Method of Multi-Mode Sensor Data Fusion with an Adaptive Deep Coupling Convolutional Auto-Encoder

To address the difficulties in fusing multi-mode sensor data for complex industrial machinery, an adaptive deep coupling convolutional auto-encoder (ADCCAE) fusion method was proposed. First, the multi-mode features extracted synchronously by the CCAE were stacked and fed to the multi-channel convolution layers for fusion. Then, the fused data was passed to all connection layers for compression and fed to the Softmax module for classification. Finally, the coupling loss function coefficients and the network parameters were optimized through an adaptive approach using the gray wolf optimization (GWO) algorithm. Experimental comparisons showed that the proposed ADCCAE fusion model was superior to existing models for multi-mode data fusion.

A multi-source data fusion modeling method for debris flow prevention engineering

The Digital Elevation Model(DEM)data of debris flow prevention engineering are the boundary of a debris flow prevention simulation,which provides accurate and reliable DEM data and is a key consideration in debris flow prevention simulations.Thus,this paper proposes a multi-source data fusion method.First,we constructed 3D models of debris flow prevention using virtual reality technology according to the relevant specifications.The 3D spatial data generated by 3D modeling were converted into DEM data for debris flow prevention engineering.Then,the accuracy and applicability of the DEM data were verified by the error analysis testing and fusion testing of the debris flow prevention simulation.Finally,we propose the Levels of Detail algorithm based on the quadtree structure to realize the visualization of a large-scale disaster prevention scene.The test results reveal that the data fusion method controlled the error rate of the DEM data of the debris flow prevention engineering within an allowable range and generated 3D volume data(obj format)to compensate for the deficiency of the DEM data whereby the 3D internal entity space is not expressed.Additionally,the levels of detailed method can dispatch the data of a large-scale debris flow hazard scene in real time to ensure a realistic 3D visualization.In summary,the proposed methods can be applied to the planning of debris flow prevention engineering and to the simulation of the debris flow prevention process.

Weighted Multi-sensor Data Level Fusion Method of Vibration Signal Based on Correlation Function

As the differences of sensor＇s precision and some random factors are difficult to control,the actual measurement signals are far from the target signals that affect the reliability and precision of rotating machinery fault diagnosis.The traditional signal processing methods,such as classical inference and weighted averaging algorithm usually lack dynamic adaptability that is easy for trends to cause the faults to be misjudged or left out.To enhance the measuring veracity and precision of vibration signal in rotary machine multi-sensor vibration signal fault diagnosis,a novel data level fusion approach is presented on the basis of correlation function analysis to fast determine the weighted value of multi-sensor vibration signals.The approach doesn＇t require knowing the prior information about sensors,and the weighted value of sensors can be confirmed depending on the correlation measure of real-time data tested in the data level fusion process.It gives greater weighted value to the greater correlation measure of sensor signals,and vice versa.The approach can effectively suppress large errors and even can still fuse data in the case of sensor failures because it takes full advantage of sensor＇s own-information to determine the weighted value.Moreover,it has good performance of anti-jamming due to the correlation measures between noise and effective signals are usually small.Through the simulation of typical signal collected from multi-sensors,the comparative analysis of dynamic adaptability and fault tolerance between the proposed approach and traditional weighted averaging approach is taken.Finally,the rotor dynamics and integrated fault simulator is taken as an example to verify the feasibility and advantages of the proposed approach,it is shown that the multi-sensor data level fusion based on correlation function weighted approach is better than the traditional weighted average approach with respect to fusion precision and dynamic adaptability.Meantime,the approach is adaptable and easy to use,can be applied to other areas of vibration measurement.

STUDY ON THE COAL-ROCK INTERFACE RECOGNITION METHOD BASED ON MULTI-SENSOR DATA FUSION TECHNIQUE

The coal-rock interface recognition method based on multi-sensor data fusiontechnique is put forward because of the localization of single type sensor recognition method. Themeasuring theory based on multi-sensor data fusion technique is analyzed, and hereby the testplatform of recognition system is manufactured. The advantage of data fusion with the fuzzy neuralnetwork (FNN) technique has been probed. The two-level FNN is constructed and data fusion is carriedout. The experiments show that in various conditions the method can always acquire a much higherrecognition rate than normal ones.

