Moving Window Strategy Research Articles

Identification of Spatial Distribution of Afforestation, Reforestation, and Deforestation and Their Impacts on Local Land Surface Temperature in Yangtze River Delta and Pearl River Delta Urban Agglomerations of China

Forest change affects local and global climate by altering the physical properties of the land surface. Accurately assessing urban forest changes in local land surface temperature (LST) is a scientific and crucial strategy for mitigating regional climate change. Despite this, few studies have attempted to accurately characterize the spatial and temporal pattern of afforestation, reforestation, and deforestation to optimize their effects on surface temperature. We used the China Land Cover Dataset and knowledge criterion-based spatial analysis model to map urban forestation (e.g., afforestation and reforestation) and deforestation. We then analyzed the impacts of these activities on LST from 2010 to 2020 based on the moving window strategy and the spatial–temporal pattern change analysis method in the urban agglomerations of the Yangtze River Delta (YRD) and Pearl River Delta (PRD), China. The results showed that forest areas declined in both regions. Most years, the annual deforestation area is greater than the yearly afforestation areas. Afforestation and reforestation had cooling effects of −0.24 ± 0.19 °C and −0.47 ± 0.15 °C in YRD and −0.46 ± 0.10 °C and −0.86 ± 0.11 °C in PRD. Deforestation and conversion of afforestation to non-forests led to cooling effects in YRD and warming effects of 1.08 ± 0.08 °C and 0.43 ± 0.19 °C in PRD. The cooling effect of forests is more evident in PRD than in YRD, and it is predominantly caused by reforestation. Moreover, forests demonstrated a significant seasonal cooling effect, except for December in YRD. Two deforestation activities exhibited seasonal warming impacts in PRD, mainly induced by deforestation, while there were inconsistent effects in YRD. Overall, this study provides practical data and decision-making support for rational urban forest management and climate benefit maximization, empowering policymakers and urban planners to make informed decisions for the benefit of their communities.

Impacts of forest cover change on local temperature in Yangtze River Delta and Pearl River Delta urban agglomerations of China

The continuous economic and ecological construction in the Yangtze River Delta (YRD) and Pearl River Delta (PRD) has caused frequent temporal and spatial changes in local forests, thus affecting the regional climate. Yet few studies have addressed the temperature feedback through biophysical mechanisms due to forest change in two urban agglomerations of China. We compared MODIS and Landsat-based land cover data to detect a more accurate forest cover change. We then used the moving window strategy and spatiotemporal pattern change analysis method to quantify and compare the actual impact of forest cover change on temperature and the differences in driving factors (e.g., evapotranspiration (ET), albedo, and precipitation) from 2010 to 2020. The results showed that Landsat-based land cover data performed well. The conversion from forest to cropland was dominated in YRD and PRD, followed by the conversion of cropland to forest, with a small proportion of forest converting to impervious surface. The afforested areas in the two regions showed a diurnal cooling effect (-0.18 ± 0.07 °C and -0.10 ± 0.13 °C, respectively), which was greater than the air temperature. Forest converting to impervious surfaces led to stronger warming (0.39 ± 0.37 °C in YRD) than that of cropland (0.05 ± 0.03 °C in YRD and 0.07 ± 0.06 °C in PRD). The daytime LST variations can be explained by ET and inconsistent albedo effects. Seasonally, the cooling effects induced by afforestation predominated during the growing season (spring and summer), accompanied by the relatively high ET. This study shows that rational afforestation and control of deforestation are helpful to achieve sustainable forest management in urban agglomerations and to regulate climate warming.

