Control method of veneer peeling equipment

Abstract

The present application provides a control method for veneer peeling equipment, which relates to the field of automated control technology. A sensor device group is used to perform data sensing on the logs to be peeled, and the initial diameter data of the logs is extracted through multi-sensor fusion and peeling calculations are performed to generate multiple peeling control parameters; based on multiple peeling control parameters, the veneer peeling equipment is simulated and controlled to generate simulated dynamic peeling results and perform defect detection and abnormality tracing, generating multiple abnormal data sources; based on multiple abnormal data sources, multiple peeling control parameters are updated and optimized, and peeling control plans are formulated and executed; the veneer peeling equipment is monitored in real time, deviation feedback is performed based on the real-time operating parameter set, and the peeling control plan is dynamically adjusted based on the feedback results. The present application solves the technical problem that the existing veneer peeling equipment control relies on manual experience, resulting in limited peeling accuracy and finished product quality, and significantly improves the peeling accuracy and product quality.

Description

Technical Field

[0001] The present application relates to the field of automation control technology, and in particular to a control method for single-board peeling equipment. Background Art

[0002] The veneer peeling machine is a key equipment for producing plywood. It is mainly used to process wood segments of a certain length and diameter into continuous veneer strips, and then cut them into veneers of certain specifications. Although the traditional veneer peeling machine is powerful, there are still many technical problems in actual operation, which limit its efficiency and product quality.

[0003] Traditional veneer peeling control methods usually rely on preset fixed parameters and manual adjustments, which have certain limitations when processing logs of different sizes and shapes. Due to the lack of accurate log size measurement and dynamic adjustment capabilities, the peeled boards often have uneven thickness, rough surfaces, and even defects. Since the parameter settings in the peeling process often rely on the operator's experience and lack scientific basis, it is easy to have unreasonable parameter settings and lead to quality problems. In addition, traditional equipment usually lacks effective real-time monitoring and dynamic adjustment capabilities. When abnormal situations occur during the peeling process, they cannot be detected and corrected in time, resulting in an increase in defects and a decrease in production efficiency. Summary of the invention

[0004] The present application provides a control method for single-board peeling equipment, which solves the technical problem that the existing single-board peeling equipment control relies on manual experience, resulting in limited peeling accuracy and finished product quality, and achieves the technical effect of significantly improving peeling accuracy and product quality.

[0005] In view of the above problems, the present application provides a control method for veneer peeling equipment, the method comprising: using a sensor device group to perform data sensing on the logs to be peeled, and performing multi-sensor fusion on the sensor data set to extract the initial diameter data of the log; performing peeling calculation based on the initial diameter data of the log, and generating multiple peeling control parameters; performing simulation control on the veneer peeling equipment based on the multiple peeling control parameters, and generating simulated dynamic peeling results; performing defect detection according to the simulated dynamic peeling results, tracing the source of abnormalities according to the detection results, and generating multiple abnormal data sources; updating and optimizing the multiple peeling control parameters based on the multiple abnormal data sources, generating multiple peeling control optimization parameters, and formulating a peeling control plan; activating the veneer peeling equipment to execute the peeling control plan, and performing real-time monitoring of the veneer peeling equipment to obtain a real-time operating parameter set of the veneer peeling equipment; performing deviation feedback according to the real-time operating parameter set, and dynamically adjusting the peeling control plan according to the feedback results to perform intelligent control on the veneer peeling equipment.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] The sensor equipment group is used to perform data sensing on the logs to be peeled, and the sensor data set is subjected to multi-sensor fusion to extract the initial diameter data of the log, accurately obtain the size information of the log, and provide basic data for subsequent peeling calculations. Peeling calculations are performed based on the initial diameter data of the log, and multiple peeling control parameters are generated. These parameters are the key to guiding the operation of the veneer peeling equipment and determine the quality and efficiency of peeling. The veneer peeling equipment is simulated and controlled based on the multiple peeling control parameters to generate simulated dynamic peeling results, and the peeling effect is predicted without actually running the equipment, providing a basis for optimizing the control scheme. Defect detection is performed based on the simulated dynamic peeling results to find out possible problems, and abnormality tracing is performed based on the detection results to generate multiple abnormal data sources; based on the multiple abnormal data sources, the multiple peeling control parameters are updated and optimized to generate multiple peeling control optimization parameters, and a peeling control scheme is formulated to provide accurate and reliable guidance and decision-making for peeling operations. Activate the veneer peeling device to execute the peeling control scheme, monitor the veneer peeling device in real time, obtain the real-time operating parameter set of the veneer peeling device, and monitor the execution effect of the peeling control scheme in real time. Perform deviation feedback according to the real-time operating parameter set, dynamically adjust the peeling control scheme according to the feedback result, perform intelligent control on the veneer peeling device, and respond to the state changes during the peeling operation in a timely manner.

[0008] To summarize, this application improves the accuracy of log diameter data through multi-sensor fusion technology, thereby providing a more reliable data basis for subsequent peeling calculations; through simulation control and defect detection, problems that may arise during the peeling process are discovered and resolved in a timely manner, thereby optimizing the peeling control parameters and improving the quality and efficiency of peeling; through real-time monitoring and deviation feedback, intelligent control of veneer peeling equipment is achieved, and the control scheme can be dynamically adjusted according to actual conditions, further improving the automation and intelligence level of peeling.

[0009] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 A flow chart of a control method for single-board peeling equipment provided in an embodiment of the present application.

