Optimization method and system for metal ceramic mixture spraying process and medium

Abstract

The invention relates to the technical field of spraying process optimization, and discloses an optimization method and system for a metal ceramic mixture spraying process and a medium. The method comprises the steps that an atomization angle image at a nozzle is shot in real time and transmitted to an information processor, an atomization angle is calculated based on the atomization angle image and compared with a preset value, when the atomization angle is smaller than a first preset value, a rapping device is triggered to vibrate a spray gun, whether the atomization angle is recovered to a third preset value or not is judged after first preset time, and if not, the next step is executed; when the atomization angle is smaller than a second preset value, the spraying slurry is switched to be high-pressure absolute ethyl alcohol, after a second preset time, the slurry is switched back, whether the atomization angle is recovered to a third preset value or not is judged, if not, the spraying pressure and the slurry viscosity are detected, an alarm signal is sent to prompt an operator to adjust, and the operation is finished. While the stability and quality of the spraying process are improved, the operation risk and cost can be reduced, and the production efficiency is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of cermet material spraying processes, and particularly relates to an optimization method, system and medium for the spraying process of cermet mixtures. More specifically, it relates to an optimization method, system and medium for the spraying process of cermet mixtures based on real-time image analysis and hierarchical control. Background Art

[0002] Currently, during the spraying process of cermet slurries, the atomization angle sometimes becomes smaller. This may be due to some powders blocking the nozzle of the spray gun, or a change in the viscosity of the slurry, or a decrease in the spraying pressure, which causes the spray atomization angle to decrease. If not dealt with in a timely manner, it will not only reduce the spraying efficiency, but also change the particle shape and size of the powders after spray drying, affecting the uniformity of the powders. If the nozzle is blocked by powders, removing the spray gun to replace or clean the nozzle will cause the spraying to pause, the tower pressure to drop, and some air to enter the spray tower, which is likely to introduce pollutants, and the process is troublesome and time-consuming. If the spraying pressure or the viscosity of the slurry changes, it is difficult for the operator to detect in a timely manner. If not dealt with in a timely manner, it will affect the spraying process. Therefore, an automatic feedback control system is needed to solve this problem.

[0003] A similar prior art is the Chinese patent application with the publication number CN114951667A, which discloses a method for preventing nozzle blockage in the gas atomization preparation of metal powders. It uses the method of pressurizing the metal material in the induction furnace body to atomize the metal material, and utilizes the pressure difference between the induction furnace body and the atomization chamber to increase the driving force of the metal liquid flowing through the nozzle to avoid nozzle blockage. This method prevents or eliminates blockage by adjusting the pressure, and the means are relatively single. The driving force of the liquid flowing through the nozzle is not only related to the pressure, but also related to the liquid concentration, etc. Without considering the liquid concentration, simply adjusting the pressure to prevent blockage has certain safety risks. At the same time, in the case of nozzle blockage or a tendency to block, there are no corresponding technical means.

[0004] Therefore, it is an urgent problem to provide an optimization method, system and medium for the spraying process of cermet mixtures to effectively avoid and eliminate nozzle blockage, improve the stability and quality of the spraying process. Summary of the Invention

[0005] The present application provides an optimization method, system and medium for the spraying process of cermet mixtures. By means of real-time monitoring, hierarchical adjustment, multi-parameter comprehensive control, image processing technology, etc., it improves the stability and quality of the spraying process, enhances the adaptability and flexibility of the system, improves the detection accuracy and reliability, and at the same time reduces the operation risk and cost. While improving the production efficiency, it also enhances the robustness and versatility of the system, having important practical application value.

[0006] In a first aspect, the present application provides an optimization method for a cermet mixture spraying process, the method comprising:

[0007] Step 1, during the spraying process, a real-time atomization angle image at the nozzle is taken and transmitted to an information processor;

[0008] Step 2, the information processor calculates the atomization angle based on the atomization angle image, compares the atomization angle with an angle preset value. When the atomization angle is less than a first preset value, step 3 is entered. When the atomization angle is less than a second preset value, step 4 is entered, where the first preset value is greater than the second preset value;

[0009] Step 3, trigger the vibrating device to vibrate the spray gun, and after a first preset time, turn off the vibrating device. Determine whether the atomization angle has recovered to a third preset value. If not, enter step 4, where the third preset value is greater than the first preset value;

[0010] Step 4, switch the spray slurry to high-pressure anhydrous ethanol, and after a second preset time, switch back to the spray slurry. Determine whether the atomization angle has recovered to the third preset value. If not, enter step 5;

[0011] Step 5, through a spray pressure detection device, detect whether the current spray pressure is abnormal. If so, send a first alarm signal to prompt the operator to adjust the spray pressure. If not, detect the slurry viscosity through a viscosity detection device, and then send a second alarm signal to prompt the operator to adjust the amount of anhydrous ethanol added.

[0012] Combined with the first aspect, in the first implementation manner of the first aspect of the present application, in step 2, when it is determined that the atomization angle is less than the first preset value, it further includes:

[0013] Obtain the historical vibration data of the nozzle within a third preset time, perform feature analysis on the historical vibration data, and calculate the change rate of specific vibration parameters;

[0014] When the change rate is less than or equal to the corresponding preset threshold, enter step 3;

[0015] When the change rate is greater than the preset threshold, enter step 5.

[0016] Combined with the first aspect, in the second implementation manner of the first aspect of the present application, the specific vibration parameter includes vibration acceleration; and / or

[0017] The specific vibration parameter includes vibration amplitude and vibration frequency.

[0018] Combined with the first aspect, in the third implementation manner of the first aspect of the present application, a gas emitter and an image acquisition device are arranged above the slurry container. In step 5, detecting the slurry viscosity through a viscosity detection device includes:

[0019] Step 51: Obtain the initial viscosity of the slurry and the relative distance between the slurry surface and the gas emitter, and select the corresponding gas flow rate based on the initial viscosity and the relative distance;

[0020] Step 52: The gas emitter applies a gas impact to the slurry surface based on the gas flow rate and obtains an image of the slurry surface at the fourth preset time;

[0021] Step 53: Extract the outermost reference wave peak contour line in the slurry surface image, calculate the length of the reference wave peak contour line, and define it as the edge line length;

[0022] Step 54: Input the relative distance, the gas flow rate, and the edge line length into a preset function to obtain the slurry viscosity.

