Research on an Equivalent Heat Source Model of the AC Arc in the Short Gap of a Copper-Core Cable and a Fire Risk Assessment Method.

The magnetohydrodynamics (MHD) model of the alternating current (AC) arc is complex, so a simplified equivalent heat source (EHS) model can be used to replace the complex model in studying the AC arc's thermal characteristics and cable fire risk. A 2D axisymmetric AC arc MHD simulation model in the short gap of a copper-core cable is established in this paper. The AC arc voltage and current obtained by the model are consistent with experiments. The AC arc's heat source distribution obtained by the MHD model is fitted to obtain the heat source function Q of the AC arc. Q is divided into 16 independent segmented heat sources, and a correction matrix is constructed to optimize the segmented heat sources. A neural network and a genetic algorithm give the prediction model and the optimal correction matrix of the segmented heat source. The EHS model optimized by the optimal correction matrix can obtain a minimum temperature error of 5.8/4.4/4.2% with the MHD model in different AC arc peak currents 2/4/6 A. The probability of a cable fire is calculated by using AC arc's optimized EHS model when different numbers of AC arcs are generated randomly in AC half-waves. The EHS model can replace the complex MHD model to study the thermal characteristics of AC arcs and quickly calculate the probability of a cable fire caused by random AC arcs.

Numerical investigations of AC arcs' thermal characteristics in the short gap of copper-cored wires.

Excessive alternating current (AC) arcs generated in electric systems will accumulate heat and easily cause fire. This paper studies the thermal characteristics of different numbers of AC arc plasma generated in a short gap of copper-cored wires in the air. The number of AC arcs is controlled in the AC arc experiment and an infrared thermal imager measures the temperature change at the specified position. Based on magnetohydrodynamics (MHD), a two-dimensional axisymmetric AC arc discharge numerical simulation model is established. The volt-ampere characteristic of the AC arc is used to solve the MHD simulation model to obtain the same 'zero current' characteristics as the real AC arc in the experiment. A large amount of heat accumulates in the electrode gaps when the arc generation, and then the heat dissipates in the 'zero current' stage. The continuously generated arc makes the temperature higher. The volume of the space area with a temperature higher than 10,000 K increases with the arc current, but is unrelated to the number of arcs. The volume of the space area with a temperature higher than 524.15 K and the temperature on the electrode are both positively correlated with the number of AC arcs and arc current. The results of this study can provide a reference for the detection standard of AC arc faults and the prevention of electrical fire.

Rapid dataset generation methods for stacked construction solid waste based on machine vision and deep learning.

The development of urbanization has brought convenience to people, but it has also brought a lot of harmful construction solid waste. The machine vision detection algorithm is the crucial technology for finely sorting solid waste, which is faster and more stable than traditional methods. However, accurate identification relies on large datasets, while the datasets from the field working conditions are scarce, and the manual annotation cost of datasets is high. To rapidly and automatically generate datasets for stacked construction waste, an acquisition and detection platform was built to automatically collect different groups of RGB-D images for instances labeling. Then, based on the distribution points generation theory and data augmentation algorithm, a rapid-generation method for synthetic construction solid waste datasets was proposed. Additionally, two automatic annotation methods for real stacked construction solid waste datasets based on semi-supervised self-training and RGB-D fusion edge detection were proposed, and datasets under real-world conditions yield better models training results. Finally, two different working conditions were designed to validate these methods. Under the simple working condition, the generated dataset achieved an F1-score of 95.98, higher than 94.81 for the manually labeled dataset. In the complicated working condition, the F1-score obtained by the rapid generation method reached 97.74. In contrast, the F1-score of the dataset obtained manually labeled was only 85.97, which demonstrates the effectiveness of proposed approaches.

A security technology of power relay using edge computing.

The purposes are to find the techniques suitable for the safety relay protection of intelligent substations and discuss the applicability of edge computing in relay protection. Regarding relay protection in intelligent substations, edge computing and optimized simulated annealing algorithm (OSAA) are combined innovatively to form an edge computing strategy. On this basis, an edge computing model is proposed based on relay fault traveling waves. Under different computing shunt tasks, OSAA can converge after about 1,100 iterations, and its computing time is relatively short. As the global optimal time delay reaches 0.5295, the corresponding computing time is 456.27s, apparently better than the linear search method. The proposed model can reduce the computing time significantly, playing an active role in the safe shunting of power relays. The simulation also finds that the voltage and current waveforms corresponding to the fault state of Phase A are consistent with the actual situations. To sum up, this model provides a reference for improving and optimizing intelligent substation relay protection.

Series AC Arc Fault Detection Method Based on High-Frequency Coupling Sensor and Convolution Neural Network.

Arc faults induced by residential low-voltage distribution network lines are still one of the main causes of residential fires. When a series arc fault occurs on the line, the value of the fault current in the circuit is limited by the load. Traditional circuit protection devices cannot detect series arcs and generate a trip signal to implement protection. This paper proposes a novel high-frequency coupling sensor for extracting the features of low-voltage series arc faults. This sensor is used to collect the high-frequency feature signals of various loads in series arc state and normal working state. The signal will be transformed into two-dimensional feature gray images according to the temporal-domain sequence. A neural network with a three-layer structure based on convolution neural network is designed, trained and tested using the various typical loads' arc states and normal states data sets composed of these images. This detection method can simultaneously accurately identify series arc, as well as the load type. Seven different domestic appliances were selected for experimental verification, including a desktop computer, vacuum cleaner, induction cooker, fluorescent lamp, dimmer, heater and electric drill. Then, the stability and universality of the detection algorithm is also verified by using electronic load with adjustable power factor and peak factor. The experimental results show that the designed sensor has the advantages of simple structure and wide frequency response range. The detection algorithm comparison confirms that the classification accuracy of the seven domestic appliances' work states in the fourteen categories could reach 98.36%. The adjustable load in the two categories could reach above 99%. The feasibility of hardware implementation based on FPGA of this method is also evaluated.

