CN117886147A - Paper conveying deviation correcting system and deviation correcting method thereof - Google Patents
Paper conveying deviation correcting system and deviation correcting method thereof Download PDFInfo
- Publication number
- CN117886147A CN117886147A CN202410081072.7A CN202410081072A CN117886147A CN 117886147 A CN117886147 A CN 117886147A CN 202410081072 A CN202410081072 A CN 202410081072A CN 117886147 A CN117886147 A CN 117886147A
- Authority
- CN
- China
- Prior art keywords
- paper
- unit
- deviation
- data
- speed
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 22
- 238000012423 maintenance Methods 0.000 claims abstract description 56
- 238000012545 processing Methods 0.000 claims abstract description 17
- 238000012937 correction Methods 0.000 claims abstract description 15
- 230000003044 adaptive effect Effects 0.000 claims abstract description 9
- 238000010801 machine learning Methods 0.000 claims description 34
- 238000004422 calculation algorithm Methods 0.000 claims description 27
- 230000007246 mechanism Effects 0.000 claims description 25
- 238000004458 analytical method Methods 0.000 claims description 20
- 230000010354 integration Effects 0.000 claims description 18
- 230000006870 function Effects 0.000 claims description 13
- 238000012544 monitoring process Methods 0.000 claims description 12
- 238000005457 optimization Methods 0.000 claims description 12
- 230000009471 action Effects 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 11
- 230000004044 response Effects 0.000 claims description 11
- 238000013480 data collection Methods 0.000 claims description 10
- 238000013135 deep learning Methods 0.000 claims description 10
- 230000004927 fusion Effects 0.000 claims description 9
- 238000010191 image analysis Methods 0.000 claims description 9
- 238000013527 convolutional neural network Methods 0.000 claims description 8
- 230000008859 change Effects 0.000 claims description 7
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 238000003066 decision tree Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000012706 support-vector machine Methods 0.000 claims description 6
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- 230000003247 decreasing effect Effects 0.000 claims description 3
- 230000000694 effects Effects 0.000 claims description 3
- 238000003709 image segmentation Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 238000007637 random forest analysis Methods 0.000 claims description 3
- 230000004913 activation Effects 0.000 claims description 2
- 238000001514 detection method Methods 0.000 claims description 2
- 230000000007 visual effect Effects 0.000 claims description 2
- 238000004519 manufacturing process Methods 0.000 abstract description 8
- 238000010586 diagram Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 239000000047 product Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000012467 final product Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000009022 nonlinear effect Effects 0.000 description 1
- 230000003449 preventive effect Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
- 230000037303 wrinkles Effects 0.000 description 1
Landscapes
- Controlling Sheets Or Webs (AREA)
Abstract
The invention relates to the technical field of paper processing, in particular to a paper conveying deviation correcting system and a deviation correcting method thereof, wherein the deviation correcting system comprises a sensor array module, a self-adaptive actuator, a machine vision module, a deviation correcting control module, a predictive maintenance module and a user interface module; wherein the sensor array module: the paper feeding device comprises a plurality of sensors which are respectively distributed on a conveying belt and used for capturing position, speed, offset, thickness and texture information of paper; an adaptive actuator: according to the paper state data provided by the sensor, the conveying direction and speed of the paper are dynamically adjusted so as to realize accurate deviation correction. According to the invention, by realizing automatic and intelligent deviation correction control, the accuracy and efficiency of paper processing are obviously improved, and meanwhile, the adaptability, reliability and general applicability of the system are enhanced, so that the production quality is improved, and meanwhile, the running cost and maintenance requirements are reduced.
Description
Technical Field
The invention relates to the technical field of paper processing, in particular to a paper conveying deviation correcting system and a deviation correcting method thereof.
Background
In modern printing and paper processing industries, the efficiency and accuracy of paper conveying systems are critical to the overall production process, and paper often suffers from problems such as offset, distortion or speed inconsistencies during the conveying process, which affect the print quality, processing efficiency, and quality of the final product, thus ensuring that the paper remains in the correct path and speed throughout the conveying process is critical to improving production efficiency and ensuring product quality.
Conventional paper transport systems rely on simple mechanical adjustments or manual intervention by operators to rectify the deviation, which is inefficient and of limited accuracy, especially in high-speed printing and mass production environments, where manual intervention is often difficult to meet production requirements, and where existing systems often perform poorly when dealing with minor deviations in paper, variations in paper properties (such as thickness and texture differences), or complex rectification scenarios.
Therefore, there is an urgent need to develop a method capable of automatically and intelligently correcting deviation of paper transportation so as to improve production efficiency and product quality.
Disclosure of Invention
Based on the above purpose, the invention provides a paper conveying deviation correcting system and a deviation correcting method thereof.
The paper conveying deviation correcting system comprises a sensor array module, a self-adaptive actuator, a machine vision module, a deviation correcting control module, a predictive maintenance module and a user interface module; wherein,
sensor array module: the device comprises a plurality of sensors which are respectively distributed on a conveyor belt and used for capturing position, speed, offset, thickness and texture information of paper and converting the captured paper state information into digital signals;
an adaptive actuator: the paper conveying device is directly connected with the sensor array module, and dynamically adjusts the conveying direction and speed of paper according to the paper state data provided by the sensor so as to realize accurate deviation correction;
machine vision module: receiving data from the sensor array module, capturing a paper image through a camera, analyzing the edge and surface characteristics of the paper by using a convolutional neural network model, and sending an image analysis result to the deviation rectification control module;
and the deviation rectifying control module is used for: optimizing a deviation rectifying strategy by using a machine learning algorithm based on data from the sensor array module and the machine vision module, and sending an accurate deviation rectifying instruction to the self-adaptive actuator based on the optimized strategy;
predictive maintenance module: predicting maintenance requirements of the system by a machine learning algorithm using the operational data collected from the sensor array module and the deskew control module;
a user interface module: an intuitive user interface is provided that allows an operator to monitor system status, adjust parameters, and manually intervene when needed.
