Search

The detection of corporate accounting fraud is a critical challenge in the financial industry, where traditional models such as neural networks, logistic regression, and support vector machines often fall short in achieving high accuracy due to the complex and evolving nature of fraudulent activities. This paper proposes an enhanced approach to fraud detection by integrating convolutional neural networks (CNN) and long short-term memory (LSTM) networks, complemented by an attention mechanism to prioritize relevant features. To further improve the model’s performance, the sparrow search algorithm (SSA) is employed for parameter optimization, ensuring the best configuration of the CNN-LSTM-Attention framework. Experimental results demonstrate that the proposed model outperforms conventional methods across various evaluation metrics, offering superior accuracy and robustness in recognizing fraudulent patterns in corporate accounting data.

Abstract This paper investigates four energy utilization scenarios with or without home‐distributed photovoltaic generation (HDPG) to reduce the generation cost and pollutant emission of the dynamic economic emission dispatch with the charging/discharging of plug‐in electric vehicles (DEED‐PEV). The first scenario considers valley filling for the charging of PEVs. The second scenario combines valley filling and peak shaving for the charging and discharging of PEVs. The third scenario adds peak shaving of HDPG to the first scenario, followed by the peak shaving with the discharging of PEVs. The fourth scenario rearranges the distribution of photovoltaic (PV) power for the third scenario, and the PV power in the afternoon is stored by a photovoltaic energy storage system (PESS) and consumed in the evening. A universal procedure is designed for the valley filling and peak shaving of the four scenarios, which is beneficial for determining the filled and shaved loads with respect to certain time intervals. An NSGA‐II method based on a modified crossover and an elimination of individuals (NSGA‐II‐MCEI) is proposed for the multiobjective optimization of DEED‐PEV. The modified crossover can improve the convergence of NSGA‐II‐MCEI, and the elimination operator can maintain the evenness of the nondominated solutions. According to experimental results, scenario 4 achieves cost savings of 95386.62 $, 85636.87 $, and 6776.85 $, respectively, for Scenarios 1, 2, and 3, and it reaches emission reductions of 27617.64 kg, 17252.71 kg, and 220.98 kg, respectively, for scenarios 1, 2, and 3. Also, scenario 4 outperforms the other three scenarios for three weather conditions such as sunny day, cloudy day, and rainy day.

This study proposes two curves that depict the vehicle–bridge contact force in a novel transportation system named AERORail, which is a lightweight cable-supported structure in which the rails and the prestressed cable form the load bearing system. Based on the contact force identified from a full-scale AERORail system, single and double-valley curves were obtained as the idealized contact force model for large- and small-span AERORail systems, respectively. This was achieved by utilizing the Bezier curves and the least squares method. The proposed curves were verified through a moving load model from a previous study under various spans and speeds. Moreover, the structural response of the AERORail structure under high-speed vehicle passing was explored using the idealized contact force model. The simulation results show that the proposed contact force model can predict the displacement response of 5 m and 15 m spans with a relative error of less than 5%, proving that the model can be used for dynamic analysis of AERORail.

Dynamic economic emission dispatch (DEED) is a fundamental and meaningful issue for a power system from the perspectives of economy and environment protection. In the mean time, reliability is an important criterion for a power system from the perspectives of maintenance and operation. Therefore, we propose an improved NSGA-III (I-NSGA-III) for the dynamic economic emission dispatch considering reliability (DEEDR). I-NSGA-III uses a novel crossover operator based on the normal distribution and an angle-based association strategy. The former produces an offspring by using the normal distribution to fully explore and exploit the solution space while remaining a relatively high population diversity. The latter considers the angle between a normalized objective vector and a reference vector as a criterion for the association operation, which is more direct and efficient to evenly distribute individuals with the same rank in the objective space. According to the indicators hypervolume and coverage in the experiments, I-NSGA-III can achieve a series of nondominated solutions with wider spread, higher diversity and stronger convergence in comparison with the other four multi-objective optimization algorithms (MOAs). Therefore, I-NSGA-III can efficiently coordinate the benefits of fuel cost, pollutant emission and system reliability, and it is a competitive and potential algorithm for DEED and DEEDR.

Corrosion of longitudinal reinforcement and stirrup in reinforced and prestressed concrete beams is very common for structures and infrastructures, which is one of the main reasons for the decrease in stiffness and durability of structure. In order to evaluate the influence of corrosion of different types of stirrups on the bearing capacity of the prestressed concrete beam, the method of using electricity to accelerate corrosion was adopted. Load experiment on 4 corroded prestressed concrete beams with different corrosion rates and different stirrup types was carried out. In this paper, reduced scale model beams were designed based on the 5 × 50 m simple-continuous box girder of the Donghai Bridge. The results show that for prestressed concrete beams with different corrosion rates and stirrup types, the load-deflection curve can be divided into an elastic stage and a plastic stage. The corrosion of longitudinal bars and stirrups will reduce the flexural capacity, but the overall decline is not obvious. When the corrosion rate is 10%, the bearing capacity of the ordinary stirrup specimen decreases by 6.1%; epoxy-coated stirrup specimen decreases by 4.9%; stainless stirrup specimen has nearly no change. The influence of different types of stirrups on cracking load, deflection, and bond-slip behavior is discussed.

The flexible structure of the new type of aerial track studied in this paper is formed by strings and tracks, which have obvious dynamic characteristics under the action of vehicle moving loads and is also an important factor affecting its performance. The paper uses the full-scale model of AERORail, based on the modal test under a specific span, combined with the fundamental frequency analysis of the structure, and carries out the dynamic load test to determine the change law of the contact force acting on the rail by the dynamic load. The time-domain improved algorithm based on the method of moments is used to identify and analyze the dynamic loads under different spans and vehicle speeds and to determine the correlation between the dispatched loads and the spans and vehicle speeds. It is proven that the occurrence time and frequency of the contact force are related to the passing time of the vehicle. The contact force fluctuates with the change in the vehicle speed, but with the increase in the span, the fluctuation of the contact force decreases obviously. The relevant conclusions provide support for the layout of the AERORail vehicle load. For this innovative structure, the relevant conclusions provide the basis for the application of this novel structure.

An improved particle swarm optimization (IPSO) is used to solve economic dispatch problem (EDP). The IPSO has two position updating strategies. In the early stage of iteration, the individual in the population updates the position according to its own best experience with a large probability. In the later stage of iteration, the individual updates the position according to the best experience in the population with a large probability. In addition, the IPSO introduces a mutation operator after position updating, which can increase the diversity of population and prevent the premature convergence. IPSO has been used to solve EDP with valve point effect. The experimental results show that IPSO is an effective algorithm to solve EDP.

This paper presented a new aerial platform-AERORail for rail transport and its structure evolution based on the elastic stiffness of cable; through the analysis on the cable properties when the cable supported a small service load with high-tensile force, summarized the theoretical basis of the AERORail structure and the corresponding simplified analysis model. There were 60 groups of experiments for a single naked cable model under different tensile forces and different services loads, and 48 groups of experiments for the cable with rail combined structure model. The experimental results of deflection characteristics were compared with the theoretical values for these two types of structures under the same conditions. It proved that the results almost met the classical cable theory. The reason is that a small deflection was required when this structure was applied. Aider the tension increments tests with moving load, it is verified that the relationships between the structure stiffness and tension force and service load are simple. Before further research and applications are made, these results are necessary for the determination of the reasonable and economic tensile force, allowable service load for the special span length for this new platform. [ABSTRACT FROM AUTHOR]