Dispensing machine equipment control method and system based on multiple scenes

Abstract

The invention belongs to the technical field of dispensing control, and particularly relates to a dispensing machine equipment control method and system based on multiple scenes. According to the invention, through real-time scene perception and prediction processing, the dispensing parameters can be dynamically adjusted, the track deviation and the glue amount error can be obviously reduced, the dispensing consistency and the yield can be improved, aiming at different substrate materials, glue types and complex tracks, the optimal parameter set can be called by one key, repeated manual debugging is not needed, the trial production and switching time is obviously shortened, and the production efficiency is improved. Equipment health monitoring and maintenance instructions are integrated in a closed-loop mode, compensation can be conducted in time when slight deviation occurs, early warning and maintenance can be conducted before a fault occurs, the equipment outage rate is reduced, the service life of key components is prolonged, a feedback mechanism of the maintenance effect and self-updating of a parameter set are achieved, the learning capacity is achieved, and the maintenance efficiency is improved along with accumulation of operation data. The control precision and the response speed are continuously improved, more complex production requirements are met, the glue amount and process parameters are accurately controlled, and material waste is reduced.

Description

Technical Field

[0001] The present invention belongs to the technical field of dispensing control, and in particular relates to a dispensing machine equipment control method and system based on multiple scenarios. Background Art

[0002] As a key process equipment in industries such as precision electronics manufacturing, semiconductor packaging, LED packaging, automotive electronics, and medical devices, glue dispensers' performance has a direct impact on product quality. The glue dispensing process requires precise application of glue at a specific location, along a specific trajectory, and with a stable amount of glue. This process is highly sensitive to various factors, including glue type, substrate material, ambient temperature and humidity, and the complexity of the dispensing path.

[0003] Existing control methods for dispensing equipment are mostly based on parameter setting for a single or a few working conditions, using static control parameters or semi-manual adjustment methods to cope with different working scenarios. As the electronics manufacturing industry develops towards high density, small size, and multiple categories, the complexity of the scenarios faced by dispensing operations has increased significantly, the dispensing path has shown nonlinear growth, and the impact of environmental fluctuations on the viscosity and flow rate of the glue has intensified. Traditional control methods are no longer able to meet the high stability and high-precision dispensing requirements under variable working conditions. Traditional control methods are usually fixed before leaving the factory and lack the ability to adapt to multiple scenarios. The data collection frequency during the dispensing process is fixed, making it difficult to flexibly adjust between normal working conditions and abnormal fluctuations. There is a lack of dynamic maintenance mechanisms based on equipment health status and dispensing quality feedback, resulting in performance degradation of the equipment during long-term operation, delayed response of the control strategy, and difficulty in timely identifying deviations and making effective compensation, which seriously affects the production line yield and equipment reliability. Summary of the Invention

[0004] The purpose of the present invention is to provide a dispensing machine equipment control method and system based on multiple scenarios, which can perceive changes in multiple scenarios, predict dispensing effects and deviations, dynamically identify control strategies, and perform adaptive maintenance and parameter optimization based on equipment status.

[0005] The technical solutions adopted by the present invention are as follows:

[0006] A method for controlling a dispensing machine device based on multiple scenarios, comprising:

[0007] Acquire scene data, where the scene data includes substrate material information, glue type information, ambient temperature and humidity information, and dispensing trajectory complexity information, and acquire a corresponding control parameter set based on the scene data;

[0008] Obtain dispensing effect data and trajectory deviation data during the dispensing process according to the control parameter set, and obtain predicted dispensing information based on the dispensing effect data and trajectory deviation data;

[0009] Extracting deviation information that does not meet preset conditions based on the predicted dispensing information, and obtaining a control strategy based on the deviation information, wherein the control strategy includes conventional, low deviation and high deviation;

[0010] Obtain equipment health information according to the control strategy, obtain corresponding equipment maintenance instructions according to the equipment health information, obtain corresponding equipment maintenance effects based on the corresponding equipment maintenance instructions, and optimize the control parameter set according to the corresponding equipment maintenance effects.

[0011] In a preferred embodiment, scene data is obtained, wherein the scene data includes substrate material, glue type, ambient temperature and humidity, and glue dispensing trajectory complexity. The step of obtaining a corresponding control parameter set based on the scene data includes:

[0012] Acquire scene data, where the scene data includes substrate material information, glue type information, ambient temperature and humidity information, and dispensing trajectory complexity information;

[0013] According to the substrate material information, glue type information, ambient temperature and humidity information and glue dispensing trajectory complexity information, the corresponding substrate material vector, glue type vector, ambient temperature and humidity value and glue dispensing trajectory complexity value are obtained respectively;

[0014] Obtain the scene value based on the substrate material vector, glue type vector, ambient temperature and humidity values, and glue dispensing trajectory complexity value;

[0015] Obtaining a parameter table, wherein the parameter table includes multiple scene value intervals and a control parameter set corresponding to each scene value interval;

[0016] Obtain the corresponding control parameter set from the parameter table according to the scene value interval corresponding to the scene value.

[0017] In a preferred embodiment, the steps of obtaining dispensing effect data and trajectory deviation data during the dispensing process according to the control parameter set, and obtaining predicted dispensing information according to the dispensing effect data and trajectory deviation data include:

[0018] Obtain corresponding ambient temperature and humidity values ​​and dispensing trajectory complexity values ​​according to ambient temperature and humidity information and dispensing trajectory complexity information;

[0019] Obtain the dispensing impact value based on the ambient temperature and humidity values ​​and the dispensing trajectory complexity value;

[0020] Obtaining a duration table, wherein the duration table includes multiple dispensing impact value intervals and a collection duration corresponding to each dispensing impact value interval;

[0021] Obtain the corresponding collection duration from the duration table according to the dispensing impact value interval corresponding to the dispensing impact value;

[0022] According to the control parameter set, the control parameters of the dispensing machine equipment are adjusted, and the dispensing start time node after the dispensing machine equipment control parameters are adjusted is obtained; the end time node is obtained based on the collection duration, and the dispensing collection period is obtained according to the start time node and the end time node;

[0023] Obtain dispensing effect data and trajectory deviation data during the dispensing collection period;

[0024] Obtain corresponding dispensing effect values ​​and trajectory deviation values ​​according to the dispensing effect data and trajectory deviation data;

[0025] The dispensing prediction value is obtained according to the dispensing effect value and the trajectory deviation value, and marked as the predicted dispensing information.

[0026] In a preferred embodiment, deviation information that does not meet the preset conditions is extracted based on the predicted dispensing information, and a control strategy is obtained according to the deviation information, wherein the control strategy includes conventional, low deviation and high deviation steps, including:

[0027] Obtaining a corresponding predicted dispensing value based on the predicted dispensing information;

[0028] Obtain the predicted dispensing threshold, and determine whether the predicted dispensing value is lower than the predicted dispensing threshold;

[0029] If the predicted dispensing value is lower than the predicted dispensing threshold, it is determined to be dispensing abnormality;

[0030] If the predicted dispensing value is not lower than the predicted dispensing threshold, it is determined that the dispensing is normal;

[0031] When it is determined that the dispensing is abnormal, standard dispensing effect data and standard trajectory data in the dispensing process are obtained according to the control parameter set, and corresponding multiple standard dispensing effect vectors and multiple standard trajectory vectors are obtained based on the standard dispensing effect data and the standard trajectory data;

[0032] Acquire corresponding multiple dispensing effect vectors and multiple trajectory deviation vectors according to the dispensing effect data and the trajectory deviation data;

[0033] Obtaining a dispensing deviation value according to a predicted dispensing value, a predicted dispensing threshold, multiple standard dispensing effect vectors, multiple standard trajectory vectors, multiple dispensing effect vectors, and multiple trajectory deviation vectors, and marking the value as deviation information;

[0034] A control strategy is obtained according to the dispensing deviation value, wherein the control strategy includes normal, low deviation and high deviation.