Further, the sensor array module comprises a photoelectric sensor, an ultrasonic sensor, an infrared sensor, a touch sensor and a data conversion unit; wherein,
the photoelectric sensor is arranged at the inlet and outlet positions of the conveying belt and used for detecting the entering and leaving moments of paper so as to calculate the running speed of the paper, and the photoelectric sensor determines the speed of the paper by measuring the time interval that light is blocked by the paper;
the ultrasonic sensors are uniformly distributed on two sides of the conveyor belt and are used for measuring the distance between the edge of the paper and the edge of the conveyor belt so as to determine the position and the transverse offset of the paper;
the infrared sensor is positioned below the conveying belt and is used for measuring the thickness of the paper, and the infrared sensor is used for determining the thickness of the paper by emitting infrared rays and detecting the intensity change of the reflected rays;
a tactile sensor arranged on the surface of the conveyor belt for detecting the texture of the sheet, the tactile sensor being to acquire texture information of the sheet by contacting the surface of the sheet and analyzing the pressure pattern;
a data conversion unit: the sensor is connected with all the sensors and is responsible for converting analog signals captured by the sensors into digital signals, and the sensor comprises an analog-digital converter and a signal processing chip which are used for processing and standardizing sensor data.
Further, the adaptive actuator comprises an actuator control unit, a servo motor group, a position adjusting mechanism, a speed adjusting mechanism and a feedback loop; wherein,
an actuator control unit: receiving digital signals from the sensor array module, the actuator control unit comprising a microprocessor and associated software algorithms, the microprocessor to parse the sensor data according to the algorithms to determine the current position, speed, offset and thickness of the paper;
servo motor unit: the paper feeding device comprises a plurality of precise servo motors which are distributed at key positions of a conveying belt, wherein the motors adjust the position and the conveying speed of paper according to instructions of an actuator control unit, so that the paper is ensured to accurately move along a preset path;
position adjustment mechanism: the position adjusting mechanism corrects the lateral deviation of the paper by fine-adjusting the position of the guide rail or the conveying roller according to the instruction of the actuator control unit;
speed adjusting mechanism: the speed adjusting mechanism is used for adjusting the conveying speed of the paper in cooperation with the servo motor group, and the speed adjusting mechanism is used for adapting to the real-time speed requirement of the paper by increasing or decreasing the rotating speed of the motor;
feedback loop: the actual operation of the actuator is fed back to the actuator control unit to ensure the accuracy of adjustment, and the feedback loop monitors and reports the actual actions of the servo motor and the position adjusting mechanism, so that the control unit can adjust the instructions in real time to achieve the optimal deviation correcting effect.
Further, the related software algorithm in the actuator control unit is specifically a PID control algorithm, which is used for calculating a control deviation,i.e. the difference between the desired paper position or velocity and the actual value, and adjusts the actuator response based on this difference, the specific formula is: where u (t) is the controller output, i.e. the control command to the actuator, e (t) is the control deviation, i.e. the difference between the setpoint and the process variable, K p 、K i And K d Proportional, integral and differential gains, respectively +.>Represents the integral of the deviation over time, for eliminating steady state errors,the change rate of the deviation is expressed and used for predicting future deviation and making corresponding adjustment.
Further, the machine vision module comprises a high-resolution camera unit, an image preprocessing unit, a deep learning analysis unit and a result output unit; wherein,
high resolution camera unit: for capturing successive images of a sheet moving along a conveyor belt, the camera unit being arranged at a position above the conveyor belt capable of capturing a full view of the sheet, including edge and surface details;
an image preprocessing unit: receiving original image data captured by a camera, and performing preliminary processing including denoising, contrast adjustment and image segmentation to ensure the quality of the image data;
deep learning analysis unit: analyzing the preprocessed image by using a convolutional neural network model for accurately identifying the edge, detection deviation and surface characteristics of the paper, wherein the convolutional neural network model is specifically expressed as: f (F) l (x)＝σ(W l *F l-1 (x)+B l ) Wherein F is l (x) Output feature map, sigma, representing the convolution layer of layer INonlinear activation function for adding nonlinear characteristics of model, W l Is the convolution kernel weight of the first layer for extracting the specific features of the paper image, which represents the convolution operation, F l-1 (x) Is the output of layer 1, or the input image in the first layer, B l Is a bias term of the first layer, and is used for adjusting the output of the convolution layer;
a result output unit: and converting the image characteristics and the paper state data processed by the deep learning analysis unit into a specific format suitable for the deviation rectifying control module, wherein the specific format is JSON or XML.
