Search Results (33)

Water, an essential asset for life and growth, is under growing pressure due to climate change, overpopulation, pollution, and industrialization. At the same time, water distribution within cities relies on piping networks that are over 30 years old and thereby prone to leaks, cracking, and losses. Taking this into account, non-revenue water (i.e., water that is distributed to homes and facilities but not returning revenues) is estimated at almost 50%. To this end, intelligent water management via computational advanced tools is required in order to optimize water usage, to mitigate losses, and, more importantly, to ensure sustainability. To address this issue, a case study was developed in this paper, following a step-by-step methodology for the city of Heraklion, Greece, in order to introduce an intelligent water management system that integrates advanced technologies into the aging water distribution infrastructure. The first step involved the digitalization of the network’s spatial data using geographic information systems (GIS), aiming at enhancing the accuracy and accessibility of water asset mapping. This methodology allowed for the creation of a framework that formed a “digital twin”, facilitating real-time analysis and effective water management. Digital twins were developed upon real-time data, validated models, or a combination of the above in order to accurately capture, simulate, and predict the operation of the real system/process, such as water distribution networks. The next step involved the incorporation of a hydraulic simulation and modeling tool that was able to analyze and calculate accurate water flow parameters (e.g., velocity, flowrate), pressure distributions, and potential inefficiencies within the network (e.g., loss of mass balance in/out of the district metered areas). This combination provided a comprehensive overview of the water system’s functionality, fostering decision-making and operational adjustments. Lastly, automatic meter reading (AMR) devices could then provide real-time data on water consumption and pressure throughout the network. These smart water meters enabled continuous monitoring and recording of anomaly detections and allowed for enhanced control over water distribution. All of the above were implemented and depicted in a web-based environment that allows users to detect water meters, check water consumption within specific time-periods, and perform real-time simulations of the implemented water network. Full article

Challenges such as perspective distortion, irregular reading regions, and complex backgrounds in natural scenes hinder the accuracy and efficiency of automatic meter reading systems. Current mainstream approaches predominantly utilize object-detection-based methods without optimizing for text characteristics, while enhancements in detection robustness under complex backgrounds typically focus on data preprocessing rather than model architecture. To address these limitations, a novel end-to-end framework, i.e., EDPNet (Efficient DB and PARSeq Network), is proposed to integrate efficient boundary detection and text recognition. EDPNet comprises two key components, EDNet for detection and EPNet for recognition, where EDNet employs EfficientNetV2-s as its backbone with the Multi-Scale KeyDrop Attention (MSKA) and Efficient Multi-scale Attention (EMA) mechanisms to address perspective distortion and complex background challenges, respectively. During the recognition stage, EPNet integrates a DropKey Attention module into the PARSeq encoder, enhancing the recognition of irregular readings while effectively mitigating overfitting. Experimental evaluations show that EDNet achieves an F1-score of 0.997988, outperforming DBNet++ (ResNet50) by 0.61%. In challenging scenarios, EDPNet surpasses state-of-the-art methods by 0.7~1.9% while reducing parameters by 20.03%. EPNet achieves 90.0% recognition accuracy, exceeding the current best performance by 0.2%. The proposed framework delivers superior accuracy and robustness in challenging conditions while remaining lightweight. Full article

In recent years, PV power plants have been widely used on the roofs of commercial buildings with grid connections, primarily to enhance self-consumption in distributed energy systems. In addition, installing PV plants on commercial buildings’ roofs is becoming increasingly important, especially in crowded cities where land is limited. Since the Sun is an intermittent energy source, PV power plants cause frequency and voltage fluctuations in the grid. The way to avoid this problem is to install PV plants together with battery storage systems. Battery storage systems prevent frequency and voltage fluctuations in the grid and provide economic benefits. This article presents the sizing and techno-economic analysis of a factory building’s rooftop PV system with a battery. The amount of energy produced by the PV plant, PV temperature, and irradiation were recorded in a data logger obtained by various sensors. These real-time measurements were continuously collected and analyzed to evaluate system performance and assess seasonal variations.Load demand data were collected through an automatic meter reading system. The installed capacity of the PV power plant is 645 kW. The optimum battery capacity determined for this factory is 130 kW for 5 h. Techno-economic analysis was carried out using metrics such as the payback period, net present value, and levelized cost of energy. As a result of the analysis using various input variables, LCOE, NPV, and PBP were determined as 0.1467 $/kWh, 4918.3 $, and 7.03 years, respectively. Full article

