Abstract：In recent years, the contribution of polarization code to communication field is becoming more and more prominent, because the theory of polarization code is proved to be able to achieve the channel limit capacity in BDMC. The decoding system of polarization codes can be realized by software or hardware, and the software decoding speed is limited by the CPU serial working mode. So it is of great value for the communication filed to implement the decoder of polarization code on FPGA with parallel working mode. Firstly the SCL decoding algorithm is introduced in this paper. Then the algorithm is optimized to improve the decoding efficiency, and the quantization improvement is carried out on FPGA. Finally, the hardware emulation of the decoder and the performance analysis are carried out on FPGA. The experimental results show that the maximum frequency of the decoder is up to 143.988 MHz, and the throughput is up to 28.79 Mb/s when the code length is 512.

Abstract：Based on the conventional design of bandgap reference using 0.18 μm process, the single event transient pulse current model was used to analyze the single event sensitivity of common CMOS two-stage amplifiers. The vertical type PNP transistor used in the bandgap reference was modeled using TCAD software, and its single event sensitivity in the bandgap reference source was verified by simulation. In the end, the radiation hardened bandgap reference was proposed.

Abstract：With the increasing number of processor cores integrated on-chip, the problem of “storage walls” in reconfigurable array processors is increasing. Traditionally, the use of multi-level shared Cache hardware design has high complexity and limited parallel access, and it is difficult to meet the memory requirements of reconfigurable array processors. This paper designs a local-priority, global-shared“physical distribution, unified logic” distributed Cache structure. The hardware overhead of this structure is small and parallel access is high. The Xilinx Virtex-6 series xc6vlx550T development board was used to test the design. The experimental results show that the average delay of proposed architecture is reduced by up to 30% compared with the similar structure, and the hardware overhead is only 5% of the Cache capacity. The maximum memory access bandwidth is 10.512 GB/s.

Abstract：In order to realize the accurate classification of EEG signals based on motion imagination, the Levenberg Marquardt(LM) algorithm is proposed to replace the BP neural network classifier to improve the classification recognition rate. Based on the BCI2008 competition laboratory paradigm, we used Emotive Epoc+ to collect four kinds of motor imagery EEG signals. After filtering the signal to dryness, the main component analysis is used to extract the characteristic values of the collected signals, and then the LM algorithm and the BP neural network are used for classification and recognition respectively. Finally, the serial communication interface is designed based on the MATLAB GUI, and the feasibility of the algorithm is verified with the Arduino intelligent car link. The results show that the average training error is 5.630 6×10-7, the classification accuracy is 86%, and the BP algorithm is 0.001 4 and 56% respectively. Compared with the LM algorithm, the classification effect is good. During the verification process, the intelligent car operation is consistent with the algorithm identification direction, and runs well. This method is practical and feasible, which lays the foundation for further developing brain computer interface.

Abstract：In order to meet the needs of electric power system monitoring, a 3 bit 5 order sigma-delta ADC is designed and implemented. The measurement results show that the dynamic range of the system is higher than 100 dB and the effective bit is greater than 16 bits, which can meet the requirements of the modern power grid system′s measurement of the transformer AC output.

Abstract：The SiP(System in Package) is introduced. Based on the SiP technology,a microsystem composed of bare dies such as FPGA，ARM，SRAM is designed. The working principle of microsystem is introduced，and the implementation process of the product is described. The system has the characteristics of light weight,small volume and complete function.

Abstract：A concurrent dual-band low noise amplifier(LNA) targeted for WLAN IEEE 802.11 a/b/g standards is designed using 0.13 μm CMOS process. To attain the power-constrained simultaneous noise figure and input matching, cascode inductive degeneration topology is adopted. The LNA achieves input reflection coefficients of -16.7 dB and -19.5 dB, forward gains of 16.8 dB and 17.2 dB at 2.4 GHz and 5.2 GHz, respectively. Furthermore, the LNA exhibits noise figures of 3.1 dB and 3.2 dB while input third-order intercept points of -18.5 and -16.5 dBm at 2.4 and 5.2 GHz, respectively. The LNA dissipates 2.64 mW of power from a 1.2 V supply.