Further, the deviation rectifying control module comprises a data fusion unit, a machine learning optimization unit, a deviation rectifying decision unit and an executor instruction generation unit; wherein,
and a data fusion unit: the data fusion unit is used for combining the edge positioning data and the surface characteristic data of the sensor with the image analysis result of the machine vision module to provide a comprehensive data view for the deviation rectifying strategy;
machine learning optimization unit: optimizing a deviation rectifying strategy by using a machine learning algorithm based on a support vector machine, wherein the specific optimization formula of the support vector machine is as follows:wherein f (x) represents a decision function for determining a specific action of paper deviation correction, alpha i Is a coefficient of a support vector, y i Is a label of training data points, representing the ideal state of the paper, K (x i X) is a kernel function for mapping data to a high-dimensional space, b is a bias term, and the position of the decision hyperplane is adjusted;
deviation correcting decision unit: determining a specific deviation rectifying strategy according to the output of the machine learning optimization unit, wherein the specific deviation rectifying strategy comprises the deviation rectifying direction, the deviation rectifying amplitude and the deviation rectifying execution time;
an actuator instruction generation unit: and generating a specific execution instruction according to the strategy determined by the deviation rectifying decision unit, and sending the generated instruction to the adaptive executor so as to implement deviation rectifying operation.
Further, the predictive maintenance module comprises a data integration unit, a machine learning analysis unit, a maintenance decision unit and a report notification unit; wherein,
a data integration unit: the system comprises a sensor array module, a deviation correction control module, an actuator response time and frequency, a data collection and integration unit and a data collection and integration unit, wherein the sensor array module and the deviation correction control module are used for collecting operation data including paper conveying speed, position deviation, actuator response time and frequency, and the data collection and integration unit can also record historical maintenance records and any abnormal events of the system;
machine learning analysis unit: analyzing the collected data by using a random forest-based machine learning algorithm, predicting the maintenance requirement of the system, wherein a specific algorithm formula is expressed as follows:
wherein Y is the prediction output, representing the estimation of the system maintenance requirement, B is the number of decision trees, determining the complexity and prediction accuracy of the model, f b Is a predictive function of the b-th decision tree, each based on the input feature X 1 ,X 2 ,…,X n Independent prediction, X 1 ,X 2 ,…,X n Input features acquired from the data collection and integration unit, including paper conveying speed, position deviation and actuator response;
maintenance decision unit: determining a specific maintenance plan and a specific schedule according to the prediction result of the machine learning analysis unit;
report notification unit: report of prediction results and maintenance suggestions is provided for operators and maintenance teams, ensuring timely maintenance decisions and implementation.
Further, the user interface module comprises a real-time data display unit, a state monitoring unit, an operation control unit and an alarm notification unit; wherein,
real-time data display unit: the real-time data display unit is responsible for displaying key data in the paper conveying process to an operator, wherein the specific key data comprise the speed, the position, the angle and any deviation condition of the paper, and the real-time data display unit intuitively displays the data in the form of figures and numbers;
system state monitoring unit: the system is characterized by providing real-time monitoring of the overall performance of the system, comprising the working state of an actuator, the reading accuracy of a sensor and the early warning of a predictive maintenance module, wherein the monitored information is displayed in the form of an instrument panel or a control panel, so that an operator can clearly know the running condition of the system;
an operation control unit: allowing an operator to manually adjust key parameters of the paper feed deviation correcting system, including adjusting the speed of the conveyor belt, changing the deviation correcting strategy, or manually triggering specific maintenance operations;
an alarm notification unit: when the system detects an anomaly or is about to reach a critical maintenance point, an alert and notification will be sent to the operator, the alert being provided in a visual and audible manner.
The paper conveying deviation correcting method comprises the following steps:
s1: setting basic parameters of the paper conveying system, including conveying belt speed, paper type and expected conveying path;
s2: continuously monitoring the speed, position and offset of the paper, and thickness and texture information of the paper;
s3: capturing an image of the paper on the conveyor belt and analyzing the edge and surface features of the paper to determine the exact position and state of the paper;
s4: according to the monitored paper state and the image analysis result, optimizing a deviation correcting strategy by using a machine learning algorithm, and ensuring that paper is accurately conveyed according to a preset path;
s5: according to the optimized deviation correcting strategy, the position and speed of the paper are adjusted, so that the paper returns to a preset conveying path;
s6: analyzing system operation data, predicting future maintenance requirements, including component replacement or system adjustments;
s7: real-time data of system status and corrective action is displayed, providing manual control options for operator intervention as needed.
The invention has the beneficial effects that:
according to the invention, the position, speed and state of the paper are monitored in real time, and advanced image processing and machine learning technologies are combined, so that the system can automatically and accurately adjust the path and speed of the paper, and the automatic and intelligent deviation correcting mechanism not only reduces the need of human intervention, but also reduces the production defects and waste caused by paper deviation.
The invention greatly improves the adaptability and the reliability of the system through the application of the predictive maintenance module, and the system can analyze the operation data and predict the potential maintenance requirement, thereby carrying out preventive maintenance before the occurrence of problems and reducing the unexpected downtime.
The present invention is not only suitable for different types and sizes of paper, but also can adapt to various production conditions, and the system can provide stable and efficient deviation correcting performance both in a high-speed printing environment and in complex paper processing application, and the flexibility and general applicability make the method of the present invention an ideal choice for various paper processing and printing applications.
Drawings
In order to more clearly illustrate the invention or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only of the invention and that other drawings can be obtained from them without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of a paper conveying deviation correcting system according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of a paper conveying deviation rectifying method according to an embodiment of the invention.
Detailed Description
The present invention will be further described in detail with reference to specific embodiments in order to make the objects, technical solutions and advantages of the present invention more apparent.
