Condition Monitoring Model Research Articles

Corrections

This article corrects the following: Volume 3 Issue 1 Journal of Dynamics, Monitoring and Diagnostics Statistical Models for Condition Monitoring and State of Health Estimation of Lithium-Ion Batteries for Ships Pages: 11-20 First Published online: 29 Feb 2024 DOI: https://doi.org/10.37965/jdmd.2024.500 On page 19 of the PDF, the following correction should be noted. The acknowledgements in the previously published PDF version were incomplete. An updated PDF version of it is provided below. This correction notice has been linked to the online version of the article.

Application of a surrogate model for condition monitoring of a digital twin gas turbine

Condition monitoring technology plays a crucial role in ensuring the reliable operation of gas turbines. Digital twin has propelled condition monitoring research into a new phase. This paper established a surrogate model of gas turbines for condition monitoring based on Markov-projection approximation subspace tracking. Furthermore, it explores the application of surrogate model in developing digital twin for gas turbines. The study initially establishes a Markov matrix and acquires an observation vector, utilizing the framework of the linear model. Utilizing real-time measurement data of gas turbine, the signal subspace of the observation vector autocorrelation matrix is updated through the projection approximation subspace tracking. By aligning this signal subspace with the generalized observability matrix, the identification results of the surrogate model parameters are obtained online. Furthermore, a variable weight projection approximation subspace tracking method has been proposed to enhance the algorithm robustness. Simulation and real experiment demonstrate that the surrogate model output effectively tracks the real-time changes in gas turbine measurement data. When faults and degradation arise, condition monitoring can be achieved by analyzing the evolution of model parameters to obtain feedback information from the gas turbine. The proposed method maintains its robustness in the presence of impulsive noise. These features offer a novel approach for the development of gas turbine digital twin.

Upstream process condition monitoring for froth flotation based on feature performance evaluation and parameter-mapped GRNN

Timely and reliable estimation of the upstream process condition in flotation process is significant for whole flotation operations. An upstream process condition monitoring model based on feature performance evaluation and parameter-mapped generalized regression neural network (GRNN) is proposed to evaluate visual feature performance and improve the generalization ability of ensemble models for zinc flotation. Firstly, different visual features are extracted, and the froth video representation is obtained. Then, feature performance evaluation is constructed, considering the correlation between different visual features and flotation indicators, and stability of feature representation ability vary. Meanwhile, feature performance evaluation indexes are calculated introducing a scale factor to integrate the Pearson correlation with feature stability coefficient. Finally, a parameter-mapped GRNN, whose base model parameters are mapped into a certain interval, is designed to monitor the upstream process condition based on the feature performance evaluation index-weighted feature vector. Experiments using real-world lead–zinc flotation data were implemented to show the potential of the feature performance evaluation and effectiveness of the proposed model.

RUL Prediction of Rolling Bearings Based on Multi-Information Fusion and Autoencoder Modeling

As an important part of industrial equipment, the safe and stable operation of rolling bearings is an important guarantee for the performance of mechanical equipment. Aiming at the problem that it is difficult to characterize the running state of rolling bearings, this paper mainly analyzes and processes the vibration signals of rolling bearings, extracts and fuses multi-information entropy, and monitors the running state of rolling bearings and predicts the remaining useful life prediction (RUL) through test verification. Firstly, in view of the difficulty in characterizing the bearings running state characteristics, a rolling bearings running state monitoring method based on multi-information entropy fusion and denoising autoencoder (DAE) was proposed to extract the multi-entropy index features of vibration signals to improve the accuracy of feature extraction, and to solve the problem of not obvious information representation of a single feature indicator and missing information in the feature screening process. Secondly, in view of the problems of low prediction accuracy and poor robustness and generalization in traditional RUL models, a rolling bearings RUL model combining convolutional autoencoder (CAE) and bidirectional long short-term memory network (BiLSTM) was proposed. The introduction of convolution operation made CAE have the feature of weight sharing, reducing the complexity of the model. Finally, the XJTU-SY data set was used to verify the constructed model. The results show that the condition monitoring model established in this paper can accurately evaluate the running state of the rolling bearing and accurately locate the failure time. At the same time, the residual life prediction model can realize the residual life prediction of most data sets, and has good accuracy and robustness.

