Furniture manufacturing full-process intelligent monitoring system based on cloud platform

Abstract

The invention relates to the technical field of furniture image recognition and monitoring, in particular to a furniture manufacturing full-process intelligent monitoring system based on a cloud platform, which is provided with a feature acquisition module, a pre-recognition module, a warping analysis module, a drying intervention regulation and control module and a regulation and control verification module. Whether the to-be-dried wood board has the warping and bending risk or not is judged based on the point cloud data of the to-be-dried wood board through a pre-recognition module, warping analysis is conducted on the to-be-dried wood board based on the texture representation vectors through a warping analysis module, and a pre-drying regulation and control mode is determined through a drying pre-regulation and control module. And judging whether an abnormal early warning signal is sent out or not according to the comparison condition of the plurality of pattern characterization vectors before and after pre-drying through a regulation and control verification module. According to the method, whether the to-be-dried wood board has the warping and bending risk or not is rapidly recognized, the adjusting mode of the drying process is adaptively determined according to the actual characteristics of the wood, and the reliability and effectiveness of intelligent monitoring of the whole furniture manufacturing process are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of furniture image recognition monitoring, and particularly relates to a furniture manufacturing whole-process intelligent monitoring system based on a cloud platform. BACKGROUND

[0002] With the acceleration of consumption upgrading and industrial transformation, the furniture manufacturing industry continues to expand, and the proportion of customized furniture orders continues to rise. The traditional standardized production mode is difficult to adapt to the flexible demand. In the whole process of furniture manufacturing, wood drying is the core link that determines product quality, directly affecting the dimensional stability, service life and subsequent processing precision of wood. As a kind of natural biomass material, wood has significant differences in internal structure such as texture direction, density distribution, heart and sapwood difference, and initial state such as moisture content gradient and geometric size uniformity. In the drying process, the uneven evaporation of water in the wood will cause complex drying stress. When the stress exceeds the local strength of the wood, it will cause irreversible defects such as warping, bending and cracking. These defects will directly cause the scrap of high-quality wood, increase production costs and prolong product delivery cycle. In the traditional production mode, the setting of drying process parameters is highly dependent on the personal experience of the operator, and it is difficult to realize standardization and large-scale replication. For wood with special texture or uneven size, there is a lack of scientific risk assessment method, and it is impossible to perform early warning and differential treatment before drying. The existing process adjustment is often carried out after the discovery of product defects, which belongs to after-the-fact remedy and cannot realize intervention in the middle of the process, resulting in a loss that has become a foregone conclusion. At the same time, the reasons for the warping of wood in drying are relatively complex, which may be due to the texture direction or the uneven thickness. The traditional method is difficult to distinguish the dominant risk type before drying, and it is impossible to apply targeted pretreatment or control strategies, which affects the effect of furniture wood drying. Therefore, it is an urgent technical problem to improve the reliability and effectiveness of the whole-process intelligent monitoring of furniture manufacturing.

[0003] For example, Chinese patent application publication No. CN120655074A discloses an industrial data management control system and method for furniture customization. The system includes a preliminary scheme formulation module, a scheme multi-source data rationality judgment module, a scheme evaluation and screening module, and a warning signal generation and processing module. The scheme multi-source data rationality judgment module sequentially performs periodic processing tests on different product assembly schemes, analyzes product qualification based on the corresponding periodic processing test reports, and calculates the comprehensive benefit of the corresponding product based on the analysis results. The invention analyzes and obtains the benefit of different component combinations in the production of products in the monitoring area, generates the best process manufacturing scheme based on the benefit, and real-time calibrates the best process manufacturing scheme based on the corresponding product demand list, thereby improving production efficiency, increasing product production flexibility, and maximizing product production efficiency.

[0004] There are also the following problems in the prior art: The prior art does not consider that defects such as warping, bending and cracking may occur in the wood drying process due to differences in its own characteristics such as texture direction or uneven size, and using the same drying process parameters will affect the quality stability of the wood. The prior art cannot quickly identify whether the wood board to be dried has a warping and bending risk, and cannot adaptively determine the adjustment mode of the drying process according to the actual characteristics of the wood, affecting the reliability and effectiveness of intelligent monitoring of the whole process of furniture manufacturing. SUMMARY

[0005] To this end, the present application provides a cloud platform-based intelligent monitoring system for the whole process of furniture manufacturing to overcome the problems that the prior art cannot quickly identify whether the wood board to be dried has a warping and bending risk, and cannot adaptively determine the adjustment mode of the drying process according to the actual characteristics of the wood, affecting the reliability and effectiveness of intelligent monitoring of the whole process of furniture manufacturing.

[0006] To achieve the above-mentioned purpose, the present application provides a cloud platform-based intelligent monitoring system for the whole process of furniture manufacturing, comprising: A feature acquisition module is used to acquire the surface texture profile and point cloud data of the wood board to be dried. A pre-recognition module is connected to the feature acquisition module and is used to determine a plurality of board discrete representation parameters based on the point cloud data of each monitoring area on the wood board to be dried, and to determine whether the wood board to be dried has a warping and bending risk based on the comparison between the board discrete representation parameters. A warping analysis module is connected to the feature acquisition module and the pre-recognition module, respectively, and is used to construct a plurality of texture representation vectors based on the surface texture profile in response to the wood board to be dried having a warping and bending risk, and to perform warping analysis on the wood board to be dried based on the texture representation vectors to determine a warping risk tendency category. A drying pre-adjustment and control module is connected to the warping analysis module and is used to determine that the pre-drying adjustment mode of the wood board to be dried is to determine the increase amplitude of the drying humidity and the decrease amplitude of the drying temperature based on the texture representation vectors, or to determine the preheating time length increase amplitude based on a plurality of board discrete representation parameters. A control verification module is connected to the feature acquisition module and the drying pre-adjustment and control module, respectively, and is used to determine a distortion tendency parameter based on the comparison of a plurality of texture representation vectors before and after pre-drying to determine whether to issue an abnormal early warning signal.