Based on the traditional saddle instrument, a portable roll-profile measuring device based on a contact sensor is designed and optimized. The positioning module is added via the machine vision method, which enables the automatic reading of measurement points. The measurement accuracy of the device is 1 μm. Possible errors caused by the process of installing the roll-profile meter are analyzed, and the installation requirements of the measuring device are provided. On this basis, the compensation method for roll measurement with the roll profile is also improved. The accuracy of the measuring device is verified by measuring the roll on the spot, and the measurement error of the flat roll is 0.02 mm. When measuring the roll crown, the measurement accuracy is improved by 69% after the compensation algorithm is applied. The measurement results meet industrial measurement requirements, which is highly significant to the intelligent operation and maintenance of the roll. Full article

The meter reading work in the power distribution room of a mine is traditionally carried out by manual inspection, which requires several workers and often lacks timeliness and efficiency. Owing to the widespread use of quadruped robots, this paper proposes a Mining Automatic Meter Reading System, named MAMRS, to identify and read pointer and digital meters in mine distribution rooms using quadruped robots. The new method consists of three stages. Initially, this technique identifies the type of meter using the ResNet18 convolutional neural network model, then proceeds to extract the dial area image using the YOLOv5 object detection algorithm, and finally reads the pointer and digital meters’ data using the U2-net algorithm and SVM, respectively. Experimental results show that the recognition accuracy rates for meter classification, pointer meter reading, and digital meter reading are 99.87%, 85.35%, and 90.73%, respectively. The MAMRS fulfills the need for fully automated and intelligent inspection of mine distribution rooms, resulting in significantly enhanced accuracy, flexibility, and innovation in inspection processes. Moreover, it reduces labor costs and improves inspection efficiency. The findings of this study serve as a reliable reference for intelligent inspection practices in the power distribution rooms of metal mines. Full article

The automatic reading recognition of pointer meters plays a crucial role in data monitoring and analysis in intelligent substations. Existing meter reading methods struggle to address challenging difficulties such as image distortion and varying illumination. To enhance their robustness and accuracy, this study proposes a novel approach that leverages the TransUNet semantic segmentation model and a perspective transformation correction method. Initially, the dial of the pointer meter is localized from the natural background using YOLOv8. Subsequently, after enhancing the image with Gamma correction technology, the scale lines and the pointer within the dial are extracted using the TransUNet model. The distorted or rotated dial can then be corrected through perspective transformation. Finally, the meter readings are accurately obtained by the Weighted Angle Method (WAM). Ablative and comparative experiments on two self-collected datasets clearly verify the effectiveness of the proposed method, with a reading accuracy of 97.81% on Simple-MeterData and 93.39% on Complex-MeterData, respectively. Full article

With the increasing complexity of the grid meter dial, precise feature extraction is becoming more and more difficult. Many automatic recognition solutions have been proposed for grid meter readings. However, traditional inspection methods cannot guarantee detection accuracy in complex environments. So, deep-learning methods are combined with grid meter recognition. Existing recognition systems that utilize segmentation models exhibit very high computation. It is challenging to ensure high real-time performance in edge computing devices. Therefore, an improved meter recognition model based on YOLOv7 is proposed in this paper. Partial convolution (PConv) is introduced into YOLOv7 to create a lighter network. Different PConv introduction locations on the base module have been used in order to find the optimal approach for reducing the parameters and floating point of operations (FLOPs). Meanwhile, the dynamic head (DyHead) module is utilized to enhance the attention mechanism for the YOLOv7 model. It can improve the detection accuracy of striped objects. As a result, this paper achieves ${\mathrm{mAP}}_{50}^{val}$ of 97.87% and ${\mathrm{mAP}}_{50:90}^{val}$ of 62.4% with only 5.37 M parameters. The improved model’s inference speed can reach 108 frames per second (FPS). It enables detection accuracy that can reach $\pm 0.1$ degrees in the grid meter. Full article