Quantifying the surface damage of involute gear flanks independent of the gear datum axis

Abstract Surface damage on involute gear tooth flanks can develop during the operation of a gearbox and affects their life, durability and efficiency. Understanding the extent and severity of this damage is critical, especially in long life applications such as wind turbines where gearboxes are a critical component that incur high down time and costs for replacement. Accessing gears in service is difficult and relating gear form measurements to the gear datum is often impossible without its removal. Additionally, damage measurements are typically not areal, which can miss the most severe areas, or require lengthy measurement times. This paper describes a method for characterising and quantifying localised damage relative to the undamaged tooth surface independent of the gear datum axis, and provides a method to estimate the damage location using involute co-ordinates. By taking soft replicas of the gear flank and measuring them with optical methods, the damage is characterised. This method allows for the areal evaluation of damage that relates to involute coordinates, which can be combined with nominal data or measurements after manufacture to create data sets for simulation in tooth contact analysis models, used to train condition monitoring models or for improved maintenance programming to improve reliability and reduce costly downtime.

A Condition Monitoring Method of Hydraulic Gear Pumps Based on Multilevel Mechanism-Data Fusion

Pumps are important components in aviation fuel hydraulic systems, and thanks to the development of sensor technology and industrial intelligence technology, it is possible to achieve efficient state monitoring of pumps. However, when data quality is poor or the amount of data is small, a single data-driven model may not be able to meet diagnostic accuracy. A condition monitoring method for hydraulic gear pumps based on mechanism-data fusion is proposed. The method combines a mechanism model based on the volumetric efficiency formula with a data-driven model based on vibration signals. First, the parameters of volumetric efficiency are solved by fitting the pressure–flow relationship. Subsequently, a multichannel fusion and multikernel function-weighted ensemble support vector classification (MCMK-SVC) is developed, to establish a data-driven model. Finally, through data-level fusion, feature-level fusion, and decision-level fusion, a condition monitoring model based on mechanism-data fusion is built. Experimental verification shows that the accuracy of the three levels of fusion models exceeds 96.9%. Compared to the single data-driven model or other traditional data-driven models, the accuracy of the proposed method has improved by 3% to 33%, demonstrating the effectiveness of the mechanism-data fusion model.

A comparative study of machine learning regression models for production systems condition monitoring

A comparative study of machine learning regression models for production systems condition monitoring

Deep CNN Model for Condition Monitoring of Road Traffic: An Application Of Computer Vision

The traffic surveillance system accumulates an enormous amount of data regarding road traffic each second. Monitoring these data with the human eye is a tedious process and it also requires manpower for monitoring. Deep learning Convolutional Neural Network (DLCNN) can be utilized for traffic monitoring and control. The traffic surveillance data are preprocessed to construct the training dataset. The Traffic net is constructed by transferring the network to traffic applications and retraining it with a self-established data set. This Traffic-net can be used for regional detection in large scale applications. Further, it can be implemented across-the-board. Further, DLCNN is used for prediction of traffic status i.e., dense traffic, low traffic, accident, and fire occurred from test sample. Finally, the simulations revealed that the proposed DLCNN resulted in superior performance as compared to existing model.

Statistical Models for Condition Monitoring and State of Health Estimation of Lithium-Ion Batteries for Ships

Battery systems are increasingly being used for powering ocean going ships, and the number of fully electric or hybrid ships relying on battery power for propulsion is growing. To ensure the safety of such ships, it is important to monitor the available energy that can be stored in the batteries, and classification societies typically require the state of health (SOH) to be verified by independent tests. This paper addresses statistical modelling of SOH for maritime lithium-ion batteries based on operational sensor data. Various methods for sensor-based, data-driven degradation monitoring will be presented, and advantages and challenges with the different approaches will be discussed. The different approaches include cumulative degradation models and snapshot models, models that need to be trained and models that need no prior training, and pure data-driven models and physics-informed models. Some of the methods only rely on measured data, such as current, voltage and temperature, whereas others rely on derived quantities such as state of charge (SOC). Models include simple statistical models and more complicated machine learning techniques. Insight from this exploration will be important in establishing a framework for data-driven diagnostics and prognostics of maritime battery systems within the scope of classification societies. Conflict of Interest Statement The authors declare no conflicts of interest.

