Rapid and precise air operation mission planning is a key technology in unmanned aerial vehicles (UAVs) autonomous combat in battles. In this paper, an end-to-end UAV intelligent mission planning ...method based on deep reinforcement learning (DRL) is proposed to solve the shortcomings of the traditional intelligent optimization algorithm, such as relying on simple, static, low-dimensional scenarios, and poor scalability. Specifically, the suppression of enemy air defense (SEAD) mission planning is described as a sequential decision-making problem and formalized as a Markov decision process (MDP). Then, the SEAD intelligent planning model based on the proximal policy optimization (PPO) algorithm is established and a general intelligent planning architecture is proposed. Furthermore, three policy training tricks, i.e., domain randomization, maximizing policy entropy, and underlying network parameter sharing, are introduced to improve the learning performance and generalizability of PPO. Experiments results show that the model in this work is efficient and stable, and can be adapted to the unknown continuous high-dimensional environment. It can be concluded that the UAV intelligent mission planning model based on DRL has powerful intelligent planning performance, and provides a new idea for researching UAV autonomy.
UAV route planning is the key issue for application of UAV in real-world scenarios. Compared with the traditional route planning methods, although the intelligent optimization algorithm has stronger ...applicability and optimization performance, it also has the problem of poor convergence accuracy and easy to fall into local optimization. Therefore, an intelligent route planning method for UAV based on chaotic random opposition-based learning and cauchy mutation improved Moth-flame optimization algorithm (OLTC-MFO) is proposed. First, the terrain environment is constructed by digital elevation map, and the threat model is established to realize the equivalent three-dimensional (3D) environment. Then, the opposite population is introduced to increase the diversity of solutions and improve the search speed of the algorithm. Then, the Logistic-Tent chaos map is introduced to realize random perturbation of flame position, which improves the global search capability of the algorithm. Finally, the probability operator and Cauchy mutation operator are introduced, which makes the algorithm not only accept the current solution with a certain probability, but also jump out of the current sub-optimal solution, thus enhancing the global search capability of the algorithm. The simulation results show that when the number of iterations is 1000, the length of route planning based on OLTC-MFO algorithm is 45.3716km shorter than MFO algorithm, and the convergence result of this method is stable and more accurate, which achieves the purpose of assisting UAV combat decision-making.
Air target threat assessment is a key issue in air defense operations. Aiming at the shortcomings of traditional threat assessment methods, such as one-sided, subjective, and low-accuracy, a new ...method of air target threat assessment based on gray neural network model (GNNM) optimized by improved moth flame optimization (IMFO) algorithm is proposed. The model fully combines with excellent optimization performance of IMFO with powerful learning performance of GNNM. Finally, the model is trained and evaluated using the target threat database data. The simulation results show that compared with the GNNM model and the MFO-GNNM model, the proposed model has a mean square error of only 0.0012 when conducting threat assessment, which has higher accuracy and evaluates 25 groups of targets in 10 milliseconds, which meets real-time requirements. Therefore, the model can be effectively used for air target threat assessment.
Conventional threat assessment model based on Bayesian Network is a reasoning process in static environment, which is difficult to deal with a large number of broken air combat data in a complex ...dynamic battlefield environment. Motivated by this fact, a Dynamic Bayesian Network-based threat assessment model is established, and a theoretical method based on Expectation Maximization to deal with missing data is proposed. Finally, simulations are presented to verify the effectiveness of the proposed structure.
This study explores the influence of different segregation configurations on the creep behaviors and mildew of maize. An inexpensive and easy‐to‐use system was designed, and three configurations of ...maize kernels distribution, i.e., uniform mixing (Mdm), alternating distribution (Mda), and segregated state distribution (Mds), with wet basis moisture content of 22.9%, were compressed under vertical pressure of 200 kPa through a one‐dimensional oedometer. The compression and creep behaviors were investigated using the strain/settlement–time results, and aerobic plate counting (APC) was performed to study the effect of distribution configuration on the mildew effect. A finite‐element model was established to simulate the temperature variation caused by physical environmental factors, and the heat production by fungi was quantified using the difference in temperature between simulation and test. The results indicate that the three‐element Schiffman model can represent the creep behavior of the maize with different distribution configurations. The average temperature of Mdm, Mda, and Mds were 7.53%, 12.98%, and 14.76% higher than the average room temperature, respectively. The aerobic plate count of Mdm, Mda, and Mds were 1.0 × 105, 2.2 × 105, and 8.8 × 105 cfu g−1 stored for 150 h, respectively. In general, the temperature and APC in segregated maize bulk are higher than uniform grain. The effectiveness of the numerical model was verified, and the heat production by maize bulk fungi was quantified using the test and numerical temperature difference. The average heat was the least in Mdm with 2.8 × 106 J m−3, and Mda and Mds were 1.7 and 2 times more than Mdm. And the heat was related to the segregation configurations and agreed very well with the APC and temperature results.
