Search

Most of the recent image segmentation methods have tried to achieve the utmost segmentation results using large-scale pixel-level annotated data sets. However, obtaining these pixel-level annotated training data is usually tedious and expensive. In this work, we address the task of semisupervised semantic segmentation, which reduces the need for large numbers of pixel-level annotated images. We propose a method for semisupervised semantic segmentation by improving the confidence of the predicted class probability map via two parts. First, we build an adversarial framework that regards the segmentation network as the generator and uses a fully convolutional network as the discriminator. The adversarial learning makes the prediction class probability closer to 1. Second, the information entropy of the predicted class probability map is computed to represent the unpredictability of the segmentation prediction. Then, we infer the label-error map of the segmentation prediction and minimize the uncertainty on misclassified regions for unlabeled images. In contrast to existing semisupervised and weakly supervised semantic segmentation methods, the proposed method results in more confident predictions by focusing on the misclassified regions, especially the boundary regions. Our experimental results on the PASCAL VOC 2012 and PASCAL-CONTEXT data sets show that the proposed method achieves competitive segmentation performance.

Most existing studies performed video denoising by using multiple adjacent noisy frames to recover one clean frame; however, despite achieving relatively good quality for each individual frame, these approaches may result in visual flickering when the denoised frames are considered in sequence. In this paper, instead of separately restoring each clean frame, we propose a multiframe-to-multiframe (MM) denoising scheme that simultaneously recovers multiple clean frames from consecutive noisy frames. The proposed MM denoising scheme uses a training strategy that optimizes the denoised video from both the spatial and temporal dimensions, enabling better temporal consistency in the denoised video. Furthermore, we present an MM network (MMNet), which adopts a spatiotemporal convolutional architecture that considers both the interframe similarity and single-frame characteristics. Benefiting from the underlying parallel mechanism of the MM denoising scheme, MMNet achieves a highly competitive denoising efficiency. Extensive analyses and experiments demonstrate that MMNet outperforms the state-of-the-art video denoising methods, yielding temporal consistency improvements of at least 13.3% and running more than 2 times faster than the other methods.

The latest research in the field of recognition of image characters has led to various developments in the modern technological works for the improvement of recognition rate and precision. This technology is significant in the field of character recognition, business card recognition, document recognition, vehicle license plate recognition etc. for smart city planning, thus its effectiveness should be improved. In order to improve the accuracy of image text recognition effectively, this article uses canny algorithm to process edge detection of text, and k-means algorithm for cluster pixel recognition. This unique combination combined with maximally stable extremal region and optimization of stroke width for image text yields better results in terms of recognition rate, recall, precision, F-score and accuracy. The results show that the correct recognition rate is 88.3% and 72.4% respectively with an accuracy value of 90.5% for the proposed method. This algorithm has high image text recognition rate, can recognize images taken in complex environment, and has good noise removal function. It is significantly an optimal algorithm for image text recognition.

Phase-shifting profilometry (PSP) via sequential fringe projection is applicable for high-accuracy 3-D measurements of static objects. However, moving objects cannot be static or quasi-static during one projection cycle, thereby causing surface misalignment and phase errors in 3-D measurements. This article proposes a motion-estimated PSP based on the fringe-oriented synthetic phase correlation algorithm (FO-SPCA), which achieves automatic 3-D measurements of objects in nonuniform 2-D motion. To robustly estimate the motion of objects among fringe images, the proposed fringe-oriented feature extraction technique obtains the surface features by eliminating the modulation influence of sinusoidal illumination. Furthermore, the FO-SPCA is developed to accurately detect the subpixel displacements of moving objects according to object surface features. With the subpixel displacements, the alignment procedure is completed through a reverse 2-D transformation and then the phase errors are compensated accordingly. The simulation and experimental results verify the feasibility and robustness of the motion-estimated PSP for the in situ 3-D measurements of nonuniform moving objects.