[0011] Figure 2 A schematic diagram of the process of defect detection in the single plate peeling equipment control method provided in an embodiment of the present application.

[0012] Figure 3A schematic diagram of a flow chart for formulating a peeling control scheme in a single-board peeling equipment control method provided in an embodiment of the present application.

[0013] Figure 4 A schematic flow chart of dynamically adjusting the peeling control scheme in the single-board peeling equipment control method provided in an embodiment of the present application. DETAILED DESCRIPTION

[0014] The embodiment of the present application provides a control method for single-board peeling equipment, and comprehensively applies multi-sensor fusion, analog control and intelligent feedback mechanism to solve the technical problem that the existing control of single-board peeling equipment relies on manual experience, resulting in limited peeling accuracy and finished product quality, thereby achieving the technical effect of significantly improving peeling accuracy and product quality.

[0015] like Figure 1 As shown, the embodiment of the present application provides a control method for a veneer peeling device, the method comprising:

[0016] Step S10: using a sensor device group to perform data sensing on the logs to be peeled, and performing multi-sensor fusion on the sensor data set to extract the initial diameter data of the logs.

[0017] Specifically, the sensor equipment group refers to a collection of multiple sensors, including multiple sensors such as laser rangefinders, cameras, ultrasonic sensors, etc., which are used to measure different physical properties of logs. Multi-sensor fusion of the sensor equipment group is to comprehensively process data from different sensors to obtain more accurate and comprehensive information.

[0018] First, a sensor device group is used to collect data on the logs to be peeled to obtain a sensor data set, where the sensor data set is the original data on the size and shape of the logs collected by the sensor device group. The sensor data set is processed by multi-sensor fusion technology, and the data from different sensors are combined to extract the initial diameter data of the logs. The multi-sensor fusion method can use multi-sensor data fusion algorithms such as Kalman filter, Bayesian estimation, and DS evidence reasoning to optimize the measurement results and improve the measurement accuracy. Multi-sensor fusion can accurately obtain the size information of the logs and provide basic data for subsequent peeling calculations.

[0019] Furthermore, step S10 of the embodiment of the present application further includes:

[0020] Step S11: Determine a plurality of sensing collection points according to the structure of the log to be peeled and the measurement requirements.

[0021] Step S12: deploying a plurality of sensor devices based on the plurality of sensor collection points to obtain the sensor device group.

[0022] Step S13: starting the sensor equipment group to perform data sensing on the logs to be peeled, and generating the sensor data set.

[0023] Step S14: extracting features from the sensor data set to determine a plurality of feature vectors.

[0024] Step S15: Associating the multiple feature vectors according to timestamps to generate a feature association factor.

[0025] Step S16: fusing the multiple feature vectors based on the feature association factor to obtain the initial diameter data of the log.

[0026] Specifically, the sensor collection points refer to multiple locations selected on the log to be peeled, where sensors are placed for data collection. The selection of these locations is based on the structure of the log to be peeled, including diameter, length, shape, etc., as well as measurement requirements such as the accuracy of the diameter data. In order to fully understand the physical characteristics of the log, the two ends, the middle, and some surface and internal locations of the log can be selected. For example, a collection point is selected every 10 cm on the log.

[0027] Multiple sensing devices are deployed at the selected collection points to form a sensing device group. For example, laser scanners are placed at both ends of the log to measure the diameter and surface profile, cameras are placed on the surface of the log for texture analysis, and ultrasonic sensors are placed inside the log to evaluate the density. These sensors can comprehensively obtain external and internal information of the log. The sensing device group is started to sense the data of the peeled log. Each sensor works simultaneously, records the data collected by each sensor, and generates a sensing data set.

[0028] Perform feature extraction on the sensor data set to determine multiple feature vectors. Feature extraction can use data processing algorithms, such as principal component analysis for dimensionality reduction and cluster analysis for classification. Feature vectors are numerical vectors that represent key features of logs. For example, a feature vector for log diameter may include information such as diameter size and position. Extract feature vectors for log diameter from laser scanning data, feature vectors for log surface defects from image data, and density from ultrasonic sensor data. The extracted feature vector may be {diameter = 20cm, texture = cracks, density = 0.9g / cm³}.

[0029] Multiple feature vectors are associated according to timestamps to generate feature association factors. Time synchronization algorithms such as linear interpolation or Kalman filtering are used to ensure the temporal consistency of each feature vector. Timestamp is a time mark for data collection, which is used to maintain data consistency and synchronization. Feature association factor is a data structure used to associate different feature vectors. Based on the feature association factor, multiple feature vectors are fused to obtain the initial diameter data of the log. This process can use multi-sensor fusion algorithms such as Kalman filtering, Bayesian estimation, and DS evidence reasoning. By fusing data from multiple sensors, more accurate log size information can be obtained, improving data accuracy and stability.

[0030] Step S20: performing peeling calculation based on the log initial diameter data to generate a plurality of peeling control parameters.

[0031] Specifically, peeling calculation refers to the use of algorithms and models to calculate the optimal peeling path and speed and other parameters based on the diameter data of the log. Peeling calculation is performed based on the extracted initial diameter data of the log. Use software such as finite element analysis and computer numerical simulation to simulate and optimize the peeling process and generate peeling control parameters. Peeling control parameters include specific operating parameters such as peeling speed, tool feed, and peeling angle. For example, assuming that the initial diameter of the log is 19.9 cm, the peeling calculation shows that the optimal peeling speed is 5 m / s, the tool feed is 2 mm, and the peeling angle is 15 degrees.

