Display process material characteristic analysis system and method

Abstract

The invention relates to the technical field of display process materials, in particular to a display process material characteristic analysis system and method. Comprising a central control unit used for setting a plurality of monitoring points according to the technological process of a display material; the monitoring unit comprises a plurality of monitoring sub-modules, and the monitoring sub-modules are used for collecting characteristic data packets of all monitoring points; the monitoring sub-module is also used for collecting auxiliary data packets of each monitoring point; the analysis unit is used for constructing a characteristic analysis model of the preprocessing model; a plurality of monitoring points are set according to the technological process of a display material, abnormal analysis is carried out on abnormal characteristic data in time by constructing an early warning sub-module corresponding to each monitoring point, and when it is judged that the characteristic data of a single monitoring point is abnormal, a corresponding abnormal data packet is generated by collecting corresponding technology monitoring data; and according to the material analysis model, process parameters causing characteristic index fluctuation are analyzed in time, a process optimization strategy is output, and the production quality and the production efficiency of the display material are improved.

Description

Technical Field

[0001] The present application relates to the technical field of display process materials, and in particular to a display process material characteristic analysis system and method. Background Art

[0002] With the development of advanced technologies such as OLED, Micro-LED, and quantum dot displays, display devices are placing increasingly stringent demands on the properties of functional materials (such as transparent electrodes, light-emitting layers, and encapsulation layers). These various characteristic parameters directly determine the brightness uniformity, color gamut, and lifespan reliability of display panels. Accurately analyzing and controlling material properties has become a core bottleneck in display manufacturing.

[0003] The current industry relies on discrete analytical equipment, unable to capture process dynamics in real time. Composition, structure, and electrical data are stored independently, lacking multi-parameter correlation analysis. This focus is limited to easily measurable parameters like film thickness and resistance, while ignoring real-time feedback from microstructure (grain boundaries, defects). Summary of the Invention

[0004] The purpose of this application is: to solve the above technical problems, this application provides a display process material characteristics analysis system and method, aiming to improve the production quality and production efficiency of display materials.

[0005] In some embodiments of the present application, multiple monitoring points are set according to the process flow of the display material, and abnormal characteristic data are timely analyzed by constructing an early warning sub-module corresponding to each monitoring point. When it is determined that the characteristic data of a single monitoring point is abnormal, the corresponding abnormal data packet is generated by collecting the corresponding process monitoring data, and the abnormal characteristic data in the process flow of the display material is timely analyzed.

[0006] In some embodiments of the present application, real-time abnormal data and offline data are mapped to the same process coordinate system through a preprocessing model, and the process parameters that cause fluctuations in characteristic indicators are analyzed in a timely manner according to the material analysis model, and a process optimization strategy is output to dynamically adjust equipment parameters and improve the production quality and production efficiency of display materials.

[0007] In some embodiments of the present application, a system for analyzing process material characteristics is provided, comprising: The central control unit is used to set multiple monitoring points according to the process flow of the display material; A monitoring unit, comprising a plurality of monitoring submodules, wherein the monitoring submodules are used to collect characteristic data packets of each monitoring point; The monitoring submodule is also used to collect auxiliary data packets from each monitoring point; An analysis unit, used for constructing a characteristic analysis model of the preprocessing model; The central control unit includes: The first processing module is used to establish a monitoring point sequence A, A=(a1, a2…a i …a n ), where a i is the i-th monitoring point; n is the number of monitoring points; The first processing module is further configured to set a monitoring sub-strategy for each monitoring point.

[0008] In some embodiments of the present application, the central control unit further includes: The second processing module is used to establish an early warning sub-model for each monitoring point; The second processing module is further configured to set a monitoring sub-strategy for each monitoring point based on all early warning sub-models; The third processing module is used to generate analysis results.

[0009] In some embodiments of the present application, the second processing module is further configured to: According to the number of monitoring points A, set a i is the target monitoring point; Obtain the process sub-process of the target monitoring point; Set multiple characteristic indicators of target monitoring points according to process sub-process; Construct an early warning sub-model for the target monitoring point based on all characteristic indicators; Set the early warning sub-model of each equipment point in turn; Establish the early warning sub-model series P, P=(p1, p2…p i …p n ), where p i is the early warning sub-model of the i-th monitoring point; n is the number of monitoring points.

