Search

Prognostics and Health Management (PHM) models aim to estimate remaining useful life (RUL) of complex systems, enabling lower maintenance costs and increased availability. A substantial body of work considers the development and testing of new models using the NASA C-MAPSS dataset as a benchmark. In recent work, the use of ensemble methods has been prevalent. This paper proposes two adaptations to one of the best-performing ensemble methods, namely the Convolutional Neural Network – Long Short-Term Memory (CNN-LSTM) network developed by Li et al. (IEEE Access , 2019, 7 , pp 75464–75475)). The first adaptation (adaptable time window, or ATW) increases accuracy of RUL estimates, with performance surpassing that of the state of the art, whereas the second (sub-network learning) does not improve performance. The results give greater insight into further development of innovative methods for prognostics, with future work focusing on translating the ATW approach to real-life industrial datasets and leveraging findings towards practical uptake for industrial applications. [ABSTRACT FROM AUTHOR]

Background: A considerable volume of possible applications of artificial intelligence (AI) in the field of rhinology exists, and research in the area is rapidly evolving. Objective: This scoping review aims to provide a brief overview of all current literature on AI in the field of rhinology. Further, it aims to highlight gaps in the literature for future rhinology researchers. Methods: OVID MEDLINE (1946-2022) and EMBASE (1974-2022) were searched from January 1, 2017 until May 14, 2022 to identify all relevant articles. The Preferred Reporting Items for Systematic Reviews and Meta-analyses Extension for Scoping Reviews checklist was used to guide the review. Results: A total of 2420 results were identified of which 62 met the eligibility criteria. A further 17 articles were included through bibliography searching, for a total of 79 articles on AI in rhinology. Each year resulted in an increase in the number of publications, from 3 articles published in 2017 to 31 articles published in 2021. Articles were produced by authors from 22 countries with a relative majority coming from the USA (19%), China (19%), and South Korea (13%). Articles were placed into 1 of 5 categories: phenotyping/endotyping (n = 12), radiological diagnostics (n = 42), prognostication (n = 10), non-radiological diagnostics (n = 7), surgical assessment/planning (n = 8). Diagnostic or prognostic utility of the AI algorithms were rated as excellent (n = 29), very good (n = 25), good (n = 7), sufficient (n = 1), bad (n = 2), or was not reported/not applicable (n = 15). Conclusions: AI is experiencing an increasingly significant role in rhinology research. Articles are showing high rates of diagnostic accuracy and are being published at an almost exponential rate around the world. Utilizing AI in radiological diagnosis was the most published topic of research, however, AI in rhinology is still in its infancy and there are several topics yet to be thoroughly explored. [ABSTRACT FROM AUTHOR]

A robust recursive zonotopic set-membership approach for remaining useful life forecasting with application to linear parameter-varying systems is proposed in this paper. The proposed approach addresses systems with degraded components formulated as a system-level prognostics problem. Thus, the critical degraded components of the system are augmented to the states resulting a nonlinear system that is reformulated as a linear parameter-varying model. Hence, joint estimation of states and parameters is adopted in a zonotopic set-membership scheme with an optimal linear matrix inequality-based tuning and assuming unknown-but-bounded noises and uncertainties. As a result, a recursive zonotopic set-membership approach is proposed for remaining useful life forecasting based on the prediction of the failure precursors of degraded systems. Finally, this approach is tested on a DC–DC converter case study with unknown degradation behaviors, and the obtained results show the estimation and the forecasting accuracy of this methodology. • Zonotopic set-membership for prognostics applications. • Joint estimation of states and parameters for degraded systems. • Bounded degradation prediction and remaining useful life forecasting. • LMI-based optimization for robust zonotopic observer tuning for LPV systems. [ABSTRACT FROM AUTHOR]