Codewords used to determine fringe orders are significant for absolute phase retrieval based on the phase-coding method. However, because of inevitable interference from image blurring, image noise, and system nonlinearity, it is challenging to significantly increase the number of codewords for high-accuracy phase retrieval. To address this challenge, this article proposes a joint coding strategy to perform the coding of high-density stripes. More specifically, codewords are simultaneously embedded into the phase domain and the intensity domain of composite fringe patterns, which greatly extends the encoding range of valid codewords. Moreover, to improve the anti-interference capability of the proposed coding strategy, a regional correction technique (RCT) is presented to remove jump phase errors induced by the inevitable interference. The results of experiments indicate that the proposed method is effective and accurate for both complex objects and a standard sphere.

Automatic defect classification in photovoltaic (PV) modules is gaining significant attention due to the limited application of manual/visual inspection. However, the automatic classification of defects in crystalline silicon solar cells is a challenging task due to the inhomogeneous intensity of cell cracks and complex background. The present study is carried out for automatic defects classification of PV cells in electroluminescence images. Two machine learning approaches, features extraction-based support vector machine (SVM) and convolutional neural network (CNN) are used for the solar cell defect classifications. Suitable hyperparameters, algorithm optimisers, and loss functions are used to achieve the best performance. Solar cell defects are divided into seven classes such as one non-defective and six defective classes. Feature extraction algorithms such as histograms of oriented gradients (HOG), KAZE, Scale-Invariant Feature Transform (SIFT) and speeded-up-robust features (SURF) are used to train the SVM classifier. Finally, the performance results are compared. It is concluded that CNN's accuracy for solar cell defect classification is 91.58% which outperforms the state-of-the-art methods. With features extraction-based SVM, accuracies of 69.95, 71.04, 68.90, and 72.74% are obtained for HOG, KAZE, SIFT, and SURF, respectively. The present study may contribute to making a PV system more efficient for classifying defects to improve the power system efficiency.

In this paper, a more effective Gaussian denoiser is designed to enhance the resulting image quality. We propose a novel image denoising method using a multiscale dilated residual network, named MDRNet. The proposed method is based on two main strategies. First, we adopt dilated convolutions in our network to enlarge the receptive field while requiring fewer parameters. The hybrid dilation rate pattern (HDP) is implemented such that each pixel in the pattern contributes similarly to the receptive field, allowing our network to learn the image details equally. Second, we employ a contextualized structure to take advantage of the low-level features which are mainly concentrated in the first two layers. Our method achieves competitive denoising performance and requires fewer parameters compared to existing denoising methods that using convolutional network. Through comprehensive experiments, we show that the denoising performance of our method is competitive with the state-of-the-art methods in terms of both quantitative and qualitative evaluation.

With the rising use of photovoltaic and ongoing installation of large-scale photovoltaic systems worldwide, the automation of photovoltaic monitoring methods becomes important, as manual/visual inspection has limited applications. This research work deals with automatic detection of photovoltaic module defects in Infrared images with isolated deep learning and develop-model transfer deep learning techniques. An Infrared images dataset containing infrared images of normal operating and defective modules is collected and used to train the networks. The dataset is obtained from Infrared imaging performed on normal operating and defective photovoltaic modules with lab induced defects. An isolated learned model is trained from scratch using a light convolutional neural network design that achieved an average accuracy of 98.67%. For transfer learning, a base model is first developed (pre-trained) from electroluminescence images dataset of photovoltaic cells and then fine-tuned on infrared images dataset, that achieved an average accuracy of 99.23%. Both frameworks require low computation power and less time; and can be implemented with ordinary hardware. They also maintained real time prediction speed. The comparison shows that the develop-model transfer learning technique can help to improve the performance. In addition, we reviewed different kind of defects detectable from infrared imaging of photovoltaic modules, that can help in manual labelling for identifying different defect categories upon access to new huge data in future studies. Last of all, the presented frameworks are applied for experimental testing and qualitative evaluation.