A Study of Multi-sensor Data Fusion System Based on MAS for Nutrient Solution Measurement

For complementarity and redundancy of multi-sensor data fusion (MSDF) system,it is an effective approach for multiple components measurement.In order to measure nutrient solution on-line,a dynamic and complex system under greenhouse environment,sensors should have intelligent properties including self-calibration and self-compensation. Meanwhile,it is necessary for multiple sensors to cooperate and interact for enhancing reliability of multi-sensor system. Because of the properties of multi-agent system (MAS),it is an appropriate tool to study MSDF system.This paper proposed an architecture of MSDF system based on MAS for the multiple components measurement of nutrient solution.The sensor agent's structure and function modules are analyzed and described in detail,the formal definitions are given,too.The relations of the sensors are modeled to implement reliability diagnosis of the multi-sensor system,so that the reliability of nutrient control system is enhanced.This study offers an effective approach for the study of MSDF.

Application of data fusion on multi-function earth drill

taking the bucket of multi function earth drill as an example, combining with the conception of multi sensor integration and data fusion, adopting the terrene column chart and digging torque formula as control dependence, the detecting method of the earth drill’s working state is introduced. Multi sensor data fusion is done with the aid of BP neural network in Matlab. The data to be interfused are pre processed and the program of simulation and “point checking” is given.

Image Processing on Geological Data in Vector Format and Multi-Source Spatial Data Fusion

The geological data are constructed in vector format in geographical information system (GIS) while other data such as remote sensing images, geographical data and geochemical data are saved in raster ones. This paper converts the vector data into 8 bit images according to their importance to mineralization each by programming. We can communicate the geological meaning with the raster images by this method. The paper also fuses geographical data and geochemical data with the programmed strata data. The result shows that image fusion can express different intensities effectively and visualize the structure characters in 2 dimensions. Furthermore, it also can produce optimized information from multi-source data and express them more directly.

Weight Data Fusion Based on Mutual Support Applied in Large Diameter Measurement

The on-line diameter measurement of larger axis workpieces is hard to achieve high precision detection, because of the bad environment of locale, the problem to amend the measuring error by non-uniform temperature field, and the difficulty to collimate and locate by usual method. By improving the measurement accuracy of larger axis accessories, it is useful to raise axis and hole＇s industry produce level. Because of the influence of complex environment in locale and some influential factors which are hard excluded from the large diameter measurement with multi-rolling-wheels method, the measurement results may not support or even contradict each other. To the situation, this paper puts forward a mutual support deviation distinguish data fusion method, including mutual support deviation detection and weight data fusion. The mutual support deviation detection part can effectively remove or weaken the unexpected impact on the measurement results and the weight data fusion part can get more accurate estimate result to the detected data. So the method can further improve the reliability of measurement results and increase the accuracy of the measurement system. By using the weight data fusion based on the mutual support （DFMS） to the simulation and experiment data, both simulation results and experiment results show that the method can effectively distinguish the data influenced by unexpected impact and improve the stability and reliability of measurement results. The new provided mutual support deviation distinguish method can be used to single sensor measurement and multi-sensor measurement, and can be used as a reference in the data distinguish of other area. The DFMS is helpful to realize the diameter measurement expanded uncertainty in 5 ×10^-6D or even higher when the measured axis workpiece＇s diameter is 1-5 m （ 1 m ≤ D ≤5 m ）.

Location Data Fusion Based on Group Consensus

A new method of multi sensor location data fusion is proposed.The method is based on group consensus approach, which constructs group utility function (or its density) based on uncertainty of each sensor, and the location estimation is obtained based on the group utility function (or its density). The simulation results show that the method is better than those of mean and median estimation, and outlier and sensor failure can not affect the location estimation.

