Failure Detection Research Articles

Nanoparticle Counting for PTI: The Dirty Tail Paradigm — A Pragmatic Proposal to Strongly Reduce Urban PN Pollution from Combustion Engine Fleets

Using solid particle number (PN) measurements in the European Periodic Technical Inspection (PTI) of diesel engines equipped with particulate filters was proposed by VERT in 2016 during the Dieselgate Hearing of the Federal Republic of Germany. An international working group developed the standards and instruments for this method over 3 years under the leadership of TNO and VERT, which were next implemented in four countries, Belgium, the Netherlands, Germany, and Switzerland, starting in 2022. PN measurement is now state of the art, enabling rapid and reliable detection of possible failures in particulate filters and the need for their immediate restoration. This paper expands on that successful experience, recommending that PN counting be used for control of PN emissions from all vehicles during PTI. It reviews results from a number of earlier studies on “high emitters” and shows some new data sets for gasoline engines. Five large vehicle fleets, diesel and gasoline, heavy-duty engines (HDE), light-duty vehicles (LDV), and non-road mobile machinery (NRMM), with and without emission aftertreatment were analyzed. It was observed that, while most vehicles in working fleets are clean (i.e., meet or often are far are below their corresponding emission limits), every fleet, however, contains some high emitters, about 4–8% of the fleet hereby termed “dirty tail” — diesel as well as gasoline engines. This small fraction dominates the PN emission of the entire fleet and may increase the overall PN emission of its corresponding fleet by more than tenfold over the level of the compliant vehicles! Experience indicates that PN emission may be a strong indicator of many different deteriorations in a combustion engine and thus can be used as a highly sensitive diagnostic signal to detect various engine or emission faults quickly and reliably. This is a new understanding of emission control of vehicle fleets: not by regulations for new vehicles only which apply for all vehicles but by selecting the high emitters and consequently repair or replace these relatively few vehicles to the extent desired in terms of emissions policy. Most countries have already implemented strong periodic technical inspection systems. We suggest to expand such tests by additionally measuring the particle number concentration in the exhaust gas of all vehicles for just 1 min, thereby detecting the high emitters. With consistent annual monitoring, this procedure will reduce urban particle pollution from combustion engines to one-tenth or lower, a significant contribution to reducing local health risks.

System Integration Failures and Their Impact on Patient Safety in Critical Care Settings

Robotic surgery systems offer precision and minimally invasive procedures, enhancing surgical outcomes in critical care settings. However, these systems' complexity, with integrated hardware and software, can lead to integration failures, compromising patient safety. This paper examines the system integration challenges in robotic surgery, explores their effects on patient safety, and suggests solutions to overcome them. Rigorous testing strategies during development and continuous monitoring of system performance are crucial in detecting failures early and ensuring reliable system operation. Keywords: Robotic Surgery Systems, System Integration, Patient Safety, Software Failures, Hardware Failures, Critical Care, Integration Testing, Failover Mechanisms, Robotic Arms, Sensor Calibration, Real-Time Data Processing, Medical Robotics, Surgical Precision, Failure Detection, Stress Testing, Fault-Tolerant Design, Error Handling, Modular Design, Quality Assurance, ISO 13485, Robotic Surgery Failures, Calibration Errors, Mako System, Da Vinci Surgical System, CyberKnife System, Automated Testing, Robotic Surgery Technology.

Detection of Pipe Ruptures in Shipboard Firefighting Systems Using Machine Learning and Deep Learning Techniques

In this paper, the application of machine learning and deep learning algorithms for fault and failure detection in maritime systems is examined, specifically focusing on the detection of pipe ruptures in a ship’s saltwater firefighting (FiFi) system using pressure sensor data. Neural network models were developed to distinguish between normal operational states and anomalies, as well as to accurately locate pipe faults within the ship. Data were collected using real-world tests with FiFi system sensors, capturing both normal operations and simulated pipe ruptures, and were meticulously labeled to facilitate neural network training. Two neural network models were introduced: one for classifying system states (normal or anomalous) based on time-series pressure data, and another for identifying the location of anomalies related to pipe ruptures. Experimental results demonstrated the efficacy of these models in detecting and localizing pipe faults, with performance evaluated using mean squared error (MSE) across different network configurations. The successful implementation of these machine learning and deep learning algorithms highlights their potential for enhancing maritime safety and operational efficiency.

Pregnancy-Induced Cardiomyopathy: What Case Managers Need to Know.

A new form of stethoscope with artificial intelligence (AI) capabilities may make the difference between early detection of pregnancy-induced cardiomyopathy or end stage postpartum heart failure. The AI stethoscope is a tool that may make that difference.

