Frequent False Alarms Research Articles

A Hybrid Machine Learning Approach for Intrusion Detection and Mitigation on IoT Smart Healthcare

Strong cybersecurity solutions are becoming more and more important as Internet of Things (IoT) technology integration in healthcare settings develops. This study offers a method for feature extraction, selection, and attack classification by fusing the discriminative capacity of feedforward neural networks (FNNs) with the adaptability of fuzzy logic systems. In delicate healthcare database of IoT wearable devices, to reduce false alarm and guaranteeing intrusion detection dependability are the main priorities. The suggested method uses a feature extraction, selection technique, training and testing based on FNN, which allows the model to adjust to the dynamic and varied character of medical data. During the assessment stage, a dataset including a range of healthcare IoT scenarios, including different kinds of attacks, is used to train and evaluate the model, the ToN_IoT dataset was used. Fuzzy logic improves the system's resilience in identifying pertinent features by managing uncertainties and imprecise input. Fuzzy logic is one of the best technique for handling uncertainty, its linguistic representation and rule reasoning helps in better identification and classification. The findings indicate a noteworthy decrease in the frequency of false alarms when juxtaposed with conventional intrusion detection systems. Results obtained from the model are 99.2, 98.8, 99.5, 99.1 & 0.008 for accuracy, precision, recall, F1-Score and False alarm respectively. Promising outcomes in protecting IoT healthcare environments are demonstrated by the suggested system, opening the door to better patient data privacy and system resilience against cyberattacks.

Optimal design of time-between-event control charts with parameter estimation

The tr chart is a Shewhart-type control chart used to monitor the time between events, especially in high-quality processes. It has been shown to be more efficient than classical attribute control charts based on count data. In practical applications, the in-control process parameters are often unknown and need to be estimated from a Phase I reference sample. When the available Phase I data are small and the chart parameters have to be estimated, a popular approach is to adjust the control chart limits from a conditional perspective to avoid frequent false alarms using the exceedance probability criterion. However, this approach ignores the practitioner-to-practitioner (p-to-p) variation caused by the random Phase I reference samples, which results in getting different control limits and chart performance for each practitioner Large p-to-p variation makes practitioners to have a limited confidence on using their own estimated charts. Hence, in this article, we propose to optimize the tr chart via an exact method so that it has a minimum p-to-p variation. Comparisons between the optimal and conventionally adjusted charts are made in both the in- and out-of-control cases. The most important results are that the optimal chart has a far smaller p-to-p variation and its unconditional average run length values are closer to the desired ones compared to the conventional approach regardless of the in- or out-of-control cases. Finally, two real examples are presented to illustrate the implementation of the proposed chart.

Design of a mining carbon monoxide sensor and analysis of multi-gas cross-interference performance

Abstract A new type of carbon monoxide sensor is designed to address the issue of cross interference of nitrogen oxide gas in the exhaust emissions of underground diesel engine rubber-tired vehicles with electrochemical carbon monoxide sensors, which leads to frequent false alarm accidents. The hardware circuit design of the DC-DC voltage reduction power supply circuit, display circuit, component signal processing circuit, etc. is detailed, At the same time, the sensitive components used in the sensor adopt a special gas filtration membrane design. Six types of gases, including hydrogen sulfide, nitric oxide, nitrogen dioxide, hydrogen, ethylene, and acetylene, were sequentially introduced in the laboratory for experimental analysis of multi-gas cross-interference performance. The experimental results have shown that the new carbon monoxide sensor can filter out nitrogen oxide gas, thereby solving the impact of underground rubber tire vehicle exhaust on the accuracy of carbon monoxide gas detection. It has broad prospects for promotion and application in coal mines underground.