[0032] Furthermore, step S20 of the embodiment of the present application further includes:

[0033] Step S21: determining the peeling start position and the peeling end position according to the log initial diameter data and the structure of the log to be peeled.

[0034] Step S22: planning a peeling path based on the peeling start position and the peeling end position.

[0035] Step S23: Calculate the peeling thickness information according to the peeling path and the peeling depth, dynamically update the initial diameter data of the log according to the peeling thickness and the peeling speed, and generate a diameter dynamic change parameter.

[0036] Step S24: determining the log center based on the initial log diameter, recording data according to the diameter dynamic change parameter combined with the log center, and determining the plurality of rotary cutting control parameters.

[0037] Specifically, the starting position and ending position of peeling are determined based on the initial diameter data of the log and the structure of the log to be peeled. The starting position of peeling refers to the position of the log where the peeling process starts, usually selected at one end of the log. The ending position of peeling refers to the position of the log where the peeling process ends, usually selected at the other end of the log. Based on the determined starting and ending positions of peeling, the peeling path is planned. Among them, the peeling path is the tool movement trajectory from the starting position to the ending position, which is used to guide the peeling operation. Using computer numerical control software such as Mastercam or SolidWorks, the movement trajectory of the tool can be simulated and planned to ensure that the tool peels along the optimal path. For example, path planning can ensure that the tool moves in a straight line at a uniform speed to minimize errors.

[0038] The peeling depth is the depth of the cutter into the log each time, which determines the thickness of the veneer. According to the planned peeling path, the peeling thickness information is calculated in combination with the peeling depth. The peeling thickness information describes the thickness of each peeling and is used to dynamically adjust the peeling parameters. Assuming that the peeling depth is 2 mm each time, the thickness of each peeling can be simulated and calculated by finite element analysis (FEA) software such as ANSYS. At the same time, the initial diameter data of the log is dynamically updated according to the peeling speed to generate dynamic diameter change parameters. For example, the diameter of the log after each peeling is reduced from 20 cm to 19.8 cm, and then to 19.6 cm. These dynamically changing parameters are used to adjust the peeling operation in real time.

[0039] The log center is determined based on the initial log diameter. The center point of the log is calculated using a geometric algorithm as a reference for peeling. For example, for a cylindrical log, its center point can be determined by calculating the midpoint of the diameter and length. Based on the dynamic diameter change parameter combined with the log center, multiple peeling parameters during the peeling process are recorded, i.e., multiple peeling control parameters, including peeling speed, tool feed rate, and peeling angle.

[0040] Through the above steps, the veneer peeling equipment can accurately determine the peeling path and control parameters, realize the fine planning and control of the peeling process, and ensure the efficiency and accuracy of the peeling operation.

[0041] Step S30: performing simulation control on the single board peeling equipment based on the multiple peeling control parameters to generate a simulated dynamic peeling result.

[0042] Specifically, simulation control refers to operating the equipment in a virtual environment to verify and optimize the control parameters. The simulated dynamic peeling results refer to the output results of the peeling process in a virtual environment, including the quality of the veneer, the peeling path, etc. The veneer peeling equipment is simulated and controlled using simulation software such as ANSYS, MATLAB Simulink, etc., based on the peeling control parameters generated in the previous step. By simulating the peeling process, simulated dynamic peeling results are generated. These results can be used to analyze the quality of the veneer and the stability of the peeling process. For example, through simulation, it was found that the surface of the veneer was smooth and had no obvious defects when the peeling speed was 5 m / s, which indicated that the control parameters were set reasonably.

[0043] Step S40: performing defect detection according to the simulated dynamic peeling result, tracing the abnormality source according to the detection result, and generating multiple abnormal data sources.

[0044] Specifically, defect detection is performed based on the simulated dynamic peeling results, that is, identifying flaws and problems generated during peeling. Image processing algorithms and machine learning models can be used to automatically identify defects on single boards. Subsequently, abnormality tracing is performed, that is, tracking and determining the cause of the defect. By analyzing the detection results, the cause of the defect is determined. For example, if a crack is detected on the edge of a single board, abnormality tracing is found to be caused by excessive tool feed.

[0045] Further, such as Figure 2 As shown, step S40 in the embodiment of the present application also includes:

[0046] Step S41: drawing a log diameter change curve based on the simulated dynamic peeling result and the diameter dynamic change parameter.

[0047] Step S42: drawing a peeling speed variation curve based on the simulated dynamic peeling result and the plurality of peeling control parameters.

[0048] Step S43: performing data processing according to the log diameter variation curve and the rotary cutting speed variation curve, and extracting the abnormal diameter reduction point and the rotary cutting speed mutation point.

[0049] Step S44: Retrieving the historical peeling record data file to set the defect recognition standard, wherein the defect recognition standard includes a preset diameter change rate and a preset rotation speed fluctuation range.

[0050] Step S45: Determine whether the point of abnormal diameter reduction meets the preset diameter change rate, and whether the rotary cutting speed mutation point is within the preset speed fluctuation range.

[0051] Step S46: If the abnormal diameter reduction point does not conform to the preset diameter change rate, and the rotary cutting speed mutation point is in the preset speed fluctuation range, then an abnormal log diameter parameter is generated according to the abnormal diameter reduction point, and the abnormal log diameter parameter is added to the detection result.

[0052] Step S47: If the abnormal diameter reduction point meets the preset diameter change rate, and the peeling speed mutation point is not in the preset speed fluctuation range, an abnormal peeling speed parameter is generated according to the peeling speed mutation point, and the abnormal peeling speed parameter is added to the detection result.

