• Mining Security Assessment in an Underground Environment using a Novel Face Recognition Method with Improved Multiscale Neural Network

    分类: 机械工程 >> 机械设计 提交时间: 2024-04-01

    摘要: Overstaffing production in underground coal mining is not convenient for daily management, and incomplete information of coal miners hinders the rescue process of firefighters during mine accidents. To address this safety sustainability issue, a novel face recognition method based on an improved multiscale neural network is proposed in this paper. A new depthwise seperable (DS)-inception block is designed and a joint supervised loss function based on center loss theory is developed to constructe a new multiscale model. The miniers can be recognized in the harsh underground environment during the life rescue. Experimental results show that the accuracy, recall and F1-score indexes of the proposed method for the miner face recognition in the underground mining environment are 97.26%, 94.17% and 95.42%, respectively. Transfer model with joint supervised loss can effectively improve the recognition accuracy by about 0.5~1.5%. In addition, the average recognition accuracy of the proposed face recognition method achieves to 91.34% and the miss detection rate is less than 5% in the dugout tunnel of coal mine.

  • A nonlinear African vulture optimization algorithm combining Henon chaotic mapping theory and reverse learning competition strategy

    分类: 工程与技术科学 >> 工程通用技术 提交时间: 2024-03-28

    摘要: As a new intelligentoptimization algorithm, the African vulturesoptimization algorithm(AVOA) has been widely used in various fields today. However, when solving complex multimodal problems, the AVOA still has some shortcomings, such as low searching accuracy, deficiency on the search capability and tendency to fall into local optimum. In order to alleviate the main shortcomings of the AVOA, a nonlinear African vulture optimization algorithm combining Henon chaotic mapping theory and reverse learning competition strategy (HWEAVOA) is proposed. Firstly, the Henon chaotic mapping theory and elite population strategy are proposed to improve the randomness and diversity of the vulture’s initial population; Furthermore, the nonlinear adaptive incremental inertial weight factor is introduced in the location update phase to rationally balance the exploration and exploitation abilities, and avoid individual falling into a local optimum; The reverse learning competition strategy is designed to expand the discovery fields for the optimal solution and strengthen the ability to jump out of thelocal optimal solution. HWEAVOA and other advanced comparison algorithms are used to solve classical and CEC2022 test functions. Compared with other algorithms, the convergence curves of the HWEAVOA drop faster and the line bodies are smoother. These experimental results show the proposed HWEAVOA is ranked first in all test functions, which is superior to the comparison algorithms in convergence speed, optimization ability, and solution stability. Meanwhile, HWEAVOA has reached the general level in thealgorithm complexity, and its overall performance is competitive in theswarm intelligence algorithms.

  • Conventional and advanced exergy-exergoeconomic exergoenvironmental analyses of an organic Rankine cycle integrated with solar and biomass energy sources

    分类: 能源科学 >> 能源(综合) 提交时间: 2024-03-29

    摘要: Considering the huge consumption of traditional energy and the rising demand for electricity, the development of renewable energy is very necessary. In this paper, an energy system integrating biomass energy, solar and two-stage organic Rankine cycle (ORC) is proposed, which uses the stable energy output of biomass energy to compensate for the volatility of solar modules. The proposed system comprises a biomass boiler, photovoltaic thermal panels (PV/T), evaporators, condensers, working medium pumps, turbines, a preheater and an air preheater. In addition, conventional and advanced exergy, exergoeconomic and exergoenvironmental (3E) analyses are carried out. Conventional 3E analyses reveal two components that require priority improvement. They are respectively evaporator 1 with the largest exergy destruction (708.2kW) and exergy destruction environmental impact rate (775.3 mPt/h) and evaporator 2 with the largest exergy destruction cost rate (19.15$/h).The results of advanced 3E analyses show that the largest avoidable endogenous exergy destruction is condenser 1 (136.6kW), the largest avoidable endogenous exergy destruction cost rate is condenser 2 (3.377$/h),and the largest avoidable endogenous exergy destruction environmental impact rate is condenser 1 (196.1mPt/h). These mean that these components have great potential for improvement in reducing exergy destruction, saving cost and protecting the environment. In addition, the avoidable endogenous exergy destruction/cost/environmental impact rate of evaporator 2 are negative, so evaporator 2 is not suitable as a priority component for improvement, which is contrary to the conclusions of conventional 3E analyses. It is found that conventional 3E analyses can only point out the biggest exergy destruction point, but cannot indicate whether the components with the greatest exergy destruction have the greatest potential for improvement. However, advanced 3E analyses can show the improvement potential of each component by improving its own performance and the external conditions. Therefore, it is necessary to conduct advanced 3E analyses.