Algorithm for Multi-laser-target Tracking Based on Clustering Fusion

Multi-laser-target tracking is an important subject in the field of signal processing of laser warners. A clustering method is applied to the measurement of laser warner, and the space-time fusion for measurements in the same cluster is accomplished. Real-time tracking of multi-laser-target and real-time picking of multi-laser-signal are introduced using data fusion of the measurements. A prototype device of the algorithm is built up. The results of experiments show that the algorithm is very effective.

基于多源数据融合的水利工程测量信息动态更新系统

现有的水利工程测量信息动态更新系统,在传输测量信息时没有最佳的路径概念,采用车轮搜索,导致信息更新所需时间较长,为优化系统运行效率,设计基于多元数据融合设计水利工程测量信息动态更新系统。设计可以增强数据更新速度的芯片作为系统硬件;构造有效路径代价函数,整编水利工程测量多源数据;选择数据传输最短路径;建立最小二乘估计数学模型,引入多元数据融合设计信息更新算法。实验结果显示:在系统更新时间的测试中,面对不同数量的并行服务器,三个对照组用时均高于实验组,可见该系统具备更好的运行效率。

基于多传感数据融合的变速运行齿轮异常振动故障诊断

变速运行齿轮异常振动故障诊断性能过差会增加汽车维护成本,缩短齿轮使用寿命。为了及时识别齿轮故障,保证汽车变速器总成具有良好的振动特性,提出基于多传感数据融合的变速运行齿轮异常振动故障诊断方法。通过分析多传感器数据融合技术,掌握变速运行齿轮异常振动故障诊断的理论框架,并以此为基础,参考传感器融合模块、特征级并行多神经网络局部诊断模块和终端分类模块,结合变分模态分解、多通道加权融合和单隐层前馈神经网络训练算法,从信号采集、信号特征提取和信号特征分类3个步骤实现变速运行齿轮异常振动故障诊断。实验结果表明:在齿轮发生轻度磨损时,磨损振动信号的幅值在20~40 mV之间,磨损振动信号的频率在0~4000 Hz区间;中度磨损时,信号的幅值在30~55 mV之间,信号频率在3000~7000 Hz区间;重度磨损时,信号幅值在50~70 mV之间,信号频率在6000~12000 Hz区间,且各阶段诊断结果均与故障程度的实际转折点吻合。由此可知在各样本数量均相同的情况下,提出的故障诊断方法预测值与真实值均相同,故障程度和故障类型的诊断性能均较好。

三维成矿预测关键问题

三维成矿预测是当前深部找矿预测和勘查的重要方法和手段,其方法体系和实践应用均已取得大量成果,但同时存在若干关键科学技术问题,导致其进一步发展受到制约。本文从多尺度三维成矿预测方法体系不完善、不确定性分析与优化研究薄弱、三维成矿预测要素挖掘存在瓶颈、缺少针对三维成矿预测的三维深度学习模型和方法等关键问题出发,对目前三维成矿预测领域相关方面的研究进展进行综合分析,并提出针对上述关键问题可能的解决方案和研究方向。预期未来三维成矿预测领域的研究工作将创新发展出多种方法,实现对三维预测信息的深度挖掘;构建形成适用的三维深度学习模型和训练方法,有效增强三维成矿预测结果的预测能力;通过系统性地开展三维成矿预测不确定性研究,进一步优化预测过程和结果,有效提高三维成矿预测方法的可靠性和准确性;形成面向多尺度三维成矿预测的方法体系,更有效地指导矿集区-矿田-勘查区块(矿床)等不同级别的深部矿产资源找矿勘查工作。相关关键问题的解决将进一步深化和完善三维成矿预测理论和方法体系,促进三维成矿预测理论方法的实践应用,显著提升深部找矿预测和勘查工作的效率与水平,助力深部找矿突破。