Introduction: There is a great need for fully automated plasma assays that can measure amyloid beta (Aβ) pathology and predict future Alzheimer's disease (AD) dementia. Methods: Two cohorts (n = 920) were examined: Panel A+ (n = 32 cognitively unimpaired [CU], n = 106 mild cognitive impairment [MCI], and n = 89 AD) and BioFINDER‐1 (n = 461 CU, n = 232 MCI). Plasma Aβ42/Aβ40, phosphorylated tau (p‐tau)181, two p‐tau217 variants, ApoE4 protein, neurofilament light, and GFAP were measured using Elecsys prototype immunoassays. Results: The best biomarker for discriminating Aβ‐positive versus Aβ‐negative participants was Aβ42/Aβ40 (are under the curve [AUC] 0.83–0.87). Combining Aβ42/Aβ40, p‐tau181, and ApoE4 improved the AUCs significantly (0.90 to 0.93; P< 0.01). Adding additional biomarkers had marginal effects (ΔAUC ≤0.01). In BioFINDER, p‐tau181, p‐tau217, and ApoE4 predicted AD dementia within 6 years in CU (AUC 0.88) and p‐tau181, p‐tau217, and Aβ42/Aβ40 in MCI (AUC 0.87). Discussion: The high accuracies for Aβ pathology and future AD dementia using fully automated instruments are promising for implementing plasma biomarkers in clinical trials and clinical routine. [ABSTRACT FROM AUTHOR]

Industrial components and systems undergo degradation in process operations. Prognostics and health management (PHM) is a process to assess and predict health conditions of components and can be applied to condition-based monitoring and maintenance. PHM is commonly utilized to analyze the health condition of a single lifecycle until failure. When maintenance occurs, degradation can be removed, and the PHM model can be restarted with new parameters related to the expected postmaintenance conditions. Maintenance actions, mostly imperfect repairs, may not entirely reset the condition to as good as new, and further degradation may occur at a higher rate. Maintenance repairs should be considered in prognostic models to predict component health more accurately. Furthermore, processes typically have more than one component that degrade and influence process measurements. The dependence of process measurements to multiple fault modes and related degradation can make individual component health monitoring complex. Commonly, faults and their related effects on process parameters must be isolated. In these cases, the diagnostics and prognostics framework should handle unsynchronized failure and maintenance reinitialization of different components for multiple fault processes. This research paper presents the Maintenance-Dependent Monitoring and Prognostics Model (MDMPM) to detect anomalies, decouple faults for different components, and predict future health conditions to calculate remaining useful life (RUL). The model is demonstrated with semisimulated nuclear power plant (NPP) data, with simultaneous condenser pump degradation and condenser tube fouling. The MDMPM shows a reliable prediction of RULs of NPP maintenance-dependent processes with interacting component degradation modes. [ABSTRACT FROM AUTHOR]

Predictive maintenance (PdM) aims the reduction of costs to increase the competitive strength of the enterprises. It uses sensor data together with analytics techniques to optimize the schedule of maintenance interventions. The application of such maintenance strategy requires the cooperation of several agents and involves knowledge and skills in distinct fields, since it encompasses from the averaging of relevant signals in the shop-floor to its processing, transmission, storage, and analysis in order to extract meaningful knowledge. PdM is a broad topic, making it impossible to address all its subtopics in the same paper. Having this into consideration, this paper focuses on the main challenges that hinder the development of a generalized data-driven system for PdM, namely: the existence of noisy or erroneous sensor data in a real industrial environment; the necessity to collect, transmit and process high volumes of data in a timely manner; and the fact that current approaches for PdM are specific for a part or equipment rather than global. This paper connects three different perspectives: anomaly detection, which allows the removal of noisy or erroneous data and the detection of relevant events that can be used to improve the prognostics methods; prognostics methods, which address the models to forecast the condition of industrial equipment; and the architectures, which may allow the deployment of the anomaly detection and prognostics methods in real-time and in different industrial scenarios. Furthermore, the last trends, current challenges and opportunities of each perspective are discussed over the paper. [ABSTRACT FROM AUTHOR]