[0007] Further, the pre-recognition module is used to determine the board discrete representation parameters based on the point cloud data of each monitoring area on the wood board to be dried, wherein, The pre-identification module is configured to acquire feature point cloud data of a plurality of collection points in a monitoring area, and determine a difference between a maximum value and a minimum value of the feature point cloud data as a board discrete representation parameter. The feature point cloud data is point cloud data in a direction perpendicular to a plane on which the wood board to be dried is located.

[0008] Further, the pre-identification module is configured to determine whether the wood board to be dried has a risk of warping and bending. The pre-identification module determines that the wood board to be dried has a risk of warping and bending based on a determination result that the board discrete representation parameter of the monitoring area on the wood board to be dried meets a risk condition of warping and bending. The risk condition of warping and bending is that a variance of the board discrete representation parameter exceeds a preset variance threshold.

[0009] Further, the warping analysis module is configured to perform warping analysis on the wood board to be dried based on the plurality of grain representation vectors. The warping analysis module is configured to calculate a vector included angle between each grain representation vector and a board reference vector, and determine a mean value of the vector included angles as a warping tendency parameter. The grain representation vector is constructed with any one endpoint of a surface grain contour as a vector starting point and another endpoint as a vector ending point, and the board reference vector is a unit vector in a length direction of the wood board to be dried.

[0010] Further, the warping analysis module is configured to determine a warping risk tendency category. The warping analysis module determines that the warping risk tendency category of the wood board to be dried is a risk tendency category of warping along grain based on a determination result that the warping tendency parameter of the wood board to be dried meets a grain tendency condition. The warping analysis module determines that the warping risk tendency category of the wood board to be dried is a non-grain warping risk tendency category based on a determination result that the warping tendency parameter of the wood board to be dried does not meet the grain tendency condition. The grain tendency condition is that the warping tendency parameter exceeds a preset warping tendency parameter threshold.

[0011] Further, the drying pre-adjustment and control module is configured to determine an adjustment and control mode of pre-drying the wood board to be dried. The drying pre-adjustment and control module determines a growth amplitude of a drying humidity and a reduction amplitude of a drying temperature according to the plurality of grain representation vectors based on a determination result that the warping risk tendency category is the risk tendency category of warping along grain. The drying pre-adjustment and control module determines a preheating time length growth amplitude of pre-drying based on a plurality of board discrete representation parameters based on a determination result that the warping risk tendency category is the non-grain warping risk tendency category.

[0012] Further, the drying pre-control module is used to determine the increasing amplitude of the drying humidity and the decreasing amplitude of the drying temperature, wherein, The increasing amplitude of the drying humidity is positively correlated with the warping tendency parameter; The decreasing amplitude of the drying temperature is positively correlated with the warping tendency parameter.

[0013] Further, the drying pre-control module is used to determine the increasing amplitude of the pre-drying preheating time, wherein, The increasing amplitude of the preheating time is positively correlated with the variance of the board discrete representation parameter.

[0014] Further, the control verification module is used to determine the distortion tendency parameter according to the comparison of the plurality of grain representation vectors before and after pre-drying, wherein, The control verification module is used to calculate the vector angle mean of the plurality of grain representation vectors before and after pre-drying, respectively; The absolute value of the difference between the vector angle means before and after pre-drying is determined as the distortion tendency parameter.

[0015] Further, the control verification module is used to determine whether to issue an abnormal early warning signal, wherein, The control verification module determines to issue an abnormal early warning signal based on the determination result that the distortion tendency parameter of the wood board to be dried does not meet the control reasonable condition; The control reasonable condition is that the distortion tendency parameter does not exceed the preset distortion tendency parameter threshold.

[0016] Compared with the prior art, the present application has the beneficial effects that the present application is provided with a feature acquisition module, a pre-recognition module, a warping analysis module, a drying pre-control module, and a control verification module, the plurality of board discrete representation parameters are determined based on the point cloud data of each monitoring area on the wood board to be dried by the pre-recognition module, it is determined whether the wood board to be dried has a warping and bending risk based on the comparison between the plurality of board discrete representation parameters, the plurality of grain representation vectors are constructed according to the surface grain contour by the warping analysis module, the wood board to be dried is analyzed for warping based on the plurality of grain representation vectors to determine the warping risk tendency category, the control mode of pre-drying the wood board to be dried is determined according to the warping risk tendency category by the drying pre-control module, the distortion tendency parameter is determined according to the comparison of the plurality of grain representation vectors before and after pre-drying by the control verification module to determine whether to issue an abnormal early warning signal, thereby, it is realized to quickly identify whether the wood board to be dried has a warping and bending risk, to adaptively determine the adjustment mode of the drying process according to the actual characteristics of the wood, and to improve the reliability and effectiveness of intelligent monitoring of the whole process of furniture manufacturing.

