CN112801392B - Intelligent speed prediction method for corrugated paper machine - Google Patents
Intelligent speed prediction method for corrugated paper machine Download PDFInfo
- Publication number
- CN112801392B CN112801392B CN202110162647.4A CN202110162647A CN112801392B CN 112801392 B CN112801392 B CN 112801392B CN 202110162647 A CN202110162647 A CN 202110162647A CN 112801392 B CN112801392 B CN 112801392B
- Authority
- CN
- China
- Prior art keywords
- data
- vehicle speed
- speed
- vibration
- uplink
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The embodiment of the invention provides an intelligent speed prediction method for a corrugated paper machine, which comprises the following steps of: step one: collecting vibration data by using MCM100 equipment; step two: reading parameter data of a production management system; step three: processing and analyzing the vibration data and the parameter data; step four: based on the feature engineering, clustering the vibration data and the parameter data by using a clustering algorithm to obtain feature training data; step five: training the feature training data by using a machine learning algorithm so as to predict the speed of the corrugated paper machine; the embodiment of the invention is convenient for predicting the speed of the corrugated paper machine and reducing the fluctuation of the speed and vibration, thereby improving the quality of paper and further realizing the improvement of the production efficiency.
Description
Technical Field
The invention relates to the technical field of intelligent manufacturing, in particular to an intelligent speed prediction method for a corrugated paper machine.
Background
The traditional paper mill can not monitor the running state of the corrugated machine and the production state of paper in real time, if abnormal conditions are not processed, the difference of the quality effect of the produced paper is large, and sometimes the corrugated paper is wrinkled and damaged, the traditional speed control mode of the corrugated paper machine is a manual adjustment method, the traditional manual adjustment method is unstable, the speed fluctuation is large, the vibration fluctuation of the corrugated paper machine is large, the corrugated paper is wrinkled and damaged, most of the time of the manual speed adjustment method does not reach the optimal speed of the corrugated paper machine under certain corrugated paper materials and breadth conditions, the production efficiency is influenced, and the labor cost for controlling the speed of the corrugated paper machine is also a great expense of a factory.
Summary of the invention
In order to overcome the defects of the prior art, the invention provides an intelligent speed prediction method for a corrugated paper machine, which is used for solving the technical problems of unstable speed, low paper quality, easy breakage of paper and low paper production efficiency of the corrugated paper machine.
The technical scheme adopted for solving the technical problems is as follows: the intelligent speed prediction method for the corrugated paper machine comprises the following steps:
step one: collecting vibration data by using MCM100 equipment;
step two: reading parameter data of a production management system;
step three: processing and analyzing the vibration data and the parameter data;
step four: based on the feature engineering, clustering the vibration data and the parameter data by using a clustering algorithm to obtain feature training data;
step five: the feature training data is trained using a machine learning algorithm to predict the speed of the corrugating machine.
Specifically, vibration data is collected using MCM100 devices, the steps comprising:
accessing a vibration sensor to acquire time domain data by using the MCM 100;
converting the time domain data into FFT spectrum data through Fourier transform;
calculating an OA value by the FFT spectrum data;
specifically, the OA value is calculated by FFT spectral data, the steps including:
by calculation of
Evaluating the vibration acceleration of the corrugated paper machine conveyor belt;
wherein OA is the OA value of the full bandwidth or a certain frequency band, n is the number of spectrum analysis strips in the full bandwidth or the frequency band, A i For amplitude values on the spectrum analysis line, i.e. FFT spectral data, N BF To weight the window factor, the Hanning window is 1.5.
Specifically, the step of reading production management system parameter data includes:
reading a text file stored in a corrugated paper machine production management system;
and acquiring target data corresponding to the corrugated medium from a text file stored in the production management system, wherein the target data comprises material data, breadth data, stupefied data and vehicle speed data.
Specifically, the vibration data and the parameter data are processed and analyzed, and the steps include:
acquiring speed data, material data and breadth data at regular time according to time sequence;
selecting data with a speed greater than 50, selecting data with a material not empty and selecting data with a width greater than 0, and carrying out data numeralization on the material data and the stupefied data;
and fixing materials, ridges and widths, and visualizing vehicle speed data and vibration data according to time sequence.
