A Method for Aero-Engine Gas Path Anomaly Detection Based on Markov Transition Field and Multi-LSTM

There are some problems such as uncertain thresholds, high dimension of monitoring parameters and unclear parameter relationships in the anomaly detection of aero-engine gas path. These problems make it difficult for the high accuracy of anomaly detection. In order to improve the accuracy of aero-engine gas path anomaly detection, a method based on Markov Transition Field and LSTM is proposed in this paper. The correlation among high-dimensional QAR data is obtained based on Markov Transition Field and hierarchical clustering. According to the correlation analysis of high-dimensional QAR data, a multi-input and multi-output LSTM network is constructed to realize one-step rolling prediction. A Gaussian mixture model of the residuals between predicted value and true value is constructed. The three-sigma rule is applied to detect outliers based on the Gaussian mixture model of the residuals. The experimental results show that the proposed method has high accuracy for aero-engine gas path anomaly detection.

Older Adult Health and Remission of Risky Drinking and Alcohol Use Disorder: A Lifespan-Developmental Study

Older-adult drinking is a growing public-health concern. As part of a larger project investigating older adulthood by contrasting this with other adult developmental periods, this study used longitudinal U.S.-representative data to test bidirectional associations between drinking and health, emphasizing aging-related health concerns as potential mechanisms of remission from risky/problem drinking. In multiple-group cross-lag models, we found that effects of poor self-reported health on drinking reductions increased with age, reached significance around midlife, and were strongest in older adulthood. However, a caveat revealed by additional Markov transition models was that these effects did not extend to relatively severe older-adult drinkers (indexed by DSM-5 AUD). In some instances, poor health even predicted less older-adult AUD remission. Altogether, findings support the notion of aging-related health concerns as important mechanisms of older-adult drinking reduction; but highlight a need to understand barriers to these mechanisms among severe older-adult drinkers, in part toward guiding lifespan-developmentally-informed interventions.

A New Bearing Fault Diagnosis Method Based on Capsule Network and Markov Transition Field/Gramian Angular Field

Compared to time-consuming and unreliable manual analysis, intelligent fault diagnosis techniques using deep learning models can improve the accuracy of intelligent fault diagnosis with their multi-layer nonlinear mapping capabilities. This paper proposes a model to perform fault diagnosis and classification by using a time series of vibration sensor data as the input. The model encodes the raw vibration signal into a two-dimensional image and performs feature extraction and classification by a deep convolutional neural network or improved capsule network. A fault diagnosis technique based on the Gramian Angular Field (GAF), the Markov Transition Field (MTF), and the Capsule Network is proposed. Experiments conducted on a bearing failure dataset from Case Western Reserve University investigated the impact of two coding methods and different network structures on the diagnosis accuracy. The results show that the GAF technique retains more complete fault characteristics, while the MTF technique contains a small number of fault characteristics but more dynamic characteristics. Therefore, the proposed method incorporates GAF images and MTF images as a dual-channel image input to the capsule network, enabling the network to obtain a more complete fault signature. Multiple sets of experiments were conducted on the bearing fault dataset at Case Western Reserve University, and the Capsule Network in the proposed model has an advantage over other convolutional neural networks and performs well in the comparison of fault diagnosis methods proposed by other researchers.

Recognizing duration effects in multistate population models

The risk of many demographic events varies by both current state and duration in that state. However, the use of such semi-Markov models has been substantially constrained by data limitations. Here, a new specification of the semi-Markov transition probability matrix in terms of the underlying rates is provided, and a general procedure is developed to estimate semi-Markov probabilities and rates from adjacent population data.Multistate models recognizing marriage and divorce by duration in state are constructed for United States Females, 1995. The results show that recognizing duration in the married and divorced states adds significantly to the model’s analytical value. Extending the constant-α method to semi-Markov models, 2000–2005 U.S. population data and 1995 cross-product ratios are employed to estimate 2000–2005 duration-dependent transfer probabilities and rates.The present analyses provide new relationships between probabilities and rates in semi-Markov models. Extending the constant cross-product ratio estimation approach opens new sources of data and expands the range of data susceptible to state-duration analyses.

