OLED production equipment fault diagnosis terminal capable of being remotely monitored

Abstract

The invention discloses an OLED (Organic Light Emitting Diode) production equipment fault diagnosis terminal capable of being remotely monitored, which relates to the technical field of fault diagnosis, and comprises the following steps: acquiring key process parameters of equipment to obtain equipment operation data; performing operation state analysis according to the equipment operation data to obtain an abnormal index; performing fault mode identification according to the abnormal index to obtain an equipment fault type; performing abnormal influence analysis according to the equipment fault type to obtain key influence parameters; performing remote abnormality diagnosis according to the key influence parameters to obtain a diagnosis result; and performing abnormal trend analysis according to the diagnosis result to obtain the equipment health state. Through parameter deviation degree calculation and multi-parameter correlation analysis, the collected key process parameters are subjected to real-time comprehensive analysis, the parameter deviation degree is quantified, coupling abnormity among the parameters is identified, the accuracy and comprehensiveness of fault diagnosis are improved, and the false alarm rate and the missing report rate are reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of fault diagnosis, in particular to a remote monitoring OLED production equipment fault diagnosis terminal. BACKGROUND

[0002] With the rapid development of OLED display screens and lighting devices, the precision and reliability requirements of production equipment are continuously improved. In the OLED production process, the evaporation, packaging, cleaning and other process links involve a variety of complex process parameters, such as evaporation source temperature, evaporation rate, cavity pressure and gas flow. Small deviations in production equipment can lead to product quality decline, yield reduction, and even equipment abnormalities.

[0003] In the prior art, there are deficiencies in running state analysis: most of the prior art only analyzes a single key parameter, ignoring the coupling effect and comprehensive trend between parameters, resulting in low abnormality recognition accuracy and easy false positives or false negatives. SUMMARY

[0004] In view of the deficiencies of the prior art, the present application provides a remote monitoring OLED production equipment fault diagnosis terminal to solve the problems raised in the background art.

[0005] To achieve the above purpose, the present application provides the following technical solutions: In a first aspect, the present application provides a remote monitoring OLED production equipment fault diagnosis terminal, comprising the following steps: S1, collecting device key process parameters to obtain device running data; S2, performing running state analysis according to the device running data to obtain abnormality indicators; S3, performing fault mode identification according to the abnormality indicators to obtain device fault types; S4, performing abnormality impact analysis according to the device fault types to obtain key impact parameters; S5, performing remote abnormality diagnosis according to the key impact parameters to obtain diagnosis results; S6, performing abnormality trend analysis according to the diagnosis results to obtain device health status.

[0006] Further optimize the technical solution, the device key process parameter collection in step S1 includes: By determining the key parameters and collection points, high-precision sensors are deployed to continuously and real-time collect key parameters, establish data files, and obtain device running data.

[0007] Further optimize the technical solution, the running state analysis in step S2 includes: According to the obtained equipment operation data, single parameter abnormalities and coupled abnormalities are captured through parameter deviation degree calculation and multi-parameter correlation analysis, and combined with trend analysis, abnormal indexes are obtained.

[0008] Further optimization of the technical solution, the parameter deviation degree calculation includes: Among them: : time When the parameter Deviation degree; : time When the parameter The collection value; : the average value of parameter In the historical normal state; : the standard deviation of parameter In the historical normal state; According to the collection value of the parameter, combined with the average value and standard deviation of the parameter in the historical normal state, the deviation degree of the parameter compared with the normal state is calculated.

[0009] Further optimization of the technical solution, the multi-parameter correlation analysis includes: Among them: : composite abnormal index At time; : the number of key parameters; : the weight of parameter ; The composite abnormal index under the same time window is obtained by weighted combination calculation on the deviation degree of multiple parameters.

[0010] Further optimization of the technical solution, the fault mode recognition in step S3 includes: According to the obtained abnormal index, the fault mode recognition is realized through historical fault mapping and possibility evaluation, and the equipment fault type is obtained.

[0011] Further optimization of the technical solution, the abnormal influence analysis in step S4 includes: According to the obtained equipment fault type, the influence degree analysis is carried out on the equipment parameters, and the key influence factors causing the equipment failure are identified.

[0012] Further optimization of the technical solution, the remote abnormal diagnosis in step S5 includes: According to the obtained key influence parameters, the real-time state of the key parameters is compared with a historical fault template, a fault risk level is judged, and an abnormal diagnosis result is obtained.

