A control system for preparing high heat-resistant grease

By designing a control system for the preparation of high heat resistance greases, and using image analysis technology to identify bubble characteristics in the stirring area, the problem of inaccurate identification of bubble information in the prior art is solved, precise control of the grease preparation process is achieved, and working efficiency is improved.

CN119793360BActive Publication Date: 2025-06-06YANAN SUIYUAN TECH DEV CO LTD +1
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
CN202510293840.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-03-13
Publication Date
2025-06-06
Estimated Expiration
2045-03-13

AI Technical Summary

Technical Problem

The prior art cannot effectively identify the bubble information in the stirring area, resulting in the inability to accurately determine the reaction state at each moment, thus the grease preparation process cannot be accurately controlled.

Method used

A control system for the preparation of high heat resistance grease was designed. By preparing a data storage module, a reaction degree evaluation module and a stirring device control module, the analysis of the image of the stirring area in succession is used to calculate the probability of bubble overlap and bubble richness, and then evaluate the reaction state and stability degree to control the stirring device.

Benefits of technology

The accurate identification of bubble characteristics in the grease mixing process is achieved, the resource waste caused by long-term operation of the mixing equipment is avoided, and the working efficiency in the grease preparation process is improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119793360B_ABST
    Figure CN119793360B_ABST
Patent Text Reader

Abstract

The present invention relates to the field of image data analysis technology, and in particular to a control system for the preparation of high heat-resistant grease. The system obtains the probability of bubble overlap in the bubble area in each frame of the stirring area image based on the change characteristics of the bubble area at the same position between adjacent frames of the stirring area image. The bubble richness of each frame of the stirring area image is determined using the bubble overlap probability, and then the reaction state in the corresponding time period is obtained. The stability of the change in the number of bubble areas and the stability of the change in the bubble richness are further considered to determine the degree of reaction stability in the real-time time period, and then the remaining preparation time in the stirring process is determined and the stirring equipment is controlled. The present invention improves the work efficiency in the stirring process during the preparation of the grease by accurately identifying the bubble characteristics in the stirring area, avoiding the waste of resources caused by the long-term operation of the stirring equipment.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the technical field of image data analysis, and in particular to a control system for preparing high-heat-resistant lubricating grease. Background Art

[0002] In the preparation process of high heat-resistant grease, the materials need to be fully mixed and reacted. The common preparation process includes: pre-mixing the base oil and thickener at an appropriate temperature, usually in a high-temperature mixer to ensure uniformity; and for thickeners that require chemical reactions such as lithium soap, stirring at a predetermined temperature and time length to ensure that the thickener is completely reacted; after the reaction is completed, antioxidants, anti-wear agents and other additives are added in sequence according to the formula, and stirring is continued until uniform; after mixing and reaction are completed, slowly cool to form a stable crystal structure, and grind to make the grease finer and grind to make the grease finer; finally, the produced grease is degassed and homogenized, and the finished grease is filled into containers to complete the production process.

[0003] In the above-mentioned process of adding various types of reaction substances or mixed substances for reaction and mixing, it is necessary to observe whether the substances in the stirring process react completely and mix evenly. Bubbles will be generated during the stirring process. The bubbles may include oxygen in the air, gases produced by the reaction, or gases dissolved in the raw materials. However, the volume of the gas generated by the environment and stirring itself is small and can be removed by subsequent degassing treatment. Although the gas generated by the reaction can be removed, if the number is too large or the volume is too large in the image collected at a certain moment, it means that the reaction process is not completed. Therefore, based on the bubble content, it can be judged whether the mixing or reaction state is complete. Therefore, in the prior art, the state of the reaction can be determined by identifying the bubble content information in the stirring area. However, in the actual reaction process, the bubbles will merge or break and disperse under the action of stirring, resulting in bubbles being blocked in the collected image, bubbles overlapping, and bubbles cannot be effectively identified, and thus the reaction state at each moment cannot be determined, and thus the grease preparation under the stirring process cannot be accurately controlled. Summary of the invention