The uncertainty in the output power of the photovoltaic (PV) power generation station due to variation in meteorological parameters is of serious concern. An accurate output power predictio...

Fault diagnosis in rolling bearings is an indispensable part of maintaining the normal operation of modern machinery, especially under the varying operating conditions. In this paper, an end-to-end adaptive anti-noise neural network framework (AAnNet) is proposed to solve the bearing fault diagnosis problem under heavy noise and varying load conditions, which takes the raw signal as input without requiring manual feature selection or denoising procedures. The proposed AAnNet employs the random sampling strategy and enhanced convolutional neural networks with the exponential linear unit as the activation function to increase the adaptability of the neural network. Moreover, the gated recurrent neural networks with attention mechanism improvement are further adopted to learn and classify the features processed by the convolutional neural networks part. Besides, we try to explain how the network works by visualizing the intrinsic features of the proposed framework. And we explore the effect of the attention mechanism in the proposed framework. Experiments show that the proposed framework achieves state-of-the-art results on two datasets under varying operating conditions.

This With the development of science and technology, the impact of the ionosphere on satellite navigation, radio communication, broadcasting, space exploration and other human activities is more and more significant, the application of radar to the ionosphere detection technology is also more and more important. In this paper, the main development course of radar is introduced briefly, the composition and working principle of radar are expounded, and the digital signal processing of radar is analyzed and studied emphatically.

Feature extraction and feature selection are vital steps to construct an intelligent diagnosis system for classifying the weld flaws from an X-ray image. Deep learning has been successfully used in image analysis and automatic object recognition. It has good performance for learning more representative hierarchical features that are more sensitive to classification. However, there are still few applications of deep learning in feature learning for classifying different weld flaws, and few studies have been performed to compare the feature classification ability of different feature extraction methods. In this paper, we developed a model based on a deep convolutional neural network (DCNN) to extract the deep features directly from X-ray images. To validate the effectiveness of deep features, we cropped patches from the X-ray images as the learning dataset. Furthermore, considering the imbalance of the number of patches with different weld flaws, we used 3 types of resampling methods for 3 balanced datasets. Using the datasets, we compared the classification ability of 5 types of features extracted using traditional methods and deep learning. The best results were obtained for the deep features from the proposed DCNN model, achieving an accuracy of 97.2%, which is considerably higher than that obtained using the traditional feature extraction methods. We believe that the proposed model could be used to help workers evaluate X-ray images more intelligently.

Low-light image is easily degraded by real noise, which brings great challenges for image enhancement task because the enhancement process will amplify the noise. To address this problem, we propose an amplified noise map guided network (AMG-Net), which simultaneously achieves the low-light enhancement and noise removal by extracting amplified noise map to guide the network training. Specifically, we build an encoder-decoder network as the basic enhancement model to get a preliminary enhanced image that usually includes amplified noise. Subsequently, we fed the preliminary enhanced image into a noise map estimator to continuously estimating the amplified noise map during the enhancement process by adopting residual connection. Finally, a residual block with adaptive instance normalization (AIN) is used to build a denoising model, which is guided by the noise map estimator to remove the amplified noise. Extensive experimental results demonstrate that the proposed AMG-Net can achieve competitive results compared with the existing state-of-the-art methods.

In a typical digital fringe projection (DFP) system, the shadows in the fringe images cause errors in the phase map. We propose a novel discriminative repair approach to remove the shadow-induced error in the phase map. The proposed approach first classifies the shadow area in the phase map obtained by the DFP into two categories: valid shadow area and invalid shadow area. Then the valid shadow area is repaired by a proposed neighboring information fusion phase estimation (NIFPE) method, which fuses the phase gradient into the result of kernel density estimation (KDE) through the Kalman filter (KF) algorithm. The invalid shadow area is repaired by a proposed background phase matching (BPM) method. The experimental results demonstrate that the shadow-induced error in the phase map can be removed, which verifies the effectiveness of the proposed approach.

This study proposes an improved extended state observer (ESO) to eliminate the effects of disturbances on the speed control system of an aerial camera lateral swing. First, a mechatronics model of ...