Specifically, based on feature engineering, the vibration data and the parameter data are clustered by using a clustering algorithm, and the steps comprise:
fixing materials, edges, widths and vehicle speeds, and calculating the average value of vibration data;
fixing materials, ridges and widths, and counting the occurrence frequency of the vehicle speed;
and the vehicle speed data with the top 12 rank is screened according to the vehicle speed frequency.
Preferably, the steps further include, after the vehicle speed data of the top 12 of the screening frequency rank are sequentially arranged according to the vehicle speed frequency:
according to the calculated average value of the vibration data of each vehicle speed, vehicle speeds smaller than the vibration average value in the 12 vehicle speeds are screened out;
using a Kmeans clustering algorithm to gather the vehicle speeds smaller than the vibration mean value into two types of vehicle speeds;
and selecting the maximum value and the minimum value of the two types of vehicle speeds to form a first vehicle speed range and a second vehicle speed range.
Preferably, after selecting the maximum value and the minimum value of the two types of vehicle speeds to form the first vehicle speed range and the second vehicle speed range, the steps further include:
judging whether the current vehicle speed is an upward vehicle speed range or a downward vehicle speed range according to the first vehicle speed range and the second vehicle speed range;
when the current vehicle speed is in the uplink vehicle speed range, the label of the uplink vehicle speed takes the average value of the uplink vehicle speed range;
and when the current vehicle speed is in the downlink vehicle speed range, taking down the average value of the downlink vehicle speed range by the label of the downlink vehicle speed.
In particular, the feature training data is trained using a machine learning algorithm to predict the speed of the corrugator machine,
the steps include:
the feature training data are divided into uplink vehicle speed training data and downlink vehicle speed training data according to the uplink vehicle speed labels and the downlink vehicle speed labels, the uplink vehicle speed training data and the downlink vehicle speed training data are respectively divided into 10 parts, the divided training data account for 8 parts, and the verification data account for 2 parts.
Specifically, after dividing the uplink vehicle speed training data and the downlink vehicle speed training data, the steps further include:
training the divided uplink vehicle speed training data and the divided downlink vehicle speed training data by using an Lgb gradient lifting tree algorithm;
and verifying the predicted uplink vehicle speed and the predicted downlink vehicle speed by using the verification data.
The embodiment of the invention has the beneficial effects that: the method comprises the following steps: collecting vibration data by using MCM100 equipment; step two: reading parameter data of a production management system; step three: processing and analyzing the vibration data and the parameter data; step four: based on the feature engineering, clustering the vibration data and the parameter data by using a clustering algorithm to obtain feature training data; step five: the machine learning algorithm is utilized to train the characteristic training data so as to predict the speed of the corrugated paper machine and reduce the fluctuation of the speed and vibration, thereby improving the quality of paper and further realizing the improvement of the production efficiency.
Drawings
Fig. 1 is a schematic flow chart of an intelligent speed prediction method for a corrugated paper machine.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The following describes in detail the implementation of the present invention in connection with specific embodiments:
embodiment one:
fig. 1 shows a flow of implementation of an intelligent speed prediction method for a corrugated paper machine according to an embodiment of the present invention, and for convenience of explanation, only the relevant parts of the embodiment of the present invention are shown, which is described in detail below:
in step S101, vibration data is collected using MCM100 devices;
specifically, vibration data is collected using MCM100 devices, the steps comprising:
accessing a vibration sensor to acquire time domain data by using the MCM 100;
converting the time domain data into FFT spectrum data through Fourier transform;
calculating an OA value by the FFT spectrum data;
specifically, the OA value is calculated by FFT spectral data, the steps including:
by calculation of
Evaluating the vibration acceleration of the corrugated paper machine conveyor belt;
wherein OA is the OA value of the full bandwidth or a certain frequency band, n is the number of spectrum analysis strips in the full bandwidth or the frequency band, A i For amplitude values on the spectrum analysis line, i.e. FFT spectral data, N BF To weight the window factor, the Hanning window is 1.5.
In this application embodiment, gather vibration data, can real-time supervision corrugated paper machine's running state, reduce the fluctuation of speed and vibration, improved the quality of paper, reduced the circumstances of paper damage.
In step S102, the production management system parameter data is read;
specifically, the step of reading production management system parameter data includes:
reading a text file stored in a corrugated paper machine production management system;
and acquiring target data corresponding to the corrugated medium from a text file stored in the production management system, wherein the target data comprises material data, breadth data, stupefied data and vehicle speed data.