[0053] Step S48: If the abnormal diameter reduction point does not conform to the preset diameter change rate, and the rotary cutting speed mutation point is not in the preset speed fluctuation range, the log diameter abnormality parameter is generated according to the abnormal diameter reduction point, the rotary cutting speed abnormality parameter is generated according to the rotary cutting speed mutation point, and the log diameter abnormality parameter and the rotary cutting speed abnormality parameter are added to the detection result.

[0054] Specifically, the log diameter change curve is a curve reflecting the change of log diameter over time during the peeling process. The peeling speed change curve is a curve reflecting the change of tool speed over time during the peeling process. Using data visualization tools such as Matplotlib or Tableau, the simulated dynamic peeling results and the diameter dynamic change parameters are combined to generate the log diameter change curve. Using the same data visualization tool, the simulation results and control parameters are combined to generate the peeling speed change curve. For example, during the peeling process, the diameter data is recorded every 1 second to generate a curve that changes over time. The speed data is recorded every 1 second to generate a curve that changes over time. The drawn curves are processed by data analysis tools such as Python, R, etc. to extract the abnormal diameter reduction points and peeling speed mutation points. The abnormal diameter reduction point is the time point when the log diameter decreases abnormally and significantly during the peeling process. The peeling speed mutation point is the time point when the tool speed changes abnormally and suddenly during the peeling process.

[0055] Defect identification standards are used to determine whether there are defects in the peeling process, including the preset diameter change rate and the preset speed fluctuation range. Retrieve the historical peeling record data archive and set the defect identification standards based on the historical data, including the preset diameter change rate and the preset speed fluctuation range. For example, set the preset diameter change rate to 0.5 cm / s and the preset speed fluctuation range to ±500 rpm. Historical data can be stored in the database and extracted through SQL queries.

[0056] The log diameter abnormality parameter is a parameter that describes the abnormal change of log diameter. The peeling speed abnormality parameter is a parameter that describes the abnormal change of peeling speed. According to the set defect recognition standard, it is judged whether the abnormal diameter reduction point and the peeling speed mutation point meet the preset standard, and the corresponding abnormal parameters are generated accordingly. The specific judgment process is as follows: If the abnormal diameter reduction point does not meet the preset diameter change rate, and the peeling speed mutation point is in the preset speed fluctuation range, the log diameter abnormality parameter is generated according to the abnormal diameter reduction point, and it is added to the detection result. If the abnormal diameter reduction point meets the preset diameter change rate, and the peeling speed mutation point is not in the preset speed fluctuation range, the peeling speed abnormality parameter is generated according to the peeling speed mutation point, and it is added to the detection result. If the abnormal diameter reduction point does not meet the preset diameter change rate, and the peeling speed mutation point is not in the preset speed fluctuation range, the log diameter abnormality parameter is generated according to the abnormal diameter reduction point, and the peeling speed abnormality parameter is generated according to the peeling speed mutation point, and both are added to the detection result.

[0057] Through the above steps, in-depth analysis and defect detection of simulated dynamic peeling results are achieved, and corresponding abnormal parameters are generated to ensure the accuracy and timeliness of defect detection. It is helpful to timely discover and solve abnormal situations in the peeling process.

[0058] Furthermore, step S40 of the embodiment of the present application further includes:

[0059] Based on the abnormal parameters of log diameter and the abnormal parameters of peeling speed, abnormal classification is performed to generate multiple abnormal categories; the correlation between the multiple abnormal categories and multiple data sources is analyzed to build a traceability causal model; and data mining is performed using the traceability causal model to obtain the multiple abnormal data sources.

[0060] Specifically, all detected abnormal parameters are collected. Using machine learning algorithms such as K-means clustering or support vector machines, the abnormal parameters are classified to generate multiple abnormal categories. The abnormal category is the result of classification based on the detected abnormal parameters of log diameter and peeling speed. These abnormal categories usually reflect the problems or abnormal conditions that may occur during the peeling process, including the abnormal diameter reduction category, that is, the log diameter decreases abnormally during the peeling process; the abnormal peeling speed fluctuation category, that is, the rotation speed of the tool fluctuates abnormally during the peeling process; the surface quality abnormal category, that is, abnormal defects or roughness appear on the surface of the peeled veneer, etc.

[0061] By analyzing the association between each anomaly category and different data sources, a traceability causal model is established. The traceability causal model is a model built based on the association between anomaly classification and data sources, and is used to analyze the causes and effects of anomalies. Causal inference algorithms such as Granger causality or Bayesian networks can be used to find out which data sources are significantly associated with which anomaly categories. For example, during the peeling process, if a sudden decrease in the diameter of the log is detected, this may be caused by wear of the cutting tool, excessive cutting speed, or internal defects in the log. If the peeling speed is detected to fluctuate violently in a short period of time, this may be caused by equipment failure, unstable power supply, or operational errors. If cracks, pits, or excessive roughness appear on the surface of the peeled veneer, this may be caused by improper tool adjustment, log defects, or unreasonable peeling parameter settings.

[0062] Finally, data mining tools such as Hadoop and Spark are used to perform data mining based on the constructed traceability causal model to extract multiple potential abnormal data sources. For example, using association rule mining algorithms such as Apriori or FP-growth, frequently occurring association patterns can be discovered, thereby identifying the root causes of the anomalies.