[0013] Further optimization of the technical solution, the abnormal trend analysis in step S6 includes: According to the obtained diagnosis result, the change trend of the equipment health state is evaluated through continuous time period result collection, the instantaneous abnormal diagnosis is converted into long-term health evaluation, and the equipment health state is obtained.

[0014] Further optimization of the technical solution includes the following functional modules: The data acquisition module, the operation analysis module, the fault identification module, the parameter analysis module, the abnormal diagnosis module and the health evaluation module.

[0015] In a second aspect, the present application provides a computer device, comprising a memory and a processor, the memory stores a computer program, wherein: the computer program instructions are executed by the processor to realize the steps of the fault diagnosis terminal of the OLED production equipment which can be remotely monitored according to the first aspect of the present application.

[0016] In a third aspect, the present application provides a computer readable storage medium, which stores a computer program, wherein: the computer program instructions are executed by the processor to realize the steps of the fault diagnosis terminal of the OLED production equipment which can be remotely monitored according to the first aspect of the present application.

[0017] Compared with the prior art, the present application provides a fault diagnosis terminal of OLED production equipment which can be remotely monitored, having the following beneficial effects: The fault diagnosis terminal of OLED production equipment which can be remotely monitored, through parameter deviation calculation and multi-parameter correlation analysis, performs real-time comprehensive analysis on the collected key process parameters, quantifies the parameter deviation degree, identifies the coupling abnormality between parameters, improves the accuracy and comprehensiveness of fault diagnosis, and reduces the false positive and false negative rates. BRIEF DESCRIPTION OF DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0019] Figure 1 A flowchart of the fault diagnosis terminal of OLED production equipment which can be remotely monitored is provided. Figure 2A module schematic diagram of a remote monitoring OLED production equipment fault diagnosis terminal provided by the present application. DETAILED DESCRIPTION

[0020] In order to make the above objectives, features and advantages of the present application more apparent, a detailed description of the specific embodiments of the present application will be given below with reference to the accompanying drawings.

[0021] In the following description, a large number of specific details are set forth in order to facilitate a thorough understanding of the present application, but the present application can also be implemented in other ways different from the description, and those skilled in the art can make similar generalizations without departing from the concept of the present application, so the present application is not limited to the specific embodiments disclosed below.

[0022] Secondly, the "one embodiment" or "embodiment" referred to herein means that the specific features, structures or characteristics can be included in at least one implementation of the present application. "In one embodiment" appearing in different places in the specification does not mean the same embodiment, nor is it an embodiment that is independent of or mutually exclusive with other embodiments.

[0023] Embodiment one: Reference Figure 1 For the first embodiment of the present application, the embodiment provides a remote monitoring OLED production equipment fault diagnosis terminal, including the following steps: S1, collecting device key process parameters to obtain device operation data.

[0024] In the present embodiment, the device key process parameter collection includes: In the OLED production process, the process parameters of the device directly determine the quality and production efficiency of the device. The deposition, packaging, printing and detection equipment will generate temperature fluctuations, vacuum changes, current, voltage and vibration and other key process data when running. These parameters may cause pixel defects, uneven film or poor packaging when slightly fluctuate. If these parameters cannot be accurately obtained, the device state cannot be judged, and reliable data basis cannot be provided for subsequent fault diagnosis and remote monitoring. Therefore, collecting device key process parameters is the premise and basis for fault diagnosis.

[0025] By determining the key parameters and collection points, deploying high-precision sensors, continuously and real-time collecting the key parameters, establishing data files, obtaining device operation data, and thus reflecting the device operation state in real time, remote monitoring support is realized, and basic data is provided for subsequent steps.

