Leather Drying Process Control System Based on Data Fusion

Abstract

This invention relates to the field of leather production technology and discloses a leather drying process control system based on data fusion for use in a flat-plate vacuum dryer. The system includes a multi-source data acquisition module, a drying state model construction module, a zoned dynamic control module, and an endpoint determination module. The multi-source data acquisition module includes a multi-point temperature sensor array arranged in each independent heating zone of the heating plate, a humidity sensor installed at the exhaust port of the vacuum chamber, and a shrinkage rate detection sensor installed on the leather fixing clamp. This invention monitors the temperature distribution of each zone of the heating plate in real time through the multi-point temperature sensor array. When a local temperature difference exceeds a preset threshold, the auxiliary heater in that area is automatically activated for compensation, effectively eliminating the inherent temperature field unevenness of the heating plate and ensuring a more uniform drying rate across all parts of the leather, avoiding localized over-drying or under-drying.

Description

Technical Field

[0001] This invention relates to the field of leather production technology, and more specifically to a leather drying process control system based on data fusion. Background Technology

[0002] Flat-plate vacuum drying is the most widely used drying process in leather production lines. It heats wet leather on a heating plate under vacuum negative pressure, causing moisture to evaporate rapidly at a lower temperature. This method offers advantages such as high drying efficiency and a smooth finished product. In existing technologies, vacuum drying equipment typically uses an integral heating plate to heat the entire piece of leather and relies on a vacuum pump to maintain a uniform vacuum level throughout the drying chamber.

[0003] However, existing vacuum drying systems have the following technical drawbacks: Due to limitations in the internal flow channel design, large-area heating plates suffer from unavoidable temperature unevenness, often resulting in significant temperature differences between the center and edges, and between different areas, leading to inconsistent drying rates in different parts of the same piece of leather. Furthermore, determining the drying endpoint relies on manual experience or timed control, which can easily lead to over-drying or insufficient drying, and there is a lack of effective methods to address post-drying moisture regain. Summary of the Invention

[0004] The purpose of this invention is to provide a data fusion-based leather drying process control system to solve the above-mentioned technical problems:

[0005] The objective of this invention can be achieved through the following technical solutions:

[0006] A data fusion-based leather drying process control system for flat-plate vacuum dryers includes a multi-source data acquisition module, a drying state model construction module, a zoned dynamic control module, and an endpoint determination module.

[0007] The multi-source data acquisition module includes a multi-point temperature sensor array arranged in each independent heating zone of the heating plate, a humidity sensor installed at the exhaust port of the vacuum chamber, and a shrinkage detection sensor installed on the leather fixing clamp.

[0008] The dry state model construction module receives real-time data collected by the multi-source data acquisition module and constructs a visualized three-dimensional spatiotemporal distribution map of temperature, humidity, and shrinkage rate.

[0009] The zone dynamic control module independently adjusts the heating power of each heating zone and the local vacuum degree of the corresponding zone according to the uneven drying area shown in the three-dimensional spatiotemporal distribution map.

[0010] The endpoint determination module combines the shrinkage rate change rate and exhaust humidity change rate of all regions to determine the shutdown timing and issue a shutdown command.

[0011] As a further technical solution, the specific process by which the zone dynamic control module adjusts the heating power of each heating zone includes:

[0012] Real-time calculation of the average temperature value of the temperature sensor array in each zone and temperature space standard deviation Where i is the partition index and t is the time; set the target temperature range [ and maximum permissible temperature difference threshold ;

[0013] like Then according to the deviation The heating power duty cycle is calculated using a PID control algorithm. The calculation formula is:

[0014] in , , These are preset proportional coefficients, integral coefficients, and differential coefficients, with limitations. The range of values ​​is a closed interval ;like Then stop heating, that is: .

[0015] As a further technical solution, the specific process of adjusting the heating power of each heating zone also includes:

[0016] Perform uniformity correction control and determine the internal temperature space standard deviation for each partition i. Is it greater than ;like Then the minimum temperature point within that partition is identified. The location of the minimum temperature point is determined, and auxiliary heaters within a preset radius around that point are activated only until the minimum temperature is met. .

