RESUMEN
Three dialkylthio benzo[1,2-b:4,5-b']dithiophene (S-BDT) based polymers have been developed using different accepting units to tune their bandgaps. The polymer:PC71BM solar cells achieved the highest power conversion efficiency (PCE) of 4.51% without any post-treatment (such as annealing and solvent additive) in conventional single-cell devices. Joint photophysical, electrical and computational studies on the polymer based solar cells revealed the considerable impact of molecular planarity on polymer design. The polymer:PC71BM devices processed with 1,8-diiodooctane for improving their morphology afforded an improved PCE value of 5.63%, with a Voc of 0.83, a Jsc of 10.24 mA cm(-2) and a FF of 66.3%.
RESUMEN
In order to help a surgeon to determine a proper canal filing cutting path in a hip replacement operation conveniently, this paper presents a kind of probe with combined structure. Firstly, the doctor can use this kind of combined probe to choose canal filing cutting path. Then, the doctor can use computer to guide the surgeon to file femoral cavity along the selected canal filing cutting path. Through hip replacement corpse experiments, filing effects and used time of using combined probe group and separate control group were analyzed. The experiment results showed that the methods introduced in this paper could lower the difficulty of hip replacement operations, improve the implantation of hip stem prostheses further, and reduce the incidence of surgical complications.
Asunto(s)
Artroplastia de Reemplazo de Cadera , Cirugía Asistida por Computador/instrumentación , Fémur , Prótesis de Cadera , HumanosRESUMEN
As an essential part of electronic component assembly, it is crucial to rapidly and accurately detect electronic components. Therefore, a lightweight electronic component detection method based on knowledge distillation is proposed in this study. First, a lightweight student model was constructed. Then, we consider issues like the teacher and student's differing expressions. A knowledge distillation method based on the combination of feature and channel is proposed to learn the teacher's rich class-related and inter-class difference features. Finally, comparative experiments were analyzed for the dataset. The results show that the student model Params (13.32 M) are reduced by 55%, and FLOPs (28.7 GMac) are reduced by 35% compared to the teacher model. The knowledge distillation method based on the combination of feature and channel improves the student model's mAP by 3.91% and 1.13% on the Pascal VOC and electronic components detection datasets, respectively. As a result of the knowledge distillation, the constructed student model strikes a superior balance between model precision and complexity, allowing for fast and accurate detection of electronic components with a detection precision (mAP) of 97.81% and a speed of 79 FPS.
RESUMEN
Vision-based object detection of PCB (printed circuit board) assembly scenes is essential in accelerating the intelligent production of electronic products. In particular, it is necessary to improve the detection accuracy as much as possible to ensure the quality of assembly products. However, the lack of object detection datasets in PCB assembly scenes is the key to restricting intellectual PCB assembly research development. As an excellent representative of the one-stage object detection model, YOLOv3 (you only look once version 3) mainly relies on placing predefined anchors on the three feature pyramid layers and realizes recognition and positioning using regression. However, the number of anchors distributed in each grid cell of different scale feature layers is usually the same. The ERF (effective receptive field) corresponding to the grid cell at different locations varies. The contradiction between the uniform distribution of fixed-size anchors and the ERF size range in different feature layers will reduce the effectiveness of object detection. Few people use ERF as a standard for assigning anchors to improve detection accuracy. To address this issue, firstly, we constructed a PCB assembly scene object detection dataset, which includes 21 classes of detection objects in three scenes before assembly, during assembly, and after assembly. Secondly, we performed a refined ERF analysis on each grid of the three output layers of YOLOv3, determined the ERF range of each layer, and proposed an anchor allocation rule based on the ERF. Finally, for the small and difficult-to-detect TH (through-holes), we increased the context information and designed improved-ASPP (Atrous spatial pyramid pooling) and channel attention joint module. Through a series of experiments on the object detection dataset of the PCB assembly scene, we found that under the framework of YOLOv3, anchor allocation based on ERF can increase mAP (mean average precision) from 79.32% to 89.86%. At the same time, our proposed method is superior to Faster R-CNN (region convolution neural network), SSD (single shot multibox detector), and YOLOv4 (you only look once version 4) in the balance of high detection accuracy and low computational complexity.