[0023] Combined with the first aspect, in the fourth implementation manner of the first aspect of the present application, step 53 includes:

[0024] Step 531: Preprocess the slurry surface image to obtain a preprocessed image;

[0025] Step 532: Assign a region identifier to each closed region in the preprocessed image and extract the region edge line of each closed region;

[0026] Step 533: Extract the edge pixel point at the uppermost part of the first region edge line and define it as the reference pixel point. Obtain N1 reference center points at a preset distance from the reference pixel point according to the first preset rule, where the first region edge line is the region edge line located at the uppermost part of the preprocessed image;

[0027] Step 534: Set a first relative distance based on the preset distance, extract any reference center point, and obtain N2 relative pixel points at the first relative distance from any reference center point according to the second preset rule. Determine whether the region identifiers corresponding to the N2 relative pixel points are all the first region identifier. If not, go to step 535; if so, go to step 537, where the first region identifier is the region identifier of the closed region surrounded by the region edge line corresponding to the reference pixel point;

[0028] Step 535: Reduce the preset distance by a fourth preset value to generate a new preset distance, and determine whether the new preset distance exceeds the preset range. If not, return to step 533; if so, go to step 536;

[0029] Step 536: Use the edge pixel point connected to the reference pixel point and not searched for the reference center point as the new reference pixel point. Determine whether the selection times of the new reference pixel point are greater than the fifth preset value. If not, return to step 533; if so, use the region edge line below the first region edge line as the new first region edge line, and then return to step 533;

[0030] Step 537: Take any reference center point as the center of the reference wave crest contour line, take the first region edge line as the reference wave crest contour line, and calculate the edge line length based on the preset distance corresponding to any reference center point.

[0031] Combined with the first aspect, in the fifth implementation manner of the first aspect of the present application, the preprocessing includes:

[0032] Perform histogram equalization on the surface image of the slurry to generate a first image;

[0033] Obtain the first intensity values of each color component at any pixel point in the first image, perform weighted average on all the first intensity values to obtain a weighted average value, and determine whether the weighted average value is greater than or equal to the intensity threshold. If so, set the intensity values of each color component at any pixel point to the intensity maximum value. If not, set the intensity values of each color component at any pixel point to the intensity minimum value. After traversing all pixel points, generate a second image;

[0034] Perform edge extraction processing on the second image to extract the edge lines of each object, and then calculate the line segment length of each edge line. When the line segment length of any edge line is less than the sixth preset value, calculate the proximity of any edge line to the ideal straight line. When the proximity is greater than the seventh preset value, delete any edge line. After traversing all edge lines, generate a third image;

[0035] Check the connectivity of any edge line in the third image. If any edge line does not form a closed loop, use morphological operations to close any edge line. After traversing all edge lines, generate a preprocessed image.

[0036] Combined with the first aspect, in the sixth implementation manner of the first aspect of the present application, the first preset rule is to take the reference pixel point as the origin, take the vertically downward direction as the polar axis direction, and sequentially obtain reference center points at the first preset angle interval;

[0037] The second preset rule is to take any reference center point as the origin, take the vertically downward direction as the polar axis direction, and sequentially obtain relative pixel points at the second preset angle interval.

[0038] In the second aspect, the present application provides an optimization system for the spray process of cermet mixture. The system includes: an imaging device and an information processor. The information processor includes an image analysis module, a first operation module, a second operation module, and an anomaly detection module;

[0039] The imaging device is used to, during the spraying process, capture the atomization angle image at the nozzle in real time and transmit the atomization angle image to the information processor;

[0040] An image analysis module, which is used to calculate the atomization angle according to the atomization angle image, compare the atomization angle with a preset angle value. When the atomization angle is less than the first preset value, it enters the first operation module. When the atomization angle is less than the second preset value, it enters the second operation module, where the first preset value is greater than the second preset value;

[0041] The first operation module is used to trigger the vibrating device to vibrate the spray gun, turn off the vibrating device after the first preset time, and judge whether the atomization angle has recovered to the third preset value. If not, it enters the second operation module, where the third preset value is greater than the first preset value;

[0042] The second operation module is used to switch the spray slurry to high-pressure anhydrous ethanol, switch back to the spray slurry after the second preset time, and judge whether the atomization angle has recovered to the third preset value. If not, it enters the abnormal detection module;

[0043] The abnormal detection module is used to detect whether the current spray pressure is abnormal through a spray pressure detection device. If so, it sends out a first alarm signal to prompt the operator to make adjustments. If not, it detects the slurry viscosity through a viscosity detection device, and then sends out a second alarm signal to prompt the operator to adjust the addition amount of anhydrous ethanol.

[0044] The third aspect of the present application provides a computer-readable storage medium, in which instructions are stored. When it runs on a computer, it enables the computer to execute the above-mentioned optimization method for the spray process of cermet mixture.

[0045] Compared with the prior art, the beneficial effects of the technical solution of the present application are at least as follows:

[0046] 1. By taking and analyzing the atomization angle image at the nozzle in real time, the deviation of the atomization angle can be found in time, and a rapid response can be made through a hierarchical adjustment mechanism to achieve the recovery of the atomization angle. While solving the problem of nozzle blockage and ensuring the stability of the spray process, it reduces manual intervention, improves production efficiency, and has high adaptability and flexibility.

[0047] 2. Not only monitoring the atomization angle, but also detecting parameters such as spray pressure and slurry viscosity, it can accurately diagnose possible problems in the spray process, such as abnormal spray pressure or inappropriate slurry viscosity, etc., providing a clear adjustment direction for the operator. Through non-contact detection methods such as image processing and gas impact, direct contact with the slurry is avoided, corrosion and pollution of the equipment are reduced, and the operation safety is improved.