[0026] The parameter collection method includes: Determination of key parameters and collection points: According to the OLED production process, the core process parameters of each equipment are determined, such as the vacuum degree of the evaporation equipment, the evaporation source temperature, the glue thickness of the packaging equipment, the UV curing intensity, the light source intensity of the optical detection equipment, etc. For each key parameter, select the appropriate sensor position to ensure that representative data are collected and the actual state of the equipment can be accurately reflected. By reasonably determining the parameters and collection points, the problem of parameter reflection deviation can be avoided, laying a foundation for the accuracy of all subsequent diagnosis steps; Deployment of high-precision sensors: Industrial-grade sensors such as pressure sensors, temperature sensors, current and voltage sensors, and vibration sensors are installed at each collection point. The running environment of OLED equipment is usually accompanied by high temperature, ultra-high vacuum, strong electromagnetic interference and other complex conditions, so high-resolution, strong anti-interference ability and fast response characteristics of sensors must be used to capture rapidly changing process parameters. According to the device environment, it is designed to be sealed, protected and signal stable, so as to have long-term running ability; Sensor signal digitization and preliminary processing: The analog signals collected by the sensor are digitized by the field acquisition card or edge node, converted into data that can be stored and transmitted, and preliminary checking is performed during digitization, such as removing obvious outliers and noise to ensure data quality; Time marking and device identification: Each data record is marked with a timestamp and device number to ensure data traceability. Continuous data is sampled to generate parameter data streams arranged in time sequence, helping to analyze the trend of parameter changes over time; Data transmission to edge node: The processed data is transmitted to the edge computing node or industrial gateway device for centralized caching and compression to reduce transmission load while maintaining data integrity in unstable or transient network interruptions. The edge node can also perform simple statistics on the data to generate real-time monitoring indicators; Data upload to remote monitoring platform: Through industrial Ethernet, optical fiber or 5G network, the data of the edge node is uploaded to the remote monitoring platform, and the information security is guaranteed. After receiving the data, it is included in the equipment running database to provide complete input for subsequent steps.

[0027] S2, running state analysis according to equipment running data, obtaining abnormal indicators.

[0028] In this embodiment, the running state analysis includes: In the production process of OLED devices, the fluctuation of a single parameter may not directly cause failure, but the combined change of multiple parameters often becomes a precursor of device abnormalities. For example, a slight fluctuation in the temperature of the evaporation source may not affect the production line for a short time, but it is accompanied by a decrease in vacuum, uneven thickness of glue, and an increase in vibration, which may cause thin film deposition defects or packaging failure. If these running data are not analyzed, these small but critical abnormal signals cannot be found, and potential failures cannot be located in advance.

[0029] According to the obtained device running data, single parameter abnormalities and coupled abnormalities are captured through parameter deviation calculation and multi-parameter correlation analysis, and a quantifiable abnormality index is obtained through trend analysis, so as to reflect the potential abnormalities and running risks of the device, provide more refined and forward-looking diagnostic basis, improve the accuracy and comprehensiveness of fault diagnosis, and reduce the false positive and false negative rates.

[0030] The specific implementation method includes: Device running data arrangement and sorting: obtaining device running data from S1, arranging them in chronological order, ensuring data integrity and continuity, and ensuring that each data contains device number, collection time and corresponding key parameter value, dividing the data into fixed time windows for subsequent calculation; Parameter deviation calculation: for each key parameter, calculate the difference between the current value and the historical normal running mean value after standardization, ensure that different parameters can be operated in dimension and range, quantify whether the parameter deviates from the normal range, generate a preliminary abnormality quantification index for each parameter, and provide an intuitive quantitative basis for judging parameter abnormalities; Multi-parameter correlation analysis: combine the deviation degrees of multiple key parameters in the same time window, identify the parameter combination that deviates at the same time by calculating the correlation trend between parameters, extract potential coupled abnormalities, generate a composite abnormality index, and use it to describe the comprehensive influence of multi-parameter joint deviation on the device running state, and provide key clues for early detection of potential failures; Abnormal development trend analysis: calculate the change rate of the parameter with time, analyze the abnormal development trend, generate an abnormality index with time sensitivity, i.e., a time-sensitive index, to judge the abnormal evolution information of the abnormality, such as short-term fluctuation or long-term trend, and provide a basis for subsequent fault prediction; Abnormal index set construction: combine the single parameter deviation degree, the composite abnormality index and the time-sensitive index to form a complete abnormality index set, which reflects the multi-dimensional and time-sensitive device state information, and serves as the basis for fault diagnosis.

[0031] Further, the parameter deviation calculation includes: Wherein: : time deviation of parameter , representing the relative degree of deviation of the current parameter value from the historical normal mean value; : time acquired value of parameter , obtained in step S1; : average value of parameter in historical normal state; : standard deviation of parameter in historical normal state; According to the acquired value of the parameter, combined with the average value and standard deviation of the parameter in the historical normal state, the deviation of the acquired parameter compared with the normal state is calculated.

[0032] Further, the multi-parameter correlation analysis includes: Wherein: : composite abnormal index at time , used to reflect the multi-parameter coupling abnormal situation and capture potential risks that cannot be reflected by single parameters; : number of key parameters; : weight of parameter , reflecting the importance of the parameter to the sensitivity of the equipment failure, which can be set according to the historical normal operation data and the contribution of each parameter abnormality to the occurrence of failure in the historical failure cases, combined with expert experience, for example, the deviation of the evaporation source temperature compared with the vacuum degree and the cavity vibration has a greater impact on the equipment, so the weight is higher; The composite abnormal index under the same time window is obtained by weighted combination calculation of the deviation of multiple parameters.