Rank-deficient square-root information filter for unified GNSS precise point positioning model

Abstract Numerous GNSS Precise Point Positioning (PPP) models have been developed through reparameterizing the rank-deficient original model, which performs well under standard conditions. However, predefined reparameterization introduces challenges, such as incomplete satellite observation utilization and the complexity of modeling original parameters, whose solutions are often model-specific and lack unification. To address these issues, we propose the Rank-Deficient Square-Root Information Filter (RD-SRIF) for processing rank-deficient observational problems. This approach enables a unified PPP model based on the original model constructed at runtime, facilitating universal solutions to challenges posed by predefined reparameterization. Theoretical analysis and experimental results demonstrate that the unified model matches the performance of classic models for normal observational conditions while offering several advantages. It effectively incorporates incomplete satellite observations to enhance ionosphere modeling, ensures rigorous modeling of original parameters for improved failure detection in dynamic models and single-frequency PPP performance. Moreover, it surpasses classic models in addressing complex challenges, such as smartphone-based PPP. The unified PPP model makes it easier to solve the modeling problems of PPP, while the RD-SRIF may also be beneficial for other GNSS or non-GNSS algorithms.

Ultrahigh Selectivity H2S Gas Sensor Based CsPbBr3 Perovskites via Pb-S Bonding Interaction.

High selectivity and sensitivity sensing of H2S gas play a decisive role in the early detection of sulfide solid-state battery failure. Herein, we construct the CsPbBr3 perovskite-based sensor that exhibits outstanding gas-sensing performance to H2S at room temperature, including high selectivity, fast response/recovery speed (73.5/275.6 s), humidity insensitivity, and long-term stability (6 weeks without degradation). The excellent selectivity of CsPbBr3 for H2S results from the formation of lead-sulfur (Pb-S) bonds exclusive to other molecules and upshifted the Fermi level at the perovskite interface by density functional theory (DFT) calculations. The in-situ experiments reveal the interaction of Pb-S bonding and the transformation of H2S molecules on the perovskite surface. The simple synthesis method and unique sensing mechanism based on perovskite semiconductors help build the room-temperature metal halide perovskite (MHP)-based gas sensors with high selectivity and fast response/recovery speed for solid-state battery failure detection in the future.

Tracking the Unseen and Unaware: Deciphering Controllers’ Detection Failures to Warnings Through Eye-Tracking Metrics

The integration of digital towers in air traffic control (ATC) intensifies visual complexity of controllers, increasing the risk of detection failure (DF) to warnings and compromising airspace safety. The inherent variability in human situational awareness and behaviors further complicates the differentiation and recognition of various DFs. This study deciphers DF by categorizing it into types based on Endsley’s situation awareness theory, identifying specific causes and key indicators. A four-phase framework—DF classification, DF induction experiment, gaze dynamics analytics, and DF-type recognition—was applied to gaze data from 26 subjects. Results revealed distinct gaze patterns for non-perception, unaware perception, and aware perception of warnings, with continuous warnings weakening operators’ awareness but enhancing foresight of warning implications. A random forest model achieved 80% precision in DF-type recognition, offering empirical support for real-time DF recognition and targeted interventions to improve visual warning detection and human-computer interaction in aviation safety.

Machine learning boosts wind turbine efficiency with smart failure detection and strategic placement

The research study objective seeks to improve the efficiency of wind turbines using state-of-the-art techniques in the domain of ML, making wind energy the key player in fashioning a favorable future. Wind Turbine Health Monitoring (WTHM) is typically achieved through either vibration analysis or by using Supervisory Control and Data Acquisition (SCADA) data of wind turbines, wherein conventional fault pattern identification is a time-consuming, guesswork process. This work proposed an intelligent automated approach to early fault detection through the implementation of the HARO (Huber Adam Regression Optimizer) model, which combines Transformer networks with Lasso Regression and the Adam optimizer. HARO is the proposed model to traditional models, including the Huber and Automatic Relevance Determination (ARD) Regressors, since Transformers are capable of learning the patterns of the sensors. The overall analysis of the results obtained illustrated that the Housing Asset Repair Optimization tool had reduced downtime while enhancing, at the same time, the accuracy of the prediction of future faults to enable the right-time planning for maintenance activities. This aspect enhances the learning process, minimizing human input and hence slightly lessens the efficiency of the turbines in HARO. The study further calls for collective research practice amongst researchers, practitioners and policymakers to address emerging issues in wind power maintenance to avoid duplication and continuously keep improving on the strategies employed towards the maintenance of wind energy. This paper also shows that ML has the possibility of improving wind turbine dependability and establishing wind energy as an essential component of renewable energy systems.

Rationale and Design of the HERZCHECK trial: Detection of Early Heart Failure Using Telemedicine and CMR in Structurally Weak Regions (NCT05122793).

