Search

Regenerative braking is one of the most important methods for improving energy utilization in electric vehicles. Electric vehicles with front-rear, individually driven configurations exhibit significant potential and flexibility for recovering braking energy. To improve the system’s high-power impact tolerance, a high-power density hydraulic energy storage system can be incorporated to facilitate a full-drive dual-motor electric–hydraulic hybrid (DMEHH) powertrain. The DMEHH system is composed of an independently driven electric–hydraulic hybrid front axle and a purely electric rear axle. In this study, a method for distributing braking torque to minimize energy loss was devised based on the proposed DMEHH powertrain. Power loss models for both the electric and hydraulic subsystems have been developed. Loss minimization control was adapted for the power loss model of the permanent magnet synchronous motors in the powertrain, and the front-rear and front electric–hydraulic torque braking distribution maps were calculated using the energy-loss minimization rule. The application of torque distribution maps resulted in energy losses less than those of the general ideal torque distribution for all braking conditions. The energy loss decreased by 27.2% when the loss minimization control method was used in the WLTC cycle, and decreased by 29.1%, 25.5%, and 21.6% in UDDS, NEDC, and US06 driving cycles, respectively.

Digital pathology and microscopic image analysis play an important role in cell morphology research. In particular, the effective segmentation of White Blood Cells (WBCs) remains a challenging problem due to the blurring boundaries of WBCs under rapid staining, as well as the adhesion between leukocytes and other cells. In this paper, we propose a novel WBC (including nuclei and cells) segmentation algorithm based on both sparsity and geometry constraints. Specifically, we first construct a sparse image representation via combining the HSL color space and the RGB color channels, followed by the use of a sparsity constraint to only preserve useful information from the nuclei features. In addition, we introduce a robust model fitting strategy (i.e., the geometry constraint) to detect cells. Our model fitting strategy is able to significantly improve the robustness of the proposed segmentation algorithm against outliers that could seriously contaminate WBCs. The experimental results show that the proposed algorithm presents clear advantages over the state-of-the-art WBC segmentation algorithms in terms of accuracy.

Accurate fire load (combustible objects) information is crucial for safety design and resilience assessment of buildings. Traditional fire load acquisition methods, such as fire load survey, which are time-consuming, tedious, and error-prone, failed to adapt to dynamic changed indoor scenes. As a starting point of automatic fire load estimation, fast recognition and detection of indoor fire load are important. Thus, this research proposes a computer vision-based method to automatically detect indoor fire loads using deep learning-based instance segmentation. First, indoor elements are classified into different categories according to their material composition. Next, an image dataset of indoor scenes with instance annotations is developed. Finally, a deep learning model, based on Mask R-CNN, is developed and trained using transfer learning to detect fire loads in images. Experimental results show that our model achieves promising accuracy, as measured by an average precision (AP) of 40.5% and AP50 of 59.2%, for instance segmentation on the dataset. A comparison with manual detection demonstrates the method’s high efficiency as it can detect fire load 1200 times faster than humans. This research contributes to the body of knowledge 1) a novel method of high accuracy and efficiency for automated fire load recognition in indoor environments based on instance segmentation; 2) training techniques for a deep learning model in a relatively small dataset of indoor images which includes complex scenes and a variety of instances; and 3) an image dataset with annotations of indoor fire loads. Although instance segmentation has been applied for several years, this is a pioneering research on using it for automated indoor fire load recognition, which paves the foundation for automatic fire load estimation and resilience assessment for the built environment.

Site planning and building design results are generally managed in Geographic Information System (GIS) and Building Information Modeling/Model (BIM) separately. The incompatibility of data has brought potential challenges for the assessment and delivery of the results. A data integration and simplification framework for improving site planning and building design is proposed in this paper. A BIM-GIS integrated model with a multi-scale data structure is developed to link the results of site planning and building design together. Geometric optimization algorithms are then designed to generate simplified building models with different levels of details (LODs) based on the information required at each scale. This paper provides a feasible way to integrate planning and design data from different sources to enhance the evaluation and delivery of the results. The proposed approach is validated by a village construction project in east China, and results show that the method is capable to integrate site planning and building design results from different platforms and support seamless visualization of multi-scale geometric data. It is also found that a seamless database facilitates understanding of planning and design results and improves communication efficiency. Currently, the main limitation of this paper is the limited access to 3D real-world data, and data collection techniques like point cloud are expected to solve the problem.

Tunnel engineering is one of the typical megaprojects given its long construction period, high construction costs and potential risks. Tunnel boring machines (TBMs) are widely used in tunnel engineering to improve work efficiency and safety. During the tunneling process, large amount of monitoring data has been recorded by TBMs to ensure construction safety. Analysis of the massive real-time monitoring data still lacks sufficiently effective methods and needs to be done manually in many cases, which brings potential dangers to construction safety. This paper proposes a hybrid data mining (DM) approach to process the real-time monitoring data from TBM automatically. Three different DM techniques are combined to improve mining process and support safety management process. In order to provide people with the experience required for on-site abnormal judgement, association rule algorithm is carried out to extract relationships among TBM parameters. To supplement the formation information required for construction decision-making process, a decision tree model is developed to classify formation data. Finally, the rate of penetration (ROP) is evaluated by neural network models to find abnormal data and give early warning. The proposed method was applied to a tunnel project in China and the application results verified that the method provided an accurate and efficient way to analyze real-time TBM monitoring data for safety management during TBM construction.

With the development of modern information technologies and more frequent utilization of information systems to operation and maintenance (O&M) management, a great amount of O&M data are collected nowadays. However, because of the large volume and poor quality, as well as a lack of effective data analysis techniques, these data are rarely analyzed and translated into useful knowledge for O&M decisions. This study presents a data model, which is named as datacube with multi-dimensional and unrestrained characteristics, for these data to better support data mining algorithms. The model organizes all the different data in both relational database and in the memories and is able to support analysis-requirements-oriented data extractions. Based on this datacube, an O&M data mining approach is proposed with procedures of data preparation, data clustering and data mining. The proposed datacube-based data mining approach was applied to the Kunming Chang Shui international airport terminal. More than 7 years on-site repairing data were used for data mining and the outcomes verified the model and the approach to be feasible and valuable for improving O&M management.