Detection Of Abnormal Conditions Research Articles

Feasibility of Monitoring Heart and Respiratory Rates Using Nonwearable Devices and Consistency of the Measured Parameters: Pilot Feasibility Study.

As Japan is the world's fastest-aging society with a declining population, it is challenging to secure human resources for care providers. Therefore, the Japanese government is promoting digital transformation and the use of nursing care equipment, including nonwearable devices that monitor heart and respiratory rates. However, the feasibility of monitoring heart and respiratory rates with nonwearable devices and the consistency of the rates measured have not been reported. In this study, we focused on a sheet-type nonwearable device (Safety Sheep Sensor) introduced in many nursing homes. We evaluated the feasibility of monitoring heart rate (HR) and respiratory rate (RR) continuously using nonwearable devices and the consistency of the HR and RR measured. A sheet-type nonwearable device that measured HR and RR every minute through body vibrations was placed under the mattress of each participant. The participants in study 1 were healthy individuals aged 20-60 years (n=21), while those in study 2 were older adults living in multidwelling houses and required nursing care (n=20). The HR was measured using standard methods by the nurse and using the wearable device (Silmee Bar-type Lite sensor), and RR was measured by the nurse. The primary outcome was the mean difference in HR and RR between nonwearable devices and standard methods. The mean difference in HR was -0.32 (SD 3.12) in study 1 and 0.04 (SD: 3.98) in study 2; both the differences were within the predefined accepted discrepancies (<5 beats/min). The mean difference in RR was -0.98 (SD 3.01) in study 1 and -0.49 (SD 2.40) in study 2; both the differences were within the predefined accepted discrepancies (3 breaths/min). HR and RR measurements obtained using the nonwearable devices and the standard method were similar. Continuous monitoring of vital signs using nonwearable devices can aid in the early detection of abnormal conditions in older people.

Abnormal Pavement Condition Detection with Vehicle Posture Data Considering Speed Variations.

Pavement condition monitoring is an important task in road asset management and efficient abnormal pavement condition detection is critical for timely conservation management decisions. The present work introduces a mobile pavement condition monitoring approach utilizing low-cost sensor technology and machine-learning-based methodologies. Specifically, an on-board unit (OBU) embedded with an inertial measurement unit (IMU) and global positioning system (GPS) is applied to collect vehicle posture data in real time. Through a comprehensive analysis of both time domain and frequency domain data features for both normal and abnormal pavement conditions, feature engineering is conducted to identify how the most important features affect abnormal pavement condition recognition. Six machine learning models are then developed to identify different types of pavement conditions. The performance of different algorithms and the significance of different features are then analyzed. Moreover, the influence of vehicle speed on pavement condition assessment is further examined and classification models for different speed intervals are developed. The results indicate that the random forest (RF) model that considers vehicle speed achieves the best performance in pavement condition monitoring. The outcomes of the present work would contribute to cost-effective pavement condition monitoring and provide an important reference for pavement maintenance sectors.

