Printing fault checking and configuration optimization method and system suitable for manufacturing industry environment

Abstract

The invention relates to a printing fault troubleshooting and configuration optimization method and system suitable for a manufacturing industry environment, and the method comprises the steps: collecting workshop environment parameters in real time, including the temperature of a heating unit, the air humidity of a workshop, and the dust concentration data of a printing head; the environment parameter overrun condition is judged, the toner melting point, the printing speed and the adjustment value of the paper preheating temperature are synchronously calculated, and a corresponding control instruction set is generated; and the control instruction set is optimized through the control algorithm model, and the printer is driven to execute dynamic adjustment, so that the purposes of self-adaptive optimization of printing parameters in a complex industrial environment, stable operation of a printing system and reduction of the failure rate are achieved.

Description

Technical Field

[0001] The present invention relates to the field of industrial automation and intelligent manufacturing technology, and in particular to a printing fault troubleshooting and configuration optimization method and system suitable for a manufacturing environment. Background Art

[0002] In the process of intelligent transformation of the manufacturing industry, the stability of industrial printing systems, as the core link for the output of production instructions and process documents, directly affects production efficiency and product quality. Traditional printing equipment mostly adopts a fixed parameter operation mode, which makes it difficult to adapt to the complex and changing workshop environment (such as high temperature and humidity, dust accumulation, and seasonal temperature and humidity fluctuations), resulting in frequent failures such as toner smearing, paper jams, and print head clogging. Although existing technologies attempt to optimize printing parameters through threshold alarms or simple linear compensation, they generally suffer from problems such as a single environmental perception dimension, lagging parameter adjustment, and insufficient consideration of the synergistic influence of multiple factors. Especially under extreme working conditions or long-term continuous operation, print quality fluctuations and equipment maintenance costs remain high, becoming one of the bottlenecks restricting digital lean management in the manufacturing industry. Summary of the Invention

[0003] The main purpose of the present invention is to provide a printing troubleshooting and configuration optimization method and system suitable for manufacturing environments. Through multi-dimensional environmental perception and intelligent collaborative control, it can achieve adaptive optimization of printing parameters in complex industrial environments, ensure the stable operation of the printing system and reduce the failure rate.

[0004] To achieve the above objectives, the present invention provides a printing troubleshooting and configuration optimization method applicable to a manufacturing environment, comprising the following steps: Real-time collection of workshop environmental parameters, including heating unit temperature, workshop air humidity, and print head dust concentration data; Determine if environmental parameters exceed the limit, calculate the adjustment values ​​of toner melting point, printing speed and paper preheating temperature simultaneously, and generate the corresponding control instruction set; The control instruction set is optimized by a control algorithm model to drive the printer to perform dynamic adjustments.

[0005] Furthermore, the step of collecting workshop environmental parameters in real time includes: The infrared temperature sensor is used to collect the ambient temperature of the printer's heating unit in real time; The workshop air humidity value and heating unit temperature reference value are collected synchronously through temperature and humidity sensors; The laser scattering dust sensor is used to collect the dust concentration value in the print head working area simultaneously; The original electrical signals output by each sensor are denoised, and the characteristic signals in the 0.5-10kHz frequency band are extracted to generate a denoised environmental parameter dataset.

[0006] Furthermore, the step of determining whether an environmental parameter exceeds a limit includes: Based on the collected data on heating unit temperature, workshop air humidity, and print head dust concentration, the LSTM neural network predicts the changing trends of heating unit temperature and workshop air humidity within the next 24 hours, and dynamically adjusts the heating unit temperature threshold, workshop air humidity threshold, and print head dust concentration threshold. Compare the environmental parameters collected in real time with the corresponding adjusted thresholds; If the real-time collected heating unit temperature is greater than the adjusted heating unit temperature threshold, the temperature is determined to be out of limit; if the real-time collected workshop air humidity is greater than the adjusted workshop air humidity threshold, the humidity is determined to be out of limit; if the real-time collected print head dust concentration is greater than the adjusted print head dust concentration threshold, the dust concentration is determined to be out of limit.

[0007] Furthermore, the step of calculating the adjustment value of the toner melting point includes: When the heating unit temperature or workshop air humidity exceeds the limit, the workshop air humidity value, heating unit temperature value and historical print head clogging probability are mapped into the toner melting point compensation coefficient based on the nonlinear regression model; A toner melting point adjustment value is generated according to the toner melting point compensation coefficient.