In the embodiment of the application, the parameter data of the production management system is read, so that the production state of a paper mill can be monitored in real time, the prediction of the suggested speed of the corrugated paper machine is facilitated, and various abnormal production conditions can be timely processed;
in step S103, vibration data and parameter data are processed and analyzed;
specifically, the vibration data and the parameter data are processed and analyzed, and the steps include:
acquiring speed data, material data and breadth data at regular time according to time sequence;
selecting data with a speed greater than 50, selecting data with a material not empty and selecting data with a width greater than 0, and carrying out data numeralization on the material data and the stupefied data;
and fixing materials, ridges and widths, and visualizing vehicle speed data and vibration data according to time sequence.
In the embodiment of the application, the statistical characteristics in the historical production data can be calculated rapidly, and the training accuracy of the suggested speed algorithm of the corrugating machine is improved.
In step S104, based on the feature engineering, clustering the vibration data and the parameter data by using a clustering algorithm to obtain feature training data;
specifically, based on feature engineering, the vibration data and the parameter data are clustered by using a clustering algorithm, and the steps comprise:
fixing materials, edges, widths and vehicle speeds, and calculating the average value of vibration data;
fixing materials, ridges and widths, and counting the occurrence frequency of the vehicle speed;
and the vehicle speed data with the top 12 rank is screened according to the vehicle speed frequency.
Preferably, the steps further include, after the vehicle speed data of the top 12 of the screening frequency rank are sequentially arranged according to the vehicle speed frequency:
according to the calculated average value of the vibration data of each vehicle speed, vehicle speeds smaller than the vibration average value in the 12 vehicle speeds are screened out;
using a Kmeans clustering algorithm to gather the vehicle speeds smaller than the vibration mean value into two types of vehicle speeds;
and selecting the maximum value and the minimum value of the two types of vehicle speeds to form a first vehicle speed range and a second vehicle speed range.
Preferably, after selecting the maximum value and the minimum value of the two types of vehicle speeds to form the first vehicle speed range and the second vehicle speed range, the steps further include:
judging whether the current vehicle speed is an upward vehicle speed range or a downward vehicle speed range according to the first vehicle speed range and the second vehicle speed range;
when the current vehicle speed is in the uplink vehicle speed range, the label of the uplink vehicle speed takes the average value of the uplink vehicle speed range;
and when the current vehicle speed is in the downlink vehicle speed range, taking down the average value of the downlink vehicle speed range by the label of the downlink vehicle speed.
In the embodiment of the application, the vehicle speed smaller than the vibration mean value can be screened out by using a reasonable method, the vehicle speed greater than the vibration mean value is avoided, paper wrinkling or breakage is avoided, the optimal recommended vehicle speed can be quickly found by using a clustering algorithm, a circulating traversing method is avoided, and the running speed of a program is improved.
In step S105, the feature training data is trained using a machine learning algorithm to predict the speed of the corrugator machine.
Specifically, the feature training data is trained using a machine learning algorithm to predict a corrugator speed, the steps comprising:
the feature training data are divided into uplink vehicle speed training data and downlink vehicle speed training data according to the uplink vehicle speed labels and the downlink vehicle speed labels, the uplink vehicle speed training data and the downlink vehicle speed training data are respectively divided into 10 parts, the divided training data account for 8 parts, and the verification data account for 2 parts.
Specifically, after dividing the uplink vehicle speed training data and the downlink vehicle speed training data, the steps further include:
training the divided uplink vehicle speed training data and the divided downlink vehicle speed training data by using an Lgb gradient lifting tree algorithm;
and verifying the predicted uplink vehicle speed and the predicted downlink vehicle speed by using the verification data.
In the embodiment of the application, the data trained by the corrugator recommended speed algorithm model is conveniently predicted, and the recommended speed prediction model can be trained.
Embodiment two:
vibration data was collected using MCM 100:
the acquisition of vibration data is very important for the speed control of the corrugating machine, and excessive vibration can cause the corrugated paper to be damaged or wrinkled, so that the vibration data is very necessary to be controlled below the vibration mean value. The main considered positions of vibration data acquisition are a driving side and an operating side of a corrugating machine, equipment used for acquiring the vibration data is MCM100, the MCM100 is a mechanical equipment state monitoring edge computing platform, four channels for receiving signals are arranged, an interface end of a vibration sensor is connected to one channel for receiving signals in the MCM100, a sensing end is arranged on the driving side of the corrugating machine, time domain data is acquired by using the vibration sensor, then the time domain data is converted into FFT (fast Fourier transform) spectrum data through Fourier transform, an OA Value (Overall Value) is calculated through the FFT spectrum data, the OA Value is a total energy expression method, the unit is g, the vibration can be evaluated according to the OA Value, and the calculation formula is as follows:
OA: full bandwidth or OA value of a certain frequency band.
n: the number of the frequency spectrum analysis strips; refers to full bandwidth or within a frequency band.