[0017] In particular, this invention uses a pre-identification module to determine whether there is a risk of warping or bending in the wood panels to be dried, based on the comparison between discrete characterization parameters of each panel. It is understood that wood shrinks during the drying process, driven by moisture loss. If the panel thickness is uneven, thinner sections will dry and begin to shrink before thicker sections. This asynchronous drying process generates uneven drying stress within the wood. The discrete characterization parameter of the panel, namely the difference between the maximum and minimum local thickness values, quantifies the intensity of the risk of asynchronous drying in each monitored area. A single local thickness difference may not necessarily lead to overall warping. When the variance of the thickness range values ​​in many local areas is large, it means that there are many strong risks within the entire panel. The varying degrees and directions of drying stress sources create complex internal stresses that can easily exceed the structural strength of wood during the drying process, causing warping or bending. Traditional production relies on visual inspection after drying, and by the time warping is detected, the wood is already deformed and unusable, resulting in a double waste of materials and energy. However, by using non-contact, rapid screening to identify high-risk boards before drying, targeted intervention measures can be taken for high-risk boards, while standard and efficient processes can be applied to low-risk boards. This ensures the overall quality pass rate while optimizing resource allocation and production efficiency. Furthermore, it enables rapid identification of warping and bending risks in boards to be dried, improving the reliability and effectiveness of intelligent monitoring throughout the furniture manufacturing process.

[0018] In particular, this invention uses a warpage analysis module to perform warpage analysis on the wood panels to be dried based on the characteristic vectors of each grain pattern to determine the warpage risk tendency category. It is understood that the grain of wood reflects the direction of its internal fiber arrangement, indicating the directionality of its physical and mechanical properties. During drying, the shrinkage rate of wood along the longitudinal direction of the fibers is relatively small, while the shrinkage rate perpendicular to the fiber direction is relatively large. When there is a systematic deviation between the grain direction on the surface of the board and the length direction of the board, i.e., when the warpage tendency parameter is large, it means that the arrangement of the wood fibers is not parallel to the force reference axis as a whole. During drying shrinkage, this structural directional deviation will cause the shrinkage force to decompose into uneven force components on the cross-section of the board, thereby generating internal torque that drives the board to undergo torsional deformation, warping, or complex twisting. If the warpage tendency... A smaller warp tendency parameter indicates a relatively straight overall grain. Due to uneven thickness, potential deformation is more likely to manifest as non-parallel warping, such as bowing, caused by the drying rate gradient and characterized primarily by bending. Traditional methods, even if they detect warping risk in wood, struggle to determine the dominant cause. By calculating the warping tendency parameter, high-risk boards are categorized into parallel and non-parallel warping risk tendencies, laying the foundation for subsequent refined control. This improves the effectiveness of preventative measures, more precisely suppressing the generation of specific types of defects at the source, increasing the yield of high-quality dried wood, and reducing energy and time costs caused by ineffective or erroneous process experiments. Furthermore, it enables the determination of the warping risk tendency category of wood to be dried, improving the reliability and effectiveness of intelligent monitoring throughout the furniture manufacturing process.

[0019] In particular, this invention, through a drying pre-regulation module, determines the increase in drying humidity and the decrease in drying temperature based on the characteristic vectors of each grain pattern under the parallel-grain warping risk tendency category. It can be understood that the parallel-grain warping risk tendency category indicates that the wood to be dried carries the risk of unbalanced torque stress generated within the board due to anisotropic shrinkage of the wood caused by diagonal grain. To suppress this deformation, it is necessary to control the rate of moisture evaporation and stress development during the drying process. Increasing the drying humidity, i.e., reducing the wet-bulb and dry-bulb temperatures, can lower the partial pressure difference of water vapor in the air above the board surface, slowing down the evaporation rate of moisture from the wood surface. This allows more time for moisture inside the wood to migrate to the surface, reducing the moisture content gradient between the inner and outer layers of the board and preventing the huge drying stress caused by the surface shrinking too quickly and locking the interior. Simultaneously reducing the drying temperature can lower the activation energy for moisture migration and the plastic flow of wood components such as lignin, making the entire drying process more efficient. The process becomes more gentle and controllable. Temperature and humidity regulation work together to ensure that the wood is in a quasi-equilibrium environment with low drying potential. This allows the shrinkage differences caused by the diagonal grain within the wood to be released slowly and synchronously to the maximum extent. This eliminates the torque stress that would cause warping during the formation process, rather than accumulating to a destructive level. For boards with slightly tilted grains (i.e., smaller warping tendency parameters), only slight adjustments are made to balance efficiency and safety. For boards with severely tilted grains and a high risk of twisting (i.e., larger warping tendency parameters), humidity is increased and temperature is decreased significantly. Through dynamic regulation, the safety of the highest-risk boards is ensured while avoiding over-treatment of medium- and low-risk boards. This improves the utilization rate of high-quality wood and reduces unit energy consumption. Furthermore, it enables the adaptive determination of the drying process adjustment method based on the actual characteristics of the wood, improving the reliability and effectiveness of intelligent monitoring throughout the furniture manufacturing process.

[0020] In particular, this invention, through a drying pre-control module, determines the increase in preheating time for pre-drying under the non-parallel grain warping risk category based on several discrete characterization parameters of the wood panels. It is understood that the main cause of non-parallel grain warping risk in wood panels is not the grain direction, but rather the difference in heat and mass transfer resistance in the thickness dimension. In thicker areas, heat transfer to the core is slower, and moisture migration outwards is longer, while in thinner areas, the opposite is true. If this difference is not addressed before entering the drying stage, it will cause the thinner areas to rapidly dehydrate and shrink, creating strong tensile constraints on the still-wet thicker areas, generating bending stress. The fundamental purpose of the preheating stage is to allow the wood to uniformly heat to the target temperature while maintaining a high humidity environment, without causing or minimally causing moisture evaporation, thus extending the drying time. The extended preheating time allows for more time for heat to penetrate, reducing the core temperature difference between thick and thin areas through heat conduction. When the fiber saturation point temperature is consistent throughout the board, subsequent dehumidification can begin, allowing for near-synchronous evaporation and shrinkage of free water in each area. This weakens the shrinkage stress gradient that causes warping at its source, providing the board with a buffer period for sufficient heat penetration and for the core temperature of thicker areas to effectively catch up with that of thinner areas. This lays the thermal foundation for subsequent uniform dehydration, thus suppressing non-parallel warping such as bowing caused by asynchronous drying rates. It also avoids the overall energy efficiency decrease caused by blindly extending the preheating time of all boards. Furthermore, it enables the adjustment of the drying process to be adaptively determined according to the actual characteristics of the wood, improving the reliability and effectiveness of intelligent monitoring throughout the furniture manufacturing process.