Wind turbine generator early fault diagnosis using LSTM-based stacked denoising autoencoder network and stacking algorithm

ABSTRACT To reduce the significant economic losses caused by the fault deterioration of wind turbine generators, it is urgent to detect and diagnose the early faults of generators. The existing condition monitoring and fault diagnosis (CMFD) methods have disadvantages of less considering data temporal characteristic, acquiring early faults with difficulty, and having lower diagnostic accuracy. To address those limitations, a novel LSDAE-stacking CMFD method of generators was proposed. Specifically, a multivariate spatiotemporal condition monitoring model (LSDAE) was established by combining the LSTM and SDAE networks, which can detect generator early anomalies through real-time monitoring the reconstruction residual. Then, based on the stacking ensemble algorithm, a multi-classification fault diagnosis model (Stacking) was constructed to identify early fault types, which can integrate advantages of different base-classifiers to achieve a better diagnostic accuracy. Case studies on three actual generator failures were employed to validate the effectiveness and accuracy of the proposed LSDAE-stacking method. The results illustrated that, compared with conventional SDAE model, the proposed LSDAE model had higher reconstruction precision and superior early-fault-warning capacities. And compared with traditional algorithms such as SVM, RF, AdaBoost, GBDT and XGBoost, the constructed Stacking model can effectively identify the fault types of generators and had higher diagnostic accuracy.

Research on unsupervised condition monitoring method of pump-type machinery in nuclear power plant

As a typical active equipment, pump machinery is widely used in nuclear power plants. Although the mechanism of pump machinery in nuclear power plants is similar to that of conventional pumps, the safety and reliability requirements of nuclear pumps are higher in complex operating environments. Once there is significant performance degradation or failure, it may cause huge security risks and economic losses. There are many pumps mechanical parameters, and it is very important to explore the correlation between multi-dimensional variables and condition. Therefore, a condition monitoring model based on Deep Denoising Autoencoder (DDAE) is constructed in this paper. This model not only ensures low false positive rate, but also realizes early abnormal monitoring and location. In order to alleviate the influence of parameter time-varying effect on the model in long-term monitoring, this paper combined equidistant sampling strategy and DDAE model to enhance the monitoring efficiency. By using the simulation data of reactor coolant pump and the actual centrifugal pump data, the monitoring and positioning capabilities of the proposed scheme under normal and abnormal conditions were verified. This paper has important reference significance for improving the intelligent operation and maintenance efficiency of nuclear power plants.

A comparative study on deep learning models for condition monitoring of advanced reactor piping systems

Advanced nuclear reactors offer innovative applications due to their portability, reliability, resiliency, and high capacity factors. To operate them on a wider scale, reducing maintenance life-cycle costs while ensuring their integrity is essential. Autonomous operations in advanced nuclear reactors using augmented Digital Twin (DT) technology can serve as a cost-effective solution by increasing awareness about the system’s health. A key component of nuclear DT frameworks is the condition monitoring of safety systems, such as piping-equipment systems, which involves acquiring and monitoring the plant’s sensor data. This research proposes a condition monitoring methodology utilizing deep learning algorithms, such as multilayer perceptions (MLP) and convolutional neural networks (CNNs), to detect degradation and its severity in nuclear piping-equipment systems. Sensor signals are processed to obtain the power spectral density and the Short-Time Fourier transform, and feature extraction methodologies are proposed to develop degradation-sensitive data repositories. The performance of MLP, one-dimensional (1D) CNN, and 2D CNN within the proposed condition monitoring framework is compared using a finite element model of a 3D piping system subjected to seismic loads as the application case study. Various approaches, such as dropout, k-Fold validation, regularization, and early stopping of training the network, are investigated to avoid overfitting the models to the input sensor data. The predictive capability and computational capacity of the deep learning algorithms are also compared to detect degradation in the Z-pipe system of the Experimental Breeder Reactor II (EBRII). The Z-pipe system is subjected to harmonic excitations that represent normal operating loads, such as pump-induced vibrations. The findings of the study indicate that the proposed artificial intelligence (AI)-driven condition monitoring framework demonstrates superior prediction accuracies with a 2D CNN, whereas the MLP exhibits higher computational efficiency.