Based on the study of RBS algorithm in wireless sensor network, an improved algorithm named RBRS is presented, to solve the time synchronization problem of multi hop networks. On the basis of RBS, the broadcast group and least square linear regression methods were used to realize entire network time synchronization in the algorithm. Synchronization error and overhead with the existing improved BRS are compared in the article. The result shows that the algorithm has certain superiority in many algorithms, which is suitable for light and low power consumption network load. Through an emulation with the matlab software, the result indicates that error accumulation is lower in the optimized algorithm, the synchronization overhead is significantly reduced and can realize the time synchronization of the whole network. A time synchronization algorithm based on RBRS algorithm is proposed for multi-hop and the low power consumption. A variable period synchronization method is introduces in the algorithm: in line with Bias maximum a posterior estimation principle, the maximum phase offset is estimated to determine the synchronization period, which can reduce the number of node synchronization, and with the least square linear regression method, the periodic fitting clock offset. The Simulation in matlab indicate that RBRS algorithm can improve the synchronization accuracy and reduce energy consumption significantly, which is conducive to extend the life of the network.

Arbitrary two-dimensional (2-D) motion introduces coordinate errors and phase errors to three-dimensional (3-D) shape measurement of objects in phase-shifting profilometry (PSP). This paper presents a new robust 3-D reconstruction method for arbitrary 2-D moving objects by introducing an adaptive reference phase map and the motion estimation based on fence image. First, a composite fence image is used to track object motion. Second, to obtain the transformation matrixes and remove the coordinate errors among object images, the angle extraction technique and the 1-D hybrid phase correlation method (1-D HPCM) are integrated to automatically estimate the sub-pixel motion of objects. Third, the phase errors are compensated to obtain the rough absolute phase map of objects by combining the transformation matrixes with the reference phase map. Finally, the absolute phase map is refined to reconstruct the 3-D surfaces of moving objects with adaptive reference phase map. The proposed computational framework can accurately and automatically realize 3-D shape measurement of arbitrary objects with 2-D movement. The results of experiment verify the effectiveness of our computational framework.

The precise estimation State of Charge (SOC) becomes great significance for Bettery Balancing Charge and Discharge Mangement (BBCDM). In this paper, aimed at this challenge, one hybrid methodology for estimating the State of Charge(SOC) of Lithium-ion Battery(LIB) is presented adopting Extended Kalman Filter (EKF) as well as combine with Recursive Lest Square(RLS). Fist, the mathematical model is estimated including the experimental data acquisition with an Open Circuit Voltage (OCV) method is presented. Second, a hybrid strategy with EKF and RLS was adopted to describe state space equation and identify model parameters during the LIB charge/discharge test. Finally, estimation of SOC adopt proposed method revealing dynamic characteristics of LIB. The simulation results have shown the effectiveness of the new methodology and better accuracy and data maintenance ability.

The quality of ground surface pregrouting (GSPG) is commonly qualitatively evaluated using single factor; however, the quality evaluation involves numerous facets, and a quantitative evaluation is rare. The aim of this study was to quantitatively evaluate the quality of a GSPG based on three aspects. The fuzzy analytic hierarchy process (FAHP) was adopted to obtain the final score and quality classification of the GSPG. Based on three aspects, namely, integrity, continuity, and sturdiness, a series of field tests was also conducted, qualitatively evaluating the quality of the GSPG preliminary, to obtain the required test data and verify the FAHP results. The results of the FAHP showed that the quality of the GSPG was 86.42, which could be classified as “Good”, whereas the field tests exhibited that the GSPG was effective, thereby verifying that the FAHP was reliable. In addition, the proposed method provided a detailed comprehension of the quality evaluation of GSPG and a frame of reference for analogous engineering.

