作者机构：
[Kang, Xiatao; Wu, Jiaying; Kang, XT; Xiao, Jingying; Yao, Jiayi] Changsha Univ Sci & Technol, Sch Comp & Commun Engn, Changsha, Peoples R China.;[Wu, Jiaying] Hunan Prov Key Lab Intelligent Proc Big Data Tran, Changsha, Peoples R China.
会议名称：
30th International Conference on Neural Information Processing (ICONIP) of the Asia-Pacific-Neural-Network-Society (APNNS)
会议时间：
NOV 20-23, 2023
会议地点：
Changsha, PEOPLES R CHINA
会议主办单位：
[Wu, Jiaying;Kang, Xiatao;Xiao, Jingying;Yao, Jiayi] Changsha Univ Sci & Technol, Sch Comp & Commun Engn, Changsha, Peoples R China.^[Wu, Jiaying] Hunan Prov Key Lab Intelligent Proc Big Data Tran, Changsha, Peoples R China.
会议论文集名称：
Lecture Notes in Computer Science
关键词：
Deep Learning;Network Pruning;Pruning Before Training;Single-shot Pruning
摘要：
Network pruning prior to training makes generalization more challenging than ever, while recent studies mainly focus on the trainability of the pruned networks in isolation. This paper explores a new perspective on loss implicit decrease of the data to be trained caused by one-batch training during each round, whose first-order approximation we term gradient coupled flow. We thus present a criterion sensitive to gradient coupled flow (GCS), which is hypothesized to capture those weights most sensitive to performance boosting at initialization. Interestingly, our explorations show there exists a linear correlation between generalization and implicit loss decrease based measurements on previous works as well as GCS, which ideally describes causes of accuracy fluctuation in a fine-grained manner. Our code is made public at: https://github.com/kangxiatao/pruning_before_training.
摘要：
Credit fraud brings billions of dollars to banks every year. However, the existing research on fraud detection methods has encountered bottlenecks. Traditional fraud detection models are difficult to improve performance and accuracy in detecting fraudulent transactions. The main reason is that the bank credit dataset is very distorted, and the proportion of positive and negative samples is seriously unbalanced, and secondly, due to data privacy and security issues, the dataset is usually not allowed to be shared between different users. In this paper, we improve and enhance the existing credit card fraud detection system, and propose Approx-SMOTE federated learning credit card fraud detection system (AFLCS), through the method of salting and interference items in the data balancing and learning module, design a federal credit fraud detection algorithm for the data after data balance, and improve the network structure of CNN and learning module, the AFLCS can not only improve the processing time by nearly 30 times without affecting the performance, and even better the privacy and security of the information system, but also reserve space for the subsequent application of the system to data expansion between different banks. We achieved our design on the pysyft framework and tested it with an approved data set. The experiments show that our indicators are higher than the existing solutions.
作者机构：
[Zhou, Jifei; Wen, Ke; He, Yecong; Sun, Jie] Changsha Univ Sci & Technol, Sch Energy & Power Engn, Changsha 410114, Peoples R China.;[Deng, Qi] TICA China Co Ltd, Nanjing 210046, Peoples R China.
会议名称：
International Conference on Smart Energy (ICSNRG)
会议时间：
SEP 17-18, 2022
会议地点：
ELECTR NETWORK
会议主办单位：
[Wen, Ke;He, Yecong;Sun, Jie;Zhou, Jifei] Changsha Univ Sci & Technol, Sch Energy & Power Engn, Changsha 410114, Peoples R China.^[Deng, Qi] TICA China Co Ltd, Nanjing 210046, Peoples R China.