[0010] In some embodiments of the present application, the setting of monitoring sub-strategies for each monitoring point includes: Obtain characteristic data packets of target monitoring points according to preset monitoring time nodes; Generate an abnormal risk value b of the target monitoring point based on the feature data packet; b= β i *(s i -s' i ) 2 ]; Among them, θ1 is the number of characteristic indicators of the target monitoring point; β i is the influencing factor of the i-th characteristic index of the target monitoring point; s i Generate the reference value of the i-th characteristic index for the characteristic data packet based on the target monitoring point; s' i is the standard reference value of the i-th characteristic index of the target monitoring point; Preset abnormal risk value threshold B1; If b < B1, the target monitoring point generates a first-level monitoring instruction, and obtains the characteristic data packet of the next monitoring time node according to the first-level monitoring instruction; If b > B1, generate a second-level monitoring instruction for the target monitoring point; The second-level monitoring instruction includes: Obtain the auxiliary data packet of the target monitoring point; Generate an abnormal data packet according to the auxiliary data packet and the characteristic data packet of the target monitoring point; Send the abnormal data packet to the third processing module.

[0011] In some embodiments of the present application, the analysis unit includes: The first analysis module is used to construct an anchored time axis according to the process flow of the display material; The first analysis module is also used to construct a preprocessing model according to the anchored time axis; The second analysis module is used to construct multiple production time intervals according to the anchored time axis; Establish a production time interval sequence W, W=(w1, w2…w i …w m ), where w i is the i-th production time interval; m is the number of production time intervals; The second processing module is also used to construct an analysis sub-model for each production time interval; Establish an analysis sub-model sequence D, D=(d1, d2…d i …d m ), where d i is the analysis sub-model of the i-th production time interval; Construct a characteristic analysis model according to the analysis sub-model sequence D.

[0012] In some embodiments of the present application, when constructing the analysis sub-model for each production time interval, it includes: Set w i as the target time interval in turn according to the production time interval sequence W; [[ID= forty-eight]] Obtain the process index parameters of the target time interval; Obtain the characteristic index parameters of the target time interval; Establish a perturbation map between the process characteristic parameters and the characteristic index parameters; Construct an analysis sub-model for the target time interval according to the perturbation map.

[0013] In some embodiments of the present application, the third processing module is also used for: Receive the abnormal data packet; Determine the production time interval of the abnormal data packet based on the preprocessing result of the abnormal data packet by the preprocessing model; Select the target sub-model according to the judgment result; The target sub-model generates analysis results of abnormal data packets.

[0014] In some embodiments of the present application, when the target sub-model generates analysis results of abnormal data packets, it includes: Generate multiple characteristic indices to be evaluated and multiple process indices to be evaluated according to the target sub-model; Establish the characteristic index series F to be evaluated, F=(f1, f2…f i …f θ ), where f i is the i-th characteristic index to be evaluated in the target sub-model; θ is the number of characteristic indexes to be evaluated in the target sub-model; Generate abnormal values ​​of each characteristic index to be evaluated in turn; Establish a sequence T of process indicators to be evaluated, T=(t1, t2…t i …t r ), where t i is the i-th process indicator to be evaluated in the target sub-model; r is the number of evaluation process indicators in the target sub-model; Generate interference risk values ​​for each process indicator to be evaluated; Generate analysis results of abnormal data packets based on all interference risk values.

[0015] In some embodiments of the present application, the interference risk value of each process indicator to be evaluated includes: According to the process index sequence T to be evaluated, set t i is the target process indicator; Generate the interference risk value h of the target process indicator; h=e1*Q1*[ η i *j i ]+e2*Q2*[ g 1i *k i ]; Wherein, e1 is the preset first weight coefficient; e2 is the preset second weight coefficient; Q1 is the preset first fixed coefficient; Q2 is the preset second fixed coefficient; λ1 is the number of risk assessment indicators; η i is the influencing factor of the i-th disturbance risk index; j i is the reference value of the i-th disturbance risk index in the target process index; θ2 is the number of associated characteristic indicators of the target process index generated based on the target sub-model; g 1i is the weighting factor of the i-th associated characteristic index of the target process index; ki is the abnormal value of the i-th associated characteristic index of the target process index.