Abstract：An electrical fire monitoring system based on Long Range(LoRa) wireless transmission technology is designed for early warning buildings, especially in ancient buildings. In this system, by monitoring the temperature of the line and the value of the residual current, the alarm information is uploaded to the monitoring host by LoRa wireless transmission technology to notify the monitor on duty, so as to prevent the occurrence of electrical fire. After field testing in ancient buildings, the results show that the system has a long transmission distance and a good wall penetration effect. This study provides a theoretical and technical support for the application of wireless monitoring and alarm in electrical building fire protection.

Abstract：Soldier tactical training is the basic movement in combats. Traditional soldier tactical training and test is finished by artificial timing and judgment which has some problems, such as low detection accuracy, low data collection and storage efficiency. Meanwhile, there are no effective solutions for the problems. Based on FPGA/MCU platform, a kind of soldier tactical training and test system is designed and implemented. The system adopted a few pairs of active correlation infrared detector, for collecting touch signals and wireless data transmission utilizing hand-held terminal. The backstage provides guidance and suggestions by analyzing data. Test results proves that the system can solve problems in current soldier tactical trainings.

Abstract：To meet the demands of large data volume, high transmission speed and high real-time computing performance in embedded image processing system, this paper proposes a high-speed data transmission storage system with multi-core DSP TMS320C 6678 as the core. Based on the DSP high-speed serial Rapid IO(SRIO) module for high-speed transmission of image data, using the SRIO module′s direct I/O transmission mode, using the 4x interface mode configuration, each interface transmission rate is 3.125 Gb/s, and theoretical transmission rate is 10 Gb/s. At the same time, DDR3 controller module is used to expand storage space and achieve shared storage of optical and radar images. The test results show that the SRIO high-speed transmission system designed has a transmission speed of more than 8Gb/s, which reaches more than 80% of the theoretical value, satisfies the high-speed transmission needs of large data, and effectively realizes data transmission and shared storage between multiple processors.

Abstract：A warp knitting electronic shogging system based on embedded microcontroller and special motion control chip is designed. The system, containing STM32 and PCL6045BL, IPC, AC servo system and guide bars and absolute encoder, realizes stable and accurate execution for warp knitting electronic shogging system. The above system components are used as the control nucleus, system management and decision supporting, actuators, and the position sensor. The system has many advantages, such as flexible changing of tissues, on-line modification, larger storage of pattern information, real-time controlling and detection and so on. As the practical application showing, the system has achieved desired design purpose and could meet the production capacity of double bar raschel warp knitting machine at 800 rows /min in field.

Abstract：An indoor moving target positioning system using UWB(Ultra-wideband) technology was designed. Through the base station installed in a specific location in the room and the tag carried by the mobile object, the improved standard TDOA(Time Difference of Arrival) positioning algorithm obtains the real-time location information of the moving target and completes the accurate positioning of the indoor moving target. Qt was used to develop a PC application software that can display the position and movement trajectory of the positioning target in real time. Finally, an experimental test platform was set up to test the system and the obtained location information was compared with the actual data. The result shows that the overall system communication is stable and meets the positioning requirements.

Abstract：An interface circuit system based on S3C2440 and VC++6.0 for photoelectric parameters detection of liquid crystal display(LCD) devices is designed. The system can detect the photoelectric parameters of various types of LCD devices commonly used in the market, not need to replace more other driver power and driver signal source and other equipment with different models, and can transmit the effective data to PC through the communication interface. The trouble caused by replacement and complex wiring of various equipment and instruments in the detection of photoelectric parameters of LCD devices is solved. The results show that the system is stable, easy to operate, simple to connect, and has high accuracy of data acquisition.

Abstract：In order to improve the accuracy of wind power short-term wind speed prediction, this paper proposes a complete integration based on adaptive noise empirical mode decomposition(CEEMDAN)-permutation entropy(PE) and quantum genetic algorithm(QGA)to optimize the BP neural network prediction model of short-term wind speed. Firstly, CEEMDAN is used to decompose the original wind speed time series and reduce the influence between different characteristic scale sequences. Secondly, in order to reduce the scale of computation, the each component sequence of decomposition is calculated for PE, and the components with similar entropy value are superimposed to form a new sequence. Finally, according to the weights of BP neural network in the initialization and random problems existing in the selection of threshold, BP parameters are optimized by quantum genetic algorithm(QGA), combined new sequences are predicted respectively and the results of each component are superimposed. The simulation results show that the proposed combination model improves the prediction accuracy, reduces the error and has high application value.

