Fault Alarm Research Articles

Trend Prediction and Operation Alarm Model Based on PCA-Based MTL and AM for the Operating Parameters of a Water Pumping Station.

In order to effectively predict the changing trend of operating parameters in the pump unit and carry out fault diagnosis and alarm processes, a trend prediction model is proposed in this paper based on PCA-based multi-task learning (MTL) and an attention mechanism (AM). The multi-task learning method based on PCA was used to process the operating data of the pump unit to make full use of the historical data to extract the key common features reflecting the operating state of the pump unit. The attention mechanism (AM) is introduced to dynamically allocate the weight coefficient of common feature mapping for highlighting the key common features and improving the prediction accuracy of the model when predicting the trend of data change for new working conditions. The model is tested with the actual operating data of a pumping station unit, and the calculation results of different models are compared and analyzed. The results show that the introduction of multi-task learning and attention mechanisms can improve the stability and accuracy of the trend prediction model compared with traditional single-task learning and static common feature mapping weights. According to the threshold analysis of the monitoring statistical parameters of the model, a multi-stage alarm model of pump unit operation condition monitoring can be established, which provides a theoretical basis for optimizing operation and maintenance management strategy in the process of pump station management.

Adaptive two-dimensional subspace identification for monitoring batch processes with limited batch data

Data-driven based batch process monitoring is of critical importance in ensuring stable operating processes and consistent product quality. For long-duration batch processes, it is unrealistic to involve expensive data to train a statistical model for monitoring. To model the inherently batch-wise and variable-wise dynamics, nonlinearity, and time-varying characteristics, this paper proposes a local learning-based two-dimensional subspace identification (LL-2D-SID) scheme based on the similarity between the ongoing batch and the previous batches. The similarity is estimated by the extended extrapolative time-warping. Unlike the conventional statistical models using rich batch data, LL-2D-SID through online optimizing mechanism using limited batch data still has good prediction performance. The application of the sintering process in the polytetrafluoroethylene production has demonstrated that the LL-2D-SID based process monitoring scheme can not only accurately track temperature changes but also timely give fault alarms with a lower error alarm rate than the other SID-based process monitoring schemes.

Design and Research of an Elevator Electric Brake Release Device with a Safety Detection Function

Abstract In response to the issues and defects associated with the current method of using electrical devices to open brakes for emergency rescue, a new elevator electric brake release device applicable to any elevator employing an electromechanical braking system has been designed. This device mainly consists of a car data collection unit and a brake release control unit, utilizing the STM32F103C8T6 microcontroller as the control core for elevator emergency rescue operations. The car data collection unit is responsible for gathering and transmitting data on the car’s operational state and position, while the brake release control unit evaluates the conditions for emergency rescue operations and performs real-time analysis, storage, and display of the collected data. It also decides whether to output a brake release signal. Experimental results show that when conditions for rescue operations are met, the electric brake release device can ensure the safe operation of the elevator; when abnormalities are detected, it outputs a signal to stop operations, alongside fault alarms and status displays.

Chaos quantum optimization‐based layered diagnosis framework for faulty sensor node diagnosis and classification in wireless sensor networks

SummaryNode faults are often influenced by factors such as physical component failure, communication module errors, battery exhaustion, and environmental factors. Various researchers have contributed to addressing the problem of detecting, diagnosing, and classifying faults in sensor networks. However, computational complexity and fault occurrence probability increase with the size of the network. In this context, an enhanced optimized layered diagnosis framework (OLDF) is proposed for detecting, diagnosing, and classifying sensor node faults. OLDF utilizes a deep belief network (DBN) with chaos quantum‐behaved particle swarm optimization (CQ‐PSO) for efficient diagnosis and classification of various sensor faults in the network. The proposed OLDF consists of two layers. In the first layer, optimized DBN with CQ‐PSO algorithm is employed to determine the fault type of the sensor nodes. Then, the fault type of sensor nodes that are classified in the first layer is given as input into the second layer of the OLDF algorithm to determine the fault severity in the network. Experimentation has been carried out by using the NS3 simulator for the OLDF framework with performance metrics such as classification accuracy, diagnosis accuracy, false positives, fault alarm rate, and average energy consumption. The validity of the proposed framework has been verified through comparisons with existing works such as MFD, INSA, FDRFC, and HFD. From the comparative analysis carried out, it is apparent that the proposed framework achieves a high classification accuracy of 89.94% and diagnosis accuracy of 93.21%, with less false positive rate, and utilizes minimum energy when compared with its counterparts.