It is to be noted that unless otherwise defined, technical or scientific terms used herein should be taken in a general sense as understood by one of ordinary skill in the art to which the present invention belongs. The terms "first," "second," and the like, as used herein, do not denote any order, quantity, or importance, but rather are used to distinguish one element from another. The word "comprising" or "comprises", and the like, means that elements or items preceding the word are included in the element or item listed after the word and equivalents thereof, but does not exclude other elements or items. The terms "connected" or "connected," and the like, are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "upper", "lower", "left", "right", etc. are used merely to indicate relative positional relationships, which may also be changed when the absolute position of the object to be described is changed.
As shown in fig. 1, the paper conveying deviation correcting system comprises a sensor array module, a self-adaptive actuator, a machine vision module, a deviation correcting control module, a predictive maintenance module and a user interface module; wherein,
sensor array module: the system comprises a plurality of sensors which are respectively distributed on a conveyor belt and used for capturing position, speed, offset, thickness and texture information of paper and converting the captured paper state information into digital signals for other modules to use;
an adaptive actuator: the paper feeding device is directly connected with the sensor array module, and dynamically adjusts the conveying direction and speed of paper according to paper state data (position, speed, offset and the like) provided by the sensor so as to realize accurate deviation correction;
machine vision module: receiving data from the sensor array module, capturing a paper image through a camera, analyzing the edge and surface characteristics of the paper by using a convolutional neural network model, and sending an image analysis result to a deviation rectification control module so as to assist in formulating a more accurate deviation rectification strategy;
and the deviation rectifying control module is used for: optimizing a deviation rectifying strategy by using a machine learning algorithm based on data from the sensor array module and the machine vision module, and sending an accurate deviation rectifying instruction to the self-adaptive actuator based on the optimized strategy;
predictive maintenance module: by utilizing the operation data collected from the sensor array module and the deviation correction control module, predicting the maintenance requirement of the system through a machine learning algorithm, reducing unexpected downtime and ensuring the long-term stable operation of the system;
a user interface module: an intuitive user interface is provided that allows an operator to monitor system status, adjust parameters, and manually intervene when needed.
The sensor array module comprises a photoelectric sensor, an ultrasonic sensor, an infrared sensor, a touch sensor and a data conversion unit; wherein,
the photoelectric sensor is arranged at the inlet and outlet positions of the conveyor belt and is used for detecting the entering and leaving moments of paper so as to calculate the running speed of the paper, and the photoelectric sensor determines the speed of the paper by measuring the time interval when light is blocked by the paper;
the ultrasonic sensors are uniformly distributed on two sides of the conveyor belt and are used for measuring the distance between the edge of the paper and the edge of the conveyor belt so as to determine the position and the transverse offset of the paper;
the infrared sensor is positioned below the conveying belt and is used for measuring the thickness of the paper, and the infrared sensor is used for determining the thickness of the paper by emitting infrared rays and detecting the intensity change of the reflected rays;
a tactile sensor arranged on the surface of the conveyor belt for detecting the texture of the sheet, the tactile sensor being to acquire texture information of the sheet by contacting the surface of the sheet and analyzing the pressure pattern;
a data conversion unit: the sensor is connected with all sensors and is responsible for converting analog signals captured by the sensors into digital signals, and the sensor comprises an analog-digital converter (ADC) and a signal processing chip which are used for processing and standardizing sensor data and ensuring the accuracy and consistency of the data.
The self-adaptive actuator comprises an actuator control unit, a servo motor unit, a position adjusting mechanism, a speed adjusting mechanism and a feedback loop; wherein,
an actuator control unit: receiving digital signals from the sensor array module, the actuator control unit comprising a microprocessor and associated software algorithms, the microprocessor will parse the sensor data according to the algorithms to determine the current position, speed, offset and thickness of the paper;
servo motor unit: the paper feeding device comprises a plurality of precise servo motors which are distributed at key positions of a conveying belt, wherein the motors adjust the position and the conveying speed of paper according to instructions of an actuator control unit, so that the paper is ensured to accurately move along a preset path;
position adjustment mechanism: the position adjusting mechanism corrects the lateral deviation of the paper by fine-adjusting the position of the guide rail or the conveying roller according to the instruction of the actuator control unit;
speed adjusting mechanism: the speed adjusting mechanism is used for adjusting the conveying speed of the paper in cooperation with the servo motor group, and the speed adjusting mechanism is used for adapting to the real-time speed requirement of the paper by increasing or decreasing the rotating speed of the motor so as to ensure the continuity and stability of the conveying process;
feedback loop: the actual operation of the actuator is fed back to the actuator control unit to ensure the accuracy of adjustment, and the feedback loop monitors and reports the actual actions of the servo motor and the position adjusting mechanism, so that the control unit can adjust the instructions in real time to achieve the optimal deviation correcting effect.
The related software algorithm in the actuator control unit is specifically a PID control algorithm, and the PID algorithm is used for calculating a control deviation, that is, a difference between a desired paper position or speed and an actual value, and adjusting the response of the actuator according to the difference, where a specific formula is as follows:where u (t) is the controller output, i.e. the control command to the actuator, e (t) is the control deviation, i.e. the difference between the setpoint (desired value) and the process variable (actual value), K p 、K i And K d Proportional, integral and differential gains, respectively, which are adjusted according to the characteristics of the system, +.>Representing the integration of the deviation over time for eliminating steady state error,/->The change rate of the deviation is represented and used for predicting future deviation and correspondingly adjusting;
the microprocessor processes the data received from the sensor array module (e.g., actual position, speed, etc. of the paper) using a PID algorithm, the microprocessor calculates the control deviation e (t), and calculates the control output u (t) according to the PID algorithm, which is then converted into an actual action command of the actuator (e.g., servo motor), for example, adjusting the rotational speed or position of the motor, to correct the deviation or speed of the paper.