Bearing is one of the critical components in rotating equipment. Therefore, accurate estimation of the remaining useful life (RUL) of bearings plays a vital role in reducing the costly unplanned maintenance and increasing the reliability of machines. This paper proposes a method for bearing prognostics that uses iteratively updated degradation regression models to capture the degradation trend in bearing's health indicator (HI), and the models are utilized to predict the degradation trajectory of HI and to estimate the RUL of bearings. The importance of determining the time to start prediction by elbow point is explained, which is often overlooked in prognostics. To improve the prognostic performance, an adaptive approach for elbow point detection is designed based on the gradient change of HIs, and a new smooth approach is applied to reduce spurious fluctuations in degradation trajectory. The effectiveness of the proposed method is validated on two publicly available data sets, i.e., IMS and FEMTO bearing prognostics data set, and its prognostic performance is compared with that of three state-of-the-art methods. The obtained results demonstrate that the proposed method can effectively detect elbow point and determine the time to start prediction, and can calibrate the degradation regression model dynamically according to the evolving degradation trend in the HI, which validates its superior prognostic performance. • A remaining useful life prediction method using the dynamic degradation regression models is proposed. • An adaptive approach for elbow point detection based gradient change of health indicator is proposed. • The proposed method is tested and validated on IMS and FEMTO bearing data sets, respectively. • The proposed algorithm shows superiority comparing to other art-of-the-state methods. [ABSTRACT FROM AUTHOR]

In recent years, the use of lithium-ion batteries has greatly expanded into products from many industrial sectors, e.g. cars, power tools or medical devices. An early prediction and robust understanding of battery faults could therefore greatly increase product quality in those fields. While current approaches for data-driven fault prediction provide good results on the exact processes they were trained on, they often lack the ability to flexibly adapt to changes, e.g. in operational or environmental parameters. Continual learning promises such flexibility, allowing for an automatic adaption of previously learnt knowledge to new tasks. Therefore, this article discusses different continual learning approaches from the group of regularization strategies, which are implemented, evaluated and compared based on a real battery wear dataset. Online elastic weight consolidation delivers the best results, but, as with all examined approaches, its performance appears to be strongly dependent on task characteristics and task sequence. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel repair priority rule for spare parts in a repair station with limited repair capacity to minimize total inventory cost per time unit. Inventory cost is composed of holding costs and backorder costs. The proposed rule uses Remaining Useful Life (RUL) predictions of functioning machines obtained from a Prognostics and Health Monitoring (PHM) system. An inventory system comprising a finite number of machines, one warehouse, and one single-server repair station is considered. Numerical experiments were conducted to compare the performance of the proposed model with the performance of three existing priority rules: a first-come, first-served (FCFS) rule, a static priority rule, and a dynamic priority rule. A testbed with 20 instances of the problem was considered. The results showed that the proposed PHM-based rule consistently reduces the inventory system cost. [ABSTRACT FROM AUTHOR]

The paper describes how the use of MIMOSA open source data model supports the development of a low-cost monitoring system that is capable to carry out automatic diagnosis and prognosis. MIMOSA follows the ISO 13374 definitions (condition monitoring) and links well with the ISO 17359 (diagnosis) and ISO 13381 (prognosis). The MIMOSA data model defines all the necessary ontology for the automatic monitoring system. As a use case the paper describes the installation of the MIMOSA data model in a Raspberry where MariaDB is used as the database engine. A low-cost MEMS accelerometer has been installed to a Raspberry thus enabling the collection of vibration data from rolling element bearings of a conveyor. The goal is to compare the results of low cost devices to a more expensive data acquisition system. The necessary signal analysis functions are programmed with VTT O&M Analytics, which provides the ability to conveniently perform signal analysis, offering a comprehensive set of algorithms that can detect a bearing failure and calculate the Remaining Useful Life (RUL). The amplitudes of the bearing fault frequencies can be reliably seen using envelope analysis, and the magnitude of the amplitudes can be used to determine whether the bearing is defective. In addition, the article discusses the system architecture, which enables data transfer from cloud to cloud conveniently and reliably, regardless of the number or location of the clouds. In conclusion, the paper summarises the key role of MIMOSA in building and using this kind of automatic monitoring systems. [ABSTRACT FROM AUTHOR]

The electric vehicle (EV) batteries should be repurposed after reaching End of Life (EoL), because it could be economically and environmentally beneficial. State of Health (SoH) estimation plays an essential role in repurposing these EoL Lithium (Li)-ion batteries. The aim of this paper is to review different SoH estimation technique to present a novel feature based classification. The review also investigates the issues and challenges in estimating SoH for Li-ion battery, with possible solutions. Furthermore, the study provides proposals for the development of SoH estimation methods for EV batteries in the context of the circular economy. [ABSTRACT FROM AUTHOR]

