For diagnosing the root cause of a fault, we developed an automated fault detection and diagnosis (AFDD) method for cooling plants, which are water-side HVAC systems. In our initial paper (part 1), we described in detail the proposed AFDD method which uses convolutional neural networks (CNN) based deep learning approach and demonstrated its effectiveness. First, the original simulation program of the cooling plant is described. In addition, we show that the system behavior during faults can be calculated by providing the fault conditions. Based on such conditions, a fault database is generated, and the features of which learned using CNN to determine which faulty behavior is close to the actual data. In our second paper (part 2), we expanded the number of fault types from 6 in the first paper to 39 and discussed the data preprocessing method to achieve a high diagnosis performance. In addition, the severity setting of the faults and the diagnostic characteristics of multiple faults were examined and analyzed in a previous related paper. As building and energy management system (BEMS) data continue to be accumulated, sufficient operational data exists for AFDD. However, there is a possibility that multiple faults, including sensor errors, will occur simultaneously in an actual system, and there are only a few effective methods for such data, and only a few applications of AFDD for BEMS data. Based on the above, we constructed a demonstration system for the proposed method and improved the operation based on the AFDD results. The primary objective of this paper is to provide an evaluation of the demonstration system and operational improvements. In the demonstration system, AFDD is automatically executed every day, and the diagnosis results and related system behaviors can be confirmed on a web browser. After discussions with local operators, the lower limit of the condenser water pump frequency, which had been diagnosed as a fault, was adjusted lower. The analysis and simulation of the BEMS data confirmed that an energy saving of approximately 3% can be achieved. The proposed method requires the construction of a simulation program, the generation of a fault database, and the training of CNN for each system, which is expensive in terms of the number of human resources and computations. Therefore, the second objective of this paper is to apply transfer learning to a similar system to reduce the computational cost of learning, and to confirm the accuracy and effectiveness of transfer learning. In addition to the trained CNN created using the proposed method, we also tried to use a pre-trained network called VGG-16 for image recognition, which is trained on more than one million images. As a result, it was shown that transfer learning reduces the computation time by approximately half when introducing AFDD to a new system, while still providing useful a BEMS data diagnosis performance. However, when transfer learning was applied to VGG-16, a sufficient performance could not be obtained. This can be attributed to the fact that the characteristics of the fault data of a cooling plant are unique to a general image. The scalability of the method is important for the widespread use of AFDD. We believe that the application of transfer learning will contribute to this scalability. Maintaining a fault database of an HVAC system is expected to contribute to an improved the scalability of the AFDD method because its features can be used for transfer learning.

In this paper, a method is proposed for generating time-series data simulating natural wind. This method can be applied to indoor ventilation and air conditioning. The simulation of natural wind described in this paper does not demonstrate a reproduction of the waveform of the sampling data, but rather a reproduction of the statistical characteristics of natural wind. First, we clarified the fundamental relation between the turbulence Intensity and frequency distribution of natural wind. In addition, we analyzed the characteristics of the time series data of natural wind based on a logistic map. We then clarified the stochastic structure of the coefficients used in the recurrence formula of the logistic map. Finally, we proposed a new BCM method through which natural wind is simulated at any mean velocity. In the BCM (Fig. 6) proposed in this paper, the frequency distribution of the wind speed is approximated based on a Weibull distribution. The turbulence intensity and mean wind velocity can be reproduced through a Weibull distribution approximation. The inverse function of the cumulative distribution of the Weibull distribution can be used to generate the elements of the probability distribution. The elements are always newly generated using the inverse function. A logistic map is used to reconstruct the elements of the probability distribution, that is, the wind speed, as time series data. In the logistic map, the probability distribution of the coefficient used in a recurrence formula is approximated using the corrected sigmoid function (Equation (10)). As a result of BCM, the waveform of the time series data (Fig. 10) was similar to that of natural wind. The frequency distribution of the wind speed and the reproduction of the turbulence intensity (Fig. 11) were also properly simulated. In addition, Chapter 5 shows how to adjust the average wind speed as required for ventilation and air conditioning. The purpose of simulating natural wind with air conditioning and ventilation is to provide unsteady wind comfort. Chaos is related to the comfort of unsteady winds, and thus, as an advantage of BCM, the characteristics of chaos can be easily evaluated using the method described in Section 3.1. The acceleration can also be approximated using the BCM * shown in Section 4.3. As a subject for future research, it is necessary to consider the change in wind speed and waveform from fan to living area. This may be achieved by modeling the change in waveform owing to the difference in velocity.

In an effort to realize a decarbonized society, it is becoming increasingly important to plan for and design the reduction of hot-water energy consumption, sparticularly in buildings with high hot-water usage. The objective of this study is to develop a practical water supply system simulation tool for calculating the energy consumption of a water heating system by calculating the water heating load profile while taking into account heat losses from the piping and storage tank as well as the equipment characteristics of the heating device in the system. In this report, the equipment and piping were subdivided into modules, a calculation method was constructed to calculate the water volume and water temperature sequentially, and an example calculation using this tool was presented for examining the resource and energy conservation in a hot-water supply system.

To achieve carbon neutrality, there is a strong need for new energy-saving methods that can be easily applied to existing facilities that consume large amounts of energy. The purpose of this study is to save energy by improving the efficiency of the variable water volume control of cold and hot water. In our previous report, we showed that will be possible to reduce the differential pressure of the pump and improve the efficiency of the variable water volume control, by confirming the state of the air conditioning system. In addition, we reported that the energy consumption of the cold water secondary pump was reduced by 55% and the WTF was 350 or higher in existing facility. We then proposed several types of confirmation methods for reducing the differential pressure. Herein, we report the following the pressure verfications during an intermediate period. The effect on the capacity for further energy saving was examined at an existing facility. We also examined the reduction of the lower limit of the pump rotation speed and the further reduction of the differential when the hot water pressure was reduced. The analysis results show that the temperature difference between the cold and hot water flows increased owing to the reduction of the differential pressure. The WTF of cold water was 700 or higher, and the WTF of hot water was 350 or greater. The temperature difference was also 20°C or higher. Based on these verifications, we propose a method for confirming the air conditioning state and thus improve the efficiency of the variable water volume control by reducing the differential pressure.

The purpose of this study is to update the water supply units(quantity) for the daily water supply load, which reflects recent water saving, as the basic unit for the design of both regular and hot water supply systems. In our initial report, we proposed the use of water supply units for hospitals, and in our second report, we proposed their use for elementary, junior high, and high schools. This third report describes a proposal for their use in an office. Many surveys and analyses regarding water usage in an office have been published. However, their findings are limited to reports from the Society subcommittee. Therefore, in this report, based on an examination of the data obtained from previous studies, we propose the design of a new water supply unit that reflects the water usage in recent years.