Asunto(s)
Algoritmos , Redes Neurales de la Computación , Sistemas de Computación , Electrónica , Proyectos de InvestigaciónRESUMEN
Recent stereo matching methods, especially end-to-end deep stereo matching networks, have achieved remarkable performance in the fields of autonomous driving and depth sensing. However, state-of-the-art stereo algorithms, even with the deep neural network framework, still have difficulties at finding correct correspondences in near-range regions and object edge cues. To reinforce the precision of disparity prediction, in the present study, we propose a parallax attention stereo matching algorithm based on the improved group-wise correlation stereo network to learn the disparity content from a stereo correspondence, and it supports end-to-end predictions of both disparity map and edge map. Particular, we advocate for a parallax attention module in three-dimensional (disparity, height and width) level, which structure ensures high-precision estimation by improving feature expression in near-range regions. This is critical for computer vision tasks and can be utilized in several existing models to enhance their performance. Moreover, in order to making full use of the edge information learned by two-dimensional feature extraction network, we propose a novel edge detection branch and multi-featured integration cost volume. It is demonstrated that based on our model, edge detection project is conducive to improve the accuracy of disparity estimation. Our method achieves better results than previous works on both Scene Flow and KITTI datasets.
Asunto(s)
Algoritmos , Procesamiento de Imagen Asistido por Computador/métodos , Aprendizaje Automático , Redes Neurales de la Computación , Atención/fisiología , Señales (Psicología) , Conjuntos de Datos como Asunto , Humanos , Imagenología Tridimensional/métodos , Aprendizaje Automático/normas , Disparidad Visual/fisiología , Percepción Visual/fisiologíaRESUMEN
This paper addresses the robust enhancement problem in the control of robot manipulators. A new hierarchical multiloop model predictive control (MPC) scheme is proposed by combining an inverse dynamics-based feedback linearization and a nonlinear disturbance observer (NDO) based uncertainty compensation. By employing inverse dynamics-based feedback linearization, the multi-link robot manipulator was decoupled to reduce the computational burden compared with the traditional MPC method. Moreover, an NDO was introduced into the input torque signal to compensate and correct the errors from external disturbances and uncertainties, aiming to enhance the robustness of the proposed controller. The feasibility of the proposed hierarchical multiloop MPC scheme was verified and validated via simulation of a 3-DOF robot manipulator. Results demonstrate that the proposed controller provides comparative accuracy and robustness and extends the existing state-of-the-art algorithms for the trajectory tracking problem of robot manipulators with disturbances.
Asunto(s)
Robótica , Dinámicas no Lineales , Simulación por Computador , Algoritmos , RetroalimentaciónRESUMEN
Due to nonlinearity and uncertainty of the robotic manipulator, the design of the robot controller has a crucial impact on its performance of motion and trajectory tracking. In this paper, the linear parameter varying (LPV) - model predictive controller (MPC) of a two-link robot manipulator is established and then the controller's optimal parameters are determined via a newly developed meta-heuristic algorithm, transient search optimization (TSO). The proposed control method is verified by set point and nonlinear trajectory tracking. In the test of set-point tracking, the LPV-MPC scheme optimized by TSO has better performance compared to the computed torque controller (CTC) schemes tuned by TSO or other metaheuristic algorithms. In addition, good performances can also be observed in the tests of nonlinear trajectory tracking via the LPV-MPC scheme by TSO. Moreover, the robustness of the method to structural uncertainty is verified by setting a large system parameter deviation. Results reveal that we achieved some improvements in the optimization of MPC of the robot manipulator by employing the proposed method.