[0063] Exemplarily, the K-means clustering algorithm can be used to divide the detected multiple diameter anomaly and speed anomaly data points into two categories: one is diameter anomaly and the other is speed anomaly. Analyze the correlation between the diameter anomaly class and the speed anomaly class and different data sources, such as temperature, humidity, tool wear, etc. Use the Bayesian network algorithm to establish the causal relationship between these anomaly categories and the data source. Based on the traceability causal model, use the association rule mining algorithm (such as Apriori) to mine frequently occurring association patterns from historical data. For example, it was found that when the temperature exceeds 30°C, the frequency of diameter anomaly increases significantly; when the tool is used for more than 100 hours, the probability of speed anomaly increases significantly.

[0064] Through the above steps, the detected anomalies can be effectively classified, a traceability causal model can be constructed, and the root causes of the anomalies can be identified using data mining technology.

[0065] Step S50: updating and optimizing the plurality of rotary cutting control parameters based on the plurality of abnormal data sources, generating a plurality of rotary cutting control optimization parameters, and formulating a rotary cutting control plan.

[0066] Specifically, the peeling control optimization parameters refer to the optimized peeling speed, tool feed rate and other parameters. The peeling control scheme refers to the scheme formulated according to the optimized parameters to guide the operation of the veneer peeling equipment. Based on the generated abnormal data source, the peeling control parameters are updated and optimized using optimization algorithms, such as genetic algorithms, particle swarm optimization, etc., to generate the peeling control optimization parameters. Then, a peeling control scheme containing these optimization parameters is formulated. For example, after optimization, the tool feed rate is adjusted to 1.8 mm to avoid crack problems.

[0067] Further, such as Figure 3 As shown, step S50 of the embodiment of the present application also includes:

[0068] Step S51: using the multiple abnormal data sources as indexes, and combining an abnormality detection algorithm to perform abnormality identification on the multiple rotary cutting control parameters to determine multiple abnormal points.

[0069] Step S52: performing abnormality diagnosis based on the multiple abnormal data sources combined with the multiple abnormal points to generate an abnormality diagnosis result.

[0070] Step S53: performing an impact analysis on the plurality of rotary cutting control parameters and the rotary cutting quality according to the abnormality diagnosis result, and generating a parameter impact coefficient.

[0071] Step S54: performing weighted optimization on the plurality of rotary cutting control parameters according to the parameter influence coefficients to generate a plurality of rotary cutting control optimization parameters.

[0072] Step S55: performing simulation verification on the plurality of rotary cutting control optimization parameters, and formulating the rotary cutting control scheme based on the verification results.

[0073] Specifically, anomalies refer to data points that are identified as abnormal in the data set, which usually deviate from the normal value range. Use anomaly detection algorithms such as the Isolation Forest Algorithm or the LOF Algorithm to scan the rotary cutting control parameter data set and identify anomalies. For example, if the tool wear sensor detects that the wear exceeds the threshold, it is marked as an anomaly point; if the temperature sensor detects a sudden temperature rise, it is also marked as an anomaly point.

[0074] Abnormal diagnosis is to determine the cause of the abnormality by analyzing the abnormal points and abnormal data sources. Use diagnostic tools such as cause-and-effect analysis and fault tree analysis to perform abnormal diagnosis, analyze the relationship between the abnormal data source and the abnormal point, determine the cause of the abnormality, and generate abnormal diagnosis results. According to the abnormal diagnosis results, multiple peeling control parameters and peeling quality are analyzed to generate parameter influence coefficients. Regression analysis or multivariate linear regression model is used to quantify the degree of influence of each control parameter on the peeling quality and generate parameter influence coefficients. Among them, the parameter influence coefficient is a coefficient that describes the degree of influence of the peeling control parameter on the peeling quality. For example, the regression analysis model is used to determine that the influence coefficient of the peeling speed on the veneer thickness is 0.8, and the influence coefficient of the tool feed rate on the veneer smoothness is 0.6.

[0075] Using optimization algorithms such as particle swarm optimization or genetic algorithm, multiple control parameters are weighted and adjusted according to the parameter influence coefficients to generate multiple optimized control parameters, namely, peeling control optimization parameters. For example, the peeling speed is adjusted to 4.8 m / s and the tool feed is adjusted to 1.9 mm through the optimization algorithm to optimize the peeling quality.

[0076] Simulation verification refers to the use of computer simulation technology to verify the effect of the optimized parameters of the peeling control. The peeling control scheme is a scheme to guide the peeling process based on the simulation verification results. Using simulation software such as ANSYS or MATLABSimulink, multiple optimized control parameters are simulated and verified to ensure their effectiveness and stability in actual operation, and the peeling control scheme is formulated based on the verification results. For example, the simulation results show that the adjusted peeling speed and tool feed rate show higher efficiency and quality in the simulation environment, verifying the feasibility of the optimized parameters.

[0077] Through the above steps, the veneer peeling equipment can effectively identify abnormalities and optimize control parameters, ensure the efficiency and stability of the peeling process, and achieve precise control and optimization of the peeling process.

[0078] Step S60: activating the veneer peeling device to execute the peeling control scheme, and performing real-time monitoring on the veneer peeling device to obtain a real-time operating parameter set of the veneer peeling device.

[0079] Specifically, the real-time operating parameter set refers to the real-time data set collected when the veneer peeling equipment is running, including data such as equipment running speed, temperature, vibration, etc. The veneer peeling equipment is activated to execute the optimized peeling control scheme, and the equipment is monitored in real time through sensors and monitoring systems to obtain the real-time operating parameter set of the equipment. For example, the temperature of the tool is monitored in real time through a temperature sensor, and the vibration of the equipment is monitored through an accelerometer to ensure stable operation of the equipment.

