Research on Tool Management and Online Detection Technology in Flexible Manufacturing System (4)

3.2 Neural Network Technology The neural network system of the tool load adaptive control adopts a 3-layer BP structure. According to the above analysis, it is obvious that the input layer has 4 nodes, and the output layer has 3 nodes, that is, the size of the load in the XYZ direction. Considering the characteristics of the load adaptive control system, the load can be considered as a continuous function of the feed rate. According to the Kolmogorov theorem, the number of nodes in the intermediate hidden layer should be 2 times the number of input points plus one. Therefore, the neural network structure has 4 nodes in the input layer, 9 nodes in the middle layer, and 3 nodes in the output layer. According to the above analysis, each node is given 4 values, and different combinations of them are used as sample input data, so that 256 samples can be obtained. The specific method is: divide each input quantity into 4 equal parts within the possible variation range, and experimentally measure the load value under each input condition. After obtaining 256 samples, the learning is performed offline, and the weight of each node is obtained. Thus, the learned neural network establishes a corresponding tool load model to provide conditions for online detection of the tool.

3.3 Tool online detection principle The principle of tool online detection is shown in Figure 1.

The cutting depth and feed rate of the tool are first measured, along with the spindle speed and the type of material being machined into the neural network controller. The load calculation is performed by the neural network controller, and the resulting load is input to the detector. The result of the detector output is compared with the input signal. If the load exceeds the crack propagation load under the fatigue condition of the tool, the feed rate of the tool is reduced, and the decrease of the feed rate is fed back to the CNC controller. The CNC controls accordingly to change the size of the load to a safe level.

4 Conclusion <br> <br> in flexible manufacturing system, a good tool management system and online testing technology, not only can improve processing productivity, reduce labor costs, but also for the optimization of the product portfolio, reduce the failure rate will play a key effect.

references:

[1] Zhang Genbao. Automated Manufacturing System [M]. Beijing: Mechanical Industry Press, 2002.

[2] Zhang Peizhong. Flexible Manufacturing System [M]. Beijing: Mechanical Industry Press, 1998.

[3] Ouyang Puren. Research on the Architecture of FMS Tool Management System[J]. Journal of Nanjing University of Science and Technology, 1996, (6): 32-34.

Previous page

PVC Suppermatt Edge Banding

PVC Super Matt Edge Banding we adopt quality PVC raw material, German UV and ink, JOWAT primer. Thousand designs, 0.35-3.0mm thickness and 12-620mm width. All high-edge raw materials to make sure our PVC matt edge banding is the first class products in this world. Sinowolf Plastic Dekor CO., LTD always focus on producing best quality edge band. Using high-end raw materials, all chemical additives import from Europe, to make sure our plastic edge banding keep stable quality 3-5 years. Our products range include PVC edge band, ABS edge band, 3D PMMA acrylic edge band, Aluminum edge band.