Andrea Staino

Bio: Andrea Staino is an academic researcher from Trinity College, Dublin. The author has contributed to research in topics: Wind power & Turbine. The author has an hindex of 10, co-authored 29 publications receiving 513 citations. Previous affiliations of Andrea Staino include Alstom & University of Calabria.

Artificial intelligence-based fault detection and diagnosis methods for building energy systems: Advantages, challenges and the future

Abstract: Artificial intelligence has showed powerful capacity in detecting and diagnosing faults of building energy systems. This paper aims at making a comprehensive literature review of artificial intelligence-based fault detection and diagnosis (FDD) methods for building energy systems in the past twenty years from 1998 to 2018, summarizing the strengths and shortcomings of the existing artificial intelligence-based methods, and revealing the most important research tasks in the future. Challenges in developing FDD methods for building energy systems are discussed firstly. Then, a comprehensive literature review is made. All methods are classified into two categories, i.e. data driven-based and knowledge driven-based. The data driven-based methods are abundant, including the classification-based, unsupervised learning-based and regression-based. They showed powerful capacity in learning patterns from training data. But, they need a large amount of training data, and have problems in reliability and robustness. The knowledge driven-based methods show powerful capacity in simulating the diagnostic thinking of experts. But, they rely on expert knowledge heavily. It is concluded that new artificial intelligence-based methodologies are needed to be able to combine the advantages of both kinds of methods in the future.

A review of strategies for building energy management system: Model predictive control, demand side management, optimization, and fault detect & diagnosis

Abstract: Building energy use is expected to grow by more than 40% in the next 20 years. Electricity remains the largest energy source consumed by buildings, and that demand is growing. To mitigate the impact of the growing demand, strategies are needed to improve buildings' energy efficiency. In residential buildings home appliances, water, and space heating are answerable for the increase of energy use, while space heating and other miscellaneous equipment are behind the increase of energy utilization in non-residential buildings. Building energy management systems support building managers and proprietors to increase energy efficiency in modern and existing buildings, non-residential and residential buildings can benefit from building energy management system to decrease energy use. Base on the type of building, different management strategies can be used to achieve energy savings. This paper presents a review of management strategies for building energy management systems for improving energy efficiency. Different management strategies are investigated in non-residential and residential buildings. Following this, the reviewed researches are discussed in terms of the type of buildings, building systems, and management strategies. Lastly, the paper discusses future challenges for the increase of energy efficiency in building energy management system.

Multi-Objective Optimization Model of Source–Load–Storage Synergetic Dispatch for a Building Energy Management System Based on TOU Price Demand Response

Abstract: The optimized operation of a building energy management system (BEMS) is of great significance to its operation security, economy, and efficiency. This paper proposes a day-ahead multiobjective optimization model for the BEMS under time-of-use price-based demand response (DR), which integrates building integrated photovoltaic with other generations to optimize the economy and occupants’ comfort by the synergetic dispatch of source–load–storage. The occupants' comfort contains three aspects of the indoor environment: visual comfort; thermal comfort; and indoor air quality comfort. With the consideration of controllable load that could participate in DR programs, the balances among different energy styles, electric, thermal, and cooling loads are guaranteed during the optimized operation. YALMIP toolbox in MATLAB was applied to solve the optimization problem. Finally, a case study was conducted to validate the effectiveness and adaptability of the proposed model.

Quantitative assessment of MRI lesion load in multiple sclerosis: A comparison of conventional spin-echo with fast fluid-attenuated inversion recovery

Abstract: In this study, we compared a fast fluid-attenuated inversion recovery (fast-FLAIR) sequence to conventional spin-echo (CSE) in the evaluation of brain MRI lesion loads of seven patients with clinically definite multiple sclerosis. Interleaved CSE (3000/20, 5 mm contiguous axial slices) and fast-FLAIR (9000/150/2200, 5 mm contiguous axial slices) sequences were performed on a 1.0 T machine. Lesions were counted consensually by two observers and then segmented independently by two other observers using a local thresholding technique, with subsequent manual editing in the case of poorly defined lesions. Four hundred and two lesions were detected in at least one of the two sequences: 128 were seen only on fast-FLAIR, 17 only on CSE. Forty-one lesions were larger on fast-FLAIR, while no lesion was considered larger on CSE. The numbers of periventricular (P = 0.05), cortical/subcortical (P = 0.02) and discrete (P = 0.05) lesions detected using fast-FLAIR were higher than those detected using CSE. The median lesion load was 7185 mm3 on CSE and 8418 mm3 on the fast-FLAIR, the average being 18% (range = 11.6-29%) higher on the fast-FLAIR images. Lesion contrast ratio was higher for lesions on the fast-FLAIR than on the CSE sequence (P < 0.0001). The percentages of poorly defined lesions which needed manual editing after the local thresholding technique was applied and the total time needed for the measurements were lower (P < 0.001) when fast-FLAIR images were used compared with CSE. This resulted in a reduced inter-rater coefficient of variation in measuring lesion volumes. Our data indicate that fast-FLAIR sequences are more sensitive than CSE in detecting multiple sclerosis lesion burden and that fast-FLAIR is a promising technique for natural history studies and clinical trials in multiple sclerosis.