[0008] Furthermore, the step of calculating the adjustment value of the printing speed includes: When the dust concentration of the print head exceeds the limit, the print speed adjustment coefficient is calculated according to the inverse proportionality rule based on the proportional relationship between the current dust concentration and the preset threshold; If the print speed adjustment factor is lower than 50% of the nominal default print speed of the device, the print speed adjustment factor is set to 50% of the default print speed, and a print speed adjustment value is generated.

[0009] Furthermore, the step of calculating the adjustment value of the paper preheating temperature includes: Real-time measurement of paper moisture content through near-infrared spectroscopy sensor; Calculate the preheating temperature adjustment value based on the workshop air humidity value, paper moisture content and the preset paper type compensation coefficient; If the preheating temperature adjustment value is lower than 60°C, the preheating temperature adjustment value is set to 60°C.

[0010] Furthermore, the step of optimizing the control instruction set through a control algorithm model includes: Based on real-time data collected from heating unit temperature, workshop air humidity, print head dust concentration, paper moisture content, toner level, and print head temperature, as well as historical environmental parameters, control instruction execution records, and print quality score datasets, a control algorithm model is used to generate candidate instruction sets for heating control, motor drive control, and preheating control. scoring the candidate instruction sets based on the print quality simulation results; According to the scoring results, the instruction set with the highest long-term printing stability score is selected as the final control instruction set through the Q-learning algorithm.

[0011] The present invention also provides a printing troubleshooting and configuration optimization system suitable for a manufacturing environment, comprising: Data acquisition unit, used to collect workshop environmental parameters in real time; An instruction generation unit is used to determine if environmental parameters exceed the limit, synchronously calculate the adjustment values ​​of the toner melting point, printing speed and paper preheating temperature, and generate a corresponding control instruction set; The instruction execution unit is used to optimize the control instruction set through a control algorithm model and drive the printer to perform dynamic adjustment.

[0012] The present invention also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the above-mentioned printing fault troubleshooting and configuration optimization method applicable to the manufacturing environment are implemented.

[0013] The present invention also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the above-mentioned printing fault troubleshooting and configuration optimization method applicable to a manufacturing environment are implemented.

[0014] The printing troubleshooting and configuration optimization method and system provided by the present invention, which are applicable to the manufacturing environment, have the following beneficial effects: This invention improves the environmental adaptability and operational reliability of industrial printing systems through multi-dimensional environmental perception, dynamic threshold prediction, and intelligent collaborative control. On the one hand, by integrating multi-source sensor data with machine learning algorithms, it enables real-time and precise control of printing parameters, effectively suppressing the interference of sudden environmental changes on printing quality. On the other hand, a multi-objective optimization strategy based on reinforcement learning balances energy efficiency and equipment life while ensuring printing accuracy, reducing unplanned downtime. Furthermore, the system's robustness is further enhanced through a closed-loop feedback mechanism and abnormal self-healing design, providing the manufacturing industry with a highly stable, low-maintenance intelligent printing solution, helping companies achieve continuity and controllability in their production processes. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1It is a flowchart of a printing troubleshooting and configuration optimization method applicable to a manufacturing environment in one embodiment of the present invention; Figure 2 It is a structural block diagram of a printing troubleshooting and configuration optimization system applicable to a manufacturing environment in one embodiment of the present invention; Figure 3 It is a schematic block diagram of the structure of a computer device according to an embodiment of the present invention.

[0016] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0018] Reference Figure 1 , which is a flow chart of a printing troubleshooting and configuration optimization method applicable to a manufacturing environment proposed by the present invention, comprising the following steps: S1, real-time collection of workshop environmental parameters, including heating unit temperature, workshop air humidity, and print head dust concentration data; S2, determining whether the environmental parameters exceed the limit, synchronously calculating the adjustment values ​​of the toner melting point, printing speed and paper preheating temperature, and generating the corresponding control instruction set; S3, optimizing the control instruction set through a control algorithm model, and driving the printer to perform dynamic adjustment.

[0019] In one embodiment, for step S1, The steps for real-time collection of workshop environmental parameters include: The infrared temperature sensor is used to collect the ambient temperature of the printer's heating unit in real time; The workshop air humidity value and heating unit temperature reference value are collected synchronously through temperature and humidity sensors; The laser scattering dust sensor is used to collect the dust concentration value in the print head working area simultaneously; The original electrical signals output by each sensor are denoised, and the characteristic signals in the 0.5-10kHz frequency band are extracted to generate a denoised environmental parameter dataset.