ADAPTATION OF THE ALGORITHM FOR DETECTING ANOMALIES IN TIME SERIES FOR NON-STATIONARY STREAMING DATA

Detection of anomalies in streaming time series data has become an important research topic due to the wide range of possible applications, including the detection of extreme weather conditions, malicious attacks on protected facilities, monitoring unauthorised gas and oil leaks, illegal pipeline connections, power cable faults, and water and other environmental pollution. Rapid detection of abnormal conditions and identifying these critical events is essential to protect lives and assets. Therefore, developing appropriate systems and detection methods is an urgent task. Anomaly detection in streaming data is challenging due to its large volume and high speed, presence of noise, and non-stationarity of the signal (or ‘concept drift’). The latter significantly complicates the identification of differences between new ‘typical’ behaviour and abnormal events. Solving this problem requires the algorithm for processing such data to learn and adapt to changing conditions. The paper proposes a modification of the algorithm for detecting anomalies in time series. This algorithm provides early detection of abnormal series in a massive collection of non-stationary streaming time series data. Anomalies are observations that are highly improbable given the previous time series values. The proposed approach is based on the primary detection of the predictive limit for the typical system behaviour using the theory of extreme values, followed by checking for the abnormality of the following series using the sliding window technique. The time series parameters are used as input data and compared by density distribution to detect any significant changes in the distribution of the characteristics. It allows the decision-making model to automatically adapt to the changing environment according to detected changes. Since anomalies are, by definition, exceptions to the typical behaviour of a system, most of the available stored data should reflect that typical behaviour of the system in question. It is unnecessary to have representative samples of all possible types of the standard behaviour of a given system for the algorithm to work well. The basic idea is to have a warm-up data set to obtain initial values for the decision model parameters. It makes it possible to determine if there is any significant difference between the last typical behaviour and the new typical behaviour. The proposed algorithm demonstrates its performance under conditions of noisy non-stationary data in several time series classes. Keywords: concept drift, extreme value theory, multivariate time series, outlier detection.

Exploring the effects of overvoltage unbalances on three phase induction motors: Insights from motor current spectral analysis and discrete wavelet transform energy assessment

This paper explores the diagnosis of faults related to 10 % and 20 % overvoltages in phase A of a three-phase induction motor. The study is based on numerical simulation results using MATLAB software. The primary objective of this research is to investigate the impact of such voltage unbalance on induction motors, principally on the three-phase stator currents and the electromagnetic torque. The results demonstrated that this voltage aberration causes significant harm to the motor. This is evidenced by the resulting highly unbalanced stator currents and oscillatory torque leading to subsequent mechanical disturbances.The study's second objective is to diagnose anomalies using Motor Current Spectral Analysis (MCSA), encompassing a comprehensive analysis of all three phases. The analysis proved to be effective in detecting such faulty circumstances. The direct current (Id) and the quadrature current (Iq) were also analyzed to reinforce the study. Providing an alternative perspective to explore the consequences of the imbalance. To enhance these findings and validate the previous analysis, the energy analysis based on Discrete Wavelet Transform (DWT) was applied to the three phases, Id and Iq currents.The assessment focused on energy analysis, enabled the detection of abnormal conditions, and demonstrated a noteworthy coherence with spectral analysis. The observed congruence provides evidence for the dependability and effectiveness of these methods in identifying faults, whether they are used in combination or separately.

Automatic Detection of Abnormal Drone Flight State by Measuring Changes in Images Captured by a Drone-Mounted Camera

Automatic Detection of Abnormal Drone Flight State by Measuring Changes in Images Captured by a Drone-Mounted Camera

Online Deep Learning for High-Speed Train Traction Motor Temperature Prediction

As the core component of the traction drive system of high-speed trains, the working condition of the traction motor is directly related to the operational safety of the train. During train operation, the temperature signal of the traction motor is constantly changing. Accurate prediction of the traction motor temperature using real-time data generated by sensors at the train end is beneficial for the early detection of abnormal motor conditions. The traditional approach is to apply prediction models from offline learning to the onboard side of the train for real-time temperature prediction, but its prediction accuracy degrades with the online data distribution changed. Therefore, this paper proposes an online deep learning model (ODL) for real-time traction motor temperature prediction. The ODL model uses DNN as its basic structure and hedging strategy to achieve online learning of the model parameters, which can dynamically adjust the model structure and parameters to adapt to streaming data with changing probability distributions. Finally, the study conducts multiple motor temperature prediction experiments using multi-sensor data from train operations. The results show that the ODL model outperforms the currently popular models in temperature prediction and can be effectively applied to real-time temperature prediction on the train end.

