadweatherNet can provide excellent performance in detecting weather conditions with an overall accuracy of 93%. The performance of RoadweatherNet was also compared with six pre-trained CNN models, namely, AlexNet, ResNet18, ResNet50, GoogLeNet, ShuffleNet, and SqueezeNet, which showed that RoadweatherNet can provide nearly identical performance with a significant reduction in training time. The proposed weather detection model is cost-efficient and requires less computational power; therefore, it can be made widely available mainly owing to the recent thriving of smartphone cameras and can be used to expand and update the current weather-based variable speed limit systems.

scholarly journals Real-Time and Robust Hydraulic System Fault Detection via Edge Computing

2020 ◽  
Vol 10 (17) ◽  
pp. 5933 ◽  
Author(s):  
Dzaky Zakiyal Fawwaz ◽  
Sang-Hwa Chung
Keyword(s):  
Time Series ◽  
Fault Detection ◽  
Real Time ◽  
Hydraulic System ◽  
Noisy Data ◽  
Sensor Data ◽  
Feature Subset ◽  
Detection Time ◽  
Detection Model ◽  
Robust Fault Detection

We consider fault detection in a hydraulic system that maintains multivariate time-series sensor data. Such a real-world industrial environment could suffer from noisy data resulting from inaccuracies in hardware sensing or external interference. Thus, we propose a real-time and robust fault detection method for hydraulic systems that leverages cooperation between cloud and edge servers. The cloud server employs a new approach that includes a genetic algorithm (GA)-based feature selection that identifies feature-to-label correlations and feature-to-feature redundancies. A GA can efficiently process large search spaces, such as solving a combinatorial optimization problem to identify the optimal feature subset. By using fewer important features that require transmission and processing, this approach reduces detection time and improves model performance. We propose a long short-term memory autoencoder for a robust fault detection model that leverages temporal information on time-series sensor data and effectively handles noisy data. This detection model is then deployed at edge servers that provide computing resources near the data source to reduce latency. Our experimental results suggest that this method outperforms prior approaches by demonstrating lower detection times, higher accuracy, and increased robustness to noisy data. While we have a 63% reduction of features, our model obtains a high accuracy of approximately 98% and is robust to noisy data with a signal-to-noise ratio near 0 dB. Our method also performs at an average detection time of only 9.42 ms with a reduced average packet size of 179.98 KB from the maximum of 343.78 KB.

Adaptive Integral Non-Singular Terminal Sliding Mode Control of a Servo-Hydraulic System

2020 ◽  
Author(s):  
Yashar Shabbouei Hagh ◽  
Reza Mohammadi Asl ◽  
Heikki Handroos
Keyword(s):  
Neural Network ◽  
Sliding Mode Control ◽  
Hydraulic System ◽  
Sliding Mode ◽  
Control Signal ◽  
Terminal Sliding Mode Control ◽  
Hydraulic Actuator ◽  
Terminal Sliding Mode ◽  
Mode Control ◽  
System States

Abstract This paper proposes an adaptive integral non-singular terminal sliding mode control in combination with a neural network (INTSMC-NN) for nonlinear servo-hydraulic actuator systems. The proposed controller has the advantages of the conventional non-singular terminal sliding mode control; it can tolerate external disturbances, evades the singularity problem of the conventional terminal sliding mode control, and also guarantees finite time convergence of states. The main problem and drawback of the sliding mode-based control is the chattering phenomenon which is caused by the switching part of the controller. This phenomenon can cause severe impacts on mechanical components of the hydraulic system. In order to overcome to this issue, and moderate the control signal, the discontinuous part of the controller is replaced by a neural network. The stability of the controller is investigated through Lyapunov stability criteria. To study the performance of the proposed INTSMC in combination with neural network a third-order nonlinear servo-hydraulic actuator is considered. Simulation results first, indicates the capability of the proposed method in eliminating the chattering from the control signal and also making the system states to track the desired trajectory with high accuracy. Second, the performance of the proposed integral NTSMC is studied and compared to the conventional NTSMC.