A i : amplitude values on the spectrum analysis line, i.e., FFT spectrum data.
N BF : the weighted window factor, hanning window, is 1.5.
Reading production management system data using software:
the parameter data acquisition method of the corrugated paper machine comprises the following steps: and reading a text file stored in a production management system in an industrial personal computer of a paper mill by using software written in a C# programming language, acquiring data such as the material and the width of corrugated medium paper, the flute shape and the running speed (vehicle speed) of the corrugated machine and the like, and storing the data in an Sql Server database. Different materials and widths can be used for the corrugated board, and the corresponding optimal running speeds are different.
Data were processed and analyzed using the Python program:
step one, connecting the data collected every day through a time field, and sequencing according to a time sequence.
Step two, data screening: selecting data with a vehicle speed greater than 50 (the data with a vehicle speed less than 50 is in an acceleration stage and should not be used as training data of an algorithm, and the vehicle speed range is 0-173), selecting data with a non-empty material (the material is empty when the vehicle is not produced), and selecting data with a width greater than 0 (the width is 0 when the vehicle is not produced).
And thirdly, digitizing two types of data, namely the material and the ridge, so that the algorithm is trained, and only the digitized data can be identified by the algorithm.
And fourthly, fixing materials, ridges and widths, visualizing the speed and vibration according to time, and analyzing the relation between the speed and vibration so as to optimize the statistical characteristics.
Statistical features were calculated using the python program and the data was clustered using a clustering algorithm:
firstly, calculating the vibration mean value of each vehicle speed, wherein the calculation method comprises the following steps: firstly, fixing materials, ribs, breadth and vehicle speed, and under the condition, obtaining an average value of vibration data to be used as the vibration average value under the condition.
Step two, counting the occurrence frequency of each vehicle speed, wherein the counting method comprises the following steps: the vibration data is not considered temporarily when the materials, the ridges and the widths are fixed, one line is added once at a certain speed, and the like.
And thirdly, arranging according to the vehicle speed frequency from large to small, screening the vehicle speed data with the frequency of 12 ranked before, and if the screening rank is smaller than the first 12, losing the characteristic data under partial conditions.
And step four, screening out the vehicle speeds smaller than the vibration mean value from the 12 vehicle speeds according to the vibration mean value of each vehicle speed calculated in the step one, wherein the vehicle speed larger than the vibration mean value possibly causes damage of the corrugating machine, and the vehicle speed excludes the prediction range of the recommended vehicle speed.
And fifthly, using a Kmeans clustering algorithm to gather the vehicle speeds smaller than the vibration mean value into two types, and selecting a first vehicle speed range and a second vehicle speed range of the maximum value and the minimum value of the two types of vehicle speeds.
Step six, judging whether the current vehicle speed is an upward vehicle speed range or a downward vehicle speed range according to the first vehicle speed range and the second vehicle speed range;
and step seven, when the current vehicle speed is in the upper vehicle speed range, the label of the upper vehicle speed takes the average value of the upper vehicle speed range, and when the current vehicle speed is in the lower vehicle speed range, the label of the lower vehicle speed takes the average value of the lower vehicle speed range.
Step eight, the generated data has seven characteristics including date, material, edge, breadth, OA value of a driving side, vibration mean value and vehicle speed, two labels of suggested uplink vehicle speed and suggested downlink vehicle speed, the seven characteristic data and the two label data are collectively called characteristic training data, and example data are shown in the following table:
training a machine learning algorithm:
step one, dividing the characteristic training data into uplink vehicle speed training data and downlink vehicle speed training data according to two labels, wherein one part is the uplink vehicle speed training data consisting of seven characteristics and uplink vehicle speed, the other part is the downlink vehicle speed training data consisting of seven characteristics and downlink vehicle speed, the uplink vehicle speed training data and the downlink vehicle speed training data are respectively divided into 10 parts, the divided training data account for 8 parts, and the verification data account for 2 parts.