融合DEM与FY-4A数据的ECMWF预报产品深度学习订正方法

精准的数值天气预报是精细化气象公共服务和商业服务的重要前提。欧洲中期天气预报中心(European Center forMedium Weather Forecasting,ECMWF)预报产品在全球被广泛采用,但始终存在系统预报误差。针对数值天气预报中的误差和多源数据融合中的非线性映射等问题,设计了一个ECMWF数值预报产品的深度学习订正模型(Numerical Forecast CorrectionNetwork,NFC-Net)。NFC-Net引入了FY-4A卫星观测数据、数字高程模型数据(Digital Elevation Model,DEM)和ERA5历史实况数据订正预报结果,利用多源数据空间分辨率对齐模块、时空特征提取模块解决多源异构数据特征的提取与融合问题,并通过UNet网络实现ECMWF预报产品的订正。为了评估所提算法的性能,利用NFC-Net对ECMWF产品中的2 m气温和10 m风速两个天气要素开展订正试验,并将试验结果与ECMWF预报结果、ANO方法订正结果、Convlstm方法订正结果、Fuse-CUnet方法订正结果和ERA5实况进行对比。结果显示,NFC-Net模型订正的2 m气温和10 m风速的均方根误差(Root Mean Squared Error,RMSE)分别较ECMWF预报产品下降49.71%和50.86%。表明NFC-Net模型可以充分利用多源数据有效改善复杂地形条件下的订正结果。NFC-Net模型可用于订正ECMWF预报结果,显著提升数值天气预报的精度。

基于D-S证据理论的农作物气候品质预测方法研究:以晚熟杂交柑橘春见为例

【目的】基于多源气象数据构建果实品质(糖含量等级)预测模型,为科学评价果实气候品质及深入挖掘农产品气候资源提供科学依据。【方法】以晚熟柑橘春见果实为研究对象,利用多源数据融合技术、人工神经网络(BP神经网络、RBF神经网络和Elman神经网络)和D-S证据理论,包括气象数据质量控制、特征选取、特征级融合、决策级融合4个步骤,构建基于多源气象数据的果实品质(糖含量等级)预测模型。【结果】春见果实品质预测模型采用BP神经网络预测结果总体准确率为87.50%,平均绝对误差(MAE)为0.150,均方根误差(RMSE)为0.447;RBF神经网络预测结果总体准确率为85.00%,MAE为0.175,RMSE为0.474;Elman神经网络预测结果总体准确率为87.50%,MAE为0.150,RMSE为0.447;D-S证据理论决策融合总体预测准确率达95.20%,分别较BP神经网络、RBF神经网络和Elman神经网络提升7.7百分点、10.2百分点和7.7百分点,MAE和RMSE分别为0.040和0.214,均明显降低。【结论】D-S证据理论决策融合后的果实品质预测准确率相比单一神经网络预测更高、误差更小。

多模态数据融合的加工作业动态手势识别方法

为了解决单模态数据所提供的特征信息缺乏而导致的识别准确率难以提高、模型鲁棒性较低等问题,提出了面向人机交互的加工作业多模态数据融合动态手势识别策略。首先,采用C3D网络模型并在视频的空间维度和时间维度对深度图像和彩色图像两种模态数据进行特征提取;其次,将两种模态数据识别结果在决策层按最大值规则进行融合,同时,将原模型使用的Relu激活函数替换为Mish激活函数优化梯度特性;最后,通过3组对比实验得到6种动态手势的平均识别准确率为96.8%。结果表明:所提方法实现了加工作业中动态手势识别的高准确率和高鲁棒性的目标,对人机交互技术在实际生产场景中的应用起到推动作用。