Energy Consumption and Efficiency Measurements of Different Excavators: Does Hybridization Pay?

2015 ◽  
Author(s):  
Arnold Hießl ◽  
Rudolf Scheidl
Keyword(s):  
Hydraulic System ◽  
Combustion Engine ◽  
Total Efficiency ◽  
Hydraulic Systems ◽  
Standard Data ◽  
Load Sensing ◽  
System States ◽  
Information Basis ◽  
Recoverable Energy ◽  
Total Inflow

A series of detailed measurements of various mechanical and hydraulic system states of different excavators was performed. Main purpose of this study was to obtain a reliable information basis for assessing the potentials of hybrid drives, in particular the amount of recoverable energy. Differences concerned the size (tonnage) of the excavators and the hydraulic systems, open center versus load sensing. All machines were tested at the same set of operation scenarios, which are typical for practice, and with different operators. To this end, all test machines have been equipped with pressure, flow rate, temperature, angular and position sensors. These signals (about sixty) and several available from the machines CAN bus were recorded with a standard data acquisition system and electronically stored for later analysis. These raw data were processed to obtain the interesting data, like speeds, power flows, energies. In addition, videos of each test were recorded to facilitate the correct interpretation of the measurements and their correlation with the actual working processes. Power flows from the combustion engine, different pumps, and at each actuator and energetic losses at the different loss sources were plotted for the different operation scenarios. Total efficiencies of the machines for different scenarios and the energy in and outflow at each actuator were computed. From the latter so called relative and absolute recovery degrees for each actuator and for the total machine in the different operation scenarios were derived. The relative recovery degree is the ratio of the total outflow energy (second and fourth quadrant) and the total inflow energy (first and third quadrant). The absolute recovery degree is the ratio of the total outflow energy of an actuator and the total energy delivered by all pumps in an operation scenario. In most operation scenarios the total efficiency of consumed mechanical output energy at the hydraulic actuators relative to delivered hydraulic energy is in the range 15% to 25%. Reasonable recovery potentials do have the swing and the boom drive. For small machines, however, the boom drive dominates.

A Variable Speed Control Hydraulic System Based on BP Neural Network PID Controller

2011 ◽  
Vol 101-102 ◽  
pp. 439-442
Author(s):  
Fang Ping Huang ◽  
Tian Hao Peng
Keyword(s):  
Neural Network ◽  
Bp Neural Network ◽  
Hydraulic System ◽  
Pid Controller ◽  
Good Control ◽  
Hydraulic Systems ◽  
Variable Speed ◽  
Control Effect ◽  
Research Results ◽  
Neural Network Pid

The variable speed hydraulic systems have many advantages, and research about this field in recent years has developed rapidly. In this paper, a variable speed hydraulic system is studied using BP Neural Network PID controller. The research results show that using BP Neural Network PID controller can achieve good control effect.

Fault Diagnosis of Gas Turbine Engines by Using Dynamic Neural Networks

2010 ◽  
Author(s):  
Rasul Mohammadi ◽  
Esmaeil Naderi ◽  
Khashayar Khorasani ◽  
Shahin Hashtrudi-Zad
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Fault Detection ◽  
Gas Turbine ◽  
Network Architecture ◽  
Turbine Engines ◽  
Gas Turbine Engines ◽  
Dynamic Neural Networks ◽  
Feed Forward ◽  
The Difference

This paper presents a novel methodology for fault detection in gas turbine engines based on the concept of dynamic neural networks. The neural network structure belongs to the class of locally recurrent globally feed-forward networks. The architecture of the network is similar to the feed-forward multi-layer perceptron with the difference that the processing units include dynamic characteristics. The dynamics present in these networks make them a powerful tool useful for identification of nonlinear systems. The dynamic neural network architecture that is described in this paper is used for fault detection in a dual-spool turbo fan engine. A number of simulation studies are conducted to demonstrate and verify the advantages of our proposed neural network diagnosis methodology.

Sign in / Sign up

Export Citation Format

Share Document