[0080] Step S70: performing deviation feedback according to the real-time operating parameter set, and dynamically adjusting the peeling control scheme according to the feedback result to perform intelligent control on the single board peeling equipment.

[0081] Specifically, deviation feedback is performed based on the real-time operating parameter set to compare the difference between the actual operating parameters and the expected parameters. Then, according to the feedback results, the automatic control system, such as PLC, DCS, etc., dynamically adjusts the rotary cutting control scheme to achieve intelligent control. For example, if real-time monitoring finds that the rotary cutting speed deviates from the set value, the system automatically adjusts the motor speed to ensure that the rotary cutting speed remains at 5 meters per second.

[0082] Further, such as Figure 4 As shown, step S70 in the embodiment of the present application also includes:

[0083] Step S71: Retrieve the historical operation record data log to set the target operation parameter range.

[0084] Step S72: comparing the real-time operating parameter set with the target operating parameter interval, identifying and extracting the real-time operating parameters that are not in the target operating parameter interval, and calculating the deviation distance value according to the extraction result.

[0085] Step S73: matching the running deviation level according to the deviation distance value, performing deviation feedback according to the matching result, and generating a feedback result.

[0086] Step S74: Determine the target adjustment direction, target adjustment time node, and target adjustment distance based on the feedback result and the expert knowledge base.

[0087] Step S75: dynamically adjusting the rotary cutting control scheme based on the target adjustment direction, the target adjustment time node, and the target adjustment distance.

[0088] Specifically, the historical operation record data log is a data log that records the past operating parameters and status of the equipment, which is used to analyze and set target parameters. The target operating parameter interval is a parameter range set based on the historical operation record data log, and this range represents the ideal operating status. Use database query tools to extract the operating parameter data for a period of time in the past from the historical operation records of the equipment. Use data processing tools, such as Python's Pandas library, to clean the extracted data and remove outliers and missing values. Perform statistical analysis on the cleaned data to calculate the mean, standard deviation, minimum value, maximum value and other statistics of each parameter. Set the target operating parameter interval based on the statistical analysis results. The mean plus or minus a certain multiple of the standard deviation is usually used as the interval range.

[0089] The deviation distance value refers to the difference between the real-time operating parameters and the target operating parameter range. Use the real-time monitoring system to collect the operating parameter data of the current equipment. Compare the real-time operating parameters with the target operating parameter range to identify the parameters that are not in the target range. For the identified deviation parameters, calculate the deviation distance value from the boundary of the target range. According to the different deviation degrees of the equipment operating parameters, multiple deviation levels are defined. The deviation level is a level system divided according to the deviation distance value, which is used to indicate the degree of deviation. For example: slight deviation: deviation distance value <0.1 (unit depends on the specific parameter); medium deviation: 0.1≤deviation distance value <0.3; severe deviation: deviation distance value ≥0.3. Match the calculated deviation distance value with the predefined deviation level. Based on the matched deviation level, generate feedback results to indicate the type and priority of adjustment required. For example, if the peeling speed is a medium deviation and the tool temperature is a severe deviation, the feedback result may indicate that the tool temperature needs to be adjusted first.

[0090] Use query tools such as SQL or machine learning models to extract relevant knowledge from the expert knowledge base. For each deviation parameter, combine the feedback results and the suggestions in the expert knowledge base to determine the target adjustment direction and adjustment distance, and combine the knowledge base suggestions and real-time operating status to determine the best adjustment time node. The target adjustment direction refers to the adjustment direction recommended in the deviation feedback, such as increasing or decreasing a parameter value. The target adjustment time node refers to the best time to implement the adjustment. The target adjustment distance refers to the size of the parameter value that needs to be adjusted. Use the PLC or DCS control system to automatically perform adjustment operations based on the determined adjustment direction, time node and distance. After the adjustment, the real-time monitoring system continuously tracks the equipment operating parameters, verifies the adjustment effect, and ensures that the equipment returns to the target range.

[0091] Through the above steps, the veneer peeling equipment can achieve real-time monitoring and dynamic adjustment, which helps to improve the stability and quality of the peeling process.

[0092] Furthermore, the embodiment of the present application also includes:

[0093] Extract the single board results peeled by the single board peeling equipment and construct a single board three-dimensional view; perform image detection and analysis based on the single board three-dimensional view to generate a detection and analysis result; automatically divide a plurality of single board levels according to the detection and analysis result, identify the single board results based on the plurality of single board levels, and generate a single board identification result; synchronously map the single board identification result to obtain a single board control effect, evaluate whether the single board control effect reaches an expected threshold, and if not, generate an alarm instruction and send it to the single board peeling equipment for control adjustment.

[0094] Specifically, the veneer three-dimensional view is a three-dimensional image constructed through 3D modeling technology based on the veneer result obtained by rotary cutting, which is used to show the shape and structure of the veneer. Image detection and analysis analyzes and detects the veneer three-dimensional view to identify quality problems or defects of the veneer. The veneer grade is to divide the veneer into different quality grades, such as high-quality, medium, and defective, based on the detection and analysis results. The veneer identification result is the result of identifying each veneer based on the veneer grade, which is used to track and manage the quality of the veneer. The veneer control effect is to evaluate whether the quality of the veneer and the control effect of the rotary cutting equipment meet the expected standards. The alarm instruction refers to the instruction generated by the system when the veneer control effect does not reach the expected threshold, prompting that the rotary cutting equipment needs to be adjusted.