This paper aims to enhance the existing Automatic Meter Reading (AMR) technologies for utilities in the public services sector, such as water, electricity, and gas, by allowing users to regularly upload images of their meters, which are then automatically processed by machines for digit recognition. We propose an end-to-end AMR approach designed explicitly for unconstrained environments, offering practical solutions to common failures encountered during the automatic recognition process, such as image blur, perspective distortion, partial reflection, poor lighting, missing digits, and intermediate digit states, to reduce the failure rate of automatic meter readings. The system’s first stage involves checking the quality of the user-uploaded images through the SVM method and requesting re-uploads for images unsuitable for digit extraction and recognition. The second stage employs deep learning models for digit localization and recognition, automatically detecting and correcting issues such as missing and intermediate digits to enhance the accuracy of automatic meter readings. Our research established a gas meter training dataset comprising 52,000 images, extensively annotated across various degrees, to train the deep learning models for high-precision digit recognition. Experimental results demonstrate that, with the simple SVM model, an accuracy of 87.03% is achieved for the classification of blurry image types. In addition, meter digit recognition (including intermediate digit states) can reach 97.6% (mAP), and the detection and correction of missing digits can be as high as 63.64%, showcasing the practical application value of the system developed in this study. Full article

The demand response program is an important feature of the smart grid. It attempts to reduce peak demand, improve the smart grid efficiency, and ensure system reliability. Implementing demand-response programs in residential and commercial buildings requires the use of smart meters and smart plugs. In this paper, we propose an architecture for a home-energy-management system based on the fog-computing paradigm, an Internet-of-Things-enabled smart plug, and a smart meter. The smart plug measures in real-time the root mean square (RMS) value of the current, frequency, power factor, active power, and reactive power. These readings are subsequently transmitted to the smart meter through the Zigbee network. Tiny machine learning algorithms are used at the smart meter to identify appliances automatically. The smart meter and smart plug were prototyped by using Raspberry Pi and Arduino, respectively. The smart plug’s accuracy was quantified by comparing it to laboratory measurements. To assess the speed and precision of the small machine learning algorithm, a publicly accessible dataset was utilized. The obtained results indicate that the accuracy of both the smart meter and the smart plug exceeds 97% and 99%, respectively. The execution of the trained decision tree and support vector machine algorithms was verified on the Raspberry Pi 3 Model B Rev 1.2, operating at a clock speed of 600 MHz. The measured latency for the decision tree classifier’s inference was 1.59 microseconds. In a practical situation, the time-of-use-based demand-response program can reduce the power cost by about 30%. Full article

This study implements techno-economic evaluations of different photovoltaic (PV) systems in the East Midlands of the UK. Three application case studies, including an office building, a domestic building, and a poultry shed, are achieved. The building electricity consumption is obtained according to hourly automatic meter readings, and the PV electricity production is predicted based on the Engineering Equation Solver 8.4 software. Meanwhile, the 25-years’ complete economic profitability investigations of the three PV systems are conducted on the basis of the Monte Carlo method; the sensitivity analyses of payback period and net present value are also carried out by using the @RISK 8 software. Furthermore, the payback period and yearly savings are investigated and compared between the Smart Export Guarantee (SEG) and feed-in tariff (FiT) schemes. Technical investigation outcomes conclude that the three PV systems are able to satisfy electrical energy requirements in summer, and the additional electricity could be exported to the grid in this period. In winter, however, the systems have less electricity output resulting in power shortage and input from the grid. Economic study results exhibit that the net present values of the office building, domestic building, and poultry shed are £9108.4, £1717.91, and £7275.86, respectively, corresponding to the payback periods of 6.15 years, 9.12 years, and 9.41 years. This implies that there is an acceptable payback period (<10 years) for the PV system installation; meanwhile, the FiT scheme has the shorter payback period compared with the SGE scheme. Full article