This study explores the influence of three segregation configurations on the creep behaviors and mildew of maize. A newly empirical analytical‐numerical method was established to evaluate the heat generated by fungi, considering segregation configuration and compression. The aerobic plate count (APC) and the temperature of in segregated maize bulk are higher than uniform grain. And the heat production was related to the segregation configurations and agreed very well with the APC and temperature results.
Breakage in maize kernels and vertical pressure in grains lead to the uneven distribution of grain bulk density, which easily causes undesired problems in terms of grain storage. The objective of ...this study was, therefore, to determine the compression and heat production of the whole kernel (WK) and half kernel (HK) under two different loadings, i.e., 50 and 150 kPa, in maize bulk. An easy-to-use element testing system was developed by modification of an oedometer, and an empirical–analytical–numerical method was established to evaluate fungal heat production, considering kernel breakage and vertical pressure. Based on the experimental results, it was found that breakage induced larger compression; the compression of HK was 62% and 58% higher than that of WK at 50 kPa and 150 kPa, respectively. The creep model of the Hooke spring–Kelvin model in series can be used to accurately describe the creep behavior of maize bulk. Fungi and aerobic plate counting (APC) were affected significantly by the breakage and vertical pressure. APC in HK was 19 and 15 times that of WK under 150 and 50 kPa, respectively. The heat released by the development of fungi was found to be directly related to the APC results. The average temperatures of WK and HK under 150 and 50 kPa were 11.1%, 9.7%, 7.9%, and 7.6% higher than the room temperature, respectively. A numerical method was established to simulate the temperature increase due to fungi development. Based on the numerical results, heat production (Q) by fungi was estimated, and the results showed that the Q in HK was 1.29 and 1.32 times that of WK on average under 150 and 50 kPa. Additionally, the heat production results agreed very well with the APC results.
Aiming at the problems of difficult handling of three-dimensional flight conflicts and unfair distribution of resolution costs, we propose a multi-aircraft conflict resolution method based on the ...network cooperative game. Firstly, we establish a flight conflict network model with aircraft as nodes and the conflict relationship between node pairs as edges. After that, we propose a comprehensive network index that can evaluate the effect of resolution strategy. Based on the concept of “nucleolus solution”, we establish a conflict network alliance with all nodes as participants, and balance the interests of all participants through the resolution cost function. In order to improve the timeliness of the method, we propose two optimization methods: adjusting high-priority nodes and customizing the initial resolution scheme. Finally, we combine the NSGA-II algorithm to solve the optimal conflict resolution scheme. The simulation results show that our method can adjust 10 aircraft in 15.17 s and resolve 12 flight conflicts in a complex conflict scenario containing 40 aircraft; our method reduces the resolution cost by more than 22.1% on average compared with the method without considering the resolution cost. The method ensures both the conflict resolution capability and the reduction in resolution cost.
Bi2WO6 was synthesized with a hydrothermal method at different pHs and used for the degradation of tetracycline (TC) in water. The mesoporous BiEWO6 prepared at pH 1 (BWO-1) displayed the highest ...adsorption and degradation capacity to TC due to its large surface area and more efficient capacity to separate photogenerated electrons and holes. 97% of TC at 20 mg · L-1 was removed by BWO-1 at 0.5 g-L-1 after 120min irradiation under simulated solar light. Only 31% of the total organic carbon (TOC) was removed after 360 min irradiation although the TC removal reached 100%, suggesting that TC was mainly transformed to intermediate products rather than completely mineralized. The inter- mediates were identified by high-performance liquid chromatography-time of flight-mass spectrometry (HPLC-TOF-MS) and possible photodegradation path- ways were proposed.