[0004] In order to solve the technical problem that the prior art cannot effectively identify bubble information, cannot determine the reaction state at each moment, and thus cannot accurately control the grease preparation under the stirring process, the purpose of the present invention is to provide a control system for the preparation of high heat-resistant grease, and the technical solution adopted is as follows:

[0005] The present invention proposes a control system for preparing high heat-resistant grease, the system comprising:

[0006] A preparation data storage module is used to obtain and store continuous multi-frame stirring area images in the reaction stirring process during the grease preparation process; the stirring process includes multiple reaction time periods, wherein the reaction time period corresponding to the real time is the real time time period;

[0007] A reaction degree evaluation module is used to obtain the bubble overlap probability of the bubble area in each stirring region image frame according to the change characteristics of the bubble area at the same position between adjacent frames of stirring region images; obtain the bubble richness of each stirring region image frame according to the area of ​​the bubble area in the stirring region image and the bubble overlap probability; and obtain the reaction state of the reaction time period according to the change characteristics of the bubble richness in the reaction time period;

[0008] The stirring device control module is used to obtain the reaction stability of the real-time time period according to the stability of the change in the number of bubble areas between the reaction time periods and the stability of the change in the bubble richness; determine the remaining preparation time under the stirring process according to the reaction stability and control the stirring device.

[0009] Furthermore, the method for obtaining the bubble overlap probability includes:

[0010] Select any one frame of stirring region image as the target stirring region image, select any one bubble region of the target stirring region image as the target bubble region; select the stirring region image of the previous frame of the target stirring region image as the comparison image; select the bubble region closest to the target bubble region in the comparison image as the comparison bubble region;

[0011] A region variation feature is obtained according to the area difference between the comparison bubble region and the target bubble region; and the bubble overlap probability of the target bubble region is obtained according to the region variation feature and the number of the comparison bubble regions.

[0012] Furthermore, the method for obtaining the bubble richness includes:

[0013] For each frame of the stirring region image, the bubble overlap probability is used as a weight, and weighted sum is performed on the areas of the bubble regions in the stirring region image to obtain the bubble richness of each frame of the stirring region image.

[0014] Furthermore, the method for obtaining the reaction state includes:

[0015] The variance of the bubble abundance within the reaction time period is taken as the reaction state.

[0016] Furthermore, the method for obtaining the stability of the change in the number of bubble regions includes:

[0017] Obtaining the time weight of each reaction time period according to the distance between the reaction time period and the real-time time period; obtaining the average number of bubble regions in all stirring region images within each reaction time period, and sorting the average number of bubble regions according to the time sequence of the reaction time periods to obtain a sequence of the average number of bubble regions;

[0018] The absolute value of the difference between each element and the next element in the average bubble area quantity sequence is used as the bubble quantity difference of each element;

[0019] The time weight of the corresponding element is used as the weight of the bubble quantity difference, and the bubble quantity differences of all elements are weighted summed to obtain the overall bubble quantity change degree;

[0020] The degree of change in the number of overall bubbles is negatively correlated and mapped to obtain the stability of the change in the number of bubble regions.

[0021] Furthermore, the method for obtaining the stability of bubble richness variation includes:

[0022] Obtaining the average bubble richness in all stirring area images in each reaction time period, and sorting the average bubble richness according to the time sequence of the reaction time period to obtain an average bubble richness sequence;

[0023] The absolute value of the difference between each element and the next element in the average bubble richness sequence is used as the bubble richness difference corresponding to each element;

[0024] The time weight of the corresponding element is used as the weight of the bubble richness difference, and the bubble richness differences of all elements are weighted summed to obtain the overall bubble richness change degree;

[0025] The overall bubble richness variation degree is negatively correlated and mapped to obtain the stability of the bubble richness variation.

[0026] Furthermore, the method for obtaining the reaction stability comprises:

[0027] Negative correlation mapping of the reaction state in the real-time time period is performed to obtain the initial reaction stability;

[0028] The product of the stability of the change in the number of bubble regions, the stability of the change in the bubble richness, and the initial reaction stability is normalized to obtain the reaction stability.

[0029] Furthermore, if the reaction stability in the real-time time period is greater than a preset stability threshold, the remaining preparation time under the stirring process is determined according to the reaction stability and the stirring device is controlled.

[0030] Further, the remaining preparation time under the stirring process is determined according to the reaction stability and the stirring device is controlled, including:

[0031] The time difference between the stirring time and the preset stirring time is obtained, the reaction stability is negatively correlated and normalized to obtain a time adjustment weight; the time adjustment weight is multiplied by the time difference to obtain a remaining preparation time.

[0032] Furthermore, the method for dividing the reaction time period includes:

[0033] Taking the start time of the stirring process as the starting point, the sliding step of the time period sliding window is set to the preset length size according to the preset length size; the time period sliding window slides on the timing range of the stirring process to divide the stirring process into multiple reaction time periods.

[0034] The present invention has the following beneficial effects:

[0035] The embodiment of the present invention takes into account that in the grease stirring process, bubbles are constantly moving. If bubbles in a certain frame image overlap, obvious bubble changes will occur in the adjacent frame image. Therefore, the present invention obtains the bubble overlap probability of the bubble area in each frame stirring area image according to the change characteristics of the bubble area at the same position between the adjacent frame stirring area images. That is, the greater the bubble overlap probability, the more bubbles overlap occurs at the corresponding position in the two adjacent frames of the image, so that a large number of bubbles are regarded as one or a small number of bubbles, which leads to the characteristic change of the bubble area. The bubble overlap probability can be further used to determine the bubble richness of each frame stirring area image, and then obtain the reaction state in the corresponding time period. In the reaction process under the grease stirring process, as the reaction proceeds, the reaction state should gradually tend to be stable. Therefore, the present invention further takes into account the stability of the change in the number of bubble areas and the stability of the change in the bubble richness to determine the reaction stability in the real-time time period, and then determine the remaining preparation time under the stirring process and control the stirring device. The present invention avoids the waste of resources caused by the long-term operation of the stirring device by accurately identifying the bubble characteristics in the stirring area, and improves the work efficiency of the stirring process in the grease preparation process. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0037] Figure 1A control system block diagram for preparing a high heat-resistant grease provided by one embodiment of the present invention;

[0038] Figure 2 A flow chart of a method for obtaining the bubble overlap probability by a reaction state evaluation module provided by an embodiment of the present invention;

[0039] Figure 3 A flow chart of a method for obtaining the stability of the change in the number of bubble regions by a stirring device control module provided in one embodiment of the present invention;

[0040] Figure 4 A curve diagram showing the change of reaction stability over time in a stirring process provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0041] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the control system for preparing a high heat-resistant grease according to the present invention, its specific implementation, structure, characteristics and effects, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0042] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0043] The specific scheme of a control system for preparing a high heat-resistant grease provided by the present invention is described in detail below in conjunction with the accompanying drawings.

[0044] See also Figure 1 , which shows a block diagram of a control system for preparing a high heat-resistant grease provided by an embodiment of the present invention. The system includes a preparation data storage module 101, a reaction state evaluation module 102 and a stirring equipment control module 103.

[0045] The preparation data storage module 101 is used to obtain and store continuous multi-frame stirring area images under the reaction stirring process in the grease preparation process. In an embodiment of the present invention, the preparation data storage module 101 collects the stirring area images through a camera installed directly above the stirring device, and transmits the collected stirring area images to the storage device through the Internet of Things.

[0046] In some implementations of the present invention, in order to facilitate the subsequent analysis and processing of the stirring area image and for storage efficiency, each stored stirring area image is grayed, wherein the graying algorithm is a technical means well known to those skilled in the art and will not be described in detail here.

[0047] The embodiment of the present invention takes into account that in the stirring process of the grease preparation process, the reaction and mixing between substances exist in multiple stages, and the reaction states in different stages are different, and the image features reflected are also different. Therefore, if the entire stirring process is analyzed globally, it is easy to weaken the obvious features. Therefore, the embodiment of the present invention includes multiple reaction time periods in the stirring process, and the reaction time period corresponding to the real time is the real time period. By dividing the time period, the entire stirring process can be analyzed locally to avoid the weakening of the features with strong reference.

[0048] The reaction state evaluation module 102 is used to obtain the bubble overlap probability of the bubble area in each frame of the stirring area image according to the change characteristics of the bubble area at the same position between adjacent frames of the stirring area image; obtain the bubble richness of each frame of the stirring area image according to the area of ​​the bubble area in the stirring area image and the bubble overlap probability; and obtain the reaction state of the reaction time period according to the change characteristics of the bubble richness within the reaction time period.

[0049] In the reaction state evaluation module 102, the reaction state is mainly determined by analyzing the bubble features in the stirring area image. In the embodiment of the present invention, a semantic segmentation algorithm or an edge detection algorithm can be selected to extract the bubble area in the image. The specific extraction method is a technical means well known to those skilled in the art and will not be described in detail here.

[0050] For a certain stirring region image, if a certain bubble region in the stirring region image is an overlapping bubble region, then different bubble region features should exist at the same position in the adjacent stirring region images, that is, the overlap can be regarded as multiple bubble regions being merged into one bubble region in a certain frame image. Therefore, the reaction state evaluation module 102 can obtain the bubble overlap probability of the bubble region in each stirring region image frame according to the change features of the bubble region at the same position between the adjacent frames of stirring region images.

[0051] For a certain bubble region, if the bubble region is a bubble region composed of overlapping bubbles, it means that other bubble regions are hidden under the bubble region, and the area credibility of the bubble region is low. Therefore, the reaction state evaluation module 102 can obtain the bubble richness of each frame of the stirring region image by combining the bubble overlap probability and the area of ​​the bubble region. That is, for a bubble region, the greater the bubble overlap probability, the richer the bubble information represented by the area of ​​the bubble region, and the greater the bubble richness; on the contrary, the smaller the bubble overlap probability, it means that the area of ​​the bubble region only represents a small amount or one bubble information, and the smaller the bubble richness.

[0052] For a reaction time period, if the current reaction time period is a reaction state, the richness of the bubbles is constantly changing. A stronger bubble richness indicates that the reaction is becoming more and more intense; a weaker bubble richness indicates that the reaction is gradually becoming gentler; if the bubble richness no longer changes, it means that the reaction of the grease material in the stirring process is completed at this time, and the bubbles may be generated by the external environment and are relatively regular. Therefore, the reaction degree evaluation module 102 can obtain the reaction state within the reaction time period based on the changing characteristics of the bubble richness within the reaction time period.

[0053] The stirring device control module 103 is used to obtain the reaction stability of the real-time time period according to the stability of the change of the number of bubble areas between the reaction time periods, and the stability of the change of the richness of bubbles. If the various reactions in the grease stirring area tend to be complete, the number and area of ​​the bubbles generated will gradually decrease with the increase of time. When the reaction is complete, due to the mixing of air during the stirring process, certain bubbles will still appear in the stirring area. The number and area of ​​the bubbles are both small and relatively stable. Therefore, the greater the stability of the change of the number of bubble areas and the greater the stability of the change of the richness of bubbles, it means that the bubbles are most likely caused by environmental factors in the stirring process at this time, indicating that the reaction stability at this time is greater, and the stirring process tends to be more completely stirred. Therefore, the remaining preparation time under the stirring process can be determined according to the reaction stability and the stirring device can be controlled.

[0054] In summary, the embodiments of the present invention take into account that in the grease stirring process, bubbles are constantly moving. If bubbles in a certain frame image overlap, obvious bubble changes will occur in adjacent frame images. Therefore, the present invention obtains the bubble overlap probability of the bubble area in each frame stirring area image based on the change characteristics of the bubble area at the same position between adjacent frame stirring area images. That is, the greater the bubble overlap probability, the more bubbles overlap at the corresponding position in the two adjacent frames of images, so that a large number of bubbles are regarded as one or a small number of bubbles, which leads to characteristic changes in the bubble area. The bubble overlap probability can be further used to determine the bubble richness of each frame stirring area image, and then obtain the reaction state in the corresponding time period. In the reaction process under the grease stirring process, as the reaction proceeds, the reaction state should gradually tend to be stable. Therefore, the present invention further takes into account the stability of the change in the number of bubble areas and the stability of the change in the bubble richness to determine the reaction stability in the real-time time period, and then determines the remaining preparation time under the stirring process and controls the stirring equipment, so as to avoid the waste of resources caused by the long-term operation of the stirring equipment, and improves the work efficiency of the stirring process in the grease preparation process.

[0055] Preferably, in one embodiment of the present invention, the method for dividing the reaction time period includes:

[0056] Taking the starting moment of the stirring process as the starting point, the sliding step of the time period sliding window is set to the preset length size according to the preset length size. The time period sliding window slides on the time range of the stirring process, and the stirring process is divided into multiple reaction time periods. It should be noted that the length on the time range represents the number of moments. In the embodiment of the present invention, each frame of the stirring area image corresponds to a moment, and the preset length size is set to 180 frames. During the sliding process of the time period sliding window, the number of moments in the last sliding process may not be 180, and it is still regarded as a reaction time period, that is, a real-time time period.

[0057] Preferably, see Figure 2 , which shows a flow chart of a method for obtaining the bubble overlap probability by a reaction state evaluation module provided by an embodiment of the present invention. In the embodiment of the present invention, the method for obtaining the bubble overlap probability includes:

[0058] Step S201: select any frame of stirring area image as the target stirring area image, select any bubble area of ​​the target stirring area image as the target bubble area; select the stirring area image of the previous frame of the target stirring area image as the comparison image; and select the bubble area closest to the target bubble area in the comparison image as the comparison bubble area.

[0059] The embodiment of the present invention selects the previous frame of the target stirring area image as the comparison image, that is, if the target bubble area in the current target stirring area image is composed of overlapping bubbles, it means that it is caused by the movement of bubbles in the comparison image of the previous frame. Therefore, the bubble area closest to the target bubble area in the comparison image is selected as the comparison bubble area. It should be noted that there may be one or more comparison bubble areas. If there is one, it means that the probability that the target bubble area is composed of overlapping bubbles is small; if there are multiple, it means that the target bubble area is an overlapping area generated by the movement of these multiple comparison bubble areas.

[0060] It should be noted that, in the embodiment of the present invention, the centroid position of each bubble region is used as the position of the bubble region, and the comparison bubble region is determined by calculating the distance between the centroid of the target bubble region at the same position in the comparison image and the centroid of the bubble region in the comparison image. The method for obtaining the distance between points is a technical means well known to those skilled in the art and will not be described in detail here.

[0061] Step S202: obtaining a region variation feature according to the area difference between the comparison bubble region and the target bubble region; obtaining a bubble overlap probability of the target bubble region according to the region variation feature and the number of the comparison bubble regions.

[0062] The more the number of contrast bubble regions, the larger the corresponding total area, and the greater the probability of bubble overlap in the target bubble region. Therefore, the regional change characteristics are obtained based on the area difference between the contrast bubble region and the target bubble region, and the bubble overlap probability of the target bubble region is further obtained by combining the number of contrast bubble regions. Similarly, the bubble overlap probability of each bubble region in each frame of the stirring region image can be obtained.

[0063] In a specific implementation of the embodiment of the present invention, the product of the regional variation feature and the number of the comparison bubble regions is normalized to obtain the bubble overlap probability. It can be expressed as: ;in is the bubble overlap probability of the rth bubble region in the jth frame stirring region image, is the number of contrast bubble regions of the rth bubble region in the jth frame stirring region image, The total area of ​​the rth bubble region in the jth frame stirring region image compared with the total area of ​​the bubble region in the j-1th frame stirring region image, The area of ​​the rth bubble region in the jth frame stirring area image, norm() is the normalization function.

[0064] It should be noted that the normalization function in the embodiment of the present invention can be implemented by using basic mathematical means such as range standardization and function mapping method, which will not be limited or elaborated here.

[0065] Preferably, in some implementations of the embodiments of the present invention, the method for obtaining the bubble richness includes:

[0066] For each frame of the stirring area image, the bubble overlap probability is used as the weight, and the area of ​​the bubble area in the stirring area image is weighted and summed to obtain the bubble richness of each frame of the stirring area image. That is, the bubble richness can be regarded as the bubble feature obtained by weighting the overlap based on the information of the bubble area. The greater the bubble richness, the richer the bubbles in the stirring area of ​​the current frame, and the larger the bubble volume.

[0067] Preferably, in some implementations of the embodiments of the present invention, there are multiple frames of stirring area images in a reaction time period, that is, there are multiple bubble richnesses. The variance of the bubble richness in the reaction time period is used as the reaction state. The larger the variance, the greater the reaction state, and the more likely it is to be in an obvious reaction state.

[0068] Preferably, see Figure 3 , which shows a flow chart of a method for obtaining the stability of the change in the number of bubble regions by a stirring device control module provided by an embodiment of the present invention. The method for obtaining the stability of the change in the number of bubble regions includes:

[0069] Step S301: Obtain the time weight of each reaction time period according to the distance between the reaction time period and the real-time time period. Obtain the average number of bubble regions in all stirring region images in each reaction time period, sort the average number of bubble regions according to the time sequence of the reaction time period, and obtain the average number of bubble regions sequence.

[0070] In the embodiment of the present invention, because the reaction time period is divided in the stirring process, each reaction time period has a corresponding order in the time range of the stirring process, so the distance between the reaction time period and the real-time time period can be regarded as the difference between the orders. Because the embodiment of the present invention is intended to analyze the reaction stability in the stirring area at the current moment, the closer the reaction time period is to the real-time time period, the stronger the reference, that is, the time weight should be negatively correlated with the distance between the time periods. The embodiment of the present invention uses the inverse of the difference between the orders as the time weight, that is, the closer to the real-time time period, the greater the time weight.

[0071] The number information of the bubble area in the entire stirring process is further extracted, and each reaction time period is analyzed to obtain the average number of bubble areas in all stirring area images in each reaction time period, and the average number of bubble areas is sorted according to the time sequence of the reaction time period to obtain the average number of bubble areas sequence. That is, each element in the average number of bubble areas sequence corresponds to a reaction time period, representing the average number of bubble areas in all stirring area images in the reaction time period.

[0072] Step S302: taking the absolute value of the difference between each element and the next element in the average bubble area quantity sequence as the bubble quantity difference of each element.

[0073] The difference in the number of bubbles represents the degree of change in the number of bubbles between two adjacent reaction time periods. The smaller the difference in the number of bubbles, the smoother the change, and the reaction time period corresponding to the element is closer to complete reaction.

[0074] Step S303: taking the time weight of the corresponding element as the weight of the bubble quantity difference, performing weighted summation on the bubble quantity differences of all elements, and obtaining the overall bubble quantity change degree.

[0075] Further combined with the time weight, the differences in the number of bubbles of all elements are weighted and summed to obtain the overall change in the number of bubbles. That is, the closer the change in the number of bubbles is to the reaction time period within the implementation time period, the greater the change, indicating that it is still in a reaction state at this time, and the reaction may gradually become more intense or the reaction gradually subsides, and the reaction is more incomplete.

[0076] Step S304: negatively correlate the change degree of the overall bubble quantity to obtain the stability of the change of the bubble area quantity.

[0077] Based on the description of step 303 above, the stability of the change in the number of bubbles in the bubble area can be obtained by negatively mapping the change in the number of bubbles in the overall bubble area. That is, the smaller the change in the number of bubbles in the overall bubble area, the more likely it is that the reaction is complete, and the bubbles in the stirring area are all bubbles generated by the stirring environment, and the greater the stability of the change in the number of bubbles in the bubble area.

[0078] In the embodiment of the present invention, considering that the overall bubble quantity change degree is a weighted summation result and therefore cannot be 0, the inverse of the overall bubble quantity change degree can be directly used as the stability of the bubble region quantity change.

[0079] Furthermore, based on the same logic as the stability of the change in the number of bubble regions, the method for obtaining the stability of the change in the bubble richness includes:

[0080] The average bubble richness in all stirring area images within each reaction time period is obtained, and the average bubble richness is sorted according to the time sequence of the reaction time period to obtain the average bubble richness sequence. The absolute value of the difference between each element and the next element in the average bubble richness sequence is used as the bubble richness difference corresponding to each element. The time weight of the corresponding element is used as the weight of the bubble richness difference, and the bubble richness differences of all elements are weighted summed to obtain the overall bubble richness change degree. The overall bubble richness change degree is negatively correlated and mapped to obtain the stability of bubble richness change.

[0081] Because the stability of bubble richness changes is based on the same logic as the stability of bubble area quantity changes, it can be regarded as analyzing whether the reaction is complete in the dimension of bubble richness, and will not be elaborated here.

[0082] Preferably, in the embodiment of the present invention, considering that the reaction state of the real-time time period directly represents the current reaction characteristics, the greater the reaction state is, the more in the reaction stage, and the less complete the reaction is, the reaction state of the real-time time period is negatively correlated and mapped to obtain the initial reaction stability. In the embodiment of the present invention, the inverse of the reaction state of the real-time time period is used as the initial reaction stability.

[0083] The product of the stability of the change of the number of bubble regions, the stability of the change of the bubble richness, and the stability of the initial reaction is further normalized to obtain the reaction stability. That is, the greater the stability of the change of the number of bubble regions, the greater the stability of the change of the bubble richness, and the greater the initial reaction stability, the more complete the stirring reaction at the real time, and the greater the reaction stability.

[0084] Preferably, in one embodiment of the present invention, if the reaction stability in the real-time time period is greater than a preset stability threshold, the remaining preparation time under the stirring process is determined based on the reaction stability and the stirring device is controlled. It should be noted that because the real-time time period corresponds to the real time moment, the embodiment of the present invention can also be regarded as obtaining a reaction stability at each real time moment. Once the reaction stability is greater than the preset stability threshold, it can be said that the stirring area is about to be completely stirred, and the control command is executed to determine the remaining preparation time under the stirring process based on the reaction stability and control the stirring device. Please refer to Figure 4 , which shows a curve diagram showing the change of reaction stability over time under a stirring process provided by an embodiment of the present invention. Figure 4 The horizontal axis is time, the vertical axis is the reaction stability, and the dotted line is the position corresponding to the stability threshold. By setting the threshold, the control system for preparing high heat-resistant grease proposed in the embodiment of the present invention can efficiently and in real time control the stirring process of the grease, thereby avoiding the waste of control resources. At each real-time moment after the feedback control command, the reaction stability state is continuously observed, and the remaining preparation time is adjusted in real time, so that the stirring equipment can be stopped in time, thereby improving the preparation efficiency and speed.

[0085] In the embodiment of the present invention, because the reaction stability is normalized data, the preset stability threshold is set to 0.8.

[0086] Furthermore, the reaction stability determines the remaining preparation time under the stirring process and controls the stirring equipment, including:

[0087] Obtain the time difference between the stirring time and the preset stirring time. The greater the reaction stability, the smaller the remaining preparation time should be, so the reaction stability is negatively correlated and normalized to obtain the time adjustment weight. The time difference is regarded as the maximum remaining time, and the time adjustment weight is used to intercept it on this basis. The time adjustment weight is multiplied by the time difference to obtain the remaining preparation time.

[0088] It should be noted that, in some embodiments of the present invention, the reaction stability is a normalized value, so the difference between the positive integer 1 and the reaction stability can be directly used as the duration adjustment weight.