[0016] In some embodiments of the present application, a method for analyzing characteristics of display process materials is provided, comprising: Set multiple monitoring points according to the process flow of display materials and build early warning sub-models for each monitoring point; Set monitoring sub-strategies for each monitoring point based on all early warning sub-models, and obtain abnormal data packets based on the monitoring sub-strategies; Generate analysis results of abnormal data packets based on the preprocessing model and feature analysis model; Among them, when constructing the early warning sub-model of each monitoring point, it includes: Establish a monitoring point sequence A, A=(a1, a2…a i …a n ), where a i is the i-th monitoring point; n is the number of monitoring points; According to the number of monitoring points A, set a i is the target monitoring point; Obtain the process sub-process of the target monitoring point; Set multiple characteristic indicators of target monitoring points according to process sub-process; Construct an early warning sub-model for the target monitoring point based on all characteristic indicators; Set the early warning sub-model of each equipment point in turn; Establish the early warning sub-model series P, P=(p1, p2…p i …p n ), where p i is the early warning sub-model of the i-th monitoring point; n is the number of monitoring points; The abnormal data packet includes: Feature data package and ancillary data package.

[0017] Compared with the prior art, the system and method for analyzing process material characteristics according to the embodiment of the present application have the following advantages: According to the process flow of display materials, multiple monitoring points are set, and by constructing early warning sub-modules corresponding to each monitoring point, abnormal characteristic data are timely analyzed. When it is judged that the characteristic data of a single monitoring point is abnormal, the corresponding process monitoring data is collected to generate the corresponding abnormal data packet, and the abnormal characteristic data in the process flow of display materials is timely analyzed.

[0018] Through the preprocessing model, real-time abnormal data and offline data are mapped to the same process coordinate system. According to the material analysis model, the process parameters that cause fluctuations in characteristic indicators are analyzed in a timely manner, and the process optimization strategy is output to dynamically adjust the equipment parameters and improve the production quality and efficiency of display materials. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 It is a structural diagram of a display process material characteristic analysis system in a preferred embodiment of the present application. DETAILED DESCRIPTION

[0020] The following embodiments are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0021] In the description of this application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating the orientation or position relationship, are based on the orientation or position relationship shown in the accompanying drawings, and are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on this application.

[0022] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature specified as "first" or "second" may explicitly or implicitly include one or more of such features. Throughout this application, unless otherwise specified, "plurality" means two or more.

[0023] In the description of this application, it should be noted that, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they can refer to fixed connections, detachable connections, or integral connections; mechanical connections or electrical connections; direct connections or indirect connections through an intermediate medium; and internal connections between two components. Those skilled in the art will understand the specific meanings of the above terms in this application based on the specific circumstances.

[0024] like Figure 1 As shown, a display process material characteristic analysis system according to a preferred embodiment of the present application includes: The central control unit is used to set multiple monitoring points according to the process flow of the display material; The monitoring unit includes multiple monitoring submodules, each of which is used to collect characteristic data packets of each monitoring point; The monitoring submodule is also used to collect auxiliary data packets from each monitoring point; An analysis unit, used for constructing a characteristic analysis model of the preprocessing model; The central control unit includes: The first processing module is used to establish a monitoring point sequence A, A=(a1, a2…a i …a n ), where a i is the i-th monitoring point; n is the number of monitoring points; The first processing module is also used to set the monitoring sub-strategy for each monitoring point; The second processing module is used to establish an early warning sub-model for each monitoring point; The second processing module is also used to set the monitoring sub-strategy of each monitoring point according to all the early warning sub-models; The third processing module is used to generate analysis results.

[0025] Specifically, a plurality of different monitoring points are set according to the process flow of the display material, and the process flow includes but is not limited to the coating process, the etching process, the annealing process, etc. According to the process position of each monitoring point, the equipment type of the corresponding monitoring sub-module is set, and the equipment type is not limited to setting a micro-spectral ellipsometer in the coating chamber and a laser interferometer surface topography instrument at the etching equipment, etc., to collect the corresponding characteristic index parameters.

[0026] Specifically, the characteristic index parameters include but are not limited to film thickness, refractive index, real-time resistance, roughness, film resistivity, square resistance, carrier concentration, mobility and other characteristic parameters that can reflect the performance of display materials.

[0027] Specifically, the auxiliary data package includes process index parameters related to the characteristic index parameters monitored at the current monitoring point, and the process index parameters include but are not limited to annealing temperature, electrical performance parameters, sputtering power, substrate temperature and other production equipment parameters related to display materials.