[0021] In particular, this invention uses a control verification module to determine whether to issue an abnormal warning signal based on the comparison of several texture characterization vectors before and after pre-drying. It is understood that in an ideal, gentle pre-drying process, a small amount of free water is removed from the wood relatively evenly, and its fiber skeleton does not undergo irreversible plastic deformation or cell collapse. Therefore, the macroscopic texture direction should maintain high stability, and the distortion tendency parameter should be small, meaning the average change in the angle between texture vectors before and after pre-drying is small. If the pre-drying parameters are set improperly, such as too low humidity or too high temperature for diagonal grain boards, or insufficient preheating for boards with uneven thickness, significant drying stress will be generated inside the wood, forcing the wood to… Microscopic slippage, yielding, or macroscopic elastic bending of the fibrous tissue leads to a change in the direction of its surface texture. The larger the torsion tendency parameter, the more significant the structural shift of the wood during the pre-drying stage. This indicates that the current control environment has failed to effectively eliminate the inherent instability of the material. The warning signal should be triggered in time so that those skilled in the art can promptly discover and deal with the current anomaly to prevent more serious damage. It can also terminate any potential batch drying defects in time and avoid the ineffective investment of a large amount of resources in the subsequent incorrect process path. In this way, the effect of the pre-drying process parameters can be verified, and the reliability and effectiveness of intelligent monitoring of the entire furniture manufacturing process can be improved. Attached Figure Description

[0022] Figure 1 This is a functional block diagram of the cloud-based intelligent monitoring system for the entire furniture manufacturing process, as described in an embodiment of the present invention. Figure 2 This is a flowchart illustrating the logic of the pre-identification module in this invention for determining whether there is a risk of warping or bending in the wooden boards to be dried. Figure 3 A flowchart illustrating the logic of the warpage analysis module in this embodiment of the invention for determining the warpage risk tendency category; Figure 4 This is a flowchart illustrating the logic of the drying pre-control module in this embodiment of the invention, which determines the control method for pre-drying the wood boards to be dried. Detailed Implementation

[0023] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0024] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0025] It should be noted that in the description of this invention, the terms "upper," "lower," "inner," "outer," etc., which indicate the direction or positional relationship, are based on the direction or positional relationship shown in the drawings. This is only for the convenience of description and is not intended to indicate or imply that the device or element must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation of this invention.

[0026] Furthermore, it should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the terms "installation" and "connection" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0027] Please see Figure 1 The diagram shown is a functional block diagram of a cloud-based intelligent monitoring system for the entire furniture manufacturing process according to an embodiment of the present invention. The cloud-based intelligent monitoring system for the entire furniture manufacturing process of the present invention includes: The feature acquisition module is used to acquire several surface texture contours and point cloud data of the wood board to be dried; Specifically, the structure of the feature acquisition module is not specifically limited in the embodiments of the present invention. Preferably, it can acquire several surface texture contours of the wood board to be dried through an industrial camera and acquire point cloud data of the wood board to be dried through a lidar device. Of course, other methods can also be used, which will not be elaborated here.

[0028] There are no restrictions on the method for obtaining the surface texture contours. For example, several surface texture contours can be obtained through edge algorithms. Of course, other methods can also be used, which will not be elaborated here.

[0029] The pre-identification module, which is connected to the feature acquisition module, is used to determine a number of discrete characterization parameters of the board based on the point cloud data of each monitoring area on the board to be dried, and to determine whether the board to be dried has a risk of warping or bending based on the comparison between the discrete characterization parameters of each board. Specifically, the embodiments of the present invention do not specifically limit the structure of the pre-identification module. Preferably, it can be a microprocessor used to determine several discrete characterization parameters of the board material and determine whether the board material to be dried has a risk of warping or bending. This will not be elaborated further.

[0030] Specifically, the monitoring areas on the wood boards to be dried can be evenly distributed in a grid pattern. The density of the monitoring areas can be set by those skilled in the art based on the accuracy requirements of intelligent monitoring throughout the furniture manufacturing process. The higher the accuracy requirements, the greater the density should be.

[0031] The warping analysis module is connected to the feature acquisition module and the pre-identification module respectively. In response to the risk of warping of the wood board to be dried, it constructs several texture representation vectors based on the surface texture contour, and performs warping analysis on the wood board to be dried based on each texture representation vector to determine the warping risk tendency category. Specifically, the embodiments of the present invention do not specifically limit the structure of the warpage analysis module. Preferably, it can be a microprocessor used to construct a texture representation vector and determine the warpage risk tendency category, which will not be elaborated further.