Anomaly detection of wind turbine based on norm-linear-ConvNeXt-TCN

The supervisory control and data acquisition (SCADA) system of wind turbines continuously collects a large amount of monitoring data during their operation. These data contain abundant information about the operating status of the turbine components. Utilizing this information makes it feasible to provide early warnings and predict the health status of the wind turbine. However, due to the strong coupling between the various components of the wind turbine, the data exhibits complex spatiotemporal relationships, multiple state parameters, strong non-linearity, and noise interference, which brings great difficulty to anomaly detection of the wind turbine. This paper proposes a new method for detecting abnormal operating conditions of wind turbines, based on a cleverly designed multi-layer linear residual module and the improved temporal convolutional network (TCN) with a new norm-linear-ConvNeXt architecture (NLC-TCN). Initially, the NLC-TCN deep learning reconstruction model is trained with historical data of normal behavior to extract the spatiotemporal features of state parameters under normal operational conditions. Subsequently, the condition score of the unit is determined by calculating the average normalized root mean square error between the reconstructed data and actual data. The streaming peaks-over-threshold real-time calculation of the anomaly warning threshold, based on extreme value theory, is then used for preliminary fault monitoring. Moreover, by shielding the fault alarm for low wind speeds and implementing a continuous delay perception mechanism, issues related to wind speed fluctuations and internal and external interference are addressed, enabling early warning for faulty units. Finally, the effectiveness and reliability of the proposed method are validated through comparative experiments using actual offshore wind farm SCADA data. The performance of the proposed method surpasses that of other compared methods. Additionally, the results of the proposed method were evaluated using the uniform manifold approximation and projection dimensionality reduction technique and kernel density estimation.

AHU sensor fault diagnosis in various operating conditions based on a hybrid data-driven model combined energy consumption

Data-driven methods has the inspiring potential for sensors fault detection in heating, ventilation, and air-conditioning (HVAC) intelligence control system. However, the interpretability of pure data-driven methods is relatively poor. Moreover, pure data-driven methods heavily rely on quality of HVAC sensor data that causes pure data driven methods have inconsistent detection efficiency in various operation conditions and sensor locations, resulting in poor general applicability. To solve above problems, an enhanced data-driven model based on energy consumption correlation (ECC) is proposed. First, the collected data from sensors are collected in chronological order and undergo data preprocessing techniques for noise removal. Subsequently, the energy consumption data is utilized to differentiate the operating conditions of the HVAC system. Simultaneously, a mapping relationship is established between sensor data and energy consumption. It uses the mapping relationship to construct the ECC for faulty sensor detection. Finally, the diagnosis of air handling unit (AHU) sensor faults is achieved by employing the hybrid data-driven model based on the ECC. The experiment conducted a comparison between the hybrid data-driven model and two novel pure data-driven methods. The results of the experiment demonstrate that the hybrid data-driven model exhibits excellent fault detection efficiency across different operating conditions and sensor locations. The fault alarm rate of the hybrid data-driven model is 0–3.26% under various AHU sensor fault conditions. And the fault diagnosis rate of the hybrid data-driven model is 96.23% and 96.11% under single-operation condition and dual-operation condition, respectively. Furthermore, compared to pure data-driven methods, the hybrid data-driven model is less affected by data quality and possesses a broader applicability.

