CN-117222590-B - Jam sign estimation device, jam sign estimation method, and recording medium

CN117222590BCN 117222590 BCN117222590 BCN 117222590BCN-117222590-B

Abstract

A jam sign estimating device (100) estimates a jam sign of a jam in a paper feeding device (200), and is provided with a sound collecting unit (112) for collecting frictional sounds of paper (10) generated when paper (10) is fed from a holding unit (270) for holding a plurality of sheets of paper (10) into the paper feeding device (200), an estimating unit (114) for estimating the presence or absence of the jam sign in the paper feeding device (200) based on an output result obtained by inputting information on the frictional sounds into a learned machine learning model, and an output unit (116) for outputting a signal for stopping feeding the paper (10) into the paper feeding device (200) to the paper feeding device (200) when the estimating unit (114) estimates the presence of the jam sign.

Inventors

WADA MASATO
MATSUMURA TOSHIYUKI

Assignees

松下电器（美国）知识产权公司

Dates

Publication Date: 20260512
Application Date: 20220113
Priority Date: 20210428

Claims (10)

1. A jam sign estimating device estimates a sign of a jam in a paper feeding device, comprising: A sound collecting unit configured to collect a friction sound generated when paper is fed from a holding unit configured to hold a plurality of sheets of paper into the paper feeding device, the friction sound being a non-audible sound generated by friction between the sheets of paper in the vicinity of a separation roller configured to separate the sheets of paper one by one in the paper feeding device; A estimating unit for estimating whether or not paper floating occurs in the paper feeding device based on an output result obtained by inputting information on the fricatives into a learned model, which is a learned machine learning model, and And an output unit configured to output a signal to the paper feeder to stop feeding the paper to the inside of the paper feeder when the estimation unit estimates that the paper is floating.
2. The jam warning apparatus of claim 1, wherein, The information on the fricatives inputted into the learned model is an image of a spectrogram of the fricatives or an image of frequency characteristics.
3. The jam warning device of claim 1 or 2, wherein, The friction sound is a non-audible sound generated by friction between the paper supplied from the holding portion and the paper held in the holding portion.
4. The jam sign-estimating apparatus as recited in claim 3, wherein, The non-audible sound is a sound of a frequency in the ultrasonic range.
5. The jam warning device of claim 1 or 2, wherein, The teacher data used in the learning of the machine learning model described above includes: 1 st data composed of information related to the above fricatives and notes indicating occurrence of paper floating, and The 2 nd data is composed of information on the above-mentioned fricatives and comments indicating that no paper floating has occurred.
6. The jam warning device of claim 1 or 2, wherein, The learned model includes a plurality of learned models corresponding to a plurality of types of paper, respectively; The jam prediction estimation device further includes a recognition unit that recognizes a type of the paper fed from the holding unit into the paper feeder; The estimating unit inputs information on the fricatives to the learned model corresponding to the identified type of paper based on the type of paper identified by the identifying unit.
7. The jam prediction mode estimation apparatus of claim 6, wherein, The identification unit identifies the type of the paper based on data acquired by at least one of an image sensor, an ultrasonic sensor, an optical sensor, a weight sensor, and machine learning.
8. The jam warning device of claim 1 or 2, wherein, The machine learning model is a convolutional neural network model.
9. A jam sign predicting method of predicting a sign of a jam in a paper feeding apparatus, comprising: a sound collecting step of collecting a friction sound generated when paper is fed from a holding portion for holding a plurality of sheets of paper into the paper feeding device, the friction sound being a non-audible sound generated by friction between the sheets of paper in the vicinity of a separation roller for separating the sheets of paper one by one in the paper feeding device; A estimating step of estimating whether or not paper floating occurs in the paper feeding device based on an output result obtained by inputting information on the fricatives into a learned model, which is a learned machine learning model, and And an output step of outputting a signal to the paper feeder to stop feeding the paper to the inside of the paper feeder when it is estimated that the paper is lifted.
10. A recording medium which is a computer-readable non-transitory recording medium in which a program for causing a computer to execute the jam sign estimation method according to claim 9 is recorded.

