Printing equipment paper reversing detection system based on photoelectric color identification

Abstract

The invention discloses a printing equipment reverse paper detection system based on photoelectric color recognition, and relates to the technical field of printing equipment quality detection and control. A multi-angle time-sharing spectrum detection module and a spectrum fusion algorithm based on angle sequence variance analysis are adopted to solve mirror reflection interference, and the detection accuracy is improved. The system controls the annular light source array to sequentially illuminate the same detection point from a plurality of different angles in a time-sharing mode and synchronously collects a series of time-sharing spectral data, and due to the fact that the intensity of specular reflection light changes violently along with the incident angle, diffuse reflection light representing the color of a paper or ink body is relatively stable, and the time-sharing spectral data is obtained. Therefore, the specular reflection component can be accurately identified and quantified by calculating the variances of the same wavelength light intensity in different angle sequences, and when the primary color spectrum feature vector is fused and generated, the data with large variance is endowed with low weight, so that the highlight interference is effectively inhibited, the stable and real surface color essential information is extracted, and the method has the advantages of being high in practicability and the like. And the discrimination accuracy under a complex working condition is obviously improved.

Description

Technical Field

[0001] This invention relates to the field of printing equipment quality inspection and control technology, specifically to a printing equipment reverse paper detection system based on photoelectric color recognition. Background Technology

[0002] In modern high-speed printing production, incorrect placement of the front and back of paper is one of the key causes of mass printing waste. Traditional manual sampling methods are inefficient and unreliable, failing to meet the real-time monitoring requirements of high-speed continuous production. Therefore, developing an online inspection system capable of automatically, accurately, and in real-time identifying the front and back of paper has significant industrial application value for ensuring printing quality and reducing material and labor waste. Existing technologies, detection methods based on single-point color or brightness contrast have been attempted, but their accuracy and stability under complex real-world conditions face serious challenges.

[0003] Existing photoelectric sensing-based reverse paper detection technologies have the following inherent drawbacks: First, printed paper generally has a glossy or coated surface, and strong specular reflection will seriously interfere with the color information received by the sensor, resulting in serious distortion of the detection results based on a single angle and a single lighting condition, and a high misjudgment rate.

[0004] Secondly, existing systems typically use static threshold judgments, lacking self-learning and adaptive capabilities. When changing printing products, ink batches, or paper types, parameters must be manually reset by professionals, making the process cumbersome and reliant on experience.

[0005] Finally, for subtle color differences or the distinction between the front and back of specific areas, traditional methods struggle to extract stable and essential features. Their discrimination models lack robustness and cannot adapt to the rapid dynamic detection of paper and the complex surface reflection characteristics on high-speed production lines.

[0006] In conclusion, the industry urgently needs a new paper-reversing detection technology that can overcome specular reflection interference, extract essential features from complex spectral signals, and maintain high precision and reliability in judging various printed materials under high-speed operation, thereby fundamentally eliminating production accidents and economic losses caused by paper reversing. Summary of the Invention

[0007] The purpose of this invention is to overcome the shortcomings of existing technologies and provide a reverse paper detection system for printing equipment based on photoelectric color recognition. This system utilizes a multi-angle time-division spectral detection module and a spectral fusion algorithm based on angle sequence variance analysis to address specular reflection interference. The system controls a ring light source array to illuminate the same detection point sequentially from multiple different angles in a time-division mode, simultaneously acquiring a series of time-division spectral data. Since the intensity of specular reflection light varies drastically with the incident angle, while diffuse reflection light, representing the color of the paper or ink itself, is relatively stable, the specular reflection component can be accurately identified and quantified by calculating the variance of the same wavelength light intensity in different angle sequences. When fusing to generate the primary color spectral feature vector, data with large variances are assigned low weights, thereby effectively suppressing high-light interference at the algorithm level and extracting stable and true surface color information. This allows the detection system to obtain reliable spectral features even on coated surfaces, significantly improving the discrimination accuracy under complex working conditions.