Proactive Fault Localization and Alarm Correlation in DWDM Networks

Proactive Fault Localization and Alarm Correlation in DWDM Networks

Transparent Grid Visualization Surveillance and Fault Warning in High Density Distributed Power Access Areas

Abstract Transparent grid, as an advanced form of “Internet + smart energy”, is of great value in supporting energy transformation and promoting the development of new power systems. Based on the grid connection requirements of high-density distributed power supply, this paper provides specific grid connection methods and trend calculations and explores the impact of grid connection on high-density distributed power supply. Subsequently, the technical framework and blueprint of the transparent grid are proposed, combined with the grid visualization system to monitor the grid state visually, and based on the random matrix single-loop theory and ARIMA algorithm to realize fault identification and early warning of the transparent grid. The analysis of the algorithm shows that the fault identification has good rapidity, feasibility, and practicability, and while ensuring that no fault alarm is issued in the case of normal disturbance of distributed power supply, it is able to issue fault alarms for all locations and types of short-circuit faults in the system and determine the fault moment within 0.1s. It is “fast”, “accurate,” and “stable” in the research and judgment of active distribution network faults, and it is more intuitive in the assignment of risk levels, and it can identify the categories and levels of faults and realize the following Visualization of early warning.

Design of Intelligent Street Lamp Control and Fault Alarm System Based on NB-IOT

Design of Intelligent Street Lamp Control and Fault Alarm System Based on NB-IOT

Correlation warping radius tracking for condition monitoring of rolling bearings under varying operating conditions

Health indicators (HI) are crucial in early fault alarm and degradation monitoring of mechanical failures. In recent years, many HIs are developed and reported, however, a constructed HI which is more sensitive to incipient defect, robust to varying operating conditions and is interpretable to characterize the degradation process is still remain to be studied. To address this issue, a more powerful and effective HI applicable for nonstationary operating condition is studied in this paper. Inspired by chaos fractal theory (CFT) and slowly varying damage dynamics theory (SVDDT), this paper calculates the range of correlation warping radius (CWR) of each segment of signal through phase space reconstruction, and then finds that the boundary of correlation warping radius range (CWR-B) in normal conditions follows a fixed linear relationship. Through the application of this linear relationship, a new health monitoring indicator for vibration signals of rotating machinery has been proposed, through correlation warping radius tracking measurement (CWRTM). The proposed indicator not only has outstanding monitoring advantages for rotating machinery in a cyclo-stationary condition, but also applicable for machinery condition monitoring under variable operating conditions, achieving the unity of methods for condition monitoring in stationary and variable operating conditions. Compared with some typical health indicators, the experimental results on bearing run-to-failure dataset and wind turbine generator bearing field dataset show that the proposed indicator in this article is not only sensitive to early-stage fault, but also validated robust to varying operating conditions.

Handling fault detection and diagnosis in incomplete sensor measurements for BAS based HVAC system

Due to the development of sensor networks, Building Automation System (BAS) based heating, ventilation, and air conditioning (HVAC) has gradually replaced traditional HVAC to improve indoor thermal comfort and decrease energy consumption. Because of inevitable faults in sensors or networks, the real-time sensor data may be incomplete with corrupted, lost or undetected missing values. Therefore, Improved Fireworks Algorithm (IFWA)-Long Short-Term Memory (LSTM) is proposed to recover incomplete measurements in BAS HVAC sensors. Because sensor data loss mostly results from incorrect control commands from the BAS system or sensor damage, there is a high probability of concurrent sensor fault. Therefore, Independent Component Analysis (ICA)-K-Nearest Neighbors (KNN) is proposed to monitor the sensor's healthy state under the measurements recovered. This paper discusses the possible causes of incomplete measurement in BAS HVAC sensors and simulates the distribution by experiment. The experiment analyzes the data recovery capability of IFWA-LSTM for different types of missing sensor data in different sensor measurement loss scenarios. The result shows that compared to the comparative methods, IFWA-LSTM achieves a 6.45 %–86.92 % improvement in recovery accuracy and a 0.0041 to 0.6340 improvement in correlation coefficients. Subsequently, it discusses the fault diagnosis rate of ICA-KNN under full measurements and incomplete measurement recovered by IFWA-LSTM. Overall, ICA-KNN achieves an average fault diagnosis rate of 99.86 % and an average fault alarm rate of 0 % under full measurement. When applied to incomplete measurement recovered by IFWA-LSTM, ICA-KNN exhibits an average fault diagnosis rate of 92.18 % and an average fault alarm rate of 1.22 %.