Modeling of AMT gearshift and clutch controls has attracted considerable attention in the past decade for optimizing the algorithms and simulation of control strategy and shift calibration, for reducing development time and costs involved in physical validation. Modeling of AMT system for simulation of gearbox and clutch performance is done using MATLAB/Simulink software. Time to market and investment for development can be greatly reduced through the use of a simulation-based design. A complete vehicle system simulation can allow multiple iterations without need for physical validation of the design concepts, prior to manufacturing test samples. This simulation methodology enables optimisation of interface components and sub-systems. Furthermore, design concepts can be tested using software model without the need of prototype parts, test vehicle, test track and test rig or test track. [ABSTRACT FROM AUTHOR]

Predictive maintenance is based primarily on Prognostics and Health Management (PHM). The prognosis is a process for learning about the health status of a system and estimating its residual time before failure. A good maintenance decision is the result of a better estimate of the latter. Recently, the emergence of IT systems in the industrial field and in particular connected objects and cloud computing have contributed strongly to the improvement of the prognosis process. In this paper, we propose a new prognosis approach based on the Cloud Computing model and the principle of multitenancy in order to present the Prognosis as a Service. This approach provides an effective prognosis solution at the request of a client while ensuring a better quality of service. The effectiveness of our solution depends on the criteria for the performance of the prognosis system based on accuracy, accuracy, mean squared error and a Quality of Service (Qos). [ABSTRACT FROM AUTHOR]

This paper presents a novel method for quantifying the effect of ambient, environmental and operating conditions on the progression of degradation in aircraft gas turbines based on the measured engine and environmental parameters. The proposed equivalent operating time (EOT) model considers the degradation modes of fouling, erosion, and blade-tip wear due to creep strain, and expresses the actual degradation rate over the engine clock time relative to a pre-defined reference condition. In this work, the effects of changing environmental and engine operating conditions on the EOT for the core engine booster compressor and the high-pressure turbine were assessed by performance simulation with an engine model. The application to a single and multiple flight scenarios showed that, compared to the actual engine clock time, the EOT provides a clear description of component degradation, prediction of remaining useful life, and sufficient margin for maintenance action to be planned and performed before functional failure. [ABSTRACT FROM AUTHOR]

Rolling element bearing is one of the critical components in rotating machines, and its running state determines machinery Remaining Useful Life (RUL). Estimating impending failure and predicting RUL of bearing is beneficial to schedule maintenance strategy and avoid abrupt shutdowns. This paper presents a novel method of RUL prediction of bearings, which can evaluate the degradation stage of bearings through dimensionless measurements and exploit the optimal RUL prediction through hybrid degradation tracing model in degradation stage. Two new measurements reflect the vibration intensity of bearings regarding normal vibration value. They can eliminate individual differences of bearings, improve sensitivity to the incipient defect of bearings, and reduce fluctuation. Moreover, they are helpful to detect the time to start prediction and set dimensionless failure threshold. SVM classifier is used to assess the degradation stage of bearing, which shows a high classification accuracy because of its excellent generalization ability and mathematical foundation. As input, the fitted measurements based on the generalized degradation model are used to train the SVM classifier. As output, five degradation stages are defined. However, actual measurements are used as inputs in the prediction process. According to the classification results, a hybrid degradation tracing model is utilized to exploit the optimal RUL prediction by tracking the degradation process of bearings. The proposed method is validated on the public IMS and PRONOSTIA bearing datasets, and its performance is compared with other methods on PRONOSTIA bearing datasets. The results show that the proposed approach is an effective way for RUL prediction of bearings within the prescribed error range. Given that the proposed measurements are dimensionless, this method can be applied under different operating conditions. • Define clear and smooth features. • A new degradation model is proposed , which combines simplicity and flexibility. • Prognostic work is converted into classification work and local prediction work. • A hybrid degradation tracking model is used to improve the accuracy of prediction. • The proposed prognostic approach can be applied under different operating conditions. [ABSTRACT FROM AUTHOR]