Heart failure (HF) is an imminent global health problem. Yet established screening algorithms for asymptomatic pre-HF, allowing for early and effective preventive interventions, are largely lacking. The HERZCHECK trial, conducted in structurally underserved rural regions of North-Eastern Germany, aims to close this gap by evaluating the feasibility, diagnostic efficacy, and cost-effectiveness of a fully mobile, telemedically-supervised screening approach, combining cardiac magnetic resonance imaging (CMR) and laboratory testing as central elements. The HERZCHECK trial is a prospective, randomized controlled trial employing a PROBE (prospective randomized open, blinded endpoint) design. The study targets asymptomatic adults aged 40-69 years without a history of HF, but with at least one of the following cardiovascular risk factors: hypertension, hypercholesterolemia, obesity, smoking/tobacco consumption, chronic diabetes mellitus, or chronic kidney disease. Participants undergo a comprehensive screening examination including a questionnaire-based medical history, laboratory testing, and CMR at baseline. Based on CMR-derived global longitudinal strain (GLS), participants are classified as stratum A (GLS < -15%), B (GLS ≥ -15% to < -11%), or C (GLS ≥ -11%), with strata B and C being defined as asymptomatic pre-HF. 10% of participants in stratum A and all of stratum B and C are subsequently randomized into two groups, receiving either conventional or innovative medical reports, the latter including information on GLS, guideline-based recommendations, and access to a life-style intervention app for cardiovascular prevention. Additionally, treating physicians of participants in the innovative group are granted access to an expert center for telemedical enquires. Follow-up assessments are performed over 12 months to evaluate changes in GLS, as well as adverse cardiac events and quality of life. HERZCHECK aims to provide a blueprint for a comprehensive, contemporary screening approach tailored to the needs of the targeted structurally underserved population. By implementing this approach in a representative at-risk cohort, HERZCHECK will provide important new information about (a) the prevalence of asymptomatic pre-HF in at-risk patients and (b) the feasibility, added diagnostic value and health economic aspects of CMR exams as part of future screening mechanisms for HF in clinical routine care. (NCT05122793).

Localization Failure Detection by Scan Matching in Forest Environment for Automatic Driving of Forestry Work Vehicle

Localization Failure Detection by Scan Matching in Forest Environment for Automatic Driving of Forestry Work Vehicle

Expertise-Enhanced Machine Learning for Failure Detection on Field-Deployed Optical Modules

Expertise-Enhanced Machine Learning for Failure Detection on Field-Deployed Optical Modules

Server Failure Detection for Robustness Analysis in Automated Manufacturing Systems with Arbitrary Resource Failures

Server Failure Detection for Robustness Analysis in Automated Manufacturing Systems with Arbitrary Resource Failures

A Review of Vibration-Based Techniques for the Condition Assessment and Failure Detection of Transformers

A Review of Vibration-Based Techniques for the Condition Assessment and Failure Detection of Transformers

A Survey of Link Failure Detection and Recovery in Software-Defined Networks

A Survey of Link Failure Detection and Recovery in Software-Defined Networks

Electric parameters analysis for the detection of possible failures in the insulation of electric motor windings

Knowledge of electric motors is of utmost importance in the industry. Knowing the anticipated data on the good or bad functioning of the equipment we work with allows us to make better decisions for their optimal development. This article presents a proposal for analyzing electrical data in induction motors, allowing a study of their behavior to be carried out to detect a possible failure in the windings due to a short circuit, defect or degradation of the insulation. With the help of a simulator, it is easier to develop this analysis. The Simulink software provided by the Matlab software shows us graphic results that we can view to predict and take preventive measures for the equipment

FAULT-TOLERANT ADAPTIVE CONTROL OF A WALKING HEXAPOD WITH FAILURE OF ONE LEG

The article is devoted to the improvement of the control system of a walking mobile robot with six legs (hexapod) in order to ensure its stable movement in case of damage or failure of one limb. A tripod gait is considered as the basic movement algorithm. The failure of one of the joints is considered as a failure of the limb. To ensure movement in the event of failure of one limb, a tripod walking algorithm has been developed, which ensures that each of the defect-free limbs remains in the stage of stable support during two phases of movement in a row. The evaluation of the possibility of fault-tolerant gait of the hexapod according to the developed algorithm was performed on the basis of support triangles and a quadrangle between the limbs that are in the support phase. The structural and functional synthesis of the system of fault-tolerant adaptive control of the hexapod, which consists of the following modules and subsystems, was performed: module of the dynamic model of the robot; basic gait algorithm module; subsystem of executive elements; diagnosis and decision-making subsystem; a subsystem of alternative gait algorithms. The structural and functional scheme of the control channel was developed and substantiated for the implementation of the algorithm for diagnosing the joint of one limb, making a decision about its condition and switching to the continuation of the basic gait algorithm, if the condition of the joint is assessed as defect-free. The scheme of the control channel for switching to the execution of an alternative gait algorithm, if the condition of the joint is assessed as defective, has been developed and substantiated. The proposed structural and functional solutions are generalized for the case of failure of other joints of the considered limb and other limbs of the hexapod. It is shown that based on the detection and localization of joint failures of the hexapod limbs, the reconfiguration of the gait algorithm and the control system takes place, and in this way a fault-tolerant adaptive control of the movement of the hexapod is realized. The implementation of the proposed alternative tripod gait algorithms and control channels in the fault-tolerant adaptive control system will ensure stable movement of the hexapod in case of failure of one of the limbs.