And secondly, training the divided uplink speed training data and the divided downlink speed training data by using an Lgb gradient lifting tree algorithm, and finely adjusting algorithm parameters to adapt to the two divided training data.
Step three, verifying the predicted uplink speed and downlink speed results by using verification data, wherein a mean-square error (MSE) is used as a standard for evaluating the accuracy of an algorithm, the MSE is a measure for reflecting the degree of difference between the predicted result and the real result, the smaller the MSE is, the higher the accuracy of the algorithm is, and when the MSE is not reduced any more, the algorithm training is stopped; algorithm training continues while the mean square error is still decreasing.
And (3) storing the trained model:
and storing the trained model into an h5 file, so that the prediction, packaging and deployment are convenient.
Packaging the model into a service: packaging the components into Web API service for calling by a proportional valve control system.
And packaging the model into Web services by using a flash framework of Python for other application programs to call.
The speed of the corrugating machine is controlled by the proportional valve: the proportional valve sends a request to the message queue through the MQTT protocol, the proportional valve control system obtains the request from the message queue through the MQTT protocol, calls the Web API service packed by Python, obtains the suggested uplink and downlink vehicle speed, puts the data into the message queue, and calls the proportional valve to control the vehicle speed of the corrugating machine.
Those of ordinary skill in the art will appreciate that the elements and algorithm steps of the embodiments described in connection with the embodiments disclosed herein can be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution.
Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention. The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily appreciate variations or alternatives within the scope of the present invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (5)
1. The intelligent speed prediction method for the corrugated paper machine is characterized by comprising the following steps of:
step one: collecting vibration data by using MCM100 equipment; accessing a vibration sensor to acquire time domain data by using the MCM 100; converting the time domain data into FFT spectrum data through Fourier transform;
step two: reading parameter data of a production management system; the parameter data comprise material data, breadth data, stupefied data and vehicle speed data;
step three: processing and analyzing the vibration data and the parameter data; acquiring speed data, material data and breadth data at regular time according to time sequence; selecting data with the speed greater than 50, selecting data with non-empty materials and selecting data with the width greater than 0, carrying out data numerical treatment on the material data and the edge data, fixing the materials, the edges and the width, visualizing the speed data and the vibration data according to time sequence, arranging the speed data in sequence according to the speed frequency, and screening the speed data with the frequency ranking of 12, wherein the method further comprises the following steps:
according to the calculated average value of the vibration data of each vehicle speed, vehicle speeds smaller than the vibration average value in the 12 vehicle speeds are screened out;
using a Kmeans clustering algorithm to gather the vehicle speeds smaller than the vibration mean value into two types of vehicle speeds;
selecting the maximum value and the minimum value of the two types of vehicle speeds to form a first vehicle speed range and a second vehicle speed range;
judging whether the current vehicle speed is an upward vehicle speed range or a downward vehicle speed range according to the first vehicle speed range and the second vehicle speed range;
when the current vehicle speed is in the uplink vehicle speed range, the label of the uplink vehicle speed takes the average value of the uplink vehicle speed range;
when the current vehicle speed is in the downlink vehicle speed range, the label of the downlink vehicle speed takes off the average value of the downlink vehicle speed range;
step four: based on the feature engineering, clustering the vibration data and the parameter data by using a clustering algorithm to obtain feature training data; fixing materials, edges, widths and vehicle speeds, and calculating the average value of vibration data; fixing materials, ridges and widths, and counting the occurrence frequency of the vehicle speed; sequentially arranging according to the vehicle speed frequency, and screening vehicle speed data with the frequency ranking of top 12;
step five: the feature training data is trained using a machine learning algorithm to predict the speed of the corrugating machine.
2. The intelligent speed prediction method for corrugated paper machine according to claim 1, wherein the MCM100 device is used to collect vibration data, and the steps include:
the OA values are calculated from the FFT spectral data.
3. The intelligent speed prediction method for corrugated paper machine according to claim 2, wherein the OA value is calculated from the FFT spectral data, the steps comprising:
by calculation of
Evaluating the vibration acceleration of the corrugated paper machine conveyor belt;
wherein OA is the OA value of the full bandwidth or a certain frequency band, n is the number of spectrum analysis strips in the full bandwidth or the frequency band, A i For amplitude values on the spectrum analysis line, i.e. FFT spectral data, N BF To weight the window factor, the Hanning window is 1.5.