Abstract：The arc fault includes parallel arc and series arc. The parallel arc fault is characterized by short circuit current and fault current is large, which can be protected by the current circuit breaker. The series arc fault is limited by the load and fault current is small，which cannot be protected by the current circuit breaker. The current waveform of normal operation and arc fault is obtained through experiments, and the characteristic values of wavelet transform are extracted. The characteristic value was input into the probabilistic neural network model. According to UL 1699 standard, arc fault is judged by calculating whether the half-cycle fault number is greater than 8 in 0.5 s. Using MATLAB simulation, 40 groups of test data are selected. 38 groups of test results are correct and 2 groups are wrong. The fault identification rate is 95%, which shows the effectiveness of the method.

Abstract：Agricultural greenhouse cultivation technology is of great significance to modern agricultural production. In order to solve the problem of on-line collection and monitoring of environmental information in agricultural greenhouses, a meteorological environmental data monitoring system for agricultural greenhouses based on Internet of Things was designed. The design used CC2530 RF module as the core chip of the terminal acquisition device. Agricultural greenhouse meteorological observation station was set up by arranging sensors such as light, soil moisture, air temperature and humidity. Short-range wireless communication was developed and corresponding specifications was established based on Z-Stack protocol stack. Collected data was based on MQTT to do push and pull of information. The system′s practicability, low cost and short development cycle was ensured by the software and hardware development of the system.After the actual use of agricultural greenhouses, advanced technology, flexible design, low cost, simple layout and high cost performance were owned by the system designed in this paper, which can effectively complete the on-line monitoring of meteorological data in agricultural greenhouses as well as provide meteorological monitoring basis for other agricultural systems.

Abstract：Systemic research has been done on the thesis of far field sound source localization combined characteristics of the speech signal in this paper. An improved MUSIC algorithm is proposed based on the traditional MUSIC algorithm in far-field of microphone array signal model, and experiments in simulated environment is carried out. Simulation results show that the improved algorithm has higher spatial identification rate and strong noise immunity, it can estimate the adjacent sound source signals with small SNR effectively, so the effectiveness and high efficiency of the improved algorithm are proved.

Abstract：In order to achieve dynamic and accurate measurement of multiple parameter information in farmland environment and improve the level of agricultural production, a weather monitoring station suitable for farmland environment is designed. Firstly, data acquisition hardware circuit based on Modbus protocol and data upload 4G gateway node circuit are designed. Secondly, the DMA controller is applied to the idle interrupt mode of the serial port to achieve efficient reception of Modbus data acquisition. Finally, the data is transmitted by the gateway node through the EDP protocol to the IoT cloud platform for analysis, evaluation and processing. The single site of the farmland meteorological monitoring station supports the real-time acquisition of 32-channel sensors, which solves the problem that the single node acquisition parameters are single and the acquisition cycle is long in the past deployment of farmland wireless sensor network nodes, and meets the needs of accurate agricultural farmland environment monitoring.

Abstract：In view of the problem that the general electronic instrument and equipment used for transient parameters testing can not work normally under the influence of strong electromagnetic interference, an overload testing device which can effectively shield the strong electromagnetic interference is designed. The shell structure of the testing device is made of multilayer metal materials with good electromagnetic shielding performance, and the internal structure is filled with polyurethane filling technology. The internal circuit system combines low-power design and data acquisition and storage technology to complete the acquisition and recording of overload parameters during the whole flight process. In the actual firing test of electromagnetic railgun, the test device reliably recorded the overload data of the projectile. The result of the experiment shows that the shell structure of the test device has effective electromagnetic shielding for strong electromagnetic fields，and the internal circuit system has successfully acquired the transient overload parameters of the projectile.