[0017] As a further technical solution, the process of the partitioned dynamic control module adjusting the local vacuum degree includes:

[0018] The instantaneous shrinkage rate S(j,t) at different detection points on the leather is acquired in real time using the shrinkage rate detection sensor, and its rate of change is calculated. Where j is the detection point index, corresponding to different vacuum regulating valve areas; with all detection points The maximum value is used as the target rate of change. ;

[0019] Calculate the velocity deviation at point j. Set a threshold for slow speed. Too fast threshold and dead zone threshold And satisfy:

[0020] According to deviation Determine the rate status:

[0021] like If so, it is judged as a state that is too slow; if If so, it is judged as an excessively fast state; if If so, it is considered a normal state; if If so, it is determined to be in a fine-tuning state.

[0022] As a further technical solution, the process of determining the endpoint and executing the anti-moisture reaction by the endpoint determination module includes:

[0023] Calculate the global mean of the rate of change of shrinkage at all detection points. and global standard deviation Calculate exhaust humidity Within the preset time window Average attenuation rate within : ;

[0024] The drying process is considered complete and an endpoint signal is generated when all three of the following conditions are met simultaneously:

[0025] ,in The first threshold; ,in The second threshold; ,in This is the third threshold.

[0026] Upon receiving the endpoint signal, the vacuum pump stops pumping air and dry hot air is introduced into the drying chamber. Once the pressure inside the drying chamber returns to normal, the air continues to be introduced for the preset duration. After the duration ends, the air introduction stops.

[0027] As a further technical solution, the system also includes a human-computer interaction interface for displaying the three-dimensional spatiotemporal distribution map in real time and highlighting areas with a risk of uneven drying in the form of warning zones. The criteria for determining the risk of uneven drying are: the spatial standard deviation of the temperature in the area is greater than the maximum permissible temperature difference threshold, or the rate of change of the shrinkage rate at that point is greater than or equal to the dead zone threshold.

[0028] As a further technical solution, the shrinkage rate detection sensor includes a laser displacement sensor and a vision camera, which non-contactly measures the positional changes of fixed points on the edge of the leather at different time points and calculates the area shrinkage rate of the leather in real time.

[0029] The beneficial effects of this invention are:

[0030] (1) The present invention monitors the temperature distribution of each zone of the heating plate in real time through a multi-point temperature sensor array. When the local temperature difference exceeds the preset threshold, the auxiliary heater in that area is automatically activated to compensate, effectively eliminating the inherent temperature field unevenness of the heating plate, making the drying rate of each part of the whole leather tend to be consistent, and avoiding the phenomenon of local over-drying or under-drying.

[0031] (2) This invention uses the shrinkage rate change rate of leather as a direct characterization index of drying rate. By comparing the deviation between the shrinkage rate of each detection point and the global maximum rate, and combining the current moisture content of the leather, a graded step-by-step adjustment strategy is adopted to automatically adjust the opening degree of the micro vacuum valve in each area. For areas where drying is too slow, the vacuum degree is increased to accelerate moisture evaporation, and for areas where drying is too fast, the vacuum degree is decreased to slow down the drying speed, thereby achieving a dynamic balance of drying rate;

[0032] (3) After determining the drying endpoint, the present invention first stops the vacuum pump, then fills the drying chamber with dry hot air at the set temperature and dew point, and continues to fill the chamber for a period of time after the pressure returns to normal pressure, so that the humidity inside and outside the leather is fully balanced before opening the door, which effectively prevents the moisture content of the dried leather from rebounding due to the adsorption of environmental moisture. Attached Figure Description

[0033] The invention will now be further described with reference to the accompanying drawings.

[0034] Figure 1 This is a framework diagram of the leather drying process control system based on data fusion in this invention. Detailed Implementation

[0035] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0036] Please see Figure 1 As shown, a data fusion-based leather drying process control system is used in a flat-plate vacuum dryer, including a multi-source data acquisition module, a drying state model construction module, a zoned dynamic control module, and an endpoint determination module.

[0037] The multi-source data acquisition module includes a multi-point temperature sensor array arranged in each independent heating zone of the heating plate, a humidity sensor installed at the exhaust port of the vacuum chamber, and a shrinkage rate detection sensor installed on the leather fixing clamp. The multi-point temperature sensor array, arranged in each independent heating zone of the heating plate and embedded 0.5mm to 2mm below the surface of the heating plate, is used to collect real-time temperature distribution data for each zone. The humidity sensor, installed at the exhaust port of the vacuum chamber, is used to collect real-time changes in exhaust humidity. The shrinkage rate detection sensor, installed on the leather fixing clamp, is a non-contact displacement detection device based on machine vision, including an industrial digital camera installed outside the observation window of the drying chamber and a high-contrast marker set on the edge of the elastic clamp, used to collect real-time shrinkage rate data at various detection points on the leather.