Data-driven long-term condition-based maintenance using anomaly detection under concept drift: A case study of an ultrasonic sieve machine

Class imbalance and concept drift are two critical barriers to applying AI-based condition monitoring models in industrial manufacturing. In practical industrial production, there are usually more normal samples than abnormal samples, and the data distribution varies over time, limiting the training and the practical deployment of AI models. This paper proposes a solution based on anomaly detection and continual learning to address these two problems. Experiments on an ultrasonic vibrating sieve verify the solution's effectiveness. Learning on the normal samples can effectively identify sieve breakage, and continual learning can prevent model performance degradation.

Hybrid GA and Improved CNN Algorithm for Power Plant Transformer Condition Monitoring Model

Hybrid GA and Improved CNN Algorithm for Power Plant Transformer Condition Monitoring Model

Spatio-temporal information analytics based performance-driven industrial process monitoring framework with cloud–edge-device collaboration

Smart manufacturing in the context of Industry 4.0 presents new characteristics, such as large-scale, complex sub-processes cooperation, and integrated information management, which makes comprehensive performance-driven process monitoring difficult to be achieved in practice. Cloud–edge-device collaboration brings new perspectives for modern industries. This paper presents a performance-driven process monitoring framework in cloud–edge-device collaborative architecture, including a spatio-temporal information analytics based method and its application to a hot strip mill process (HSMP). Firstly, an integrated performance-driven process monitoring framework is proposed, where different monitoring tasks are deployed in the device, edge, and cloud layers, respectively. Secondly, a new performance-related spatio-temporal information analytics based fault detection and localization method is developed. In detail, temporal kernel canonical correlation analysis (CCA) is employed to extract the canonical correlation features with nonlinearities in the temporal domains, and spatial CCA is designed to form the spatial features. Based on the spatio-temporal features, the equipment operation condition monitoring model is developed in the device layer for real-time fault localization, and the process monitoring model is deployed in the edge for fault detection. Furthermore, to give a high-level evaluation of the operating status of the process, a qualitative trend analysis based operation risks evaluation model is deployed in the cloud. Different from the traditional architectures, the data processing capability of each layer is fully utilized in the proposed one, and the function is relevant to the enterprise management system. It provides a topological basis with clear priorities for subsequent process regulation and optimization. Finally, an actual HSMP is introduced to testify the performance of the framework. From the results, the fault detection rates are improved in comparison with traditional methods, and the fault localization results are consistent with the actual situations.

The Application of an Artificial Neural Network as a Baseline Model for Condition Monitoring of Innovative Humidified Micro Gas Turbine Cycles

Abstract Due to high penetration of renewables, the EU energy system is undergoing a transition from large-scale centralized generation toward small-scale distributed generation. The increasing share of intermittent renewables such as solar and wind has become the main driver for dispatchable distributed energy generation technologies to maintain the grid flexibility and stability. In this context, micro gas turbines (MGTs) with high fuel and operation flexibility could play a crucial role to guarantee the grid stability, enabling deeper penetration of the intermittent renewable energy sources. Despite this, the MGT market is still considered to be niche, and there are R&D&I challenges that need to be addressed to further promote this technology in distributed generation applications. Innovative MGT cycles based on a cycle humidification concept can be considered to obtain higher system performance. However, given the fact that MGTs are installed close to the consumption points, where they are operated by nontechnical prosumers with very limited access to maintenance services, they should also offer high availability and reliability to avoid unexpected outages and secure the supply. Therefore, intelligent monitoring systems are needed that can support nonexpert end-users to detect degradation and plan maintenance before a breakdown occurs. In this study, we investigated and developed advanced methods based on artificial neural networks (ANNs) for condition monitoring of a humidified MGT cycle under real-life operational conditions. To create a high-performing model, extensive data preprocessing has been conducted to remove data outliers and select optimum model features, which provide best results. Additionally, the model hyperparameters such as learning rate, momentum, and number of hidden nodes have been altered to achieve the most accurate predictions. The results of this study have provided a baseline ANN model capable of conducting condition monitoring of a micro humid air turbine (mHAT) system, which will be applied to additional studies in the future.

