• Energy Research

The purpose of this paper is to establish a decision-making system for assembly clearance parameters and machine quality level by analyzing the data of assembly clearance parameters of diesel engine. Accordingly, we present an extension of the rough set theory based on mixed-integer linear programming (MILP) for rough set-based classification (MILP-FRST). Traditional rough set theory has two shortcomings. First, it is sensitive to noise data, resulting in a low accuracy of decision systems based on rough sets. Second, in the classification problem based on rough sets, the attributes cannot be automatically determined. MILP-FRST has the advantages of MILP in resisting noisy data and has the ability to select attributes flexibly and automatically. In order to prove the validity and advantages of the proposed model, we used the machine quality data and assembly clearance data of 29 diesel engines of a certain type to validate the proposed model. Experiments show that the proposed decision-making method based on MILP-FRST model can accurately determine the quality level of the whole machine according to the assembly clearance parameters.

The development of urban rail transit is of great significance to the sustainable development of cities. However, the formulation of public norms of the urban rail transit train operation scheme lacks the corresponding theoretical support, rationality and scientificity. Therefore, based on the research on passenger flow conditions, this paper establishes an optimization model of express train operation and uses a heuristic genetic algorithm to solve it. In addition, this paper takes the Beijing Changping Line as an example to conduct empirical research. Results show that the optimization model established reduces the operation cost of operating enterprises, improves the capacity of urban rail transit, reduces travel time and maintains the full load rate of trains at a more comfortable level. This will improve the attractiveness of urban rail transit and promote benign interaction between operators and passengers. It will also provide a theoretical basis for formulating public norms of transit train operation, make it more scientific and reasonable and promote the development of urban rail transit.

This paper studies the cyclic dynamic gaming case of the r-interdiction median problem with fortification (CDGC-RIMF), which is important for strengthening a facility’s reliability and invulnerability under various possible attacks. We formulated the CDGC-RIMF as a bi-objective mixed-integer linear programming (MILP) model with two opposing goals to minimize/maximize the loss from both the designer (leader) and attacker (follower) sides. The first goal was to identify the most cost-effective plan to build and fortify the facility considering minimum loss, whereas the attacker followed the designer to seek the most destructive way of attacking to cause maximum loss. We found that the two sides could not reach a static equilibrium with a single pair of confrontational plans in an ordinary case, but were able to reach a dynamically cyclic equilibrium when the plan involved multiple pairs. The proposed bi-objective model aimed to discover the optimal cyclic plans for both sides to reach a dynamic equilibrium. To solve this problem, we first started from the designer’s side with a design and fortification plan, and then the attacker was able to generate their worst attack plan based on that design. After that, the designer changed their plan again based on the attacker’s plan in order to minimize loss, and the attacker correspondingly modified their plan to achieve maximum loss. This game looped until, finally, a cyclic equilibrium was reached. This equilibrium was deemed to be optimal for both sides because there was always more loss for either side if they left the equilibrium first. This game falls into the subgame of a perfect Nash equilibrium—a kind of complete game. The proposed bi-objective model was directly solved by the CPLEX solver to achieve optimal solutions for small-sized problems and near-optimal feasible solutions for larger-sized problems. Furthermore, for large-scale problems, we developed a heuristic algorithm that implemented dynamic iterative partial optimization alongside MILP (DIPO-MILP), which showed better performance compared with the CPLEX solver when solving large-scale problems.

This article proposes an improved artificial bee colony algorithm (IABC) for maintaining a balance between the exploratory and exploitative abilities of the algorithm. Therefore, unmodeled dynamic characteristics can be effectively estimated, which can improve the estimation accuracy of the system and create conditions for later system modeling and control. The proposed IABC algorithm uses two new search expressions to generate new alternative solutions and the global optimal solution is considered in the search process. Exploiting the simple structure and fast global convergence of artificial bee colony algorithm, an improved clustering algorithm combining IABC and Kernel fuzzy c-means (KFCM) iteration is also proposed. KFCM algorithm is sensitive to the initial clustering center and can easily fall into local optimum; and the improved clustering algorithm solves this issue. Compared with other algorithms, IABC algorithm can converge faster and more accurately for a given parameter structure and number of cycles. Three sets of benchmark test functions and six sets of UC Irvine standard datasets were used in the simulation experiments conducted. Experimental results show that KFCM-IABC can aggregate datasets faster than generalized fuzzy c-means (GFCM)-IABC because of the use of IABC. The proposed algorithm improves class validity index from 1 to 4%, thereby exhibiting the advantages of strong robustness and high clustering accuracy.