[0038] The dry state model construction module receives real-time data collected by the multi-source data acquisition module and constructs a visualized three-dimensional spatiotemporal distribution map of temperature, humidity, and shrinkage rate.

[0039] The zone dynamic control module is configured to independently adjust the heating power of the corresponding heating zone and adjust the local vacuum level by controlling the opening of the micro vacuum regulating valve in the corresponding zone, based on the uneven drying regions identified in the three-dimensional spatiotemporal distribution map where the rate of change of shrinkage is lower than the global average.

[0040] The endpoint determination module combines the shrinkage rate change rate and exhaust humidity change rate of all regions to determine the shutdown timing and issue a shutdown command.

[0041] Through the above technical solution, this embodiment integrates multi-source data of temperature, humidity and shrinkage rate to construct a three-dimensional spatiotemporal distribution map, and independently adjusts the heating power and local vacuum degree in different areas accordingly. Finally, the drying endpoint is determined by a combination of multiple conditions, including the shrinkage rate change rate and the exhaust humidity decay rate, so as to achieve precise closed-loop control of the leather drying process.

[0042] The specific process by which the dynamic control module adjusts the heating power of each heating zone includes:

[0043] Real-time calculation of the average temperature value of the temperature sensor array in each zone and temperature space standard deviation Where i is the partition index and t is the time; set the target temperature range [ and maximum permissible temperature difference threshold ;

[0044] like Then according to the deviation The heating power duty cycle is calculated using a PID control algorithm. The calculation formula is:

[0045] in , , These are preset proportional coefficients, integral coefficients, and differential coefficients, with limitations. The range of values ​​is a closed interval ;like Then stop heating, that is: .

[0046] The specific process of adjusting the heating power of each heating zone also includes:

[0047] Perform uniformity correction control and determine the internal temperature space standard deviation for each partition i. Is it greater than ;like Then the minimum temperature point within that partition is identified. The location of the minimum temperature point is determined, and auxiliary heaters within a preset radius around that point are activated only until the minimum temperature is met. .

[0048] Through the above technical solution, this embodiment provides a specific process for adjusting the heating power of each heating zone. A multi-point temperature sensor array monitors the temperature distribution of each zone of the heating plate in real time. When a local temperature difference exceeds a preset threshold, the auxiliary heater in that area is automatically activated for compensation, effectively eliminating the inherent uneven temperature field problem of the heating plate and ensuring a more uniform drying rate across all parts of the leather, avoiding localized over-drying or under-drying.

[0049] The process by which the partition dynamic control module adjusts the local vacuum level includes:

[0050] The instantaneous shrinkage rate S(j,t) at different detection points on the leather is obtained in real time using the shrinkage rate detection sensor, specifically the area shrinkage rate.

[0051] The specific method for obtaining the shrinkage rate S(j,t) is as follows: Before drying begins, record the initial position of the marker at each detection point. During the drying process, the camera continuously acquires images at a preset sampling frequency, and the real-time position of each marker is identified through image processing algorithms. ; Calculate the displacement:

[0052] Since leather shrinkage mainly occurs along its length, the area shrinkage rate is... With linear shrinkage rate The relationship is:

[0053] The formula for calculating the linear shrinkage rate is: In the formula, This represents the initial distance between the detection points. It should also be noted that when... When the value is small (e.g., less than 5%), an approximate formula can be used to simplify the calculation: .

[0054] Calculate its rate of change Where j is the detection point index, corresponding to different vacuum regulating valve areas; with all detection points The maximum value is used as the target rate of change. ;

[0055] Calculate the velocity deviation at point j. Set a threshold for slow speed. Too fast threshold and dead zone threshold And satisfy:

[0056] According to deviation Determine the rate status:

[0057] like If so, it is judged as a state that is too slow; if If so, it is judged as an excessively fast state; if If so, it is considered a normal state; if If so, it is determined to be in a fine-tuning state.

[0058] After the assessment is completed, the adjustment amount is determined based on the moisture content:

[0059] Obtain the current average moisture content of the leather. Specifically, it can be calculated by integrating the measured values ​​from the exhaust humidity sensor.