Abstract：The navigation signals can be blocked, faded and interfered, when a satellite navigation receiver is carried by high dynamic vehicles and working in complex environments. Besides, the carrier Doppler measurements in the navigation receiver will rapidly change due to high dynamics. As a result, the algorithms of smoothing the pseudorange measurements with the carrier-phase measurements are no longer applicable. Furthermore, the conventional techniques of smoothing the pseudo-range measurements with the integral of carrier Doppler measurements, generally use a fixed window for calculating the initial value of pseudoranges, and then can cause a large error in the initial value if the measurements with significant biases or the outliers are involved in the fixed window. In addition, the error in the integral of carrier Doppler measurements is accumulated over the smoothing time. Therefore, an improved algorithm of smoothing the pseudo-range measurements with the integral of carrier Doppler measurements is proposed. By employing a sliding window to replace the fixed window for calculating the initial value of pseudoranges, more accurate initial values for smoothing can be estimated. And the changes in pseudorange are calculated based on the weighted accumulation of carrier Doppler measurements. In consideration of the ionospheric variations, accumulated error and other factors, the lengths of the sliding window and the consequent smoothing window are chosen. The experimental results in both the static positioning and the simulated flight navigation show that the positioning accuracy is improved. Moreover, the estimation error in the initial value of pseudoranges and the accumulated error in the integral of carrier Doppler measurements are efficiently reduced.

Abstract：When the civil UAV system is integrated, it needs to meet the requirements of data transmission from multiple serial devices between the air and the ground. The existing main method is to forward multiple data by the Autopilot and ground control station, but this method has the problems of low efficiency and communication blocking happens when facing large amount of data. This paper designs a serial port switch, and realizes efficient multi-channel data transmission function through a dedicated message protocol and multi-thread communication program based on RT-Thread real-time operating system. A priority queue scheduling algorithm is implemented based on thread priority to ensure that high priority data will not be blocked due to large amount of data, improving system reliability. The test results show that the design can transmit multi-channel data in real time and reliably, which satisfies the data transmission requirements of the UAV system and has important practical significance and application value.

Abstract：Ad Hoc network is a new type of communication technology that has developed rapidly in the field of wireless communication in recent years. It does not rely on fixed communications infrastructure, and has great flexibility and independence. It is applicable to many scenarios where network cabling is difficult. DSR protocol is an on-demand routing control protocol designed for Ad Hoc networks. It is considered to be one of the most promising Ad Hoc network routing protocols. The core of the DSR protocol is the routing table entry that the node manages to communicate with other nodes. This article focuses on designing and implementing an FPGA method that supports DSR routing table entry management based on finite state machines (FSM).

Abstract：In the current anti-jamming communication, the spread spectrum communication has been studied deeply with the advantages of strong anti-jamming ability and good security performance. In this paper, the code index modulation and multi-ary spread spectrum technology are analyzed and compared. Code index modulation technology is based on the development of direct sequence spread spectrum, in the transmitter information bits are mapped to the pseudo noise(PN) code index and the modulation symbol respectively. The in-phase and orthogonal parts of the modulation symbol select PN codes activated to spread spectrum, and then transmitted through an antenna. The difference between multi-ary spread spectrum technology and code index modulation technology is that the multi-ary spread spectrum technology does not have modulation symbols, and only sends out the activated spread spectrum code through the antenna. This paper will introduce the basic models, spread spectrum gain analysis and complexity analysis of the two kinds of spread spectrum technology. The simulation results show that the code index modulation system has higher spectral efficiency and anti-interference ability.

Abstract：In order to solve the problem of power supply of wireless monitoring node in coal mine working face， a thermoelectric energy harvesting device for the surface temperature difference of downhole equipment is designed based on the thermal electric generator(TEG) and boost management module in this paper. The device is used to charge the lithium ion battery. Experimental results show that the circuit can continue energy harvesting from input sources as low as 100 mV. The stable output power of TEG can be increased by several tens of times using air cooling or water cooling. The bq25505 device is specifically designed to efficiently extract the power generated from the TEG. It can significantly increase the discharge working time of the lithium battery, and the energy conversion efficiency of the module is up to 67%. Therefore, the device can effectively improve the working cycle of the downhole wireless node.

Abstract：Correntropy based algorithms are widely used in non-Gaussian signal processing, but they also suffer from the conflict between the step size and the misadjustment. In order to solve this problem, a convex combination filter based on maximum correntropy criterion(CMCC) was proposed to obtain the fast convergence speed of the filter with large step size as well as the low misadjustment of the filter with small step size. However, the convex combination of two filters with different step sizes will result in the penalties in terms of the combined filter′s convergence speed and the ability to track the optimal value. In this paper, a multi-convex combination filter based on maximum correntropy criterion(MCMCC) is proposed to provide more adaptive filters with different step sizes, so that the weight ratio can be flexibly adjusted for more step sizes, and thus having better tracking ability. Simulation results show that compared with the CMCC algorithm, the proposed MCMCC algorithm has faster convergence speed, stronger re-convergence performance and better tracking ability in the system identification for in the presence of mixed Gaussian noise and abrupt change.