[0020] In specific implementation, a non-contact infrared temperature sensor, deployed within a 5cm radius of the printer's heating unit, directly monitors the real-time temperature of the heating unit's heat dissipation area. The temperature around the heating unit directly affects toner melting efficiency. Traditional contact temperature measurement is susceptible to mechanical vibration, while infrared temperature measurement avoids measurement errors caused by physical contact (such as thermal conduction lag). The infrared temperature sensor is tilted 30° toward the heating unit's heat dissipation outlet to avoid obstruction by paper transport. Furthermore, a digital integrated temperature and humidity sensor (such as the SHT35) is installed 30cm directly above the printer's paper feed path, parallel to the paper transport plane. Since the paper feed path is a critical area where paper is most affected by ambient temperature and humidity, installing the sensor in this location accurately reflects the risk of moisture absorption and deformation. Humidity measurements are used to calculate the paper preheating temperature. The ambient temperature around the heating unit, measured by the temperature and humidity sensor, is used to cross-validate the infrared temperature data and eliminate local overheating interference. A high-precision laser particle sensor (such as the PMS5003S), installed 1cm from the air inlet on the side of the printhead, monitors dust concentration entering the printhead in real time. Print head clogging is primarily caused by inhaled dust. Traditional sensors deployed on the ceiling of the workshop cannot reflect the actual operating conditions of the print head. In this implementation, the sensors are positioned to directly monitor dust concentration at the air inlet, improving monitoring accuracy. Furthermore, the sensors' built-in microfans generate stable airflow, preventing measurement fluctuations caused by airflow disturbances in the workshop. Wavelet packet decomposition is performed on the raw electrical signals from each sensor, using the Symlets wavelet basis function (Sym8) with a decomposition layer of five. The 0.5-10 kHz frequency band, which contains the sensor's effective response signal, is extracted while filtering out low-frequency mechanical vibration noise (<0.5 kHz) and high-frequency electromagnetic interference (>10 kHz). The Stein Unbiased Risk Threshold (SURE) algorithm is applied to the decomposed sub-band signals, retaining over 95% of the effective signal energy. The denoised multi-sensor data is aligned by timestamp to construct an environmental parameter dataset. A hardware-triggered synchronization mechanism is used to ensure that the multi-sensor sampling time deviation is less than 1 ms.

[0021] Comparison with traditional solutions: index Traditional solution (single-point thermometer and hygrometer + gravity dust detection) Solution of the present invention Temperature measurement accuracy ±2℃ ±0.5℃ (infrared + ambient temperature cross-verification) Dust response delay 5-10 minutes (gravity sedimentation method) Real-time (laser scattering + air inlet deployment) Signal anti-interference ability Susceptible to motor start and stop interference Wavelet packet decomposition + frequency band filtering This embodiment solves the core problems of environmental parameter collection being susceptible to interference and lack of local working condition monitoring in manufacturing environments through precise sensor selection and positioning, wavelet packet dynamic denoising, and multi-source data fusion, providing a high-precision data foundation for subsequent dynamic adjustment of printing parameters.

[0022] In one embodiment, for step S2, The steps to determine if an environmental parameter exceeds a limit include: Based on the collected data on heating unit temperature, workshop air humidity, and print head dust concentration, the LSTM neural network predicts the changing trends of heating unit temperature and workshop air humidity within the next 24 hours, and dynamically adjusts the heating unit temperature threshold, workshop air humidity threshold, and print head dust concentration threshold. Compare the environmental parameters collected in real time with the corresponding adjusted thresholds; If the real-time collected heating unit temperature is greater than the adjusted heating unit temperature threshold, the temperature is determined to be out of limit; if the real-time collected workshop air humidity is greater than the adjusted workshop air humidity threshold, the humidity is determined to be out of limit; if the real-time collected print head dust concentration is greater than the adjusted print head dust concentration threshold, the dust concentration is determined to be out of limit.

