Zhenzhong Sun

A multi-pattern deep fusion model for short-term bus passenger flow forecasting

Abstract Short-term passenger flow forecasting is one of the crucial components in transportation systems with data support for transportation planning and management. For forecasting bus passenger flow, this paper proposes a multi-pattern deep fusion (MPDF) approach that is constructed by fusing deep belief networks (DBNs) corresponding to multiple patterns. The dataset of the short-term bus passenger flow is first segmented into different clusters by an affinity propagation algorithm. The passenger flow distribution of these clusters is subsequently analyzed for identifying different patterns. In each pattern, a DBN is developed as a deep representation for the passenger flow. The outputs of the DBNs are finally fused by chronological order rearrangement. Taking a bus line in Guangzhou city of China as an example, the present MPDF approach is modeled. Five approaches, non-parametric and parametric models, are applied to the same case for comparison. The results show that, the proposed model overwhelms all the peer methods in terms of mean absolute percentage error, root-mean-square error, and determination coefficient criteria. In addition, there exists significant difference between the addressed model and the comparison models. It is recommended from the present study that the deep learning technique incorporating the pattern analysis is promising in forecasting the short-term passenger flow.

An Improved Shuffled Frog Leaping Algorithm for Assembly Sequence Planning of Remote Handling Maintenance in Radioactive Environment

Assembly sequence planning (ASP) of remote handling maintenance in radioactive environment is a combinatorial optimization problem. This study proposes an improved shuffled frog leaping algorithm (SFLA) for the combinatorial optimization problem of ASP. An ASP experiment is conducted to verify the feasibility and stability of the improved SFLA. Simultaneously, the improved SFLA is compared with SFLA, genetic algorithm, particle swarm optimization, and adaptive mutation particle swarm optimization in terms of efficiency and capability of locating the best global assembly sequence. Experiment results show that the proposed algorithm exhibits outstanding performance in solving the ASP problem. The application of the proposed algorithm should increase the level of ASP in a radioactive environment.

Hybrid Optimization Algorithm of Particle Swarm Optimization and Cuckoo Search for Preventive Maintenance Period Optimization

All equipment must be maintained during its lifetime to ensure normal operation. Maintenance is one of the critical roles in the success of manufacturing enterprises. This paper proposed a preventive maintenance period optimization model (PMPOM) to find an optimal preventive maintenance period. By making use of the advantages of particle swarm optimization (PSO) and cuckoo search (CS) algorithm, a hybrid optimization algorithm of PSO and CS is proposed to solve the PMPOM problem. The test functions show that the proposed algorithm exhibits more outstanding performance than particle swarm optimization and cuckoo search. Experiment results show that the proposed algorithm has advantages of strong optimization ability and fast convergence speed to solve the PMPOM problem.

Deep neural network for manufacturing quality prediction

Expected product quality is affected by multi-parameter in complex manufacturing processes. Product quality prediction can offer the possibility of designing better system parameters at the early production stage. Many existing approaches fail at providing favorable results duo to shallow architecture in prediction model that can not learn multi-parameters features insufficiently. To address this issue, a deep neural network (DNN), consisting of a deep belief network (DBN) in the bottom and a regression layer on the top, is proposed in this paper. The DBN uses a greedy algorithm for unsupervised feature learning. It could learn effective features for manufacturing quality prediction in an unsupervised pattern which has been proven to be effective for many fields. Then the learned features are inputted into the regression tool, and the quality predictions are obtained. One type of manufacturing system with multi-parameter is investigated by the proposed DNN model. The experiments show that the DNN has good performance of the deep architecture, and overwhelms the peer shallow models. It is recommended from this study that the deep learning technique is more promising in manufacturing quality prediction.

Petrochemical Enterprise Safety Performance Assessment Based on Interval Number

Safety performance assessment is the measurement of a petrochemical enterprise’s achievement in safety management. In order to receive a comprehensive and objective evaluation result, it is necessary to consider all evaluation factors and the numerical uncertainty caused by fuzziness when safety performance assessment is conducted. To improve conventional safety performance evaluation, an evaluation index system is established, and the interval number is used in this study by using interval number to quantify scores and calculate the safety level of petrochemical enterprise safety. A case of petrochemical enterprise is used to illustrate the effectiveness of the method and system. This method is applied to the comprehensive evaluation of petrochemical enterprise safety to achieve good results.

An Approach for Integrated Analysis of Human Factors in Remote Handling Maintenance

Considering dangerous environmental conditions, maintenance of radioactive equipment can be performed by remote handling maintenance (RHM) system. The RHM system is a sophisticated man-machine system. Therefore, human factors analysis is an inevitable aspect considered in guaranteeing successful and safe task performance. This study proposes an approach for integrated analysis of human factors in RHM so as to make the evaluating process more practical. In the approach, indicators of accessibility, health safety, and fatigue are analyzed using virtual human simulation technologies. The human error factors in the maintenance process are analyzed using the human error probability (HEP) based on the success likelihood index method- (SLIM-) analytic hierarchy process (AHP). The psychological factors level of maintenance personnel is determined with an expert scoring. The human factors for the entire RHM system are then evaluated using the interval method. An application example is present, and the application results show that the approach can support the evaluation of the human factors in RHM.

Multilayered Pipe Cutting Test for Remote Handling Maintenance

Based on the requirements for remote handling maintenance (RHM) of China Spallation Neutron Source (CSNS) multilayered pipes, pipes cutting tests were performed under remote handling maintenance conditions. In this study, the results were obtained from different cutting directions and supporting intensities of pipe baseplates comparisons: When enough power was provided and the blade gripper did not slip, the cutting direction had little impact on the cutting capacity but more on the fault surface; the clearance between the blades caused the rotating torque; for remote handling maintenance, good horizontal support of the long-handled lever of the hydraulic cutter was required. Significant conclusions were made for multilayered pipe cutting that are crucial for auxiliary tools development for remote handling maintenance.