Farm-specific estimates of forage variability result in larger optimal control limits for forage quality monitoring

Variation in forage composition decreases the accuracy of diets delivered to dairy cows. However, variability of forages can be managed using a renewal reward model (RRM) and genetic algorithm (GA) to optimize sampling and monitoring practices for farm conditions. Specifically, use of quality-control-charts to monitor forage composition can identify changes in composition for which adjustment in the formulated diet will result in a better match of the nutrients delivered to cows. The objectives of this study were 1) assess the use of a clustering algorithm to estimate the mean time the process is stable or in-control (d) (TStable) and the magnitude of the change in forage composition between stable periods (ΔForage) for corn silage and alfalfa-grass silage which are input parameters for the RRM; 2) compare optimized farm-specific sampling practices (number of samples (n), sampling interval (TSample) and control limits (ΔLimit) using previously proposed defaults and our estimates for the TStable and ΔForage input parameters; and 3) conduct a simulation study to compare the number of recommended diet changes costs of quality control under the proposed sampling and monitoring protocols. We estimated the TStable and ΔForage parameters for corn silage NDF and starch and alfalfa-grass silage NDF and CP using a k-means clustering approach applied to forage samples collected from 8 farms, 3x/week during a 16-week period. We compared 4 sampling and monitoring protocols that resulted from the 2 methods for estimating TStable and ΔForage (default values and our proposed method) and either optimizing only the control limit (Optim1) or optimizing the control limits, the number of samples, and the number of days between sampling (Optim2). We simulated the outcomes of implementing the optimized monitoring protocols using a quality control chart for corn silage and alfalfa-grass silage of each farm. Estimates of T^Stable and Δ^Forage from the k-means clustering analysis were, respectively, shorter and larger than previously proposed default values. In the simulated quality control monitoring, larger Δ^Forage estimates increased the optimized ΔLimit resulting in fewer detected shifts in composition of forages and a lower frequency of false alarms and a lower quality control cost ($/d). Recommended diet reformulation intervals from the simulated quality control analysis were specific for the type of forage and farm management practices. The median of the diet reformulation intervals for all farms using our optimal protocols was 14 d (Q1 = 8, Q3 = 26) for corn silage and 16 d (Q1 = 8, Q3 = 26) for alfalfa-grass silage.

A multi-head self-attention autoencoder network for fault detection of wind turbine gearboxes under random loads*

Wind turbine gearboxes work under random load for extended periods of time, and the fault detection indicator constructed by the existing deep learning models fluctuate constantly due to the load, which is easy to cause frequent false alarms. Therefore, a multihead self-attention autoencoder network is proposed and combined with a dynamic alarm threshold to detect faults in a wind turbine gearbox subjected to random loads. The multiheaded attention mechanism layer enhances the feature-extraction capability of the proposed network by extracting global and local features from input data. Furthermore, to suppress the influence of the random load, a dynamic warning threshold was designed based on the reconstruction error between the inputs and outputs of the proposed network. Finally, the effectiveness of the proposed method was verified using the vibration data of wind turbine gearboxes from an actual wind farm.

High incidence of inappropriate alarms due to artifact sensing and misclassification of episodes in patients with wearable cardioverter-defibrillators

