Unlock instant, AI-driven research and patent intelligence for your innovation.

Interactive multi-model filtering method of automatic feeding and weighing system

An interactive multi-model, weighing system technology, applied in the field of automatic feeding and weighing, which can solve problems such as model mismatch

Active Publication Date: 2021-06-18
HUBEI POLYTECHNIC UNIV
View PDF9 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Aiming at the technical problems existing in the prior art, the present invention provides an interactive multi-mode

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Interactive multi-model filtering method of automatic feeding and weighing system
  • Interactive multi-model filtering method of automatic feeding and weighing system
  • Interactive multi-model filtering method of automatic feeding and weighing system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0079] Embodiment 1 of the present invention is an embodiment of an interactive multi-model filtering method according to the present invention, and the technical problem to be solved by the embodiment of the present invention is to add speed in automatic feeding system. It is not easy to ensure that the refueling, the addition is too slow, the contradiction is too low, providing an interactive multi-model filtering method for automatic feeding weighing system, and can accurately estimate the real weight of materials by multi-model switches. The thick feeding and cutting feed can be accurately switched. Finally, with a grain factory automatically weigh the packaged equipment, the sampling cycle can be 0.1s, 5kg, 10kg, and 15kg sampling data for interactive multi-model else, and with Kalman estimated and else. The root mean square error of the manda, the stable time is compared with the stability error. As a result, the present invention can improve the weighing accuracy in the cas...

Embodiment 2

[0144] Embodiment 2, the present invention, is a specific application embodiment of an interactive multi-model filtering method of an automatic feeding weighing system according to the present invention. In order to verify the dynamic performance of this algorithm, this article is automatically weighing a grain machine factory. The equipment is platform, sampling cycle is 0.1s, 15kg sampling data for Kalman, homologable Karman, interactive multi-model Kalman and interactive multi-model hikalman filtering, using IMM algorithm available automatic feeding weighing The post-test mode probability of the model is like Figure 5 Indicated. It can be seen that the IMM algorithm can adaptively identify the real dynamic weighing state of the automatic feeding, especially in the initial feed and thick feeding section process being affected by impact force, aerial flying material and system vibration, and cannot be consistent with a single model. Adaptive multi-model interaction, quickly and a...

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

No PUM Login to View More

Abstract

The invention relates to an interactive multi-model filtering method of an automatic feeding and weighing system. The method comprises the following steps: constructing a physical model of a weighing structure and a state equation and a measurement equation of the weighing structure; constructing an interactive multi-model of parameters of the state equation and the measurement equation; calculating a mixed state estimation value and a mixed covariance estimation value of each model according to a state equation corresponding to the interactive multi-model; performing unscented Kalman filtering on each input model, and outputting a state estimation value and a covariance estimation value corresponding to each model at the current moment; calculating the applicable weight value of each model, and finally updating the probability matrix of each model; weighting and combining the filtering result of each model according to the model probability, and outputting an optimal state estimation value at the current moment and a corresponding state estimation covariance. The real weight of the materials can be accurately estimated through switching among multiple models, and then coarse and fine feeding and feeding cutting can be accurately switched, so that the requirement for weighing precision is met while the packaging efficiency is improved.

Description

Technical field [0001] The present invention relates to the field of automatic feeding weighing, and more particularly to an interactive multi-model filtering method for automatic feeding weighing systems. Background technique [0002] At present, in the fields of food, industrial raw materials, drugs and metal hardware, many production lines have automatic feeding, the speed and accuracy of the weighing is the guarantee of this link. How to quickly estimate the true weight of the truth from the unstable dynamic weighing signal to reduce the effects of disturbance noise on dynamic weighing precision, which is the difficulty of this link. There are many scholars to improve the improvement of the improving precision, mainly with the simulation of decomposition, Kalman filtering, neural network and noise model identification method and wavelet filtering method, each method improves the weighing accuracy varying degrees, But all have their own shortcomings. Experience modal decomposi...

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
no application Login to View More
IPC IPC(8): G06F17/10G06F17/18G06F30/20
CPCG06F17/10G06F17/18G06F30/20
Inventor 李玉平
Owner HUBEI POLYTECHNIC UNIV