[0060] Two moisture content thresholds are set: a high moisture content threshold and a low moisture content threshold. and low moisture content threshold , %

[0061] Set multiple preset adjustment steps, including large adjustment steps. Medium-amplitude adjustment step size Slightly adjust the step size Fine-tuning step size And satisfy:

[0062] Determine the aperture adjustment amount based on the rate state and moisture content range. :

[0063] Too slow state and ,but ;

[0064] Too slow state and ,but ;

[0065] Too slow state and ,but ;

[0066] Too fast and ,but ;

[0067] Too fast and ,but ;

[0068] Under normal circumstances, ;

[0069] Fine-tuning the state and ,but ;

[0070] Fine-tuning the state and ,but .

[0071] Then calculate the new valve opening.

[0072] Will Limited to a preset physical opening range Internal, i.e., final valve opening degree

[0073] Output control signals to drive the micro vacuum regulating valve in the corresponding area to perform opening changes.

[0074] Through the above technical solution, this embodiment provides a process for adjusting the local vacuum level. Specifically, using the leather shrinkage rate change rate as a direct indicator of the drying rate, by comparing the deviation of the shrinkage rate at each detection point from the global maximum rate, and combining this with the current moisture content of the leather, a graded, step-by-step adjustment strategy is adopted to automatically adjust the opening of the micro-vacuum valves in each area. For areas where drying is too slow, the vacuum level is increased to accelerate moisture evaporation; for areas where drying is too fast, the vacuum level is decreased to slow down the drying speed, thus achieving a dynamic balance in the drying rate.

[0075] The process of the endpoint determination module completing the determination and executing the anti-moisture-reversion procedure includes:

[0076] Calculate the global mean of the rate of change of shrinkage at all detection points. and global standard deviation :

[0077] ;

[0078] Where N is the total number of detection points;

[0079] Calculate exhaust humidity Within the preset time window Average attenuation rate within : ;

[0080] The drying process is considered complete and an endpoint signal is generated when all three of the following conditions are met simultaneously:

[0081] ,in The first threshold (the upper limit of the rate of change of shrinkage, with a value of 0.05~0.1% per second);

[0082] ,in The second threshold (the upper limit of the shrinkage rate consistency, with a value of 0.02~0.05% per second);

[0083] ,in The third threshold (the upper limit of humidity decay rate, with a value of 0.1~0.5% relative humidity per second).

[0084] Upon receiving the endpoint signal, the vacuum pump stops, and hot dry air is introduced into the drying chamber. The hot dry air setting parameters are: temperature... Dew point Once the pressure inside the drying chamber returns to normal, continue inflation for a preset time of 10±2 seconds to balance the humidity inside and outside the leather; stop inflation after the maintenance time ends.

[0085] Through the above technical solution, this embodiment provides a process for the endpoint determination module to determine completion and execute the anti-moisture-rebound process. Specifically, after determining the drying endpoint, the vacuum pump is stopped first, and then dry hot air with a set temperature and dew point is introduced into the drying chamber. After the pressure returns to normal, the air is continued to be supplied for a period of time to fully balance the internal and external humidity of the leather before the door is opened. This effectively prevents the moisture content of the dried leather from rebounding due to the absorption of environmental moisture.

[0086] The system also includes a human-computer interaction interface for real-time display of the three-dimensional spatiotemporal distribution map. This interface includes a display screen and a graphical rendering engine. The display screen shows the three-dimensional spatiotemporal distribution map generated by the drying state model construction module in real time. The graphical rendering engine highlights areas at risk of uneven drying on the three-dimensional spatiotemporal distribution map with bright colors. Warning areas are presented with flashing colors or reddish-brown gradients that distinguish them from normal areas, and operators can view specific parameter values ​​for these areas by touching or clicking with a mouse.

[0087] The shrinkage rate detection sensor includes a laser displacement sensor or a vision camera, which non-contactly measures the positional changes of fixed points on the leather edge at different time points to calculate the area shrinkage rate of the leather in real time. Specifically, for example, an industrial digital camera is used, installed outside the observation window of the drying chamber of the flat-panel vacuum dryer, with the lens optical axis perpendicular to the leather plane, a resolution of no less than 5 million pixels, and a sampling frequency of no less than 10 frames per second.

[0088] This invention can be a system, method, and / or computer program product. A computer program product may include a computer-readable storage medium having computer-readable program instructions loaded thereon for causing a processor to implement various aspects of the invention.

[0089] Computer-readable storage media can be tangible devices capable of holding and storing instructions for use by an instruction execution device. Computer-readable storage media can be, for example, electrical storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory sticks, floppy disks, mechanical encoding devices, such as punch cards or recessed protrusions storing instructions thereon, and any suitable combination thereof. The computer-readable storage media used herein are not to be construed as transient signals themselves, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses through fiber optic cables), or electrical signals transmitted through wires.