基于交叉注意力的多源数据融合的气体泄漏检测

为解决单一传感器在管道气体泄漏检测时容易出现误报、漏报的问题,及时预警并反馈泄漏状况,提出一种基于交叉注意力的多源数据融合管道泄漏检测方法。首先,利用预训练的ShuffleNetV2模型提取热像仪数据的空间特征;然后,结合一维卷积神经网络(1DCNN)和双向门控循环单元(BiGRU),构建1DCNN-BiGRU模型,以提取气体传感器数据的时序特征;最后,运用交叉注意力捕获数据的时空关联性得到2个数据源的特征表示,通过残差方式进行特征连接后输入到分类层中,得到识别结果。结果表明:所构建的多源数据融合模型(SCGA)对气体识别准确率为99.22%,损失值在0~0.04内波动;与仅使用气体传感器数据的支持向量机(SVM)、1DCNN、BiGRU模型相比,准确率至少提升4.12%;与仅使用热图像传感器数据的MobileNetV3、ShuffleNetV2、ResNet18模型相比,准确率至少提升1.14%;与将时序特征和空间特征直接拼接的多源数据融合模型(SCG)相比,准确率提升1%。SCGA模型对气体识别具有较高精度。

基于多尺度骨架图和局部视觉上下文融合的驾驶员行为识别方法

识别非驾驶行为是提高驾驶安全性的重要手段之一。目前基于骨架序列和图像的融合识别方法具有计算量大和特征融合困难的问题。针对上述问题,本文提出一种基于多尺度骨架图和局部视觉上下文融合的驾驶员行为识别模型(skeleton-image based behavior recognition network,SIBBR-Net)。SIBBR-Net通过基于多尺度图的图卷积网络和基于局部视觉及注意力机制的卷积神经网络,充分提取运动和外观特征,较好地平衡了模型表征能力和计算量间的关系。基于手部运动的特征双向引导学习策略、自适应特征融合模块和静态特征空间上的辅助损失,使运动和外观特征间互相引导更新并实现自适应融合。最终在Drive&Act数据集进行算法测试,SIBBR-Net在动态标签和静态标签条件下的平均正确率分别为61.78%和80.42%,每秒浮点运算次数为25.92G,较最优方法降低了76.96%。

综掘工作面风流调控下风速及瓦斯粉尘浓度融合预测模型研究

针对综掘工作面传统的通风总量控制管理模式不能根据实际需求进行风流调控,造成瓦斯及粉尘聚集和污染隐患等问题,对风流调控下的风速及瓦斯粉尘浓度多源数据融合神经网络预测模型进行了研究。采用欧拉-拉格朗日法建立了风流调控下的瓦斯及粉尘气固耦合模型并进行了测试验证,模拟分析瓦斯和粉尘颗粒在综掘巷道的分布情况,获取大量不同风流调控方案下的风速及瓦斯粉尘浓度样本数据。采用多层感知器神经网络技术建立预测模型结构,选取对瓦斯及粉尘浓度具有较大影响的风流调控等参数作为输入层,根据风速及瓦斯粉尘的隐患位置确定输出层,对样本数据进行预处理,通过引入差分进化算法搜索最佳隐藏层节点数和学习率,利用TensorFlow框架搭建多源数据融合神经网络预测模型。以陕北某矿综掘工作面为研究对象,对不同风流调控方案进行预测和井下实测验证。结果表明:该模型相对误差最大值为9.7%,具有较高的准确性;选取出风口距端头最短距离5 m和最远距离10 m这2种工况下的最佳调控方案,与调控前相比,风速符合规范要求,端头死角区瓦斯体积分数分别降低34%和35%,回风侧人行处平均粉尘质量浓度分别降低40%和41%,司机处粉尘质量浓度分别降低38%和36%,研究可为风流调控提供参考。

多源数据融合在行政区域界线争议处理中的探索与应用

行政区域界线精准落地对资源保护利用及国家长治久安至关重要。随着城市化进程加快及优化调整举措推进,界线争议时有发生,给相关部门日常事务管理带来了诸多挑战。依据高精度行政区域界线勘定工作中争议处理原则与程序,探讨和分析了多源数据融合分析方法在争议解决中的应用,并结合具体案例,重点论述了高精度多源数据融合方法在不同区域(山区、城区)类型争议处理中的可操作性。实践表明,多源数据融合为稳定研判争议解决方案提供了有效的数据支撑,争议界线落地后为行业部门事务管理提供了强有力的法定依据。