A Neural Network Based Adaptive Control Method for Gas Valve
A self-adaptive control and neural network technology, applied in the field of air valve self-adaptive control based on neural network, can solve the problems of slow speed, difficulty, and poor weft adaptability.
Active Publication Date: 2017-01-18
杭州纳众科技有限公司
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0002] The air-jet loom is a shuttleless loom that uses jet air to pull the weft yarn through the shed. The weft insertion method of the traditional air-jet loom determines that its adaptability to the weft yarn is not very good, especially with the increase in product complexity, weft yarns with different characteristics There are more and more varieties of mixed weaving, but the weft insertion control scheme of the traditional air-jet loom cannot meet this demand at all. Its inherent defect is that the speed of the vehicle is slow
Traditional air-jet loom weft insertion control method: Engineers edit the weft insertion characteristics of various weft yarns according to the characteristics of various weft yarns, and then manually correct the weft insertion data gradually through on-site machine adjustments. It becomes very difficult in the case of weaving. It is difficult to meet the weft insertion of one kind of weft yarn to meet the requirement of another kind of weft yarn. Even if the opening time of the nozzle is increased to meet this requirement, it is a waste of a lot of compressed air to achieve it, which is very unfavorable. energy saving
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0044] Such as figure 1 As shown, the artificial neural network consists of an input layer, a hidden layer and an output layer. The number of neuron units in each layer can be set according to different application situations. Here, three air valve control is taken as an example.
[0045] Such as figure 2 As shown, the control scheme structure of a neural network-based air valve adaptive control method includes a weft arrival time observer and a weft arrival time target, a learning algorithm, a BP neural network NN, and a controlled object (air valve).
[0046] A kind of neural network-based air valve self-adaptive control method of the present invention, this method specifically comprises the following steps:
[0047] Step (1): Select the structure of the BP neural network NN in advance, that is, select the number of input layer nodes M, the number of hidden layer nodes Q and the number of output layer nodes N, and give the initial value of the weighting coefficient of each...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses an air valve self-adaptation control method based on the neural network. According to the air valve self-adaptation control method based on the neural network, a weft reaching time observer, a weft reaching time target, a learning algorithm, the BPNN and a controlled object (namely an air valve) are included. According to the air valve self-adaptation control method based on the neural network, weft insertion of an air jet loom can adapt to weaving of various wefts automatically. Compared with a traditional weft insertion control mode of the air jet loom, mixed weaving of wefts of different characteristics is very convenient, it is unnecessary to waste a large amount of compressed air to adjust the starting time of a large nozzle, and the effects of energy conservation and environment protection are achieved.
Description
technical field [0001] The invention belongs to the field of textiles, and in particular relates to an adaptive control method for an air valve based on a neural network. Background technique [0002] The air-jet loom is a shuttleless loom that uses jet air to pull the weft yarn through the shed. The weft insertion method of the traditional air-jet loom determines that its adaptability to the weft yarn is not very good, especially with the increase in product complexity, weft yarns with different characteristics There are more and more varieties of mixed weaving, but the weft insertion control scheme of the traditional air-jet loom cannot meet this demand at all. Its inherent defect is that the vehicle speed is slow. Traditional air-jet loom weft insertion control method: Engineers edit the weft insertion characteristics of various weft yarns according to the characteristics of various weft yarns, and then manually correct the weft insertion data gradually through on-site m...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G05B13/04
Inventor 李波金崇程章永亮高明煜王亮吕程辉戴岳尧
Owner 杭州纳众科技有限公司