[0035] In a preferred embodiment, a control strategy is obtained based on the dispensing deviation value, wherein the control strategy includes conventional, low deviation and high deviation steps, including:

[0036] Get the strategy range and determine whether the dispensing deviation value is within the strategy range;

[0037] If the dispensing deviation value is within the strategy range, the control strategy is determined to be conventional;

[0038] If the dispensing deviation value is not within the strategy range and is less than the lower limit of the strategy range, the control strategy is judged to be low deviation;

[0039] If the dispensing deviation value is not within the strategy range and is greater than the upper limit of the strategy range, the control strategy is determined to be high deviation.

[0040] In a preferred embodiment, the steps of obtaining device health information according to a control strategy, obtaining corresponding device maintenance instructions according to the device health information, obtaining corresponding device maintenance effects based on the corresponding device maintenance instructions, and optimizing a control parameter set according to the corresponding device maintenance effects include:

[0041] When the control strategy is conventional, the corresponding dispensing effect value and trajectory deviation value are obtained according to the dispensing effect data and trajectory deviation data, and the corresponding ambient temperature and humidity weight and dispensing trajectory complexity weight are obtained based on the ambient temperature and humidity information and the dispensing trajectory complexity information;

[0042] The device health value is obtained based on the dispensing effect value, trajectory deviation value, ambient temperature and humidity weight, and dispensing trajectory complexity weight, and marked as device health information;

[0043] Obtaining a maintenance instruction table, wherein the maintenance instruction table includes multiple device health value intervals and device maintenance instructions corresponding to each device health value interval;

[0044] Obtain corresponding equipment maintenance instructions from the maintenance instruction table according to the equipment health value interval corresponding to the equipment health value;

[0045] A corresponding equipment maintenance effect is obtained based on the corresponding equipment maintenance instruction, and a control parameter set is optimized according to the corresponding equipment maintenance effect.

[0046] In a preferred embodiment, the steps of obtaining device health information according to a control strategy, obtaining corresponding device maintenance instructions according to the device health information, obtaining corresponding device maintenance effects based on the corresponding device maintenance instructions, and optimizing a control parameter set according to the corresponding device maintenance effects include:

[0047] When the control strategy is low deviation, the corresponding low data acquisition frequency is obtained based on the control strategy being low deviation, and multiple dispensing effect stage values ​​and multiple trajectory deviation stage values ​​are obtained according to the low data acquisition frequency during the dispensing process, and the corresponding ambient temperature and humidity weights and dispensing trajectory complexity weights are obtained based on the ambient temperature and humidity information and the dispensing trajectory complexity information;

[0048] Obtain the low dispensing effect stage threshold and the low trajectory deviation stage threshold;

[0049] Obtaining dispensing effect stage values ​​that are less than a low dispensing effect stage threshold and summarizing them into a low dispensing effect stage value set;

[0050] Obtain trajectory deviation stage values ​​that are less than a low trajectory deviation stage threshold and summarize them into a low trajectory deviation stage value set;

[0051] Obtain a low device health value based on the low dispensing effect stage value set, the low trajectory deviation stage value set, the ambient temperature and humidity weight, and the dispensing trajectory complexity weight, and mark it as device health information;

[0052] Obtaining a low maintenance instruction table, wherein the low maintenance instruction table includes multiple low device health value intervals and device maintenance instructions corresponding to each low device health value interval;

[0053] Obtain corresponding equipment maintenance instructions from the low maintenance instruction table according to the low equipment health value interval corresponding to the low equipment health value;

[0054] A corresponding equipment maintenance effect is obtained based on the corresponding equipment maintenance instruction, and a control parameter set is optimized according to the corresponding equipment maintenance effect.

[0055] In a preferred embodiment, the steps of obtaining device health information according to a control strategy, obtaining corresponding device maintenance instructions according to the device health information, obtaining corresponding device maintenance effects based on the corresponding device maintenance instructions, and optimizing a control parameter set according to the corresponding device maintenance effects include:

[0056] When the control strategy is high deviation, the corresponding high data acquisition frequency is obtained based on the control strategy being high deviation, and multiple dispensing effect stage values ​​and multiple trajectory deviation stage values ​​in the dispensing process are obtained according to the high data acquisition frequency, and the corresponding ambient temperature and humidity weights and dispensing trajectory complexity weights are obtained based on the ambient temperature and humidity information and the dispensing trajectory complexity information;

[0057] Obtain the high dispensing effect stage value interval and the high trajectory deviation stage value interval;

[0058] Obtaining the dispensing effect stage values ​​that are not within the high dispensing effect stage value range and summarizing them into a high dispensing effect stage value set;

[0059] Obtain trajectory deviation stage values ​​that are not within the high trajectory deviation stage value interval and summarize them into a high trajectory deviation stage value set;

[0060] Obtain high device health values ​​based on the high dispensing effect stage value set, high trajectory deviation stage value set, ambient temperature and humidity weights, and dispensing trajectory complexity weights, and mark them as device health information;

[0061] Obtaining a high maintenance instruction table, wherein the high maintenance instruction table includes multiple high equipment health value intervals and equipment maintenance instructions corresponding to each high equipment health value interval;

[0062] Obtain corresponding equipment maintenance instructions from the high maintenance instruction table according to the high equipment health value interval corresponding to the high equipment health value;

[0063] A corresponding equipment maintenance effect is obtained based on the corresponding equipment maintenance instruction, and a control parameter set is optimized according to the corresponding equipment maintenance effect.

[0064] The present invention also provides a dispensing machine device control system based on multiple scenarios, which is used for the above-mentioned dispensing machine device control method based on multiple scenarios, including:

[0065] The scene module is used to obtain scene data, where the scene data includes substrate material information, glue type information, ambient temperature and humidity information, and dispensing trajectory complexity information, and obtain the corresponding control parameter set based on the scene data;

[0066] A prediction module is used to obtain dispensing effect data and trajectory deviation data during the dispensing process according to the control parameter set, and obtain predicted dispensing information based on the dispensing effect data and trajectory deviation data;

[0067] A control module is used to extract deviation information that does not meet preset conditions based on the predicted dispensing information, and obtain a control strategy based on the deviation information, wherein the control strategy includes normal, low deviation and high deviation;

[0068] The optimization module is used to obtain equipment health information according to the control strategy, obtain corresponding equipment maintenance instructions according to the equipment health information, obtain corresponding equipment maintenance effects based on the corresponding equipment maintenance instructions, and optimize the control parameter set according to the corresponding equipment maintenance effects.

[0069] And, a dispensing machine control terminal based on multiple scenarios, including:

[0070] one or more processors;

[0071] a storage device having one or more programs stored thereon;

[0072] When one or more programs are executed by one or more processors, the one or more processors implement a dispensing machine device control method based on multiple scenarios.