[0048] 3. Automated processing and accurate diagnosis reduce the fault time, avoid unnecessary adjustment measures, and have simple operation and short time consumption, reducing the maintenance cost and production cost, and can improve the enterprise's benefit revenue. Description of the Drawings

[0049] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can also be obtained based on these drawings.

[0050] Figure 1 It is a schematic diagram of an embodiment of an optimization method for the spray process of cermet mixture in the embodiments of the present application;

[0051] Figure 2 It is a schematic diagram of an embodiment of the atomization angle image in the embodiments of the present application;

[0052] Figure 3 It is a schematic diagram of the installation of the spray device in the embodiments of the present application;

[0053] Figure 4 It is a schematic diagram of the installation of the rapping device in the embodiments of the present application;

[0054] Figure 5 It is the first schematic diagram of the preprocessing image in the embodiments of the present application;

[0055] Figure 6 It is the second schematic diagram of the preprocessing image in the embodiments of the present application;

[0056] Figure 7 It is a schematic diagram of an embodiment of an optimization system for the spray process of cermet mixture in the embodiments of the present application;

[0057] Among them, 1 is a spray tower, 2 is a nozzle, 3 is a rapping device, 4 is a fixed bayonet, 5 is a rapping hammer, and 6 is a spray gun. Detailed implementation manners

[0058] The embodiments of the present application provide an optimization method, system and medium for the spray process of cermet mixture. The terms "first", "second", "third", "fourth", etc. (if any) in the specification, claims and accompanying drawings of the present application are used to distinguish similar objects, and do not necessarily describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments described here can be implemented in an order other than that illustrated or described here. In addition, the terms "include" or "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units does not necessarily limit to those clearly listed steps or units, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0059] For ease of understanding, the specific process of the embodiments of the present application will be described below. Please refer to Figure 1 An embodiment of the optimization method for the metal-ceramic mixture spraying process in the embodiments of the present application includes:

[0060] Step 1: During the spraying process, the atomization angle image at the nozzle is captured in real time, and the atomization angle image is transmitted to the information processor.

[0061] The installation schematic diagram of the spraying device is as shown in Figure 3 shown, and the schematic diagram of the atomization angle image is as shown in Figure 2 shown.

[0062] Specifically, a high-resolution camera or a high-speed camera is installed near the nozzle, and an appropriate acquisition frequency is set according to the process requirements, such as acquiring several frames or dozens of frames per second, to ensure that the dynamic changes during the atomization process can be captured. During the spraying process, the image acquisition device in the spray tower captures the atomization angle image at the nozzle in real time according to the above acquisition frequency, and transmits the image data to the information processor by wired or wireless means.

[0063] Step 2: The information processor calculates the atomization angle based on the atomization angle image, compares the atomization angle with the angle preset value. When the atomization angle is less than the first preset value, go to Step 3; when the atomization angle is less than the second preset value, go to Step 4, where the first preset value is greater than the second preset value.

[0064] By capturing the atomization angle image at the nozzle in real time, the intuitive information of the atomization effect during the spraying process can be obtained immediately. The atomization angle is a key indicator for measuring the spraying effect and affects the spraying coverage. By calculating and comparing the atomization angle in real time, abnormal situations during the spraying process, such as nozzle blockage, slurry viscosity change, air pressure fluctuation, etc., can be detected in time, thus avoiding product quality problems or equipment damage. During the spraying process, there may be interference factors such as water vapor and dust, which affect the image quality. Before calculating the atomization angle, image enhancement techniques, such as defogging algorithms and noise suppression algorithms, are preferably used to improve the image clarity.

[0065] The first preset value and the second preset value are set according to the experience of those skilled in the art or according to the actual application scenario, and the embodiments of the present application do not limit this. Exemplarily, the first preset value is 90% of the maximum atomization angle, and the second preset value is 75% of the maximum atomization angle. When the atomization angle is less than the second preset value, it indicates that there is a serious deviation in the atomization angle, the nozzle blockage is relatively serious, and the atomization effect of the spray has seriously deviated from the normal range, and relatively radical adjustment measures may be required; when the atomization angle is greater than the second preset value but less than the first preset value, it indicates that there is a slight deviation in the atomization angle, the nozzle blockage problem is relatively light, and the atomization effect of the spray may be slightly affected, and it may be possible to return to the normal state through simple preliminary adjustment measures. By setting two preset values, hierarchical processing of the atomization angle deviation is achieved. This hierarchical strategy can avoid taking excessive adjustment measures for slight deviations, and at the same time ensure that effective remedial measures can be taken in case of serious deviations, improving the flexibility and adaptability of the system while ensuring the stability of the spraying process and product quality.

[0066] Step 3: Trigger the vibrating device to vibrate the spray gun, and turn off the vibrating device after the first preset time. Determine whether the atomization angle has returned to the third preset value. If not, go to step 4, where the third preset value is greater than the first preset value.

[0067] The installation schematic diagram of the vibrating device is as Figure 4 shown. The vibrating device is installed on the spray gun and clears the possible blockages inside the spray gun through periodic vibration. Specifically, when the atomization angle is greater than the second preset value and less than the first preset value, the vibration motor is started, and the vibrating device vibrates the spray gun according to the preset vibration parameters (frequency, amplitude, etc.) to clear the blockages at the nozzle. The first preset time is the duration of the spray gun vibration operation, which is set according to the experience of those skilled in the art or according to the actual application scenario, and the embodiments of the present application do not limit this. The setting of this time needs to be optimized according to the actual process and vibration effect to ensure that the vibration can effectively improve the atomization angle while avoiding damage to the equipment caused by excessive vibration.

[0068] The third preset value represents the ideal atomization angle range, that is, the above-mentioned maximum atomization angle, which is set according to the actual process. If the atomization angle can return to the third preset value, it indicates that the adjustment measure of vibrating the spray gun is effective and the problem has been solved, and the vibrating device can be turned off to continue the normal spraying operation.