Abstract：Vehicular Ad hoc Networks(VANETs) have special characteristics on the highway, such as high speed，low density, scarce communication infrastructure, and low vehicle connectivity. These characters make it difficult for vehicles on the highway to access to other vehicles or Road Side Units(RSUs). This paper presents a model which implements fog computing in highway service areas to assist vehicles in acquiring content of interest. In this Vehicle Fog Computing(VFC) model, the highway service area collects various services provided by vehicles from various places, and uses a large number of parked vehicles and slow-moving vehicles as fog devices. Localized forwarding through VFC not only reduces communication latency, but also achieves satisfactory content access and real-time data streaming. Moreover, this paper formulates the relationship between communication energy consumption and system delay, then uses the Outer Approximation(OA) algorithm to optimize its trade-off in fog computing. The simulation results show that the communication delay of the system will be significantly reduced with the increase of energy consumption by using the communication mode and equalization optimization algorithm combined with fog computing and cloud computing.

Abstract：Historical data is the real-time data record generated by the operation of equipment in industrial production. Aiming at the problems such as oversize of data, low efficiency in the process of data collection and storage of domestic PLC monitor and control system, a cross-platform, meeting the requirements of industrial production, facilitating the backtracking of problem collection and storage method is proposed. Data is compressed and collected by using the way of key frames and change sets. This design divides multiple memory buffers and uses timestamp change to achieve automatic switching so as to enhance data read and write efficiency. Meanwhile, the signal and slot mechanism of Qt are used to trigger the thread for data storage operation, which implements data collection and storage at the same time. Running on Windows and Linux operating system platforms, both function and performance of the design meet the requirements.

Abstract：With the rise of deep learning in recent years, it has made major breakthroughs in machine learning fields such as target detection, image classification, speech recognition, and natural language processing. Among them, convolutional neural networks are widely used in deep learning. Since the emergence of VGGNet, neural networks have gradually developed deeper and the network has become deeper. This not only increases the demand for operating memory and running memory, but also greatly increases the amount of computation. The requirements for hardware platform resources are getting higher and higher. Therefore, it is particularly difficult to apply deep learning to embedded platforms. In this paper, by pruning the model, the trained network model is compressed, the unimportant parameters are eliminated, the model is reduced, and the computational complexity of the network is reduced. The deep learning will be applied to the embedded platform.

Abstract：A FPGA-based data acquisition system is designed，which is operated near space. In order to make the system run stably, this paper designs the system from both hardware and software. On the hardware side, FPGA is used as the controller of the acquisition system due to its strong anti-interference ability. Both the modules of sensor data acquisition and the implementing agency are redundantly processed and divided into main board and slave board to ensure the effectiveness of the system. In terms of software, based on the results of signal classification, it performs modular processing, analyzes the possible problems in the code and designs the state machine to deal with complex tasks. After testing, the data acquisition system can operate stably for a long time, can send sample data in real time, and can also respond to commands from the ground command station.

Abstract：In order to solve the guidance problem of forklift type Automated Guided Vehicle(AGV) under complex path, a vehicle action command algorithm is proposed. It is different from the traditional way to write the single action instruction into the RFID electronic tag. The instruction generated by the algorithm is stored in the vehicle control system and is identified as the instruction execution condition with the label location. Based on the establishment of the dispatching map model and the label coding, path planning is carried out and the action command algorithm is designed. The C language programming is used to select the model and RC522 radio frequency identification module based on ARM architecture to verify the algorithm. The experiment shows that the vehicle can identify the label information and execute the corresponding action instructions, and perform different actions at the same label when performing different tasks, which improves the label utilization and completes the scheduling task more flexibly.

Abstract：Earth System Model(ESM) is a useful approach to predict the future climate changes. Physical parameterizations are its crucial components and contain a large number of parameters, which introduces tremendous uncertainties regarding the models′ performance. Traditional sensitivity analysis methods are widely used to identify the most influential parameters, however, they do not consider the impact of the dynamic changes of the parameter interactions on the screening process. In this study, a typical benchmark from the literature is used to analyze the bias of the screening results caused by this change. A Dynamic Sensitivity Analysis Method(DSAM) is proposed. The method was used on a numerical function, which is a typical screening test problem in computer experiment literature, as well as on a ESM(Single column Community Atmosphere Model, SCAM). DSAM and traditional methods have a quantitative difference up to 29%. In parameter optimization based on the screening results, the optimization results of the model increased by 67%.