The machine vision module comprises a high-resolution camera unit, an image preprocessing unit, a deep learning analysis unit and a result output unit; wherein,
high resolution camera unit: for capturing successive images of a sheet moving along a conveyor belt, the camera unit being arranged at a position above the conveyor belt capable of capturing a full view of the sheet, including edge and surface details;
an image preprocessing unit: receiving original image data captured by a camera, and performing preliminary processing including denoising, contrast adjustment and image segmentation to ensure the quality of the image data, so as to prepare for subsequent deep learning analysis;
deep learning analysis unit: the preprocessed image is analyzed using a convolutional neural network model for accurately identifying paper edges, detecting deviations, and surface features, such as texture and color variations, which is specifically expressed as: f (F) l (x)＝σ(W l *F l-1 (x)+B l ) Wherein F is l (x) Output characteristic diagram representing a first convolution layer, sigma being nonlinearActivating functions, e.g. ReLU (RectifiedLinearUnit), for increasing the non-linear properties of the model, can help the model learn more complex features, W l Is the convolution kernel weight of the first layer for extracting specific features of the paper image, such as edges, textures, etc., representing the convolution operation, F l-1 (x) Is the output of layer 1, or the input image in the first layer, B l Is a bias term of the first layer, and is used for adjusting the output of the convolution layer;
a result output unit: and converting the image characteristics and the paper state data processed by the deep learning analysis unit into a specific format suitable for the deviation rectifying control module, wherein the specific format is JSON or XML.
The deviation rectifying control module comprises a data fusion unit, a machine learning optimization unit, a deviation rectifying decision unit and an executor instruction generation unit; wherein,
and a data fusion unit: the data fusion unit is used for combining the edge positioning data and the surface characteristic data of the sensor with the image analysis result of the machine vision module to provide a comprehensive data view for the deviation rectifying strategy;
machine learning optimization unit: the correction strategy is optimized by using a machine learning algorithm based on a support vector machine, and a specific optimization formula of the support vector machine is as follows:wherein f (x) represents a decision function for determining a specific action of correcting the paper, e.g. adjusting the position or angle of the paper, alpha i Is a coefficient of the support vector, which is determined by the training process and represents the importance of each support vector in the decision, y i Is a label of training data points, representing the ideal state of the paper (e.g., correctly aligned or offset), K (x i X) is a kernel function for mapping data into a high dimensional space to better separate different states of the paper, in a paper rectification system, this can be a Radial Basis Function (RBF) kernel or polynomial kernel to capture complex relationships of paper state data, b is a bias term to adjust decision hyperplaneA location;
deviation correcting decision unit: determining a specific deviation rectifying strategy according to the output of the machine learning optimization unit, wherein the specific deviation rectifying strategy comprises the deviation rectifying direction, the deviation rectifying amplitude and the deviation rectifying execution time; the specific decision logic of the deviation rectifying decision unit is as follows:
when the sensor data or the machine vision module indicates that the paper position deviates from the expected path, the deviation correcting decision unit calculates the required position adjustment amount, for example, if the paper deviates from the center line to the right, the instruction executor adjusts the paper to the left;
paper speed changes, such as sensor data indicating that paper is traveling faster or slower than a set speed, the decision unit adjusts the speed of the actuator to ensure that paper is traveling at a constant speed through the conveyor belt;
if the machine vision module detects that the paper has deviation (such as distortion or inclination) from the expected angle, the decision unit sends out an instruction to adjust the angle of the paper so as to return to the correct posture;
if the machine vision module recognizes abnormal features (such as wrinkles, breaks or stains) on the surface of the paper, the decision unit may decide to slow down the transport speed, perform additional checks or mark it as defective,
under the condition that a plurality of factors affect the state of paper at the same time, the decision unit performs comprehensive analysis to determine a group of deviation correcting actions, and the position, the speed and the angle are synchronously adjusted;
an actuator instruction generation unit: and generating specific execution instructions (such as adjustment angles, change speeds and the like) according to the strategy determined by the deviation rectification decision unit, and sending the generated instructions to the adaptive executor so as to implement deviation rectification operation.
The predictive maintenance module comprises a data integration unit, a machine learning analysis unit, a maintenance decision unit and a report notification unit; wherein,
a data integration unit: the data collection and integration unit is used for collecting operation data from the sensor array module and the deviation correction control module, including paper conveying speed, position deviation, actuator response time and frequency, and recording historical maintenance records of the system and any abnormal events such as paper faults or excessive adjustment of the actuator;
machine learning analysis unit: analyzing the collected data by using a random forest-based machine learning algorithm, predicting the maintenance requirement of the system, wherein a specific algorithm formula is expressed as follows:
wherein Y is a predictive output representing an estimate of system maintenance requirements, such as component replacement probability or regulatory requirements, B is the number of decision trees, determining model complexity and predictive accuracy, B can be determined based on system complexity and data diversity in a sheet delivery correction system, f b Is a predictive function of the b-th decision tree, each based on the input feature X 1 ,X 2 ,…,X n Independent prediction, X 1 ,X 2 ,…,X n Input features acquired from the data collection and integration unit, including paper conveying speed, position deviation and actuator response;
maintenance decision unit: determining a specific maintenance plan and schedule according to the prediction result of the machine learning analysis unit, for example, if the prediction shows that a certain component has a high failure probability, the component is scheduled to be replaced at the next shutdown;
report notification unit: report of prediction results and maintenance suggestions is provided for operators and maintenance teams, ensuring timely maintenance decisions and implementation.