Abnormal State Detection in Lithium-ion Battery Using Dynamic Frequency Memory and Correlation Attention LSTM Autoencoder

Abnormal State Detection in Lithium-ion Battery Using Dynamic Frequency Memory and Correlation Attention LSTM Autoencoder

Anomaly Detection of Axial Piston Pump Based on the DTW-RCK-IF Composite Method Using Pressure Signals

Axial piston pumps are critical components of hydraulic systems due to their compact design and high volumetric efficiency, making them widely used. However, they are prone to failure in harsh environments characterized by high pressure and heavy loads over extended periods. Therefore, detecting abnormal behavior in axial piston pumps is of significant importance. Traditional detection methods often rely on vibration signals from the pump casings; however, these signals are susceptible to external environmental interference. In contrast, pressure signals exhibit greater stability. In this study, we propose a novel anomaly detection method for axial piston pumps, referred to as DTW-RCK-IF, which combines dynamic time warping (DTW) for data segmentation, a random convolutional kernel (RCK) for feature extraction, and isolation forest (IF) for anomaly detection using pressure signals. The model is trained using normal operating data to enable the effective detection of abnormal states. First, the DTW algorithm is employed to segment the raw data, ensuring a high degree of similarity between the segmented data. Next, the random convolutional kernel approach is used in a convolutional neural network for feature extraction, resulting in features that are representative of normal operating conditions. Finally, the isolation forest algorithm calculates the anomaly scores for anomaly detection. Experimental simulations on axial piston pumps demonstrate that, compared with vibration signals, the DTW-RCK-IF approach using pressure signals yields superior results in detecting abnormal data, with an average F1 score of 98.79% and a good fault warning effect. Validation using the publicly available CWRU-bearing and XJTU-SY-bearing full-life datasets further confirms the effectiveness of this method, with average F1 scores of 99.35% and 99.73%, respectively, highlighting its broad applicability and potential for widespread use.

Digital twin-driven robotic arm operation simulation and health management research

To reduce the complexity of monitoring and management of robots in service, a six-axis robot control system based on digital twin is proposed. Based on 3D printing technology, a six-axis robot is developed. At the same time, the kinematics of the robot is analyzed, and its kinematics model is built using the D-H rule. The forward and reverse kinematics of the robot are solved. Through the two-way data interaction between the model layer and the entity layer, the simulation operation of the robot and the twin synchronous operation of the virtual real robot are realized. Based on the real-time data drive, the key parameters of the robot are monitored, and the health parameter table of the current, voltage, joint vibration, and other parameters of the robot system is established. Based on the idea of comparison of the same kind, the abnormal state detection of the robot is realized through quantitative analysis. Finally, the feasibility of the proposed system is verified by experiments.

The Monitoring of Abnormal Fluid Properties Based on PCA Technique as an Alternative Strategy to Support Autonomous Drilling Operations

Summary The well drilling process requires constant monitoring to ensure that the properties of the drilling fluids remain within acceptable ranges for safe and effective operation of the well drilling process. The present work developed a principal component analysis (PCA)-based methodology for diagnosing anomalies in drilling fluids, and detecting and identifying abnormal drilling fluid properties during well drilling operations. The main novelty of the present work regards the application of multivariate techniques for diagnosing anomalies (faults) in drilling fluids, increasing the literature on fault diagnosis techniques applied to the petroleum industry, and producing a promising methodology for field applications. The proposed technique was implemented and validated in a pilot drilling fluid production unit through continuous online monitoring of the conductivity, density, and apparent viscosity of drilling fluids. Model training was carried out with data collected during assisted normal operation, allowing detection of abnormal conditions with less than 1% of false positives and less than 0.5% of false negatives. Additionally, the proposed methodology also allowed the correct diagnosis of the observed faults. The results indicated that PCA-based approaches can be used for the online monitoring of drilling fluid properties and fault diagnosis in real well drilling operations.