Multiscale monitoring of industrial chemical process using wavelet-entropy aided machine learning approach

In recent decades, machine learning (ML) techniques have been effectively applied for industrial process monitoring to assure safety and high-quality yield. Traditional process fault detection, identification, and diagnosis (FDI&D) approaches are insufficiently smart to address the modern complex challenges of real-time industrial chemical processes. The detection and diagnostic resolution of the traditional monitoring approach are less robust, inefficient, and produce the wrong interpretation of actual fault information. These approaches are based on a single-scale fault illustration and cannot effectively address multiple fault depiction roots. This study introduces a novel ML-aided methodological framework for industrial and manufacturing monitoring systems. The proposed ML framework is developed using Principal component analysis (PCA), Shannon information entropy (IE), wavelet transformation (WT), and signed directed graph (SDG). It includes fault detection, identification, and diagnostic propagation root-path interpretation to address the safety challenges of modern, real-time industrial chemical processes. The proposed methodological framework is validated using the Tennessee Eastman process (TEP) benchmark to highlight their performance and efficiency. The results of this study determined that the new proposed approach is more efficient in terms of accuracy, robustness, and actual propagation root cause than traditional techniques. It has a high fault detection rate (FDR), low fault alarm rate (FAR) that identifies and recognizes the actual faulty-correlated variables to establish the SDG model framework for determining the actual diagnostic propagation root path. It initially enables operators to react to unusual incidents, ensuring industrial safety, minimizing economic loss, and avoiding disasters.

Variable partition based parallel dictionary learning for linearity and nonlinearity coexisting dynamic process monitoring

In practical industrial processes with complex mechanisms, there are both linear and nonlinear relationships between process variables. However, focusing solely on one of these relationships can lead to the neglect of important information related to faults. This neglect can degrade the monitoring performance and increase the potential risk of catastrophic accidents caused by unreliable fault alarms. In order to solve this puzzle, this paper proposes a variable partition based parallel dictionary learning (PDL) method. Firstly, a linearity maximization analysis (LMA) method is presented to recognize linear variable subsets efficiently. The collinearity of variables is evaluated using the variance inflation factor, then linear and nonlinear variable subsets can be divided by maximizing the linear correlation between one variable and the rest. After that, a PDL based monitoring model can be constructed in all subsets to extract linear and nonlinear features concurrently. Finally, based on Bayesian inference, the monitoring results of all subsets are fused to construct a global monitoring statistic. The effectiveness of the proposed approach is illustrated by a numerical simulation case, the continuous stirred tank heater, the Tennessee Eastman process, and a real industrial roasting process. Experiment results show that linear and nonlinear variable subsets can be divided reasonably according to the proposed LMA method. Meanwhile, compared with several state-of-the-art methods, the proposed method can achieve better monitoring results by modeling linear and nonlinear data parts separately, which further demonstrates the feasibility of the proposed method.

A comparative investigation between rule- and inverse model-based fault detection and diagnostics for HVAC control systems

Fault detection and diagnostics (FDD) tools provide valuable information regarding system faults and deviation from expected operation. Most existing FDD tools apply rule-based fault detection algorithms that generate an alarm when a rule is met; however, these tools cannot evaluate the overall performance of a system. Inverse-model-based FDD algorithms can be deployed to complement the fault alarms triggered by rule-based building energy management systems (BEMS). This paper examines the faults detected by rule- and inverse model-based algorithms used to detect faults in multiple zone variable air volume air handling unit systems. The capability of the rule- and inverse model-based algorithms in detecting and diagnosing faults is demonstrated through illustrative examples using data from three commercial buildings in New Brunswick, Canada. The results show that inverse model-based algorithms could diagnose faults that were not detected by the rule-based FDD algorithms implemented in a commercially available BEMS tool.

