A displacement measurement system based on a single mode fiber and a coupler is proposed. The two arms of the output end of the coupler are connected with a collimating lens to form a differential structure when irradiated to both sides of the measured object. The displacement resolution of the system is improved by two times, the resolution can reach a quarter of the wavelength, and the whole system is less disturbed by temperature. Through simulation analysis and experimental verification, the feasibility of this method is proved. Multiple Hilbert transform method is used to carry out displacement reconstruction. The results show that the displacement reconstruction accuracy of this system is also better than that of single-channel system, and the reconstruction error is reduced from 111 nm to 60 nm.

The traditional LE(Laplacian Eigenmaps) algorithm uses Euclidean distance to measure the position relationship between sample points, which is only applicable to linear data sets. However, the data in practical engineering often show strong non-linearity, which makes the final embedding results difficult to reflect the essential characteristics of the original data. An algorithm for D-LE(Double metric constraint Laplace Eigenmaps) based on Double metric constraint is proposed. The algorithm uses cosine similarity to evaluate the similarity between samples, and combines the measurement relations between samples and between samples and local manifolds to build dimensionality reduction model. Experiments on three bearing datasets show that this method can significantly improve the dimensionality reduction effect for processing nonlinear datasets.

PDT(Professional Digital Trunking) standard protocol can not meet the requirement of large number of terminals reporting positioning data periodically in a specified short time. In order to solve this problem, an efficient positioning data reporting method based on group text short message pull-up and dedicated data channel reporting is proposed. Firstly, the cable dispatching terminal initiates the positioning data pull-up request, and then PDT system encapsulates the group text short message and sends it to target terminals. Finally, target terminals report the positioning data on the dedicated data channel in sequence. The effectiveness and feasibility of the method are proved by the experimental simulation.

According to the teaching objectives and requirements of the electronic measurement experiment, an experimental teaching platform for electronic measurement is developed, which introduces the advanced technology of electronic measurement. It solves the problem that the function of the existing electronic measurement experimental teaching platformcan does not satisfy the multi-level personnel training. The platform adopts modular and open design idea, in which a signal source module based on DDS(Direct Digital Freqiaency Synthesizers) technology, a bandpass filter module, an AC(Alternating Cunent) voltage parameter measurement module, a digital frequency meter module based on DDS technology are provided. It provides a practical platform for students to verify theoretical knowledge. And it provides an open hardware platform and resources for comprehensive design experiments. This platform enables students to master the theoretical knowledge of electronic measurement in depth, and exercises innovative thinking and practical ability, and finally realizes a high level multi-level talented person training goal.

A variable gain iterative learning control law is proposed to solve the problem that the tracking efficiency of nonlinear 3-DOF(three-Degree-Of-Freedom) manipulator's trajectory tracking control system is low in the presence of disturbance. First, the Lagrangian method is used to establish the kinetic equation. Then, the variable gain iterative learning controller with three degrees of freedom manipulator structure is designed and its convergence is analyzed. Finally, through Matlab Simulink simulation module, the three-degree-of-freedom manipulator control system simulation diagram is constructed, and the comparative simulation test of closed-loop fixed constant and closed-loop variable gain PD(Proportion Differentiation) iterative learning control is carried out. Simulation results show that the three-degree-of-freedom manipulator based on variable gain iterative learning can converge to the desired trajectory in a short time in the presence of interference.

In order to improve the experimental teaching effect of programmable logic control system, based on the elevator simulation model of "Siemens Cup" China Intelligent Manufacturing Challenge, taking the five-story elevator for teaching as the controlled object, replacing the electrical control system of the original teaching elevator, adopting Siemens S7-1200 series programmable controller, frequency converter and touch screen, and configuring hardware system terminals, a new elevator teaching and training platform is developed, and a new experimental teaching mode of "virtual-real" combination is established. And the modular idea is introduced into the system design, which makes it easy to adjust the training content, so that students can learn the relevant course content from easy to difficult. From virtual simulation to practical operation, this training platform stimulates students' interest in learning and plays an active role in cultivating students' professional quality. Key words: virtual simulation; elevator model; programmable logic controller

With the widespread use of knowledge graphs, in order to improve the accuracy and efficiency of extracting knowledge data and product data from them, the method and system use a knowledge graph as a data source, and formulates business data extraction and organization rules based on actual business requirements (the extraction rules are the mapping rules in the title, the expression description methods and specification constraints of the design rules are designed by us, and the actual requirements can be filled out by the business demander), and support the extraction of subgraphs that meet the rules from the knowledge graph according to the rules. Because the subgraph conforms to the rules of the business demander, the subgraph contains the data and organizational structure that meet the business requirements. Further, through data product generation rules (generating data products that are ultimately required by business users, such as report files and statistical tables, from subgraph data with relatively fixed structure and actual business meaning), generate the required data products from the extracted subgraphs ( report documents, statistical tables, etc). Rapid and automatic generation of data products such as text, charts, and report documents are achieved by using SPARQL query language, natural language generation, and other technologies to use knowledge graphs as data sources, which has substantially improved efficiency.