Abnormal Condition Detection Method of Industrial Processes Based on the Cascaded Bagging-PCA and CNN Classification Network

The accurate detection of abnormal working conditions is very important for the safe and stable operation of production process in process industry. Considering that normal data can be easily obtained in industry, unsupervised learning is one of the important methods of anomaly detection. Different from the experience setting of unsupervised anomaly detection index, supervised learning can set anomaly detection index automatically. But it is mostly used in the research of fault classification. In this paper, a new Cascaded Bagging-PCA and CNN Classification Network (CBPCA-CNN) was proposed to realize supervised anomaly detection. The proposed CBPCA-CNN method had the advantages of unsupervised feature extraction and supervised classification decision, which was helpful to improve the detection accuracy. The validation results on the standard data set of the TE process showed that the average accuracy of CBPCA-CNN method was 97.67%, which was higher than the compared methods. This paper verified the feasibility of using supervised learning method to solve anomaly detection.

Underground abnormal sensor condition detection based on gas monitoring data and deep learning image feature engineering

Underground gas sensors as the most intuitive tool for monitoring gas concentrations in underground mining, yet they are subject to frequent anomalies due to ground pressure, constructions, even malicious masking by workers. Due to the depth of underground mining and the complexity of the environment, it is almost impossible to manually monitor the status of the all the sensors. Thus, the ability to accurately identify the working status of gas sensors at the working face are critical importance to mining safety. In this paper, we propose a deep learning feature engineering based approach to coupling the relationship between underground sensors. Experiment results show that the relationship between gas sensors can be expressed by position and time, so that when a sensor such as upper corner T0 malfunctions, it can be detected by other sensors such as T1 and T2. By converting the gas concentration into the form of recurrence plots (RPs), we are able to transform time-series gas concentration data into images with more dimensions in time lag, and enabling the application of more efficient and accurate machine vision methods. Based on the location of sensors at the working face, we found that the sensors at positions T0, T1 and T2 are correlated as the wind flows through the tunnel and have a higher correlation in the subsections of the time series. And those correlation can directly use to check the operating status of the sensors. We also discuss whether the relationships between the data itself can be preserved at the feature level during the mapping of gas concentrations to features, since deep learning (DL) looks like the next promise future after digitization in the mining industrialization with more and more data analysis and placing the results under a larger decision. This feature-based approach for gas concentration analysis can also be used for prediction and early warning.

Insulator Abnormal Condition Detection from Small Data Samples.

Insulators are an important part of transmission lines in active distribution networks, and their performance has an impact on the power system's normal operation, security, and dependability. Traditional insulator detection methods, on the other hand, necessitate a significant amount of labor and material resources, necessitating the development of a new detection method to substitute manpower. This paper investigates the abnormal condition detection of insulators based on UAV vision sensors using artificial intelligence algorithms from small samples. Firstly, artificial intelligence for the image data volume requirements was large, i.e., the insulator image samples taken by the UAV vision sensor inspection were not enough, or there was a missing image problem, so the data enhancement method was used to expand the small sample data. Then, the YOLOV5 algorithm was used to compare detection results before and after the extended dataset's optimization to demonstrate the expanded dataset's dependability and universality, and the results revealed that the expanded dataset improved detection accuracy and precision. The insulator abnormal condition detection method based on small sample image data acquired by the visual sensors studied in this paper has certain theoretical guiding significance and engineering application prospects for the safe operation of active distribution networks.

Abnormal diagnosis of acoustic emission pipeline working conditions based on PSO-LSTM-DAE

To solve the problem of difficult identification of pipeline working conditions, acoustic emission was used to extract abnormal pipeline data, and a PSO-Lstm-DAE model was proposed to classify and identify abnormal working conditions of acoustic emission pipelines. The algorithm took advantage of the timing characteristics of LSTM and the noise reduction ability of DAE and set the optimal superparameters through PSO. In this paper, four commonly used abnormal condition detection data sets were collected, and algorithm tests were carried out on the data sets and compared with other anomaly detection algorithms. The classification accuracy of the proposed PSO-LSTM-DAE model was 95.68%. The results of multiple indexes show that the PSO-LSTM-DAE model proposed in this paper has significant advantages in the diagnosis of abnormal pipeline conditions.