[0008] To solve the above-mentioned technical problems, the present invention provides the following technical solution: a reverse paper detection system for printing equipment based on photoelectric color recognition, the system comprising: a multi-angle time-division spectral detection module, an intelligent control and processing module, a human-computer interaction module, a status signal output module, and an equipment linkage control module; The multi-angle time-division spectral detection module is used to emit multi-angle time-division light onto the surface of the paper being tested and to collect the corresponding reflectance spectral sequence. The intelligent control and processing module is electrically connected to the multi-angle time-division spectral detection module. It is used to control the illumination sequence, process spectral data, perform spectral fusion and feature comparison, generate paper front and back status judgment results, and support switching between learning mode and detection mode. The human-computer interaction module is connected to the intelligent control and processing module and is used for system parameter setting, detection point position calibration, and detection benchmark learning and storage. The status signal output module is used to convert the paper front and back status judgment result in the intelligent control and processing module into an industrial control standard electrical signal. The equipment linkage control module is a programmable logic controller for the printing equipment. It is connected to the status signal output module through a digital input port and is used to receive the industrial control standard electrical signal and execute predetermined equipment control commands accordingly.

[0009] Furthermore, the multi-angle time-division spectral detection module includes a ring light source array unit and a high-speed spectral sensing unit; The ring light source array unit is composed of at least three sets of independently controllable light-emitting diode subarrays uniformly arranged along the ring substrate. The angle between the optical axis of each set of light-emitting diode subarrays and the normal of the surface of the paper being tested is different, so as to provide multiple incident light illumination conditions covering multiple angles. The high-speed spectral sensing unit has its optical axis perpendicular to the surface of the paper being tested and is arranged coaxially with the center of the ring light source array unit. It is used to synchronously collect the reflected light from a specific point on the surface of the paper being tested when each group of LED subarrays is individually lit and to resolve its spectral data.

[0010] Furthermore, the intelligent control and processing module controls the illumination sequence of the multi-angle time-division spectral detection module through a time-division lighting mode. The working principle of the time-division lighting mode is as follows: Within one detection cycle, the intelligent control and processing module drives each group of light-emitting diode subarrays in the ring light source array unit to light up sequentially and individually in a preset order; Whenever a group of light-emitting diode subarrays is lit, the intelligent control and processing module synchronously triggers the high-speed spectral sensing unit to perform a spectral and image sampling. This allows for the acquisition of multiple independent time-division spectral data of the same paper detection point under illumination at multiple different incident angles.

[0011] Furthermore, the intelligent control and processing module includes a spectral sequence fusion analysis unit and an intelligent discrimination unit; The spectral sequence fusion analysis unit is used to process multiple independent time-division spectral data, distinguish and suppress specular reflection components, extract diffuse reflection stable spectral features representing the body color of paper and ink, and generate primary color spectral feature vectors. The intelligent discrimination unit is used to compare the primary color spectral feature vector obtained in real time with the pre-stored standard primary color spectral feature template, and output the paper front and back status judgment result.

[0012] Furthermore, the steps of the spectral sequence fusion analysis unit in processing the time-division spectral sequence and extracting the primary color spectral feature vector are as follows: For a detection point, in The spectral response vectors collected at different incident angles are: ; Calculate the detection point in all Mean vector of spectral response at each angle ; Calculate the spectral response vector at each angle With mean vector Difference vector ; Calculate the variance of the magnitude of the difference vector. ,in, Representing vectors The Euclidean norm; Spectral response vector for all angles Weighted fusion is performed to calculate the final primary color spectral eigenvector. Among them, the weighting coefficient With variance They are inversely correlated.