[0069] As a preliminary response measure to the atomization angle deviation, when the problem is relatively minor, the vibrating device is automatically triggered to vibrate the spray gun to try to restore the spraying state, avoiding direct more stringent adjustments, reducing manual intervention, improving production efficiency. At the same time, by cleaning the nozzle in a timely manner, the service life of the equipment can be extended and the maintenance cost can be reduced.

[0070] Step 4: Switch the spray slurry to high-pressure absolute ethanol, and after a second preset time, switch back to the spray slurry. Determine whether the atomization angle has recovered to a third preset value. If not, proceed to Step 5.

[0071] High-pressure absolute ethanol has good solubility, volatility, and cleaning ability, and can quickly dissolve the residues or impurities at the nozzle, thus effectively removing stubborn blockages at the nozzle.

[0072] Specifically, when the atomization angle is less than the second preset value, the nozzle is cleaned with high-pressure absolute ethanol at a set pressure. The second preset time is the duration of the high-pressure absolute ethanol spray, which is optimized according to the actual process and the cleaning effect of high-pressure absolute ethanol to ensure that the high-pressure absolute ethanol can fully clean the nozzle and improve the atomization effect. The second preset time is usually short because the high-pressure absolute ethanol spray is a relatively radical adjustment measure, and long-term use may have an unnecessary impact on the spray system. In addition, the volatility of high-pressure absolute ethanol is strong, and long-term use may cause waste.

[0073] If the atomization angle can recover to the third preset value, it indicates that the adjustment measure of cleaning with high-pressure absolute ethanol is effective, and normal spray operation continues. If not, it indicates that the reduction of the atomization angle may not be caused by nozzle blockage, and further abnormal detection and processing are carried out. This hierarchical adjustment mechanism not only improves the adaptability and stability of the system, but also optimizes the use of resources, ensuring the quality and efficiency of the spray process.

[0074] Step 5: Use a spray pressure detection device to detect whether the current spray pressure is abnormal. If so, send a first alarm signal to prompt the operator to adjust the spray pressure. If not, use a viscosity detection device to detect the viscosity of the slurry, and then send a second alarm signal to prompt the operator to adjust the amount of absolute ethanol added.

[0075] After preliminary cleaning and deep washing, if the atomization angle still fails to return to normal, it is necessary to further analyze the root cause of the abnormal spraying. Specifically, a decrease in the spraying pressure will cause a decrease in the atomization angle. The spraying pressure value is detected by a pressure sensor, and the detected spraying pressure value is compared with a preset pressure range. If the pressure value exceeds the preset range, it is determined that the spraying pressure is abnormal, and a first alarm signal is issued to inform the operator that the spraying pressure needs to be adjusted. If the spraying pressure is normal, but the atomization angle still fails to return to the ideal state, the viscosity of the slurry is further detected. When the spraying pressure is constant, too high or too low viscosity of the slurry will affect the spraying effect, resulting in abnormal atomization angle and affecting the spraying effect. When the viscosity of the slurry is detected to be abnormal, a second alarm signal is issued to inform the operator that the amount of anhydrous ethanol added needs to be adjusted to change the viscosity of the slurry and make the viscosity return to the preset viscosity. The alarm signal can be used to prompt the operator by sound, light or other means. Preferably, spray pressure data can be obtained when the atomization angle is abnormal and still fails to return to normal after preliminary cleaning and deep washing, reducing the data transmission volume and data transmission pressure.

[0076] By detecting the spraying pressure and the viscosity of the slurry, further analyzing the cause of the abnormal spraying, and guiding the operator to make corresponding adjustments, the automation degree of the production process can be improved, manual intervention can be reduced, the stability of the spraying process can be quickly restored, the production efficiency can be increased, and the product quality can be ensured.

[0077] Preferably, if the problem cannot be solved by adjustment, further troubleshooting and repair may be required, such as checking components such as nozzles and pumps.

[0078] In a specific embodiment, in step 2, when it is determined that the atomization angle is less than the first preset value, it further includes:

[0079] Obtain the historical vibration data of the nozzle within the third preset time, perform feature analysis on the historical vibration data, and calculate the change rate of specific vibration parameters;

[0080] When the change rate is less than or equal to the corresponding preset threshold, enter step 3;

[0081] When the change rate is greater than the preset threshold, enter step 5.

[0082] Specifically, a vibration sensor is configured on the nozzle to monitor the vibration state of the nozzle. When it is monitored that the atomization angle is less than the first preset value, the historical vibration data of the nozzle is obtained. The historical vibration data is the vibration data within the third preset time before the moment when it is determined that the atomization angle is less than the first preset value. The third preset time is set according to the experience of those skilled in the art or according to the actual application scenario. Preferably, the third preset time is set based on the acquisition period of the vibration sensor.

[0083] When the nozzle is operating normally, the slurry passing through the nozzle will generate a certain flow rate and pressure. The flow of this fluid will generate vibrations inside the nozzle. The intensity of the vibration is closely related to the flow characteristics of the fluid (such as flow rate, pressure, etc.). The normally flowing fluid can generate stable vibrations. When the nozzle is blocked, the flow channel of the slurry becomes narrower, and the flow rate and pressure distribution of the slurry passing through the nozzle change, resulting in an increase in hydrodynamic instability. This instability will weaken the vibration intensity of the nozzle (vibration frequency, vibration amplitude, vibration acceleration, vibration speed, etc.). During the blocking process, the flow characteristics of the fluid gradually change, and the flow rate and pressure distribution of the fluid will gradually adjust, making the change in vibration intensity relatively gentle. When the spraying pressure decreases, the slurry ejection volume decreases, the atomization angle decreases, the flow rate and impact force of the fluid decrease, resulting in a decrease in vibration intensity. Moreover, the decrease in spraying pressure will cause the flow rate and impact force of the fluid to decrease rapidly. This change occurs instantaneously, so the change in vibration intensity is also relatively sudden. When the viscosity of the slurry increases, the flow resistance increases, the slurry ejection volume decreases, the atomization angle decreases, the flow rate and impact force of the fluid decrease, thereby leading to a decrease in vibration intensity. Moreover, the increase in the viscosity of the slurry will immediately affect the flow characteristics of the fluid, causing the flow rate and impact force of the fluid to decrease. This change also occurs instantaneously, so the change in vibration intensity is also relatively sudden.