[0032] The drying pre-control module, which is connected to the warping analysis module, is used to determine the control method for pre-drying the wood board to be dried according to the warping risk tendency category. This method involves determining the increase rate of drying humidity and the decrease rate of drying temperature based on each of the texture characterization vectors, or determining the increase rate of preheating time based on several discrete characterization parameters of the board. Specifically, the embodiments of the present invention do not specifically limit the structure of the drying pre-control module. Preferably, it can be a processor used in a computer to determine the control method for pre-drying the wood boards to be dried, which will not be elaborated further.

[0033] The control and verification module is connected to the feature acquisition module and the drying pre-control module respectively. It is used to determine the distortion tendency parameter based on the comparison of several texture characterization vectors before and after pre-drying, so as to determine whether to issue an abnormal warning signal.

[0034] Specifically, the embodiments of the present invention do not impose specific limitations on the structure of the control verification module. Preferably, it can be a microprocessor used to determine whether to issue an abnormal warning signal, which will not be elaborated further.

[0035] Specifically, the pre-identification module is used to determine the discrete characterization parameters of the board based on the point cloud data of each monitoring area on the board to be dried, wherein, The pre-identification module is used to acquire feature point cloud data of several collection points within the monitoring area, and the difference between the maximum value and the minimum value of the feature point cloud data is determined as the discrete characterization parameter of the board material. The feature point cloud data refers to the point cloud data that is perpendicular to the plane of the wooden board to be dried.

[0036] Specifically, the collection points within the monitoring area can be evenly distributed.

[0037] Please see Figure 2 The diagram shown is a flowchart illustrating the logic of the pre-identification module in an embodiment of the present invention for determining whether the wooden board to be dried has a risk of warping or bending. The pre-identification module is used to determine whether the wooden board to be dried has a risk of warping or bending. The pre-identification module determines that the board to be dried has a risk of warping or bending based on the determination result that the discrete characterization parameters of the board in the monitoring area of ​​the board to be dried meet the conditions for warping and bending risk. Based on the determination result that the discrete characterization parameters of the board in the monitoring area on the board to be dried do not meet the conditions for warping and bending risk, it is determined that the board to be dried does not have the risk of warping and bending. The warping risk condition is that the variance of the discrete characterization parameters of the board exceeds a preset variance threshold.

[0038] Specifically, the preset variance threshold is the product of the variance reference value and the risk factor. The variance reference value is the mean variance of the same working conditions in historical data. The risk factor can be set by those skilled in the art based on the accuracy requirements of intelligent monitoring of the entire furniture manufacturing process. The higher the accuracy requirement, the smaller the value should be. The value range can be [1.05, 1.15], preferably 1.1.

[0039] Specifically, this embodiment of the invention uses a pre-identification module to determine whether there is a risk of warping or bending in the wood panels to be dried, based on the comparison between discrete characterization parameters of each panel. It is understood that wood shrinks during the drying process, driven by moisture loss. If the panel thickness is uneven, thinner areas will dry and begin to shrink before thicker areas. This asynchronous drying process generates uneven drying stress within the wood. The discrete characterization parameter of the panel, i.e., the difference between the maximum and minimum local thickness values, quantifies the intensity of the risk of asynchronous drying in each monitoring area. A single local thickness difference may not necessarily lead to overall warping. When the variance of the thickness range values ​​in many local areas is large, it means that warping exists within the entire panel. Numerous drying stress sources of varying intensity and direction can easily exceed the structural strength of wood during the drying process, causing warping or bending. Traditional production relies on visual inspection after drying, and by the time warping is detected, the wood is already deformed and unusable, resulting in a double waste of materials and energy. However, by using non-contact, rapid screening to identify high-risk boards before drying, targeted intervention measures can be taken for high-risk boards, while standard and efficient processes can be applied to low-risk boards. This ensures the overall quality pass rate while optimizing resource allocation and production efficiency. Furthermore, it enables rapid identification of warping and bending risks in boards to be dried, improving the reliability and effectiveness of intelligent monitoring throughout the furniture manufacturing process.

[0040] Specifically, the warping analysis module is used to perform warping analysis on the wood board to be dried based on each of the texture characterization vectors, wherein, The warping analysis module is used to calculate the vector angle between each texture characterization vector and the plate reference vector, and the mean value of the vector angle is determined as the warping tendency parameter. The texture representation vector is constructed with one endpoint of the surface texture contour as the vector starting point and the other endpoint as the vector ending point, and the board reference vector is the unit vector along the length direction of the board to be dried.

[0041] It is understandable that the surface texture outline represents the wood grain. Since there may be minor splits in the wood grain, in practice, only the main diameter that has the main influence is considered. Therefore, when capturing the surface texture outline, only the texture outline with a texture diameter greater than a predetermined threshold is considered to eliminate the influence of splits. The predetermined threshold can be calculated by those skilled in the art based on the average of experimental data under several identical working conditions.

[0042] In particular, for wood grain patterns with branches, it is necessary to segment them. The segmentation nodes are the nodes corresponding to the branches of the wood grain pattern, so as to obtain several independent wood grain patterns with relatively concentrated directions, and then obtain the grain pattern representation vector corresponding to each wood grain pattern.

[0043] Please see Figure 3The diagram shown is a logical flowchart of the warpage analysis module in an embodiment of the present invention for determining the warpage risk propensity category. The warpage analysis module is used to determine the warpage risk propensity category. The warping analysis module determines the warping risk tendency category of the wood board to be dried as the parallel warping risk tendency category based on the judgment result that the warping tendency parameters of the wood board to be dried meet the parallel warping tendency condition. Based on the determination result that the warping tendency parameters of the wood board to be dried do not meet the grain-side tendency condition, the warping risk tendency category of the wood board to be dried is determined to be the non-grain-side warping risk tendency category. The condition for parallel warping tendency is that the warping tendency parameter exceeds a preset warping tendency parameter threshold.