[0013] Furthermore, the intelligent discrimination unit uses spectral angular distance as a measure of the similarity between the real-time primary color spectral feature vector and the standard primary color spectral feature template. The discrimination steps are as follows: The paper primary color spectral feature vector obtained after real-time acquisition and processing by the spectral sequence fusion analysis module is: ; Combined with the standard primary color spectral feature template vector stored in learning mode ; Calculate the real-time primary color spectral feature vector With the standard primary color spectral feature template vector spectral angular distance between Where · represents the dot product operation of vectors. and These represent the magnitudes of the vectors, respectively. Set the discrimination threshold ,when When the current paper is determined to be front-side up, When the current paper is reversed, it is determined that the current paper is reversed.

[0014] Furthermore, in the intelligent control and processing module: in the learning mode, the intelligent control and processing module controls the system to detect the known positive standard sample, and processes the obtained time-division spectral sequence of the standard sample through the spectral sequence fusion analysis unit to generate and store it as a standard feature template.

[0015] Furthermore, in the intelligent control and processing module: in the detection mode, the intelligent control and processing module controls the paper to be inspected to perform real-time detection, processes the real-time time-division spectral sequence obtained by the spectral sequence fusion analysis unit to generate a real-time primary color spectral feature vector, and compares the real-time primary color spectral feature vector with the standard feature template by the intelligent discrimination unit.

[0016] Furthermore, when the intelligent control and processing module determines that the current paper is reversed in the detection mode, the equipment linkage control module sends a stop signal to the programmable logic controller of the printing equipment. The stop signal triggers the programmable logic controller to execute a preset emergency stop control program. The final output instruction of the emergency stop control program is to control the main drive motor of the printing equipment to stop running.

[0017] Compared with existing technologies, this photoelectric color recognition-based printing equipment reverse paper detection system has the following advantages: I. This invention employs a multi-angle time-division spectral detection module and a spectral fusion algorithm based on angle sequence variance analysis to address specular reflection interference. The system controls a ring light source array to illuminate the same detection point sequentially from multiple different angles in a time-division mode, and simultaneously collects a series of time-division spectral data. Since the intensity of specular reflected light varies drastically with the incident angle, while diffuse reflected light, representing the color of the paper or ink itself, is relatively stable, the specular reflection component can be accurately identified and quantified by calculating the variance of the same wavelength light intensity in different angle sequences. When fusing to generate the primary color spectral feature vector, data with large variance are assigned low weights, thereby effectively suppressing high-light interference, extracting stable and true surface color information, and significantly improving the discrimination accuracy under complex working conditions.

[0018] Second, this invention achieves autonomous calibration and sensitive discrimination of subtle color differences by designing an intelligent control process that includes learning and detection modes and using spectral angular distance as the discrimination criterion. In learning mode, the system can quickly collect multi-angle spectral data of qualified front samples and automatically generate high-fidelity standard feature templates through a fusion algorithm, reducing the usage threshold and avoiding subjective errors. In detection mode, the system compares the real-time extracted primary color spectral feature vectors with the template vectors and uses spectral angular distance for measurement to calculate the angle between the two multi-dimensional spectral vectors in space. This enables the system to effectively distinguish between front and back states that are difficult to distinguish using traditional methods, even though they have similar colors but different spectral distributions, thus improving the system's discrimination sensitivity and generalization ability.

[0019] Other advantages, objectives and features of the invention will be set forth in part in the description which follows, and in part will be apparent to those skilled in the art from the following examination or study, or may be learned from the practice of the invention. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is an operation flowchart for a reverse paper detection system for printing equipment based on photoelectric color recognition. Figure 2 This is a block diagram of the module composition of a reverse paper detection system for printing equipment based on photoelectric color recognition; Figure 3 This is a flowchart of the time-division lighting mode in the reverse paper detection system of a printing equipment based on photoelectric color recognition. Detailed Implementation

[0022] To better understand the above technical solutions, a detailed description of the solutions will be provided below in conjunction with the accompanying drawings and specific embodiments. Obviously, the described embodiments are merely some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0023] The terminology used in the embodiments of this invention is for the purpose of describing particular embodiments only and is not intended to limit the invention. The singular forms “a,” “the,” and “the” as used in the embodiments of this invention and the appended claims are also intended to include the plural forms, and “multiple” generally includes at least two unless the context clearly indicates otherwise.

