In response to the problem of poor detection performance of the traditional Sobel operator in edge detection, a high-precision edge detection algorithm based on Sobel operator-assisted Holistically-nested Edge Detecti...
详细信息
ISBN:
(数字)9798331506056
ISBN:
(纸本)9798331506063
In response to the problem of poor detection performance of the traditional Sobel operator in edge detection, a high-precision edge detection algorithm based on Sobel operator-assisted Holistically-nested Edge Detection (HED) network was proposed, which is named ISAHED here. The algorithm is designed as follows. Firstly, an improved Sobel operator based on the traditional Sobel operator was proposed through adding gradient direction. Then, the image output by the improved Sobel operator is taken as the ground-truth image and as the end-to-end comparison object in a HED-like network. Finally, the ISAHED algorithm outputs edge images with better quality through iterative learning of the HED-like neural network. The experimental results prove that the proposed ISAHED algorithm has better edge detection performance by visually observing the final edge images and further evaluating the values of FOM. This work provides an important reference for the further development of the edge detection technology.
Mobile robots for Gas Source Localization (GSL) tasks are a safer alternative than human and animal rescuers in hazardous scenarios. Existing research primarily concentrates on rule-based algorithms or conventional ar...
详细信息
ISBN:
(数字)9798350385724
ISBN:
(纸本)9798350385731
Mobile robots for Gas Source Localization (GSL) tasks are a safer alternative than human and animal rescuers in hazardous scenarios. Existing research primarily concentrates on rule-based algorithms or conventional artificial neural networks (ANNs). However, these approaches are either inapplicable in cluttered environments or undeployable due to their high energy consumption and the demand for substantial computational resources. This paper introduces the application of energy-efficient spiking neural networks (SNNs) to address robotic GSL tasks. A pipeline is proposed to train SNNs with deep Q learning and a pretrain-finetune paradigm. To facilitate the training process, a small dataset of gas dispersion is generated utilizing openFoam and GADEN, a high-fidelity simulator for gas dispersion. Data from a simplified plume model are leveraged to pretrain an ANN, the activation function of which gradually transitions from a bounded rectified linear unit (bReLU) to a step function. Subsequently, an SNN initialized with the ANN parameters undergoes finetuning on the GADEN-based dataset. The training pipeline significantly reduces training time compared to direct training of SNNs. The trained SNN is validated within the GADEN simulation environment and compared to three different models, demonstrating promising performance and superior generalization despite limited training data.
Aluminum-based microgroove surfaces with reentrant cavities (MSRCs) were fabricated by two staggered ploughing/extrusion processes to meet the requirements of lightweight phase change heat transfer *** MSRCs with diff...
详细信息
Aluminum-based microgroove surfaces with reentrant cavities (MSRCs) were fabricated by two staggered ploughing/extrusion processes to meet the requirements of lightweight phase change heat transfer *** MSRCs with different stagger angles between cavities and microgrooves (MGs) were fabricated to study the effect of stagger angle on capillary *** rise and permeability tests were performed on all MSRCs and the results were compared with MGs having the same processing *** was found that MSRCs with smaller stagger angles have higher capillary height,and the maximum enhancement maintained by MSRC45 was about 54.84%.However,MSRCs with larger stagger angles were found to have higher ***,the capillary parameter K·ΔP_(cap)was used as a comprehensive index to evaluate these ***90 and MSRC75 obtained the largest K·ΔP_(cap)values without and with the effect of gravity considered,*** all MSRCs had a higher capillary rise height than MGs,smaller stagger angles (≤60°) seriously reduced the permeability of MSRCs and even resulted in smaller K·ΔP_(cap)value than that of MGs when calculated considering the effect of ***,MSRCs with larger stagger angles (≥75°) may be the optimum wicks due to the good balance between capillary pressure and permeability.
Tensegrity structure constitutes a self-supporting and self-stressed spatial grid framework, comprising distinct compression components and continuous tension components, which integrates the benefits of rigid structu...
详细信息
Time-sensitive networks(TSNs)support not only traditional best-effort communications but also deterministic communications,which send each packet at a deterministic time so that the data transmissions of networked con...