Aiming at the problem of poor performance of traditional Faster R-CNN(Region-Convolutional Neural Networks) in detecting small target defects on steel surface, a new method for steel surface defect detection based on improved Faster R-CNN is proposed. First, the GA-RPN(Guided Anchoring Region Proposal Network) is introduced to predict the position and shape of the anchor points, and an adjustable mechanism is designed to solve the problem that the shape offset of network anchors exceed the region of interest, thereby solving the influence of irrelevant features. Then, a multi-task FPN (Feature Pyramid Network) structure is used to shorten the high-level feature location information mapping path, and can solve the insufficient features fusion of adjacent layers features fusion and re-sampling, and to improve the performance of small target detection. The results show that the recall rate and accuracy of the network are improved. Therefore, this method has better performance and can effectively detect steel surface defects.

Aiming at the problem of insufficient concentration and effective utilization of the existing tourist data of Changbai Mountain scenic spots, through reasonable development of a Python-based web crawler, we have realized the crawling of some Changbai Mountain tourism data, and used Tableau tools to make a visual analysis of the data. Accurately excavating the potential relationship between the number of tourists and various factors from multiple dimensions presents a more intuitive effect, which is conducive to the observation of trend distribution, and lays the foundation for the further development of reasonable tourism strategies in the Changbai Mountain area.

Aiming at the problem that the traditional high-cost and low-efficiency sea area supervision methods such as field investigation and evidence collection and manual comparison of remote sensing images can not meet the current regulatory requirements, we use satellite remote sensing images and deep learning algorithm to propose a comprehensive control method for large-scale, fast and dynamic sea use. Based on massive images and multi-source marine basic data, multi planning fusion analysis, fast R-CNN(Regions with Convolutional Neural Networks features) algorithm, an artificial intelligence recognition model is established to realize automatic recognition and early warning of maritime targets, illegal sea occupation and ecological environment damage. We analyze the principle of fast R-CNN algorithm, uses satellite remote sensing data of different years, different satellites and different resolutions, establishes more than 10 000 image sample database for five kinds of common marine targets, and conducts training and testing with VGG16 and RestNet101 network models. The experimental results show that the computational complexity of RestNet101 model is slightly larger than that of VGG16 model, but it has stronger ability of complex feature extraction, and is more suitable for the detection and recognition of complex sea targets; the overall recognition accuracy of the five types of targets is more than 80% . Combined with the marine planning data, the model realizes the rapid automatic supervision and early warning of illegal user behavior in large-scale sea area, which provides a new idea for the intelligent marine supervision.

To improve the accuracy of the prediction results, a prediction model is designed based on VMD- IWOA-LSSVM(Variational Mode Decomposition-Improved Whale Optimization Algorithm-Least Square Support Vector Machine). The original load data is decomposed into multiple sub-sequences by the variational modal algorithm. The decomposed data is entered respectively least squares support vector machine optimized by an improved whale optimization algorithm through population mutation strategy and neighborhood search extension. The final prediction result is obtained after the prediction results of each sub-sequence are added. Comparing to simulation experiment VMD-WOA-LSSVM and VMD-IWOA-LSSVM, mean Absolute Percentage Error of VMD- IWOA-LSSVM drops 0. 17 and 0. 33 respectively at the April 1 and August 1 than VMD-WOA-LSSVM. It proves that the short-term load prediction model of the VMD-IWOA-LSSVM can effectively improve the accuracy of power load forecasting.

Aiming at the problem of motor bearing failure identification problems, a fault diagnosis method for motor bearings based on BAS(Beetle Antennae Search) algorithm and PNN( Probabilistic Neural Network) is proposed. The LLE (Locally Linear Embedding) algorithm is used to obtain the sensitive characteristics of the vibration signal to ensure the reliability and sensitivity of the vibration signal. The Beetle Antennae Search algorithm is used to find the optimal smoothing factor in the model to avoid the influence of subjective empirical selection on the diagnosis results. The experimental results show the effectiveness of the method, and it can accurately identify the fault type.

CNN ( Convolutional Neural Network) has large amount of computation, in order to achieve the purpose of fast data processing, hardware means are needed to accelerate. Based on the architecture characteristics of FPGA(Field Programmable Gate Array), a parallel computing acceleration strategy based on FPGA is proposed. The specific methods of this strategy include: reducing the data reading delay by reasonably distributing on-chip memory and off chip memory; accelerating the convolution operation by multi-channel parallel flow; reducing access delay by convolutional layer data sharing. PYNQ-Z2 development platform is used to accelerate the convolutional neural network YOLOv2 and achieve the detection and identification of the target object. The processing capacity of this design is 27.03 GOP / s, compared with CPU ( E5-2620v4 ), the processing capacity is 6. 57 times that of CPU and the power consumption is 3% of CPU.

 Existing performance prediction research focuses on how to build prediction model, ignoring the importance of prediction time. In order to solve this problem, a prediction model based on BP ( Back Propagation) neural network is proposed to find out the potential relationship between freshmen's grades and graduation grades and realize the principle of early guidance and early effect. Through a random prediction experiment on the grades of 2016 students majoring in information and computing science in a university, it is proved that there is a potential relationship between freshman scores and graduation scores. The proposed prediction model has excellent prediction accuracy and good practicability and popularization, which can become an important part of improving teaching quality and play a greater role in realizing the goal of talent training.

To share data in a smart grid safely and efficiently, AEDS (Attribute-Based Encryption Secure Data Sharing) algorithm is proposed. In AEDS, we propose a practical attribute-based encryption scheme for securing data sharing and data access in smart grid architectures with the added advantage of obfuscating the access policy. This is aimed at preserving data privacy in the context of competing smart grid operators. We build our algorithm on linear secret sharing scheme for supporting any monotone access structures and thus enhancing the expressiveness of access policies. The performance analysis shows that the proposed AEDS algorithm effectively improves the access efficiency and enhances the security of access data.

In order to remotely manage and monitor laboratory equipment, combined with Android wear, MySQL, redis and other technologies, based on the cloud platform connecting devices, micro WSGI(Web Server Gateway Interface) server is built using the flask framework to provide device monitoring services for the client based on the virtual control panel APP. The virtual control panel can be used to manage different kinds of devices. The functions of controlling the device and querying the status are realized. The design and function realization of the virtual control panel are studied, and the test result graph of the virtual panel is given. Tests show that the virtual control panel is stable and reliable. The virtual panel realizes the separation of the application interface control and the control logic, and facilitates the user to control and manage the device, and can be effectively applied to the APP design of the monitoring device.

In order to solve the problem of inconsistent quality and integrity of observation data acquired by users at different times caused by lagging quality control, combined with the complexity and real-time characteristics of automatic weather station observation data, based on the physical and climatic characteristics of atmospheric variables reflected by the data and the basic rules that the data must follow, a three-level automatic quality control system for automatic weather station data is designed and developed based on the data validity and consistency check. The key quality control technologies used in the development mainly include the first level quality control technology effectiveness check, the second level quality control technology time consistency check and internal consistency check, and the third level quality control technology space consistency check. The time consistency check also includes time-varying check and continuity check. The internal consistency check includes three kinds of check technologies: the relationship between the same elements, different elements, and the relationship between element values and statistical values. The spatial consistency check adopts the optimal interpolation method. After consulting a large number of references, the boundary range and threshold of relevant meteorological elements are optimized. The system implements hierarchical quality control technology, and carries out three-level quality control for the element value and statistical value of automatic weather station. It has good operability and practicability, can realize computer automatic processing, and has high efficiency in detecting suspicious data. It can effectively improve the consistency and accuracy of data and reduce manual labor.

In colleges and universities, the registration of major transfer is very popular, and it is often difficult to allocate. Therefore, making preparations in advance is important in major transfer. If we can predict the enrollment of major transfer students in that year, it will be of great help to the follow-up work of colleges and universities. Popular college students to professional enrollment of Jilin University from 2003 to 2017 is used to establish the number of popular college students forecast model; the DNN(Deep Neural Network) deep learning network structure is introduced in the Google research and development of tensorflow framework to establish the number of popular college students forecast model; finally, the training data for 15 years is used to predict the number of popular college students in 2020 analysis. The method proposed can better solve the problem of the number of candidates for major transfer in popular colleges, and has a certain guiding significance for the follow-up work.

In order to solve the problem of staff drowsiness in night shift, an adaptive warehouse guard robot with automatic obstacle avoidance, adaptive composition, automatic navigation and positioning is designed to assist the guard patrol. The robot is perceived by photoelectric, gyroscope, laser radar and other sensors, and is controlled by Intel5 microprocessor equipped with ROS(Robot Operating System) robot operating system. It adopts open source design mode, combines SLAM( Simultaneous Localization And Mapping) and analog keyboard control technology, and is equipped with a variety of environmental monitoring sensors such as camera and noise acquisition module. It supports TeamViewer to remotely monitor and obtain the position and state information of the current robot in real time, which has strong compatibility and scalability. The test results show that the adaptive duty robot can get rid of the keyboard autonomous mapping, patrol and other auxiliary duty personnel work, has market application value.