Cross-domain tool wear condition monitoring via residual attention hybrid adaptation network

Intelligent models for tool wear condition monitoring (TWCM) have been extensively researched. However, in industrial scenarios, limited acquired monitoring signals and variations of machining parameters lead to insufficient training samples and data distribution shifts for the models. To address the issues, this research presents a novel residual attention hybrid adaptation network (RAHAN) model based on a residual attention network (ResAttNet) and a hybrid adaptation strategy. In the RAHAN model, by integrating a channel attention mechanism and deep residual modules, ResAttNet is designed as a feature extractor to acquire features from monitoring signals for tool wear conditions. Embedding subdomain adaptation into a condition recognizer while establishing separate adversarial learning in a domain obfuscator, the hybrid adaptation strategy is developed to eliminate global distribution shifts and align local distributions of each tool wear phase simultaneously. Six migration tasks under a laboratory and two factory machining platforms were conducted to evaluate the effectiveness of the RAHAN model. Compared with a baseline model, four ablation models, and six state-of-the-art transfer learning models, the RAHAN model achieved the highest average accuracy of 92.70% on six migration tasks. Furthermore, the RAHAN model shows clearer feature representations of each tool wear condition than other compared models. The comparative results demonstrate that the RAHAN model has superior transferability and therefore can be considered as a good potential solution to support cross-domain TWCM under different machining processes.

A Hidden Markov Model for Condition Monitoring of Time Series Data in Complex Network Systems

Time series data are ubiquitous in complex network systems, where each component of the system is treated as a vertex and has sequentially collected autocorrelated observations for condition monitoring. In many cases, components transit between different states, such as “normal,” “degrading,” “failure,” etc., and under different states their distributions vary, resulting in the mixture marginal distribution of each vertex's time series data. Moreover, states of different components influence each other through the system's network topology, i.e., the state of a component itself and its neighbors jointly affect its data distribution. For efficient condition monitoring, it is important to capture the state evolution of all vertices as a whole over time. However, the state-switching may be unobservable, which complicates the modeling. Hence, this article proposes a hidden Markov model for networked time series data with mixture marginal distributions. The Markov transition rule for latent states captures the state-switching behavior and the AR model reveals the temporal dependence of vertices. The states of different vertices further influence each other through the network topology structure. The Baum–Welch algorithm is used to estimate the parameters of the proposed model, allowing for state inference and data fitting. Extensive numerical studies as well as real case studies demonstrate the effectiveness and applicability of the proposed model.

Hybrid system response model for condition monitoring of bearings under time-varying operating conditions

Hybrid system response model for condition monitoring of bearings under time-varying operating conditions

Statistical process control versus deep learning for power plant condition monitoring

This study compares four models for industrial condition monitoring including a principal components analysis (PCA) approach and three deep learning models, one of which is a new, lightweight version of another. We also propose a simple attention mechanism for enchancing deep learning models with better predictions and feature importance. Two datasets are used, one simulated from the Tennessee Eastman Process, the other from two feedwater pumps at a Danish combined heat and power plant. Our final results show evidence in favour of the PCA-based approach as it has detection ability comparable to the deep learning approaches as well as faster training time, fewer hyperparameters, as well as robustness to changing operating conditions. We conclude the paper by putting into perspective the importance of building up complexity incrementally with a recommendation to start modelling with simpler and well-tested models before the adoption of more advanced, less transparent models.