会议论文集名称：
Journal of Physics Conference Series
摘要：
In order to explore the energy performance of a university building integrated with solar PV and energy storage, in this paper, DesignBuilder was used to establish the teaching building model and calculate the load based on the characteristics of the teaching building of a university, a simulation model of the photovoltaic & energy storage integrated system was built with TRNSYS. Then analysing the energy performance and economy of the system. The results show that, from the overall demand, the solar electricity generation capacity of the photovoltaic & energy storage integrated teaching building can basically meet the demand for air conditioning electricity, and there is more remaining electricity for the electricity grid. The energy performance of the system in different seasons (summer, spring and autumn transition season, winter) and the complementarity among various electric quantities are studied, including electricity consumption, electricity generation, municipal electricity supply, remaining electricity on grid, battery charge, battery discharge. The economic analysis of the system shows that Solar fraction (SF)=0.93, Self-Consumption Ratio (SCR)=0.13, Return on Investment (ROI)=0.219 years, Payback Period (PBP)=4.75 years, which proves its feasibility.
摘要：
Logs record both the normal and abnormal system operating status at any time, which are crucial data during system operation. Log anomaly detection can help with system debugging and analyzing root causes, such as system fault, shutdown fault, null-pointer exception, illegal-argument exception, and class cast exception. Deep learning is widely applied to log anomaly detection to enhance detection accuracy. However, the deep learning model requires a lot of label logs, which consume large amounts of labor and time. To tackle this label requirement problem, the pre-training model is introduced, for instance, the Bidirectional Encoder Representations from Transformers (BERT). However, the pre-training model brings new problems. The parameters of BERT needed to be fine-tuned are huge, resulting in a high training overhead. Besides, the direct word sequence input representation of BERT ignores the semantic information among logs. Therefore, we propose a parameter-efficient log anomaly detection scheme (LogBP-LORA) based on BERT and Low-Rank Adaptation (LORA). LORA is an effective parameter-tuning strategy. LogBP-LORA increases bypass weight matrices and only updates the bypass parameters instead of all the original parameters to reduce the training overhead. Additionally, LogBP-LORA exploits log event sequence representation to obtain more semantic information with a shorter sequence length. Extensive experiments carry on three public log datasets, BGL, Thunderbird, and HDFS, demonstrate LogBP-LORA can obtain favorable performance with lower resource consumption. When fewer label data is available, LogBP-LORA achieves about 10%-99% higher F1-score compared with Neurallog, Deeplog, MADDC, and Loganomaly. The training parameters of LogBP-LoRA are only 0.06% of the original parameters of BERT.
作者：
Xin, Feng;Zhang, Junying;Yang, Yanfeng;Cao, Wenguang;Zhao, Bin
期刊：
Energy Reports,2023年9(SUPPL-6):154-162 ISSN：2352-4847
通讯作者：
Zhao, B
作者机构：
[Xin, Feng; Cao, Wenguang; Zhao, Bin; Yang, Yanfeng] Changsha Univ Sci & Technol, Sch Energy & Power Engn, Changsha 410114, Peoples R China.;[Zhang, Junying] Huazhong Univ Sci & Technol, Sch Energy & Power Engn, Wuhan 430074, Peoples R China.
通讯机构：
[Zhao, B ] C;Changsha Univ Sci & Technol, Sch Energy & Power Engn, Changsha 410114, Peoples R China.
会议名称：
7th International Conference on Energy and Environmental Science (ICEES)
会议时间：
JAN 06-08, 2023
会议地点：
PEOPLES R CHINA
会议主办单位：
[Xin, Feng;Yang, Yanfeng;Cao, Wenguang;Zhao, Bin] Changsha Univ Sci & Technol, Sch Energy & Power Engn, Changsha 410114, Peoples R China.^[Zhang, Junying] Huazhong Univ Sci & Technol, Sch Energy & Power Engn, Wuhan, Peoples R China.