[0073] The technical effects achieved by the present invention are:

[0074] The present invention can dynamically adjust dispensing parameters through real-time scene perception and predictive processing, significantly reduce trajectory deviation and glue quantity error, improve dispensing consistency and yield rate, and call the optimal parameter set for different substrate materials, glue types and complex trajectories with one click, without the need for multiple manual debugging, significantly shortening trial production and switching time, and integrating equipment health monitoring and maintenance instruction closed-loop, which can not only compensate in time when slight deviations occur, but also warn and perform maintenance before a fault occurs, reducing equipment downtime and extending the service life of key components. The feedback mechanism of maintenance effects and the self-update of parameter sets have "learning" capabilities. With the accumulation of operating data, the control accuracy and response speed continue to improve, adapting to more complex production needs, accurately controlling the glue quantity and process parameters, reducing material waste, predictive maintenance reducing emergency repair costs, and improving process switching and debugging efficiency, further reducing production cycle and labor costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] Figure 1 is a flow chart of the method provided by the present invention;

[0076] Figure 2 This is a system module diagram provided by the present invention. DETAILED DESCRIPTION

[0077] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0078] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0079] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in a preferred embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it constitute a separate or selective embodiment that is mutually exclusive of other embodiments.

[0080] Secondly, the present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention in detail, for the sake of convenience, the schematic diagrams are only examples and should not limit the scope of protection of the present invention.

[0081] Please see the attached Figure 1 As shown, a method for controlling a dispensing machine device based on multiple scenarios is provided, including:

[0082] S1. Acquire scene data, where the scene data includes substrate material information, glue type information, ambient temperature and humidity information, and dispensing trajectory complexity information, and acquire a corresponding control parameter set based on the scene data;

[0083] S2. Obtain dispensing effect data and trajectory deviation data during the dispensing process according to the control parameter set, and obtain predicted dispensing information based on the dispensing effect data and trajectory deviation data;

[0084] S3. Extracting deviation information that does not meet preset conditions based on the predicted dispensing information, and obtaining a control strategy based on the deviation information, wherein the control strategy includes conventional, low deviation, and high deviation;

[0085] S4. Obtain equipment health information according to the control strategy, obtain corresponding equipment maintenance instructions according to the equipment health information, obtain corresponding equipment maintenance effects based on the corresponding equipment maintenance instructions, and optimize the control parameter set according to the corresponding equipment maintenance effects.

[0086] As in the above steps S1 to S4, scene data such as substrate material, glue type, ambient temperature and humidity, and dispensing trajectory complexity are collected in real time through sensors and preset databases. Based on these data, the control parameter set (such as pressing pressure, dispensing speed, heating temperature, etc.) that best matches the current scene is queried and loaded in the parameter library. During the dispensing process, the actual dispensing effect (such as glue dot diameter, glue line width) and trajectory deviation (based on the trajectory offset of vision or encoder feedback) are continuously collected. Using a pre-trained model or empirical formula, these data are used to generate "predicted dispensing information", that is, to predict the deviation trend and quality change that may occur in subsequent dispensing. Deviation information exceeding the preset threshold is extracted from the predicted information, and the degree of deviation is judged, which is divided into three scenarios: "normal", "low deviation" and "high deviation". According to different deviation levels, the corresponding control strategy is dynamically selected. While executing the control strategy, the core components (such as dispensing valves, air sources, drive motors, etc.) are monitored for health to obtain equipment health information. Based on the health status, maintenance instructions (such as cleaning) are automatically generated. Valve, replace seals, calibrate guide rails), and evaluate the maintenance effect after maintenance. Optimize the control parameter set based on the equipment maintenance effect to continuously update and improve the parameter set. Through real-time scene perception and predictive processing, it can dynamically adjust the dispensing parameters, significantly reduce trajectory deviation and glue amount error, improve dispensing consistency and yield rate, and call the optimal parameter set for different substrate materials, glue types and complex trajectories with one click. No manual debugging is required, which significantly shortens the trial production and switching time. The closed-loop integration of equipment health monitoring and maintenance instructions can not only compensate for slight deviations in time, but also warn and perform maintenance before failures occur, reducing equipment downtime and extending the service life of key components. The feedback mechanism of maintenance effect and the self-update of parameter sets have "learning" capabilities. With the accumulation of operating data, the control accuracy and response speed continue to improve, adapting to more complex production needs, accurately controlling glue amount and process parameters, reducing material waste, predictive maintenance reducing emergency repair costs, and improving process switching and debugging efficiency, further reducing production cycle and labor costs.

[0087] In a preferred embodiment, scene data is obtained, wherein the scene data includes substrate material, glue type, ambient temperature and humidity, and dispensing trajectory complexity, and the step of obtaining a corresponding control parameter set based on the scene data includes:

[0088] S101, acquiring scene data, wherein the scene data includes substrate material information, glue type information, ambient temperature and humidity information, and dispensing trajectory complexity information;

[0089] S102, obtaining the corresponding substrate material vector, glue type vector, ambient temperature and humidity value, and glue dispensing trajectory complexity value according to the substrate material information, glue type information, ambient temperature and humidity information, and glue dispensing trajectory complexity information;

[0090] S103, obtaining a scene value according to the substrate material vector, the glue type vector, the ambient temperature and humidity values, and the glue dispensing trajectory complexity value;

[0091] S104, obtaining a parameter table, wherein the parameter table includes multiple scene value intervals and a control parameter set corresponding to each scene value interval;

[0092] S105 . Obtain a corresponding control parameter set from a parameter table according to a scene value interval corresponding to the scene value.

[0093] As in steps S101 to S105 above, four types of basic scene information are acquired in real time through the integrated sensor and database interface, namely, substrate material (such as ceramic, glass, PCB), glue type (such as epoxy, silicone, UV glue), ambient temperature and humidity (current temperature and relative humidity), and dispensing trajectory complexity (quantified based on the number of inflection points or curve length). The four types of original information are standardized or queried and mapped to generate corresponding numerical features: substrate material vector, glue type vector, ambient temperature and humidity value, and trajectory complexity value. The categories and continuous values ​​are uniformly encoded into the same feature space, and the four substrate material vectors, glue type vector, ambient temperature and humidity value, and trajectory complexity value are calculated to obtain a single scalar "scene value" to comprehensively quantify the difficulty and risk of the current dispensing working condition. The calculation formula of the scene value is C=J·S·h g, where C represents the scenario value, J represents the substrate material vector, S represents the glue type vector, h represents the ambient temperature and humidity value, and g represents the dispensing trajectory complexity value. A "parameter table" is preset to divide the possible scenario values ​​into several continuous intervals. A set of experimentally optimized control parameter sets (such as dispensing pressure, injection speed, heating temperature, etc.) is configured for each interval. The calculated scenario value is quickly located according to its corresponding interval, and the corresponding control parameter set is retrieved from the parameter table for direct call and execution by the dispensing robot arm or dispensing valve group. The entire process from data collection to parameter acquisition is simple, and the parameter retrieval time is constant, meeting the needs of fast switching on the production line. When adding a new substrate material or glue type, only the corresponding vector mapping or parameter table entry needs to be supplemented, without changing the core algorithm, making it easy to maintain and upgrade.