[0028] In a preferred embodiment of the present application, the second processing module is further configured to: According to the number of monitoring points A, set a i is the target monitoring point; Obtain the process sub-process of the target monitoring point; Set multiple characteristic indicators of target monitoring points according to process sub-process; Construct an early warning sub-model for the target monitoring point based on all characteristic indicators; Set the early warning sub-model of each equipment point in turn; Establish the early warning sub-model series P, P=(p1, p2…p i …pn ), where p i is the warning sub-model of the i-th monitoring point; n is the number of monitoring points.

[0029] Specifically, corresponding characteristic index parameters are selected according to the process sub-flow corresponding to the monitoring point. For example, if the process sub-flow corresponding to the monitoring point is the coating process, its corresponding characteristic indexes include but are not limited to multiple parameters such as film thickness, refractive index, porosity, crystallinity, surface roughness, etc.

[0030] Specifically, by analyzing historical data, the optimal value of each characteristic index is set as the standard reference value, and the corresponding warning sub-model is constructed according to the standard reference values of all characteristic indexes.

[0031] Specifically, when setting the monitoring sub-strategies of each monitoring point, it includes: Obtain the characteristic data packet of the target monitoring point according to the preset monitoring time node; Generate the abnormal risk value b of the target monitoring point according to the characteristic data packet; b = β i *(s i - s' i ) 2 ; where, θ1 is the number of characteristic indexes of the target monitoring point; β i is the influence factor of the i-th characteristic index of the target monitoring point; s i is the reference value of the i-th characteristic index generated based on the characteristic data packet of the target monitoring point; s' i is the standard reference value of the i-th characteristic index of the target monitoring point; Preset the abnormal risk value threshold B1; If b < B1, the target monitoring point generates a first-level monitoring instruction, and obtains the characteristic data packet of the next monitoring time node according to the first-level monitoring instruction; If b > B1, generate a second-level monitoring instruction for the target monitoring point; The second-level monitoring instruction includes: Obtain the auxiliary data packet of the target monitoring point; Generate an abnormal data packet according to the auxiliary data packet and the characteristic data packet of the target monitoring point; Send the abnormal data packet to the third processing module.

[0032] Specifically, the abnormal risk value threshold can be set according to historical parameters.

[0033] Specifically, the influence factors of each characteristic index can be set according to their influence degrees on the performance of the display material, and the greater the influence degree, the larger the value of the corresponding influence factor.

[0034] Specifically, the larger the abnormal risk value, the greater the possibility that the display material at the current monitoring point has a performance defect risk, and the relevant abnormal characteristic data needs to be analyzed in a timely manner.

[0035] Specifically, the first-level monitoring instruction means that the production process of the current monitoring point is normal, and it is only necessary to obtain the characteristic indicator data according to the normal monitoring time node.

[0036] It can be understood that in the above embodiment, multiple monitoring points are set according to the process flow of the display material, and the abnormal characteristic data are analyzed in a timely manner by constructing an early warning sub-module corresponding to each monitoring point. When it is determined that the characteristic data of a single monitoring point is abnormal, the corresponding abnormal data packet is generated by collecting the corresponding process monitoring data, and the abnormal characteristic data in the process flow of the display material is analyzed in a timely manner.

[0037] In a preferred embodiment of the present application, the analysis unit includes: a first analysis module for constructing an anchor timeline based on a process flow of display materials; The first analysis module is further used to construct a preprocessing model based on the anchor time axis; The second analysis module is used to construct multiple production time intervals based on the anchor time axis; Establish a production time interval sequence W, W=(w1, w2…w i …w m ), where w i is the i-th production time interval; m is the number of production time intervals; The second processing module is also used to construct an analysis sub-model for each production time interval; Establish the analysis sub-model sequence D, D=(d1, d2…d i …d m ), where d i is the analytical sub-model for the i-th production time interval; A characteristic analysis model is constructed according to the analysis sub-model sequence D.

[0038] Specifically, an offline database is constructed by collecting historical data, and the disturbance maps of each corresponding production time interval are generated based on the analysis of data at different production process moments in the offline database.

[0039] Specifically, by constructing an anchored timeline, we can quickly locate the process coordinate system corresponding to the real-time abnormal data packet, thereby aligning the real-time abnormal data packet with the relevant data in the offline database in time and space.