It is essential to enhance the ability of wind speeds forecasting for wind energy and wind resource planning. For this purpose, a hybrid strategy has been proposed based on spatio-temporal covariance model which combined the spatio-temporal ordinary kriging (STOK) technology with autoregressive integrated moving average (ARIMA) regression smoothing method. This is because wind speed time series exhibits a long-term dependency. In the case study, both STOK method and ARIMA method are employed and their performances are compared. The ARIMA model can obtain a necessary and sufficient smoothing condition for them to be smoothed. Meanwhile, further theoretical analysis is provided to discuss why the STOK method is potentially more accurate than the ARIMA method for wind speed time series prediction. Results show that the proposed method outperforms the Non-Sep-Gneiting model by 9% and 7.2% in terms of mean absolute error (MAE) and root-mean-square error (RMSE).

Short-term wind speed prediction is an essential task for wind resource and wind energy planning. However, most of this literature does not take into account the spatio-termporal correlation of wind data from the geographical field. For this reason, we propose an integrated spatio-temporal kriging and functional kriging strategy to exploit such spatio-temporal correlation into the wind speed prediction. First, the deterministic trend component in wind data is estimated to be removed. The residuals are used for spatio-temporal modeling and prediction. Based on the spatio-temporal kriging framework, four spatio-temporal covariance models (product-sum model, separable exponential product model, separable and nonseparable Gneiting models) are considered which describe the spatio-temporal correlation of wind data. In particular, the flexibility of using the nonseparable Gneiting model is highlighted. More specifically, four spatio-temporal random fields are modeled from the 12 wind monitoring stations over Ireland. We also use an involved weighted least squares method for estimating parameters of the four covariance models involved in the spatio-temporal kriging strategy. We apply the fitted covariance models to generate day-ahead wind speed predictions at both observed and nonobserved locations where wind station already exist but also to nearby locations. Leave-one-out cross-validation is applied to check the significance of the difference among the four models, these spatio-temporal ordinary kriging (STOK), functional ordinary kriging (FOK) and autoregressive integrated moving average (ARIMA) methods are compared for day-ahead wind speed predictions. Forecasting results indicate that the predicting accuracy is improved almost 33.5% using FOK compared with three approaches which confirm the effectiveness of the functional kriging method in the paper.

Accurate wind speed prediction plays an important role in the planning and development of wind power plant. Wind speed prediction can reduce the impact of wind power grid connection and improve the control of wind power systems. In this study, wind speed is considered as a geographical variable. We firstly used exploratory methods to examine the spatio-temporal dependence on wind field. The variogram was taken into account in analysing the spatial structure in the rectangular grid. Then the exponential model was adopted to fit the anisotropic feature of variogram. The de-trended data have been computed by using a geostatistical kriging estimator. The results were compared with the leave-one-out cross-validation (LOOCV) method. The accuracy of the proposed method was verified to obtain the best estimated results.

Pixel-by-pixel phase unwrapping (PPU) has been employed to rapidly achieve three-dimensional (3-D) shape measurement without additional projection patterns. However, the maximum measurement depth range that traditional PPU can handle is within 2π in phase domain; thus PPU fails to measure the dynamic object surface when the object moves in a large depth range. In this paper, we propose a novel adaptive pixel-by-pixel phase unwrapping (APPU), which extends PPU to an unlimited depth range. First, with PPU, temporary phase maps of objects are obtained referring to the absolute phase map of a background plane. Second, we quantify the difference between the image edges of the temporary phase maps and the practical depth edges of dynamic objects. Moreover, according to the degree of the edge difference, the temporary phase maps are categorized into two classes: failed phase maps and relative phase maps. Third, by combining a mobile reference phase map and the edge difference quantization technique, the failed phase maps are correspondently converted into relative phase maps. Finally, the relative phase maps are innovatively transformed into the absolute phase maps using a new shadow-informed depth estimation method (SDEM). The proposed approach is suitable for high-speed 3-D shape measurement without depth limitations or additional projection patterns.