The remaining useful lifetime (RUL) is the time remaining until an asset no longer meets operational requirements. An accurate estimation of the RUL is central to prognostics and health management systems. However, the RUL of an asset is usually very difficult to estimate and to achieve in any industry. This is because the RUL strongly depends on manufacturing, the operating environment, and the observed condition monitoring. Here, we use physics-based approaches and data-driven approaches to predict the RUL of four essential components of a passenger car, namely engine, brake pads, springs, and tires. Our results show good agreement of both approaches. In addition, we develop a hybrid framework to generate a data set of RULs of a car fleet. This framework can be used to establish an optimal maintenance schedule for a car fleet, such as the fleet of a taxi company. [ABSTRACT FROM AUTHOR]

For decades, maintenance of facilities and equipment, as well as related activities (from fault detection to prognostics and health management), has a proven impact on efficiency of production systems and is thus still the subject of numerous developments (from corrective to proactive maintenance). These developments are supported by the increase in digital pervasiveness accompanying the Industry 4.0. concept, based in particular on the use of Cyber-Physical Systems. In addition, we are witnessing the growing interest of the political and academic world and public opinion with regard to the sustainable impact of human activity. For company decision-makers, triple bottom line accounting frameworks have been introduced at higher decision levels (strategic) based on economic, social, and environmental performance indicators. This triple preoccupation has not yet been integrated into studies on middle (tactical) and lower (operational) decision levels, and paradoxically, not into production facility health management either. In this paper, we propose the deployment of a framework helping decisions makers to be environmentally aware in the maintenance of cyber physical systems. This framework consists of three key elements: a new maintenance policy called Sustainable Condition-Based Maintenance (SCBM), which requires the assessment of the Remaining Sustainable Life (RSL) as a key indicator; an adaptation and extension of a generic prognostic business process initially proposed for traditional Conditions Based Maintenance (CBM); and an organization adapted to the prognosis of the environmental performance of systems, based on holonic structures. We present the implementation of such a framework on a real Cyber Physical Systems under development. [ABSTRACT FROM AUTHOR]

Centralized monitoring techniques have become more widely used as business demands and budgetary cuts for companies require streamlined operation and maintenance of a company's assets. These assets may be located at a single site where the monitoring is taking place, or they may be located all over a state, country or the world. Local data collection with consolidated servers allows a central maintenance center to pool big data for fleet-wide monitoring purposes. Advanced pattern recognition (APR) software solutions have been on the forefront of managing big data for dealing with a multitude of assets. APR techniques can provide evidence that a machine is not operating as expected, but the condition detected could indicate many possible underlying faults. The root cause may still be unknown. Causal network analysis has been widely used in providing differential diagnosis in the medical field when a set of symptoms are known. This method is based on Bayesian probability which can handle uncertainty in the data, both input and output, and has a good theoretical foundation. This paper discusses methods to utilize pattern anomalies as symptoms for a causal network to diagnose asset conditions and to mitigate failures for predictive maintenance programs. [ABSTRACT FROM AUTHOR]

This paper details an Integrated Prognostics Module for real-time condition monitoring of the dry clutch system and gearbox used on Automated Manual Transmission (AMT). The real-time sensor data of the clutch actuator and gear actuator piston positions are analysed for monitoring the condition of the clutch system and gearbox synchroniser. Original parameters of the new clutch and gearbox hardware are stored in the Electrically Erasable Programmable Read-only Memory (EEPROM) of the AMT controller and the real-time data is used by the integrated prognostics module for assessing the degradation/wear. Clutch slip during torque transmission and the synchronization time are continuously monitored for providing timely alert for re-calibration of the AMT system. Thus, Condition monitoring of an AMT system provides enhanced prognostic functionality which ensures consistent clutch performance, gear shift quality and timely warning for recalibration, repair and/or replacement of the critical wear and tear parts. Also, systematic analysis of the monitored data provides an accurate diagnosis of a developing fault. [ABSTRACT FROM AUTHOR]

