The purpose of this research is to establish a method of detecting and diagnosing faults in heat source systems by applying machine learning. In a previous paper, a fault database that includes six types of fault conditions was generated through detailed simulation, the features of the faults were extracted from the database using a Convolutional Neural Network (CNN), and it was elucidated that Fault Detection and Diagnosis (FDD) was possible by the learned CNN. However, preprocessing of the raw fault database was not examined for more appropriate diagnosis of the real data called Building Energy Management System (BEMS) data. The objective of this study is to propose a method for preprocessing the raw fault data and to elucidate the effectiveness of the FDD with the proposed preprocessing method compared to BEMS data analysis. The operation data collected in 1 day was regarded as 1 data to be learned or diagnosed. We targeted a heat source system that comprises two chillers and cooling towers, pumps for chilled water and condenser water respectively, and secondary chilled water pumps. First, we generated the fault database that has 39 types of faults such as improper set values and sensor errors. The simulation for the database was run based on the input from real data over one year in 2013. Then, we conducted four case studies on the preprocessing of the database as follows: -Case1, a case that utilizes the normalized database -Case2, a case that utilizes the normalized discrepancy between the condition without faults and the fault data -Case3, a case wherein extracted data that is different from the condition without faults in addition to Case2 -Case4, a case where the number of each fault data is equal in addition to Case3. As for the learning accuracy in the cases, the CNN learned the fault database with high accuracy in Case3 (98.5%) and Case4 (98.3%). Then, in each case, BEMS data over one year in 2014 was diagnosed and the BEMS data was analyzed based on the diagnosis. As a result of comparing the diagnosis by the CNN and the BEMS data analysis, Case4 diagnosed the BEMS data most properly, and it mainly diagnosed five types of faults according to the period when the faults actually occurred. From the above results, it was clarified that even though the system has a fault, the features of the fault do not always emerge in the data, and it emerges according to the operation of the system. This phenomenon was identified from both the diagnosis by the CNN and the BEMS data analysis. In the diagnosis of the BEMS data, there was a period when only one fault was diagnosed despite the occurrence of two types of faults. Therefore, the development of a method that enables detecting and diagnosing multiple faults more accurately is a future task.

In order to construct an environmentally conscious building, it is important to set up the construction planning concept, numerical targets, and required performance. Further it is important to lay a consistent management system from the planning stage to the operation stage and to transmit the target and required performance to the operational stage. In this research, we proposed the design of a management system and a practical method based on the planning stage as a new management method. Further we developed a resource and energy management system using BEMS data and a simulation model as a management tool. We applied this method to a real hospital and built a management system. In addition that grasps energy and resources data as per sector and purpose. We evaluated the performance in terms of energy saving and water saving, and we determined the effectiveness of this method.

This paper describes the actual condition of Aqua Marine Fukushima(AMF) damage by the Great East Japan Earthquake and Tsunami. The investigation showed that the tsunami height was 75cm at the entrance door of the AMF, and the depth of subsidence was 110cm at the outdoor aisle in front of the main entrance. Further the outdoor area condition of AMF was described. An emergency response plan was studied in the preliminary design. However, the electricity machine room and the generator machine room did not show any damage, and therefore, it was possible to restart the machines after the disaster. The process of AMF restart will be described after this paper.　

We studied the number of failures and troubles (F/T) and the required time to repair using building maintenance records in certain hospital. Our previous paper presented the characteristics and the time to repair with regard to F/T in the sickrooms, staff corners, outpatient service rooms including other consultation rooms, and medical checkup centers. This paper focuses on the F/T of the kitchen equipment, garbage processing equipment / waste water treatment equipment, medical sanitation systems, and routine works for sanitary systems. The purpose of this research is to provide information for the design from the building operation stage to planning the maintenance structure. The number of maintenance records for the kitchen equipment, garbage processing equipment / waste water treatment equipment, medical sanitation systems and routine works are 204, 27, 990, and 113, respectively. In this paper, the breakdowns of F/T were shown by four aforementioned categories. In addition, the number of F/T for new occurrences and those for equipments restored after the next day were presented. The carryover rate and the outsourcing rate of the kitchen equipment were remarkably higher than other sanitary systems and their time to repair also was longer. Therefore, the findings obtained through part1 and pard2 of the reports can be used as benchmarks for identifying the F/T of sanitary systems based on the building floor space and the number of beds in large-scale general hospitals. These findings are meaningful for use as basic information for estimating the maintenance labor burden. In addition, from the viewpoint of equipment design, it will be useful reference information for examining the availability in judging the number of installed sanitary appliances.