Automatic defect detection is gaining huge importance in photovoltaic (PV) field due to limited application of manual/visual inspection and rising production quantities of PV modules. This study is conducted for automatic detection of PV module defects in electroluminescence (EL) images. We presented a novel approach using light convolutional neural network architecture for recognizing defects in EL images which achieves state of the art results of 93.02% on solar cell dataset of EL images. It requires less computational power and time. It can work on an ordinary CPU computer while maintaining real time speed. It takes only 8.07 ms for predicting one image. For proposing light architecture, we perform extensive experimentation on series of architectures. Moreover, we evaluate data augmentation operations to deal with data scarcity. Overfitting appears a significant problem; thus, we adopt appropriate strategies to generalize model. The impact of each strategy is presented. In addition, cracking patterns and defects that can appear in EL images are reviewed; which will help to label new images appropriately for predicting specific defect types upon availability of large data. The proposed framework is experimentally applied in lab and can help for automatic defect detection in field and industry.

Sparse component analysis (SCA) has been widely used for blind source separation(BSS) for many years. Recently, SCA has been applied to operational modal analysis (OMA), which is also known as output-only modal identification. This paper considers the sparsity of sources’ time-frequency (TF) representation and proposes a new TF-domain SCA under the OMA framework. First, the measurements from the sensors are transformed to the TF domain to get a sparse representation. Then, single-source-points (SSPs) are detected to better reveal the hyperlines which correspond to the columns of the mixing matrix. The K-hyperline clustering algorithm is used to identify the direction vectors of the hyperlines and then the mixing matrix is calculated. Finally, basis pursuit de-noising technique is used to recover the modal responses, from which the modal parameters are computed. The proposed method is valid even if the number of active modes exceed the number of sensors. Numerical simulation and experimental verification demonstrate the good performance of the proposed method.

This note reports an efficient singular value decomposition (SVD)-based vibration extraction approach that recovers sound information in silent high-speed video. A high-speed camera of which frame rates are in the range of 2 kHz–10 kHz is applied to film the vibrating objects. Sub-images cut from video frames are transformed into column vectors and then reconstructed to a new matrix. The SVD of the new matrix produces orthonormal image bases (OIBs) and image projections onto specific OIB can be recovered as understandable acoustical signals. Standard frequencies of 256 Hz and 512 Hz tuning forks are extracted offline from their vibrating surfaces and a 3.35 s speech signal is recovered online from a piece of paper that is stimulated by sound waves within 1 min.

In order to extract the maximum power from PV system, the maximum power point tracking (MPPT) technology has always been applied in PV system. At present, various MPPT control methods have been presented. The perturb and observe (P&O) and conductance increment methods are the most popular and widely used under the constant irradiance. However, these methods exhibit fluctuations among the maximum power point (MPP). In addition, the changes of the environmental parameters, such as cloud cover, plant shelter, and the building block, will lead to the radiation change and then have a direct effect on the location of MPP. In this paper, a feasible MPPT method is proposed to adapt to the variation of the irradiance. This work applies the glowworm swarm optimization (GSO) algorithm to determine the optimal value of a reference voltage in the PV system. The performance of the proposed GSO algorithm is evaluated by comparing it with the conventional P&O method in terms of tracking speed and accuracy by utilizing MATLAB/SIMULINK. The simulation results demonstrate that the tracking capability of the GSO algorithm is superior to that of the traditional P&O algorithm, particularly under low radiance and sudden mutation irradiance conditions.

This paper proposed a novel in-plane displacement field measurement algorithm using an optical flow strategy. We built a linear illumination model between images before and after deformation to guarantee intensity invariability. We used image upsampling and a reliability-guided strategy to find the matching points accurate to 0.5 pixels in the reference and deformed images. The criterion to determine the reliability is zero-mean normalized cross-correlation coefficient. Afterward, we used the brightness constancy constraint combined with Lucas-Kanade optical flow constraint in a specific image region to obtain an overdetermined linear equation. We applied the noniterative least-squares algorithm to solve the equations and to achieve the displacement offsets. This research utilized multithread calculation to handle the complete cracking applications. We estimated the computing efficiency and calculation precision of the proposed method through a series of experimental speckle patterns. All results demonstrated the correctness, effectiveness, and robustness of the proposed method.