[0084] As can be seen from the above, the change trend of the vibration data is relatively gentle when the nozzle is blocked, while the change trend of the vibration data is relatively sudden when the liquid concentration increases and the liquid pressure decreases. Therefore, it is possible to judge whether the nozzle is blocked based on the change rate of specific vibration parameters. When the change rate is less than or equal to the corresponding preset threshold, enter the adjustment measures corresponding to nozzle blockage; when the change rate is greater than the preset threshold, enter the detection steps of spraying parameters such as pressure.

[0085] By combining the current atomization angle and the historical vibration data of the nozzle, a more comprehensive assessment of the nozzle state can be carried out, thereby optimizing the adjustment strategy and improving the stability and efficiency of the metal ceramic mixture spraying process.

[0086] Specifically, the collected vibration signals usually contain noise and interference components and need to be preprocessed to extract useful information. Exemplarily, the vibration signals are filtered to remove high-frequency noise and low-frequency drift. A band-pass filter can be used to set a reasonable frequency range (such as 10 Hz to 10 kHz) to retain the frequency components related to the nozzle vibration.

[0087] In a specific embodiment, the specific vibration parameter includes vibration acceleration; and / or

[0088] The specific vibration parameter includes vibration amplitude and vibration frequency.

[0089] Specifically, when the change rate of the vibration acceleration is less than or equal to the corresponding preset threshold, it indicates that the nozzle is blocked; or, when the change rates of the vibration amplitude and the vibration frequency are respectively less than or equal to the corresponding preset thresholds, it indicates that the nozzle is blocked; or, when the change rates of the vibration acceleration, the vibration amplitude and the vibration frequency are respectively less than or equal to the corresponding preset thresholds, it indicates that the nozzle is blocked.

[0090] In a specific embodiment, a gas emitter and an image acquisition device are arranged above the slurry container. In step 5, detecting the slurry viscosity by the viscosity detection device includes:

[0091] Step 51: Obtain the initial viscosity of the slurry and the relative distance between the slurry surface and the gas emitter, and select the corresponding gas flow rate based on the initial viscosity and the relative distance.

[0092] Step 52: The gas emitter applies a gas impact to the slurry surface based on the gas flow rate, and acquires an image of the slurry surface at the fourth preset time.

[0093] Step 53: Extract the outermost reference wave peak contour line in the slurry surface image, calculate the length of the reference wave peak contour line, and define it as the edge line length.

[0094] Step 54: Input the relative distance, the gas flow rate and the edge line length into a preset function to obtain the slurry viscosity.

[0095] When gas (usually air or other inert gas) is ejected from the nozzle outlet at high speed onto the slurry surface, the kinetic energy of the gas will exert an impact force on the slurry surface. This impact force acts on the slurry surface, causing disturbances in the surface layer of the slurry, displacing the slurry surface around the ejection point, and forming a series of concentric annular ripples. The number and size of the concentric annular ripples are related to the relative distance between the gas emitter and the slurry surface, the gas flow rate, and the slurry viscosity. Therefore, by real-time monitoring or image acquisition technology, the ripple image on the slurry surface can be captured for studying the slurry viscosity, etc.

[0096] The disturbance of the gas to the slurry surface (i.e., the significance of the concentric annular ripples) is affected by the gas flow rate, the relative distance between the gas emitter and the slurry surface, and the slurry viscosity. To generate significant disturbances on the slurry surface, it needs to be large enough to produce obvious wave peaks, but not too large to avoid slurry splashing or excessive disturbance. Before the spraying step starts, the initial viscosity of the slurry will be measured. To ensure obtaining an effective slurry surface image, the corresponding gas flow rate is selected based on the initial viscosity and the relative distance. Preferably, a relationship model between the initial viscosity, the relative height and the gas flow rate can be established through experiments or empirical data, and the gas flow rate can be obtained based on this relationship model; or multiple fixed gas flow rates can be set, and the corresponding gas flow rate is selected based on the initial viscosity and the relative distance.

[0097] The above-mentioned fourth preset time is the time within a preset time period after the gas emitter triggers the high-pressure gas injection. Exemplarily, the preset time period is 0.4 seconds, which is specifically set according to the experience of those skilled in the art or according to the actual application scenario.

[0098] The greater the viscosity of the slurry, the greater its surface tension and the stronger its resistance to gas impact, resulting in a higher wave peak height and a smaller range of outward expansion of the wave peak; the smaller the viscosity of the slurry, the easier it is for the slurry to be disturbed by gas impact, and the larger the range of outward expansion of the wave peak. That is to say, the outermost ripple of the concentric circular ripples on the surface image of the slurry is the maximum disturbance range caused by gas impact on the slurry surface. The position and shape of the outermost contour line can more truly reflect the viscosity characteristics of the slurry. Calculating the slurry viscosity based on the outermost reference wave peak contour line can more accurately reflect the true viscosity of the slurry, thereby achieving more reliable viscosity detection.

[0099] Specifically, a preset function between the edge line length and the viscosity can be established through experimental data, such as a linear regression model, a polynomial model, or a neural network model, etc. The gas flow rate, relative distance, and edge line length are mapped to the slurry viscosity through this preset function.

[0100] According to the technical solution of the present invention, the viscosity of the slurry can be measured in real time in the slurry container without sampling and offline analysis, with low cost, avoiding problems such as contamination and wear that may be caused by contacting the slurry, and being able to reduce slurry waste, improve the automation degree and stability of the production process, and at the same time reduce the workload and safety risks of operators.

[0101] In a specific embodiment, step 53 includes:

[0102] Step 531: Preprocess the surface image of the slurry to obtain a preprocessed image.

[0103] Step 532: Assign a region identifier to each closed region in the preprocessed image, and extract the region edge line of each closed region.

[0104] Step 533: Extract the uppermost edge pixel point of the first region edge line, define it as a reference pixel point, and obtain N1 reference center points at a preset distance from the reference pixel point according to the first preset rule, where the first region edge line is the region edge line located at the uppermost part of the preprocessed image.