[0095] First, a laser scanner or structured light scanner is used to scan the veneer cut out to obtain its three-dimensional data. These data are processed by three-dimensional modeling software such as MeshLab or Blender to construct a three-dimensional view of the veneer. Then, computer vision technology is used to process the three-dimensional view of the veneer to extract surface and internal feature information. Subsequently, a machine learning algorithm is used. For example, a convolutional neural network or a decision tree is used to perform defect detection and feature analysis on the processed image to generate detection and analysis results. Based on these detection and analysis results, the veneers are automatically divided into different grades, such as high-quality, medium and defective, using preset rules or classification algorithms, and the veneers are identified based on these grades to generate veneer identification results. In order to ensure that the quality of the veneer meets expectations, it is also necessary to synchronously map the veneer identification results with the control parameters of the peeling equipment, and evaluate the control effect of the veneer by analyzing these mapping results. If the evaluation result shows that the control effect does not reach the expected threshold, the system will generate an alarm instruction, prompting that the peeling equipment needs to be adjusted. For example, after acquiring three-dimensional data through laser scanning, MeshLab is used to construct a three-dimensional view, and then OpenCV is used for image processing and CNN model is used for defect detection. Finally, the single board grade and identification are generated, and the control effect of the equipment is ensured through a real-time monitoring and evaluation system.

[0096] Through the above steps, comprehensive inspection and quality assessment of the peeling results can be achieved to ensure that the equipment operates in the best condition and improve production efficiency and product quality.

[0097] In summary, the control method of the veneer peeling equipment provided in the embodiment of the present application has the following technical effects:

[0098] The sensor equipment group is used to perform data sensing on the logs to be peeled, and the sensor data set is subjected to multi-sensor fusion to extract the initial diameter data of the log, accurately obtain the size information of the log, and provide basic data for subsequent peeling calculations. Peeling calculations are performed based on the initial diameter data of the log, and multiple peeling control parameters are generated. These parameters are the key to guiding the operation of the veneer peeling equipment and determine the quality and efficiency of peeling. The veneer peeling equipment is simulated and controlled based on the multiple peeling control parameters to generate simulated dynamic peeling results, and the peeling effect is predicted without actually running the equipment, providing a basis for optimizing the control scheme. Defect detection is performed based on the simulated dynamic peeling results to find out possible problems, and abnormality tracing is performed based on the detection results to generate multiple abnormal data sources; based on the multiple abnormal data sources, the multiple peeling control parameters are updated and optimized to generate multiple peeling control optimization parameters, and a peeling control scheme is formulated to provide accurate and reliable guidance and decision-making for peeling operations. Activate the veneer peeling device to execute the peeling control scheme, monitor the veneer peeling device in real time, obtain the real-time operating parameter set of the veneer peeling device, and monitor the execution effect of the peeling control scheme in real time. Perform deviation feedback according to the real-time operating parameter set, dynamically adjust the peeling control scheme according to the feedback result, intelligently control the veneer peeling device, and respond to state changes during the peeling operation in a timely manner. Extract the veneer results and evaluate the veneer control effect. When the veneer control effect does not meet expectations, generate an alarm instruction and send it to the veneer peeling device for control adjustment, so as to achieve comprehensive detection and quality evaluation of the peeling results and ensure that the equipment operates in the best state.

[0099] In general, the embodiment of the present application obtains accurate log diameter data and generates rotary cutting control parameters through multi-sensor fusion technology; through simulation control and defect detection, it promptly discovers and solves problems that may arise during the rotary cutting process, thereby optimizing the rotary cutting control parameters and improving the quality and efficiency of rotary cutting; through real-time monitoring and deviation feedback, it realizes intelligent control of the veneer rotary cutting equipment, and can dynamically adjust the control scheme according to actual conditions, further improving the automation and intelligence level of rotary cutting, and significantly improving the rotary cutting accuracy and product quality.