[0024] To address the problems of high misjudgment rates, poor adaptability, and cumbersome adjustments in existing reverse-paper detection technologies for printing equipment, such as significant interference from specular reflection, lack of adaptability, and difficulty in extracting stable color features, this invention provides a reverse-paper detection system for printing equipment based on photoelectric color recognition. This system aims to achieve real-time, high-precision, and adaptive detection of the front and back of printed paper through multi-angle time-division spectral detection, spectral sequence fusion analysis, and intelligent discrimination mechanisms. It also integrates with the printing equipment control system to automatically execute control commands such as machine stop, thereby eliminating batch defects caused by reversed paper placement during high-speed continuous printing. This invention is primarily applicable to various high-speed offset printing machines, gravure printing machines, flexographic printing machines, digital printing machines, and post-press processing equipment, especially in production scenarios with high requirements for front-and-back consistency, such as label printing, packaging printing, and ticket printing.

[0025] This invention constructs an integrated system consisting of a multi-angle time-division spectral detection module, an intelligent control and processing module, a human-machine interaction module, a status signal output module, and an equipment linkage control module. This system enables the extraction and stable discrimination of the essential characteristics of paper surface color. Combined with an industrial control interface, it achieves seamless connection between detection results and equipment actions, thereby improving the automation level and quality control capabilities of printing production.

[0026] Specifically, such as Figure 2 As shown, the printing equipment reverse paper detection system based on photoelectric color recognition includes a multi-angle time-division spectral detection module, an intelligent control and processing module, a human-machine interaction module, a status signal output module, and an equipment linkage control module. The multi-angle time-division spectral detection module is used to emit multi-angle time-division light onto the surface of the paper being tested and to collect the corresponding reflectance spectral sequence. The intelligent control and processing module is electrically connected to the multi-angle time-division spectral detection module. It is used to control the illumination sequence, process spectral data, perform spectral fusion and feature comparison, generate paper front and back status judgment results, and support switching between learning mode and detection mode. The human-computer interaction module is connected to the intelligent control and processing module and is used for system parameter setting, detection point position calibration, and detection benchmark learning and storage. The status signal output module is used to convert the paper front and back status judgment result in the intelligent control and processing module into an industrial control standard electrical signal; The equipment linkage control module is a programmable logic controller for the printing equipment. It is connected to the status signal output module through a digital input port and is used to receive the industrial control standard electrical signals and execute predetermined equipment control commands accordingly.

[0027] The multi-angle time-division spectral detection module includes a ring light source array unit and a high-speed spectral sensor unit, wherein: The ring light source array unit consists of at least three independently controllable light-emitting diode subarrays uniformly arranged along the ring substrate. The angle between the optical axis of each LED subarray and the normal to the surface of the paper being tested is different, so as to provide multiple incident light illumination conditions covering multiple angles.

[0028] The optical axis of the high-speed spectral sensing unit is perpendicular to the surface of the paper being tested and is arranged coaxially with the center of the ring light source array unit. It is used to synchronously collect the reflected light from a specific point on the surface of the paper being tested when each group of LED subarrays is lit individually and to resolve its spectral data.

[0029] The intelligent control and processing module includes a spectral sequence fusion analysis unit and an intelligent discrimination unit, and controls the illumination timing of the multi-angle time-division spectral detection module through a time-division lighting mode, such as... Figure 3 As shown, the workflow of the time-sharing lighting mode is as follows: Within one detection cycle, the intelligent control and processing module drives each group of light-emitting diode subarrays in the ring light source array unit to light up sequentially and individually in a preset order; Whenever a group of light-emitting diode subarrays is lit, the intelligent control and processing module synchronously triggers the high-speed spectral sensing unit to perform a spectral and image sampling. Multiple independent time-division spectral data of the same paper detection point under illumination at multiple different incident angles were obtained.