[0040] Specifically, when constructing the analysis sub-model for each production time interval, it includes: Set w in sequence according to the production time interval sequence Wi is the target time interval; Obtain process index parameters of the target time interval; Obtain characteristic indicator parameters of the target time interval; Establish a disturbance map between process characteristic parameters and characteristic index parameters; An analytical sub-model for the target time interval is constructed based on the disturbance spectrum.

[0041] Specifically, quantitative association rules of various process indicators and characteristic indicators are generated according to the process indicator parameters and characteristic indicator parameters related to the target time interval, so as to construct the corresponding disturbance map.

[0042] In a preferred embodiment of the present application, the third processing module is further configured to: Receive abnormal data packets; Determine the production time interval of the abnormal data packet based on the preprocessing result of the abnormal data packet by the preprocessing model; Select the target sub-model according to the judgment result; The target sub-model generates analysis results of abnormal data packets.

[0043] Specifically, when the target sub-model generates analysis results for abnormal data packets, the following are included: Generate multiple characteristic indices to be evaluated and multiple process indices to be evaluated according to the target sub-model; Establish the characteristic index series F to be evaluated, F=(f1, f2…f i …f θ ), where f i is the i-th characteristic index to be evaluated in the target sub-model; θ is the number of characteristic indexes to be evaluated in the target sub-model; Generate abnormal values ​​of each characteristic index to be evaluated in turn; Establish a sequence T of process indicators to be evaluated, T=(t1, t2…t i …t r ), where t i is the i-th process indicator to be evaluated in the target sub-model; r is the number of evaluation process indicators in the target sub-model; Generate interference risk values ​​for each process indicator to be evaluated; Generate analysis results of abnormal data packets based on all interference risk values.

[0044] Specifically, the greater the interference risk value of the process indicator being evaluated, the higher the corresponding adjustment order. Root cause inference is performed based on the abnormal parameters of each characteristic indicator being evaluated, and an adjustment order is generated based on the interference risk value of each process indicator being evaluated, thereby outputting a process optimization plan. Equipment parameters are dynamically adjusted through a reinforcement learning algorithm.

[0045] Specifically, the interference risk value of each process indicator to be evaluated includes: According to the process index sequence T to be evaluated, set t i is the target process indicator; Generate the interference risk value h of the target process indicator; h=e1*Q1*[ η i *j i ]+e2*Q2*[ g 1i *k i ]; Wherein, e1 is the preset first weight coefficient; e2 is the preset second weight coefficient; Q1 is the preset first fixed coefficient; Q2 is the preset second fixed coefficient; λ1 is the number of risk assessment indicators; η i is the influencing factor of the i-th disturbance risk index; j i is the reference value of the i-th disturbance risk index in the target process index; θ2 is the number of associated characteristic indicators of the target process index generated based on the target sub-model; g 1i is the weighting factor of the i-th associated characteristic index of the target process index; k i is the abnormal value of the i-th associated characteristic index of the target process index.

[0046] Specifically, the larger the disturbance risk value, the greater the possibility that the current target process indicators are abnormal, and the target process indicators need to be adjusted in a timely manner.

[0047] Specifically, the disturbance risk indicators include, but are not limited to, the deviation between the real-time value and the standard value of the target process indicator, the fluctuation parameter of the target process indicator, etc.

[0048] Specifically, the abnormal value of each characteristic indicator is the difference between the real-time value and the standard value, and the weighting coefficient of each related characteristic indicator is set according to the degree of interference of the fluctuation of the target process indicator on the related characteristic indicator. The greater the interference degree, the larger the value of the corresponding weighting coefficient.

[0049] Specifically, all parameters in the model are normalized by presetting a first fixed coefficient and a second fixed coefficient, so that each parameter in the model is in the same value range.

[0050] It can be understood that in the above embodiment, the real-time abnormal data and offline data are mapped to the same process coordinate system through the preprocessing model, and the process parameters that cause fluctuations in characteristic indicators are analyzed in a timely manner according to the material analysis model, and the process optimization strategy is output, so as to dynamically adjust the equipment parameters and improve the production quality and production efficiency of display materials.