In this paper, we propose an automatic detection schema including three stages for weld defects in x-ray images. Firstly, the preprocessing procedure for the image is implemented to locate the weld region; Then a classification model which is trained and tested by the patches cropped from x-ray images is constructed based on deep neural network. And this model can learn the intrinsic feature of images without extra calculation; Finally, the sliding-window approach is utilized to detect the whole images based on the trained model. In order to evaluate the performance of the model, we carry out several experiments. The results demonstrate that the classification model we proposed is effective in the detection of welded joints quality.

In this study, a high-speed camera system is developed to complete the vibration measurement in real time and to overcome the mass introduced by conventional contact measurements. The proposed system consists of a notebook computer and a high-speed camera which can capture the images as many as 1000 frames per second. In order to process the captured images in the computer, the normalized cross-correlation (NCC) template tracking algorithm with subpixel accuracy is introduced. Additionally, a modified local search algorithm based on the NCC is proposed to reduce the computation time and to increase efficiency significantly. The modified algorithm can rapidly accomplish one displacement extraction 10 times faster than the traditional template matching without installing any target panel onto the structures. Two experiments were carried out under laboratory and outdoor conditions to validate the accuracy and efficiency of the system performance in practice. The results demonstrated the high accuracy and efficiency of the camera system in extracting vibrating signals.

High-speed cameras provide full field measurement of structure motions and have been applied in nondestructive testing and noncontact structure monitoring. Recently, a phase-based method has been proposed to extract sound-induced vibrations from phase variations in videos, and this method provides insights into the study of remote sound surveillance and material analysis. An efficient singular value decomposition (SVD)-based approach is introduced to detect sound-induced subtle motions from pixel intensities in silent high-speed videos. A high-speed camera is initially applied to capture a video of the vibrating objects stimulated by sound fluctuations. Then, subimages collected from a small region on the captured video are reshaped into vectors and reconstructed to form a matrix. Orthonormal image bases (OIBs) are obtained from the SVD of the matrix; available vibration signal can then be obtained by projecting subsequent subimages onto specific OIBs. A simulation test is initiated to validate the effectiveness and efficiency of the proposed method. Two experiments are conducted to demonstrate the potential applications in sound recovery and material analysis. Results show that the proposed method efficiently detects subtle motions from the video.

The pitching axis of a satellite camera is controlled under the weightless environment. A novel active disturbance rejection controller is designed to eliminate the influences of the pitching axis. The novel active disturbance rejection controller is designed based on a new nonlinear function, and thus, this function is first established. The function exhibits better continuity and smoothness than previously available functions, hence, it can effectively improve the high-frequency flutter phenomenon. Therefore, the novel active disturbance rejection controller based on the new nonlinear function can eliminate disturbances of the pitching axis. The novel active disturbance rejection controller is composed of a tracking differentiator, a novel extended state observer, and a novel nonlinear state error feedback. The tracking differentiator is used to arrange the transient process. Nonlinear dynamics, model uncertainty, and external disturbances are extended to a new state. The novel extended state observer is utilized to observe this state. The overtime variation of the system can be predicted and compensated using the novel extended state observer. The novel nonlinear state error feedback is adopted to restrain the residual errors of the system. Finally, simulation experiments are performed, and results show that the novel active disturbance rejection controller exhibits better performance than the traditional active disturbance rejection controller.