[0030] The spectral sequence fusion analysis unit is used to process multiple independent time-division spectral data, distinguish and suppress specular reflection components, extract diffuse reflection stable spectral features representing the body color of paper and ink, and generate primary color spectral feature vectors.

[0031] The intelligent discrimination unit is used to compare the primary color spectral feature vector obtained in real time with the pre-stored standard primary color spectral feature template, and output the paper front and back status judgment result.

[0032] Meanwhile, the intelligent control and processing module supports switching between learning mode and detection mode. Its specific working principle is as follows: In learning mode, the intelligent control and processing module controls the system to detect the known positive standard sample, and processes the obtained time-division spectral sequence of the standard sample through the spectral sequence fusion analysis unit to generate and store it as a standard feature template. In detection mode, the intelligent control and processing module controls the paper to be inspected to perform real-time detection. The real-time time-division spectral sequence obtained by the spectral sequence fusion analysis unit is processed to generate a real-time primary color spectral feature vector, and the real-time primary color spectral feature vector is compared with a standard feature template by the intelligent discrimination unit.

[0033] The human-machine interaction module is connected to the intelligent control and processing module, providing functions for setting system parameters, calibrating detection point positions, and learning and storing detection benchmarks. It is presented in the form of a touch screen or industrial control computer interface, supporting users to perform visual operations.

[0034] The aforementioned status signal output module is used to convert the paper front and back status judgment result output by the intelligent control and processing module into industrial control standard electrical signals, such as 24VDC level signals, relay contact signals, or digital IO signals, so as to be compatible with downstream equipment interfaces.

[0035] The aforementioned equipment linkage control module is the original programmable logic controller (PLC) of the printing equipment, connected to the status signal output module via a digital input port. It receives standard industrial control electrical signals and executes predetermined equipment control commands, such as emergency stop, alarm, and rejection. In the specific implementation process, the multi-angle time-division spectral detection module is installed on the paper feeding path of the printing equipment to ensure that its optical axis is perpendicular to the paper surface and that the illumination range of the ring light source array covers the paper area to be detected. Through the human-machine interface, the operator can visually calibrate the detection point to ensure that the spectral sensing unit is aligned with the preset detection area.

[0036] After the system is powered on, it enters the initialization state. The intelligent control and processing module confirms that each LED subarray and spectral sensor of the multi-angle time-division spectral detection module are working normally, and the system enters the learning mode.

[0037] In learning mode, the operator places a standard sample paper, confirmed to be front-side, into the detection position. The intelligent control and processing module initiates the time-division spectral acquisition process: it controls the ring light source array unit to illuminate each group of LED sub-arrays in a preset order. Each time a group is illuminated, the high-speed spectral sensing unit is simultaneously triggered to collect the reflectance spectral data under that angle of illumination.

[0038] For a single detection point, the system acquires a set of spectral response vector sequences at N different incident angles. .

[0039] Spectral sequence fusion analysis unit for spectral response vector sequence The process involves extracting the primary color spectral feature vectors. Specific steps include: Calculate the mean vector of the spectral response at the detection point at all N angles: ; Calculate the spectral response vector at each angle With mean vector Difference vector ; Calculate the variance of the magnitude of the difference vector. ,in, Representing vectors The Euclidean norm and the variance V reflect the degree of fluctuation of the spectral data at different angles. The greater the fluctuation, the stronger the specular reflection component. Spectral response vector for all angles Weighted fusion is performed to calculate the final primary color spectral eigenvector. Among them, the weighting coefficient With variance The system exhibits an inverse correlation, meaning that data with large variance are assigned lower weights, while data with small variance are assigned higher weights. This allows the system to effectively suppress specular interference and extract stable spectral features that represent the true color of paper or ink.