[0051] Based on another preferred embodiment of a display process material characteristic analysis system in any of the above preferred embodiments, this preferred embodiment provides a display process material characteristic analysis method, including: Set multiple monitoring points according to the process flow of display materials and build early warning sub-models for each monitoring point; Set monitoring sub-strategies for each monitoring point based on all early warning sub-models, and obtain abnormal data packets based on the monitoring sub-strategies; Generate analysis results of abnormal data packets based on the preprocessing model and feature analysis model; Among them, when constructing the early warning sub-model of each monitoring point, it includes: Establish a monitoring point sequence A, A=(a1, a2…a i …a n ), where a i is the i-th monitoring point; n is the number of monitoring points; According to the number of monitoring points A, set a i is the target monitoring point; Obtain the process sub-process of the target monitoring point; Set multiple characteristic indicators of target monitoring points according to process sub-process; Construct an early warning sub-model for the target monitoring point based on all characteristic indicators; Set the early warning sub-model of each equipment point in turn; Establish the early warning sub-model series P, P=(p1, p2…p i …p n ), where p i is the early warning sub-model of the i-th monitoring point; n is the number of monitoring points; The abnormal data packet includes: Feature data package and ancillary data package.

[0052] According to the first concept of the present application, multiple monitoring points are set according to the process flow of the display material, and the abnormal characteristic data are analyzed in time by constructing the early warning sub-module corresponding to each monitoring point. When it is judged that the characteristic data of a single monitoring point is abnormal, the corresponding abnormal data packet is generated by collecting the corresponding process monitoring data, and the abnormal characteristic data in the process flow of the display material is analyzed in time.

[0053] According to the second concept of this application, real-time abnormal data and offline data are mapped to the same process coordinate system through a preprocessing model, and the process parameters that cause fluctuations in characteristic indicators are analyzed in a timely manner according to the material analysis model, and the process optimization strategy is output to dynamically adjust the equipment parameters and improve the production quality and production efficiency of display materials.

[0054] The above is only a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and replacements can be made without departing from the technical principles of the present application. These improvements and replacements should also be regarded as the scope of protection of the present application.

Claims

1. A display process material characteristic analysis system, characterized in that: It includes: A central control unit for setting multiple monitoring points according to the process flow of the display material; A monitoring unit including multiple monitoring sub-modules, and the monitoring sub-module is used to collect characteristic data packets of each monitoring point; The monitoring sub-module is also used to collect auxiliary data packets of each monitoring point; An analysis unit for constructing a characteristic analysis model of a preprocessing model; The central control unit includes: The first processing module is used to establish a monitoring point sequence A, A=(a1, a2…a i …a n ), where a i is the i-th monitoring point; n is the number of monitoring points; The first processing module is also used to set monitoring sub-strategies for each monitoring point.

2. The display process material characteristic analysis system according to claim 1, wherein: The central control unit further includes: A second processing module for establishing an early warning sub-model for each monitoring point; The second processing module is also used to set monitoring sub-strategies for each monitoring point according to all the early warning sub-models; A third processing module for generating an analysis result.

3. The display process material characteristic analysis system according to claim 2, wherein: The second processing module is also used to: According to the number of monitoring points A, set a i is the target monitoring point; Obtain the process sub-flow of the target monitoring point; Set multiple characteristic indicators for the target monitoring point according to the process sub-flow; Construct an early warning sub-model for the target monitoring point according to all the characteristic indicators; Set the early warning sub-models for each equipment point in sequence; Establish the early warning sub-model series P, P=(p1, p2…p i …p n ), where p i is the early warning sub-model of the i-th monitoring point; n is the number of monitoring points.

4. The display process material characteristic analysis system according to claim 3, wherein: When setting the monitoring sub-strategies for each monitoring point, it includes: Obtain the characteristic data packet of the target monitoring point according to the preset monitoring time node; Generate an abnormal risk value b for the target monitoring point according to the characteristic data packet; b= b i *(s i -s' i ) 2 ]; Among them, θ1 is the number of characteristic indicators of the target monitoring point; β i is the influencing factor of the i-th characteristic index of the target monitoring point; s i Generate the reference value of the i-th characteristic index for the characteristic data packet based on the target monitoring point; s' i is the standard reference value of the i-th characteristic index of the target monitoring point; Preset an abnormal risk value threshold B1; If b < B1, the target monitoring point generates a first-level monitoring instruction, and obtains the characteristic data packet of the next monitoring time node according to the first-level monitoring instruction; If b > B1, generate a second-level monitoring instruction for the target monitoring point; The second-level monitoring instruction includes: Obtain the auxiliary data packet of the target monitoring point; Generate an abnormal data packet according to the auxiliary data packet and the characteristic data packet of the target monitoring point; Send the abnormal data packet to the third processing module.