The user interface module comprises a real-time data display unit, a state monitoring unit, an operation control unit and an alarm notification unit; wherein,
real-time data display unit: the real-time data display unit is responsible for displaying key data in the paper conveying process to an operator, wherein the specific key data comprise the speed, the position, the angle and any deviation condition of the paper, and the real-time data display unit intuitively displays the data in the form of figures and numbers so as to ensure that the operator can quickly understand the current system state;
system state monitoring unit: the system is characterized by providing real-time monitoring of the overall performance of the system, comprising the working state of an actuator, the reading accuracy of a sensor and the early warning of a predictive maintenance module, wherein the monitored information is displayed in the form of an instrument panel or a control panel, so that an operator can clearly know the running condition of the system;
an operation control unit: allowing an operator to manually adjust key parameters of the paper feed deviation correcting system, including adjusting the speed of the conveyor belt, changing the deviation correcting strategy, or manually triggering specific maintenance operations;
an alarm notification unit: when the system detects an anomaly or is about to reach a critical maintenance point, an alert and notification will be sent to the operator, the alert being provided visually and audibly to ensure that the operator can respond in time to any emergency situation of the system.
As shown in fig. 2, the paper conveying deviation rectifying method includes the following steps:
s1: setting basic parameters of the paper conveying system, including conveying belt speed, paper type and expected conveying path;
s2: continuously monitoring the speed, position and offset of the paper, and thickness and texture information of the paper;
s3: capturing an image of the paper on the conveyor belt and analyzing the edge and surface features of the paper to determine the exact position and state of the paper;
s4: according to the monitored paper state and the image analysis result, optimizing a deviation correcting strategy by using a machine learning algorithm, and ensuring that paper is accurately conveyed according to a preset path;
s5: according to the optimized deviation correcting strategy, the position and speed of the paper are adjusted, so that the paper returns to a preset conveying path;
s6: analyzing system operation data, predicting future maintenance requirements, including component replacement or system adjustments;
s7: real-time data of system status and corrective action is displayed, providing manual control options for operator intervention as needed.
The present invention is intended to embrace all such alternatives, modifications and variances which fall within the broad scope of the appended claims. Therefore, any omission, modification, equivalent replacement, improvement, etc. of the present invention should be included in the scope of the present invention.
Claims (9)
1. The paper conveying deviation correcting system is characterized by comprising a sensor array module, a self-adaptive actuator, a machine vision module, a deviation correcting control module, a predictive maintenance module and a user interface module; wherein,
sensor array module: the device comprises a plurality of sensors which are respectively distributed on a conveyor belt and used for capturing position, speed, offset, thickness and texture information of paper and converting the captured paper state information into digital signals;
an adaptive actuator: the paper conveying device is directly connected with the sensor array module, and dynamically adjusts the conveying direction and speed of paper according to the paper state data provided by the sensor so as to realize accurate deviation correction;
machine vision module: receiving data from the sensor array module, capturing a paper image through a camera, analyzing the edge and surface characteristics of the paper by using a convolutional neural network model, and sending an image analysis result to the deviation rectification control module;
and the deviation rectifying control module is used for: optimizing a deviation rectifying strategy by using a machine learning algorithm based on data from the sensor array module and the machine vision module, and sending an accurate deviation rectifying instruction to the self-adaptive actuator based on the optimized strategy;
predictive maintenance module: predicting maintenance requirements of the system by a machine learning algorithm using the operational data collected from the sensor array module and the deskew control module;
a user interface module: an intuitive user interface is provided that allows an operator to monitor system status, adjust parameters, and manually intervene when needed.
2. The paper feed deviation correcting system according to claim 1, wherein the sensor array module includes a photoelectric sensor, an ultrasonic sensor, an infrared sensor, a tactile sensor, and a data conversion unit; wherein,
the photoelectric sensor is arranged at the inlet and outlet positions of the conveying belt and used for detecting the entering and leaving moments of paper so as to calculate the running speed of the paper, and the photoelectric sensor determines the speed of the paper by measuring the time interval that light is blocked by the paper;
the ultrasonic sensors are uniformly distributed on two sides of the conveyor belt and are used for measuring the distance between the edge of the paper and the edge of the conveyor belt so as to determine the position and the transverse offset of the paper;
the infrared sensor is positioned below the conveying belt and is used for measuring the thickness of the paper, and the infrared sensor is used for determining the thickness of the paper by emitting infrared rays and detecting the intensity change of the reflected rays;
a tactile sensor arranged on the surface of the conveyor belt for detecting the texture of the sheet, the tactile sensor being to acquire texture information of the sheet by contacting the surface of the sheet and analyzing the pressure pattern;
a data conversion unit: the sensor is connected with all the sensors and is responsible for converting analog signals captured by the sensors into digital signals, and the sensor comprises an analog-digital converter and a signal processing chip which are used for processing and standardizing sensor data.