[0023] In the implementation, the LSTM neural network dynamic threshold prediction phase uses time-series data on heating unit temperature, workshop air humidity, and print head dust concentration, sampled every 10 minutes over the past 72 hours, combined with the workshop production schedule as input. A two-layer LSTM network (128 neurons per layer) with a fully connected layer is used to generate hourly predictions of heating unit temperature, workshop air humidity, and print head dust concentration trends for the next 24 hours. Dropout (0.2) is applied to prevent overfitting. The predictions are then adjusted to the predicted mean and standard deviation of the heating unit temperature, set to the mean plus twice the standard deviation to avoid false triggering due to occasional peaks. The workshop air humidity threshold is set to ±5% of the current value when the predicted fluctuation exceeds ±15% to accommodate sudden environmental changes. The print head dust concentration threshold is adjusted based on the predicted maximum value and equipment density, with different upper concentration limits corresponding to low, medium, and high equipment density. Integrating shift schedule data also prevents invalid alarms during non-production periods.

[0024] When performing real-time parameter comparison and over-limit determination, the real-time acquired parameters are first precisely aligned with the predicted thresholds by timestamp, with deviations calibrated to within ±1 second. An exponentially weighted moving average (smoothing coefficient α = 0.2) is used to process transient data spikes. Regarding over-limit determination, if the workshop air humidity or heating unit temperature exceeds the threshold for three consecutive sampling points (30 minutes), or the print head dust concentration exceeds the threshold once and persists for 5 minutes, it is determined to be over-limit. If both the heating unit temperature and workshop air humidity exceed the limit simultaneously, a composite alarm is triggered and the toner melting point parameters are adjusted preferentially. Regarding exception handling, when sensor data is abnormal, the predicted threshold is switched to for temporary reference and verified with redundant sensors. If the confidence level of the prediction model is less than 80%, dynamic adjustment is suspended and the factory default threshold is enabled. In an industrial scenario verification in an electronic product assembly workshop, the heating unit temperature fluctuates between 15°C and 35°C, the workshop air humidity fluctuates between 30% and 85%, and the print head dust concentration peaks at 300μg / m³. Comparison of the dynamic threshold solution of the present invention with the fixed threshold solution: index Fixed threshold scheme Dynamic threshold scheme of the present invention Heating unit temperature false alarm rate 28% 9% False alarm rate of workshop air humidity 25% 8% Fault response delay 2-4 hours 10-30 minutes Maintenance costs High (manual inspection) Low (auto-adjust) In typical application scenarios, such as during the rainy season, the workshop air humidity threshold is raised in advance to avoid frequent preheating adjustments. In equipment-intensive areas, the threshold is adjusted based on print head dust concentration predictions to reduce unnecessary print speed reductions. Furthermore, in the technical drawing and data association process, the LSTM network training process uses time-series data of heating unit temperature, workshop air humidity, and print head dust concentration as a foundation. High prediction accuracy (R²=0.93) is achieved through data normalization (Z-score) and a custom loss function (incorporating MAE and a threshold deviation penalty term). This embodiment dynamically adjusts thresholds and multi-condition over-limit judgment rules through LSTM time-series predictions, overcoming the shortcomings of traditional fixed thresholds in complex industrial environments. It demonstrates superior prediction accuracy, response speed, and anti-interference capabilities, laying a reliable decision-making foundation for printing parameter optimization.

[0025] In one embodiment, the step of calculating the adjustment value of the toner melting point includes: When the heating unit temperature or workshop air humidity exceeds the limit, the workshop air humidity value, heating unit temperature value and historical print head clogging probability are mapped into the toner melting point compensation coefficient based on the nonlinear regression model; A toner melting point adjustment value is generated according to the toner melting point compensation coefficient.