Abstract Background The wearable cardioverter-defibrillator (WCD) has become a useful tool used for temporary protection from sudden cardiac death. However, since the WCD uses surface electrodes to detect arrhythmias, it is prone to inappropriate detection. Although shock conversion rates for the WCD are high for detected events, its efficacy in clinical practice tends to be degraded by patient noncompliance. Reasons include wear discomfort and frequent false alarms, that may interrupt sleep and generate anxiety. Data on the incidence of false alarms emitted by the WCD and their predictors are rare. Purpose The aim of our study was to assess both artifact and misclassification burden and wear compliance in patients with a WCD. Methods and Results We conducted a single-centre retrospective observational study analyzing patients with a WCD prescribed at our institution. In total, in 134 patients (mean age 51.7 ± 13.8 ys, 79.1% male) provided with a WCD, arrhythmia recordings were analyzed and categorized as either non-sustained ventricular tachycardia, sustained ventricular tachycardia / fibrillation, and artifact sensing or misclassified episodes. Indication for WCD prescription was both primary and secondary prophylactic. All patients received optimal medical therapy. Baseline evaluation in all patients included transthoracic echocardiography, 12-lead electrocardiogram, and baseline laboratory values. A total of 3019 false WCD alarms were documented in 134 patients (average number of false alarms 22.5 ± 130.4 episodes per patient) over a mean WCD wearing time of 71.5 ± 70.9 days (daily wearing time 20.2 ± 5.9 hs). In total, in 78 patients (58.2%), either artifact sensing (41.8%), misclassified episodes (3.7%) or both (9.7%) occurred. Misclassified episodes included sinus tachycardias, atrial flutter, atrial fibrillation, ventricular extrasystoles, and intermittent bundle branch block. At multivariate analysis, WCD wearing time (HR 1.02; 95% CI 1.01-1.02; P < 0.001) and loop diuretics (HR 0.16; 95% CI 0.06-0.44; P < 0.001) were identified as independent predictors of artifact episode occurrence. In terms of the frequency of artifact episodes, loop diuretics (HR -0.11; 95% CI interval -0.21-0.0001; P = 0.049), angiotensin receptor-neprilysin inhibitors (ARNIs) (HR -0.11; 95% CI -0.22-0.01; P = 0.03), and the R-amplitude (HR -0.17; 95% CI -0.27-0.07; P = 0.01) of the WCD baseline electrocardiogram (ECG) were independent predictors. In addition, WCD wearing time (HR 1.00; 95% CI 1.00-1.01; P = 0.04), atrial fibrillation (HR 4.03; 95% CI 1.15-14.11; P < 0.001), and ARNIs (HR 3.17; 95% CI 1.05-9.52; P < 0.001) were significantly associated with the occurrence of misdetected / misclassified episodes. Conclusions In conclusion, In WCD patients with a ZOLL LifeVest system, false alarms emitted by the device were frequent and most common caused by artefacts.

Combinatorial reasoning-based abnormal sensor recognition method for subsea production control system

The subsea production system is a vital equipment for offshore oil and gas production. The control system is one of the most important parts of it. Collecting and processing the signals of subsea sensors is the only way to judge whether the subsea production control system is normal. However, subsea sensors degrade rapidly due to harsh working environments and long service time. This leads to frequent false alarm incidents. A combinatorial reasoning-based abnormal sensor recognition method for subsea production control system is proposed. A combinatorial algorithm is proposed to group sensors. The long short-term memory network (LSTM) is used to establish a single inference model. A counting-based judging method is proposed to identify abnormal sensors. Field data from an offshore platform in the South China Sea is used to demonstrate the effect of the proposed method. The results show that the proposed method can identify the abnormal sensors effectively.

An adaptive metaheuristic optimization approach for Tennessee Eastman process for an industrial fault tolerant control system.

The Tennessee Eastman Process (TEP) is widely recognized as a standard reference for assessing the effectiveness of fault detection and false alarm tracking methods in intricate industrial operations. This paper presents a novel methodology that employs the Adaptive Crow Search Algorithm (ACSA) to improve fault identification capabilities and mitigate the occurrence of false alarms in the TEP. The ACSA is an optimization approach that draws inspiration from the observed behavior of crows in their natural environment. This algorithm possesses the capability to adapt its search behavior in response to the changing dynamics of the optimization process. The primary objective of our research is to devise a monitoring strategy that is adaptable in nature, with the aim of efficiently identifying faults within the TEP while simultaneously minimizing the occurrence of false alarms. The ACSA is applied in order to enhance the optimization of monitoring variables, alarm thresholds, and decision criteria selection and configuration. When compared to traditional static approaches, the ACSA-based monitoring strategy is better at finding faults and reducing false alarms because it adapts well to changes in process dynamics and disturbances. In order to assess the efficacy of our suggested methodology, we have conducted comprehensive simulations on the TEP dataset. The findings suggest that the monitoring strategy based on ACSA demonstrates superior fault identification rates while concurrently mitigating the frequency of false alarms. In addition, the flexibility of ACSA allows it to efficiently manage process variations, disturbances, and uncertainties, thereby enhancing its robustness and reliability in practical scenarios. To validate the effectiveness of our proposed approach, extensive simulations were conducted on the TEP dataset. The results indicate that the ACSA-based monitoring strategy achieves higher fault detection rates while simultaneously reducing the occurrence of false alarms. Moreover, the adaptability of ACSA enables it to effectively handle process variations, disturbances, and uncertainties, making it robust and reliable for real-world applications. The contributions of this research extend beyond the TEP, as the adaptive monitoring strategy utilizing ACSA can be applied to other complex industrial processes. The findings of this study provide valuable insights into the development of advanced fault detection and false alarm monitoring techniques, offering significant benefits in terms of process safety, reliability, and operational efficiency.