GTFP: Network Fault Prediction Based on Graph and Time Series

With the explosion of 5G network scale, the network structure becomes increasingly complex. During the operation of the network devices, the probability of anomalies or faults increases accordingly. Network faults may lead to the disappearance of important information and cause unpredictable losses. The prediction of network faults can enhance the quality of network services and reduce economic loss. In this paper, we propose the concept of 4D features and use the BERT algorithm to extract semantic features, the graph neural network algorithm to extract network topology information, and the Temporal Convolutional Network (TCN) algorithm to extract time series. Based on this, we propose Fault Prediction based on GraphSage and TCN (GTFP), an end-to-end solution of network fault alarm prediction, which is based on GraphSage and TCN (GTCN), a hybrid algorithm of a graph neural network and the TCN model. Our solution takes the historical alarm data as input. First, we filter out the alarm noises irrelevant to the faults through data cleaning. Then, we employ feature engineering to extract the valid alarm features, including the statistical features of the network alarm information, the semantic features of the alarm texts, the sequential features of the alarms and the network topology features of the nodes where the alarms are located. Finally, we use GTCN to predict future fault alarms based on the extracted features. Experiments on the alarm data of a real service system show that GTFP performs better than the state-of-the-art algorithms of fault alarm prediction.

Semi-Supervised Anomaly Detection of Dissolved Oxygen Sensor in Wastewater Treatment Plants.

As the world progresses toward a digitally connected and sustainable future, the integration of semi-supervised anomaly detection in wastewater treatment processes (WWTPs) promises to become an essential tool in preserving water resources and assuring the continuous effectiveness of plants. When these complex and dynamic systems are coupled with limited historical anomaly data or complex anomalies, it is crucial to have powerful tools capable of detecting subtle deviations from normal behavior to enable the early detection of equipment malfunctions. To address this challenge, in this study, we analyzed five semi-supervised machine learning techniques (SSLs) such as Isolation Forest (IF), Local Outlier Factor (LOF), One-Class Support Vector Machine (OCSVM), Multilayer Perceptron Autoencoder (MLP-AE), and Convolutional Autoencoder (Conv-AE) for detecting different anomalies (complete, concurrent, and complex) of the Dissolved Oxygen (DO) sensor and aeration valve in the WWTP. The best results are obtained in the case of Conv-AE algorithm, with an accuracy of 98.36 for complete faults, 97.81% for concurrent faults, and 98.64% for complex faults (a combination of incipient and concurrent faults). Additionally, we developed an anomaly detection system for the most effective semi-supervised technique, which can provide the detection of delay time and generate a fault alarm for each considered anomaly.

Improved OAKR approach to condition monitoring of rotating machinery

Faults in main subsystems or components of a rotating machine often causes unscheduled shutdown, which may lead to not only huge economic losses, but also safety accidents. As an important part of intelligent maintenance, condition monitoring becomes a powerful tool in reducing maintenance costs through automatic fault alarming, thereby reducing potential downtime while improving system safety and reliability. An optimized auto-associative kernelregression (OAKR) model has been proposed recently and demonstrated as a promising tool for condition monitoring of various turbomachines, which is independent of fault mode and machine type. However, the fault identification accuracy of this approach largely relies on data quality in practical applications. Data incompleteness, parameter variation and system complexity often result in the inaccuracy of fault alarming for complicated rotating machinery. This paper proposes an improved OAKR method to address these issues, including utilizing wavelet packet Bayesian thresholding method (WPB) to reduce noise in the raw multivariate data, developing the Manhattan distance to calculate the sample similarity, and constructing a multivariate health index based on Multivariate Permutation Entropy to identify potential faults in equipment condition monitoring. Parametric analysis and a comparison study with original AAKR and OAKR methods by using the actual data of a gas turbine are conducted to illustrate the effectiveness and feasibility of the proposed methodology.