[0026] Specifically, a nonlinear regression model was constructed based on environmental parameters such as temperature (T), humidity (H), dust concentration (D), and the historical print head clogging probability (P clog ) (Count the proportion of print head blockage times to total print tasks under the same environmental parameter combination in the past 30 days. For example, when T=40℃ and H=80%, the blockage probability P clog =15%) as input. A Gaussian process regression (GPR) model was selected with the Matern 5 / 2 kernel function, leveraging its nonlinear mapping capability to capture the complex relationship between environmental parameters and toner viscosity. The GPR model then calculated the melting point compensation coefficient: The model is trained using 100,000 sets of historical data collected from 100 industrial printers. The goal is to minimize the mean square error between the predicted melting point compensation coefficient and the actual manually adjusted value. The melting point compensation coefficient ΔP based on the model output m , combined with the nominal melting point value P of the equipment default (such as laser printer 180 - 220 ℃), according to the formula Calculate the toner melting point adjustment value P opt . At the same time limit ΔP m In the range of [-0.2, +0.3], if it exceeds the range, manual review will be triggered. For example, in high temperature and high humidity environment (T=45℃, H=85%, P clog =20%), ΔPm =+0.25,P opt Up to 275℃; low temperature dry environment (T=10℃, H=30%, P clog =5%), ΔP m =-0.1, P opt is 198°C. Comparison with the traditional linear model: index Linear Model Gaussian process regression model Prediction Error (MSE) 0.045 0.012 Reduced congestion rate 18% 42% Parameter sensitivity High (manual calibration coefficient required) Low (adaptive nonlinear relationship) In terms of exception handling and robustness design, when input parameters exceed historical distributions or model confidence falls below 90%, conservative adjustment mode is activated and the system switches to the expert experience rule base, respectively. Furthermore, model parameters are automatically updated for every 1,000 new print task data entries to account for changes such as equipment aging and toner batch variations. In technical drawings, 3D surface plots and influence curves visualize nonlinear relationships. In summary, this embodiment, through the Gaussian process regression model and dynamic compensation mechanism, achieves highly adaptive toner melting point parameters for complex industrial environments. This demonstrates excellent prediction accuracy, failure rate control, and resource conservation, providing a key guarantee for the stable and reliable operation of manufacturing printing systems.

[0027] In one embodiment, the step of calculating the adjustment value of the printing speed includes: When the dust concentration of the print head exceeds the limit, the print speed adjustment coefficient is calculated according to the inverse proportionality rule based on the proportional relationship between the current dust concentration and the preset threshold; If the print speed adjustment factor is lower than 50% of the nominal default print speed of the device, the print speed adjustment factor is set to 50% of the default print speed, and a print speed adjustment value is generated.

[0028] Specifically, the dust concentration threshold The settings are dynamically adjusted according to the printer model and workshop environment. For example, in a standard workshop (dust concentration baseline ≤ 100μg / m³) ; High dust workshop (such as wood processing) , when the real-time dust concentration When the speed adjustment coefficient is calculated according to the formula for: in, The speed is the nominal speed. The higher the dust concentration is, the lower the printing speed is inversely proportional to reduce the amount of dust entering the print head per unit time. Set the speed lower limit protection, forced setting , to avoid production stagnation or increased mechanical wear caused by too low speed; experiments show that when the speed is less than 50% of the nominal value, the torque fluctuation of the paper feed motor increases by 3 times, and the probability of paper jam increases to 12%. The raw dust concentration data collected by the sensor is filtered with a sliding window mean (window size = 10 seconds) to eliminate instantaneous fluctuation interference; if three consecutive sampling cycles , triggering an emergency stop and starting the print head self-cleaning procedure (such as high-pressure air purging). Convert to stepper motor pulse frequency (k is the motor characteristic constant).

[0029] In the specific implementation, a packaging printing workshop (dust concentration range 50-600μg / m³, nominal speed , the effect comparison is as follows: Dust concentration range Traditional solution (fixed speed) Dynamic adjustment scheme of the present invention ≤ 80 pages / minute, 5% jam rate 80 pages / minute, 5% jam rate =2 80 pages / minute, 28% jam rate 40 pages / minute, 9% jam rate =3 Shutdown maintenance 50% speed + self-cleaning, 15% clogging rate Set threshold adaptive calibration, monthly statistical analysis of actual dust concentration distribution, automatic update If a new production line is added to the workshop and the dust baseline increases, the system will automatically identify it and prompt for threshold revisions. Set up a fault fallback mechanism to switch to conservative mode when the dust sensor fails. , ensuring basic safe operation; abnormal events are recorded, maintenance work orders are generated, and pushed to the workshop management system. This embodiment uses an inversely proportional dynamic speed reduction strategy and a speed limit protection mechanism to intelligently balance printing efficiency and equipment reliability when dust concentration exceeds the limit, eliminating the drawbacks of blind speed reduction or forced shutdown in traditional solutions.

[0030] In one embodiment, the step of calculating the adjustment value of the paper preheating temperature includes: Real-time measurement of paper moisture content through near-infrared spectroscopy sensor; Calculate the preheating temperature adjustment value based on the workshop air humidity value, paper moisture content and the preset paper type compensation coefficient; If the preheating temperature adjustment value is lower than 60°C, the preheating temperature adjustment value is set to 60°C.