Bayesian dynamic modelling for probabilistic prediction of pavement condition

Significant funds have been allocated to maintain road networks each year in developed countries. Performance prediction is crucial for pavement management systems to adjust working plans and budget allocation. As a Bayesian nonparametric method, Gaussian process regression (GPR) is powerful in predicting nonlinear time series and quantifying uncertainty. However, it remains computationally intensive and fails to adapt to the time-varying characteristics. To address such issues, a dynamic GPR model is proposed for probabilistic prediction of the International Roughness Index (IRI) for flexible pavements. A moving window strategy is developed to substantially shrink the size of training data, which effectively alleviates computational cost and thus leads to a dynamic GPR. A genetic algorithm is then adopted to determine the optimal window size by considering the trade-off between computational efficiency and accuracy. A dataset acquired from Long-Term Pavement Performance (LTPP) is used to demonstrate the feasibility of the dynamic GPR. Its performance is compared to traditional GPR as well as dynamic and static Bayesian linear regression (BLR) models. The comparison results indicate that the proposed dynamic GPR can increase the accuracy by 0.86, 1.52, and 2.27 times for dynamic BLR, static GPR, and static BLR, respectively. It exhibits the best results in terms of accuracy and uncertainty metrics due to its nonlinear modelling and time-varying ability.

Multi-source information fusion-based dynamic model for online prediction of rate of penetration (ROP) in drilling process

Rate of penetration (ROP) accurate prediction can effectively reduce drilling cycle time and operation cost. However, the complexity and variability of drilling process is not conducive to accurate ROP modeling. The existing ROP models focus on static prediction considering drilling data, which cannot effectively solve the ROP mutation problem caused by complex formations. Some ROP online prediction studies have great real-time capture capability, but without considering the formation lithology adequately, and can be limited in practical application. In this paper, a multi-source information fusion-based dynamic model for online prediction of ROP in drilling process is proposed, which consists of three stages (drilling data pre-processing, optimized ROP modeling, and ROP model updating). In the first stage, three drilling parameters including weight on bit, rotational speed, and torque are filtered by using the outlier removing and wavelet filtering techniques. In the second stage, a novel ROP modeling method, named as hybrid bat algorithm optimized - restricted Boltzmann machine - back propagation neural network (HBAO-RBM-BPNN) is proposed to build the ROP prediction model. In the last stage, formation drillability variation and time interval are used as update conditions, and the established ROP model is updated via a moving window strategy to realize high accuracy online prediction of ROP. Multi-source (formation and drilling) information fusion is considered in this key stage. Finally, the proposed method and seven ROP prediction methods (two offline and five online) are compared through the use of industrial data from a drilling site in Dandong area, Northeast China. The comparison results verify the effectiveness of the proposed method, which lays a foundation for intelligent optimization control of complex geological drilling process.

An Improved Dynamic Optimization Control System for the Drilling Rate of Penetration (ROP) and Its Industrial Application

Optimization control of the rate of penetration (ROP) is crucial in the drilling process due to its vital role in improving the drilling efficiency and safety. In this paper, an improved dynamic optimization control system for ROP is proposed and successfully applied to a drilling site. First, a three layers (intelligent optimization layer, basic automation layer, and process monitoring layer) system framework is proposed according to the drilling characteristics. After that, “If-Then” strategy is used as the method to identify the rotary drilling condition from four different working conditions. Moving-window strategy is selected to establish the dynamic ROP model that can better adapt to environmental changes. Moreover, Jaya algorithm, a new meta-heuristic optimization method is introduced to solve the dynamic ROP optimization issue. In the simulations, the optimization performance of the proposed system is better than moving window-extreme learning machine-hybrid bat algorithm with more stable (fewer switch times) drilling operational parameters. Finally, in an industrial application to a drilling process in Dandong area, Northeast China, the ROP was improved by 20.79% compared with manual operation. Both simulation and industrial application results indicated that the proposed system has significantly improved the drilling efficiency and safety.

