An EMD-SVR method for non-stationary time series prediction

This article, written by Senior Technology Editor Dennis Denney, contains highlights of paper SPE 151765, ’Key Elements of a Migrant-Worker Health and Welfare Program and Its Effect on a Major Construction Project,’ by Israr Ahmed and Herman Wirtz, Qatar Shell; Robin Patrick Donnelly and Alistair Fraser, Shell International; and Salvador Castillo, Qatar Shell, prepared for the 2012 SPE Middle East Health, Safety, Security, and Environment Conference and Exhibition, Abu Dhabi, 2-4 April. The paper has not been peer reviewed. The Pearl gas-to-liquids (GTL) project required construction of a state-of-the-art hydrocarbon-processing facility with, at peak, 55,000 employed on site. The company created a worker health and welfare program, with a goal to enhance health and performance by creating a culture of care and concern for the wellbeing of workers throughout construction and to mitigate projected risks for a project of such magnitude. Introduction Traditionally, construction camps are high risk and high public exposure. There has been a historical tendency to leave the matter of construction-camp planning, design, and management to contractors, with associated risks of under-performance. It is unusual to find a holistic approach for camps that integrates the material aspects with quality of living conditions, action to create social cohesion, and an appreciation of overall worker welfare. However, the realization that there is an opportunity to go beyond compliance with design standards gave rise to a shift toward use of “behavioral and holistic interventions” to improve the safety culture and attitude among workers. The worker-welfare program was born with the consideration of capitalizing on the caring aspect of safety. Particularly, the program envisioned to create a facility and community that show empathy for people, a place where members of a large multinational/multicultural workforce live happily and in harmony with each other, where they could enjoy high-quality fulfillment of basic needs and psychosocial support. Therefore, a holistic approach was used that aimed at delivering initiatives targeting the entire range of physical, emotional, mental, and even transpersonal needs of workers in a “high-risk” work area. Theory The challenge of making respect for people visible and objective in Shell’s practices was given further push in the area of health, safety, and environmental management. First, in the area of health management, it was imperative in building projects and in operations that controls and regulations be in place to protect and promote the health of employees, contractors, and neighbors by eliminating, reducing, or mitigating health risks in the workplace.

As the rapid development of modern technology, industrial companies have to manufacture high-reliability and long-lifetime products to satisfy the changing needs of the customers. In such cases, it is difficult to assess the reliability and lifetime of the product with traditional life testing. Thus how to evaluate the lifetime and reliability index of these products is an urgent problem to be solved. For some products, it is possible to obtain the performance degradation information by the accelerated degradation testing (ADT). Therefore, to utilize the product degradation information may be an effective way to resolve this issue. However, most of lifetime prediction methods in use are mainly based on single prediction model with the disadvantage of low robustness and inaccuracy, so it cannot get the high credible lifetime of the product. This paper will adopt the prediction thought of combining two single models to establish a new prediction model, also propose a combined life prediction method based on the performance degradation data by using the particle swarm optimization (PSO) with immunity algorithms (IA). The author selects two better prediction models, which are time series model and the model of Brownian motion with drift, to predict the degradation path of the product separately. As the degradation process of the product is stochastic, and these two models are also well suited for this process. So each of them is good for long-term prediction. Then the objective function of the sum of the absolute errors is established with weight coefficients which are used to combine these prediction methods and integrate the prediction results. And the objective function is minimized with the IA-PSO, which has the characteristics of fast global optimization and uses to determine the weight coefficients for each of the prediction models. This approach can reduce the blindness of calculation and improve the accuracy of the prediction model. To verify this combined prediction method, the application of SLD's performance degradation data is demonstrated in this paper, the result shows that the combined prediction method based on the IA-PSO is effective and reasonable, and evidently has less prediction errors than each of single model. Therefore, this method plays an instructive way in engineering practice and research field.

Soldiers rely heavily on their vision, which is crucial not only for daily activities but also for the effective operation of defense systems, weaponry, and other military applications. However, various eye disorders, such as those related to increased intra-ocular pressure, can lead to irreversible vision loss, severely impacting a soldier’s operational capabilities. While extensive research has been conducted on detecting such ocular conditions, there remains a critical need for more accurate diagnostic methods to ensure early detection and treatment. In this study, we propose a novel approach combining Empirical Mode Decomposition (EMD) and Variational Mode Decomposition (VMD) for enhanced detection of eye disorders from retinal fundus images. The proposed method includes a comprehensive preprocessing phase, followed by decomposition using EMD and VMD techniques. The decomposed images undergo feature extraction through feature combination, with subsequent normalization and selection using z-score and the Relief method, respectively. Classification is performed using Support Vector Machines (SVM) with various kernels, including cubic, Gaussian, linear, and quadratic. The results demonstrate that the proposed method achieves high accuracy, with SVM kernel functions yielding accuracies of 98.30 %, 96.59 %, 96.59 %, and 97.87 % for 10-fold cross-validation, respectively. Additionally, the evaluation metrics, including sensitivity and specificity, indicate superior performance compared to state-of-the-art methods for similar datasets. This advanced diagnostic approach offers significant improvements in detecting eye disorders, which could be crucial in defense applications. Early and accurate diagnosis by military ophthalmologists can lead to better decision-making and timely interventions, ultimately preserving the vision and effectiveness of soldiers in the war.

Time series prediction is not easy to achieve high accuracy. non-linear and unstable characteristics make the time series prediction difficult. The variety of dataset make the prediction result debatable. In order to solve this problem, in this paper we propose a deep learning prediction method based on decomposition, reconstruction and combination, which combines ways of communication field. The model is decomposed by Empirical Mode Decomposition, Principal Component Analysis and Long Short-Term Memory networks (EPL below). And also, the proposed interval EPL (IEPL below) improve and consummate the EPL model. The EPL and IEPL experiment results will bring average 5% higher accuracy than that of existing research.

Traditional life evaluation theory established on the basis of mass failure data, the phenomena of little or naught failure put forward challenges for existing life evaluation theory. The performance degradation data provides useful information for products' life and reliability, and gives feasible way for life evaluation. The limitations of existing stochastic process models for performance degradation are analyzed; a new approach based on performance degradation amplitude is brought forward, the calculation methods based on degradation amplitude analysis are given out. For degradation product with large amplitude size, by way of fitting the reliability of every moments, the performance degradation rule can be got and the products' life can be forecast; for small amplitude size, the degradation path is selected in accordance to engineering experience and products' failure mechanism, the products' expected life and reliability is evaluated based on appropriate distribution model. An example of laser device with performance degradation data is given out to validate the effectiveness of the method.

The characteristics of performance degradation data are analyzed. The disciplinarians of numerical control machine tool performance degradation data with time are analyzed, the reliability assessment methods with performance degradation data based on performance degradation distribution is presented. The performance gradation data contain abundant numerical control machine tool reliability information, the reliability and lifetime of numerical control machine tool can be evaluated with performance degradation data availably, even if the failure time cannot be obtained by life testing.

The applications of deep learning and artificial intelligence have permeated daily life, with time series prediction emerging as a focal area of research due to its significance in data analysis. The evolution of deep learning methods for time series prediction has progressed from the Convolutional Neural Network (CNN) and the Recurrent Neural Network (RNN) to the recently popularized Transformer network. However, each of these methods has encountered specific issues. Recent studies have questioned the effectiveness of the self-attention mechanism in Transformers for time series prediction, prompting a reevaluation of approaches to LTSF (Long Time Series Forecasting) problems. To circumvent the limitations present in current models, this paper introduces a novel hybrid network, Temporal Convolutional Network-Linear (TCN-Linear), which leverages the temporal prediction capabilities of the Temporal Convolutional Network (TCN) to enhance the capacity of LSTF-Linear. Time series from three classical chaotic systems (Lorenz, Mackey-Glass, and Rossler) and real-world stock data serve as experimental datasets. Numerical simulation results indicate that, compared to classical networks and novel hybrid models, our model achieves the lowest RMSE, MAE, and MSE with the fewest training parameters, and its R2 value is the closest to 1.

Health monitoring and prognostics of axial piston pump is very helpful for the safety of aerial hydraulic system. Directing to the difficulties of measuring the wear loss between the valve plate and cylinder barrel, this paper presents a hybrid prediction method based on EMD (Empirical Mode Decomposition) and SVM (Support Vector Machine), in which EMD is used to get the pump's health state and PSO (Particle Swarm Optimization)-SVM is used to make a prediction for the pump's remaining useful lifetime. Oil-return flow was selected to indicate the wear condition of pump with several IMFs. SVM was trained by these IMFs, and then be used to predict the oil-return flow one-step ahead or multi-step ahead. In the SVM's training process, PSO was used to search the optimal parameter of SVM's kernel function. Applications show that hybrid prediction method has higher prediction precision and could be applied for the remaining useful lifetime prognostics.

Aiming at the problems of low accuracy and low robustness in current prediction methods of rolling bearing performance degradation, this paper propose a performance degradation prediction method based on empirical mode decomposition (EMD) and support vector data description (SVDD). Unlike the features extracted by wavelet analysis, the EMD algorithm has better adaptive capability and can better avoid the interference of high frequency noise. fiber Bragg grating (FBG) are used to extract the bearing vibration signal. The use of FBG sensors can better avoid the interference of electromagnetic noise, so that the vibration signal can be accurately extracted in the industrial strong magnetic environment. The Empirical Mode Decomposition is used to decompose data and extract effective intrinsic mode function (IMF) components. Six features of Intrinsic Mode Function components are extracted to form feature vectors and used as training data. Because the IMF component obtained by EMD decomposition has removed most of the noise signals, the signal features are more significant and thus effectively improve the accuracy of subsequent recognition. This paper use Support Vector Data Description for performance degradation prediction and evaluates the degradation performance of the rolling bearing by calculating the degradation value. Experiments show the proposed method can detect the performance degradation process of the rolling bearing and effectively predict the remaining service life. Due to the high recognition accuracy, the proposed method is able to identify the current state of ball bearings and predict their remaining service life.

