Ad agencies have turned their attention to online and in-app advertising in response to the expansion of digital technology and social media. Internet advertising represents a major revenue source for advertising netw...
详细信息
Withthe continuous advancement of photovoltaic poverty alleviation and the "coal-to-electricity"policies in China, rural areas face issues such as limited optimization methods for user heating systems and t...
详细信息
In grid computing environment, a balanced transaction scheduling is a NP-hard problem. In this paper, a technique for load-balanced transaction scheduling using Gaussian mixture model-ant colony optimization algorithm...
详细信息
ISBN:
(纸本)9783031837821;9783031837838
In grid computing environment, a balanced transaction scheduling is a NP-hard problem. In this paper, a technique for load-balanced transaction scheduling using Gaussian mixture model-ant colony optimization algorithm is proposed. Gaussian mixture model, which is based on Gaussian density functions, provides clustering characteristics. Our proposed algorithm uses this clustering method to identify the cluster of nodes with less nodes and uses ant colony optimization to find out the appropriate node for the final selection. the proposed algorithm outperforms the existing algorithms.
Marine engines have a high risk of failure during navigation and face issues such as varying operating conditions and complex faults. Existing research mainly focuses on fault diagnosis of marine engines under single ...
详细信息
ISBN:
(纸本)9798350375084;9798350375077
Marine engines have a high risk of failure during navigation and face issues such as varying operating conditions and complex faults. Existing research mainly focuses on fault diagnosis of marine engines under single operating conditions, neglecting the applicability of these methods under other conditions. To address this issue, this paper employs domain adaptation techniques to study cross-condition fault diagnosis of marine engines. Firstly, a self-calibrating convolutional neural network is used to extract health state features from engine operation data. Meanwhile, by integrating adversarial and subdomain adaptation techniques, the distribution differences in global domains and local subdomains under different operating conditions are reduced, thereby improving the fault diagnosis accuracy under variable conditions. Finally, the effectiveness of the diagnostic model is validated based on simulated marine engine fault data. For the designed one-to-one and one-to-many condition transfer tasks, the average fault diagnosis accuracy reaches approximately 90%, achieving higher recognition accuracy compared to other methods. the research results can provide theoretical reference for fault diagnosis of marine engines under variable operating conditions.
this work proposes a novel physics-based Cartpole simulation environment as a new benchmark to address the sim-to-real transfer. Our simulation environment extends the original Gymnasium Cartpole environment with addi...
详细信息
ISBN:
(纸本)9798350349467;9798350349450
this work proposes a novel physics-based Cartpole simulation environment as a new benchmark to address the sim-to-real transfer. Our simulation environment extends the original Gymnasium Cartpole environment with additional physics and data-driven models for friction, air resistance, and the non-linear behavior of the applied force on the cart inspired by a real-world experimental setup. We implement the Gymnasium environment interface, allowing us to use our implementation as a drop-in replacement with configurable simulation fidelity. We show that our physics-based Cartpole simulation with Reinforcement learning minimizes the reality gap to our real-world Cartpole setup without increasing computational efforts considerably. Moreover, our simulation environment is an efficient surrogate model for a real Cartpole, and thus provides a rare example of closing the reality gap.
Traditional property management services often struggle with challenges such as long response times and difficulties in effectively addressing complex tenant issues. While Large Language Models (LLMs), like ChatGPT, o...
详细信息
Withthe growing integration of Artificial Intelligence (AI) in hybrid vehicles, significant advancements have been made in improving their environmental perception, energy management, path planning, and charge optimi...
详细信息
the proceedings contain 67 papers. the topics discussed include: optimization of robot machining process parameters based on multi-feature signal fusion analysis;structural design and finite element analysis of materi...
ISBN:
(纸本)9798400709937
the proceedings contain 67 papers. the topics discussed include: optimization of robot machining process parameters based on multi-feature signal fusion analysis;structural design and finite element analysis of material handling robots;optimization method for operation configuration of space manipulator for on-orbit assembly;research on vertical parking path planning for smart cars;architecture capability indicator system of command and control system;state of the art and development trends for inspection robots applied in substations;design of a cross-spring flexure hinge with variable thickness based on Bezier curve;design and simulation of pilot flow-controlled load sensitive hydraulic system;and design and simulation of forestry fruit collecting robots with wheel-foot transformation.
the study is on investigating the machinability aspects of Al7075, a high-strength and lightweight alloy commonly used in automobiles, aircraft structures, defense equipment, etc. the work presented includes cutting f...
详细信息
the study is on investigating the machinability aspects of Al7075, a high-strength and lightweight alloy commonly used in automobiles, aircraft structures, defense equipment, etc. the work presented includes cutting forces, specific power, surface roughness, and tool wear while milling Al7075 alloy. A central composite design in response surface methodology is used to determine the optimum parameters, i.e., cutting speed, feed rate, and depth of cut with above responses. the prediction models are developed followed by ANOVA analysis to understand the role of input parameters on responses. these models are in good agreement with experimental results, followed by parametric optimization using desirability approach. Simultaneously, the evolutionary algorithms like real-coded genetic algorithm, teaching-learning-based optimization, and JAYA are employed for selecting the machining parameters and corresponding responses. the optimized results show that JAYA and TLBO algorithms are better to effectively minimize the responses in milling Al-7075.
To maintain stable production operations, it's crucial to promptly assess the corrosion trends in industrial circulating cooling water quality. A prediction method of corrosion rate based on Extreme Gradient Boost...
详细信息
暂无评论