[0040] Extracted primary color spectral feature vector Stored as a standard feature template It can be named and saved in the human-computer interaction interface, and supports the management of multiple product templates.

[0041] After learning is complete, the system switches to detection mode. In detection mode, the system performs real-time detection on the paper to be inspected. For each sheet of paper that passes through the detection point, the system repeats the above-described time-division spectral acquisition and fusion process to obtain the real-time primary color spectral feature vector. .

[0042] The intelligent discrimination unit uses spectral angular distance as a similarity metric to calculate real-time vectors. With standard template vector Spectral angular distance between them: , where · represents the dot product operation of vectors, and ‖·‖ represents the magnitude of the vectors. The smaller the spectral angular distance S, the closer the directions of the two vectors are in the spectral feature space, that is, the more similar their colors are in essence.

[0043] The system presets a discrimination threshold. ,when When, determine that the current paper is front-side; when When the current paper is reversed, it is determined that the current paper is reversed.

[0044] If the result is positive, the system has no special output and the printing equipment continues to operate normally. If the result is negative, the intelligent control and processing module immediately sends a "reverse paper" signal to the status signal output module. The status signal output module converts the signal into an industrial standard level signal and transmits it to the digital input port of the printing equipment PLC via cable.

[0045] Upon receiving the signal, the equipment linkage control module (PLC) immediately executes the preset emergency stop control program. Its final output instruction is to control the main drive motor of the printing equipment to stop running. At the same time, it may trigger an audible and visual alarm to remind the operator to handle the situation, thus realizing a closed-loop response from detection to control and effectively preventing the reversed paper from continuing to enter the printing unit and causing waste.

[0046] like Figure 1 As shown below, the specific workflow of this system will be explained in detail using a high-speed printing production scenario. This workflow is divided into two main modes: learning mode (used for setting standards during order changeovers) and inspection mode (used for normal production). The specific workflow steps are as follows: (1) Learning mode Mode selection and startup: Operators can switch the system's working mode to learning mode through the human-computer interaction module.

[0047] Place the standard sample: Use a known, correctly positioned front-side sheet of paper as the standard sample and place it at the testing station of the printing equipment.

[0048] Trigger the learning process: Issue the start-learning command through the human-computer interaction interface.

[0049] Perform multi-angle spectral scanning: The system controls the ring light source array unit to sequentially and individually illuminate each group of LED subarrays at different angles in a preset order.

[0050] At the moment each set of light sources is lit, the high-speed spectral sensing unit simultaneously acquires the reflectance spectral data of the paper detection point.

[0051] Spectral data fusion processing: The intelligent control and processing module processes the time-division spectral data collected from multiple angles, suppresses specular reflection interference by analyzing the sequence variance, and extracts a stable primary color spectral feature vector representing the body color of the paper.

[0052] Template storage: The calculated primary color spectral feature vectors are used as standard primary color spectral feature templates and stored in the system. Once the learning mode is complete, this process is repeated multiple times to obtain a more robust average template.

[0053] (2) Detection mode Mode switching: Operators can switch the system's working mode to detection mode through the human-machine interaction module.

[0054] Paper feeding: The printing equipment starts running at high speed, and the paper to be inspected is continuously fed to the inspection station.

[0055] Arrival Detection: The synchronous sensor installed upstream of the detection probe detects the arrival of the paper's leading edge and immediately sends a trigger signal to the intelligent control and processing module.

[0056] Real-time multi-angle spectral acquisition: After receiving the trigger signal, the intelligent control and processing module immediately controls the multi-angle time-division spectral detection module to acquire the real-time multi-angle time-division spectral data of the current paper detection point.

[0057] Real-time feature extraction: The intelligent control and processing module fuses and processes real-time spectral data to generate the real-time primary color spectral feature vector of the current paper.