[0105] Step 534: Set the first relative distance based on a preset distance, extract any reference center point, obtain N2 relative pixel points at the first relative distance from any reference center point according to the second preset rule, and determine whether the region identifiers corresponding to the N2 relative pixel points are all the first region identifier. If not, proceed to step 535; if so, proceed to step 537. Here, the first region identifier is the region identifier of the closed region surrounded by the region edge line corresponding to the reference pixel point.

[0106] Step 535: Reduce the preset distance by a fourth preset value to generate a new preset distance, and determine whether the new preset distance exceeds the preset range. If not, return to step 533; if so, proceed to step 536.

[0107] Step 536: Use the edge pixel points connected to the reference pixel point that have not been searched for the reference center point as new reference pixel points, and determine whether the selection times of the new reference pixel points are greater than a fifth preset value. If not, return to step 533; if so, use the region edge line below the first region edge line as the new first region edge line, and then return to step 533.

[0108] Step 537: Use any reference center point as the center of the reference peak contour line, use the first region edge line as the reference peak contour line, and calculate the edge line length based on the preset distance corresponding to any reference center point.

[0109] Specifically, before the spraying step starts, the initial viscosity of the slurry is measured. During the spraying process, the moisture in the slurry gradually evaporates with atomization and hot air drying. As the moisture decreases, the concentration of solid particles in the slurry relatively increases, resulting in an increase in viscosity. However, even though the viscosity will increase, the range of its increase is predictable. Before identifying the outermost reference peak contour line in the slurry surface image, multiple preset distances are preferably set according to the viscosity prediction range. Since the smaller the slurry viscosity, the larger the range of peak expansion, and the larger the slurry viscosity, the smaller the range of peak expansion, each preset distance can be analyzed and detected in descending order to quickly identify the reference peak contour line.

[0110] After obtaining the reference center point, subtract the set distance from the preset distance to obtain the first relative distance. The set distance is set according to the experience of those skilled in the art or according to the actual application scenario. Preferably, the first relative distance is slightly less than the preset distance. Exemplarily, if the first preset distance is 5 cm and the set distance is 0.5 cm, then the first relative distance is 4.5 cm.

[0111] Take Figure 5 and Figure 6 as examples to illustrate the embodiments of the present application.

[0112] Such as Figure 5As shown, there is an interfering pseudo-peak contour line CL1, whose area is labeled as A, and its corresponding reference pixel point is a1. The reference peak contour line is CL2, whose area is labeled as B. When the first preset angular interval is 90°, with a1 as the center, four reference center points b1, b2, b3, and b4 at a preset distance from a1 are obtained. As can be seen from the figure, the area labeled as A is the closed area enclosed by the area edge line CL1. The area labels of the relative pixel points surrounding any of the reference center points are not all A. After adjusting the reference pixel points and the preset distance of the area edge line CL1, it can be determined that the area edge line CL1 is not the reference peak contour line. Further, the area edge line CL2 below the area edge line CL1 is detected.

[0113] As Figure 6 shown, the reference pixel point corresponding to the area edge line CL2 is a2. When the first preset angular interval is 90°, with a2 as the center, four reference center points b5, b6, b7, and b8 at a preset distance from a2 are obtained. Subsequently, the relative pixel points surrounding any of the reference center points are further identified and detected. The area labeled as B is the closed area enclosed by the area edge line CL2. Taking the reference center point b5 as an example, when the second preset angular interval is 60°, with b5 as the center, six relative pixel points (c1, c2, c3, c4, c5, c6) at a first relative distance from b5 are obtained. These six relative pixel points are all within area B, that is, their corresponding area labels are all B. According to the geometric properties of the circle, it can be judged that the area edge line CL2 is circular, the reference center point b5 is its center, and since the area edge line CL2 is the first area edge line that meets the judgment conditions, it can be determined that it is the reference peak contour line.

[0114] Specifically, the reference pixel points can also be extracted from the leftmost or rightmost side of the area edge curve. Due to the existence of interference noise, etc., the area edge line may not be a regular circle. Based on this, the pixel points on the area edge line can be extracted sequentially in the clockwise or counterclockwise direction for analysis. At the same time, a new selection times threshold (i.e., the fifth preset value) for the reference pixel points is set to avoid excessive pixel points of the area edge line that do not meet the judgment conditions from being selected as reference pixel points, reducing the number of calculations and saving computing resources.

[0115] Preferably, in step 532, the erosion operation in morphological operations can be used to reduce the width of the contour line and make the contour line thinner.

[0116] In a specific embodiment, the preprocessing includes:

[0117] (1) Performing histogram equalization on the slurry surface image to generate a first image.

[0118] (2) Obtain the first intensity values of each color component at any pixel point in the first image, perform weighted averaging on all the first intensity values to obtain a weighted average value, and determine whether the weighted average value is greater than or equal to the intensity threshold. If so, set the intensity values of each color component at any pixel point to the intensity maximum value. If not, set the intensity values of each color component at any pixel point to the intensity minimum value. After traversing all the pixel points, generate a second image.

[0119] (3) Perform edge extraction processing on the second image to extract the edge lines of each object, and then calculate the line segment length of each edge line. When the line segment length of any edge line is less than the sixth preset value, calculate the proximity of any edge line to the ideal straight line. When the proximity is greater than the seventh preset value, delete any edge line. After traversing all the edge lines, generate a third image.

[0120] (4) Check the connectivity of any edge line in the third image. If any edge line does not form a closed loop, use morphological operations to close any edge line. After traversing all the edge lines, generate a preprocessed image.

[0121] The slurry surface image may have insufficient contrast due to reasons such as uneven illumination, improper camera exposure settings, and the characteristics of the slurry itself. Before performing edge line extraction, first perform histogram equalization processing to enhance the contrast of the image, make the gray distribution of the image more uniform, thereby highlighting the detailed information in the image and making the wave peak contour clearer.

