Across the globe, smart meters and Advanced Metering Infrastructure (AMI) are emerging technologies extensively deployed by key players in the energy sector. As Hong Kong’s largest electricity utility, CLP Power Hong Kong Limited (CLP Power) is committed to installing 2.8 million smart meters by 2025 to support the government’s smart city initiative. To address the growing challenges of maintaining meter asset health amid increasing meter volumes, CLP Power’s Smart Metering Remote Monitoring Centre (SMRMC) developed the Meter Malfunction Analyser (MMA). This condition monitoring system consolidates, analyses, and visualises smart meter data on a centralised platform. Leveraging the MMA has substantially reduced the triage time per case, achieving a total of 70% reduction in overall processing time. The number of alarms requiring review has decreased to one-sixth of the previous daily average, while overall precision has more than quadrupled. The MMA has maximised the value of big data as a strategic asset, enhancing condition monitoring performance, streamlining SMRMC operations, and strengthening gatekeeping mechanisms for grid-side irregularities. This data analytics foundation is set to pave the way for CLP’s sustainable development in the digitalisation of metering operations in Hong Kong.
Category: ypec-2024
This project presents an innovative approach for detecting defects in train wheels within the MTR network, leveraging vibration detection at railway points. The current methods of in- workshop wheel defect inspection, such as visual inspection and ultrasonic techniques, are limited by their interval-based scheduling and partial coverage of the wheel tread area. To address these limitations, this project uses artificial intelligence to extend the functionality of existing point vibration monitoring systems to detect abnormalities in train wheels and predict maintenance needs. The proposed system is expected to optimize maintenance resources, reduce unscheduled downtime, and advance the MTR’s operational capabilities through AI-driven predictive analytics. This project underscores the potential of this technology to revolutionize train wheel maintenance by providing a more efficient, accurate, and cost-effective solution. The effectiveness of this invention has been proven by cross-checking with existing maintenance logs of train wheels. Subject to data quality, our invention could predict wheel turning maintenance need for train wheels in the next five days with an accuracy of around 60%. It was found that our invention was most effective in detecting wheel flats and cavities.
Traditional DC-DC converter topology derivation methods typically depend on human expertise, which is largely learned from existing topologies. This reliance may restrict the diversity of the results due to the limitations inherent in human learning capacity. In this letter, artificial intelligence (AI) is employed to compensate for human learning capabilities, and a novel hybrid-learning topology derivation method is proposed. In the method, graph variational auto-encoders (GraphVAE) is utilized to learn topology generative rules from existing topologies directly. Besides, human expertise is further integrated into GraphVAE to refine these generative rulers, so that the proposed method can derive topologies by combining AI and human insights. To demonstrate the effectiveness of the proposed method, we applied it to the discovery of single-switch converters (SSCs). The GraphVAE model is trained by 135 existing SSCs and successfully derives 78 new SSC topologies with different performance characteristics. These results highlight the method’s ability to enhance both the efficiency and creativity in deriving topologies.
The ELEMENTS mall in Hong Kong, operated by MTR Corporation Limited (MTRC), is spearheading a pioneering project to address the energy efficiency and indoor environmental challenges faced by buildings over two decades old. At the core of this initiative is an advanced AI platform seamlessly integrated into the NEURON digital system, targeting the enhancement of the Mechanical Ventilation and Air Conditioning (MVAC) system. This collaborative effort involves MTRC, Arup providing technical Retro-Commissioning (RCx) consultancy, and Neuron Operations Limited offering strategic AI and Machine Learning (ML) expertise. The project leverages AI and ML techniques, such as Recurrent Neural Networks (RNNs) and Long Short-Term Memory (LSTM), to refine MVAC operations, optimize chiller efficiency, and enable real-time optimization through predictive regression forecasting. The results have been impressive, with the initiative achieving a minimum of 9% annual reduction in MVAC energy consumption. Improvements in airside optimization and Indoor Air Quality (IAQ) have been realized through sensor-enabled monitoring of occupancy levels, enabling proactive adjustments to ventilation and temperature settings. Critically, the project incorporates a data quality assessment framework, facilitating continuous Retro-Commissioning and seamless AI integration. This innovative dual approach of supervised machine learning and self-adaptive reinforcement learning sets a new benchmark in the industry.
As essential equipment, autonomous underwater vehicles (AUVs) play a vital role in ocean detection, pipeline inspection, and military patrol. However, the cruise time is always limited by the low energy capacity. Wireless power transfer (WPT) technology is regarded as a safe and effective energy supply method for AUVs in the future. Conventionally, the magnetic core in WPT systems is spliced by pieces of ferrites, which is time-consuming and makes it difficult to realize a seamless fit on the curved surface. This project proposes and designs a compact coupler with a novel flexible nanocrystalline flake ribbon (NFR) magnetic core. The NFR not only enhances the application flexibility of the WPT system but also significantly reduces the system’s weight. The transmission characteristics and temperature performance of the AUV WPT system have been investigated under different power levels. Finally, the NFR with a permeability of 800 is chosen as the magnetic core, and the DC-DC system efficiency reaches 92.85% with 1 kW output power. Moreover, the maximum temperature can be restricted to 54.1 ℃, and the weight of the NFR cores is 290 g, accounting for merely 4.65% of the coupler.
Our research introduces a novel dynamic wireless charging system for Automated Guided Vehicles (AGVs), a rapidly growing market segment in the era of automation. The primary innovation of our project lies in enhancing AGV’s operational efficiency through dynamic wireless charging, offering significant market value. We employ a Tetris-shaped transmitting coil array, a unique approach that effectively mitigates primary-secondary mutual inductance fluctuation. Moreover, our system utilizes a newly proposed periodic energy control on the secondary side, eliminating the need for primary-secondary communication. These innovations not only improve AGV performance but also promise to revolutionize the wireless charging industry.
Due to the proliferation of information, both Artificial Intelligence (Al) and High-Performance Computing (HPC) are experiencing heightened demands. However, the use of conventional electronic integrated circuits, which consumes substantial physical space and energy during the transmission and processing of massive data, imposes limitations on the growth of HPC and Al. Consequently, the industry urgently needs a novel generation of high-speed and low-latency optical interconnection and computing technology. Leveraging the industry’s top-rated optical material, lithium niobate (LN), we have pioneered a wafer-scale nanofabrication technology. This innovation allows us to deliver a photonic system-on-chip that simultaneously features ultrahigh-speed electro-optic modulation and low-loss chip-scale integration while dramatically reducing size and electric energy consumption by >1000. A significant boost in device performance. We’re not just improving the technology – we’re redefining it.