[0058] Feature comparison and discrimination: The intelligent discrimination unit calculates the spectral angular distance between the real-time primary color spectral feature vector and the pre-stored standard primary color spectral feature template to measure the similarity between the two.

[0059] Judgment and Decision Making: If the calculated similarity is lower than the preset threshold, the current paper is determined to be front-side.

[0060] If the calculated similarity is higher than the preset threshold, the current paper is determined to be the reverse side.

[0061] Results output and device linkage: Front: The status signal output module does not generate abnormal signals, the equipment linkage control module (i.e., PLC) does not receive the stop command, the printing equipment continues to operate normally, and the system is ready to detect the next sheet of paper.

[0062] On the other hand: The status signal output module immediately generates a standard "paper reversal" fault electrical signal and sends it to the equipment linkage control module (PLC).

[0063] Emergency shutdown of equipment: After receiving the "paper reversal" signal, the PLC immediately executes the preset emergency stop control program, cuts off the power supply to the main drive motor or starts the brake, so that the printing equipment stops running in an emergency, and triggers an audible and visual alarm at the same time.

[0064] Loop detection: For front-side paper, the system process ends after detection is completed and immediately resets to prepare for repeating the detection process for the next sheet of paper.

[0065] In summary, this invention constructs a high-precision, high-response automatic detection system for reversed printing paper by employing multi-angle time-division spectral detection, variance-weighted spectral fusion, intelligent spectral angular distance discrimination, and seamless integration with industrial control systems. This system upgrades the traditional, manual, easily interfered with, and poorly adaptable detection method into a fully automatic, essential feature extraction, and self-learning intelligent detection solution. It fundamentally solves the quality accidents and material waste caused by reversed paper in high-speed printing, providing reliable technical support for the intelligent upgrading and quality control of the printing industry.

[0066] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any simple modifications, equivalent changes and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. A reverse paper detection system for printing equipment based on photoelectric color recognition, characterized in that, The system includes: a multi-angle time-division spectral detection module, an intelligent control and processing module, a human-machine interaction module, a status signal output module, and an equipment linkage control module; The multi-angle time-division spectral detection module is used to emit multi-angle time-division light onto the surface of the paper being tested and to collect the corresponding reflectance spectral sequence. The intelligent control and processing module is electrically connected to the multi-angle time-division spectral detection module. It is used to control the illumination sequence, process spectral data, perform spectral fusion and feature comparison, generate paper front and back status judgment results, and support switching between learning mode and detection mode. The human-computer interaction module is connected to the intelligent control and processing module and is used for system parameter setting, detection point position calibration, and detection benchmark learning and storage. The status signal output module is used to convert the paper front and back status judgment result in the intelligent control and processing module into an industrial control standard electrical signal. The equipment linkage control module is a programmable logic controller for the printing equipment. It is connected to the status signal output module through a digital input port and is used to receive the industrial control standard electrical signal and execute predetermined equipment control commands accordingly.

2. The printing equipment reverse paper detection system based on photoelectric color recognition according to claim 1, characterized in that, The multi-angle time-division spectral detection module includes a ring light source array unit and a high-speed spectral sensing unit; The ring light source array unit is composed of at least three sets of independently controllable light-emitting diode subarrays uniformly arranged along the ring substrate. The angle between the optical axis of each set of light-emitting diode subarrays and the normal of the surface of the paper being tested is different, so as to provide multiple incident light illumination conditions covering multiple angles. The high-speed spectral sensing unit has its optical axis perpendicular to the surface of the paper being tested and is arranged coaxially with the center of the ring light source array unit. It is used to synchronously collect the reflected light from a specific point on the surface of the paper being tested when each group of LED subarrays is individually lit and to resolve its spectral data.