Scale-independent shrinkage broad learning system for wheelset bearing anomaly detection under variable conditions

Wheelset bearing fault diagnosis is essential to guarantee safe rail system operation. However, real-time monitoring signals of high-speed trains are nonstationary under variable conditions. Additionally, wheelset bearings operate in a normal state most of the time, and therefore, only normal data are available for training in practice. Under such a scenario of variable operating conditions and lacking labelled data, it is still necessary to timely detect the possible abnormal states of wheelset bearings. Currently, one-class classification is a suitable approach for real-time anomaly detection, but its accuracy is affected by the linear relationship of network nodes. Concerning this issue, this paper presents a novel method named scale-independent shrinkage broad learning to detect the abnormal states of wheelset bearings in real time. First, scaled rotation regularization is presented to convert the output constraint into the node distance constraint. Then, the variance-guided mapping mechanism is constructed to solve the linear relationship between nodes. Meanwhile, the optimal network mapping parameters are generated iteratively according to a so-called high-polymerization strategy, with which new output weights are formed after the feedback calculation. This method eliminates the linear correlation of node features during the iteration and realizes one-class classification detection of abnormal states. Finally, wheelset bearing data collected from a test rig of a Chinese rolling stock company are utilized to demonstrate the feasibility and effectiveness of the proposed approach in variable conditions.

Early Detection of Health Condition Degradation of Circuit Breaker Based on Electrical Quantity Monitoring

Circuit breakers on the filter bank branches in converter stations are vulnerable to contact wear and mechanical deterioration caused by frequent operations, which can lead to circuit breaker breakdowns and explosions. It is imperative to conduct research on the early detection of abnormal states in circuit breakers. Existing electrical quantity-based detection methods are constrained by a priori assumptions, and their measurement methods are susceptible to interference, leading to misjudgments. To address this issue, this paper examines the influence of changes in critical breakdown field strength and contact spacing on circuit breaker operation states. It also proposes a technical scheme that employs breakdown current values to comprehensively characterize circuit breaker operation states, replacing the use of critical breakdown field strength and contact spacing. An early detection method for abnormal circuit breaker states based on a sequence of breakdown current ratios at different times is proposed, and its effectiveness is verified through simulation and field recording data.

Leveraging and Refining Image Recognition Technology for Intelligent Logistics Sorting Systems

Obstacles in the realm of target detection, tracking accuracy, real-time performance, and robustness have been identified within the context of intelligent logistics sorting systems, which incorporate image recognition technology. Furthermore, the critical role of detecting anomalous states in augmenting sorting efficiency and curtailing errors is underscored. Image recognition technologies of a conventional nature tend to suffer from limitations in their applicability and robustness. In practical working environments, a paucity of abnormal data from logistics sorting targets is observed, which inhibits the application of supervised learning methods of deep learning. Addressing these challenges, an unsupervised deep learning method is introduced for the detection of anomalous states in logistics sorting targets. This approach reinterprets the detection of logistics sorting targets as an anomaly detection problem and utilizes Variational AutoEncoders (VAE) for modeling the distribution of normal data. This method's dependency rests exclusively on normal data for training, thereby circumventing the need for a substantial quantity of abnormal samples. In practical deployments, the anomalous state of logistics sorting targets is discerned by the method through the computation of similarity and implementation of labeling algorithms, evidencing robustness, generalizability, and adaptability. Overall, this method is presented as an effective solution for the detection of anomalous states within intelligent logistics sorting scenarios, serving to decrease labeling costs, enhance detection accuracy and efficiency, and satisfying the practical requisites of logistics sorting systems for abnormal state detection.