[0031] Specifically, a short-wave near-infrared sensor (wavelength range 900-1700nm) is installed at the entrance of the printer's paper feed channel, maintaining a 5mm distance from the paper surface. When each batch of paper enters for the first time, a baseline calibration is automatically performed: the spectral signal of the dry reference paper (moisture content ≤ 3%) is measured, and the ambient light interference is dynamically corrected. It supports a library of common paper types (kraft paper, coated paper, thermal paper, etc.), and can automatically update and load other types of paper. The absorption characteristic curves of different papers are preset, and the workshop air humidity H and paper moisture content collected in step S1 are automatically calibrated. (real-time measurement value of near infrared sensor) and paper type compensation coefficient (According to the paper material table (such as kraft paper k type =+5℃, thermal paper k type =-3℃) for calculation, dynamic preheating temperature The calculation formula is: ,in, Determined by thermodynamic experiments ; Set the lower limit protection of temperature, forced setting , preventing low temperatures from causing paper to become damp and sticky or poor toner adhesion. Preheating control execution and verification: A PID algorithm is used to adjust the power of the ceramic heater, with a response time of ≤5 seconds; a patch thermocouple is used to monitor the surface temperature of the preheating roller in real time and dynamically correct the heating instructions. For abnormal handling, if the near-infrared sensor fails, a simplified model based on ambient humidity is used: Abnormal events are recorded and maintenance alerts are triggered. If the moisture content varies by more than ±5% for three consecutive times, printing is paused and a paper batch abnormality check prompt is issued. This embodiment utilizes real-time near-infrared moisture content measurement and a multi-parameter dynamic compensation model to precisely control paper preheating temperature, resolving paper jams and print quality issues caused by a mismatch between ambient humidity and the actual moisture content of the paper, a common problem in traditional solutions.

[0032] In one embodiment, for step S3, The step of optimizing the control instruction set by using a control algorithm model includes: Based on real-time data collected from heating unit temperature, workshop air humidity, print head dust concentration, paper moisture content, toner level, and print head temperature, as well as historical environmental parameters, control instruction execution records, and print quality score datasets, a control algorithm model is used to generate candidate instruction sets for heating control, motor drive control, and preheating control. scoring the candidate instruction sets based on the print quality simulation results; According to the scoring results, the instruction set with the highest long-term printing stability score is selected as the final control instruction set through the Q-learning algorithm.

[0033] In the specific implementation process, the control algorithm model architecture is a hybrid model of GAN (Generative Adversarial Network) and DRL (Deep Reinforcement Learning). In the generator network (Generator), the real-time collected heating unit temperature, workshop air humidity, print head dust concentration, paper moisture content, toner remaining, print head temperature data, as well as historical environmental parameters (temperature, humidity, dust concentration change trend in the past 24 hours), control instruction execution records (heating power, print speed adjustment value) and print quality score (paper jam rate, toner adhesion uniformity) data set are used as model inputs to output candidate instruction sets, such as input heating control temperature , motor drive speed , preheating temperature Output candidate instruction 1 and candidate instruction 2: 、 The network structure is a 3-layer fully connected neural network (256-128-64 nodes), and the activation function is LeakyReLU. Discriminator network (Discriminator): The input is the candidate instruction set and simulation results (toner uniformity, paper jam probability, energy consumption), and the output is the print quality score , the scoring rules are . The network structure is symmetrical with the generator, and the last layer is a Sigmoid function. Based on thermodynamics and fluid mechanics models, the printing effects under different instruction sets are simulated. Specifically, it includes calculating the matching degree between the diffusion coefficient of the toner in the high-temperature molten state and the surface roughness of the paper to evaluate the uniformity of toner adhesion; predicting the risk of paper jams through the Logistic regression model based on the preheating temperature, motor speed and paper moisture content; statistically analyzing the power consumption of the heating unit and the motor, and calculating the energy consumption per printed page (Wh / page) to evaluate the energy efficiency ratio. In the Q-learning reinforcement learning decision, the state space and action space are defined: ; ; Reward Function , where the long-term stability factor is the normalized value of the inverse of the number of interruptions to the printing task in the past 24 hours; the parameter adjustment amplitude penalty is the sum of the absolute values ​​of the difference between the control instruction and the previous instruction, in order to prevent frequent and drastic adjustments. The action value function is updated through the Q-learning algorithm , selects the instruction set that maximizes the long-term cumulative reward, which is used to balance immediate and future rewards.