关键词：
Working gas;Enhancement of heat transfer;Oscillating flow;Heating tube;Spiral insert
摘要：
The working gas type had an important effect on the heat transfer performance of the turbulence device in the heater of Stirling engine, but the related researches were scarce, especially under the oscillatory flow. This work investigated the effects of four working gases (i.e., H-2, He, N-2, and CO2) on the heat transfer characteristics of a heating tube with spiral insert compared with a smooth tube under oscillating flow for a Stirling engine. The transient physical fields under different phase angles in an oscillatory cycle were analyzed, and the Nusselt (Nu) number, pressure loss and outlet temperature of working gas were studied. The results show that the cycle average Nu number of the enhanced tube with H-2, He, N-2, and CO2 as working gas increased to 1.67, 1.62, 1.61 and 1.72 times when comparing with those of the smooth tube. The cycle average friction coefficient increased to 1.96, 2.37, 2.36 and 2.62 times, respectively. Moreover, the performance evaluation criterion (PEC) values of the enhanced tube using the four types of working gas were all greater than 1 (1.21 similar to 1.33). This implies that the comprehensive heat transfer performance of the heating tube with spiral insert was all improved with the four types of working gas. Moreover, the heat transfer enhancement effect was best when hydrogen was used. While considering the thermodynamic performance and safety reliability, the helium was more recommended. The findings are beneficial to enhance the operating efficiency of a Stirling engine. (c) 2023 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
作者机构：
[Zhu W.; Zhang H.; Wang W.; Wang X.] Economic and Technological Research Institute, State Grid Jiangxi Electric Power Co., Ltd, Jiangxi Province, Nanchang City, China;[Ouyang B.] Changsha University of Science and Technology, Hunan Province, Changsha City, China
会议名称：
7th International Conference on Sustainable Energy Engineering, ICSEE 2023
会议时间：
17 February 2022 through 19 February 2022
关键词：
Carbon emissions;Energy storage;High proportion of clean energy;Timing optimization;Uncertainty of randomness
关键词：
VSC-based DC grids;DCCB;DC interruption;current commutation;controllable oscillating
摘要：
The DC circuit breaker (DCCB) is one of the key devices to ensure the stable operation of VSC-based DC grids. Compared to solid-state and hybrid DC circuit breakers, mechanical DC circuit breakers have the advantages of low on-state losses and good economics. However, existing mechanical DC circuit breakers still suffer from problems such as high voltage level of pre-charging system, inability to achieve continuous interruption, and poor economics when applied to high voltage levels. To address these problems, a novel controllable oscillating homopolar coupling DC Circuit Breaker (COHC-DCCB) is proposed in this paper. Firstly, the mathematical model of the controllable oscillating circuit is constructed, and its oscillation mechanism is analyzed. Then, the operation principle of the proposed COHC-DCCB is described. Finally, the effectiveness and feasibility of the proposed COHC-DCCB is verified by extensive simulations with PSCAD/EMTDC.
作者机构：
[Zhou, Xichao; Yang, Jialin; Cong, Lin] State Grid Integrated Energy Serv Grp Co Ltd, Beijing, Peoples R China.;[Shi, Liguo] State Grid Qingdao Power Supply Co, Qingdao, Shandong, Peoples R China.;[Jiang, Fei; Liu, Libo] Changsha Univ Sci & Technol, Changsha, Peoples R China.;[Zhang, Aiqun] State Grid Shandong Elect Power Co, Qingdao, Shandong, Peoples R China.;[Cong, Lin] State Grid Integrated Energy Serv Grp Co Ltd, Beijing, Peoples R China.
会议名称：
5th Asia Energy and Electrical Engineering Symposium (AEEES)
会议时间：
MAR 23-26, 2023
会议地点：
Chengdu, PEOPLES R CHINA
会议主办单位：
[Cong, Lin;Yang, Jialin;Zhou, Xichao] State Grid Integrated Energy Serv Grp Co Ltd, Beijing, Peoples R China.^[Shi, Liguo] State Grid Qingdao Power Supply Co, Qingdao, Shandong, Peoples R China.^[Liu, Libo;Jiang, Fei] Changsha Univ Sci & Technol, Changsha, Peoples R China.^[Zhang, Aiqun] State Grid Shandong Elect Power Co, Qingdao, Shandong, Peoples R China.
关键词：
integrated energy system;intelligent operation and maintenance;business process optimization;event management
摘要：
With the continuous development of intelligent operation and maintenance of integrated energy system (IES-IOM), the operation and maintenance business activities are gradually diversified and complex. Aiming at the problems of complex process chain and low operation and maintenance efficiency in the operation and maintenance business, the optimization design scheme of IES-IOM business process is proposed. Firstly, the current IES-IOM business process scheme is analyzed. Secondly, based on the business process optimization principle, the intelligent operation and maintenance business process optimization method is proposed. Finally, an example of event management in IES-IOM business process is analyzed. The results show that the proposed process optimization method can improve the overall work efficiency and reduce the business time consumption by 11% compared with that before optimization.