A framework via impulses-oriented Gini index and extreme value distribution for rolling bearing dynamic fault alarm and identification

Rolling bearing dynamic fault alarm and identification is essential in condition-based maintenance and can prevent serious accidents. However, an integrated framework with dynamic adaptability and full interpretability is rarely reported for this issue based on sparsity measures and statistical properties. Therefore, a framework via impulses-oriented Gini index and extreme value distribution is developed in this paper. First, for attenuating normal-phase amplitude oscillations of the Gini index, periodical impulses-oriented Gini index (PIGI) and sparsity-smoothed periodical impulses-oriented Gini index (SPIGI) are defined successively through enhanced envelope impulses extraction to improve incipient fault sensitivity and robustness against interferences. Next, a dynamic alarm threshold setting strategy is built by fitting the available PIGIs using generalized extreme value distribution (GEVD). Further, a novel framework, without prior knowledge and complex signal processing algorithms, is established based on PIGI, SPIGI, and GEVD-based thresholds for dynamic fault alarm and identification. The verification results on simulation and experimental data indicate that the proposed framework is effective in balancing false alarms and missed alarms and detecting incipient faults, and thus would have favorable application prospects.

Fault Diagnosis of Wind Turbine Generators Based on Stacking Integration Algorithm and Adaptive Threshold.

Fault alarm time lag is one of the difficulties in fault diagnosis of wind turbine generators (WTGs), and the existing methods are insufficient to achieve accurate and rapid fault diagnosis of WTGs, and the operation and maintenance costs of WTGs are too high. To invent a new method for fast and accurate fault diagnosis of WTGs, this study constructs a stacking integration model based on the machine learning algorithms light gradient boosting machine (LightGBM), extreme gradient boosting (XGBoost), and stochastic gradient descent regressor (SGDRegressor) using publicly available datasets from Energias De Portugal (EDP). This model is automatically tuned for hyperparameters during training using Bayesian tuning, and the coefficient of determination (R2) and root mean square error (RMSE) were used to evaluate the model to determine its applicability and accuracy. The fitted residuals of the test set were calculated, the Pauta criterion (3σ) and the temporal sliding window were applied, and a final adaptive threshold method for accurate fault diagnosis and alarming was created. The model validation results show that the adaptive threshold method proposed in this study is better than the fixed threshold for diagnosis, and the alarm times for the GENERATOR fault type, GENERATOR_BEARING fault type, and TRANSFORMER fault type are 1.5 h, 5.8 h, and 3 h earlier, respectively.

A Novel Error-Correcting Particle Swarm Optimization Back Propagation Fault Diagnosis Method for Microgrid

Compared to traditional power grids, microgrids have a more flexible operating mode. There are various distributed power sources within the microgrid, and different types of distributed power sources have different control methods. Once a short-circuit fault occurs in the microgrid, these characteristics will increase the difficulty of microgrid fault diagnosis and reduce the accuracy of microgrid fault diagnosis. This paper proposes an error-correcting particle swarm optimization back propagation microgrid fault diagnosis method for the diagnosis of short-circuit faults in microgrids that identifies the accuracy of alarm signals, corrects unreasonable signals, and obtains the correct fault set of the microgrid through the temporal logic relationship between each protection. Using the particle swarm optimization back propagation (PSO-BP) neural network algorithm to train fault alarm signals, fast convergence can be achieved, and accurate diagnostic results can be obtained after the sixth generation training is completed. As this fault diagnosis algorithm is applied to line protection equipment, it can be used to diagnose all types of short-circuit faults. This algorithm is easy to implement and has a small data scale, which is conducive to efficient and concise fault diagnoses in microgrids.