RESUMEN
Deep learning based on a convolutional neural network (CNN) has been successfully applied to stereo matching. Compared with the traditional method, the speed and accuracy of this method have been greatly improved. However, the existing stereo matching framework based on a CNN often encounters two problems. First, the existing stereo matching network has many parameters, which leads to the matching running time being too long. Second, the disparity estimation is inadequate in some regions where reflections, repeated textures, and fine structures may lead to ill-posed problems. Through the lightweight improvement of the PSMNet (Pyramid Stereo Matching Network) model, the common matching effect of ill-conditioned areas such as repeated texture areas and weak texture areas is solved. In the feature extraction part, ResNeXt is introduced to learn unitary feature extraction, and the ASPP (Atrous Spatial Pyramid Pooling) module is trained to extract multiscale spatial feature information. The feature fusion module is designed to effectively fuse the feature information of different scales to construct the matching cost volume. The improved 3D CNN uses the stacked encoding and decoding structure to further regularize the matching cost volume and obtain the corresponding relationship between feature points under different parallax conditions. Finally, the disparity map is obtained by a regression. We evaluate our method on the Scene Flow, KITTI 2012, and KITTI 2015 stereo datasets. The experiments show that the proposed stereo matching network achieves a comparable prediction accuracy and much faster running speed compared with PSMNet.
Asunto(s)
Bases de Datos Factuales , Procesamiento de Imagen Asistido por Computador , Modelos Teóricos , Redes Neurales de la Computación , HumanosRESUMEN
Vision-based recognizing and positioning of electronic components on the PCB (printed circuit board) can improve the quality inspection efficiency of electronic products in the manufacturing process. With the improvement of the design and the production process, the electronic components on the PCB show the characteristics of small sizes and similar appearances, which brings challenges to visual object detection. This paper designs a real-time electronic component detection network through effective receptive field size and anchor size matching in YOLOv3. We make contributions in the following three aspects: (1) realizing the calculation and visualization of the effective receptive field size of the different depth layers of the CNN (convolutional neural network) based on gradient backpropagation; (2) proposing a modular YOLOv3 composition strategy that can be added and removed; and (3) designing a lightweight and efficient detection network by effective receptive field size and anchor size matching algorithm. Compared with the Faster-RCNN (regions with convolutional neural network) features, SSD (single-shot multibox detectors), and original YOLOv3, our method not only has the highest detection mAP (mean average precision) on the PCB electronic component dataset, which is 95.03%, the smallest parameter size of the memory, about 1/3 of the original YOLOv3 parameter amount, but also the second-best performance on FLOPs (floating point operations).
Asunto(s)
Algoritmos , Redes Neurales de la Computación , ElectrónicaRESUMEN
In this work, we have reported for the first time an efficient all-polymer tandem cell using identical sub-cells based on P2F-DO:N2200. A high power conversion efficiency (PCE) of 6.70% was achieved, which is among the highest efficiencies for all polymer solar cells and 43% larger than the PCE of single junction cell. The largely improved device performance can be mainly attributed to the enhanced absorption of tandem cell. Meanwhile, the carrier collection in device remains efficient by optimizing the recombination layer and sub-cell film thickness. Thus tandem structure can become an easy approach to effectively boost the performance of current all polymer solar cells.
RESUMEN
Nanocrystal array solar cells based on lead chalcogenide quantum dots (QDs) have recently achieved a high power conversion efficiency of over 8%. The device performance is expected to further increase by using 1-dimensional nanorods (NRs), due to their improved carrier transport over zero-dimensional quantum dots. However, previously reported PbSe NRs have not been used in solar cells mainly because of their large diameters, resulting in a small bandgap unsuitable for photovoltaic application. In this work, we have demonstrated a new method for synthesizing monodisperse ultra-small PbSe NRs with the diameter approaching 2 nm (Eg > 1.2 eV), which can be attributed to the use of diphenylphosphine (DPP) and trans-2-octenoic acid (t-2-OA). The introduction of trace DPP can greatly lower the reaction temperature, leading to reduced diameters for the obtained PbSe NRs as well as largely increased yield. The use of short-chain t-2-OA together with oleic acid as capping ligands results in high monomer reactivity, fast nucleus diffusion and high growth rate, which realize the anisotropic growth of ultra-small PbSe NRs at low reaction temperatures. The PbSe NRs show n-type properties and high electron mobility as measured using field-effect transistors. The PbSe NRs with narrow diameters also demonstrate a suitable bandgap for photovoltaic application. They are used for the first time in solar cells and their improved efficiency is demonstrated when used together with QDs.