摘要：
In recent years, there has been a great development in the research of automated detection of diabetic retinopathy, and deep learning algorithms have been more and more widely used in this field. In this paper, we propose a channel cross enhancement network based on a two-stream model for diabetic retinopathy severity grading for the detailed performance of diabetic retinopathy images on different channels (RGB). The model takes the features of the full-channel input image as global features and the features extracted from the green channel of the original image as local features, and the local features complement the global features to enhance the model's ability to extract the global channel information of the image. In addition, a channel cross-attention module (CCAM) is designed to achieve the effective extraction of global channel features and the interaction of local channel features with global channel features. The proposed method is validated on the Messidor-2 dataset, and the experimental results show that the proposed method outperforms the existing methods in terms of accuracy and AUC values. After experimental validation, the method proposed in this paper can be effectively used for the auxiliary diagnosis of diabetic retinopathy, helping doctors to provide an effective basis for early clinical treatment.
摘要：
The load of power system exhibits evident characteristics of volatility and randomness. The traditional load forecasting algorithm usually studies and trains the historical data to obtain the load model, which makes it difficult to adapt to the load dynamic change situation, and then resulting the unreasonable inaccurate prediction. In this paper, a combinatorial machine learning model is adopted to forecast short-term power load using a dynamic adjustable weight. Firstly, a combined machine learning model is constructed using three types of algorithms including the improved long and short-term neural network, bagging algorithm, and boosting regression algorithm. The weight of each algorithm is determined dynamically by the improved error function. Secondly, the dynamic error function and the optimal weight optimization algorithm are employed so as to balance the contradiction between the speed and accuracy of dynamic adjustment. For different months or different days within a month, different weight adjustment algorithms are selected for enhancement. In addition, a penalty term is introduced to improve the algorithm accuracy and the final prediction outcomes. Finally, a practical load prediction case is simulated and compared with the traditional combined prediction model with fixed weights. It is verified that the proposed model can effectively eliminate the excessive errors caused by the poor dynamic response effect. It has a good dynamic response effect and accurate prediction. The error rate is only 1.24% when the load fluctuation is significant. This study provides a novel approach to forecasting short-term power load. (c) 2023 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
期刊：
Energy Reports,2023年9(SUPPL-6):275-283 ISSN：2352-4847
通讯作者：
Zhao, B
作者机构：
[Xin, Feng; Wu, Hu; Sun, Yuting; Zhao, Bin; Yang, Yanfeng] Changsha Univ Sci & Technol, Sch Energy & Power Engn, Changsha 410114, Peoples R China.;[Zhang, Junying] Huazhong Univ Sci & Technol, Sch Energy & Power Engn, Wuhan 430074, Peoples R China.
通讯机构：
[Zhao, B ] C;Changsha Univ Sci & Technol, Sch Energy & Power Engn, Changsha 410114, Peoples R China.
会议名称：
7th International Conference on Energy and Environmental Science (ICEES)
会议时间：
JAN 06-08, 2023
会议地点：
PEOPLES R CHINA
会议主办单位：
[Xin, Feng;Wu, Hu;Sun, Yuting;Yang, Yanfeng;Zhao, Bin] Changsha Univ Sci & Technol, Sch Energy & Power Engn, Changsha 410114, Peoples R China.^[Zhang, Junying] Huazhong Univ Sci & Technol, Sch Energy & Power Engn, Wuhan 430074, Peoples R China.