Hybrid Edge–Cloud Models for Bearing Failure Detection in a Fleet of Machines

Real-time condition monitoring of machinery is increasingly being adopted to minimize costs and enhance operational efficiency. By leveraging large-scale data acquisition and intelligent algorithms, failures can be detected and predicted, thereby reducing machine downtime. In this paper, we present a novel hybrid edge–cloud system for detecting rotational bearing failures using accelerometer data. We evaluate both supervised and unsupervised neural network approaches, highlighting their respective strengths and limitations. Supervised models demonstrate high accuracy but require labeled datasets representative of the failures of interesting data that are challenging to acquire due to the rarity of anomalies. Conversely, unsupervised models rely on data from normal operational conditions, which is more readily available. However, these models classify all deviations from normalcy as anomalies, including those unrelated to failure, leading to costly false positives. To address these challenges, we propose a distributed system that integrates supervised and unsupervised learning. A compact unsupervised model is deployed on edge devices near the machines to compress sensor data, which are then transmitted to a centralized cloud-based system. Over time, these data are automatically labeled and used to train a supervised model, improving the accuracy of failure predictions. Our approach enables efficient, scalable failure detection across a fleet of machines while balancing the trade-offs between supervised and unsupervised learning.

Early detection of heart failure using in-patient longitudinal electronic health records.

Heart Failure (HF) is common, with worldwide prevalence of 1%-3% and a lifetime risk of 20% for individuals 40 years or older. Despite its considerable health economic burden, techniques for early detection of HF in the general population are sparse. In this work we tested the hypothesis that a simple Transformer neural network, trained on comprehensive collection of secondary care data across the general population, can be used to prospectively (three-year predictive window) identify patients at an increased risk of first hospitalisation due to HF (HHF). The model was trained using routinely-collected, secondary care health data, including patient demographics, A&E attendances, hospitalisations, outpatient data, medications, blood tests, and vital sign measurements obtained across five years of longitudinal electronic health records (EHRs). The training cohort consisted of n = 183,894 individuals (n = 161,658 age/sex-matched controls and n = 22,236 of first hospitalisation due to HF after a three-year predictive window). Model performance was validated in an independent testing set of n = 8,977 patients (n = 945 HHF patients). Testing set probabilities were well-calibrated and achieved good discriminatory power with Area Under Receiver Operating Characteristic Curve (AUROC]) of 0.86, sensitivity of 36.4% (95% CI: 33.33%-39.56%), specificity of 98.26% (95% CI: 97.95%-98.53%), and PPV of 69.88% (95% CI: 65.86%-73.62%). At Probability of HHF ≥ 90% the model achieved 100% PPV (95% CI: 96.73%-100%) and sensitivity of 11.7% (95% CI: 9.72%-13.91%). Performance was not affected by patient sex or socioeconomic deprivation deciles. Performance was significantly better in Asian, Black, and Mixed ethnicities (AUROC 0.932-0.945) and in the 79-86 age group (AUROC 0.889). We present the first evidence that routinely collected secondary care health record data can be used in the general population to stratify patients at risk of first HHF.

Structural Health Monitoring of Nuclear Site Facilities Using Optimal Sensor Placement for Damage Detection and Prediction of Failure

Structural Health Monitoring of Nuclear Site Facilities Using Optimal Sensor Placement for Damage Detection and Prediction of Failure

Residual based tilt tri‐rotor UAV actuator fault detection using TSK fuzzy model

AbstractUndetected actuator faults on tilt tri‐rotor UAVs can lead to system failures and uncontrolled crashes. Multiple flight modes result in complex models with strong nonlinearity, making fault detection of their actuators a very challenging task. To address this issue, this article proposes a fault detection method based on residual generated by using TSK fuzzy model. Initially, the flight modes of the tilt tri‐rotor UAV are modeled as the TSK fuzzy model. Following this, the residual generator is employed for rapid detection of actuator failures. To enhance detection accuracy, the kernel principal component analysis (KPCA) algorithm is used for a secondary confirmation. The proposed algorithm was validated using both a simulation platform and real flight data. The results demonstrate that the fault detection algorithm achieves high accuracy and real‐time performance, with a computing time of approximately 41 ms in real controller hardware, thus meeting the requirements of practical applications.