The current manual reading of substation pointer meters wastes human resources, and existing algorithms have limitations in accuracy and robustness for detecting various pointer meters. This paper proposes a method for recognizing pointer meters based on Yolov7 and Hough transform to improve their automatic readability. The proposed method consists of three main contributions: (1) Using Yolov7 object detection technology, which is the latest Yolo technology, to enhance instrument recognition accuracy. (2) Providing a formula for calculating the angle of a square pointer meter after Hough transformation. (3) Applying OCR recognition to the instrument dial to obtain the model and scale value. This information helps differentiate between meter models and determine the measuring range. Test results demonstrate that the proposed algorithm achieves high accuracy and robustness in detecting different types and ranges of instruments. The map of the Yolov7 model on the instrument dataset is as high as 99.8%. Additionally, the accuracy of pointer readings obtained using this method exceeds 95%, indicating promising applications for a wide range of scenarios. Full article

Meter reading is an important part of intelligent inspection, and the current meter reading method based on target detection has problems of low accuracy and large error. In order to improve the accuracy of automatic meter reading, this paper proposes an automatic reading method for pointer-type meters based on the YOLOv5-Meter Reading (YOLOv5-MR) model. Firstly, in order to improve the detection performance of small targets in YOLOv5 framework, a multi-scale target detection layer is added to the YOLOv5 framework, and a set of Anchors is designed based on the lightning rod dial data set; secondly, the loss function and up-sampling method are improved to enhance the model training convergence speed and obtain the optimal up-sampling parameters; Finally, a new external circle fitting method of the dial is proposed, and the dial reading is calculated by the center angle algorithm. The experimental results on the self-built dataset show that the Mean Average Precision (mAP) of the YOLOv5-MR target detection model reaches 79%, which is 3% better than the YOLOv5 model, and outperforms other advanced pointer-type meter reading models. Full article

The ongoing reading process of digital meters is time-consuming and prone to errors, as operators capture images and manually update the system with the new readings. This work proposes to automate this operation through a deep learning-powered solution for universal controllers and flow meters that can be seamlessly incorporated into operators’ existing workflow. Firstly, the digital display area of the equipment is extracted with a screen detection module, and a perspective correction step is performed. Subsequently, the text regions are identified with a fine-tuned EAST text detector, and the important readings are selected through template matching based on the expected graphical structure. Finally, a fine-tuned convolutional recurrent neural network model recognizes the text and registers it. Evaluation experiments confirm the robustness and potential for workload reduction of the proposed system, which correctly extracts 55.47% and 63.70% of the values for reading in universal controllers, and 73.08% of the values from flow meters. Furthermore, this pipeline performs in real time in a low-end mobile device, with an average execution time in preview of under 250 ms for screen detection and on an acquired photo of 1500 ms for the entire pipeline. Full article

Many tasks that require a large workforce are automated. In many areas of the world, the consumption of utilities, such as electricity, gas and water, is monitored by meters that need to be read by humans. The reading of such meters requires the presence of an employee or a representative of the utility provider. Automatic meter reading is crucial in the implementation of smart grids. For this reason, with the aim to boost the implementation of the smart grid paradigm, in this paper, we propose a method aimed to automatically read digits from a dial meter. In detail, the proposed method aims to localise the dial meter from an image, to detect the digits and to classify the digits. Deep learning is exploited, and, in particular, the YOLOv5s model is considered for the localisation of digits and for their recognition. An experimental real-world case study is presented to confirm the effectiveness of the proposed method for automatic digit localisation recognition from dial meters. Full article

Electricity consumption is rising due to population growth, climate change, urbanization, and the increasing use of electronic devices. The trend of the Internet of Things has contributed to the creation of devices that promote the thrift and efficient use of electrical energy. Currently, most projects relating to this issue focus solely on monitoring energy consumption without providing relevant parameters or switching on/off electronic devices. Therefore, this paper presents in detail the design, construction, and validation of a smart meter with load control aimed at being part of a home energy management system. With its own electronic design, the proposal differs from others in many aspects. For example, it was developed using a simple IoT architecture with in-built WiFi technology to enable direct connection to the internet, while at the same time being big enough to be part of standardized electrical enclosures. Unlike other smart meters with load control, this one not only provides the amount of energy consumption, but rms current and voltage, active, reactive, and apparent power, reactive energy, and power factor—parameters that could be useful for future studies. In addition, this work presents evidence based on experimentation that the prototype in all its readings achieves an absolute percentage error of less than 1%. A real-life application of the device was also demonstrated in this document by measuring different appliances and switching them on/off manually and automatically using a web-deployed application. Full article