3. The paper feed deviation correcting system according to claim 2, wherein the adaptive actuator comprises an actuator control unit, a servo motor group, a position adjustment mechanism, a speed adjustment mechanism, and a feedback loop; wherein,
an actuator control unit: receiving digital signals from the sensor array module, the actuator control unit comprising a microprocessor and associated software algorithms, the microprocessor to parse the sensor data according to the algorithms to determine the current position, speed, offset and thickness of the paper;
servo motor unit: the paper feeding device comprises a plurality of precise servo motors which are distributed at key positions of a conveying belt, wherein the motors adjust the position and the conveying speed of paper according to instructions of an actuator control unit, so that the paper is ensured to accurately move along a preset path;
position adjustment mechanism: the position adjusting mechanism corrects the lateral deviation of the paper by fine-adjusting the position of the guide rail or the conveying roller according to the instruction of the actuator control unit;
speed adjusting mechanism: the speed adjusting mechanism is used for adjusting the conveying speed of the paper in cooperation with the servo motor group, and the speed adjusting mechanism is used for adapting to the real-time speed requirement of the paper by increasing or decreasing the rotating speed of the motor;
feedback loop: the actual operation of the actuator is fed back to the actuator control unit to ensure the accuracy of adjustment, and the feedback loop monitors and reports the actual actions of the servo motor and the position adjusting mechanism, so that the control unit can adjust the instructions in real time to achieve the optimal deviation correcting effect.
4. A paper feed deviation correcting system according to claim 3, wherein the relevant software algorithm in the actuator control unit is specifically a PID control algorithm, which is used to calculate a control deviation, i.e. a difference between the desired paper position or speed and the actual value, and adjust the response of the actuator according to the difference, the specific formula being:where u (t) is the controller output, i.e. the control command to the actuator, e (t) is the control deviation, i.e. the difference between the setpoint and the process variable, K p 、K i And K d Proportional, integral and differential gains, respectively +.>Representing the integration of the deviation over time for eliminating steady state error,/->Representing the rate of change of the deviation for predicting future deviations and proceedingAnd correspondingly adjusting.
5. The paper feed deviation correcting system according to claim 4, wherein the machine vision module comprises a high resolution camera unit, an image preprocessing unit, a deep learning analysis unit, and a result output unit; wherein,
high resolution camera unit: for capturing successive images of a sheet moving along a conveyor belt, the camera unit being arranged at a position above the conveyor belt capable of capturing a full view of the sheet, including edge and surface details;
an image preprocessing unit: receiving original image data captured by a camera, and performing preliminary processing including denoising, contrast adjustment and image segmentation to ensure the quality of the image data;
deep learning analysis unit: analyzing the preprocessed image by using a convolutional neural network model for accurately identifying the edge, detection deviation and surface characteristics of the paper, wherein the convolutional neural network model is specifically expressed as: f (F) l (x)＝σ(W l *F l-1 (x)+B l ) Wherein F is l (x) Output feature map representing layer I convolution layer, sigma nonlinear activation function for increasing nonlinear characteristics of model, W l Is the convolution kernel weight of the first layer for extracting the specific features of the paper image, which represents the convolution operation, F l-1 (x) Is the output of layer 1, or the input image in the first layer, B l Is a bias term of the first layer, and is used for adjusting the output of the convolution layer;
a result output unit: and converting the image characteristics and the paper state data processed by the deep learning analysis unit into a specific format suitable for the deviation rectifying control module, wherein the specific format is JSON or XML.
6. The paper feed deviation correcting system according to claim 5, wherein the deviation correcting control module comprises a data fusion unit, a machine learning optimization unit, a deviation correcting decision unit and an actuator instruction generation unit; wherein,
and a data fusion unit: the data fusion unit is used for combining the edge positioning data and the surface characteristic data of the sensor with the image analysis result of the machine vision module to provide a comprehensive data view for the deviation rectifying strategy;
machine learning optimization unit: optimizing a deviation rectifying strategy by using a machine learning algorithm based on a support vector machine, wherein the specific optimization formula of the support vector machine is as follows:wherein f (x) represents a decision function for determining a specific action of paper deviation correction, alpha i Is a coefficient of a support vector, y i Is a label of training data points, representing the ideal state of the paper, K (x i X) is a kernel function for mapping data to a high-dimensional space, b is a bias term, and the position of the decision hyperplane is adjusted;
deviation correcting decision unit: determining a specific deviation rectifying strategy according to the output of the machine learning optimization unit, wherein the specific deviation rectifying strategy comprises the deviation rectifying direction, the deviation rectifying amplitude and the deviation rectifying execution time;
an actuator instruction generation unit: and generating a specific execution instruction according to the strategy determined by the deviation rectifying decision unit, and sending the generated instruction to the adaptive executor so as to implement deviation rectifying operation.
7. The paper feed deviation correcting system according to claim 6, wherein the predictive maintenance module includes a data integration unit, a machine learning analysis unit, a maintenance decision unit, and a report notification unit; wherein,
a data integration unit: the system comprises a sensor array module, a deviation correction control module, an actuator response time and frequency, a data collection and integration unit and a data collection and integration unit, wherein the sensor array module and the deviation correction control module are used for collecting operation data including paper conveying speed, position deviation, actuator response time and frequency, and the data collection and integration unit can also record historical maintenance records and any abnormal events of the system;
machine learning analysis unit: analyzing the collected data by using a random forest-based machine learning algorithm, predicting the maintenance requirement of the system, wherein a specific algorithm formula is expressed as follows:
wherein Y is the prediction output, representing the estimation of the system maintenance requirement, B is the number of decision trees, determining the complexity and prediction accuracy of the model, f b Is a predictive function of the b-th decision tree, each based on the input feature X 1 ,X 2 ,…,X n Independent prediction, X 1 ,X 2 ,…,X n Input features acquired from the data collection and integration unit, including paper conveying speed, position deviation and actuator response;
maintenance decision unit: determining a specific maintenance plan and a specific schedule according to the prediction result of the machine learning analysis unit;
report notification unit: report of prediction results and maintenance suggestions is provided for operators and maintenance teams, ensuring timely maintenance decisions and implementation.