HighlightsWhat are the main findings?Time-frequency features extracted using EMD, DWT, and combined EMD+DWT effectively separate earthquake and noise signals.Random Forest classifier with Lasso-selected EMD+DWT features achieved 100% accuracy, specificity, and sensitivity.What are the implication of the main findings?Time-frequency-based feature extraction and selection improve real-time earth-quake detection.The approach provides a robust foundation for operational monitoring and ear-ly-warning systems.Earthquakes are sudden and destructive natural events caused by tectonic movements in the Earth’s crust. Although they cannot be predicted with certainty, rapid and reliable detection is essential to reduce loss of life and property. This study aims to automatically distinguish earthquake and noise signals from real seismic data by analyzing time-frequency features. Signals were scaled using z-score normalization, and extracted with Empirical Mode Decomposition (EMD), Discrete Wavelet Transform (DWT), and combined EMD+DWT methods. Feature selection methods such as Lasso, ReliefF, and Student’s t-test were applied to identify the most discriminative features. Classification was performed with Ensemble Bagged Trees, Decision Trees, Random Forest, k-Nearest Neighbors (k-NN), and Support Vector Machines (SVM). The highest performance was achieved using the RF classifier with the Lasso-based EMD+DWT feature set, reaching 100% accuracy, specificity, and sensitivity. Overall, DWT and EMD+DWT features yielded higher performance than EMD alone. While k-NN and SVM were less effective, tree-based methods achieved superior results. Moreover, Lasso and ReliefF outperformed Student’s t-test. These findings show that time-frequency-based features are crucial for separating earthquake signals from noise and provide a basis for improving real-time detection. The study contributes to the academic literature and holds significant potential for integration into early warning and earthquake monitoring systems.

Feature extraction and recognition of ictal EEG using EMD and SVM

Fault classification in power systems using EMD and SVM

The early and accurately detection of brucellosis incidence change is of great importance for implementing brucellosis prevention strategic health planning. The present study investigated and compared the performance of the three data mining techniques, random forest (RF), support vector machine (SVM) and multivariate adaptive regression splines (MARSs), in time series modelling and predicting of monthly brucellosis data from 2005 (March/April) to 2017 (February/March) extracted from a national public health surveillance system in Hamadan located in west of Iran. The performances were compared based on the root mean square errors, mean absolute errors, determination coefficient (R2 ) and intraclass correlation coefficient criteria. Results indicated that the RF model outperformed the SVM and MARS models in modeling used data and it can be utilized successfully utilized to diagnose the behaviour of brucellosis over time. Further research with application of such novel time series models in practice provides the most appropriate method in the control and prevention of future outbreaks for the epidemiologist.

ObjectivesRA has an affinity for smaller joints, thus its effect on the foot/ankle is widely known. Despite this, there is lack of adherence to foot management standards by podiatrists. This research aimed to audit the adherence to these standards and compare them with well-established adherence to management standards in the diabetic foot.MethodsIn this clinical audit, data were obtained via six National Health Service (NHS) podiatry departments in North-East London on service provision, management, treatment and professional development on both RA and diabetic foot health via foot management clinical audit tools. Descriptive analyses were conducted and analysed to identify patterns and trends, with set standard compliance conditions calculated on the Net Promotor Score (NPS) metric to allow for multi-comparison.ResultsAll areas of RA foot health management were found to have poor compliance when compared with diabetes foot health management. When using NPS, no trust audited met the majority of foot health standards in RA, with only two having a positive score (meeting the minimum standards), compared with all trusts posting a positive NPS on diabetes foot health standards.Conclusion Our results indicate that poor compliance to RA foot health standards is prevalent across the audited region and might be resulting in worsening foot outcomes despite a paradigm shift in other areas of RA management. Enhanced training and knowledge are required for better adherence to the standards set out and to improve foot health management in RA.

For dynamic weighing about loaders, to obtain a quick and exact measure result synchronously is a complex problem. Based on an existent dynamic weighing method about loaders, an original integrative modeling method for dynamic weighing is given. In the method, empirical mode decomposition is used to be the signal processing method for local pressure signal contaminated; and the least square support vector machines is used to be learning machine for dynamic pressure compensation varying with different lift crane velocity; also the Bayesian evidence framework for selecting and tuning parameters of least square support vector machines; Finally, after doing some simple linear proportional calculation, the weight of load is obtained. In the end, emulation analysis and test results all indicate that by using the above modeling method, measure precision within 1% can be obtained.