Sequential pattern mining (SPM) is an effective and important method for analyzing time series. This paper proposed a SPM algorithm to mine fault sequential patterns in text data. Because the structure of text data is poor and there are many different forms of text expression for the same concept, the traditional SPM algorithm cannot be directly applied to text data. The proposed algorithm is designed to solve this problem. First, this study measured the similarity of fault text data and classified similar faults into one class. Next, this paper proposed a new text similarity measurement model based on the word embedding distance. Compared with the classic text similarity measurement method, this model can achieve good results in short text classification. Then, on the basis of fault classification, this paper proposed the SPM algorithm with an event window, which is a time soft constraint for obtaining a certain number of sequential patterns according to needs. Finally, this study used the fault text records of a certain aircraft as experimental data for mining fault sequential patterns. Experiment showed that this algorithm can effectively mine sequential patterns in text data. The proposed algorithm can be widely applied to text time series data in many fields such as industry, business, finance and so on.

The dynamic lot-sizing problem under a time-varying environment considers new features of the production system where factors such as production setup cost, unit inventory-holding cost, and unit price of manufacturing resources may vary in different periods over the whole planning horizon. Traditional lot-sizing theorems and algorithms are no longer fit for these situations as they had assumed constant environments. In our study, we investigated the dynamic lot-sizing problem with deteriorating production setup cost, a typical time-varying environment where the production setup is assumed to consume more preparing time and manufacturing resources as the production interval lasts longer. We proposed new lot-sizing models based on the traditional lot-sizing model considering the changing setup cost as a new constraint, called uncapacitatied dynamic single-level lot-sizing under a time-varying environment (UDSLLS-TVE for short). The UDSLLS-TVE problem has a more realistic significance and higher research value as it is closer to reality and has higher computational complexity as well. We proposed two mathematical programming models to describe UDSLLS_TVE with or without nonlinear components, respectively. Properties of the UDSLLS-TVE models were extensively analyzed and an exact algorithm based on forward dynamic programming (FDP) was proposed to solve this problem with a complexity of O (n2). Comparative experiments with the commercial MIP solver CPLEX on synthesized problem instances showed that the FDP algorithm is a global optimization algorithm and has a high computational efficiency.

Air quality issues are critical to daily life and public health. However, air quality data are characterized by complexity and nonlinearity due to multiple factors. Coupled with the exponentially growing data volume, this provides both opportunities and challenges for utilizing deep learning techniques to reveal complex relationships in massive knowledge from multiple sources for correct air quality prediction. This paper proposes a prediction hybrid framework for air quality integrated with W-BiLSTM(PSO)-GRU and XGBoost methods. Exploiting the potential of wavelet decomposition and PSO parameter optimization, the prediction accuracy, stability and robustness was improved. The results indicate that the R2 values of PM2.5, PM10, SO2, CO, NO2, and O3 predictions exceeded 0.94, and the MAE and RMSE values were lower than 0.02 and 0.03, respectively. By integrating the state-of-the-art XGBoost algorithm, meteorological data from neighboring monitoring stations were taken into account to predict air quality trends, resulting in a wider range of forecasts. This strategic merger not only enhanced the prediction accuracy, but also effectively solved the problem of sudden interruption of monitoring. Rigorous analysis and careful experiments showed that the proposed method is effective and has high application value in air quality prediction, building a solid framework for informed decision-making and sustainable development policy formulation.

Traffic flow prediction is one of the basic, key problems with developing an intelligent transportation system since accurate and timely traffic flow prediction can provide information support and decision support for traffic control and guidance. However, due to the complex characteristics of traffic information, it is still a challenging task. This paper proposes a novel hybrid deep learning model for short-term traffic flow prediction by considering the inherent features of traffic data. The proposed model consists of three components: the recent, daily and weekly components. The recent component is integrated with an improved graph convolutional network (GCN) and bi-directional LSTM (Bi-LSTM). It is designed to capture spatiotemporal features. The remaining two components are built by multi-layer Bi-LSTM. They are developed to extract the periodic features. The proposed model focus on the important information by using an attention mechanism. We tested the performance of our model with a real-world traffic dataset and the experimental results indicate that our model has better prediction performance than those developed previously.