A Novel Methodology for Series Arc Fault Detection by Temporal Domain Visualization and Convolutional Neural Network.

AC arc faults are one of the most important causes of residential electrical wiring fires, which may produce extremely high temperatures and easily ignite surrounding combustible materials. The global interest in machine learning-based methods for arc fault diagnosis applications is increasing due to continuous challenges in efficiency and accuracy. In this paper, a temporal domain visualization convolutional neural network (TDV-CNN) methodology is proposed. The current transformer and high-speed data acquisition system are used to collect the current of a series of arc faults, then the signal is filtered by a digital filter and converted into a gray image in time sequence before being fed into TDV-CNN. Five different electric loads were selected for experimental validation with various signal characteristics, including vacuum cleaner, fluorescent lamp, dimmer, heater, and desktop computer. The experimental results confirm that the classification accuracy of the five loads' work states in the ten categories could reach 98.7% or even higher by adjusting parameters perfectly. The methodology is believed to be reliable for series arc detection with relatively high accuracy and also has important potential applications in other fault diagnosis fields.

An arc fault diagnosis algorithm using multiinformation fusion and support vector machines.

Arc faults in low-voltage electrical circuits are the main hidden cause of electric fires. Accurate identification of arc faults is essential for safe power consumption. In this paper, a detection algorithm for arc faults is tested in a low-voltage circuit. With capacitance coupling and a logarithmic detector, the high-frequency radiation characteristics of arc faults can be extracted. A rapid method for computing the current waveform slope characteristics of an arc fault provides another characteristic. Current waveform periodic integral characteristics can be extracted according to asymmetries of the arc faults. These three characteristics are used to develop a detection algorithm of arc faults based on multiinformation fusion and support vector machine learning models. The tests indicated that for series arc faults with single and combination loads and for parallel arc faults between metallic contacts and along carbonization paths, the recognition algorithm could effectively avoid the problems of crosstalk and signal loss during arc fault detection.

An experimental study on the thermal characteristics and heating effect of arc-fault from Cu core in residential electrical wiring fires.

The characteristics of a series direct current (DC) arc-fault including both electrical and thermal parameters were investigated based on an arc-fault simulator to provide references for multi-parameter electrical fire detection method. Tests on arc fault behavior with three different initial circuit voltages, resistances and arc gaps were conducted, respectively. The influences of circuit conditions on arc dynamic image, voltage, current or power were interpreted. Also, the temperature rises of electrode surface and ambient air were studied. The results showed that, first, significant variations of arc structure and light emitting were observed under different conditions. A thin outer burning layer of vapor generated from electrodes with orange light was found due to the extremely high arc temperature. Second, with the increasing electrode gap in discharging, the arc power was shown to have a non monotonic relationship with arc length for constant initial circuit voltage and resistance. Finally, the temperature rises of electrode surface caused by heat transfer from arc were found to be not sensitive with increasing arc length due to special heat transfer mechanism. In addition, temperature of ambient air showed a large gradient in radial direction of arc.

A Novel Arc Fault Detector for Early Detection of Electrical Fires.

Arc faults can produce very high temperatures and can easily ignite combustible materials; thus, they represent one of the most important causes of electrical fires. The application of arc fault detection, as an emerging early fire detection technology, is required by the National Electrical Code to reduce the occurrence of electrical fires. However, the concealment, randomness and diversity of arc faults make them difficult to detect. To improve the accuracy of arc fault detection, a novel arc fault detector (AFD) is developed in this study. First, an experimental arc fault platform is built to study electrical fires. A high-frequency transducer and a current transducer are used to measure typical load signals of arc faults and normal states. After the common features of these signals are studied, high-frequency energy and current variations are extracted as an input eigenvector for use by an arc fault detection algorithm. Then, the detection algorithm based on a weighted least squares support vector machine is designed and successfully applied in a microprocessor. Finally, an AFD is developed. The test results show that the AFD can detect arc faults in a timely manner and interrupt the circuit power supply before electrical fires can occur. The AFD is not influenced by cross talk or transient processes, and the detection accuracy is very high. Hence, the AFD can be installed in low-voltage circuits to monitor circuit states in real-time to facilitate the early detection of electrical fires.

[Research on process character information in early fire based on Fourier transform infrared spectrum detection].

CO was chosen as an early fire detection factor through analyzing all kinds of characters in the process of fires, and an experiment system was established based on Fourier transform infrared spectrometer. Through this system, lots of early fire experiments were carried out, and the authors got the CO concentrations of all kinds of materials. Using the concentration of CO, an autoregressive integrated model was established by time series analysis, then the process characters phi1 and phi2 were extracted from them. Through analyzing the phase graph of the process characters, it was found that the real fires and the nuisance fires were distributed in different regions. Plenty of experiments indicate that this detection method can discriminate between real fire sources and nuisance sources quickly when fires occur.

[Research on early fire detection with CO-CO2 FTIR-spectroscopy].

A new fire detection method is put forward based on the theory of FTIR spectroscopy through analyzing all kinds of detection methods, in which CO and CO2 are chosen as early fire detection objects, and an early fire experiment system has been set up. The concentration characters of CO and CO2 were obtained through early fire experiments including real alarm sources and nuisance alarm sources. In real alarm sources there are abundant CO and CO2 which change regularly. In nuisance alarm sources there is almost no CO. So it's feasible to reduce the false alarms and increase the sensitivity of early fire detectors through analyzing the concentration characters of CO and CO2.