详细信息
Time-sensitive networks(TSNs)support not only traditional best-effort communications but also deterministic communications,which send each packet at a deterministic time so that the data transmissions of networked control systems can be precisely scheduled to guarantee hard real-time ***-wait scheduling is suitable for such TSNs and generates the schedules of deterministic communications with the minimal network resources so that all of the remaining resources can be used to improve the throughput of best-effort ***,due to inappropriate message fragmentation,the realtime performance of no-wait scheduling algorithms is ***,in this paper,joint algorithms of message fragmentation and no-wait scheduling are ***,a specification for the joint problem based on optimization modulo theories is proposed so that off-the-shelf solvers can be used to find optimal ***,to improve the scalability of our algorithm,the worst-case delay of messages is analyzed,and then,based on the analysis,a heuristic algorithm is proposed to construct low-delay ***,we conduct extensive test cases to evaluate our proposed *** evaluation results indicate that,compared to existing algorithms,the proposed joint algorithm improves schedulability by up to 50%.
Safe & smart move (SSM) aims to help industrial vehicular robot (IVR), such as warehousing robots, running safely and smartly by detecting the obstacles in front and maintaining a safe distance & attitude. How...
详细信息
ISBN:
(数字)9798350391916
ISBN:
(纸本)9798350391923
Safe & smart move (SSM) aims to help industrial vehicular robot (IVR), such as warehousing robots, running safely and smartly by detecting the obstacles in front and maintaining a safe distance & attitude. However, the traditional SSM methods suffer the drawbacks of limited ranges, inaccurate regression of safety distance & orientation between the robot and the forward unexpected obstacles, and the inappropriate IVR control strategies. To solve these issues, this paper designs an innovative real-time safety-aware framework using the complementary Wheel-Encoder and Inertial-RGB-Depth measurements to ensure the IVR running safely, reasonably and reliably. To estimate the robot running states, we take advantages of the complementary wheel encoder, monocular RGB images and inertial measurements to obtain the robot positions, orientations, angular and linear velocities in a tightly-coupled manner. To improve the safety relative distance & attitude estimation accuracy, we exploit the RGB and depth measurements in a task-oriented fashion. The forward obstacles with the specific contours are detected using the Mask-RCNN model, followed by the Gaussian Mixture Model to obtain the forward obstacle depth. Eventually, an IVR control strategy is designed to maintain the robot safety distance and orientation, and to keep the minimum damage to the robot mechanical system. The presented method has been evaluated on the developed industrial vehicular robot safety perception platform. The experimental results prove the competitiveness against the state-of-the-art methods.
To realize the high-precision clock synchronization of various types of control equipment in the industrial process control network, a high-precision clock synchronizing system is designed and implemented. The system ...
详细信息
ISBN:
(数字)9798350353174
ISBN:
(纸本)9798350353181
To realize the high-precision clock synchronization of various types of control equipment in the industrial process control network, a high-precision clock synchronizing system is designed and implemented. The system uses RT1064 microprocessor as the core, combined with ieee1588v2 high-accuracy clock synchronization protocol, and uses the MAC kernel integrated in rt1064 to support hardware timestamp function to achieve high-precision time synchronization between devices; Finally, the test verification platform is built to test and verify the accuracy. The test results show that the clock synchronization accuracy is within ± 400ns after the system runs stably, which meets the design requirements.
The traditional finite set model predictive control has the advantages of fast response and strong robustness. The threevector model predictive current control(TV-MPCC) improves the problem of large current ripple bas...
详细信息
ISBN:
(数字)9789887581581
ISBN:
(纸本)9798350366907
The traditional finite set model predictive control has the advantages of fast response and strong robustness. The threevector model predictive current control(TV-MPCC) improves the problem of large current ripple based on single-vector model predictive current control(MPCC) and can realize deadbeat current control. Still, it cannot avoid the influence of parameter disturbance. To solve this problem, this paper constructs an ultra-local model based on the input and output information of the motor and designs an adaptive sliding mode observer to estimate the unknown part of the model. Finally, the designed threevector model-free predictive current control with adaptive sliding mode observer(TV-MFPCC-ASMO) is simulated and compared with the traditional three-vector model predictive control. It has been proved that the proposed method can effectively suppress the system disturbance when the motor parameters are mismatched and improve the motor's steady-state and dynamic performance during operation.
The rapid transformation of Industrial Cyber-Physical System (ICPS) has introduced significant cyber security challenges, particularly in the context of ICPS. Wireless networks are a critical component of these system...
详细信息
Compact models are useful to avoid spending a numerous amount of time in numerical simulations which can accurately evaluate the ultra-short channel device properties. One numerical compact model proposed here is desc...
详细信息
暂无评论