3. The printing equipment reverse paper detection system based on photoelectric color recognition according to claim 1, characterized in that, The intelligent control and processing module controls the illumination sequence of the multi-angle time-division spectral detection module through a time-division lighting mode. The working principle of the time-division lighting mode is as follows: Within one detection cycle, the intelligent control and processing module drives each group of light-emitting diode subarrays in the ring light source array unit to light up sequentially and individually in a preset order; Whenever a group of light-emitting diode subarrays is lit, the intelligent control and processing module synchronously triggers the high-speed spectral sensing unit to perform a spectral and image sampling. This allows for the acquisition of multiple independent time-division spectral data of the same paper detection point under illumination at multiple different incident angles.

4. The printing equipment reverse paper detection system based on photoelectric color recognition according to claim 1, characterized in that, The intelligent control and processing module includes a spectral sequence fusion analysis unit and an intelligent discrimination unit; The spectral sequence fusion analysis unit is used to process multiple independent time-division spectral data, distinguish and suppress specular reflection components, extract diffuse reflection stable spectral features representing the body color of paper and ink, and generate primary color spectral feature vectors. The intelligent discrimination unit is used to compare the primary color spectral feature vector obtained in real time with the pre-stored standard primary color spectral feature template, and output the paper front and back status judgment result.

5. The printing equipment reverse paper detection system based on photoelectric color recognition according to claim 4, characterized in that, The steps of the spectral sequence fusion analysis unit in processing time-division spectral sequences and extracting primary color spectral feature vectors are as follows: For a detection point, in The spectral response vectors collected at different incident angles are: ; Calculate the detection point in all Mean vector of spectral response at each angle ; Calculate the spectral response vector at each angle With mean vector Difference vector ; Calculate the variance of the magnitude of the difference vector. ,in, Representing vectors The Euclidean norm; Spectral response vector for all angles Weighted fusion is performed to calculate the final primary color spectral eigenvector. Among them, the weighting coefficient With variance They are inversely correlated.

6. The printing equipment reverse paper detection system based on photoelectric color recognition according to claim 4, characterized in that, The intelligent discrimination unit uses spectral angular distance as a measure of the similarity between the real-time primary color spectral feature vector and the standard primary color spectral feature template. The discrimination steps are as follows: The paper primary color spectral feature vector obtained after real-time acquisition and processing by the spectral sequence fusion analysis module is: ; Combined with the standard primary color spectral feature template vector stored in learning mode ; Calculate the real-time primary color spectral feature vector With the standard primary color spectral feature template vector spectral angular distance between Where · represents the dot product operation of vectors. and These represent the magnitudes of the vectors, respectively. Set the discrimination threshold ,when When the current paper is determined to be front-side up, When the current paper is reversed, it is determined that the current paper is reversed.

7. The printing equipment reverse paper detection system based on photoelectric color recognition according to claim 1, characterized in that, In the intelligent control and processing module: in the learning mode, the intelligent control and processing module controls the system to detect the known positive standard sample, and processes the obtained time-division spectral sequence of the standard sample through the spectral sequence fusion analysis unit to generate and store it as a standard feature template.

8. The printing equipment reverse paper detection system based on photoelectric color recognition according to claim 1, characterized in that, In the intelligent control and processing module: under the detection mode, the intelligent control and processing module controls the paper to be inspected to perform real-time detection, processes the real-time time-division spectral sequence obtained by the spectral sequence fusion analysis unit to generate a real-time primary color spectral feature vector, and compares the real-time primary color spectral feature vector with the standard feature template by the intelligent discrimination unit.

9. The printing equipment reverse paper detection system based on photoelectric color recognition according to claim 1, characterized in that, When the device linkage control module determines that the current paper is reversed in the detection mode of the intelligent control and processing module, it sends a stop signal to the programmable logic controller of the printing equipment. The stop signal triggers the programmable logic controller to execute a preset emergency stop control program. The final output instruction of the emergency stop control program is to control the main drive motor of the printing equipment to stop running.

Images