Background Chronic obstructive pulmonary disease (COPD) is a common respiratory disease that often coexists with malnutrition during acute exacerbation (AECOPD) and significantly affects the ...prognosis. Previous studies have shown that growth differentiation factor 15 (GDF15) levels promote appetite suppression, weight loss, and muscle weakness, and are markedly high in peripheral blood following inflammatory stimulation. However, it is still unknown whether serum GDF15 levels can be used to predict malnutrition in patients with AECOPD. Methods A total of 142 patients admitted to the Department of Respiratory Medicine at Anshun People’s Hospital between December 2022 and August 2023 were selected for this study. The participants were divided into two groups: malnutrition group ( n = 44) and non-malnutrition group ( n = 98) based on a body mass index (BMI) < 18.5 kg/m 2 , according to the Global Leadership Initiative on Malnutrition (GLIM) criteria. Serum GDF15 levels were measured using the enzyme-linked immunosorbent assay (ELISA) and compared between the two groups. Spearman correlation analysis was used to examine the association between serum GDF15 levels, baseline data, and clinical indicators. Binary logistic regression was used to identify the independent risk factors for AECOPD combined with malnutrition. The predictive value of serum GDF15, albumin (ALB), and a combination of these was evaluated to identify malnutrition in patients with AECOPD using a receiver operating characteristic (ROC) curve. Results Serum GDF15 levels in patients with malnutrition and AECOPD were significantly higher than those in patients without malnutrition, whereas the serum ALB levels were significantly lower than those in patients without malnutrition ( p < 0.001). Moreover, serum GDF15 levels were negatively correlated with BMI ( r = −0.562, p < 0.001), mid-arm circumference ( r = −0.505, p < 0.001), calf circumference ( r = −0.490, p < 0.001), total protein ( r = −0.486, p < 0.001), ALB ( r = −0.445, p < 0.001), and prognostic nutritional index ( r = −0.276, p = 0.001), and positively correlated with C-reactive protein ( r = 0.318, p < 0.001), COPD assessment test score ( r = 0.286, p = 0.001), modified medical research council classification ( r = 0.310, p < 0.001), and global initiative for chronic obstructive pulmonary disease grade ( r = 0.177, p = 0.035). Furthermore, serum GDF15 levels were an independent risk factor for malnutrition in patients with AECOPD (OR = 1.010, 95% CI, 1.003∼1.016). The optimal cut-off value of serum GDF15 level was 1,092.885 pg/mL, with a sensitivity of 65.90% and a specificity of 89.80%, while the serum ALB level was 36.15 g/L, with a sensitivity of 86.40% and a specificity of 65.00%, as well as a combined sensitivity of 84.10% and a specificity of 73.90%. Serum GDF15 and serum ALB levels had a good predictive ability (AUC = 0.856, AUC = 0.887), and the ROC revealed a greater combined prediction value for the two (AUC = 0.935). Conclusion Serum GDF15 levels could be used as a potential biomarker in the prediction of malnutrition in patients with AECOPD, offering a guidance for future clinical evaluation of malnutrition.
Unmanned aerial vehicle (UAV) swarm cooperative decision-making has attracted increasing attentions because of its low-cost, reusable, and distributed characteristics. However, existing ...non-learning-based methods rely on small-scale, known scenarios, and cannot solve complex multi-agent cooperation problem in large-scale, uncertain scenarios. This paper proposes a hierarchical multi-agent reinforcement learning (HMARL) method to solve the heterogeneous UAV swarm cooperative decision-making problem for the typical suppression of enemy air defense (SEAD) mission, which is decoupled into two sub-problems, i.e., the higher-level target allocation (TA) sub-problem and the lower-level cooperative attacking (CA) sub-problem. A HMARL agent model, consisting of a multi-agent deep Q network (MADQN) based TA agent and multiple independent asynchronous proximal policy optimization (IAPPO) based CA agents, is established. MADQN-TA agent can dynamically adjust the TA schemes according to the relative position. To encourage exploration and promote learning efficiency, the Metropolis criterion and inter-agent information exchange techniques are introduced. IAPPO-CA agent adopts independent learning paradigm, which can easily scale with the number of agents. Comparative simulation results validate the effectiveness, robustness, and scalability of the proposed method.