Description

Jam sign estimation device, jam sign estimation method, and recording medium Technical Field The present disclosure relates to a jam sign estimation device, a jam sign estimation method, and a recording medium. Background For example, in a paper feeder that feeds paper to an image reading apparatus such as a printer or an image copying apparatus (so-called scanner), paper jam may occur due to, for example, paper double feed, skew feed, staple stapling, or the like. Depending on the degree of paper jam, not only may the job be stopped, but also the paper may be damaged and unusable. Therefore, a technique of detecting the occurrence of a jam in advance is demanded. For example, patent document 1 discloses a technique of receiving an ultrasonic wave transmitted from an ultrasonic wave transmitting unit provided at one part of a medium supporting unit by an ultrasonic wave receiving unit provided at the other part of the medium supporting unit, and determining whether or not there is a floating of a medium with respect to a mounting surface (hereinafter, referred to as a paper floating) based on a sound pressure of the received ultrasonic wave. Prior art literature Patent literature Patent document 1 Japanese patent application laid-open No. 2020-142868 Disclosure of Invention Problems to be solved by the invention However, in the technique described in patent document 1, it is necessary to provide an ultrasonic wave transmitting unit in order to determine whether or not paper floating occurs, and it is difficult to say that it is possible to easily estimate the presence or absence of a sign of paper jam (that is, occurrence of paper floating). An object of the present disclosure is to provide a jam sign estimating device, a jam sign estimating method, and a recording medium capable of easily predicting the presence or absence of a sign of a jam. Means for solving the problems A jam sign estimating device according to an aspect of the present disclosure is a jam sign estimating device for estimating a sign of a jam in a paper feeding device, and includes a sound collecting unit configured to collect a friction sound generated when paper is fed from a holding unit configured to hold a plurality of sheets of paper into the paper feeding device, a estimating unit configured to estimate whether or not a sign of a jam in the paper feeding device is present based on an output result obtained by inputting information related to the friction sound into a learned model, which is a machine learning model, and an output unit configured to output a signal to stop feeding the paper into the paper feeding device to the paper feeding device when the estimating unit estimates that the sign of the jam is present. Effects of the invention According to the present disclosure, it is possible to provide a warning estimating device, a warning estimating method, and a recording medium that can easily estimate whether a warning of a jam exists. Drawings Fig. 1 is a diagram showing an example of a paper feeding apparatus to which the jam prediction estimation apparatus according to embodiment 1 is applied. Fig. 2 is a diagram showing an example of a conveying section of the paper feeding device according to embodiment 1. Fig. 3 is a diagram showing an example of the configuration of the jam sign estimation device and the paper feeding device according to embodiment 1. Fig. 4 is a diagram showing an example of a sign of a jam in embodiment 1. Fig. 5 is a flowchart showing the operation of the jam sign estimation device according to embodiment 1. Fig. 6 is a diagram showing an example of the configuration of a jam sign estimation device according to modification 1 of embodiment 1. Fig. 7 is a diagram showing an example of the configuration of the jam sign estimation device and the paper feeding device according to embodiment 2. Fig. 8 is a flowchart showing the operation of the jam sign estimation device according to embodiment 2. Fig. 9 is a diagram showing an example of the configuration of a jam sign estimation device and a paper feeding device according to modification 1 of embodiment 2. Fig. 10 is a flowchart showing the operation of the jam warning estimation device according to modification 1 of embodiment 2. Fig. 11 is a diagram for explaining the machine learning model used in embodiment 1 and embodiment 2. Fig. 12 is a graph showing the results of example 1. Fig. 13 is a graph showing the results of example 2. Fig. 14 is a graph comparing the estimation accuracy of example 1 and example 2 for 4 kinds of paper of example 2. Detailed Description (Summary of the disclosure) A jam sign estimating device according to an aspect of the present disclosure is a jam sign estimating device for estimating a sign of a jam in a paper feeding device, and includes a sound collecting unit configured to collect a friction sound generated when paper is fed from a holding unit configured to hold a plurality of sheets of paper into the paper feedi