Early Detection and Diagnosis of Wind Turbine Abnormal Conditions Using an Interpretable Supervised Variational Autoencoder Model

The operation and maintenance of wind turbines benefit from reliable information on the wind turbine condition. Data-driven models use data from the supervisory data acquisition system. In particular, great performance is reported for artificial intelligence models. However, the lack of interpretability limits their effective industrial implementation. The present work introduces a new condition-monitoring approach for wind turbines featuring a built-in visualization tool that confers interpretability upon the model outcomes. The proposed approach is based on a supervised implementation of the variational autoencoder model, which allows the projection of the wind turbine system onto a low-dimensional representation space. Three outcomes follow from such representation: a health indicator for the early detection of abnormal conditions, a classifier providing the diagnosis status, and a visualization tool depicting the wind turbine condition as a trajectory in a 2D plot. The approach is implemented with a vast database. Two case studies demonstrate the potential of the proposed approach. The proposed health indicator detects the main bearing overtemperature 11 days before the control system alarm, one week earlier than a competing approach. Study cases illustrate that the built-in visualization tool enhances the interpretability and trust in the model outcomes, thus supporting wind turbine operation and maintenance.

Current Transformer Saturation Detection Method Based on Artificial Neural Network

When current transformer is saturated, mainly due to the presence of an exponentially decaying DC component in the fault current, its secondary current has a distinctive distorted waveform which significantly differs from its primary (true) waveform. It leads to an underestimation of the secondary current value calculated by the relay protection compared to its true value. Thus, in its turn, results in trip time delay or even in a relay protection devices operation failure, since its settings and algorithms are calculated and designed on the assumption that the secondary current waveform is sinusoidal and proportional to the primary. And since, when using classical electromagnetic current transformer, it is impossible to exclude the possibility of its saturation, the detection of such abnormal condition is an urgent technical problem. The article proposes to use an artificial neural network for this purpose, which, together with the traditional method of saturation detection based on adjacent secondary current samples comparison, allows implementing a fast and reliable current transformer saturation detector. The article details the stages of the practical implementation of such an artificial neural network. The MATLAB-Simulink environment was used for assess the proposed saturation detector operation. The experiments that had been performed confirmed that proposed method provides fast and accurate saturation detection within the wide range of the power system and current transformer parameters change.

Smart Transportation: An Overview of Technologies and Applications.

As technology continues to evolve, our society is becoming enriched with more intelligent devices that help us perform our daily activities more efficiently and effectively. One of the most significant technological advancements of our time is the Internet of Things (IoT), which interconnects various smart devices (such as smart mobiles, intelligent refrigerators, smartwatches, smart fire alarms, smart door locks, and many more) allowing them to communicate with each other and exchange data seamlessly. We now use IoT technology to carry out our daily activities, for example, transportation. In particular, the field of smart transportation has intrigued researchers due to its potential to revolutionize the way we move people and goods. IoT provides drivers in a smart city with many benefits, including traffic management, improved logistics, efficient parking systems, and enhanced safety measures. Smart transportation is the integration of all these benefits into applications for transportation systems. However, as a way of further improving the benefits provided by smart transportation, other technologies have been explored, such as machine learning, big data, and distributed ledgers. Some examples of their application are the optimization of routes, parking, street lighting, accident prevention, detection of abnormal traffic conditions, and maintenance of roads. In this paper, we aim to provide a detailed understanding of the developments in the applications mentioned earlier and examine current researches that base their applications on these sectors. We aim to conduct a self-contained review of the different technologies used in smart transportation today and their respective challenges. Our methodology encompassed identifying and screening articles on smart transportation technologies and its applications. To identify articles addressing our topic of review, we searched for articles in the four significant databases: IEEE Xplore, ACM Digital Library, Science Direct, and Springer. Consequently, we examined the communication mechanisms, architectures, and frameworks that enable these smart transportation applications and systems. We also explored the communication protocols enabling smart transportation, including Wi-Fi, Bluetooth, and cellular networks, and how they contribute to seamless data exchange. We delved into the different architectures and frameworks used in smart transportation, including cloud computing, edge computing, and fog computing. Lastly, we outlined current challenges in the smart transportation field and suggested potential future research directions. We will examine data privacy and security issues, network scalability, and interoperability between different IoT devices.