Abstract：The bipolar DC micro-grid based on the Buck-Boost voltage balancer framework has been widely studied. The effective control voltage balancer keeps the positive and negative voltage of the system equal, to ensure the power quality of the system. Aiming at the control of Buck-Boost voltage balancer, a double integral sliding mode controller is designed. This method takes into account the nonlinearity and dynamic state of the system, and adopts double integral sliding surface to reduce the steady-state error. The experimental results show that compared with the traditional PI controller, the controller designed in this paper can effectively shorten the dynamic adjustment time and reduce the difference between positive and negative voltage.

Abstract：Aiming at the problems of low multi-step prediction accuracy and poor online prediction adaptability for the algorithm of relevance vector machine,an improved incremental relevance vector machine model is proposed to predict the state-of-charge of Li-ion battery on line. The voltage, charge and discharge current and surface temperature are selected as the model input, and the state-of-charge is used as the output of the model to construct the training set of the model. A fast-sequence sparse Bayesian learning algorithm is chosen for training, and combined with incremental learning method to establish the incremental learning relevance vector machine model for researching on online prediction methods of Li-ion battery. The study found that by adjusting the kernel parameters automatically, it can guarantee a higher prediction accuracy. Experimental results show that this method has the characteristics of high prediction accuracy, fast calculation speed and strong universality, it can provide reference for the prediction and application of the state-of-charge of Li-ion batteries.

Abstract：This paper proposes an improved turn-off time control strategy for the problem of the AC input current distortion that may occur after switching the operating mode of the Boost PFC converter. This strategy does not require multiple operating modes. Any pattern recognition and control algorithm can achieve unity power factor correction. Compared with the traditional single-mode shutdown time control strategy, it can reduce input current distortion and improve THD performance.

Abstract：Current harmonics and power loss caused by traditional two-level inverters working under high-frequency switching need to be solved urgently. Multi-level inverters do not require a boost converter stage and can output multiple different voltage levels with a small THD of the output voltage.A single-phase asymmetrical five-level transformerless PV inverter topology is proposed, consisting of a basic H-bridge and a T-bridge. The T-bridge is located between the H-bridge and the DC voltage-dividing capacitor. The power tube and diode consist of parallel bridges.Several working states of the new topology are analyzed in detail. The corresponding PWM modulation strategy is given. The simulation verifies the effectiveness of the topology and modulation strategy.

Abstract：The bulky electrolytic capacitor is conventionally used to curb the output voltage ripple of output DC-link in the front-end PFC AC/DC converter, which is applied for the on-board charger of the electrical vehicle. Due to the drawbacks of electrolytic capacitor, such as the short lifetime, susceptibility to temperature and other reasons, the reliability and usage cycle of on-board charger are reduced, even leading to the system breakdown. In order to decline the output voltage ripple in the output DC-link, the PFC AC/DC converter paralleled with power decoupling circuit at the output side is proposed, ensuring safe and reliable operation in the on-board charger. It contributes to diminish the volume of output filtering capacitor sharply and utilize the excellent film capacitor instead of the electrolytic capacitor. In this paper, the mathematical model of power decoupling circuit is established based on the detailed analysis of the circuit operation. Besides, the improved PR(Proportional Resonant) controller is designed to dominate the power decoupling circuit. In order to improve the control performance and robustness, the model-free nonlinear power control strategy is implemented to the PFC AC/DC converter. Based on the aforementioned researches, a 700 W experiment prototype is developed. The feasibility and efficiency of the proposed method are validated by the DSPACE 1007 test platform.

Abstract：Current residual current action protection device cannot detect the type of residual current in the electric shock current. In this paper, an electric shock test platform is built and the residual current data is obtained by experiment. Based on the above data, this paper presents a residual current classification method based on the AdaBoost algorithm, which firstly obtains the characteristic components of different types of residual current components, and then maps these component features to the AdaBoost algorithm. The type of electric shock current in total residual current is detected by AdaBoost algorithm. Compared with SVM and random forests, the results show that the proposed method has some advantages, which can provide theoretical basis and support for the development of the subsequent adaptive residual current action protection device.