关键词：
Eccentric tube;Heat transfer enhancement;Longitudinal vortex;Lead;Eccentricity
摘要：
Enhancing the heat transfer performance of heat exchangers is crucial for solving energy shortage and environmental pollution problems. Eccentric structure tube, with the advantages of small volume ratio, large heat transfer area, compact structure, and cleanliness, was used in this work to strengthen the heat transfer performance. A three-dimensional numerical simulation method was used to investigate the flow and heat transfer characteristics of the working medium in an eccentric tube under the laminar flow condition. The results display that the Nusselt (Nu) number, friction factor, and comprehensive performance evaluation coefficient (PEC) of the eccentric tube decreased with the increase of lead (s). With increasing eccentric distance, the Nu number and friction factor increased and the PEC first increased and then slightly decreased. At an s of 50 mm and eccentric distance of 4 mm, the PEC could reach 2.43. (c) 2023 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
摘要：
Independence and sparsity are proved to be two basic features for spatial activations of functional magnetic resonance imaging (fMRI) data, and have shown efficiency in analysis of magnitude-only fMRI data. Since complex-valued fMRI data contains additional brain activity information beyond magnitude-only fMRI data, we propose to incorporate sparsity constraint into complex independent vector analysis (IVA) to take advantages of the two features in analyzing multi-subject complexvalued fMRI data. Specifically, we propose to improve a complexvalued IVA algorithm named AFIVA (adaptive fixed-point IVA) to add a phase sparsity constraint on spatial maps. Based on the cost function of AFIVA, we further implement the phase sparsity constraint using smoothed L0 norm, and utilize noncircularity of spatial maps as well in the second update of phase sparsity to extract meaningful activations. The results from experimental complex-valued fMRI datasets show that the proposed method yields higher accuracy than AFIVA in terms of true positive rates, confirming the advantage of sparsity in de-noising the independent spatial maps.
作者机构：
[Kang, Xiatao; Li, Ping; Yao, Jiayi] Changsha Univ Sci & Technol, Sch Comp & Commun Engn, Changsha, Peoples R China.;[Li, Chengxi] Xidian Univ, Sch Comp, Xian, Peoples R China.;[Li, Ping] Hunan Prov Key Lab Intelligent Proc Big Data Tran, Changsha, Peoples R China.
会议名称：
16th Asian Conference on Computer Vision (ACCV)
会议时间：
DEC 04-08, 2022
会议地点：
Macao, PEOPLES R CHINA
会议主办单位：
[Kang, Xiatao;Li, Ping;Yao, Jiayi] Changsha Univ Sci & Technol, Sch Comp & Commun Engn, Changsha, Peoples R China.^[Li, Chengxi] Xidian Univ, Sch Comp, Xian, Peoples R China.^[Li, Ping] Hunan Prov Key Lab Intelligent Proc Big Data Tran, Changsha, Peoples R China.
会议论文集名称：
Lecture Notes in Computer Science
关键词：
Deep learning;Reinforcement learning;Network pruning;Pruning before training
摘要：
Pruning on neural networks before training not only compresses the original models, but also accelerates the network training phase, which has substantial application value. The current work focuses on fine-grained pruning, which uses metrics to calculate weight scores for weight screening, and extends from the initial single-order pruning to iterative pruning. Through these works, we argue that network pruning can be summarized as an expressive force transfer process of weights, where the reserved weights will take on the expressive force from the removed ones for the purpose of maintaining the performance of original networks. In order to achieve optimal expressive force scheduling, we propose a pruning scheme before training called Neural Network Panning which guides expressive force transfer through multi-index and multi-process steps, and designs a kind of panning agent based on reinforcement learning to automate processes. Experimental results show that Panning performs better than various available pruning before training methods. Our code is made public at: https://github.com/kangxiatao/RLPanning.
作者机构：
[Li, Zihong; Chen, Donglin] Changsha Univ Sci & Technol, Sch Energy & Power Engn, Changsha 410114, Peoples R China.;[Yin, Liguo] China Datang Grp Co Ltd, Prod Management & Environm Protect Dept, Beijing 100033, Peoples R China.;[Yang, Ningwu] Datang Huayin Elect Power Co Ltd, Safety Dept, Changsha 410114, Peoples R China.;[Liu, Wenzhe] Hunan Datang Xianyi Technol Co Ltd, Changsha 410114, Peoples R China.
