摘要：【中文】一种便携式多功能操作台，本申请加工工作台面后侧端有防滑手提柄，伸缩式固定带一端固定在加工工作台面底部另一端有锁扣的扣紧部分，锁扣的固定部分固定在加工工作台面另一侧，加工工作台面中部上方有Z轴向工作台滑轨，Z轴向工作台滑轨的工作板面支撑滑块上固定有工作面板，H型可伸缩支撑立柱固定在加工工作台面上，H型可伸缩支撑立柱一侧有X轴向可伸缩滑轨，滑轨座在X轴向可伸缩滑轨，滑轨座后侧有原料储存盒，滑轨座前侧有Y轴向可伸缩滑轨，移动原料暂存装置设置在Y轴向可伸缩滑轨一侧，移动原料暂存装置底端有喷头。本申请设备后侧有把手，工作部分可以收起，收起后通过固定带进行固定，这样收起后更易于携带，并且整体操作方便。 【EN】The utility model provides a portable multifunctional operation platform, this application processing table surface rear end has anti-skidding portable handle, telescopic fixed band one end is fixed and is had the straining part of hasp at the processing table surface bottom other end, the fixed part of hasp is fixed at the processing table surface opposite side, there is Z axial workstation slide rail processing table surface middle part top, be fixed with the work panel on the work face supporting slide of Z axial workstation slide rail, the scalable support post of H type is fixed on processing table surface, there is the scalable slide rail of X axial on one side of the scalable support post of H type, the slide rail seat is at the scalable slide rail of X axial, slide rail seat rear side has the raw materials to store the box, slide rail seat front side has the scalable slide rail of Y axial, remove raw materials temporary storage device and set up in Y axial scalable slide rail one side, it has the shower nozzle to. This application equipment rear side has the handle, and the working part can be packed up, packs up the back and fixes through the fixed band, packs up the back like this and changes in carrying to whole convenient operation.

摘要：【中文】一种噪声环境下多维力传感器的解耦方法。该方法包括以下步骤：步骤1，通过信号调理电路和采集系统获取传感器输出电压U与标准砝码重量(力)F相对应的标定数据；步骤2，将步骤1中获得的标定数据添加噪声，其中信噪比控制在20～30dB之间；步骤3，将步骤2中生成的多组噪声样本顺序依次拼接，同时进行归一化处理，形成新的数据样本；步骤4，将步骤3中获取的样本输入到深度神经网络(DNN)中进行训练，并判断是否达到模型收敛的条件，若达到条件，跳转至步骤4，否则继续执行步骤2；步骤5，模型训练结束，并将训练得到的模型嵌入传感器采集系统，最终应用于实际工业现场。本发明提高了传感器在噪声环境下的鲁棒性，具有良好的实际应用价值。 【EN】A decoupling method of a multi-dimensional force sensor in a noise environment. The method comprises the following steps: step 1, acquiring calibration data corresponding to the output voltage U of a sensor and the weight (force) F of a standard weight through a signal conditioning circuit and an acquisition system; step 2, adding noise to the calibration data obtained in the step 1, wherein the signal-to-noise ratio is controlled to be 20-30 dB; step 3, sequentially splicing the multiple groups of noise samples generated in the step 2, and simultaneously performing normalization processing to form a new data sample; step 4, inputting the sample obtained in the step 3 into a Deep Neural Network (DNN) for training, judging whether a condition of model convergence is reached, if so, jumping to the step 4, otherwise, continuing to execute the step 2; and 5, finishing model training, embedding the trained model into a sensor acquisition system, and finally applying the model to an actual industrial field. The invention improves the robustness of the sensor in a noise environment and has good practical application value.