Real-time motion planning for an autonomous mobile robot with wheel-ground adhesion constraint

The paper proposes a new real-time motion planning technique for an autonomous mobile robot that is able to find a collision-free path and a corresponding time-optimal trajectory while taking into account limits on the actuator capacities and constraints from the wheel-ground adhesion. The proposed technique includes two sub-modules. The first one, an optimal path planner, is based on the discretization of the robot workspace and dynamic programming principle. It allows finding the shortest path in the robot environment to avoid obstacles and reach the robot target. The second one, an optimal trajectory generator, operates with the discretized robot state-space and also employs dynamic programming techniques. It produces a time-optimal motion along the obtained path, which may include numerous regular and singular trajectory sections caused by the simultaneous application of actuator and wheel-ground adhesion constraints. To adapt this technique to real-time implementation, a moving window strategy is presented that allows regularly updating the robot motion profile in a dynamic environment. The advantages of the developed technique and its suitability for real-time control are illustrated by experimental studies implemented on a car-like mobile robot.

Online Prediction of Cutting Temperature Using Self-Adaptive Local Learning and Dynamic CNN

To maintain a high-quality machining process, it is necessary to develop an online cutting temperature prediction model accurately. However, using the conventional cutting temperature modeling methods, it is difficult to capture the continuous and multivariate time-variant characteristic of cutting temperature. Recently, local learning and switching dynamics have been employed to identify the time-variant characteristic. However, it requires quantitative and precise analysis with certain switching patterns, which are hard to realize in the machining process. In this article, a self-adaptive local learning method integrated with dynamic convolutional neural networks (DCNN) is proposed. The moving window strategy and t-test analysis of performance maps are first to give the local domains. Then, a DCNN is designed to capture spatial cross-correlations and temporal autocorrelations in each local domain. Finally, the local models are ensemble using Bayesian ensemble learning. The effectiveness of the proposed method is demonstrated through different process information and tool conditions.

A Gaussian processes-based approach for damage detection of concrete structure using temperature-induced strain

Concrete structures in cold regions are highly susceptible to internal cracks due to the periodic variation of temperature and the alternation of drying and wetting in the long term. Conventional damage detecting techniques for concrete are often destructive and need tedious manual operation. Concrete strain monitoring is a non-destructive measurement technique, which provides continuously streaming strain data and has the potential of detecting damage automatically based on a data-driven approach. Temperature-induced strains are highly responsive to damage to concrete structures under the freeze-thaw (F-T) cycles. In this regard, we propose a novel damage detection approach based on temperature-induced strains. The proposed method separates the temperature-induced component from the measured data based on the independent component analysis, which improves the modeling accuracy of the Gaussian processes modeling (GPM) approach for detecting damage. The principle of damage detection is extracting the features related to the damage from the measured strain data. The model residuals of temperature-induced strains are extracted as features that are sensitive to concrete damage. A novel damage index is established to determine the presence of structural damage based on the Kolmogorov Smirnov (KS) test, which estimates the probability distribution of residuals. To increase the reliability of damage detection and decrease the pseudo fault alarm rate, the general extreme value (GEV) theory is considered to determine a reliable threshold limit. A moving window strategy is introduced to perform damage detection and identify the damage occurrence time effectively. Monitoring data of the F-T cycle experiment are utilized to validate the proposed method. The results of three different damage cases demonstrate the effectiveness of the proposed data-driven method in terms of detecting the damage and identifying the damage occurrence time. The variation rules of the concrete temperature characteristics are revealed through the damage detection results under F-T cycles.

Sparse Gaussian process regression for multi-step ahead forecasting of wind gusts combining numerical weather predictions and on-site measurements

Accurate forecasts of wind gusts are crucially important for wind power generation, severe weather warnings, and the regulation of vehicle speed. To improve the short-term and long-term forecasting accuracy, the sparse Gaussian process regression (GPR) model that reduces the complexity of full GPR is employed for wind gust forecasting by combining numerical weather prediction (NWP) data and on-site measurements. Historical measurements of wind gusts and the European Centre for Medium-Range Weather Forecasts (ECMWF) data are used as inputs of sparse GPR models. In particular, the historical wind gust input allows the sparse GPR model to adapt to the local change of wind speed at specific locations. A moving window strategy is introduced to perform multi-step forecasting and reduce the size of training data. The feasibility of the proposed method is illustrated by measurements collected from the outdoor competition venues in the 2022 Winter Olympics. The presented approach is then compared with the ECMWF, GPR, random forest, ECMWF-Sparse GPR, and ECMWF-MLR models. The results indicate that the proposed method exhibits the best forecasting performance than other models, and it improves the forecasting accuracy in both short-term and long-term time scales.