[0100] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A control method for a veneer peeling device, characterized in that: The method comprises: The sensor equipment group is used to perform data sensing on the peeled logs, and the sensor data set is subjected to multi-sensor fusion to extract the initial diameter data of the logs; Perform peeling calculation based on the log initial diameter data to generate multiple peeling control parameters; Performing simulation control on the single board peeling equipment based on the multiple peeling control parameters to generate a simulated dynamic peeling result; Perform defect detection according to the simulated dynamic peeling results, perform abnormality tracing according to the detection results, and generate multiple abnormality data sources; Based on the multiple abnormal data sources, the multiple rotary cutting control parameters are updated and optimized, multiple rotary cutting control optimization parameters are generated, and a rotary cutting control plan is formulated; Activating the veneer peeling device to execute the peeling control scheme, and performing real-time monitoring on the veneer peeling device to obtain a real-time operating parameter set of the veneer peeling device; Deviation feedback is performed according to the real-time operating parameter set, and the peeling control scheme is dynamically adjusted according to the feedback result to perform intelligent control on the single board peeling equipment; Wherein, the defect detection according to the simulated dynamic peeling result includes: Based on the simulated dynamic peeling result and the diameter dynamic change parameter, a log diameter change curve is drawn; Drawing a rotary cutting speed change curve based on the simulated dynamic rotary cutting result and the multiple rotary cutting control parameters; Performing data processing according to the log diameter change curve and the rotary cutting speed change curve to extract the abnormal diameter reduction point and the rotary cutting speed mutation point; Retrieving historical peeling record data files to set defect recognition standards, wherein the defect recognition standards include a preset diameter change rate and a preset speed fluctuation range; Determine whether the abnormal diameter reduction point meets the preset diameter change rate, and whether the rotary cutting speed mutation point is within the preset speed fluctuation range; If the abnormal diameter reduction point does not conform to the preset diameter change rate, and the rotary cutting speed mutation point is within the preset speed fluctuation range, then a log diameter abnormality parameter is generated according to the abnormal diameter reduction point, and the log diameter abnormality parameter is added to the detection result; If the abnormal diameter reduction point meets the preset diameter change rate, and the peeling speed mutation point is not in the preset speed fluctuation range, then an abnormal peeling speed parameter is generated according to the peeling speed mutation point, and the abnormal peeling speed parameter is added to the detection result; If the abnormal diameter reduction point does not conform to the preset diameter change rate, and the rotary cutting speed mutation point is not in the preset speed fluctuation range, the log diameter abnormality parameter is generated according to the abnormal diameter reduction point, the rotary cutting speed abnormality parameter is generated according to the rotary cutting speed mutation point, and the log diameter abnormality parameter and the rotary cutting speed abnormality parameter are added to the detection result; The abnormality tracing is performed according to the detection results to generate multiple abnormal data sources, including: Based on the log diameter abnormality parameter and the peeling speed abnormality parameter, abnormality classification is performed to generate multiple abnormality categories; Analyze the association between the multiple abnormal categories and multiple data sources, and build a traceability causal model; The traceability causal model is used to perform data mining to obtain the multiple abnormal data sources.

2. The control method of veneer peeling equipment according to claim 1, characterized in that: The sensor equipment group is used to perform data sensing on the peeled logs, and the sensor data set is subjected to multi-sensor fusion to extract the initial diameter data of the logs. The method includes: Determine multiple sensing collection points based on the structure of the log to be peeled and the measurement requirements; Arrange a plurality of sensor devices based on the plurality of sensor collection points to obtain the sensor device group; Starting the sensor device group to perform data sensing on the logs to be peeled, and generating the sensor data set; Performing feature extraction on the sensor data set to determine a plurality of feature vectors; Associating the multiple feature vectors according to timestamps to generate a feature association factor; The multiple feature vectors are fused based on the feature association factor to obtain the initial diameter data of the log.

3. The control method of veneer peeling equipment according to claim 2, characterized in that: Based on the log initial diameter data, peeling calculation is performed to generate multiple peeling control parameters, the method comprising: Determine the starting position and the ending position of peeling according to the initial diameter data of the log and the structure of the log to be peeled; Planning a peeling path based on the peeling starting position and the peeling ending position; Calculate the peeling thickness information according to the peeling path combined with the peeling depth, dynamically update the initial diameter data of the log according to the peeling thickness and the peeling speed, and generate a diameter dynamic change parameter; The log center is determined based on the calculation of the initial log diameter, and the data is recorded according to the diameter dynamic change parameter combined with the log center to determine the multiple rotary cutting control parameters.

4. The control method of veneer peeling equipment according to claim 1, characterized in that: The method includes updating and optimizing the multiple rotary cutting control parameters based on the multiple abnormal data sources, generating multiple rotary cutting control optimization parameters, and formulating a rotary cutting control scheme, wherein the method includes: Using the multiple abnormal data sources as indexes, and combining an abnormality detection algorithm to perform abnormality identification on the multiple rotary cutting control parameters, and determine multiple abnormal points; Performing abnormality diagnosis based on the multiple abnormal data sources combined with the multiple abnormal points to generate an abnormality diagnosis result; Performing an impact analysis on the multiple peeling control parameters and the peeling quality according to the abnormal diagnosis result to generate a parameter impact coefficient; Performing weighted optimization on the plurality of rotary cutting control parameters according to the parameter influence coefficients to generate a plurality of rotary cutting control optimization parameters; The plurality of rotary cutting control optimization parameters are simulated and verified, and the rotary cutting control scheme is formulated based on the verification results.

5. The control method of veneer peeling equipment according to claim 1, characterized in that: Deviation feedback is performed according to the real-time operating parameter set, and the peeling control scheme is dynamically adjusted according to the feedback result to intelligently control the single board peeling device, the method comprising: Retrieve historical operation record data log to set target operation parameter range; Comparing the real-time operating parameter set with the target operating parameter interval, identifying and extracting the real-time operating parameters that are not in the target operating parameter interval, and calculating the deviation distance value according to the extraction result; Matching the running deviation level according to the deviation distance value, performing deviation feedback according to the matching result, and generating a feedback result; Based on the feedback results and the expert knowledge base, determine the target adjustment direction, target adjustment time node, and target adjustment distance; The rotary cutting control scheme is dynamically adjusted based on the target adjustment direction, the target adjustment time node, and the target adjustment distance.

6. The control method of veneer peeling equipment according to claim 1, characterized in that: The method further comprises: Extract the veneer results peeled by the veneer peeling equipment and construct a 3D view of the veneer; Perform image detection and analysis based on the three-dimensional view of the single board to generate a detection and analysis result; Automatically classify a plurality of single board grades according to the detection and analysis results, identify the single board results based on the plurality of single board grades, and generate a single board identification result; The single board identification result is synchronously mapped to obtain the single board control effect, and whether the single board control effect reaches the expected threshold is evaluated. If not, an alarm instruction is generated and sent to the single board peeling equipment for control adjustment.

Images