[0044] Specifically, the preset warping tendency parameter threshold is the product of the warping tendency parameter reference value and the warping factor. The warping tendency parameter reference value is the average value of the warping tendency parameter under the same working conditions in historical data. The warping factor can be set by those skilled in the art according to the accuracy requirements of intelligent monitoring of the entire furniture manufacturing process. The higher the accuracy requirement, the smaller the value should be. The value range can be [1.05, 1.2], preferably 1.1.

[0045] Specifically, this embodiment of the invention uses a warpage analysis module to perform warpage analysis on the wood panels to be dried based on the texture representation vectors to determine the warpage risk category. It is understood that the wood grain reflects the direction of its internal fiber arrangement, indicating the directionality of its physical and mechanical properties. During drying, the shrinkage rate of wood along the fiber longitudinal direction is relatively small, while the shrinkage rate perpendicular to the fiber direction is relatively large. When there is a systematic deviation between the grain direction on the surface of the board and the length direction of the board, i.e., when the warpage tendency parameter is large, it means that the arrangement of the wood fibers is not parallel to the force reference axis as a whole. During drying shrinkage, this structural directional deviation will cause the shrinkage force to decompose into uneven force components on the cross-section of the board, thereby generating internal torque that drives the board to undergo torsional deformation, warping, or complex twisting. If warpage occurs... A smaller warp tendency parameter indicates that the overall grain is relatively straight. Due to the uneven thickness, the potential deformation is more likely to manifest as non-parallel warping, such as bowing, caused by the drying rate gradient and characterized primarily by bending. Traditional methods, even if they detect the risk of warping in the wood, struggle to determine the dominant cause. By calculating the warp tendency parameter, high-risk boards can be categorized into parallel and non-parallel warping risk tendencies, laying the foundation for subsequent refined control. This improves the effectiveness of preventative measures, more precisely suppresses the generation of specific types of defects at the source, increases the yield of high-quality dried wood, and reduces energy and time costs caused by ineffective or erroneous process experiments. Furthermore, it enables the determination of the warping risk tendency category of the wood to be dried, improving the reliability and effectiveness of intelligent monitoring throughout the furniture manufacturing process.

[0046] Please see Figure 4 The diagram shown is a logic flowchart illustrating how the drying pre-control module determines the control method for pre-drying the wooden board to be dried, according to an embodiment of the present invention. The drying pre-control module is used to determine the control method for pre-drying the wooden board to be dried. The drying pre-control module determines the increase in drying humidity and the decrease in drying temperature based on the determination result that the warping risk tendency category is the parallel warping risk tendency category, according to each of the texture characterization vectors. Based on the determination result of the warping risk tendency category being the non-parallel warping risk tendency category, the increase rate of preheating time for pre-drying is determined according to several discrete characterization parameters of the board.

[0047] Specifically, the drying pre-control module is used to determine the rate of increase in drying humidity and the rate of decrease in drying temperature, wherein, The increase in drying humidity is positively correlated with the warping tendency parameter; The decrease in drying temperature is positively correlated with the warping tendency parameter.

[0048] Specifically, the increase in drying humidity is calculated as humidity factor × warpage tendency parameter / warpage tendency parameter reference value, and the decrease in drying temperature is calculated as temperature factor × warpage tendency parameter / warpage tendency parameter reference value. The warpage tendency parameter reference value is the average warpage tendency parameter under the same working conditions in historical data. The humidity factor and temperature factor can be calculated by those skilled in the art based on several historical experimental data. The humidity factor can be in the range of [0.1, 0.3], and the temperature factor can be in the range of [0.05, 0.15], to avoid adjusting the drying humidity and drying temperature too much or too little. Preferably, the humidity factor can be 0.2, and the temperature factor can be 0.1.

[0049] Specifically, in this embodiment of the invention, the drying pre-control module determines the increase in drying humidity and the decrease in drying temperature based on the characteristic vectors of each grain pattern under the parallel-grain warping risk tendency category. It can be understood that the parallel-grain warping risk tendency category indicates that the wood to be dried has the risk of unbalanced torque stress generated within the board due to anisotropic shrinkage of the wood caused by diagonal grain. To suppress this deformation, it is necessary to control the rate of moisture evaporation and stress development during the drying process. Increasing the drying humidity, i.e., reducing the wet-bulb and dry-bulb temperatures, can reduce the partial pressure difference of water vapor in the air on the board surface, slowing down the evaporation rate of moisture on the wood surface. This allows more time for moisture inside the wood to migrate to the surface, reducing the moisture content gradient between the inner and outer layers of the board and avoiding the huge drying stress caused by the surface shrinking too quickly and locking the interior. Simultaneously reducing the drying temperature can reduce the activation energy for moisture migration and plastic flow of wood components such as lignin, making the entire board more stable. The drying process becomes more gentle and controllable. Temperature and humidity regulation work together to ensure that the wood is in a quasi-equilibrium environment with low drying potential. This allows the shrinkage differences caused by the diagonal grain within the wood to be released slowly and synchronously to the maximum extent. This eliminates the torque stress that could lead to warping during the formation process, rather than accumulating to a destructive level. For boards with slightly tilted grains (i.e., smaller warping tendency parameters), only minor adjustments are made to balance efficiency and safety. However, for boards with severely tilted grains and a high risk of twisting (i.e., larger warping tendency parameters), humidity is significantly increased and temperature is decreased. Through dynamic regulation, the safety of the highest-risk boards is ensured while avoiding over-treatment of medium- and low-risk boards. This improves the utilization rate of high-quality wood and reduces unit energy consumption. Furthermore, it enables the adaptive determination of the drying process adjustment method based on the actual characteristics of the wood, improving the reliability and effectiveness of intelligent monitoring throughout the furniture manufacturing process.