[0090] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to the computer-readable storage media in the respective computing / processing device.

[0091] While the present invention has been disclosed above, its scope of protection is not limited thereto. Those skilled in the art can make various changes and modifications without departing from the spirit and scope of the present invention, and all such changes and modifications will fall within the scope of protection of the present invention.

Claims

1. A data fusion-based leather drying process control system for a flat-plate vacuum dryer, characterized in that: include: The multi-source data acquisition module includes a multi-point temperature sensor array arranged in each independent heating zone of the heating plate, a humidity sensor installed at the exhaust port of the vacuum chamber, and a shrinkage detection sensor installed on the leather fixing clamp. The dry state model construction module receives real-time data collected by the multi-source data acquisition module and constructs a visualized three-dimensional spatiotemporal distribution map of temperature, humidity, and shrinkage rate. The zone dynamic control module independently adjusts the heating power of each heating zone and the local vacuum degree of the corresponding zone according to the uneven drying area shown in the three-dimensional spatiotemporal distribution map. The endpoint determination module combines the shrinkage rate change rate and exhaust humidity change rate of all regions to determine the shutdown timing and issue a shutdown command.

2. The leather drying process control system based on data fusion according to claim 1, characterized in that, The specific process by which the dynamic control module adjusts the heating power of each heating zone includes: Real-time calculation of the average temperature value of the temperature sensor array in each zone and temperature space standard deviation Where i is the partition index and t is the time; set the target temperature range [ and maximum permissible temperature difference threshold ; like Then according to the deviation The heating power duty cycle is calculated using a PID control algorithm. The calculation formula is: in , , These are preset proportional coefficients, integral coefficients, and differential coefficients, with limitations. The range of values ​​is a closed interval ;like Then stop heating, that is: .

3. The leather drying process control system based on data fusion according to claim 2, characterized in that, The specific process of adjusting the heating power of each heating zone also includes: Perform uniformity correction control and determine the internal temperature space standard deviation for each partition i. Is it greater than ;like Then the minimum temperature point within that partition is identified. The location of the minimum temperature point is determined, and auxiliary heaters within a preset radius around that point are activated only until the minimum temperature is met. .

4. The leather drying process control system based on data fusion according to claim 3, characterized in that, The process by which the partition dynamic control module adjusts the local vacuum level includes: The instantaneous shrinkage rate S(j,t) at different detection points on the leather is acquired in real time using the shrinkage rate detection sensor, and its rate of change is calculated. Where j is the detection point index, corresponding to different vacuum regulating valve areas; with all detection points The maximum value is used as the target rate of change. ; Calculate the velocity deviation at point j. Set a threshold for slow speed. Too fast threshold and dead zone threshold And satisfy: According to deviation Determine the rate status: like If so, it is judged as a state that is too slow; if If so, it is judged as an excessively fast state; if If so, it is considered a normal state; if If so, it is determined to be in a fine-tuning state.

5. The leather drying process control system based on data fusion according to claim 4, characterized in that, The process of determining the completion of the endpoint determination module and executing the anti-moisture reversion process includes: Calculate the global mean of the rate of change of shrinkage at all detection points. and global standard deviation Calculate exhaust humidity Within the preset time window Average attenuation rate within : ; The drying process is considered complete and an endpoint signal is generated when all three of the following conditions are met simultaneously: ,in The first threshold; ,in The second threshold; ,in The third threshold; Upon receiving the endpoint signal, the vacuum pump stops pumping air and dry hot air is introduced into the drying chamber. Once the pressure inside the drying chamber returns to normal, the air continues to be introduced for the preset duration. After the duration ends, the air introduction stops.

6. The leather drying process control system based on data fusion according to claim 5, characterized in that, The system also includes a human-computer interaction interface for displaying the three-dimensional spatiotemporal distribution map in real time and highlighting areas with uneven drying risk in the form of warning areas; wherein, the judgment condition for uneven drying risk is: the temperature spatial standard deviation of the area is greater than the maximum allowable temperature difference threshold, or the shrinkage rate change rate deviation of the point is greater than or equal to the dead zone threshold.

7. The leather drying process control system based on data fusion according to claim 6, characterized in that, The shrinkage rate detection sensor includes a laser displacement sensor and a vision camera. It measures the positional changes of fixed points on the edge of the leather at different time points in a non-contact manner and calculates the area shrinkage rate of the leather in real time.

Images