Dissemination of cancer cells from the primary tumor and their spread to distant sites of the body is the leading cause of mortality in metastatic cancer patients. Metastatic cancer cells invade surrounding tissues and blood vessels by forming F-actin-rich protrusions known as invadopodia, which degrade the extracellular matrix and enable invasion of tumor cells through it. Invadopodia have now been observed in vivo , and recent evidence demonstrates direct molecular links between assembly of invadopodia and cancer metastasis in both mouse models and in human patients. While significant progress has been achieved in the last decade in understanding the molecular mechanisms and signaling pathways regulating invadopodia formation and function, the application of this knowledge to development of prognostic and therapeutic approaches for cancer metastasis has not been discussed before. Here, we provide a detailed overview of current prognostic markers and tests for cancer metastasis and discuss their advantages, disadvantages, and their predicted efficiency. Using bioinformatic patient database analysis, we demonstrate, for the first time, a significant correlation between invadopodia-associated genes to breast cancer metastasis, suggesting that invadopodia could be used as both a prognostic marker and as a therapeutic target for blocking cancer metastasis. We include here a novel network interaction map of invadopodia-associated proteins with currently available inhibitors, demonstrating a central role for the recently identified EGFR-Pyk2-Src-Arg-cortactin invadopodial pathway, to which re-purposing of existent inhibitors could be used to block breast cancer metastasis. We then present an updated overview of current cancer-related clinical trials, demonstrating the negligible number of trials focusing on cancer metastasis. We also discuss the difficulties and complexity of performing cancer metastasis clinical trials, and the possible development of anti-metastasis drug resistance when using a prolonged preventive treatment with invadopodia inhibitors. This review presents a new perspective on invadopodia-mediated tumor invasiveness and may lead to the development of novel prognostic and therapeutic approaches for cancer metastasis. [ABSTRACT FROM AUTHOR]

The rolling element bearing is the leading cause of failures in rotating machinery; on that account, the accurate prediction of its remaining useful life (RUL) using sensor data is an important challenge to improve the reliability and decrease the maintenance costs. Classical data-driven approaches rely on manually extracted features from raw sensor data followed by an estimation of a health indicator, the degradation states and the prediction of RUL using a failure threshold. Based on the recent success of deep neural networks in various artificial intelligence domains, we propose an end-to-end deep framework for RUL estimation based on convolutional and long-short-term memory (LSTM) recurrent units. First the neural network extracts the local features directly from sensor data using the convolutional layer, then an LSTM layer is introduced to capture the degradation process, finally the RUL is estimated using the LSTM outputs and the prediction time value. Experiments are conducted on the ball bearing data provided by FEMTO-ST Institute. The results demonstrate the efficiency of our approach. [ABSTRACT FROM AUTHOR]

An essential process in prognostics and health management (PHM) is remaining useful life (RUL) prediction. The traditional Recurrent Neural Networks (RNNs) and their variants are not very efficient at solving the regression problems of RUL prediction. Given this problem, an attention-based Gate Recurrent Unit (ABGRU) for RUL prediction is proposed in this paper. Firstly, the dataset is preprocessed, and the RUL labels are modeled using the piecewise linear degradation method. Then, a GRU network based on an encoder–decoder framework with an attention mechanism is proposed. The network can assign weights according to the importance of feature information and effectively use the feature information to predict RUL. The validity of the proposed framework is verified in the NASA C-MAPSS benchmark dataset. The results show that the presented method outperforms the existing state-of-the-art approaches and provides a new solution for RUL Prediction. • Propose a novel method for RUL predictions based on an attention-based GRU. • Construct an Encoder–Decoder model that integrates GRU. • The attention assigns weights and uses the feature information effectively. • Comparisons with state-of-the-art verify the superiority of the proposed method. [ABSTRACT FROM AUTHOR]

Autocorrelation is a special case of cross-correlation wherein a signal is correlated with a time-lagged version of itself - the resulting signal comprises only the periodic information from the original signal whilst reducing noise. This property of autocorrelation can be particularly useful in analysing bearing faults since vibration data from a bearing, with local faults/defects, consists of cyclostationary acceleration signals usually contaminated with noise from sensors and other environmental factors. This study introduces a method which provides early failure warning in rolling element bearings by applying an autocorrelation operation to vibration data. The Sequential Probability Ratio Test (SPRT) is used to detect anomalies indicative of incipient failure. The results from the autocorrelation analysis are compared with results from a simple moving-RMS analysis of the acceleration data. The developed method is shown to provide an earlier warning of failure than the RMS-based method. This method can detect early stages of degradation in bearings - which in turn allows earlier scheduling of maintenance and the avoidance of system failures. [ABSTRACT FROM AUTHOR]