[0089] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0090] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A control system for preparing high heat-resistant grease, characterized in that: The system comprises: A preparation data storage module is used to obtain and store continuous multi-frame stirring area images in the reaction stirring process during the grease preparation process; the stirring process includes multiple reaction time periods, wherein the reaction time period corresponding to the real time is the real time time period; A reaction degree evaluation module is used to obtain the bubble overlap probability of the bubble area in each stirring region image frame according to the change characteristics of the bubble area at the same position between adjacent frames of stirring region images; obtain the bubble richness of each stirring region image frame according to the area of ​​the bubble area in the stirring region image and the bubble overlap probability; and obtain the reaction state of the reaction time period according to the change characteristics of the bubble richness in the reaction time period; A stirring device control module, used to obtain the reaction stability of the real-time time period according to the stability of the change of the number of bubble areas between the reaction time periods and the stability of the change of the bubble richness; determine the remaining preparation time under the stirring process according to the reaction stability and control the stirring device; The method for obtaining the stability of the change in the number of bubble regions includes: Obtaining the time weight of each reaction time period according to the distance between the reaction time period and the real-time time period; obtaining the average number of bubble regions in all stirring region images within each reaction time period, and sorting the average number of bubble regions according to the time sequence of the reaction time periods to obtain a sequence of the average number of bubble regions; The absolute value of the difference between each element and the next element in the average bubble area quantity sequence is used as the bubble quantity difference of each element; The time weight of the corresponding element is used as the weight of the bubble quantity difference, and the bubble quantity differences of all elements are weighted summed to obtain the overall bubble quantity change degree; The degree of change in the number of overall bubbles is negatively correlated and mapped to obtain the stability of the change in the number of bubble regions.

2. A control system for preparing high heat-resistant grease according to claim 1, characterized in that: The method for obtaining the bubble overlap probability includes: Select any one frame of stirring region image as the target stirring region image, select any one bubble region of the target stirring region image as the target bubble region; select the stirring region image of the previous frame of the target stirring region image as the comparison image; select the bubble region closest to the target bubble region in the comparison image as the comparison bubble region; A region variation feature is obtained according to the area difference between the comparison bubble region and the target bubble region; and the bubble overlap probability of the target bubble region is obtained according to the region variation feature and the number of the comparison bubble regions.

3. A control system for preparing a high heat-resistant grease according to claim 1, characterized in that: The method for obtaining the bubble richness comprises: For each frame of the stirring region image, the bubble overlap probability is used as a weight, and weighted sum is performed on the areas of the bubble regions in the stirring region image to obtain the bubble richness of each frame of the stirring region image.

4. A control system for preparing high heat-resistant grease according to claim 1, characterized in that: The method for obtaining the reaction state includes: The variance of the bubble abundance within the reaction time period is taken as the reaction state.

5. A control system for preparing high heat-resistant grease according to claim 1, characterized in that: The method for obtaining the stability of bubble richness variation includes: Obtaining the average bubble richness in all stirring area images in each reaction time period, and sorting the average bubble richness according to the time sequence of the reaction time period to obtain an average bubble richness sequence; The absolute value of the difference between each element and the next element in the average bubble richness sequence is used as the bubble richness difference corresponding to each element; The time weight of the corresponding element is used as the weight of the bubble richness difference, and the bubble richness differences of all elements are weighted summed to obtain the overall bubble richness change degree; The overall bubble richness variation degree is negatively correlated and mapped to obtain the stability of the bubble richness variation.

6. A control system for preparing high heat-resistant grease according to claim 1, characterized in that: The method for obtaining the reaction stability comprises: Negative correlation mapping of the reaction state in the real-time time period is performed to obtain the initial reaction stability; The product of the stability of the change in the number of bubble regions, the stability of the change in the bubble richness, and the initial reaction stability is normalized to obtain the reaction stability.

7. A control system for preparing high heat-resistant grease according to claim 1, characterized in that: If the reaction stability in the real-time time period is greater than a preset stability threshold, the remaining preparation time under the stirring process is determined according to the reaction stability and the stirring device is controlled.

8. A control system for preparing a high heat-resistant grease according to claim 1 or 7, characterized in that: The remaining preparation time under the stirring process is determined according to the reaction stability and the stirring equipment is controlled, including: The time difference between the stirring time and the preset stirring time is obtained, the reaction stability is negatively correlated and normalized to obtain a time adjustment weight; the time adjustment weight is multiplied by the time difference to obtain a remaining preparation time.

9. A control system for preparing high heat-resistant grease according to claim 1, characterized in that: The method for dividing the reaction time period includes: Taking the start time of the stirring process as the starting point, the sliding step of the time period sliding window is set to the preset length size according to the preset length size; the time period sliding window slides on the timing range of the stirring process to divide the stirring process into multiple reaction time periods.

Citation Information

Patent Citations

  • Image Recognition and Analysis System and Software

    US20080166037A1