[0034] Perform instruction set analysis and signal conversion. For heating control instructions , converted into PWM (pulse width modulation) signal to control the power of the ceramic heater. The formula is , where K p is the PID proportional coefficient, The current real-time temperature value of the printer heating unit is collected by a patch thermocouple or infrared temperature sensor; for the motor drive instruction C s When converting the adjusted speed into a motor control signal, the pulse frequency needs to be calculated based on the proportional relationship of the nominal speed to ensure that the instruction matches the hardware. The formula is , The default printing speed of the printer is factory-declared, for example, 100 pages per minute (the specific value varies depending on the device model). Is the basic pulse frequency; for the preheating control instruction C p The temperature of the preheating roller is controlled by the on-off time of the solid-state relay (SSR). The formula is: , where 60 is the lower limit of the preheating temperature (to prevent condensation), 20 is the linear scaling factor (to convert the temperature difference into a time increment), and 100ms is the time base unit (which needs to be calibrated according to the power of the heating element). Real-time collection of print quality data after execution (such as toner uniformity image analysis, paper jam sensor signal), if the actual effect deviates from the simulation score by more than 15%, trigger online model fine-tuning, including updating the generator and discriminator weights (learning rate , adjust the reward function weight (for example, increase the energy efficiency ratio coefficient). If the instruction set execution fails three times in a row (such as paper jam, toner not melting), it switches to safe mode, uses factory default parameters, and runs at a 50% speed reduction. At the same time, it sends a fault code to the operation and maintenance platform, requesting manual intervention.

[0035] Reference Figure 2 , is a structural block diagram of a printing troubleshooting and configuration optimization system applicable to a manufacturing environment in one embodiment of the present invention, comprising: Data acquisition unit, used to collect workshop environmental parameters in real time; An instruction generation unit is used to determine if environmental parameters exceed the limit, synchronously calculate the adjustment values ​​of the toner melting point, printing speed and paper preheating temperature, and generate a corresponding control instruction set; The instruction execution unit is used to optimize the control instruction set through a control algorithm model and drive the printer to perform dynamic adjustment.

[0036] For the specific implementation of each unit in the above device example, please refer to the above method embodiment, which will not be repeated here.

[0037] Reference Figure 3 In an embodiment of the present invention, a computer device is also provided. The computer device may be a server, and its internal structure may be as follows: Figure 3 As shown. The computer device includes a processor, memory, display screen, input device, network interface and database connected via a system bus. The processor of the computer design is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store the corresponding data in this embodiment. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, the above method is implemented.

[0038] Those skilled in the art will understand that Figure 3 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present invention and does not constitute a limitation on the computer device to which the solution of the present invention is applied.

[0039] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which implements the above-described method when executed by a processor. It is understood that the computer-readable storage medium in this embodiment can be a volatile readable storage medium or a non-volatile readable storage medium.

[0040] In summary, the present invention collects workshop environmental parameters in real time, including heating unit temperature, workshop air humidity, and print head dust concentration data; determines whether the environmental parameters exceed the limit, synchronously calculates the adjustment values ​​of the toner melting point, printing speed, and paper preheating temperature, and generates a corresponding control instruction set; optimizes the control instruction set through a control algorithm model, drives the printer to perform dynamic adjustments, and realizes adaptive optimization of printing parameters in complex industrial environments, thereby ensuring stable operation of the printing system and reducing the failure rate.

[0041] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing the relevant hardware using a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the above-described method embodiments. Any reference to memory, storage, database, or other media provided herein and used in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double-speed SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct RAMbus dynamic RAM (DRDRAM), and RAMbus dynamic RAM.

[0042] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, apparatus, article, or method comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, apparatus, article, or method. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, apparatus, article, or method comprising the element.

Claims

1. A printing troubleshooting and configuration optimization method suitable for a manufacturing environment, characterized in that: The following steps are involved: Real-time collection of workshop environmental parameters, including heating unit temperature, workshop air humidity, and print head dust concentration data; Determine if environmental parameters exceed the limit, calculate the adjustment values ​​of toner melting point, printing speed and paper preheating temperature simultaneously, and generate the corresponding control instruction set; The control instruction set is optimized by a control algorithm model to drive the printer to perform dynamic adjustments.