[0050] Specifically, the drying pre-control module is used to determine the increase rate of the preheating time for pre-drying, wherein, The increase in preheating time is positively correlated with the variance of the discrete characterization parameters of the board.

[0051] Specifically, the increase in preheating time is calculated as: duration factor × variance of discrete characterization parameters of the board / reference value of variance of discrete characterization parameters of the board. The reference value of variance of discrete characterization parameters of the board is the mean variance of discrete characterization parameters of the board under the same working conditions in historical data. The duration factor can be calculated by those skilled in the art based on several historical experimental data, and the value range can be [0.05, 0.2] to avoid adjusting the preheating time to be too long or too short. Preferably, it can be 0.1.

[0052] Specifically, in this embodiment of the invention, the drying pre-control module determines the increase in preheating time for pre-drying under the non-parallel grain warping risk category based on several discrete characterization parameters of the wood panels. It is understood that the main cause of non-parallel grain warping risk in wood panels is not the grain direction, but rather the difference in heat and mass transfer resistance in the thickness dimension. In thicker areas, heat transfer to the core is slower, and moisture migration to the outside is longer, while in thinner areas, the opposite is true. If this difference is not addressed before entering the drying stage, it will cause the thinner areas to rapidly dehydrate and shrink, creating strong tensile constraints on the still-wet thicker areas, generating bending stress. The fundamental purpose of the preheating stage is to uniformly raise the temperature of the entire wood to the target temperature while maintaining a high humidity environment, without causing or minimally causing moisture evaporation. Extending the preheating time allows for more time for heat to penetrate, reducing the core temperature difference between thick and thin areas through heat conduction. When the fiber saturation point temperature is consistent throughout the board, subsequent dehumidification can begin, allowing free water to evaporate and shrink almost synchronously in each area. This weakens the shrinkage stress gradient that causes bending at its source, providing the board with a buffer period where heat can fully penetrate and the core temperature of the thicker areas can effectively catch up with that of the thinner areas. This lays the thermal foundation for subsequent uniform dehydration, thus suppressing non-parallel warping caused by asynchronous drying rates. At the same time, it avoids the overall energy efficiency decrease caused by blindly extending the preheating time of all boards. Furthermore, it enables the adjustment of the drying process to be adaptively determined according to the actual characteristics of the wood, improving the reliability and effectiveness of intelligent monitoring throughout the furniture manufacturing process.

[0053] Specifically, the control and verification module is used to determine the distortion tendency parameter based on the comparison of several texture characterization vectors before and after pre-drying, wherein, The control and verification module is used to calculate the mean of the vector angle between several texture characterization vectors before and after pre-drying. The absolute value of the difference between the mean values ​​of the vector angles before and after pre-drying is determined as the distortion tendency parameter.

[0054] Specifically, the control verification module is used to determine whether to issue an abnormal warning signal, wherein, The control verification module issues an abnormal warning signal based on the determination result that the torsion tendency parameters of the wood board to be dried do not meet the reasonable control conditions. The control verification module determines that no abnormal warning signal will be issued based on the judgment result that the torsion tendency parameters of the wood board to be dried meet the reasonable control conditions. The reasonable condition for regulation is that the distortion tendency parameter does not exceed the preset distortion tendency parameter threshold.

[0055] Specifically, the preset distortion tendency parameter threshold is the product of the distortion tendency parameter reference value and the distortion factor. The distortion tendency parameter reference value is the average distortion tendency parameter under the same working conditions in historical data. The distortion factor can be set by those skilled in the art according to the accuracy requirements of intelligent monitoring of the entire furniture manufacturing process. The higher the accuracy requirement, the smaller the value should be. The value range can be [1.05, 1.2], preferably 1.1.

[0056] Specifically, in this embodiment of the invention, the control verification module determines whether to issue an abnormal warning signal based on the comparison of several texture characterization vectors before and after pre-drying. It is understood that in an ideal, gentle pre-drying process, a small amount of free water is removed from the wood relatively evenly, and its fiber skeleton does not undergo irreversible plastic deformation or cell collapse. Therefore, the macroscopic texture direction should maintain high stability, and the distortion tendency parameter should be small, meaning the average change in the angle between texture vectors before and after pre-drying is small. If the pre-drying parameters are set improperly, such as too low humidity or too high temperature for diagonal grain boards, or insufficient preheating for boards with uneven thickness, significant drying stress will be generated inside the wood, forcing… The microscopic slippage, yielding, or macroscopic elastic bending of the wood fiber structure leads to a change in the direction of its surface grain. The larger the torsion tendency parameter, the more significant the structural shift of the wood during the pre-drying stage. This indicates that the current control environment has failed to effectively eliminate the inherent instability of the material. The warning signal should be triggered in time so that those skilled in the art can promptly discover and deal with the current anomaly to prevent more serious damage. It can also terminate any potential batch drying defects in time and avoid the ineffective investment of a large amount of resources in the subsequent incorrect process path. In this way, the effect of the pre-drying process parameters can be verified, and the reliability and effectiveness of intelligent monitoring of the entire furniture manufacturing process can be improved.

[0057] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

[0058] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A cloud platform-based intelligent monitoring system for the whole process of furniture manufacturing, characterized in that, The method comprises the following steps: a feature acquisition module is used to acquire surface texture profiles and point cloud data of a wood board to be dried; a pre-recognition module connected with the feature acquisition module is used to determine a plurality of discrete board feature parameters based on the point cloud data of each monitoring area on the wood board to be dried, and determine whether the wood board to be dried has a warping risk based on the comparison between the discrete board feature parameters; a warping analysis module connected with the feature acquisition module and the pre-recognition module is used to, in response to the wood board to be dried having a warping risk, construct a plurality of texture feature vectors according to the surface texture profiles, and perform warping analysis on the wood board to be dried based on the texture feature vectors to determine a warping risk tendency category; a drying pre-control module connected with the warping analysis module is used to determine, according to the warping risk tendency category, that the control mode of pre-drying the wood board to be dried is to determine the increase amplitude of drying humidity and the decrease amplitude of drying temperature according to the texture feature vectors, or to determine the increase amplitude of pre-drying preheating time according to a plurality of discrete board feature parameters; a control verification module connected with the feature acquisition module and the drying pre-control module is used to determine a distortion tendency parameter according to the comparison between a plurality of texture feature vectors before and after pre-drying, and determine whether to issue an abnormal early warning signal. 2.The cloud platform-based intelligent monitoring system for whole-process furniture manufacturing according to claim 1, characterized in that, The pre-recognition module is used to determine a discrete board feature parameter based on the point cloud data of each monitoring area on the wood board to be dried, wherein The pre-recognition module is used to acquire feature point cloud data of a plurality of collection points in the monitoring area, and determine the difference between the maximum value and the minimum value of the feature point cloud data as the discrete board feature parameter; The feature point cloud data is the point cloud data perpendicular to the plane direction of the wood board to be dried. 3.The cloud platform-based intelligent monitoring system for whole-process furniture manufacturing according to claim 2, characterized in that, The pre-recognition module is used to determine whether the wood board to be dried has a warping risk, wherein The pre-recognition module determines that the wood board to be dried has a warping risk based on the determination result that the discrete board feature parameter of the monitoring area on the wood board to be dried meets the warping risk condition; The warping risk condition is that the variance of the discrete board feature parameter exceeds a preset variance threshold. 4.The cloud platform-based intelligent monitoring system for whole-process furniture manufacturing according to claim 3, characterized in that, The warping analysis module is used to perform warping analysis on the wood board to be dried based on the texture feature vectors, wherein The warping analysis module is used to calculate the vector included angle between each texture feature vector and a board reference vector, and determine the average value of the vector included angle as a warping tendency parameter; The texture feature vector is constructed with any one endpoint of the surface texture profile as the vector starting point and the other endpoint as the vector ending point, and the board reference vector is a unit vector in the length direction of the wood board to be dried. 5.The cloud platform-based intelligent monitoring system for whole-process furniture manufacturing according to claim 4, characterized in that, The warping analysis module is used to determine a warping risk tendency category, wherein The warping analysis module determines that the warping risk tendency category of the wood board to be dried is a parallel grain warping risk tendency category based on the determination result that the warping tendency parameter of the wood board to be dried meets the parallel grain tendency condition. determining, based on a result of determining that the warping tendency parameter of the wood board to be dried does not meet the condition of the tendency to warp along the grain, that the wood board to be dried belongs to a non-tendency-to-warp-along-the-grain category; the condition of the tendency to warp along the grain is that the warping tendency parameter exceeds a preset warping tendency parameter threshold. 6.The cloud platform-based intelligent monitoring system for whole-process furniture manufacturing according to claim 5, characterized in that, The drying pre-adjustment module is configured to determine an adjustment mode for pre-drying the wood board to be dried, wherein the drying pre-adjustment module determines, based on a result of determining that the wood board to be dried belongs to the tendency-to-warp-along-the-grain category, a growth range of drying humidity and a reduction range of drying temperature according to the grain feature vectors; based on a result of determining that the wood board to be dried belongs to the non-tendency-to-warp-along-the-grain category, the drying pre-adjustment module determines a growth range of pre-drying preheating time according to the board discrete feature parameters. 7.The cloud platform-based intelligent monitoring system for whole-process furniture manufacturing according to claim 6, characterized in that, The drying pre-adjustment module is configured to determine a growth range of drying humidity and a reduction range of drying temperature, wherein the growth range of the drying humidity is positively correlated with the warping tendency parameter; the reduction range of the drying temperature is positively correlated with the warping tendency parameter. 8.The cloud platform-based intelligent monitoring system for whole-process furniture manufacturing according to claim 7, characterized in that, The drying pre-adjustment module is configured to determine a growth range of pre-drying preheating time, wherein the growth range of the preheating time is positively correlated with the variance of the board discrete feature parameters. 9.The cloud platform-based intelligent monitoring system for whole-process furniture manufacturing according to claim 8, characterized in that, The adjustment verification module is configured to determine a distortion tendency parameter according to a comparison of the grain feature vectors before and after pre-drying, wherein The adjustment verification module is configured to calculate the average vector angle of the grain feature vectors before and after pre-drying, respectively; the absolute value of the difference between the average vector angles before and after pre-drying is determined as the distortion tendency parameter. 10.The cloud platform-based intelligent monitoring system for whole-process furniture manufacturing according to claim 9, wherein, The adjustment verification module is configured to determine whether to issue an abnormal early warning signal, wherein the adjustment verification module determines to issue the abnormal early warning signal based on a result of determining that the distortion tendency parameter of the wood board to be dried does not meet a reasonable adjustment condition; the reasonable adjustment condition is that the distortion tendency parameter does not exceed a preset distortion tendency parameter threshold.

Images