8. The paper feed deviation correcting system according to claim 7, wherein the user interface module includes a real-time data display unit, a status monitoring unit, an operation control unit, and an alarm notification unit; wherein,
real-time data display unit: the real-time data display unit is responsible for displaying key data in the paper conveying process to an operator, wherein the specific key data comprise the speed, the position, the angle and any deviation condition of the paper, and the real-time data display unit intuitively displays the data in the form of figures and numbers;
system state monitoring unit: the system is characterized by providing real-time monitoring of the overall performance of the system, comprising the working state of an actuator, the reading accuracy of a sensor and the early warning of a predictive maintenance module, wherein the monitored information is displayed in the form of an instrument panel or a control panel, so that an operator can clearly know the running condition of the system;
an operation control unit: allowing an operator to manually adjust key parameters of the paper feed deviation correcting system, including adjusting the speed of the conveyor belt, changing the deviation correcting strategy, or manually triggering specific maintenance operations;
an alarm notification unit: when the system detects an anomaly or is about to reach a critical maintenance point, an alert and notification will be sent to the operator, the alert being provided in a visual and audible manner.
9. The paper conveying deviation correcting method is characterized by comprising the following steps of:
s1: setting basic parameters of the paper conveying system, including conveying belt speed, paper type and expected conveying path;
s2: continuously monitoring the speed, position and offset of the paper, and thickness and texture information of the paper;
s3: capturing an image of the paper on the conveyor belt and analyzing the edge and surface features of the paper to determine the exact position and state of the paper;
s4: according to the monitored paper state and the image analysis result, optimizing a deviation correcting strategy by using a machine learning algorithm, and ensuring that paper is accurately conveyed according to a preset path;
s5: according to the optimized deviation correcting strategy, the position and speed of the paper are adjusted, so that the paper returns to a preset conveying path;
s6: analyzing system operation data, predicting future maintenance requirements, including component replacement or system adjustments;
s7: real-time data of system status and corrective action is displayed, providing manual control options for operator intervention as needed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410081072.7A CN117886147A (en) | 2024-01-19 | 2024-01-19 | Paper conveying deviation correcting system and deviation correcting method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410081072.7A CN117886147A (en) | 2024-01-19 | 2024-01-19 | Paper conveying deviation correcting system and deviation correcting method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117886147A true CN117886147A (en) | 2024-04-16 |
Family
ID=90648739
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410081072.7A Pending CN117886147A (en) | 2024-01-19 | 2024-01-19 | Paper conveying deviation correcting system and deviation correcting method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117886147A (en) |
-
2024
- 2024-01-19 CN CN202410081072.7A patent/CN117886147A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112179910B (en) | Real-time detection processing method and system for defects of lithium battery pole piece | |
| EP1808018B1 (en) | Image sensor annotation method and apparatus | |
| US20230115878A1 (en) | Machine learning method for anomaly detection in an electrical system | |
| US20110141266A1 (en) | Monitoring system of a dynamical arrangement of pieces taking part in a process related to a manufacturing executing system | |
| CN109675935A (en) | A kind of IPCA operation of rolling on-line fault diagnosis method becoming control limit | |
| EP4028841B1 (en) | Systems and methods for detecting wind turbine operation anomaly using deep learning | |
| CN110303491A (en) | Act history management system | |
| KR101203325B1 (en) | Inventory control for web-based articles | |
| CN116902536A (en) | Intelligent deviation rectifying system of belt conveyor | |
| CN114407079B (en) | Method for controlling mechanical arm mounting bolt | |
| CN117886147A (en) | Paper conveying deviation correcting system and deviation correcting method thereof | |
| CN113702393A (en) | Intrinsic safety type mining conveyor belt surface damage detection system and detection method | |
| CN117583751A (en) | H-shaped steel laser cutting deformation compensation algorithm | |
| US11374534B2 (en) | Optoelectronic solar cell test system for an in-line solar cell production plant, and method for optimizing the in-line production of solar cells using an optoelectronic solar cell test system of this type | |
| CN115993366B (en) | Workpiece surface detection method and system based on sensing equipment | |
| CN116840240A (en) | Visual detection system of power supply distributor | |
| US20230186454A1 (en) | Machine vision system for inspecting quality of various non-woven materials | |
| CN116147697B (en) | Unattended monitoring method and system for aluminum hydroxide | |
| WO2021041422A1 (en) | Ai-powered autonomous 3d printer | |
| CN113420612B (en) | Production beat calculation method based on machine vision | |
| CN113269736B (en) | Method, system and medium for automated inspection of fastener dimensions | |
| US11609836B2 (en) | Operation method and operation device of failure detection and classification model | |
| US20130186055A1 (en) | System and method for the management of the flow rate of a feed line | |
| Takiguchi et al. | Exposure system improvement for greater productivity | |
| CN113283339A (en) | Machine vision-based method for monitoring material shortage abnormity of industrial mineral aggregate conveying belt |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication |