Automatic control method and control system for a high-resilience sports floor mat production plant

Abstract

The application relates to the technical field of industrial control, in particular to an automatic control method and a control system of a high-rebound sports floor mat production equipment, the method comprising the following steps: acquiring process parameter information and observation parameter information of the production equipment to be controlled; driving a preset simulation production equipment to perform simulation production based on the process parameter information and the observation parameter information, so as to obtain a simulation mapping image; judging whether hidden danger features are contained in the simulation mapping image, if yes, performing hidden danger tracing based on the hidden danger features to obtain a hidden danger tracing result; optimizing the process parameter information based on the hidden danger tracing result, so as to obtain target execution parameter information, and performing production control based on the target execution parameter information. The application can reduce the probability of the phenomenon of appearing and bubbling or collapsing of the floor mat.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of industrial control, in particular to an automatic control method and control system for high-rebound sports floor production equipment. BACKGROUND

[0002] As a functional product widely used in sports venues, fitness rooms, children's playgrounds and other places, the performance and quality of high-rebound sports floor are directly related to the safety and experience of users. In the early days, the production of high-rebound sports floor mainly relied on manual operation and simple mechanical equipment, with low production efficiency and unstable product quality. In recent years, with the rapid development of artificial intelligence, Internet of Things, big data and other technologies, high-rebound sports floor production equipment is developing towards intelligentization. Intelligent equipment not only can realize automatic control of the production process, but also can collect production data in real time through sensors, and process and analyze the data by using big data analysis and artificial intelligence algorithms to realize intelligent optimization and predictive maintenance of the production process.

[0003] However, the foaming effect of sports floor is a complex multivariate coupling result, which is usually limited by variable complexity, equipment performance and external interference, etc. Therefore, it is difficult to completely eliminate defects such as bubble inclusion or bubble collapse. Sports floor with bubble inclusion or bubble collapse may cause impact force buffering failure, which may endanger the life and health of users. SUMMARY

[0004] In order to reduce the probability of bubble inclusion or bubble collapse in the floor, thereby improving the production quality of sports floor, the present application provides an automatic control method and control system for high-rebound sports floor production equipment.

[0005] In a first aspect, the present application provides an automatic control method for high-rebound sports floor production equipment, which adopts the following technical solution:

[0006] An automatic control method for high-rebound sports floor production equipment, comprising:

[0007] Obtaining process parameter information and observation parameter information of a production equipment to be controlled;

[0008] Driving a preset simulation production equipment to perform simulation production based on the process parameter information and the observation parameter information, to obtain a simulation mapping image;

[0009] Judging whether the simulation mapping image contains hidden danger features, and if so, performing hidden danger tracing based on the hidden danger features to obtain a hidden danger tracing result;

[0010] Optimizing the process parameter information based on the hidden danger tracing result to obtain target execution parameter information, and performing production control based on the target execution parameter information.

[0011] By adopting the technical scheme, after the process parameter information is acquired, the preset simulation model is simulated and driven in combination with the observation parameter information, so as to simulate the actual production process of the production equipment, whether the hidden danger feature is contained in the simulation mapping image is identified and judged, whether the process parameter information needs to be optimized is judged, the process parameter information is found and optimized in time in the simulation production process instead of being adjusted in the actual production process, the timeliness and accuracy when the hidden danger feature is found are improved, in addition, the process parameter is optimized or adjusted in time through the simulation production, the probability of the bubble or the bubble collapse phenomenon in the sports mat in the actual production process is reduced, and therefore the production quality of the sports mat is improved.

[0012] In a possible implementation manner, the hidden danger tracing based on the hidden danger feature includes:

[0013] The hidden danger surface feature and the hidden danger distribution of the hidden danger feature are determined based on the simulation mapping image, and a hidden danger feature distribution map is determined based on the hidden danger surface feature and the hidden danger distribution.

[0014] A plurality of process parameter combinations are determined based on the process parameter information, and a process influence distribution map corresponding to each process parameter combination is acquired.

[0015] The hidden danger feature distribution map is matched with each process influence distribution map, a target process influence distribution map is determined from all the process influence distribution maps based on a matching result, and an image matching value between the target process influence distribution map and the hidden danger feature distribution map is the highest.

[0016] The hidden danger tracing result is determined according to the process parameter combination corresponding to the target process influence distribution map.

[0017] By adopting the technical scheme, the hidden danger surface feature and the spatial distribution rule are extracted, the abstract quality defect is converted into a visual image, a visual analysis benchmark is provided for hidden danger tracing, a plurality of process influence distribution maps are obtained by combining and analyzing each process parameter, and the process parameter combination most likely to cause the hidden danger feature is selected from the plurality of process parameter combinations through image matching, and the accuracy of hidden danger tracing is improved.

[0018] In a possible implementation manner, when the hidden danger surface feature includes a preset target hidden danger feature, the method further includes:

[0019] A target hidden danger distribution and a target hidden danger proportion corresponding to the preset target hidden danger feature are determined from the hidden danger feature distribution map.

[0020] determine a process influence weight corresponding to the process parameter information based on the target hidden danger distribution and the target hidden danger proportion, and determine a fusion process influence map based on the process influence weight;

[0021] perform image matching on the fusion process influence map and the hidden danger feature distribution map to obtain a fusion matching value, and when the fusion matching value is higher than a preset matching threshold, determine a hidden danger traceability result based on a process parameter combination corresponding to the fusion process influence map.

[0022] By adopting the above technical solution, the key defect type is automatically focused through the preset target hidden danger feature screening mechanism. By analyzing the hidden danger distribution and the hidden danger proportion of the target hidden danger feature, the process parameters that may cause hidden danger phenomena can be accurately traced. After determining the process influence weight corresponding to the process parameter information, image matching is performed for verification. That is, only when the fusion matching value obtained by performing image matching on the fusion process influence map and the hidden danger feature distribution map meets the condition, the hidden danger traceability result is determined based on the fusion process influence map, thereby further improving the accuracy of determining the hidden danger traceability result.

[0023] In a possible implementation manner, the production control based on the target execution parameter information comprises:

[0024] driving the preset simulation production equipment to perform optimized simulation production based on the target execution parameter information to obtain an optimized simulation mapping image;

[0025] determining an optimization layer according to the simulation mapping image before optimization and the optimized simulation mapping image after optimization;

[0026] determining a hidden danger optimization coverage rate and a hidden danger optimization rate based on the optimization layer;

[0027] when the hidden danger optimization coverage rate is higher than a preset coverage rate threshold and the hidden danger optimization rate is higher than a preset optimization rate threshold, performing production control based on the target execution parameter information.

[0028] By adopting the above technical solution, the two-way verification of process improvement is realized through the closed-loop process of parameter optimization-simulation verification-effect quantification, which facilitates early investigation and analysis of the production effect after adjustment of the process parameter information, thereby avoiding the passive mode of trial and error-rework, and facilitating improvement of the optimization rate and precision.

[0029] In a possible implementation manner, when no optimization operation is detected within a first preset time period, the method further comprises:

[0030] obtaining historical production log information corresponding to a second preset time period, and determining a first intelligent control adjustment parameter interval corresponding to the process parameter information based on the historical production log information.

[0031] Obtain the actual observation parameter information corresponding to the current moment, generate feedback information based on the actual observation parameter information, and send the feedback information to relevant staff to remind them to select observation parameters to focus on from the actual observation parameter information;

[0032] After receiving the observation parameters selected by the relevant staff, the second intelligent control adjustment parameter range corresponding to the process parameter information is determined based on the observation parameters.

[0033] Based on the first intelligent control adjustment parameter range and the second intelligent control adjustment parameter range, a target intelligent control adjustment parameter range is determined, and intelligent auxiliary control is initiated based on the target intelligent control adjustment parameter range.

[0034] By adopting the above technical solution, the first intelligent control adjustment parameter range is obtained through historical production log information, and the second intelligent control adjustment parameter range is determined based on expert advice. The target intelligent control adjustment parameter range is determined through a combination of intelligent calculation and manual intervention, which helps to improve the accuracy of the intelligent assisted control stage. This reduces the probability of bubble formation or collapse during the intelligent assisted control stage. Activating intelligent assisted control also reduces the processing pressure on the system during the automatic control of production equipment.

[0035] In one possible implementation, after initiating intelligent auxiliary control based on the target intelligent control adjustment parameter range, the method further includes:

[0036] Obtain the control log and actual production images corresponding to the third preset time period, and determine the control intervention value based on the control log;

[0037] Based on the control log, the control area is determined, and the rate of change of bubble parameters corresponding to the control area is determined from the actual production image;

[0038] The duration of maintenance is determined based on the control intervention value and the rate of change of the bubble parameters, and the time for intelligent assistance to exit is determined based on the duration of maintenance.

[0039] By adopting the above technical solution and analyzing the control logs after the intelligent assisted control is initiated, it is convenient to assess whether the production status of the production equipment is stable. In addition, by identifying and analyzing the change rate of bubble parameters corresponding to the control area from the actual production images, it is convenient to monitor the quality of the finished sports mat during the intelligent assisted control process. By coupling the production status of the production equipment and the quality of the finished product during the intelligent assisted control stage, the duration of the intelligent assisted control operation can be analyzed and determined to avoid exiting the intelligent assisted control operation too early or too late.

[0040] In a second aspect, the application provides a control system, which adopts the technical scheme as follows:

[0041] A control system, comprising:

[0042] at least one processor;

[0043] a memory;

[0044] at least one application program, wherein the at least one application program is stored in the memory and is configured to be executed by the at least one processor, and the at least one application program is configured to execute the automatic control method of the high-rebound sports floor production equipment.

[0045] In a third aspect, the application provides a computer-readable storage medium, which adopts the technical scheme as follows:

[0046] A computer-readable storage medium, comprising a computer program capable of being loaded and executed by a processor to execute the automatic control method of the high-rebound sports floor production equipment.

[0047] In a fourth aspect, the application provides a computer program product, which adopts the technical scheme as follows:

[0048] A computer program product, comprising a computer program, which, when executed by a processor, implements the automatic control method of the high-rebound sports floor production equipment.

[0049] In summary, the application has at least one of the following beneficial technical effects:

[0050] By simulating and driving the preset simulation model in combination with the observation parameter information after obtaining the process parameter information, the actual production process of the production equipment can be simulated, whether the hidden danger features are contained in the simulation mapping image can be identified and judged, whether the process parameter information needs to be optimized can be judged, the process parameter information can be found and optimized in time during the simulation production process instead of being adjusted in the actual production process, the timeliness and accuracy of finding hidden danger features can be improved, in addition, the process parameters can be optimized or adjusted in time through simulation production, the probability of the appearance of the bubble or the collapse bubble phenomenon in the sports floor in the actual production process can be reduced, and thus the production quality of the sports floor can be improved.

[0051] Through the closed-loop process of parameter optimization-simulation verification-effect quantification, bidirectional verification of process improvement is realized, the production effect after adjustment of the process parameter information can be investigated and analyzed in advance, the passive mode of trial and error-rework can be avoided, and the optimization rate and precision degree can be improved. BRIEF DESCRIPTION OF DRAWINGS

[0052] Figure 1is a flowchart of an automatic control method of a high-resilience sports floor mat production equipment in embodiments of the present application;

[0053] Figure 2 is a production control flowchart in embodiments of the present application;

[0054] Figure 3 is a structure diagram of a control system in embodiments of the present application. DETAILED DESCRIPTION

[0055] The following will be described in detail in combination with the accompanying drawings. Figures 1 to 3 The present application is further described in detail.

[0056] Those skilled in the art can make modifications to the present embodiments according to needs after reading the present specification, but as long as the modifications are within the scope of the claims of the present application, they are protected by the patent law.

[0057] To make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below in combination with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of the present application.

[0058] It should be noted that in optional embodiments of the present application, the object information and other related data involved in the embodiments of the present application when applied to specific products or technologies need to obtain the permission or consent of the object, and the collection, use and processing of the related data need to comply with the relevant laws, regulations and standards of the country and region. That is, if the embodiments of the present application involve data related to the object, the data needs to be obtained with the authorization and consent of the object, the authorization and consent of the relevant department, and in compliance with the relevant laws, regulations and standards of the country and region. If the embodiments involve personal information, the consent of the individual needs to be obtained for all personal information, and if the information involves sensitive information, the separate consent of the information subject needs to be obtained, and the embodiments also need to be implemented with the authorization and consent of the object.

[0059] Specifically, the embodiment of the present application provides an automatic control method of a high-rebound sports floor mat production equipment, which is executed by a control system. The control system can be a server or a terminal device. The server can be a physical server, a server cluster composed of multiple physical servers or a distributed system, or a cloud server providing cloud computing services. The terminal device can be a smart phone, a tablet computer, a notebook computer, a desktop computer, etc., but is not limited thereto. The terminal device and the server can be directly or indirectly connected through wired or wireless communication, and the embodiment of the present application does not limit this.

[0060] Reference Figure 1 , Figure 1 is a flowchart of an automatic control method of a high-rebound sports floor mat production equipment in the embodiment of the present application. The method comprises steps S110-S140, wherein:

[0061] Step S110: Obtain process parameter information and observation parameter information of a production equipment to be controlled.

[0062] Specifically, the production equipment to be controlled is a high-rebound sports floor mat production equipment that needs to be automatically controlled. The production equipment to be controlled can cover all processes of foaming, mixing, extruding and molding. The foaming equipment is the core equipment for producing high-rebound sports floor mats, which is mainly used to generate chemical cross-linking polyethylene foam material through chemical reaction. The foaming equipment can be a high-pressure foaming machine or a PU foaming equipment. The specific foaming equipment can be set by relevant staff according to the actual production situation. The mixing equipment is mainly used to pre-mix the raw materials before foaming to ensure the uniformity of the formula, which directly affects the physical properties of the final product. The extruding equipment is mainly used to mix the foamed material with antioxidants, flame retardants and other additives uniformly, and form continuous particles or sheets through the extruding process. The extruding equipment can be a double-screw extruder. The molding equipment is mainly used to heat and plasticize the particles or sheets output by the double-screw extruder, and then extrude them into the final shape of the floor mat through a mold.

[0063] The process parameter information of the to-be-controlled production equipment includes, but is not limited to, temperature, pressure, cooling rate and raw material ratio involved in the processing process. As for the temperature, since the chemical cross-linking polyethylene foaming belongs to a chemical reaction, the temperature will affect the reaction speed and the foam quality. If the temperature is too high, the reaction may be too fast, and the foam structure may be unstable. If the temperature is too low, the reaction may be incomplete, and the resilience performance may be affected. Therefore, the temperature of the foaming, mixing and extruding stages needs to be considered and analyzed when automatically controlling the to-be-controlled production equipment. As for the pressure, since the pressure directly affects the formation and distribution of bubbles in the sports air cushion during the foaming process, when the pressure is insufficient, the bubbles in the sports air cushion may be too large or unevenly distributed, and the phenomenon of bubble collapse or bubble merging may occur. When the pressure is too high, the generation of bubbles in the sports air cushion may be inhibited, and thus the elasticity may be affected. Therefore, the pressure condition needs to be considered and analyzed when automatically controlling the to-be-controlled production equipment. As for the cooling rate, since the cooling rate affects the solidification speed and structural stability of the foam, if the cooling rate is too fast, internal stress may be caused, and the sports air cushion may be easily deformed. If the cooling rate is too slow, the production efficiency may be low, and even overheating decomposition may occur. Therefore, the cooling rate needs to be considered and analyzed when automatically controlling the to-be-controlled production equipment, to ensure the dimensional stability and uniform internal structure of the product. As for the raw material ratio, the raw material ratio directly affects the physical properties of the sports air cushion, such as the resilience, density and hardness. The process parameter information of the to-be-controlled production equipment can be collected by temperature sensors, pressure sensors, flow meters and weighing sensors arranged at the to-be-controlled production equipment, and uploaded to the control system. The specific process parameter information is not limited in the embodiments of the present application, and can be set by relevant technical personnel according to actual needs.

[0064] The observation parameter information of the to-be-controlled production equipment includes, but is not limited to, equipment state and environmental parameters. The equipment state includes, but is not limited to, running state, fault state and maintenance state. The environmental parameters include, but are not limited to, temperature and humidity. The specific content can be set by relevant technical personnel according to actual needs. The observation parameter information can be collected by sensors arranged at the to-be-controlled production equipment, and can also be recorded by relevant staff and uploaded to the control system.

[0065] Step S120: driving a preset simulation production equipment to simulate production based on the process parameter information and the observation parameter information, to obtain a simulation mapping image.

[0066] Specifically, the process parameter information and the observation parameter information of the to-be-controlled production equipment are collected during a trial run stage after starting the to-be-controlled production equipment. The production and processing conditions of the to-be-controlled production equipment in a future period of time are simulated and predicted based on the process parameter information and the observation parameter information collected during the trial run stage.

[0067] The simulation prediction process can include: establishing a preset simulation production device corresponding to the production device to be controlled, wherein, according to the production process of the high resilience sports floor mat, a mathematical model or a physical model capable of describing the foaming, mixing, extruding and molding processes of the actual production device to be controlled can be established, the mathematical model can include differential equations, difference equations or statistical models for describing the interaction and influence between process parameters, and the physical model can be based on finite element analysis or computational fluid dynamics to more accurately simulate physical phenomena in the production process, such as the formation and solidification process of the foam. The process of constructing the preset simulation production device is not specifically limited in the embodiments of the present application, as long as it can simulate the production and processing process of the production device to be controlled. After the preset simulation production device is constructed, the process parameter information and the observation parameter information can be input into the preset simulation production device, so that the preset simulation production device can simulate the production and processing tasks that may be faced in the future for a period of time according to the current state of the actual production device to be controlled. A large amount of simulation data will be generated in the simulation production process, including but not limited to simulation temperature distribution, simulation pressure change, simulation foam structure and other key simulation index data. The key simulation index data can be converted into intuitive images, i.e. simulation mapping images, by using preset data visualization technology, wherein the preset data visualization technology can be Matplotlib, OpenGL or Unity, and the specific preset data visualization technology is not specifically limited in the embodiments of the present application.

[0068] Step S130: determining whether the simulation mapping image contains hidden danger features, and if so, performing hidden danger tracing based on the hidden danger features to obtain a hidden danger tracing result.

[0069] Specifically, the hidden danger feature can be a bubble merging feature or a bubble collapsing feature. The feature can be identified from the simulation mapping image according to a preset feature recognition algorithm. When the simulation mapping image includes the hidden danger feature, it indicates that bubble merging or bubble collapsing may occur in the simulation production process. At this time, the cause of the hidden danger feature needs to be traced. Bubble merging refers to the phenomenon that two or more bubbles merge into a large bubble during the foaming process, which is usually caused by the pressure difference between bubbles or insufficient melt strength. Bubble collapsing refers to the phenomenon that a bubble collapses after formation, which may be caused by the diffusion of gas in the bubble to the melt, resulting in the collapse of the bubble due to the loss of support. When the temperature is abnormal, the melt strength of the polymer may decrease, causing the bubble to break, merge or collapse during growth. When the pressure is abnormal, the internal pressure of the bubble may be lower than the ambient pressure due to insufficient pressure, causing the gas to escape from the bubble, leading to bubble collapsing. When the cooling rate is abnormal, the bubble surface may solidify due to excessive cooling rate, while the internal temperature is still high, which may cause the bubble to break or collapse. When the raw material ratio is abnormal, the proportion of related cross-linking agents or additives may be too large or too small, affecting the physical properties of the foam, such as strength and toughness, thereby increasing the risk of bubble collapsing. Therefore, when the simulation mapping image includes the hidden danger feature, it indicates that there may be abnormal conditions in the process parameter information. At this time, the abnormal process parameter information needs to be determined through hidden danger tracing.

[0070] Further, in order to improve the accuracy of hidden danger tracing, hidden danger tracing based on hidden danger features obtains hidden danger tracing results, which can specifically include:

[0071] Based on the simulation mapping image, the hidden danger surface feature and the hidden danger distribution of the hidden danger feature are determined, and based on the hidden danger surface feature and the hidden danger distribution, a hidden danger feature distribution map is determined. Based on the process parameter information, a plurality of process parameter combinations are determined, and a process influence distribution map corresponding to each process parameter combination is obtained. The hidden danger feature distribution map and each process influence distribution map are image matched, and based on the image matching result, a target process influence distribution map is determined from all process influence distribution maps. The image matching value between the target process influence distribution map and the hidden danger feature distribution map is the highest. The hidden danger tracing result is determined according to the process parameter combination corresponding to the target process influence distribution map.

[0072] Specifically, the hidden danger surface features and the hidden danger distribution of the hidden danger features can be identified from the simulation mapping image according to a preset feature recognition algorithm. The hidden danger surface features can be bubble morphology, collapse depth, bubble color, bubble brightness, and the like. Since bubbles that are in the process of merging or collapsing can lose their original circular or elliptical shape and become flat or concave, and the internal structure can also change due to the merging or collapsing, the bubble brightness can decrease or the bubble color can change. Therefore, the hidden danger in the simulation mapping image can be further analyzed by observing the hidden danger surface features. The hidden danger distribution is the distribution or aggregation of the hidden danger features in the simulation mapping image. The hidden danger feature distribution map determined according to the hidden danger surface features and the hidden danger distribution only contains the areas in the simulation mapping image where the hidden danger features exist, and the hidden danger surface features corresponding to each hidden danger feature, that is, the hidden danger feature distribution map is a partial image of the simulation mapping image. Based on the hidden danger surface features and the hidden danger distribution, the specific position of each hidden danger feature in the simulation mapping image can be determined when the hidden danger feature distribution map is determined. The center coordinates, boundary coordinates, or pixel positions of each hidden danger feature can be recorded to achieve this. Then, the extracted hidden danger surface features and the specific positions corresponding to each hidden danger feature are mapped into a two-dimensional or three-dimensional space to generate the hidden danger feature distribution map. The specific generation method is not limited in the embodiments of the present application.

[0073] Since the process parameter information includes multiple process parameters, multiple process parameter combinations corresponding to the process parameter information can be obtained through feature combination. Each process parameter combination includes at least one process parameter. For example, the process parameter information includes three process parameters A, B, and C, and the corresponding process parameter combinations can be A, B, C, AB, AC, BC, and ABC. Since different process parameters can cause different abnormal phenomena after being abnormal, for example, temperature abnormality mainly affects the chemical reaction speed and foam quality, which can cause the reaction to be too fast or too slow, and the foam structure to be unstable, while pressure abnormality directly affects the formation and distribution of bubbles. The abnormality of temperature can be manifested as irregular bubble morphology, color or brightness change in the simulation mapping image, and the abnormality of pressure can be manifested as bubbles of different sizes and uneven distribution in the simulation mapping image. The process impact distribution maps corresponding to different process parameter combinations are different. The process impact distribution map corresponding to each process parameter combination can be determined by relevant staff according to historical experimental data and uploaded to the control system in advance.

[0074] The process impact distribution diagram is a diagram showing the possible bubble surface features and distribution after an abnormality occurs in the process parameters included in the corresponding process parameter combination. By matching the hidden danger feature distribution diagram with the process impact distribution diagram corresponding to each process parameter combination, and determining the target process impact distribution diagram with the highest similarity to the hidden danger feature distribution diagram from multiple process impact distribution diagrams, it is determined that the situation in the hidden danger feature distribution diagram is more likely to occur when an abnormality occurs in the process parameter combination corresponding to the target process impact distribution diagram. At this time, the final hidden danger traceability result is determined based on the process parameter combination corresponding to the target process impact distribution diagram, thereby improving the pertinence and accuracy of determining the hidden danger traceability result.

[0075] Further, when the hidden danger surface features include a preset target hidden danger feature, the method provided in the embodiments of the present application further includes:

[0076] determining a target hidden danger distribution and a target hidden danger proportion corresponding to the preset target hidden danger feature from the hidden danger feature distribution diagram; determining a process impact weight corresponding to the process parameter information based on the target hidden danger distribution and the target hidden danger proportion, and determining a fused process impact diagram based on the process impact weight; performing image matching on the fused process impact diagram and the hidden danger feature distribution diagram to obtain a fused matching value, and determining a hidden danger traceability result based on the process parameter combination corresponding to the fused process impact diagram when the fused matching value is higher than a preset matching threshold.

[0077] Specifically, the preset target hidden danger feature can be a preset bubble shape, a bubble collapse depth higher than a preset depth threshold, a preset bubble color, or a bubble brightness higher than a preset brightness. The specific content can be determined by relevant staff according to historical experimental data and uploaded to the control system. When the hidden danger surface features do not include the preset target hidden danger feature, the process impact distribution diagram determined by the relevant staff according to the historical experimental data can be directly used. However, when the hidden danger surface features include the preset target hidden danger feature, the hidden danger situation is more serious, and at this time, a corresponding fused process impact diagram can be individually formulated according to the specific performance of the hidden danger feature in the hidden danger feature distribution diagram. Specifically, the target hidden danger distribution and the target hidden danger proportion corresponding to the preset target hidden danger feature can be identified from the hidden danger feature distribution diagram according to a preset feature recognition algorithm. Different target hidden danger distributions and target hidden danger proportions correspond to different process impact weights, wherein the target hidden danger distribution can be an aggregation score of the target hidden danger feature, which can be determined by calculating the adjacent distance between each target hidden danger feature and its nearest neighbor target hidden danger feature in the hidden danger feature distribution diagram, and then analyzing the distribution of these adjacent distances according to a preset spatial statistical algorithm. The preset spatial statistical algorithm can be Ripley's K function, and the specific algorithm is not limited in the embodiments of the present application.

[0078] The process influence weight corresponding to the target hidden danger distribution and the target hidden danger proportion can be determined according to the preset influence weight mapping relationship. For example, the process parameter information corresponding to the hidden danger feature distribution map includes three process parameters A, B and C, the aggregation score corresponding to the target hidden danger distribution is 3, and the target hidden danger proportion is 40%. The corresponding process influence weight is A: B: C = 2: 3: 5. The specific content of the preset influence weight mapping relationship is not limited in the embodiment of the application, and can be determined by relevant staff according to historical experimental data and uploaded to the control system. The fusion process influence map corresponding to the determined process influence weight can be determined. For example, when the process influence weight is A: B: C = 2: 3: 5, the corresponding fusion process influence map is the influence generated after 20% process parameter A is abnormal, the influence generated after 30% process parameter B is abnormal, and the fusion phenomenon that can be caused after 50% process parameter C is abnormal.

[0079] After the fusion process influence map is determined, the fusion process influence map and the hidden danger feature distribution map are matched to obtain a fusion matching value. Only when the fusion matching value is higher than the preset matching threshold, the hidden danger traceability result can be determined based on the process parameter combination corresponding to the fusion process influence map. If the fusion matching value is not higher than the preset matching threshold, the determination method for the hidden danger traceability result when the preset target hidden danger feature is not included in the hidden danger surface feature in the above embodiment is still used for determination.

[0080] Step S140: optimizing the process parameter information based on the hidden danger traceability result to obtain target execution parameter information, and performing production control based on the target execution parameter information.

[0081] Specifically, when the process parameter information is optimized, the process parameter to be optimized can be identified from the hidden danger traceability result, and then targeted adjustment can be performed based on the process parameter to be optimized. The specific adjustment value is not limited in the embodiment of the application, as long as the abnormal probability of appearing and bubbling or collapsing based on the optimized process parameter information during actual processing is lower than the preset probability threshold. The specific preset probability threshold is not limited in the embodiment of the application, and can be determined by relevant staff according to historical experimental data and uploaded to the control system.

[0082] For the embodiments of the present application, after obtaining the process parameter information, the preset simulation model is simulated and driven in combination with the observation parameter information, so as to simulate the actual production process of the production equipment, to identify and judge whether the hidden danger features are contained in the simulation mapping image, to facilitate the judgment of whether the process parameter information needs to be optimized, to find and optimize the process parameter information in time in the simulation production process, instead of adjusting the process parameter information in the actual production process, to facilitate the improvement of the timeliness and accuracy when the hidden danger features are found, in addition, the process parameters are optimized or adjusted in time through the simulation production, to facilitate the reduction of the probability of the appearance of the bubble or the collapse bubble phenomenon in the actual production process of the sports mat, thereby facilitating the improvement of the production quality of the sports mat.

[0083] Further, in order to improve the optimization rate and accuracy, when the target execution parameter information is used for production control, steps S210-S240 can be included, as shown in the following table: Figure 2

[0084] Step S210: driving the preset simulation production equipment based on the target execution parameter information to perform optimization simulation production, to obtain an optimization simulation mapping image.

[0085] Step S220: determining an optimization layer according to the simulation mapping image before optimization and the optimization simulation mapping image after optimization.

[0086] Specifically, after the target execution parameter information is determined, the actual production is not directly performed according to the target execution parameter information, but the optimization simulation is first performed based on the target execution parameter information to obtain an optimization simulation mapping image, and the optimization result is evaluated by analyzing the optimization simulation mapping image, and when the optimization effect meets the preset condition, the actual production control of the production equipment to be controlled can be performed according to the target execution parameter information.

[0087] The target execution parameter information can be input into the preset simulation production equipment for optimization simulation production, and after the optimization simulation mapping image is obtained, the simulation mapping image before optimization and the optimization simulation mapping image after optimization are preprocessed, so as to improve the image quality of the simulation mapping image and the optimization simulation mapping image, to facilitate subsequent feature extraction and analysis operations, and the image preprocessing includes but is not limited to denoising, contrast enhancement, image correction, etc. The preset image processing technology can be used to extract hidden danger features such as bubble shape, collapse depth, color change, brightness anomaly, etc. from the optimization simulation mapping image and the simulation mapping image, and then the preset feature matching algorithm is used to identify the changes of the hidden danger features between the two images, and the optimization layer is determined based on the changes.

[0088] Step S230: determining a hidden danger optimization coverage and a hidden danger optimization rate based on the optimization layer.

[0089] ​Step S240: When the hidden danger optimization coverage rate is higher than the preset coverage rate threshold, and the hidden danger optimization rate is higher than the preset optimization rate threshold, production control is performed based on the target execution parameter information.

[0090] Specifically, the hidden danger optimization coverage rate is used to reflect the coverage degree of the optimization measures on the hidden danger area containing the hidden danger feature in the simulation mapping image. The hidden danger optimization coverage rate can be obtained by calculating the ratio of the area of the hidden danger area after optimization to the area of the hidden danger area before optimization. The formula can be expressed as: hidden danger optimization coverage rate = (area of hidden danger area before optimization-area of hidden danger area after optimization) / area of hidden danger area before optimization x 100%. The hidden danger optimization rate is used to reflect the reduction degree of the optimization measures on the hidden danger feature in the simulation mapping image. The hidden danger optimization rate can be obtained by calculating the change in the number of hidden danger features before and after optimization. The formula can be expressed as: hidden danger optimization rate = (number of hidden danger features before optimization-number of hidden danger features after optimization) / number of hidden danger features before optimization x 100%. When the hidden danger optimization coverage rate is higher than the preset coverage rate threshold, and the hidden danger optimization rate is higher than the preset optimization rate threshold, it indicates that the optimization effect meets the preset condition. At this time, the actual production control of the production equipment to be controlled can be performed based on the target execution parameter information. The specific preset coverage rate threshold and the preset optimization rate threshold are not limited in the embodiments of the present application, and can be determined by relevant personnel according to historical experimental data and uploaded to the control system.

[0091] Through the closed-loop process of parameter optimization-simulation verification-effect quantification, bidirectional verification of process improvement is realized, which facilitates early examination and analysis of the production effect after adjustment of the process parameter information, thereby facilitating avoidance of the passive mode of trial and error-rework, and facilitating improvement of the optimization rate and precision.

[0092] Further, when no optimization operation is detected within the first preset time period, the method provided in the embodiments of the present application further comprises:

[0093] obtaining historical production log information corresponding to a second preset time period, and determining a first intelligent control adjustment parameter interval corresponding to the process parameter information based on the historical production log information; obtaining actual observation parameter information corresponding to the current time, generating feedback information based on the actual observation parameter information, and feeding back the feedback information to the relevant personnel to remind the relevant personnel to select a concerned observation parameter from the actual observation parameter information; after receiving the concerned observation parameter selected by the relevant personnel, determining a second intelligent control adjustment parameter interval corresponding to the process parameter information based on the concerned observation parameter; determining a target intelligent control adjustment parameter interval based on the first intelligent control adjustment parameter interval and the second intelligent control adjustment parameter interval, and starting intelligent auxiliary regulation and control based on the target intelligent control adjustment parameter interval.

[0094] Specifically, the first preset time period is a period of time after the last time an optimization operation is detected, and the duration corresponding to the first preset time can be 30 minutes, and can also be 40 minutes. The specific duration is not limited in the embodiments of the present application. If no optimization operation is detected within the first preset time period, it can be indicated that the working state of the to-be-controlled production equipment in the first preset time period is relatively stable. The second preset time period is a period of time before the current time, and the duration corresponding to the second preset time period can be 24 hours, and can also be 36 hours. The specific duration is not limited in the embodiments of the present application.

[0095] The historical production log information contains key data such as historical set values, historical actual processing values, abnormal events in the production process, and product quality detection results of each process parameter in the historical production stage. After obtaining the historical production log information corresponding to the second preset time period, the historical production log information can be cleaned and preprocessed to remove invalid data in the historical production log information. According to the historical production log information, the first intelligent control adjustment parameter interval corresponding to the process parameter information is determined, which is used to reflect the stable working range of the to-be-controlled production equipment in the historical production process, that is, when the to-be-controlled production equipment performs processing operation according to the first intelligent control adjustment parameter interval in the historical production stage, the probability of abnormality or failure of the to-be-controlled production equipment is relatively low.

[0096] The actual observation parameter information is the actual device state and actual environment parameter actually collected at the current time. Different actual observation parameter information may face different hidden risks. Feedback information containing the actual observation parameter information is fed back to the relevant staff through a user interface, an alarm system or a mobile application, etc. to remind the relevant staff to select the observation parameter of interest according to personal experience. The observation parameter of interest is a process parameter that the relevant staff considers to be particularly concerned about or adjusted in the current production process. After receiving the observation parameter of interest fed back by the relevant staff, the safety range of the observation parameter of interest, i.e., the second intelligent control adjustment parameter interval, can be predicted based on the process knowledge base or expert system contained in the control system. The process knowledge base or expert system can be uploaded to the control system in advance by the relevant staff according to historical experimental data.

[0097] The first intelligent control adjustment parameter interval and the second intelligent control adjustment parameter interval are intersected and fused to obtain a target intelligent control adjustment parameter interval which comprehensively considers historical stability and real-time attention demand, each process parameter in the process parameter information is automatically adjusted according to the target intelligent control adjustment parameter interval, so as to keep the process parameter in the target interval, the target intelligent control adjustment parameter interval is determined by means of intelligent calculation and manual intervention, so as to improve the accuracy of the intelligent auxiliary control stage, thereby reducing the probability of bubble collapse or bubble collapse in the intelligent auxiliary control stage, and the processing pressure of the system in the automatic control process of the production equipment is reduced by starting the intelligent auxiliary control.

[0098] Further, in order to avoid too early or too late exit of the intelligent auxiliary control operation, after starting the intelligent auxiliary control based on the target intelligent control adjustment parameter interval, the method provided by the embodiment of the application further comprises:

[0099] The control log and the actual production image corresponding to the third preset time period are obtained, and a control intervention value is determined based on the control log; a control region is determined based on the control log, and a bubble parameter change rate corresponding to the control region is determined from the actual production image; a maintenance time length is determined based on the control intervention value and the bubble parameter change rate, and an intelligent auxiliary exit time is determined based on the maintenance time length.

[0100] Specifically, the third preset time period is a period of time after starting the intelligent auxiliary control operation. After starting the intelligent auxiliary control operation, it is not necessary to control the production equipment in real time, as long as each process parameter is located in the corresponding intelligent control adjustment parameter interval. However, the production equipment to be controlled is not always suitable for the intelligent auxiliary control state. The control log in the third preset time period can be extracted from the control system. The control log should include detailed records of the intelligent control operation, such as control frequency, control amplitude, control time and other key information. By quantifying the control log, the corresponding control disturbance value can be obtained. The more the control frequency, the greater the control amplitude, and the higher the control frequency, the higher the corresponding control disturbance value.

[0101] At the same time, the actual production image in the third preset time period can also be obtained from the monitoring system of the production site. According to the feature recognition algorithm, the change of the bubble parameter corresponding to the bubble structure in the third preset time period can be determined from the actual production image. The bubble parameter can be bubble density, pore diameter uniformity, wall thickness ratio, etc. The bubble parameter change rate can be determined by calculating the difference between each bubble parameter at different time points and dividing the time interval. The bubble parameter change rate is the average change rate of all bubble parameters.

[0102] The different control intervention values and the different bubble parameters change rates correspond to different maintenance durations, the maintenance duration of the actual production image corresponding control intervention value and bubble parameter change rate can be determined based on a preset duration mapping relationship, the current time is taken as a starting point, and a time reached after the maintenance duration is an intelligent auxiliary exit time, an exit operation is performed at the intelligent auxiliary exit time, the intervention of the intelligent auxiliary control is stopped, and the real-time control of the production equipment to be controlled is re-performed according to real-time conditions. The production state and the finished product quality of the production equipment in the intelligent auxiliary control stage are coupled, the maintenance duration of the intelligent auxiliary control operation is analyzed and determined, and the intelligent auxiliary control operation is avoided from being exited too early or too late.

[0103] An embodiment of the present application provides a control system, as shown in Figure 3 Figure 3 The control system 300 shown in the figure comprises a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, for example, connected through a bus 302. Optionally, the control system 300 can further comprise a transceiver 304. It should be noted that the transceiver 304 is not limited to one in actual application, and the structure of the control system 300 does not constitute a limitation on the embodiments of the present application.

[0104] The processor 301 can be a CPU (Central Processing Unit, central processor), a general-purpose processor, a DSP (Digital Signal Processor, data signal processor), an ASIC (Application Specific Integrated Circuit, application specific integrated circuit), an FPGA (Field Programmable Gate Array, field programmable gate array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It can realize or execute various exemplary logical blocks, modules and circuits described in combination with the disclosure content of the present application. The processor 301 can also be a combination of computing functions, such as one or more microprocessor combinations, DSP and microprocessor combinations, etc.

[0105] The bus 302 can comprise a channel for transmitting information between the above-mentioned components. The bus 302 can be a PCI (Peripheral Component Interconnect, peripheral component interconnect) bus or an EISA (Extended Industry Standard Architecture, extended industry standard architecture) bus, etc. The bus 302 can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, Figure 3 In the figure, only one line is used to represent the bus, but it does not mean that there is only one bus or only one type of bus. ​

[0106] The memory 303 can be a ROM (Read Only Memory) or other type of static storage device that can store static information and instructions, a RAM (Random Access Memory) or other type of dynamic storage device that can store information and instructions, an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, a magnetic disk storage or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and that can be accessed by a computer, but is not limited thereto.

[0107] The memory 303 is configured to store application program codes for implementing the solutions of the present application, and the processor 301 is configured to control the execution. The processor 301 is configured to execute the application program codes stored in the memory 303 to implement the content shown in the foregoing method embodiments.

[0108] The control system includes, but is not limited to, a mobile terminal such as a mobile phone, a notebook computer, a digital broadcast receiver, a PDA (Personal Digital Assistant), a PAD (Tablet Personal Computer), a PMP (Portable Multimedia Player), a vehicle terminal (for example, a vehicle navigation terminal), and the like, and a fixed terminal such as a digital TV, a desktop computer, and the like. It can also be a server or the like. Figure 3 The control system shown is only an example, and should not bring any limitation to the functions and use range of the embodiments of the present application.

[0109] The embodiments of the present application provide a computer readable storage medium, which has stored thereon a computer program, and when the computer program is run on a computer, the computer can execute the corresponding content in the foregoing method embodiments.

[0110] The embodiments of the present application provide a computer program product, which includes a computer program, and when the computer program is executed by a processor, the method in any of the foregoing embodiments is implemented.

[0111] It should be understood that although the steps in the flowcharts of the drawings are shown in a sequential order following the arrows, the steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated otherwise herein, the execution of the steps is not strictly limited to the order indicated by the arrows, and can be executed in other orders. Moreover, at least some of the steps in the flowcharts of the drawings can include multiple sub-steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of which is not necessarily sequential, but can be round-robin or alternating with at least some of the other steps or sub-steps or stages of other steps.

[0112] The above only describes some embodiments of the present application, and it should be pointed out that for those skilled in the art, without departing from the principles of the present application, a number of improvements and refinements can be made, which should also be considered as the protection scope of the present application.

Claims

1. An automatic control method of a high-resilience sports floor mat production apparatus, characterized by, The method comprises the following steps: acquiring process parameter information and observation parameter information of a production device to be controlled; driving a preset simulation production device to perform simulation production based on the process parameter information and the observation parameter information, and obtaining a simulation mapping image; determining whether the simulation mapping image contains a hidden danger feature, and if so, performing hidden danger tracing based on the hidden danger feature to obtain a hidden danger tracing result; optimizing the process parameter information based on the hidden danger tracing result to obtain target execution parameter information, and performing production control based on the target execution parameter information; wherein the hidden danger tracing based on the hidden danger feature to obtain a hidden danger tracing result comprises: determining a hidden danger surface feature and a hidden danger distribution of the hidden danger feature based on the simulation mapping image, and determining a hidden danger feature distribution map based on the hidden danger surface feature and the hidden danger distribution; determining a plurality of process parameter combinations based on the process parameter information, and obtaining a process influence distribution map corresponding to each process parameter combination; performing image matching on the hidden danger feature distribution map and each process influence distribution map, determining a target process influence distribution map from all the process influence distribution maps based on the image matching result, and the image matching value between the target process influence distribution map and the hidden danger feature distribution map is the highest; determining the hidden danger tracing result according to the process parameter combination corresponding to the target process influence distribution map; wherein when the hidden danger surface feature contains a preset target hidden danger feature, the method further comprises: determining a target hidden danger distribution and a target hidden danger proportion corresponding to the preset target hidden danger feature from the hidden danger feature distribution map; determining a process influence weight corresponding to the process parameter information based on the target hidden danger distribution and the target hidden danger proportion, and determining a fused process influence map based on the process influence weight; performing image matching on the fused process influence map and the hidden danger feature distribution map to obtain a fused matching value, and when the fused matching value is higher than a preset matching threshold, determining the hidden danger tracing result based on the process parameter combination corresponding to the fused process influence map; wherein the production control based on the target execution parameter information comprises: driving the preset simulation production device to perform optimized simulation production based on the target execution parameter information, and obtaining an optimized simulation mapping image; determining an optimization layer according to the simulation mapping image before optimization and the optimized simulation mapping image after optimization; calculating the ratio of the hidden danger area after optimization to the hidden danger area before optimization in the optimization layer to obtain a hidden danger optimization coverage rate, and the formula is: hidden danger optimization coverage rate=(hidden danger area before optimization-hidden danger area after optimization) / hidden danger area before optimization×100%, wherein the hidden danger optimization coverage rate reflects the coverage degree of the optimization measure on the hidden danger area containing the hidden danger feature in the simulation mapping image; calculating the change of the number of hidden danger features before and after optimization to obtain a hidden danger optimization rate, and the formula is: hidden danger optimization rate=(number of hidden danger features before optimization-number of hidden danger features after optimization) / number of hidden danger features before optimization×100%, wherein the hidden danger optimization rate reflects the reduction degree of the optimization measure on the hidden danger containing the hidden danger feature in the simulation mapping image; When the hidden danger optimization coverage is higher than a preset coverage threshold, and the hidden danger optimization rate is higher than a preset optimization rate threshold, production control is performed based on the target execution parameter information; When no optimization operation is detected within a first preset time period, the method further includes: obtaining historical production log information corresponding to a second preset time period, and determining a first intelligent control adjustment parameter interval corresponding to the process parameter information based on the historical production log information; obtaining actual observation parameter information corresponding to a current time, generating feedback information based on the actual observation parameter information, and feeding back the feedback information to relevant staff to remind the relevant staff to select a concerned observation parameter from the actual observation parameter information; after receiving the concerned observation parameter selected by the relevant staff, determining a second intelligent control adjustment parameter interval corresponding to the process parameter information based on the concerned observation parameter; determining a target intelligent control adjustment parameter interval based on the first intelligent control adjustment parameter interval and the second intelligent control adjustment parameter interval, and starting intelligent auxiliary control based on the target intelligent control adjustment parameter interval; After the intelligent auxiliary control is started based on the target intelligent control adjustment parameter interval, the method further includes: obtaining a control log and an actual production image corresponding to a third preset time period, and determining a control intervention value based on the control log, wherein the control log contains a control number, a control amplitude, and a control time of the intelligent control operation, and the control log is quantified to obtain a corresponding control disturbance value, wherein the more the control number, the greater the control amplitude, and the higher the control frequency, the higher the corresponding control disturbance value; determining a control region based on the control log, determining a cell parameter corresponding to a cell structure from the actual production image according to a feature recognition algorithm, the cell parameter being a cell density, a pore size uniformity, and a wall thickness ratio, calculating a difference value of each cell parameter at different time points within the third preset time period, and dividing the difference value by a time interval to determine a cell parameter change rate, the cell parameter change rate being an average change rate of all cell parameters; determining a maintenance time length of the control intervention value and the cell parameter change rate corresponding to the actual production image based on a preset time length mapping relationship, the maintenance time length being different for different control intervention values and cell parameter change rates, the time at which the current time is reached after the maintenance time length is an intelligent auxiliary exit time, and an exit operation is performed at the intelligent auxiliary exit time to stop the intervention of the intelligent auxiliary control.

2. A control system characterized by, The control system includes: at least one processor; a memory; at least one application program, wherein the at least one application program is stored in the memory and is configured to be executed by the at least one processor, and the at least one application program is configured to perform the automatic control method of the high-rebound sports floor mat production equipment as claimed in claim 1.

3. A computer-readable storage medium, characterized in that, including: a computer program stored in the memory and capable of being loaded and executed by the processor to perform the automatic control method of the high-rebound sports floor mat production equipment as claimed in claim 1.

4. A computer program product, characterized in that, including a computer program, which, when executed by a processor, implements the steps of the automatic control method of the high-rebound sports floor mat production equipment as claimed in claim 1.

Images