Adaptive Soft-Sensor Modeling of SMB Chromatographic Separation Process Based on Dynamic Fuzzy Neural Network and Moving Window Strategy

Adaptive Soft-Sensor Modeling of SMB Chromatographic Separation Process Based on Dynamic Fuzzy Neural Network and Moving Window Strategy

A novel dynamic model for the online prediction of rate of penetration and its industrial application to a drilling process

Accurate prediction of the rate of penetration (ROP) is a difficult issue in the drilling process, especially under complex formation conditions. Many methods, such as mechanism and machine learning, were introduced to investigate it. However, most of them are offline prediction methods which may not be capable of capturing the online trend of ROP. In this paper, a novel dynamic model for ROP prediction is proposed considering the process characteristics, which consists of three stages. In the first stage, the correlations between ROP and eight drilling parameters are analyzed, and the rotational speed, weight on bit, depth are selected as the model inputs. In the second stage, the drilling data are pre-processed by using the filtering and re-sampling techniques. In the last stage, the moving window strategy, extreme learning machine, and 10-fold cross validation are used to establish the ROP model. Our main idea of online prediction of ROP lies in this last stage. Specifically, two steps (modeling and prediction) are executed alternately in the moving drilling depth windows so as to predict the ROP more accurately. Finally, the proposed ROP prediction model is applied to the drilling well ZK3 in Xiangyang area, Central China. The prediction accuracy is improved by at least 7% compared with seven well-known ROP prediction methods, two online and five offline, which validates the effectiveness of the proposed method. It is believed that the proposed model provides a basis for intelligent optimization control in drilling process.

Natural visibility encoding for time series and its application in stock trend prediction

As a newly developed method, the natural visibility graph (NVG) has attracted great attention. Most of the previous research focuses on exploring the time series using the NVG from the angle of the complex network while few efforts have been paid to the degree sequence of the NVG. Recently, two studies indicate that the degree sequence of the horizontal visibility graph (HVG) represents the local motif information of the time series and utilize it to classify time series. Though the performance of the HVG-based classification algorithm is not satisfying, we would like to further explore whether the degree sequence of the NVG could be utilized in practical applications. Hence, we propose the concept of natural visibility encoding for the time series to extract the motif information from the time series through the NVG transformation. To obtain the local motif information from the whole time series, a moving window encoding strategy is also developed. The stock trend prediction (STP) problem is selected as the application area and a universal STP framework is proposed based on the natural visibility encoding and the moving window strategy. By conducting three experiments with over twenty baseline algorithms and the ablation study, the validation, effectiveness, and robustness of the proposed framework are proven. The success of the proposed framework suggests that the degree sequence of the NVG transformation could provide useful information for practical usage. We hope our work could inspire further efforts on investigating the degree sequence of the NVG transformation in the dimension of time.

Performance evaluation of the Bühlmann credibility approach in predicting mortality rates

Modeling mortality is an important thing for insurance company in determining the appropriate premium for a policy holder. This paper explains the Bühlmann credibility approach for modeling mortality. Bühlmann’s credibility model is generally used to predict the value of a random variable in the next future period. In predicting the value of a random variable in the next two or more future periods, an approach is needed. In this paper, the Bühlmann credibility approach is done through 2 strategies: the expanding window strategy and the moving window strategy. The expanding window strategy is done by adding the predicted value to the data to produce a predicted value in the following year while the moving window strategy is done by adding the predicted value to the data and discarding the oldest data to produce a predicted value in the following year. Mortality prediction performances from the Bühlmann credibility approach are being analysed by comparing the values of AAMAPE and the reduction ratio of the Bühlmann credibility approach to the Lee-Carter model. From this paper, it was found that the Bühlmann credibility approach produced better mortality predictions compared to the Lee-Carter model in case of Australian mortality data.