会议名称：
International Conference on Smart Energy (ICSNRG)
会议时间：
SEP 17-18, 2022
会议地点：
ELECTR NETWORK
会议主办单位：
[Li, Zihong;Chen, Donglin] Changsha Univ Sci & Technol, Sch Energy & Power Engn, Changsha 410114, Peoples R China.^[Yin, Liguo] China Datang Grp Co Ltd, Prod Management & Environm Protect Dept, Beijing 100033, Peoples R China.^[Yang, Ningwu] Datang Huayin Elect Power Co Ltd, Safety Dept, Changsha 410114, Peoples R China.^[Liu, Wenzhe] Hunan Datang Xianyi Technol Co Ltd, Changsha 410114, Peoples R China.
摘要：
At present, the decision-making method of coal purchase in most coal-fired power stations is based on the experience of blending coal and burning in thermal power units, but this method does not consider the factors of economy and transportation. In order to solve this problem, this paper proposes a method to optimize the coal purchasing scheme of coal-fired power plants based on the joint optimization decision model of coal purchasing and dispatching. First fuel characteristics of mixed coal and purchasing cost model was constructed to determine the fountainhead procurement constraints, and mixing coal prices, then dispatching model was constructed to determine the scheduling constraints and transport price, the final will buy coal cost and transportation cost summation minimum and the nature of the mixed coal constraints as a joint decision model, and USES the particle swarm optimization algorithm to solve it. The decision model is applied to a power plant for verification, and the calculation results show that the total purchasing cost of power plant is greatly reduced.
摘要：
With the continuous shrinking of the size of the semiconductor process, the multi-node upset (MNU) brought about by the charge-sharing effect in the nano-integrated circuit has a huge impact on the reliability of the chip. In this paper, a low-delay quadruple-node-upset self-recoverable (LDQNUSR) latch is proposed, which employs seven identical multi-level soft-error interception modules (SIM), each of which is composed of six two-input C-element (CEs) and an inverter. Due to the error interception characteristics of each SIM and the mutual feedback mechanism, this latch has complete quadruple-node-upset (QNU) self-recovery capabilities. Simulation results show that the proposed latch can tolerate all QNUs and can self-recover from any QNUs. In addition, latch overhead can be reduced due to the use of high-speed transmission gates and clock gating techniques. The proposed latch has lower delay compared to the latest LDAVPM latch.
会议名称：
International Conference on Frontiers of Energy and Environment Engineering (CFEEE)
会议时间：
DEC 16-18, 2022
会议地点：
PEOPLES R CHINA
会议主办单位：
[Li, Zhenxing;Weng, Hanli;Li, Zhenhua] China Three Gorges Univ, Hubei Prov Key Lab Operat & Control, Cascaded Hydropower Stn, Yichang 443002, Peoples R China.^[Li, Zhenxing;Hu, Cong;Tan, Hong] China Three Gorges Univ, Coll Elect Engn & New Energy, Yichang 443002, Peoples R China.^[Wang, Zhenyu] Hunan Prov Key Lab Intelligent Live Working Techno, Changsha 410004, Peoples R China.
关键词：
Large-scale power transmission bases;Oscillation center;Energy rebalancing;Flexible extrapolation strategy
摘要：
The oscillation center may intrude into the generator group when out-of-step oscillation occurs in a large-scale power transmission base. This will lead to an "avalanche" generator tripping of the generator group and seriously affect the safety and stability of the system. Considering that the HVDC system has the advantages of large capacity and long transmission distance, it is often used as a parallel transmission corridor for large-scale power transmission bases. In addition, there is generally a certain reserve capacity in power plants. Starting from inputting reserve capacity and increasing the DC transmission power, a flexible extrapolation strategy of oscillation center based on energy rebalancing is proposed in this paper. The reserve energy at the sending system, the transfer energy in the transmission corridor, and the cut energy at the receiving end are counted. Then the energy transferred in the DC system is comprehensively predicted for complete extrapolation of the oscillation center, and the energy transfer constraints are formulated. The specific energy adjustment schemes of the sending system, power transmission corridor, and the receiving system are determined on the premise of meeting the stability of the system. Finally, the feasibility of this strategy is verified by simulation with the impedance trajectory of the generator and the change curve of power angle during the oscillation period. (c) 2023 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
摘要：
For conflict problems, attitudes of agents on issues are often lost due to some mistakes, and trisecting a set of agents is an important research topic of conflict analysis, and three-way decisions with rankings and references provides an effective method for trisecting a set of agents. In this paper, we divide a set of issues into two disjoint parts from different perspectives, and give the support and opposition rankings of issues and the support and opposition reference tuples for an incomplete situation table. Then, we design an alliance measure with regard to an issue by a transition probability function, and develop an additive alliance measure regarding multiple issues with conditional weights of issues. Afterwards, we take the additive alliance measure to trisect a set of agents towards multiple issues, and give three types of decision rules by considering the weights of agents. Finally, we design an algorithm for deriving three types of decision rules, and use an example to show how to make decisions with the proposed model.