4. The method of claim 1, wherein the feature training data is trained using a machine learning algorithm to predict the speed of the corrugator machine, the steps comprising:
the feature training data are divided into uplink vehicle speed training data and downlink vehicle speed training data according to the uplink vehicle speed labels and the downlink vehicle speed labels, the uplink vehicle speed training data and the downlink vehicle speed training data are respectively divided into 10 parts, the divided training data account for 8 parts, and the verification data account for 2 parts.
5. The intelligent speed prediction method for corrugated paper machine according to claim 4, wherein after dividing into uplink speed training data and downlink speed training data, the steps further comprise:
training the divided uplink vehicle speed training data and the divided downlink vehicle speed training data by using an Lgb gradient lifting tree algorithm;
and verifying the predicted uplink vehicle speed and the predicted downlink vehicle speed by using the verification data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110162647.4A CN112801392B (en) | 2021-02-05 | 2021-02-05 | Intelligent speed prediction method for corrugated paper machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110162647.4A CN112801392B (en) | 2021-02-05 | 2021-02-05 | Intelligent speed prediction method for corrugated paper machine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112801392A CN112801392A (en) | 2021-05-14 |
| CN112801392B true CN112801392B (en) | 2023-07-04 |
Family
ID=75814445
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110162647.4A Active CN112801392B (en) | 2021-02-05 | 2021-02-05 | Intelligent speed prediction method for corrugated paper machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112801392B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117521423B (en) * | 2024-01-05 | 2024-04-05 | 山东鑫林纸制品有限公司 | Intelligent prediction method and device for machine speed of corrugated paper processing and storage medium |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6087796A (en) * | 1998-06-16 | 2000-07-11 | Csi Technology, Inc. | Method and apparatus for determining electric motor speed using vibration and flux |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP6959278B2 (en) * | 2019-02-27 | 2021-11-02 | ファナック株式会社 | Chatter vibration judgment device, machine learning device and system |
-
2021
- 2021-02-05 CN CN202110162647.4A patent/CN112801392B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6087796A (en) * | 1998-06-16 | 2000-07-11 | Csi Technology, Inc. | Method and apparatus for determining electric motor speed using vibration and flux |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112801392A (en) | 2021-05-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109102189B (en) | Electrical equipment health management system and method | |
| CN108446864B (en) | Big data analysis-based fault early warning system and method for rail transit equipment | |
| CN116304766B (en) | Multi-sensor-based quick assessment method for state of switch cabinet | |
| CN112801392B (en) | Intelligent speed prediction method for corrugated paper machine | |
| CN110594107A (en) | Wind turbine generator fault detection method and device based on rapid gradient elevator | |
| CN110992209A (en) | Flow prediction method | |
| CN115309217A (en) | Intelligent monitoring control method and system for textile workshop | |
| CN107527121A (en) | A kind of method of the information system running status diagnosis prediction of power network | |
| CN109002026B (en) | Hydroelectric generating set full-condition comprehensive parameter degradation trend analysis method | |
| CN115426243A (en) | Network equipment fault maintenance method based on big data | |
| CN116028887B (en) | Analysis method of continuous industrial production data | |
| CN113567162A (en) | Fan fault intelligent diagnosis device and method based on acoustic sensor | |
| CN113139880A (en) | Wind turbine generator actual power curve fitting method, device, equipment and storage medium | |
| CN117111551A (en) | AMES system-based medicine production quality monitoring method and system | |
| CN109598309B (en) | Detection system and monitoring method of metal packaging punching machine | |
| CN116771601A (en) | Temperature sensing-based wind turbine generator set optimal control method and system | |
| CN107121493A (en) | A kind of equipment damage detection method and system | |
| CN114662058B (en) | Wireless station monitoring method and device | |
| CN116502043A (en) | Finish rolling motor state analysis method based on isolated forest algorithm | |
| CN115345430A (en) | Health degree evaluation method and system of chip mounter | |
| CN115797355A (en) | Fault detection method and system for solar photovoltaic power generation device | |
| CN113847232B (en) | Air compressor cluster operation adjusting method and system based on cloud edge cooperation | |
| CN115660288A (en) | Analysis management system based on internet big data | |
| CN114726088A (en) | Fault recording system for photovoltaic system and configuration self-adaption method | |
| CN115766376A (en) | Data analysis processing method based on data analysis of Internet of things equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |