摘要：【中文】本发明涉及一种基于目标检测的校园走廊场景智能监控方法，其特征在于，该方法使用基于YOLOv3目标检测网络搭建的目标检测模型，通过由深度可分离卷积组成的倒置残差模块进行特征提取，实现对监控视频画面的实时目标检测，并将轻量级目标检测网络分散部署到手机、开发板等廉价设备中解决针对校园监控场景做打架和摔倒等危险行为实时检测报警，与现有技术相比，本发明具有保证准确度的情况下降低计算量，且降低部署成本的等优点。 【EN】The invention relates to a campus corridor scene intelligent monitoring method based on target detection, which is characterized in that a target detection model built based on a YOLOv3 target detection network is used, feature extraction is carried out through an inverted residual error module formed by deep separable convolution, real-time target detection of a monitoring video picture is realized, and a lightweight target detection network is dispersedly deployed in cheap equipment such as a mobile phone and a development board, so that real-time detection and alarm of dangerous behaviors such as putting up and falling down aiming at a campus monitoring scene are realized.

摘要：【中文】本发明涉及一种基于注意力机制的稀疏编码方法，该方法在原有模型LISTA的基础上加入注意力机制网络，从而充分利用迭代历史信息，加速模型收敛，并在此基础上进行监督学习，提高图像分类的准确率。与现有技术相比，本发明具有算法复杂度更低，实验证明效果更佳等优点。 【EN】The invention relates to a sparse coding method based on attention mechanism, which adds an attention mechanism network on the basis of an original model LISTA (Linear iterative latent Interactive application), thereby fully utilizing iteration historical information, accelerating model convergence, carrying out supervised learning on the basis and improving the accuracy of image classification. Compared with the prior art, the method has the advantages of lower algorithm complexity, better effect proved by experiments and the like.

摘要：【中文】本发明涉及一种用于风电塔筒的螺母松动检测方法，包括以下步骤：采集二维图像数据；通过随机森林分类模型检测螺母在二维图像中的位置；通过回归模型获取二维图像中每个螺母相对于相机坐标系的初步平移向量；选取其最接近的预设的螺母姿态模板；优化目标函数获取每个螺母的当前旋转向量R’和当前平移向量T’；将旋转向量R’和当前平移向量T’与其预设的原始旋转向量R₀和原始平移向量T₀比较，判定螺母发生松动。与现有技术相比，本发明通过使用计算机视觉以及机器学习技术，能够依靠少量的模板就能得到相对精确的初始位姿，降低算法实现的成本，而且精度较高且有效减少了人工成本。 【EN】The invention relates to a nut loosening detection method for a wind power tower, which comprises the following steps: collecting two-dimensional image data; detecting the position of the nut in the two-dimensional image through a random forest classification model; acquiring a primary translation vector of each nut in the two-dimensional image relative to a camera coordinate system through a regression model; selecting a preset nut posture template which is closest to the preset nut posture template; optimizing an objective function to obtain a current rotation vector R 'and a current translation vector T' of each nut; the rotation vector R 'and the current translation vector T' are compared with the preset original rotation vector R₀And the original translation vector T₀And comparing to judge that the nut is loosened. Compared with the prior art, the method has the advantages that the computer vision and machine learning technology are used, the relatively accurate initial pose can be obtained by a small number of templates, the algorithm implementation cost is reduced, the precision is high, and the labor cost is effectively reduced.

摘要：【中文】本发明涉及一种基于最小二乘支持向量机的风电站出力超短时预测方法，具体包括以下步骤：步骤S1：利用变分模态分解将风速时间序列分解为N个不同尺度的模态分量；步骤S2：为各模态分量分别建立最小二乘支持向量机的LSSVM预测模型；步骤S3：将风速历史序列的数据集分割成训练集、交叉验证集和测试集，并对数据进行归一化处理；步骤S4：通过训练集滚动训练LSSVM预测模型，在交叉验证集上利用粒子群优化算法优化LSSVN预测模型的核宽度和惩罚因子，然后在测试集上测试误差，得到小于误差阈值的最优LSSVM预测模型。与现有技术相比，本发明具有降低风速非平稳性的影响、提高预测精度等优点。 【EN】The invention relates to a method for ultra-short output prediction of a wind power station based on a least square support vector machine, which specifically comprises the following steps: step S1: decomposing the wind speed time series into N modal components with different scales by utilizing variational modal decomposition; step S2: respectively establishing an LSSVM prediction model of a least square support vector machine for each modal component; step S3: dividing a data set of the wind speed historical sequence into a training set, a cross validation set and a test set, and carrying out normalization processing on the data; step S4: and rolling the LSSVM prediction model through a training set, optimizing the kernel width and penalty factors of the LSSVN prediction model on a cross validation set by utilizing a particle swarm optimization algorithm, and then testing errors on a test set to obtain the optimal LSSVM prediction model smaller than an error threshold. Compared with the prior art, the method has the advantages of reducing the influence of wind speed non-stationarity, improving prediction precision and the like.

摘要：【中文】本发明公开了一种柔性生产线结构，包括：负载房，负载房中具有至少一处负载架。自动流水线，自动流水线包括上层流水线、下层流水线、升降小车、升降台和动力电机柜。测试线，测试线包括第一手动流水线、测试柜和包装台。生产线，生产线包括第二流水线、重型物料架、线边物料架和组装托盘。该柔性生产线结构设计新颖，布局紧凑，能够方便的实现不同功率段工控产品的切换生产、测试，能够方便的实现不同功率的产能替换；为应对公司后期产量扩大，可以根据瓶颈步骤需要，扩充生产线或测试线或负载数量，能够轻松提升产能而不需要完全新建产线。 【EN】The invention discloses a flexible production line structure, comprising: the load room is provided with at least one load frame. The automatic assembly line comprises an upper assembly line, a lower assembly line, a lifting trolley, a lifting platform and a power electric cabinet. The test line, the test line includes first manual assembly line, test cabinet and packing platform. The production line comprises a second production line, a heavy material rack, a line edge material rack and an assembling tray. The flexible production line has novel structure design and compact layout, can conveniently realize the switching production and test of industrial control products with different power sections, and can conveniently realize the capacity replacement with different powers; in order to deal with the later-stage yield expansion of a company, production lines or test lines or the number of loads can be expanded according to the requirements of bottleneck steps, and the capacity can be easily improved without completely building a new production line.

摘要：【中文】本发明公开了一种车载液氢液位测量装置以及其构成的液位计，该一种车载液氢液位测量装置包括第一电容式测量组件，包括内管，及套在内管外的外管，所述内管与所述外管之间形成第一液位腔，所述内管的内腔为第二液位腔；第二电容式测量组件，设于第二液位腔中，并与第二液位腔的腔壁间隔设置；绝缘定位结构，与所述第一电容式测量组件、所述第二电容式测量组件分别连接，并设有连通所述第一液位腔和第二液位腔的流通通孔。本发明能够适用于车载状态下温度较低的液氢的测量，测量精度高，满足车载液氢液位测量的需求。 【EN】The invention discloses a vehicle-mounted liquid hydrogen liquid level measuring device and a liquid level meter formed by the same, wherein the vehicle-mounted liquid hydrogen liquid level measuring device comprises a first capacitance type measuring component, an inner tube and an outer tube sleeved outside the inner tube, a first liquid level cavity is formed between the inner tube and the outer tube, and the inner cavity of the inner tube is a second liquid level cavity; the second capacitance type measuring component is arranged in the second liquid level cavity and is arranged at an interval with the cavity wall of the second liquid level cavity; and the insulation positioning structure is respectively connected with the first capacitance type measuring component and the second capacitance type measuring component and is provided with a circulation through hole communicated with the first liquid level cavity and the second liquid level cavity. The invention can be suitable for measuring the liquid hydrogen with lower temperature in a vehicle-mounted state, has high measurement precision and meets the requirement of vehicle-mounted liquid hydrogen liquid level measurement.

摘要：【中文】本发明公开了一种利用煤矸石处理煤矿酸性废水的装置及方法，包括处理箱，处理箱上部左侧连接有进水管，处理箱右侧底部连接有排水管，处理箱上设有多组处理组件，处理组件包括外壳，外壳上开有多组通孔，外壳内底壁上依次铺设有石英砂层培养胶颗粒层、硫酸盐还原菌层和煤矸石颗粒层，外壳右侧粘接有密封垫；本发明中，通过设置多组处理组件对酸性废水进行多次处理，对废水的处理效果好，且煤矸石可在煤矿内进行取材，取材十分方便，成本较低，同时处理组件与处理箱之间为抽拉式连接，可在使用一段时间后，对煤矸石层和硫酸盐还原菌层进行更换，使用起来极为方便。 【EN】The invention discloses a device and a method for treating acid wastewater of a coal mine by using coal gangue, and the device and the method comprise a treatment box, wherein the left side of the upper part of the treatment box is connected with a water inlet pipe, the bottom of the right side of the treatment box is connected with a water drain pipe, the treatment box is provided with a plurality of groups of treatment components, each treatment component comprises a shell, a plurality of groups of through holes are formed in the shell, a quartz sand layer culture colloidal particle layer, a sulfate reducing bacteria layer and a coal gangue particle layer are sequentially paved on the bottom wall in the; according to the invention, multiple groups of treatment assemblies are arranged to treat the acidic wastewater for multiple times, the wastewater treatment effect is good, the coal gangue can be obtained in a coal mine, the material taking is very convenient, the cost is low, and meanwhile, the treatment assemblies and the treatment box are connected in a drawing mode, so that the coal gangue layer and the sulfate reducing bacteria layer can be replaced after the coal gangue layer and the sulfate reducing bacteria layer are used for a period of time, and the use is very convenient.

摘要：【中文】本发明公开了一种评价CO₂对平板酸岩反应速率影响的测试装置及方法，该装置结构包括酸液输送单元、CO₂输送单元、混合罐、平板夹持器、回收液罐、真空泵；所述混合罐设有酸液入口、CO₂气体入口、混相流体出口，酸液入口连接酸液输送单元，CO₂气体入口CO₂输送单元连接，混相流体出口连接平板夹持器，平板夹持器连接回收液罐，回收液罐连接真空泵。CO₂输送单元包括CO₂气瓶，与CO₂气瓶连接的气体增压泵，气体增压泵出口连接混合罐的气体入口。本发明的测试装置和方法能够真实模拟施工过程中CO₂、酸混合流体与岩石的化学反应，在不同环境条件下测试酸岩反应速率，用以指导CO₂酸压工艺技术措施。 【EN】The invention discloses a method for evaluating CO₂The device structurally comprises an acid liquor conveying unit, a CO (carbon monoxide) testing device and a CO testing method₂The device comprises a conveying unit, a mixing tank, a flat plate clamp, a recovery liquid tank and a vacuum pump; the mixing tank is provided with an acid liquor inlet and CO₂A gas inlet, a mixed phase fluid outlet, an acid liquor inlet connected with an acid liquor conveying unit, and CO₂Gas inlet CO₂The conveying unit is connected, the mixed phase fluid outlet is connected with the flat plate holder, the flat plate holder is connected with the recovery liquid tank, and the recovery liquid tank is connected with the vacuum pump. CO 2₂The transport unit comprises CO₂Gas cylinders, with CO₂The gas booster pump is connected with the gas cylinder, and the outlet of the gas booster pump is connected with the gas inlet of the mixing tank. The testing device and the testing method can truly simulate CO in the construction process₂Acid mixed fluid and rock chemical reaction in different environmentsAcid rock reaction rate was tested under conditions to guide CO₂Acid fracturing process technical measures.

摘要：【中文】本发明涉及交通仿真技术领域，尤其涉及一种基于互联网大数据的实时交通仿真分析系统与方法包括数据存储模块、数据处理模块、仿真管理模块和用户终端模块；所述数据存储模块用于互联网大数据的准备与存储，数据存储模块用于接收来自互联网大数据、检测器、人工设计的仿真方案和仿真基础数据的信息；输入的数据包括静态数据和动态数据；所述数据处理模块用于数据的预处理、数据分析、数据融合和数据转换。本发明打破了传统的OD反推、最短路求解等方法，简化了仿真过程，提高了仿真的真实性和准确性，解决现有技术中依赖历史的、离线的数据才能实现交通仿真且仿真核心模型和算法无法与大数据形成良性交互的问题。 【EN】The invention relates to the technical field of traffic simulation, in particular to a real-time traffic simulation analysis system and method based on internet big data, which comprises a data storage module, a data processing module, a simulation management module and a user terminal module; the data storage module is used for preparing and storing the Internet big data, and the data storage module is used for receiving information from the Internet big data, the detector, a simulation scheme of artificial design and simulation basic data; the input data comprises static data and dynamic data; the data processing module is used for preprocessing data, analyzing data, fusing data and converting data. The invention breaks through the traditional methods of OD reverse-pushing, shortest path solving and the like, simplifies the simulation process, improves the authenticity and the accuracy of the simulation, and solves the problems that the traffic simulation can be realized only by relying on historical and offline data and the simulation core model and algorithm can not form good interaction with big data in the prior art.