5. The display process material characteristic analysis system according to claim 4, wherein: The analysis unit includes: A first analysis module for constructing an anchored time axis according to the process flow of the display material; The first analysis module is also used to construct a preprocessing model according to the anchored time axis; A second analysis module for constructing multiple production time intervals according to the anchored time axis; Establish a production time interval sequence W, W=(w1, w2…w i …w m ), where w i is the i-th production time interval; m is the number of production time intervals; The second processing module is also used to construct analysis sub-models for each production time interval; Establish the analysis sub-model sequence D, D=(d1, d2…d i …d m ), where d i is the analytical sub-model for the i-th production time interval; Construct a characteristic analysis model according to the analysis sub-model sequence D.

6. The display process material characteristic analysis system according to claim 5, characterized in that: When constructing the analysis sub-models for each production time interval, it includes: Set w in sequence according to the production time interval sequence W i is the target time interval; Obtain the process index parameters of the target time interval; Obtain the characteristic index parameters of the target time interval; Establish a perturbation map between the process characteristic parameters and the characteristic index parameters; Construct an analysis sub-model for the target time interval according to the perturbation map.

7. The display process material characteristic analysis system according to claim 5, wherein: The third processing module is also used to: Receive the abnormal data packet; Judge the production time interval where the abnormal data packet is located based on the preprocessing result of the abnormal data packet by the preprocessing model; Select a target sub-model according to the judgment result; [[ID= 8. The display process material characteristic analysis system according to claim 7, wherein: ​ ​ Establish the characteristic index series F to be evaluated, F=(f1, f2…f i …f θ ), where f i is the i-th characteristic index to be evaluated in the target sub-model; θ is the number of characteristic indexes to be evaluated in the target sub-model; ​ Establish a sequence T of process indicators to be evaluated, T=(t1, t2…t i …t r ), where t i is the i-th process indicator to be evaluated in the target sub-model; r is the number of evaluation process indicators in the target sub-model; ​ ​ 9. The display process material characteristic analysis system according to claim 8, wherein: ​ According to the process index sequence T to be evaluated, set t i is the target process indicator; Generate the interference risk value h of the target process indicator; h=e1*Q1*[ η i *j i ]+e2*Q2*[ g 1i *k i ]; Wherein, e1 is the preset first weight coefficient; e2 is the preset second weight coefficient; Q1 is the preset first fixed coefficient; Q2 is the preset second fixed coefficient; λ1 is the number of risk assessment indicators; η i is the influencing factor of the i-th disturbance risk index; j i is the reference value of the i-th disturbance risk index in the target process index; θ2 is the number of associated characteristic indicators of the target process index generated based on the target sub-model; g 1i is the weighting factor of the i-th associated characteristic index of the target process index; k i is the abnormal value of the i-th associated characteristic index of the target process index.

10. A method for analyzing characteristics of display process materials, applied to the display process material characteristics analysis system according to any one of claims 1 to 8, characterized in that: include: Set multiple monitoring points according to the process flow of display materials and build early warning sub-models for each monitoring point; Set monitoring sub-strategies for each monitoring point based on all early warning sub-models, and obtain abnormal data packets based on the monitoring sub-strategies; Generate analysis results of abnormal data packets based on the preprocessing model and feature analysis model; Among them, when constructing the early warning sub-model of each monitoring point, it includes: Establish a monitoring point sequence A, A=(a1, a2…a i …a n ), where a i is the i-th monitoring point; n is the number of monitoring points; According to the number of monitoring points A, set a i is the target monitoring point; Obtain the process sub-process of the target monitoring point; Set multiple characteristic indicators of target monitoring points according to process sub-process; Construct an early warning sub-model for the target monitoring point based on all characteristic indicators; Set the early warning sub-model of each equipment point in turn; Establish the early warning sub-model series P, P=(p1, p2…p i …p n ), where p i is the early warning sub-model of the i-th monitoring point; n is the number of monitoring points; The abnormal data packet includes: Feature data package and ancillary data package.

Images