Gearbox Condition Monitoring and Diagnosis of Unlabeled Vibration Signals Using a Supervised Learning Classifier

Data-based equipment fault detection and diagnosis is an important research area in the smart factory era, which began with the Fourth Industrial Revolution. Steel manufacturing is a typical processing industry, and efficient equipment operation can improve product quality and cost. Steel production systems require precise control of the equipment, which is a complex process. A gearbox transmits power between shafts and is an essential piece of mechanical equipment. A gearbox malfunction can cause serious problems not only in production, quality, and delivery but in safety. Many researchers are developing methods for monitoring gearbox condition and for diagnosing failures in order to resolve problems. In most data-driven methods, the analysis data set is derived from a distribution of identical data with failure mode labels. Industrial sites, however, often collect data without information on the failure type or failure status due to varying operating conditions and periodic repair. Therefore, the data sets not only include frequent false alarms, but they cannot explain the causes of the alarms. In this paper, a framework called the Reduced Lagrange Method (R-LM) periodically assigns pseudolabels to vibration signals collected without labels and creates an input data set. In order to monitor the status of equipment and to diagnose failures, the input data set is fed into a supervised learning classifier. To verify the proposed method, we build a test rig using motors and gearboxes that are used on production sites in order to artificially simulate defects in the gears and to operate them to collect vibration data. Data features are extracted from the frequency domain and time domain, and pseudolabeling is applied. There were fewer false alarms when applying R-LM, and it was possible to explain which features were responsible for equipment status changes, which improved field applicability. It was possible to detect changes in equipment conditions before a catastrophic failure, thus providing meaningful alarm and warning information, as well as further promising research topics.

Residual Convolutional Attention Model With Transfer Learning for Detecting Multianomalous Features in Structural Vibration Data

In response to the data anomalies and frequent false alarms caused by harsh environments in long‐term structural health monitoring (SHM), this study has reframed the detection of abnormal vibration data as a time series classification problem. This approach identifies multiple anomalous features, thereby reducing manual detection costs. The novel developed Convolutional Neural Network with Squeeze‐and‐Excitation and Multi‐Head Self‐Attention (CNN–SE–MHSA) employs a deep residual network structure with channel and spatial attention mechanisms, effectively handling the global long‐term dependencies required for anomaly feature learning. It better understands and utilizes feature information across different levels and dimensions, enhancing classification accuracy in complex anomaly situations. Through t‐SNE dimensionality reduction visualization and interpretability analysis, it is demonstrated that the model excels in identifying critical features. Furthermore, by generating simulated data with a variational autoencoder (VAE) and implementing transfer learning strategies based on these data, the issue of low recognition accuracy for complex anomaly data due to data imbalance can be effectively mitigated. In a 25‐day long‐term monitoring experiment of indoor tunnel lining structures, this method demonstrated an average accuracy rate exceeding 96% and a rapid detection capability within 16 min. The results indicate that this method achieves high accuracy in anomaly detection for long‐term monitoring data, even when relying exclusively on time‐domain data.