Dynamics of Area Substitution of Pulses in India

Background: Pulses have been very curial in many aspects like; rich source of protein, economy aspect and contribute to agricultural and environmental sustainability. In this investigation an attempt has been made to evaluate the dynamics of area substitution between pulses and other crops, extent of spatial shift among pulses producing states and some policy measures have been suggested to stabilize the area under pulses across states. Methods: Secondary data on area of principal crops for the period 1966-2016 was used in this article. By computing quartile values, all states and groups of states were clubbed into four different quartiles for each decade. Area substitution among principal field crops including pulses has been analyzed using first order Markov transition probability matrix (TPM). Result: This TPM was further used to evaluate the mobility of membership status of states under pulses production. It was found that period 1986-2006 happened to be the golden period for area under pulses in India. Mean area under pulses had increased for first three decades and in the subsequent two decades mean area (quartile values) had declined substantially.

Modeling and forecasting of rainfall reoccurrence changes using Markov Switching in Iran

This paper represents the recurrence (reoccurrence) changes in the rainfall series using Markov Switching models (MSM). The switching employs a dynamic pattern that allows a linear model to be combined with nonlinearity models a discrete structure. The result is the Markov Switching models (MSM) reoccurrence predicting technique. Markov Switching models (MSM) were employed to analyze rainfall reoccurrence with spatiotemporal regime probabilities. In this study, Markov Switching models (MSM) were used based on the simple exogenous probability frame by identifying a first-order Markov process for the regime probabilities. The Markov transition matrix and regime probabilities were used to analyze the rainfall reoccurrence in 167 synoptic and climatology stations. The analysis results show a low distribution from 0.0 to 0.2 (0–20%) per day spatially from selecting stations, probability mean of daily rainfall recurrence is 0.84, and a different distribution based on the second regime was found to be more remarkable to the rainfall variability. The rainfall reoccurrence in daily rainfall was estimated with relatively low variability and strong reoccurrence daily with ranged from 0.851 to 0.995 (85.1–99.5%) per day based on the spatial distribution. The variability analysis of rainfall in the intermediate and long variability and irregular variability patterns would be helpful for the rainfall variability for environmental planning.

Product Quality Prediction for Wire Electrical Discharge Machining with Markov Transition Fields and Convolutional Long Short-Term Memory Neural Networks

This paper proposes a wire electrical discharge machining (WEDM) product quality prediction method, called MTF-CLSTM, to integrate the Markov transition field (MTF) and the convolutional long short-term memory (CLSTM) neural network. The proposed MTF-CLSTM method can accurately predict WEDM workpiece surface roughness right after manufacturing by collecting and analyzing static machining parameters and dynamic manufacturing conditions. The highly accurate prediction is due to the following two reasons. First, MTF can transform data into images to extract data temporal information and state transition probability information. Second, the CLSTM neural network can extract image spacial features and temporal relationship of data that are separated far apart. In short, MTF-CLSTM predicts WEDM workpiece surface roughness with the MTF model and the CLSTM neural network using static machining parameters and dynamic manufacturing conditions. MTF-CLSTM is compared with 10 related research studies in many aspects. There is only one existing method that is like MTF-CLSTM to predict WEDM workpiece surface roughness by using static machining parameters and dynamic manufacturing conditions. Experiments are conducted to evaluate MTF-CLSTM performance to show that MTF-CLSTM significantly outperforms the existing method in terms of the prediction mean absolute percentage error.

A Comparative Study of the Impact of Data Augmentation in Machine Learning Based Classification Accuracy

Traumatic Brain Injury is the primary cause of death and disability all over the world. Monitoring the intracranial pressure (ICP) and classifying it for hypertension signals is of crucial importance. This thesis explores the possibility of a better classification of the ICP signal and detection of hypertensive signal prior to the actual occurrence of the hypertensive episodes. This study differ from other approaches astime series is converted into images by Gramian angular field and Markov transition matrix and augmented with data. Due to unbalanced data, the effect of smote extended nearest neighbour algorithm for balancing the data is examined. We use various machine learning algorithms to classify the ICP signals. The results obtained shoe that Ada boost performance is the best among compared algorithms. F1 score of the Ada boost is 0.95 on original dataset, and 0.9967 on balanced and augmented dataset. Quadratic Discriminant Analysis F1 score is 1 when data is augmented and balanced.