[0122] The wave peak is the raised part of the slurry surface and usually reflects more light. Due to the stronger reflected light, the pixel points in the wave peak area receive a higher light intensity, and the pixel points in the wave peak area usually have a higher gray value (brighter). The wave trough is the sunken part of the slurry surface. After the light irradiates the wave trough, it will scatter, and less light is reflected to the camera sensor. The pixel points in the wave trough area usually have a lower gray value (darker). When the weighted average value of any pixel point is greater than or equal to the intensity threshold, set the intensity values of its each color component to the intensity maximum value (such as 255) to make it appear white. When the weighted average value of any pixel point is less than the intensity threshold, set the intensity values of its each color component to the intensity minimum value (such as 0) to make it appear black. Based on this, the image information can be simplified, the wave peak contour can be highlighted, the wave peak contour appears white, and the background appears black. Among them, the intensity threshold is set according to the experience of those skilled in the art or according to the actual application scenario.

[0123] After edge extraction processing, based on the line segment length of the edge line and its proximity to the ideal straight line, approximate straight lines with shorter lengths are deleted. While effectively removing noise interference and simplifying the image structure, it is ensured that line segments belonging to the peak contour are not deleted, thereby more accurately extracting the true peak contour line. To ensure the connectivity of the edge line and form a complete peak contour, morphological operations such as dilation, erosion, opening operation, or closing operation are performed on the unclosed edge line to close the unclosed edge line. In addition, interpolation methods (interpolating between break points to fill in missing pixels), contour approximation methods, etc. can also be used to close the unclosed edge line.

[0124] This technical solution ensures the integrity and accuracy of the peak contour line through precise edge extraction and interference removal, helps improve the accuracy and reliability of viscosity detection, and enhances the overall performance of the system.

[0125] In a specific embodiment, the first preset rule is to take the reference pixel point as the origin, the vertically downward direction as the polar axis direction, and sequentially obtain reference center points at the first preset angular interval.

[0126] The second preset rule is to take any reference center point as the origin, the vertically downward direction as the polar axis direction, and sequentially obtain relative pixel points at the second preset angular interval.

[0127] Specifically, the first preset angular interval and the second preset angular interval are set according to the experience of those skilled in the art or according to the actual application scenario. Exemplarily, the first preset angular interval is 45° or 90°, and the second preset angular interval is 30° or 45°. The second preset angular interval can be less than, equal to, or not equal to the first preset angular interval.

[0128] Exemplarily, when the first preset angular interval is 45°, taking the reference pixel point as the origin, the vertically downward direction as the polar axis direction, 8 reference center points are sequentially obtained at an angular interval of 45°; when the second preset angular interval is 30°, taking any reference center point as the origin, the vertically downward direction as the polar axis direction, 12 relative pixel points are sequentially obtained at an angular interval of 30°.

[0129] The optimization method for the metal ceramic mixture spraying process in the embodiments of the present application is described above. Next, the optimization system for the metal ceramic mixture spraying process in the embodiments of the present application will be described. Please refer to Figure 7 , an embodiment of the optimization system for the metal ceramic mixture spraying process in the embodiments of the present application includes: an imaging device 10 and an information processor 20. The information processor 20 includes an image analysis module 201, a first operation module 202, a second operation module 203, and an anomaly detection module 204.

[0130] The imaging device 10 is used to capture the atomization angle image at the nozzle in real time during the spraying process and transmit the atomization angle image to the information processor 20.

[0131] The image analysis module 201 is used to calculate the atomization angle based on the atomization angle image, compare the atomization angle with the preset angle value. When the atomization angle is less than the first preset value, it enters the first operation module 202. When the atomization angle is less than the second preset value, it enters the second operation module 203, where the first preset value is greater than the second preset value.

[0132] The first operation module 202 is used to trigger the vibrating device to vibrate the spray gun, close the vibrating device after the first preset time, and determine whether the atomization angle has recovered to the third preset value. If not, it enters the second operation module 203, where the third preset value is greater than the first preset value.

[0133] The second operation module 203 is used to switch the spray slurry to high-pressure anhydrous ethanol, switch back to the spray slurry after the second preset time, and determine whether the atomization angle has recovered to the third preset value. If not, it enters the abnormal detection module 204.

[0134] The abnormal detection module 204 is used to detect whether the current spray pressure is abnormal through the spray pressure detection device. If so, it issues a first alarm signal to prompt the operator to make adjustments. If not, it detects the slurry viscosity through the viscosity detection device and then issues a second alarm signal to prompt the operator to adjust the amount of anhydrous ethanol added.

[0135] This application also provides a computer-readable storage medium. The computer-readable storage medium can be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When the instructions run on a computer, the computer is made to execute the steps of the optimization method for the metal-ceramic mixture spraying process.

[0136] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described system, system, and unit can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0137] When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application. The foregoing storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks, or optical discs.

[0138] As described above, the above embodiments are only used to illustrate the technical solution of this application, rather than to limit it; although this application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of various embodiments of this application.

Claims

1. An optimization method for a metal-ceramic mixture spray process, characterized in that: The method comprises: Step 1: During the spraying process, an image of the atomization angle at the nozzle is captured in real time, and the image of the atomization angle is transmitted to an information processor; Step 2, the information processor calculates the fog angle based on the fog angle image, and compares the fog angle with a preset angle value. When the fog angle is less than a first preset value, the process proceeds to step 3; when the fog angle is less than a second preset value, the process proceeds to step 4, wherein the first preset value is greater than the second preset value. Step 3, triggering the rapping device to vibrate the spray gun, closing the rapping device after a first preset time, and judging whether the atomization angle is restored to a third preset value, if not, entering step 4, wherein the third preset value is greater than the first preset value; Step 4, switching the spray slurry to high-pressure anhydrous ethanol, and switching back to the spray slurry after the second preset time, and judging whether the atomization angle is restored to the third preset value, if not, proceeding to step 5; Step 5: Use the spray pressure detection device to detect whether the current spray pressure is abnormal. If so, a first alarm signal is issued to prompt the operator to adjust the spray pressure. If not, the viscosity of the slurry is detected by the viscosity detection device, and then a second alarm signal is issued to prompt the operator to adjust the amount of anhydrous ethanol added.