Enhancing Anomaly Detection Models for Industrial Applications through SVM-Based False Positive Classification

Unsupervised anomaly detection models are crucial for the efficiency of industrial applications. However, frequent false alarms hinder the widespread adoption of unsupervised anomaly detection, especially in fault detection tasks. To this end, our research delves into the dependence of false alarms on the baseline anomaly detector by analyzing the high-response regions in anomaly maps. We introduce an SVM-based false positive classifier as a post-processing module, which identifies false alarms from positive predictions at the object level. Moreover, we devise a sample synthesis strategy that generates synthetic false positives from the trained baseline detector while producing synthetic defect patch features from fuzzy domain knowledge. Following comprehensive evaluations, we showcase substantial performance enhancements in two advanced out-of-distribution anomaly detection models, Cflow and Fastflow, across image and pixel-level anomaly detection performance metrics. Substantive improvements are observed in two distinct industrial applications, with notable instances of elevating the image-level F1-score from 46.15% to 78.26% in optimal scenarios and boosting pixel-level AUROC from 72.36% to 94.74%.

Simulation Study for Parametric EWMA and NPWEWPA-SR Control Charts Against Non-Normality Assumptions

Common control chart types such as EWMA require assumptions to have valid information. The study compares IC robustness and OOC performance for parametric EWMA and NPEWMA-SR control charts in violation of symmetrical assumption. The Monte Carlo simulation study held scale parameters with various shape parameters in Weibull distribution. First finding in this paper was both parametric EWMA and NPEWMA-SR control charts were not suitable for the application in asymmetrical distribution due to weak IC robustness and frequent false alarm will be occurred. Although EWMA-X ̅ The control chart showed a most stable OOC performance; the weak IC robustness made the control chart unacceptable. Whereas, NPEWMA-SR control chart lost the ability in small shift detection when symmetrical assumption violated. Moreover, two different weightage of current sample for both parametric EWMA and NPEWMA-SR control charts were also investigated. The results showed that weightage of current sample for both parametric EWMA and NPEWMA-SR control charts did not affect the ARL value trend in different skewness of Weibull distribution.

An Online Anomaly Detection Approach for Fault Detection on Fire Alarm Systems

The early detection of fire is of utmost importance since it is related to devastating threats regarding human lives and economic losses. Unfortunately, fire alarm sensory systems are known to be prone to failures and frequent false alarms, putting people and buildings at risk. In this sense, it is essential to guarantee smoke detectors’ correct functioning. Traditionally, these systems have been subject to periodic maintenance plans, which do not consider the state of the fire alarm sensors and are, therefore, sometimes carried out not when necessary but according to a predefined conservative schedule. Intending to contribute to designing a predictive maintenance plan, we propose an online data-driven anomaly detection of smoke sensors that model the behaviour of these systems over time and detect abnormal patterns that can indicate a potential failure. Our approach was applied to data collected from independent fire alarm sensory systems installed with four customers, from which about three years of data are available. For one of the customers, the obtained results were promising, with a precision score of 1 with no false positives for 3 out of 4 possible faults. Analysis of the remaining customers’ results highlighted possible reasons and potential improvements to address this problem better. These findings can provide valuable insights for future research in this area.

Unbiased estimation based multivariate alarm design considering temporal and multimodal process characteristics

In alarm systems, conventional univariate alarm methods often result in frequent false and missing alarms, calling for an urgent need to introduce multivariate information. For the multivariate alarm design, although each variable’s detection sensitivity is improved with the assistance of other variables, it is also susceptible to anomalies of other variables. Therefore, it is a challenge to properly introduce multivariate information, especially for complex processes subject to operating condition changes. This paper proposes a multivariate alarm framework that complements temporal and multimodal process characteristics to better alarm for variables by unbiased estimation. The temporal and multimodal characteristics are explored by prediction-oriented network structure and reconstruction-oriented network structure, respectively. To make them properly integrated, pattern labels that reveal the modes change are designed and used as the bridge between the temporal and the multimodal parts. On the one hand, the consideration of two types of characteristics allows perceiving temporal-related and modal-related faults, promoting sensitive alarm performance. On the other hand, unifying the two types of networks can eliminate the estimation bias of normal variables, making them unsusceptible to anomalies of other variables and promoting accurate alarm performance. Experiments on the coal mill prove the effectiveness of the proposed method regarding false alarm rate and missing alarm rate.