作者：
Min Ruan;Cheng Zhao;Yao Xiao;ShiRong Yao;Jing Huang
期刊：
E3S Web of Conferences,2023年406:02014-null ISSN：2267-1242
通讯作者：
Huang, J.
作者机构：
[Ruan M.; Zhao C.; Yao S.; Xiao Y.] School of Energy and Power Engineering, Changsha University of Science & Technology, Changsha, 410076, China;[Huang J.] State Key Laboratory of Utilization of Woody Oil Resource, Hunan Academy of Forestry, Hunan, Changsha, 410004, China
通讯机构：
[Huang, J.] S;State Key Laboratory of Utilization of Woody Oil Resource, Hunan, China
会议名称：
9th International Conference on Energy Materials and Environment Engineering, ICEMEE 2023
摘要：
In this paper, it was studied that the effects of heating rate and four metal oxide on the combustion characteristics of excess sludge, such as CaO, Fe<sub>2<sub/>O<sub>3<sub/>, MgO and Al<sub>2<sub/>O<sub>3<sub/>, and the combustion kinetic parameters of sludge were obtained based on Coats-Redfern model. This result indicated that the ignition of sludge can be restricted with the increase of heating rate, but it was conducive to burnout, and the increasing about the flammability, stability and comprehensive combustion characteristic index of sludge. The addition of Fe<sub>2<sub/>O<sub>3<sub/> and Al<sub>2<sub/>O<sub>3<sub/> could improve the ignition performance of sludge to a certain extent, which was most obvious at the heating rate of 10 and 20 °C/min, respectively. Furthermore, the existence of Fe<sub>2<sub/>O<sub>3<sub/>, MgO and Al<sub>2<sub/>O<sub>3<sub/> can improve the burnout performance of sludge, represented by MgO. Under the condition of low heating rate, the presence of Fe<sub>2<sub/>O<sub>3<sub/> and MgO was beneficial to improve the comprehensive combustion characteristics of sludge. According to the distribution of combustion kinetics parameters, it was showed an increasing trend about the activation energy of sludge with the increase of heating rate at the range of 374.88-575.61 °C, which was also unfavorable to the combustion of fixed carbon. At the same heating rate, the activation energy decreased by adding Fe<sub>2<sub/>O<sub>3<sub/> and Al<sub>2<sub/>O<sub>3<sub/> at the range of 148.40-374.88 °C, which was beneficial to the release of volatiles and the combustion reaction, while the activation energy at the range of 374.88-575.61 °C decreased after adding CaO, which promoted the combustion of fixed carbon.
作者机构：
Key Laboratory of Hunan Province for Internet of Things and Information Security, Xiangtan University, Hunan, Xiangtan, 411105, China;School of Computer Science, Xiangtan University, Xiangtan, 411105, China;[Deng Q.] School of Computer Science and Engineering and School of Software, Guangxi Normal University, Guangxi, 541001, China;[Wang S.] The Computer and Communication Engineering Institute, Changsha University of Science and Technology, Changsha, 410114, China;[Sun T.; Long S.; Shen D.] Key Laboratory of Hunan Province for Internet of Things and Information Security, Xiangtan University, Hunan, Xiangtan, 411105, China, School of Computer Science, Xiangtan University, Xiangtan, 411105, China
会议名称：
29th International Conference on Neural Information Processing, ICONIP 2022