A new crude oil price forecasting model based on variational mode decomposition

Crude oil price prediction helps to get a better understanding of the global economic situation. Recently, variational mode decomposition (VMD) is introduced into the field of crude oil price forecasting. However, there is a lack of general selection rule for VMD-parameter and the widely adopted one-time decomposition strategy seems not suitable for practical application. Thus, an improved signal-energy based (ISE) rule is proposed as an improvement of the existing signal-energy based (SE) rule for the VMD-parameter selection. The moving-window strategy is put forward as a supplement for the decomposition strategy. Finally, a prediction model (VMD-LSTM-MW model) is built by combining the VMD, the long short-term memory (LSTM) network, and the moving-window strategy. The effectiveness of the ISE rule, the validity of the moving-window strategy, and the superiority of the VMD-LSTM-MW model are demonstrated by conducting monthly and daily crude oil price prediction experiments.

An Improved Spatiotemporal Data Fusion Method Using Surface Heterogeneity Information Based on ESTARFM

The use of the spatiotemporal data fusion method as an effective data interpolation method has received extensive attention in remote sensing (RS) academia. The enhanced spatial and temporal adaptive reflectance fusion model (ESTARFM) is one of the most famous spatiotemporal data fusion methods, as it is widely used to generate synthetic data. However, the ESTARFM algorithm uses moving windows with a fixed size to get the information around the central pixel, which hampers the efficiency and precision of spatiotemporal data fusion. In this paper, a modified ESTARFM data fusion algorithm that integrated the surface spatial information via a statistical method was developed. In the modified algorithm, the local variance of pixels around the central one was used as an index to adaptively determine the window size. Satellite images from two regions were acquired by employing the ESTARFM and modified algorithm. Results showed that the images predicted using the modified algorithm obtained more details than ESTARFM, as the frequency of pixels with the absolute difference of mean value of six bands’ reflectance between true observed image and predicted between 0 and 0.04 were 78% by ESTARFM and 85% by modified algorithm, respectively. In addition, the efficiency of the modified algorithm improved and the verification test showed the robustness of the modified algorithm. These promising results demonstrated the superiority of the modified algorithm to provide synthetic images compared with ESTARFM. Our research enriches the spatiotemporal data fusion method, and the automatic selection of moving window strategy lays the foundation of automatic processing of spatiotemporal data fusion on a large scale.

Density peaks clustering‐based steady/transition mode identification and monitoring of multimode processes

AbstractMultimode is the characteristic of industrial manufacturing processes due to different production strategies and environments. For multimode process monitoring, it is a challenge to identify different steady modes and transition modes. In this paper, a k nearest neighbours (KNN)‐based density peaks clustering (DPC) method is applied to identify different modes. First, the local density of each sample, which is obtained with a KNN constraint and its minimum distance to the higher local density points are calculated as two indicators of the DPC algorithm to find the cluster centres of the training data. Then, the transition modes are identified by combining the moving window strategy and the DPC algorithm, where an index called the local density‐distance ratio (LDDR) is employed. Finally, the monitoring algorithm is used to detect the faults for each operation mode. The effectiveness and advantages of the proposed method are illustrated by a numerical example and a Tennessee Eastman (TE) benchmark process.