CrimeNet: Neural Structured Learning using Vision Transformer for violence detection

The state of the art in violence detection in videos has improved in recent years thanks to deep learning models, but it is still below 90% of average precision in the most complex datasets, which may pose a problem of frequent false alarms in video surveillance environments and may cause security guards to disable the artificial intelligence system.In this study, we propose a new neural network based on Vision Transformer (ViT) and Neural Structured Learning (NSL) with adversarial training. This network, called CrimeNet, outperforms previous works by a large margin and reduces practically to zero the false positives. Our tests on the four most challenging violence-related datasets (binary and multi-class) show the effectiveness of CrimeNet, improving the state of the art from 9.4 to 22.17 percentage points in ROC AUC depending on the dataset. In addition, we present a generalisation study on our model by training and testing it on different datasets. The obtained results show that CrimeNet improves over competing methods with a gain of between 12.39 and 25.22 percentage points, showing remarkable robustness.

E-detectors: A Nonparametric Framework for Sequential Change Detection

Sequential change detection is a classical problem with a variety of applications. However, the majority of prior work has been parametric, for example, focusing on exponential families. We develop a fundamentally new and general framework for sequential change detection when the pre- and post-change distributions are nonparametrically specified (and thus composite). Our procedures come with clean, nonasymptotic bounds on the average run length (frequency of false alarms). In certain nonparametric cases (like sub-Gaussian or sub-exponential), we also provide near-optimal bounds on the detection delay following a changepoint. The primary technical tool that we introduce is called an e-detector, which is composed of sums of e-processes—a fundamental generalization of nonnegative supermartingales—that are started at consecutive times. We first introduce simple Shiryaev-Roberts and CUSUM-style e-detectors, and then show how to design their mixtures in order to achieve both statistical and computational efficiency. Our e-detector framework can be instantiated to recover classical likelihood-based procedures for parametric problems, as well as yielding the first change detection method for many nonparametric problems. As a running example, we tackle the problem of detecting changes in the mean of a bounded random variable without i.i.d. assumptions, with an application to tracking the performance of a basketball team over multiple seasons.

Unified Quality-Aware Compression and Pulse-Respiration Rates Estimation Framework for Reducing Energy Consumption and False Alarms of Wearable PPG Monitoring Devices

Objective: Due to the high demands of tiny, compact, lightweight and low-cost photoplethysmogram (PPG) monitoring devices, these devices are resource-constrained including limited battery power. Consequently, it highly demands frequent charge or battery replacement in the case of continuous PPG sensing and transmission. Further, PPG signals are often corrupted severely under ambulatory and exercise recording conditions that leads to frequent false alarms. Method: In this paper, we propose a unified quality-aware compression and pulse-respiration rates estimation framework for reducing energy consumption and false alarms of wearable and edge PPG monitoring devices by exploring predictive coding technique for jointly performing signal quality assessment (SQA), data compression and pulse rate (PR) and respiration rate (RR) estimation without use of different domains of signal processing techniques that can be achieved by using the features extracted from the smoothed prediction error signal. Results: By using the five standard PPG databases, the performance of the proposed unified framework is evaluated in terms of compression ratio (CR), mean absolute error (MAE), false alarm reduction rate (FARR), processing time (PT) and energy saving (ES). The compression, PR and RR estimation and SQA results are compared with that of the existing methods and also with results of uncompressed PPG signals with sampling rates of 125 Hz and 25 Hz. Conclusion: The proposed unified quality-aware framework achieves an average CR of 4%, SQA (Se of 92.00%, FARR of 84.87%), PR (MAE: 0.46 ±1.20) and RR (MAE: 1.75 (0.65-4.45), PT (sec) of 15.34 ±0.01) and ES of 70.28% which outperforms the results of uncompressed PPG signal with a sampling rate of 125 Hz. Significance: Arduino Due computing platform based implementation demonstrates the real-time feasibility of the proposed unified quality-aware PR-RR estimation and data compression and transmission framework on the limited computational resources. Thus, it has great potential in improving energy-efficiency and trustworthiness of wearable and edge PPG monitoring devices.