2. The optimization method for the metal-ceramic mixture spraying process according to claim 1, characterized in that: In the step 2, when it is determined that the atomization angle is less than the first preset value, the step further includes: Acquire historical vibration data of the nozzle within a third preset time, perform feature analysis on the historical vibration data, and calculate the change rate of a specific vibration parameter; When the change rate is less than or equal to the corresponding preset threshold, proceed to step 3; When the change rate is greater than the preset threshold, go to step 5.

3. The optimization method for the metal-ceramic mixture spraying process according to claim 2, characterized in that: The specific vibration parameters include vibration acceleration; and / or The specific vibration parameters include vibration amplitude and vibration frequency.

4. The optimization method for the metal-ceramic mixture spraying process according to claim 1, characterized in that: A gas emitter and an image acquisition device are arranged above the slurry container. In the step 5, detecting the viscosity of the slurry by the viscosity detection device includes: Step 51, obtaining the initial viscosity of the slurry and the relative distance between the slurry surface and the gas emitter, and selecting a corresponding gas flow rate based on the initial viscosity and the relative distance; Step 52, the gas emitter applies a gas impact to the slurry surface based on the gas flow rate, and acquires a slurry surface image at a fourth preset time; Step 53, extracting the outermost reference peak contour line in the slurry surface image, calculating the length of the reference peak contour line, and defining it as the edge line length; Step 54: input the relative distance, the gas flow rate and the edge line length into a preset function to obtain the slurry viscosity.

5. The optimization method for metal-ceramic mixture spraying process according to claim 4, characterized in that: The step 53 comprises: Step 531, preprocessing the slurry surface image to obtain a preprocessed image; Step 532: assigning a region identifier to each closed region in the preprocessed image, and extracting a region edge line of each closed region; Step 533: extract the top edge pixel point of the first region edge line, define it as a reference pixel point, and obtain N1 reference center points at a preset distance from the reference pixel point according to a first preset rule, wherein the first region edge line is the region edge line located at the top of the preprocessed image; Step 534: set a first relative distance based on the preset distance, extract any reference center point, obtain N2 relative pixel points at the first relative distance from any reference center point according to a second preset rule, and determine whether the region identifiers corresponding to the N2 relative pixel points are all first region identifiers; if not, proceed to step 535; if yes, proceed to step 537, wherein the first region identifier is the region identifier of the closed region surrounded by the region edge line corresponding to the reference pixel point; Step 535, reducing the preset distance by a fourth preset value to generate a new preset distance, and determining whether the new preset distance exceeds a preset range, if not, returning to step 533, if yes, proceeding to step 536; Step 536: taking an edge pixel point connected to the reference pixel point and not subjected to a reference center point search as a new reference pixel point, and determining whether the number of selections of the new reference pixel point is greater than a fifth preset value; if not, returning to step 533; if yes, taking the region edge line below the first region edge line as a new first region edge line, and then returning to step 533; Step 537: use any of the reference center points as the center of the reference peak contour line, use the first area edge line as the reference peak contour line, and calculate the edge line length based on the preset distance corresponding to any of the reference center points.

6. The optimization method for metal-ceramic mixture spraying process according to claim 5, characterized in that: The pre-processing comprises: Performing histogram equalization on the slurry surface image to generate a first image; Obtain a first intensity value of each color component at any pixel point in the first image, perform weighted averaging on all first intensity values ​​to obtain a weighted average value, determine whether the weighted average value is greater than or equal to an intensity threshold, if so, set the intensity value of each color component at any pixel point to a maximum intensity value, if not, set the intensity value of each color component at any pixel point to a minimum intensity value, and generate a second image after traversing all pixel points; Performing edge extraction processing on the second image to extract edge lines of each object, then calculating the line segment length of each edge line, when the line segment length of any edge line is less than a sixth preset value, calculating the proximity of any edge line to an ideal straight line, when the proximity is greater than a seventh preset value, deleting any edge line, and generating a third image after traversing all edge lines; Check the connectivity of any edge line in the third image. If any edge line does not form a closed loop, use morphological operations to close any edge line. After traversing all edge lines, generate the preprocessed image.

7. The optimization method for metal-ceramic mixture spraying process according to claim 5, characterized in that: The first preset rule is to take the reference pixel point as the origin, take the vertical downward direction as the polar axis direction, and sequentially obtain the reference center point at first preset angle intervals; The second preset rule is to take any of the reference center points as the origin, take the vertical downward direction as the polar axis direction, and sequentially acquire the relative pixel points at second preset angle intervals.

8. An optimization system for metal-ceramic mixture spraying process, characterized in that: The system comprises: an imaging device and an information processor, wherein the information processor comprises an image analysis module, a first operation module, a second operation module and an abnormality detection module; The imaging device is used to capture the atomization angle image at the nozzle in real time during the spraying process, and transmit the atomization angle image to the information processor; The image analysis module is used to calculate the fog angle according to the fog angle image, compare the fog angle with a preset angle value, and enter the first operation module when the fog angle is less than a first preset value, and enter the second operation module when the fog angle is less than a second preset value, wherein the first preset value is greater than the second preset value; The first operating module is used to trigger the rapping device to vibrate the spray gun, turn off the rapping device after a first preset time, determine whether the atomization angle is restored to a third preset value, and if not, enter the second operating module, wherein the third preset value is greater than the first preset value; The second operation module is used to switch the spray slurry to high-pressure anhydrous ethanol, switch back to the spray slurry after the second preset time, and judge whether the atomization angle is restored to the third preset value. If not, enter the abnormality detection module; The abnormality detection module is used to detect whether the current spray pressure is abnormal through a spray pressure detection device. If so, a first alarm signal is issued to prompt the operator to make adjustments. If not, the viscosity of the slurry is detected through a viscosity detection device, and then a second alarm signal is issued to prompt the operator to adjust the amount of anhydrous ethanol added.

9. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instructions are executed by a processor, an optimization method for a metal-ceramic mixture spraying process as described in any one of claims 1 to 7 is implemented.

Images