[0094] In a preferred embodiment, the steps of obtaining dispensing effect data and trajectory deviation data during the dispensing process according to the control parameter set, and obtaining predicted dispensing information according to the dispensing effect data and trajectory deviation data include:

[0095] S201, obtaining corresponding ambient temperature and humidity values ​​and dispensing trajectory complexity values ​​according to ambient temperature and humidity information and dispensing trajectory complexity information;

[0096] S202, obtaining a dispensing impact value according to the ambient temperature and humidity values ​​and the dispensing trajectory complexity value;

[0097] S203, obtaining a duration table, wherein the duration table includes a plurality of dispensing impact value intervals and a collection duration corresponding to each dispensing impact value interval;

[0098] S204, obtaining the corresponding collection time from the time table according to the dispensing impact value interval corresponding to the dispensing impact value;

[0099] S205, regulating the control parameters of the dispensing machine according to the control parameter set, obtaining the dispensing start time node after the dispensing machine control parameters are regulated; obtaining the end time node based on the collection duration, and obtaining the dispensing collection period according to the start time node and the end time node;

[0100] S206, obtaining dispensing effect data and trajectory deviation data within the dispensing collection period;

[0101] S207, obtaining corresponding dispensing effect values ​​and trajectory deviation values ​​according to the dispensing effect data and the trajectory deviation data;

[0102] S208 , obtaining a dispensing prediction value according to the dispensing effect value and the trajectory deviation value, and marking it as predicted dispensing information.

[0103] As in the above steps S201 to S208, the ambient temperature and humidity values ​​and trajectory complexity values ​​read from the scene data provide an input basis for impact assessment. The ambient temperature and humidity values ​​are multiplied by the dispensing trajectory complexity value, and the product is marked as the dispensing impact value, which represents the real-time interference level of the current environment and trajectory complexity on the dispensing quality and stability. A "duration table" is preset to divide the dispensing impact value into several intervals, each interval corresponding to an optimal data collection duration. According to the interval to which the current dispensing impact value belongs, the corresponding collection duration is dynamically retrieved to ensure that sufficient data can be obtained under different interferences without excessively extending the sampling time. According to the control parameter set, the dispensing action is started, the start time node is recorded, and the end time node is calculated in combination with the collection duration. The two define the collection period of this dispensing. During the collection period, the visual system, flow / pressure sensor and encoder are used in parallel Collection: Dispensing effect data (such as glue dot diameter, glue line width, surface uniformity), trajectory deviation data (real-time position offset, hysteresis, etc.), filtering, denoising and feature extraction of the original signal, respectively, to obtain the dispensing effect value and trajectory deviation value, and calculate the dispensing prediction value based on the dispensing effect value and trajectory deviation value, and mark it as predicted dispensing information to provide a decision-making basis for control strategy adjustment. The calculation formula of the dispensing prediction value is Y=X·G, where Y represents the dispensing prediction value, X represents the dispensing effect value, and G represents the trajectory deviation value. The collection time is dynamically adjusted with the environment and trajectory complexity, which not only ensures data integrity but also improves sampling efficiency. The prediction information is quickly generated, and potential deviation trends can be discovered in time during the dispensing process, leaving sufficient response time for the downstream control strategy. The strategy adjustment is triggered only when the prediction value indicates that it may deviate from the preset target, reducing interference with normal working conditions.

[0104] In a preferred embodiment, deviation information that does not meet the preset conditions is extracted based on the predicted dispensing information, and a control strategy is obtained according to the deviation information, wherein the control strategy includes conventional, low deviation and high deviation steps, including:

[0105] S301, obtaining a corresponding predicted dispensing value based on the predicted dispensing information;

[0106] S302, obtaining a predicted dispensing threshold, and determining whether the predicted dispensing value is lower than the predicted dispensing threshold;

[0107] If the predicted dispensing value is lower than the predicted dispensing threshold, it is determined to be dispensing abnormality;

[0108] If the predicted dispensing value is not lower than the predicted dispensing threshold, it is determined that the dispensing is normal;

[0109] S303, when it is determined that the dispensing is abnormal, obtaining standard dispensing effect data and standard trajectory data during the dispensing process according to the control parameter set, and obtaining corresponding multiple standard dispensing effect vectors and multiple standard trajectory vectors based on the standard dispensing effect data and the standard trajectory data;

[0110] S304, obtaining corresponding multiple dispensing effect vectors and multiple trajectory deviation vectors according to the dispensing effect data and the trajectory deviation data;

[0111] S305, obtaining a dispensing deviation value according to the predicted dispensing value, the predicted dispensing threshold, multiple standard dispensing effect vectors, multiple standard trajectory vectors, multiple dispensing effect vectors, and multiple trajectory deviation vectors, and marking it as deviation information;

[0112] S306 , obtaining a control strategy according to the dispensing deviation value, wherein the control strategy includes normal, low deviation and high deviation.

[0113] As in the above steps S301 to S306, a single predicted dispensing value is directly read from the generated predicted dispensing information. This value can reflect the future glue amount, glue point shape or deviation trend. A predicted dispensing threshold is preset to judge normal and abnormal. If the predicted dispensing value is less than the threshold, it is judged as "dispensing abnormality". If the predicted dispensing value is greater than or equal to the threshold, it is judged as "dispensing normal". In the case of "dispensing abnormality", the standard dispensing effect data and standard trajectory data corresponding to the current control parameter set are called, and vectorized into multiple standard dispensing effect vectors and standard trajectory vectors respectively. As an ideal reference set, the dispensing effect data and trajectory deviation data collected during this dispensing process are filtered and feature extracted to generate multiple dispensing effect vectors and multiple trajectory deviation vectors as the actual performance set. The dispensing deviation value is obtained based on the predicted dispensing value, the predicted dispensing threshold, multiple standard dispensing effect vectors, multiple standard trajectory vectors, multiple dispensing effect vectors and multiple trajectory deviation vectors. The dispensing deviation value is comprehensively calculated to obtain the dispensing deviation value, and it is marked as deviation information. The calculation formula of the dispensing deviation value is: In the formula, Z represents the dispensing deviation value, Y represents the dispensing prediction value, and Y threshold It represents the dispensing prediction threshold, i represents the number of multiple standard dispensing effect vectors, the number of multiple standard trajectory vectors, the number of multiple dispensing effect vectors and the number of multiple trajectory deviation vectors, where i = 1, 2, 3…m, D i Represented as the i-th dispensing effect vector, d i Expressed as the i-th standard dispensing effect vector, P i Expressed as the i-th trajectory deviation vector, p iIt is represented as the i-th standard trajectory vector. According to the size of the dispensing deviation value and the preset classification rules, it is mapped to one of the three control strategies: conventional strategy, low deviation strategy, and high deviation strategy. The threshold judgment link realizes the real-time identification of dispensing abnormalities and can respond immediately when the deviation is still small. The deviation is divided into three levels: conventional, low deviation, and high deviation. It can not only reduce the disturbance to normal working conditions, but also provide sufficient compensation for major deviations.

[0114] In a preferred embodiment, a control strategy is obtained based on the dispensing deviation value, wherein the control strategy includes the steps of normal, low deviation and high deviation, including:

[0115] Get the strategy range and determine whether the dispensing deviation value is within the strategy range;

[0116] S3061a, if the dispensing deviation value is within the strategy range, the control strategy is determined to be normal;

[0117] S3061b, if the dispensing deviation value is not within the strategy range and is less than the lower limit of the strategy range, the control strategy is determined to be low deviation;

[0118] S3061c: If the dispensing deviation value is not within the strategy range and is greater than the upper limit of the strategy range, the control strategy is determined to be high deviation.

[0119] As mentioned above, regarding the three control strategies of S3061a, S3061b and S3061c, an acceptable deviation range is pre-set, which is called the "strategy range". If the dispensing deviation value calculated in real time is within the strategy range, it is considered that the deviation is within the acceptable range and no excessive intervention is required. The control strategy is set to "normal". If the dispensing deviation value is not within the strategy range and is less than the lower limit of the strategy range, it is determined to be a slight deviation. The control strategy is set to "low deviation". Small parameter fine-tuning or slight compensation is performed. If the dispensing deviation value is not within the strategy range, , and is greater than the upper limit of the strategy interval, it is judged as a serious deviation, and the control strategy is set to "high deviation", which will trigger significant parameter adjustments, path recalibration or pause actions for deep correction. Here, "low deviation" and "high deviation" can be set with different thresholds according to production needs to achieve a more fine-grained response. Through a single strategy interval, the deviation is mapped to three-speed strategies, which can not only make slight compensation for small fluctuations but also take strong corrections for major deviations, so as to "prescribe the right medicine for the disease" and complete the strategy selection. The computational complexity is low and meets the real-time requirements.

[0120] In the first embodiment, the control strategy is conventional. The steps of obtaining device health information according to the control strategy, obtaining corresponding device maintenance instructions according to the device health information, obtaining corresponding device maintenance effects based on the corresponding device maintenance instructions, and optimizing the control parameter set according to the corresponding device maintenance effects include:

[0121] S40a1. When the control strategy is conventional, obtain corresponding dispensing effect values ​​and trajectory deviation values ​​according to the dispensing effect data and trajectory deviation data, and obtain corresponding ambient temperature and humidity weights and dispensing trajectory complexity weights based on ambient temperature and humidity information and dispensing trajectory complexity information;

[0122] S40a2. Obtain the device health value based on the dispensing effect value, the trajectory deviation value, the ambient temperature and humidity weight, and the dispensing trajectory complexity weight, and mark it as device health information;

[0123] S40a3. Obtain a maintenance instruction table, wherein the maintenance instruction table includes multiple device health value intervals and device maintenance instructions corresponding to each device health value interval;

[0124] S40a4, obtaining a corresponding device maintenance instruction from the maintenance instruction table according to the device health value interval corresponding to the device health value;

[0125] S40a5. Obtain a corresponding equipment maintenance effect based on the corresponding equipment maintenance instruction, and optimize the control parameter set according to the corresponding equipment maintenance effect.

[0126] As in the above steps S40a1 to S40a5, the dispensing effect value and the trajectory deviation value are extracted respectively from the dispensing effect data and the trajectory deviation data obtained in the dispensing process. At the same time, based on the current ambient temperature and humidity information and the dispensing trajectory complexity information, the corresponding ambient temperature and humidity weight and the trajectory complexity weight are extracted through mapping or model for subsequent weighting. The device health value is calculated according to the dispensing effect value, the trajectory deviation value and the two weights, and is marked as device health information. The calculation formula of the device health value is K=X·G·α·β, where K represents the device health value, X represents the dispensing effect value, G represents the trajectory deviation value, α represents the ambient temperature and humidity weight, and β represents the dispensing trajectory complexity weight. A maintenance instruction table is preset to divide the possible device health values ​​into several intervals, and each interval corresponds to one or more device maintenance instructions. Commands (such as cleaning valves, calibrating guide rails, replacing sealing rings, etc.) are located according to the calculated equipment health value, and the corresponding equipment maintenance instructions are retrieved from the maintenance instruction table. The equipment is maintained accordingly according to the retrieved maintenance instructions. After the maintenance is completed, the equipment maintenance effect is evaluated (such as improved valve patency and restored air pressure stability), and the effect is fed back to the control parameter set for optimization. The existing parameter set is fine-tuned or retrained to improve the subsequent dispensing quality and equipment stability. Through regular health value evaluation and interval mapping, it is possible to detect and perform maintenance in the early stage of equipment performance degradation, reduce the risk of sudden failures, and combine process indicators (effect value, deviation value) with environment / complexity weights. The health value more comprehensively reflects the true status of the equipment, and the maintenance effect directly drives the optimization of the parameter set to ensure that the system performance quickly returns and continuously improves after maintenance.

[0127] The second embodiment differs from the first embodiment in that the control strategy is conventional low deviation. The steps of obtaining device health information according to the control strategy, obtaining corresponding device maintenance instructions according to the device health information, obtaining corresponding device maintenance effects based on the corresponding device maintenance instructions, and optimizing the control parameter set according to the corresponding device maintenance effects include:

[0128] S40b1. When the control strategy is low deviation, obtain a corresponding low data acquisition frequency based on the low deviation control strategy, obtain multiple dispensing effect stage values ​​and multiple trajectory deviation stage values ​​during the dispensing process according to the low data acquisition frequency, and obtain corresponding ambient temperature and humidity weights and dispensing trajectory complexity weights based on the ambient temperature and humidity information and the dispensing trajectory complexity information;

[0129] S40b2, obtaining a low dispensing effect stage threshold and a low trajectory deviation stage threshold;

[0130] S40b3, obtaining dispensing effect stage values ​​that are less than the low dispensing effect stage threshold, and summarizing them into a low dispensing effect stage value set;

[0131] S40b4, obtaining trajectory deviation stage values ​​that are less than the low trajectory deviation stage threshold, and summarizing them into a low trajectory deviation stage value set;

[0132] S40b5. Obtain a low device health value based on the low dispensing effect stage value set, the low trajectory deviation stage value set, the ambient temperature and humidity weight, and the dispensing trajectory complexity weight, and mark it as device health information;

[0133] S40b6. Obtain a low maintenance instruction table, wherein the low maintenance instruction table includes multiple low device health value intervals and device maintenance instructions corresponding to each low device health value interval;

[0134] S40b7, obtaining a corresponding device maintenance instruction from the low maintenance instruction table according to the low device health value interval corresponding to the low device health value;

[0135] S40b8. Obtain a corresponding equipment maintenance effect based on the corresponding equipment maintenance instruction, and optimize the control parameter set according to the corresponding equipment maintenance effect.

[0136] As in the above steps S40b1 to S40b8, when the control strategy is "low deviation", switch to low data acquisition frequency, collect data at low acquisition frequency time intervals during the dispensing process, multiple dispensing effect stage values ​​(reflecting the amount and shape of glue in each stage), multiple trajectory deviation stage values ​​(reflecting the trajectory offset in each stage), and at the same time, map the ambient temperature and humidity weights and the trajectory complexity weights based on the current ambient temperature and humidity information and the dispensing trajectory complexity information, pre-set the low dispensing effect stage threshold and the low trajectory deviation stage threshold as the boundary for determining slight abnormalities, usually corresponding to Within an acceptable small range of fluctuations, from the collected stage values, the dispensing effect stage values ​​that are less than the low dispensing effect stage threshold are screened out, and the low dispensing effect stage value set is aggregated to characterize the stage of slight quality degradation. Similarly, from multiple trajectory deviation stage values, the trajectory deviation stage values ​​that are less than the low trajectory deviation stage threshold are screened out, and the low trajectory deviation stage value set is aggregated to reflect the period of slight trajectory deviation. The scalar low device health value is calculated and output based on the two types of stage value sets and the environment and complexity weights, which is marked as the device health information of this step. The calculation formula of the low device health value is: Where K low It represents the low equipment health value, d represents the number of multiple low dispensing effect stage values ​​in the low dispensing effect stage value set, where d = 1, 2, 3...t, (X low ) d It is expressed as the dispensing effect value, q is expressed as the number of multiple low trajectory deviation stage values ​​in the low trajectory deviation stage value set, where q = 1, 2, 3...p, (G low ) q It is expressed as the trajectory deviation value, α is expressed as the ambient temperature and humidity weight, β is expressed as the dispensing trajectory complexity weight, and a low maintenance instruction table is preset to divide low equipment health values ​​in different ranges into intervals. Each interval corresponds to a light maintenance instruction (such as fine-tuning pressure, simple cleaning or parameter review). According to the low equipment health value calculated in real time, the interval to which it belongs is located, and the corresponding equipment maintenance instruction is retrieved from the table. The equipment is lightly maintained according to the retrieved instruction. After maintenance, the equipment maintenance effect is evaluated (such as further reduction of deviation, slight improvement of surface quality), and the results are fed back to the control parameter set for optimization. The current parameter set is fine-tuned to improve the stability and consistency of the subsequent dispensing process. The low acquisition frequency and small range threshold design avoid excessive intervention in normal working conditions, and the maintenance actions are more streamlined and efficient. Low-intensity maintenance is performed only when slight deviations occur, reducing unnecessary downtime and material waste, and reducing maintenance costs and energy consumption.

[0137] The third embodiment differs from the first embodiment in that the control strategy is conventional high deviation. The steps of obtaining device health information according to the control strategy, obtaining corresponding device maintenance instructions according to the device health information, obtaining corresponding device maintenance effects based on the corresponding device maintenance instructions, and optimizing the control parameter set according to the corresponding device maintenance effects include:

[0138] S40c1. When the control strategy is high deviation, a corresponding high data acquisition frequency is obtained based on the high deviation control strategy, multiple dispensing effect stage values ​​and multiple trajectory deviation stage values ​​in the dispensing process are obtained according to the high data acquisition frequency, and corresponding ambient temperature and humidity weights and dispensing trajectory complexity weights are obtained based on the ambient temperature and humidity information and the dispensing trajectory complexity information;

[0139] S40c2, obtaining a high dispensing effect stage value interval and a high trajectory deviation stage value interval;

[0140] S40c3, obtaining the dispensing effect stage values ​​that are not within the high dispensing effect stage value range, and summarizing them into a high dispensing effect stage value set;

[0141] S40c4, obtaining trajectory deviation stage values ​​that are not within the high trajectory deviation stage value interval, and summarizing them into a high trajectory deviation stage value set;

[0142] S40c5. Obtain a high device health value based on the high dispensing effect stage value set, the high trajectory deviation stage value set, the ambient temperature and humidity weight, and the dispensing trajectory complexity weight, and mark it as device health information;

[0143] S40c6. Obtain a high maintenance instruction table, wherein the high maintenance instruction table includes multiple high device health value intervals and device maintenance instructions corresponding to each high device health value interval;

[0144] S40c7. Obtain the corresponding equipment maintenance instruction from the high maintenance instruction table according to the high equipment health value interval corresponding to the high equipment health value;

[0145] S40c8. Obtain a corresponding equipment maintenance effect based on the corresponding equipment maintenance instruction, and optimize the control parameter set according to the corresponding equipment maintenance effect.

[0146] As in the above steps S40c1 to S40c8, after determining that it is a "high deviation" control strategy, switch to a high data acquisition frequency, collect multiple dispensing effect stage values ​​and multiple trajectory deviation stage values ​​in parallel at shorter time intervals during the entire dispensing process, and at the same time, read the current ambient temperature and humidity information and the dispensing trajectory complexity information, and map them to the corresponding ambient temperature and humidity weights and trajectory complexity weights, pre-define the high dispensing effect stage value interval and the high trajectory deviation stage value interval, which respectively represent the lowest acceptable boundaries of the dispensing quality and trajectory deviation of each stage, from acquisition to From the multiple dispensing effect stage values, those values ​​that are not in the high dispensing effect stage value range are screened out, and the values ​​are aggregated into a high dispensing effect stage value set to characterize the specific stage of quality deterioration. Similarly, from the multiple trajectory deviation stage values, the values ​​that are not in the high trajectory deviation stage value range are screened out, and the values ​​are aggregated into a high trajectory deviation stage value set to accurately reflect the trajectory out of control stage. The high device health value is calculated based on the high dispensing effect stage value set, the high trajectory deviation stage value set, the ambient temperature and humidity weights, and the trajectory complexity weights, and marked as device health information. The calculation formula for the high device health value is: Where K tall It represents the high equipment health value, a represents the number of multiple high glue effect stage values ​​in the high glue effect stage value set, where a=1,2,3…n, (X tall ) a It is represented by the dispensing effect value, j is represented by the number of multiple high trajectory deviation stage values ​​in the high trajectory deviation stage value set, where j = 1, 2, 3...f, (G tall ) j It is expressed as the trajectory deviation value, α is expressed as the ambient temperature and humidity weight, β is expressed as the dispensing trajectory complexity weight, and a high maintenance instruction table is preset to divide the high equipment health value into several intervals. Each interval corresponds to a deeper or more urgent equipment maintenance instruction (such as full calibration, key component replacement, deep cleaning, etc.). According to the calculated high equipment health value, the interval to which it belongs is located, and the corresponding equipment maintenance instruction is retrieved from the high maintenance instruction table. According to the retrieved instruction, high-intensity maintenance is performed on the equipment. After completion, the equipment maintenance effect is evaluated (such as a significant decrease in deviation, temperature and pressure return to stability), and the equipment maintenance instruction is stored. The effect is fed back to the control parameter set for optimization, and the parameter set is deeply fine-tuned or retrained to achieve the best control performance for "high deviation" working conditions. High-frequency phased acquisition and multi-threshold screening can accurately locate the specific time period and cause of dispensing quality and trajectory out of control, providing a clear basis for subsequent maintenance. By mapping deeper maintenance instructions through high equipment health value intervals, a graded response from light cleaning to replacement of key components is achieved, which saves costs and ensures results. It can timely discover and deeply process high deviation stages, avoid equipment shutdown or product scrapping caused by serious loss of control, and significantly improve production reliability.

[0147] It should be noted that the steps of obtaining the corresponding equipment maintenance effect based on the corresponding equipment maintenance instruction and optimizing the control parameter set according to the corresponding equipment maintenance effect include: after executing the maintenance instruction, obtaining equipment maintenance effect feedback data (such as the degree of recovery of dispensing accuracy, deviation change trend, etc.), and judging whether the optimization goal is achieved based on the maintenance effect. If it does not meet the standard, the control parameter set is further adjusted, and compared with the preset parameter adjustment table in combination with the non-standard data. The parameter adjustment table includes multiple specific values ​​of non-standard parameters and the adjustment strategy corresponding to each specific value of non-standard parameters. Based on the maintenance effect and deviation response, comprehensive adjustments are made to control variables including but not limited to pressure control parameters, dispensing speed parameters, valve opening time, trajectory fine-tuning parameters, etc. The updated parameter set is used for subsequent dispensing control to achieve closed-loop adaptive optimization.

[0148] Please see the attached Figure 2 As shown, the present invention also provides a dispensing machine device control system based on multiple scenarios, which is used for the above-mentioned dispensing machine device control method based on multiple scenarios, including:

[0149] The scene module is used to obtain scene data, where the scene data includes substrate material information, glue type information, ambient temperature and humidity information, and dispensing trajectory complexity information, and obtain the corresponding control parameter set based on the scene data;

[0150] A prediction module is used to obtain dispensing effect data and trajectory deviation data during the dispensing process according to the control parameter set, and obtain predicted dispensing information based on the dispensing effect data and trajectory deviation data;

[0151] A control module is used to extract deviation information that does not meet preset conditions based on the predicted dispensing information, and obtain a control strategy based on the deviation information, wherein the control strategy includes normal, low deviation and high deviation;

[0152] The optimization module is used to obtain equipment health information according to the control strategy, obtain corresponding equipment maintenance instructions according to the equipment health information, obtain corresponding equipment maintenance effects based on the corresponding equipment maintenance instructions, and optimize the control parameter set according to the corresponding equipment maintenance effects.

[0153] The above-mentioned scenario module collects original information such as substrate material, glue type, ambient temperature and humidity, and dispensing trajectory complexity through sensors and database interfaces, standardizes and encodes each type of information, calculates a single scenario value, and quickly retrieves and loads the optimal control parameter set according to the interval to which the scenario value belongs in the preset parameter table. The prediction module calculates the dispensing impact value based on the ambient temperature and humidity and trajectory complexity and adaptively determines the data collection time. After the dispensing action is started, the effect data (glue point size, uniformity) and trajectory deviation are collected at the set frequency (conventional / low frequency / high frequency). Data, filter and extract features of the original signal to obtain the dispensing effect value and trajectory deviation value, and extract the "predicted dispensing value", that is, predict the dispensing quality and deviation trend. The control module extracts the predicted dispensing value from the prediction information and compares it with the preset threshold to determine "normal" or "abnormal". If abnormal, load the standard effect and trajectory vector that matches the current parameter set, compare it with the actual vector, calculate the comprehensive deviation value, and select the "conventional", "low deviation" or "high deviation" strategy according to the deviation value and strategy interval mapping. The optimization module uses the low resource overhead model under the conventional strategy. The system calculates equipment health values ​​using a formula, performs light maintenance, and fine-tunes parameters based on the maintenance instruction table. Under a low-deviation strategy, it collects medium-frequency data, filters value sets for minor anomalies, calculates low-level equipment health values, performs medium-intensity maintenance, and updates parameters. Under a high-deviation strategy, it enables high-frequency data collection, locates value sets for major anomalies, calculates high-level equipment health values, performs deep maintenance (such as component replacement and deep cleaning), and retrains or recalibrates the parameter set. From material, glue, environment, complexity, to performance, deviation, and ultimately equipment health, it implements layer-by-layer quantification and modeling to achieve refined management. The closed-loop integration of equipment health monitoring and maintenance instructions not only enables timely compensation for minor deviations but also provides early warning and maintenance execution before failures occur, reducing equipment downtime and extending the service life of critical components. The feedback mechanism for maintenance effectiveness and the self-updating of parameter sets demonstrate "learning" capabilities. As operational data accumulates, control accuracy and response speed continue to improve, adapting to more complex production needs. It precisely controls glue volume and process parameters, reducing material waste. Predictive maintenance reduces emergency repair costs, and improved process switching and debugging efficiency further reduce production cycle times and labor costs.

[0154] And, a dispensing machine control terminal based on multiple scenarios, including:

[0155] one or more processors;

[0156] a storage device having one or more programs stored thereon;

[0157] When one or more programs are executed by one or more processors, the one or more processors implement a dispensing machine device control method based on multiple scenarios.

[0158] The foregoing is merely a preferred embodiment of the present invention. It should be noted that those skilled in the art may make various improvements and modifications without departing from the principles of the present invention, and such improvements and modifications are also within the scope of protection of the present invention. Structures, devices, and operating methods not specifically described or explained herein shall, unless otherwise specified or limited, be implemented in accordance with conventional means in the art.

Claims

1. A method for controlling a dispensing machine based on multiple scenarios, characterized in that: include: Acquire scene data, where the scene data includes substrate material information, glue type information, ambient temperature and humidity information, and dispensing trajectory complexity information, and acquire a corresponding control parameter set based on the scene data; Obtain dispensing effect data and trajectory deviation data during the dispensing process according to the control parameter set, and obtain predicted dispensing information based on the dispensing effect data and trajectory deviation data; Extracting deviation information that does not meet preset conditions based on the predicted dispensing information, and obtaining a control strategy based on the deviation information, wherein the control strategy includes conventional, low deviation and high deviation; Obtain equipment health information according to the control strategy, obtain corresponding equipment maintenance instructions according to the equipment health information, obtain corresponding equipment maintenance effects based on the corresponding equipment maintenance instructions, and optimize the control parameter set according to the corresponding equipment maintenance effects.

2. The multi-scenario dispensing machine control method according to claim 1 is characterized in that: Acquiring scene data, where the scene data includes substrate material, glue type, ambient temperature and humidity, and dispensing trajectory complexity, and the steps of acquiring a corresponding control parameter set based on the scene data include: Acquire scene data, where the scene data includes substrate material information, glue type information, ambient temperature and humidity information, and dispensing trajectory complexity information; According to the substrate material information, glue type information, ambient temperature and humidity information and glue dispensing trajectory complexity information, the corresponding substrate material vector, glue type vector, ambient temperature and humidity value and glue dispensing trajectory complexity value are obtained respectively; Obtain the scene value based on the substrate material vector, glue type vector, ambient temperature and humidity values, and glue dispensing trajectory complexity value; Obtaining a parameter table, wherein the parameter table includes multiple scene value intervals and a control parameter set corresponding to each scene value interval; Obtain the corresponding control parameter set from the parameter table according to the scene value interval corresponding to the scene value.

3. The multi-scenario dispensing machine control method according to claim 1 is characterized in that: The steps of obtaining dispensing effect data and trajectory deviation data during the dispensing process according to the control parameter set, and obtaining predicted dispensing information according to the dispensing effect data and the trajectory deviation data include: Obtain corresponding ambient temperature and humidity values ​​and dispensing trajectory complexity values ​​according to ambient temperature and humidity information and dispensing trajectory complexity information; Obtain the dispensing impact value based on the ambient temperature and humidity values ​​and the dispensing trajectory complexity value; Obtaining a duration table, wherein the duration table includes multiple dispensing impact value intervals and a collection duration corresponding to each dispensing impact value interval; Obtain the corresponding collection duration from the duration table according to the dispensing impact value interval corresponding to the dispensing impact value; According to the control parameter set, the control parameters of the dispensing machine device are adjusted, and the dispensing start time node after the dispensing machine device control parameters are adjusted is obtained; the end time node is obtained based on the collection duration, and the dispensing collection period is obtained according to the start time node and the end time node; Obtain dispensing effect data and trajectory deviation data during the dispensing collection period; Obtain corresponding dispensing effect values ​​and trajectory deviation values ​​according to the dispensing effect data and trajectory deviation data; The dispensing prediction value is obtained according to the dispensing effect value and the trajectory deviation value, and marked as the predicted dispensing information.

4. The method for controlling a dispensing machine based on multiple scenarios according to claim 1, characterized in that: Deviation information that does not meet preset conditions is extracted based on the predicted dispensing information, and a control strategy is obtained according to the deviation information, wherein the control strategy includes conventional, low deviation and high deviation steps, including: Obtaining a corresponding predicted dispensing value based on the predicted dispensing information; Obtain the predicted dispensing threshold, and determine whether the predicted dispensing value is lower than the predicted dispensing threshold; If the predicted dispensing value is lower than the predicted dispensing threshold, it is determined to be dispensing abnormality; If the predicted dispensing value is not lower than the predicted dispensing threshold, it is determined that the dispensing is normal; When it is determined that the dispensing is abnormal, standard dispensing effect data and standard trajectory data in the dispensing process are obtained according to the control parameter set, and corresponding multiple standard dispensing effect vectors and multiple standard trajectory vectors are obtained based on the standard dispensing effect data and the standard trajectory data; Acquire corresponding multiple dispensing effect vectors and multiple trajectory deviation vectors according to the dispensing effect data and the trajectory deviation data; Obtaining a dispensing deviation value according to a predicted dispensing value, a predicted dispensing threshold, multiple standard dispensing effect vectors, multiple standard trajectory vectors, multiple dispensing effect vectors, and multiple trajectory deviation vectors, and marking the value as deviation information; A control strategy is obtained according to the dispensing deviation value, wherein the control strategy includes normal, low deviation and high deviation.

5. The method for controlling a dispensing machine based on multiple scenarios according to claim 4 is characterized in that: A control strategy is obtained based on the dispensing deviation value, wherein the control strategy includes steps of normal, low deviation, and high deviation, including: Get the strategy range and determine whether the dispensing deviation value is within the strategy range; If the dispensing deviation value is within the strategy range, the control strategy is determined to be conventional; If the dispensing deviation value is not within the strategy range and is less than the lower limit of the strategy range, the control strategy is judged to be low deviation; If the dispensing deviation value is not within the strategy range and is greater than the upper limit of the strategy range, the control strategy is determined to be high deviation.

6. The multi-scenario dispensing machine control method according to claim 5 is characterized in that: The steps of obtaining equipment health information according to a control strategy, obtaining corresponding equipment maintenance instructions according to the equipment health information, obtaining corresponding equipment maintenance effects based on the corresponding equipment maintenance instructions, and optimizing a control parameter set according to the corresponding equipment maintenance effects include: When the control strategy is conventional, the corresponding dispensing effect value and trajectory deviation value are obtained according to the dispensing effect data and trajectory deviation data, and the corresponding ambient temperature and humidity weight and dispensing trajectory complexity weight are obtained based on the ambient temperature and humidity information and the dispensing trajectory complexity information; The device health value is obtained based on the dispensing effect value, trajectory deviation value, ambient temperature and humidity weight, and dispensing trajectory complexity weight, and marked as device health information; Obtaining a maintenance instruction table, wherein the maintenance instruction table includes multiple device health value intervals and device maintenance instructions corresponding to each device health value interval; Obtain corresponding equipment maintenance instructions from the maintenance instruction table according to the equipment health value interval corresponding to the equipment health value; A corresponding equipment maintenance effect is obtained based on the corresponding equipment maintenance instruction, and a control parameter set is optimized according to the corresponding equipment maintenance effect.

7. The multi-scenario dispensing machine control method according to claim 5 is characterized in that: The steps of obtaining equipment health information according to a control strategy, obtaining corresponding equipment maintenance instructions according to the equipment health information, obtaining corresponding equipment maintenance effects based on the corresponding equipment maintenance instructions, and optimizing a control parameter set according to the corresponding equipment maintenance effects include: When the control strategy is low deviation, the corresponding low data acquisition frequency is obtained based on the control strategy being low deviation, and multiple dispensing effect stage values ​​and multiple trajectory deviation stage values ​​are obtained according to the low data acquisition frequency during the dispensing process, and the corresponding ambient temperature and humidity weights and dispensing trajectory complexity weights are obtained based on the ambient temperature and humidity information and the dispensing trajectory complexity information; Obtain the low dispensing effect stage threshold and the low trajectory deviation stage threshold; Obtaining dispensing effect stage values ​​that are less than a low dispensing effect stage threshold and summarizing them into a low dispensing effect stage value set; Obtain trajectory deviation stage values ​​that are less than a low trajectory deviation stage threshold and summarize them into a low trajectory deviation stage value set; Obtain a low device health value based on the low dispensing effect stage value set, the low trajectory deviation stage value set, the ambient temperature and humidity weight, and the dispensing trajectory complexity weight, and mark it as device health information; Obtaining a low maintenance instruction table, wherein the low maintenance instruction table includes multiple low device health value intervals and device maintenance instructions corresponding to each low device health value interval; Obtain corresponding equipment maintenance instructions from the low maintenance instruction table according to the low equipment health value interval corresponding to the low equipment health value; A corresponding equipment maintenance effect is obtained based on the corresponding equipment maintenance instruction, and a control parameter set is optimized according to the corresponding equipment maintenance effect.

8. The multi-scenario dispensing machine control method according to claim 5, characterized in that: The steps of obtaining equipment health information according to a control strategy, obtaining corresponding equipment maintenance instructions according to the equipment health information, obtaining corresponding equipment maintenance effects based on the corresponding equipment maintenance instructions, and optimizing a control parameter set according to the corresponding equipment maintenance effects include: When the control strategy is high deviation, the corresponding high data acquisition frequency is obtained based on the control strategy being high deviation, and multiple dispensing effect stage values ​​and multiple trajectory deviation stage values ​​in the dispensing process are obtained according to the high data acquisition frequency, and the corresponding ambient temperature and humidity weights and dispensing trajectory complexity weights are obtained based on the ambient temperature and humidity information and the dispensing trajectory complexity information; Obtain the high dispensing effect stage value interval and the high trajectory deviation stage value interval; Obtaining the dispensing effect stage values ​​that are not within the high dispensing effect stage value range and summarizing them into a high dispensing effect stage value set; Obtain trajectory deviation stage values ​​that are not within the high trajectory deviation stage value interval and summarize them into a high trajectory deviation stage value set; Obtain high device health values ​​based on the high dispensing effect stage value set, high trajectory deviation stage value set, ambient temperature and humidity weights, and dispensing trajectory complexity weights, and mark them as device health information; Obtaining a high maintenance instruction table, wherein the high maintenance instruction table includes multiple high equipment health value intervals and equipment maintenance instructions corresponding to each high equipment health value interval; Obtain corresponding equipment maintenance instructions from the high maintenance instruction table according to the high equipment health value interval corresponding to the high equipment health value; A corresponding equipment maintenance effect is obtained based on the corresponding equipment maintenance instruction, and a control parameter set is optimized according to the corresponding equipment maintenance effect.

9. A multi-scenario dispensing machine control system, applied to the multi-scenario dispensing machine control method according to any one of claims 1 to 8, characterized in that: include: The scene module is used to obtain scene data, where the scene data includes substrate material information, glue type information, ambient temperature and humidity information, and dispensing trajectory complexity information, and obtain the corresponding control parameter set based on the scene data; A prediction module is used to obtain dispensing effect data and trajectory deviation data during the dispensing process according to the control parameter set, and obtain predicted dispensing information based on the dispensing effect data and trajectory deviation data; A control module is used to extract deviation information that does not meet preset conditions based on the predicted dispensing information, and obtain a control strategy based on the deviation information, wherein the control strategy includes normal, low deviation and high deviation; The optimization module is used to obtain equipment health information according to the control strategy, obtain corresponding equipment maintenance instructions according to the equipment health information, obtain corresponding equipment maintenance effects based on the corresponding equipment maintenance instructions, and optimize the control parameter set according to the corresponding equipment maintenance effects.

10. A dispensing machine control terminal based on multiple scenarios, characterized in that: include: one or more processors; a storage device having one or more programs stored thereon; When one or more programs are executed by one or more processors, the one or more processors implement the multi-scenario dispensing machine control method described in any one of claims 1 to 8.

Images