The development of image sensors and optics lenses has contributed to the rapidly increasing use of vision-based methods as noncontact measurement methods in many areas. A high-speed camera system is developed to realize the displacement measurement in real time. Conventional visual measurement algorithms are commonly subjected to various shortcomings, such as complex processes, multiparameter adjustments, or integer-pixel accuracy. Inspired from the combination of block-matching algorithm and simplified optical flow, a motion estimation algorithm that uses modified Taylor approximation is proposed and applied to the vision sensor system. Simplifying integer-pixel searching with a rounding-iterative operation enables the modified algorithm to rapidly accomplish one displacement extraction within 1 ms and yield satisfactory subpixel accuracy. The performance of the vision sensor is evaluated through a simulation test and two experiments on a grating ruler motion platform and a steering wheel system of a forklift. Experimental results show that the developed vision sensor can extract accurate displacement signals and accomplish the vibration measurement of engineering structures.

Rotational angle and speed are important parameters for condition monitoring and fault diagnosis of rotating machineries, and their measurement is useful in precision machining and early warning of faults. In this study, a novel vision-based measurement algorithm is proposed to complete this task. A high-speed camera is first used to capture the video of the rotational object. To extract the rotational angle, the template-based Lucas-Kanade algorithm is introduced to complete motion tracking by aligning the template image in the video sequence. Given the special case of nonplanar surface of the cylinder object, a nonlinear transformation is designed for modeling the rotation tracking. In spite of the unconventional and complex form, the transformation can realize angle extraction concisely with only one parameter. A simulation is then conducted to verify the tracking effect, and a practical tracking strategy is further proposed to track consecutively the video sequence. Based on the proposed algorithm, instantaneous rotational speed (IRS) can be measured accurately and efficiently. Finally, the effectiveness of the proposed algorithm is verified on a brushless direct current motor test rig through the comparison with results obtained by the microphone. Experimental results demonstrate that the proposed algorithm can extract accurately rotational angles and can measure IRS with the advantage of noncontact and effectiveness.

In this paper, an efficient control system development method based on real-time virtual hardware-in-the-loop simulation is presented. Instead of developing and testing control system after physical prototype is produced, it can be conducted immediately after concept of controlled system is designed by developing a pure software real-time simulator. In this simulator, all the hardware is virtual. The appearance and operation of these virtual hardware is programmed to imitate corresponding physical prototypes so as to implement real-time virtual hardware-in-the-loop simulation. So The control software and the control logic of control system can be developed quickly. And the source code is compatible with both the simulation platform and physical platform. Moreover, It's much easier and faster to debug and test the control logic in such a way. An example of a large and high-groove density ruling engine is provided to explain detail implementation of the proposed method.

This paper introduces a hybrid scheme that combines the advantages of grey relation analysis and rough sets for fault diagnosis. The introduced scheme starts with reduce superfluous attributes and quantitatively determine the relative importance of the attributes, and then grey correlation analysis is used to calculate the grey correlation degree of all the standard fault states with respect to the current state according to reduced attributes and their relative importance, so that the fault can be found. We develop a graphical user interface of the prototype based on Matlab7.1 to test the proposed method. The experimental results show that the hybrid scheme applied in this study performs well and lays the foundation for the intelligent fault diagnosis.

The problem of process planning is mapped into a path searching problem in a state space. Then an ant system based approach is adopted to optimize the process concerning workshop resource. Instead of using local pheromone, the adopted method uses global distance to guide the ants. A state is encoded by the currently selected machine and tool, the set-up direction, the finish level of machining, etc. The path evaluation function may be defined flexibly to reflect the conditions of real workshop. A prototype system is developed to prove the efficiency of the approach.

Failure can be prevented in time by prediction of equipment maintenance so as to promote reliability only if failures can be early predicted. Substantially, it can be boiled down to a pattern recognition problem. Recenty, support vector machine (SVM) becomes a hot technique in this area. When using SVM, how to simultaneously obtain the optimal feature subset and SVM parameters is a crucial problem. This study proposes a method for improving SVM performance in two aspects at one time: feature subset selection and parameter optimization. Fuzzy adaptive particle swarm optimization (FAPSO) is used to optimize both a feature subset and parameters of SVM simultaneously for predictive maintenance. Case analysis shows that this algorithm is scientific and efficient, and adapts to predictive maintenance management for any complicated equipment.