An Intelligent Logic-Based Mold Breakout Prediction System Algorithm for the Continuous Casting Process of Steel: A Novel Study.

Mold breakout is one of the significant problems in a continuous casting machine (caster). It represents one of the key areas within the steel production facilities of a steel plant. A breakout event on a caster will always cause safety hazards, high repair costs, loss of production, and shutdown of the caster for a short while. In this paper, a logic-judgment-based mold breakout prediction system has been developed for a continuous casting machine. This system developed new algorithms to detect the different sticker behaviors. With more algorithms running, each algorithm is more specialized in the other behaviors of stickers. This new logic-based breakout prediction system (BOPS) not only detects sticker breakouts but also detects breakouts that takes place due to variations in casting speed, mold level fluctuation, and taper/mold problems. This system also finds the exact location of the breakout in the mold and reduces the number of false alarms. The task of the system is to recognize a sticker and prevent a breakout. Moreover, the breakout prediction system uses an online thermal map of the mold for process visualization and assisting breakout prediction. This is done by alerting the operating staff or automatically reducing the cast speed according to the location of alarmed thermocouples, the type of steel, the tundish temperature, and the size of the cold slab width. By applying the proposed model in an actual steel plant, field application results show that it could timely detect all 13 breakouts with a detection ratio of 100%, and the frequency of false alarms was less than 0.056% times/heat. It has the additional advantage of not needing a lot of learning data, as most neural networks do. Thus, this new logical BOPS system should not only detect the sticker breakouts but also detect breakouts taking place due to variations in casting speed and mold level fluctuation.

Constructing control charts for autocorrelated data using an exhaustive systematic samples pooled variance estimator

SPC with positive autocorrelation is well known to result in frequent false alarms if the autocorrelation is ignored. The autocorrelation is a nuisance and not a feature that merits modeling and understanding. This paper proposes exhaustive systematic sampling, which is similar to Bayesian thinning except no observations are dropped, to create a pooled variance estimator that can be used in Shewhart control charts with competitive performance. The expected value and variance are derived using quadratic forms that is nonparametric in the sense no distribution or time series model is assumed. Practical guidance for choosing the systematic sampling interval is offered to choose a value large enough to be approximately unbiased and not too big to inflate variance. The proposed control charts are compared to time series residual control charts in a simulation study that validates using the empirical reference distribution control limits to preserve stated in-control false alarm probability and demonstrates similar performance.

Early Fault Warning Method of Wind Turbine Main Transmission System Based on SCADA and CMS Data

The main transmission system of wind turbines is a multi-component coupling system, and its operational state is complex and varied. These lead to frequent false alarms and missed alarms in existing monitoring systems. To accurately obtain the operational state of the main transmission system and detect its abnormal operation, an early fault warning method for the main transmission system based on SCADA and CMS data is proposed. Firstly, the SCADA and CMS feature parameters relevant to the operating status of the main transmission system are selected by two different methods separately, and the correlation mechanism between the feature parameters and the operating characteristics of the main transmission system is further analyzed. Secondly, the Long Short-Term Memory (LSTM) network-based prediction model of the main transmission system operating parameters is established, in which SCADA and CMS feature parameters are fused as the input feature vectors. Then, the predicted residuals of the state evaluation parameters are used as the operational state evaluation index. The early fault warning model is established by Analytic Hierarchy Process (AHP) and Kernel Density Estimation (KDE). Finally, a case study is used to verify the correct performance of the proposed method. The results show that this method can realize early warning functions 73 h earlier than the existing SCADA system. The method can provide a theoretical basis for the safe operation and condition-based maintenance of wind turbines.