Adaptive Hybrid Soft-Sensor Model of Grinding Process Based on Regularized Extreme Learning Machine and Least Squares Support Vector Machine Optimized by Golden Sine Harris Hawk Optimization Algorithm

Soft-sensor technology plays a vital role in tracking and monitoring the key production indicators of the grinding and classifying process. Least squares support vector machine (LSSVM), as a soft-sensor model with strong generalization ability, can be used to predict key production indicators in complex grinding processes. The traditional crossvalidation method cannot obtain the ideal structure parameters of LSSVM. In order to improve the prediction accuracy of LSSVM, a golden sine Harris Hawk optimization (GSHHO) algorithm was proposed to optimize the structure parameters of LSSVM models with linear kernel, sigmoid kernel, polynomial kernel, and radial basis kernel, and the influences of GSHHO algorithm on the prediction accuracy under these LSSVM models were studied. In order to deal with the problem that the prediction accuracy of the model decreases due to changes of industrial status, this paper adopts moving window (MW) strategy to adaptively revise the LSSVM (MW-LSSVM), which greatly improves the prediction accuracy of the LSSVM. The prediction accuracy of the regularized extreme learning machine with MW strategy (MW-RELM) is higher than that of MW-LSSVM at some moments. Based on the training errors of LSSVM and RELM within the window, this paper proposes an adaptive hybrid soft-sensing model that switches between LSSVM and RELM. Compared with the previous MW-LSSVM, MW-neural network trained with extended Kalman filter(MW-KNN), and MW-RELM, the prediction accuracy of the hybrid model is further improved. Simulation results show that the proposed hybrid adaptive soft-sensor model has good generalization ability and prediction accuracy.

Defect Detection in Composite Products Based on Sparse Moving Window Principal Component Thermography

As a nondestructive testing (NDT) technology, pulsed thermography (PT) has been widely used in the defect detection of the composite products due to its efficiency and large detection range. To enhance the distinction between defective and defect-free region and eliminate the influence of the measurement noise and nonuniform background of the thermal image generated by PT, a number of thermographic data analysis approaches have been proposed. However, these traditional methods only consider the correlations among the pixel while leave the time series correlations unmodeled. In this paper, a sparse moving window principal component thermography (SMWPCT) method is proposed to incorporate several thermal images using the moving window strategy. Also, the sparse trick is used to provide clearer and more interpretable results because of the structure sparsity. The effectiveness of the method is verified by the defect detection experiment of carbon fiber-reinforced plastic specimens.

The Online Soft Computing Models of key variables based on the Boundary Forest method

The Online Soft Computing Models (OSCMs) based on ensemble methods are novel and quite effective data-driven tools for predicting key variables. The current challenge encountered by them is how to enhance the reliability caused by both the uncertainty from noise and the unsuitable specifications of models, on the premise of high predicting accuracy and low computational cost. To meet the current challenge, the OSCM based on the Boundary Forest (OSCM-BF) is proposed in this paper. The BF combines a set of the Tree-Structure Ensemble (TSE) models. In terms of the different values of θ (i.e., the minimum size of leaf nodes), the BF enhances the reliability of a single TSE not only by overlapping the gap segments of output range (i.e., connecting the discontinuous boundaries of leaf nodes), but also by possessing stronger robustness via producing enough diversity. Moreover, a theoretical range of the value of θ constructed by BF is provided. Since the simplicity, the nice interpretability and the flexibility on large-scale data, the moving-window strategy was adopted to realize the update of the BF models. The experiments on the noisy data from the industrial process of Ladle Furnace reveal that the OSCM-BF can enhance the reliability of the OSCM-TSE on the premise of high predicting accuracy and low computational cost.

Real Time Motion Generation for Mobile Robot

Abstract The paper proposes a new real time motion generation technique for a mobile robot, which is able to find time-optimal motions along a curved path taking into account capabilities of the driving motors and ensuring the wheels rolling without skidding. The problem is converted to a time-optimal control of a second-order dynamic system under constraints on the control input, the first derivative of output, and mixed constraint on the control variable and the output derivative. After the state space discretization, the original problem is presented as a combinatorial one where the desired robot trajectory corresponds to a shortest path on the relevant graph. To find this path and ensure its real time implementation, a moving window strategy combined with dynamic programming is proposed. Advantages of this approach and its suitability to real time control are illustrated by a case study dealing the fastest motion of the mobile robot along a sinusoidal path.