2. The printing troubleshooting and configuration optimization method applicable to the manufacturing environment according to claim 1 is characterized in that: The step of collecting workshop environmental parameters in real time includes: The infrared temperature sensor is used to collect the ambient temperature of the printer's heating unit in real time; The workshop air humidity value and heating unit temperature reference value are collected synchronously through temperature and humidity sensors; The laser scattering dust sensor is used to collect the dust concentration value in the print head working area simultaneously; The original electrical signals output by each sensor are denoised, and the characteristic signals in the 0.5-10kHz frequency band are extracted to generate a denoised environmental parameter dataset.

3. The printing troubleshooting and configuration optimization method applicable to the manufacturing environment according to claim 1, characterized in that: The step of determining whether the environmental parameters exceed the limit includes: Based on the collected data on heating unit temperature, workshop air humidity, and print head dust concentration, the LSTM neural network predicts the changing trends of heating unit temperature and workshop air humidity within the next 24 hours, and dynamically adjusts the heating unit temperature threshold, workshop air humidity threshold, and print head dust concentration threshold. Compare the environmental parameters collected in real time with the corresponding adjusted thresholds; If the real-time collected heating unit temperature is greater than the adjusted heating unit temperature threshold, the temperature is determined to be out of limit; if the real-time collected workshop air humidity is greater than the adjusted workshop air humidity threshold, the humidity is determined to be out of limit; if the real-time collected print head dust concentration is greater than the adjusted print head dust concentration threshold, the dust concentration is determined to be out of limit.

4. The printing troubleshooting and configuration optimization method applicable to a manufacturing environment according to claim 1, characterized in that: The step of calculating the adjustment value of the toner melting point includes: When the heating unit temperature or workshop air humidity exceeds the limit, the workshop air humidity value, heating unit temperature value and historical print head clogging probability are mapped into the toner melting point compensation coefficient based on the nonlinear regression model; A toner melting point adjustment value is generated according to the toner melting point compensation coefficient.

5. The printing troubleshooting and configuration optimization method applicable to a manufacturing environment according to claim 1, characterized in that: The step of calculating the adjustment value of the printing speed includes: When the dust concentration of the print head exceeds the limit, the print speed adjustment coefficient is calculated according to the inverse proportionality rule based on the proportional relationship between the current dust concentration and the preset threshold; If the print speed adjustment factor is lower than 50% of the nominal default print speed of the device, the print speed adjustment factor is set to 50% of the default print speed, and a print speed adjustment value is generated.

6. The printing troubleshooting and configuration optimization method applicable to a manufacturing environment according to claim 1, characterized in that: The step of calculating the adjustment value of the paper preheating temperature includes: Real-time measurement of paper moisture content through near-infrared spectroscopy sensor; Calculate the preheating temperature adjustment value based on the workshop air humidity value, paper moisture content and the preset paper type compensation coefficient; If the preheating temperature adjustment value is lower than 60°C, the preheating temperature adjustment value is set to 60°C.

7. The printing troubleshooting and configuration optimization method applicable to a manufacturing environment according to claim 1, characterized in that: The step of optimizing the control instruction set by using a control algorithm model includes: Based on real-time data collected from heating unit temperature, workshop air humidity, print head dust concentration, paper moisture content, toner level, and print head temperature, as well as historical environmental parameters, control instruction execution records, and print quality score datasets, a control algorithm model is used to generate candidate instruction sets for heating control, motor drive control, and preheating control. scoring the candidate instruction sets based on the print quality simulation results; According to the scoring results, the instruction set with the highest long-term printing stability score is selected as the final control instruction set through the Q-learning algorithm.

8. A printing troubleshooting and configuration optimization system suitable for a manufacturing environment, characterized in that: include: Data acquisition unit, used to collect workshop environmental parameters in real time; An instruction generation unit is used to determine if environmental parameters exceed the limit, synchronously calculate the adjustment values ​​of the toner melting point, printing speed and paper preheating temperature, and generate a corresponding control instruction set; The instruction execution unit is used to optimize the control instruction set through a control algorithm model and drive the printer to perform dynamic adjustment.

9. A computer device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the processor executes the computer program, the steps of the printing troubleshooting and configuration optimization method applicable to the manufacturing environment as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the printing fault troubleshooting and configuration optimization method applicable to a manufacturing environment according to any one of claims 1 to 7 are implemented.

Images