[0033] Further, the time-sensitive index includes: Wherein: : time-sensitive index of parameter at time , used to quantify the rate of change of parameter deviation with time and evaluate the development trend of abnormality; : deviation of parameter at time ; : time interval; The time-sensitive index is obtained by calculating the rate of change of the parameter deviation degree in a period of time.

[0034] S3, identifying a fault mode according to the abnormal index to obtain a device fault type.

[0035] In the embodiment, the fault mode identification includes: In OLED production, device faults have diversity and coupling effects, for example, an evaporation source of an evaporation device may be blocked, a vacuum leak may occur, or temperature control may fail, an encapsulation device may have uneven glue thickness, UV curing abnormalities, etc. It is difficult to directly correspond to a specific fault type through an abnormal index, especially when multiple parameters deviate at the same time, it is more difficult to determine the fault type through intuitive experience.

[0036] According to the obtained abnormal index, through historical fault mapping and possibility evaluation, the fault mode identification is realized to obtain a clear device fault type, thereby supporting the real-time judgment and priority sorting of the remote monitoring terminal on the fault, quantifying the potential risk, guiding the maintenance or intervention, and improving the accuracy and adaptability of fault diagnosis.

[0037] The method steps of fault mode identification include: Constructing a historical fault feature library: collecting device historical operation data and fault records, arranging key abnormal indexes and their dynamic change modes corresponding to each typical fault into a feature template, and each fault feature includes parameter deviation degree combination, composite abnormal index and time-sensitive trend; Obtaining real-time abnormal indexes: obtaining a complete set of abnormal indexes of the current time window from S2, including single parameter deviation degree, composite abnormal index and time-sensitive index, and keeping consistent with the historical fault template in dimension, range and structure, facilitating subsequent calculation; Similarity calculation: comparing the real-time abnormal index with the historical fault feature library to quantify the similarity of each fault, for example, calculating the similarity according to the difference between the real-time abnormal index (including single parameter deviation degree index and composite abnormal index) and the indexes of each fault in the historical fault feature library, and normalizing to the range of 0 to 1, so that the greater the similarity value, the more likely it is this fault. Record the similarity value of each fault as the preliminary possibility; Possibility evaluation: combining the similarity result with the time-sensitive index to dynamically correct the preliminary possibility, for example, if the time-sensitive trend is consistent with the historical fault feature, the possibility is improved (for example, 20% higher than the preliminary possibility, and more than 1 is set to 1), if the index fluctuation trend is inconsistent with the historical fault feature, the possibility is moderately reduced (for example, 20% lower than the preliminary possibility), generate the final possibility of each fault, and label the possibility level (such as less than 0.4 for low, 0.4 to 0.8 for medium, and greater than 0.8 for high); Fault type output: according to the size of the possibility, output the fault type and the corresponding confidence and possibility level, return the result to the remote monitoring terminal, realize visual display and priority sorting, and provide clear intervention target for maintenance personnel.

[0038] S4, abnormal influence analysis according to the device fault type, and obtain key influence parameters.

[0039] In this embodiment, the abnormal influence analysis includes: The complexity of OLED device lies in the high coupling relationship between different process parameters. The same fault may be caused by the abnormal combination of multiple parameters, and a single parameter change may not immediately appear as a fault. It is necessary to determine which parameters play a leading role in the current fault mode through abnormal influence analysis to avoid blindly adjusting irrelevant parameters in the maintenance or adjustment process, and to improve the diagnosis efficiency and maintenance accuracy.

[0040] According to the obtained device fault type, the influence degree of the device parameters is analyzed, the key influence factors causing the device to fail are identified, and accurate parameter priority sorting and risk indication are provided for the remote monitoring terminal, so as to support subsequent maintenance strategy and process adjustment.

[0041] The implementation method of this step includes: Selecting the current fault mode related parameters: according to the fault type output by S3, query the historical fault template, determine the main parameter set involved in this fault mode, these parameters are potential key influence parameters, usually including single parameter deviation obvious, high correlation of composite index, and obvious rising trend of time sensitive index; Calculating the abnormal contribution degree of each parameter: for the selected parameters, combining the abnormal index provided by S2, the contribution degree of each parameter to the fault mode is evaluated, the abnormal contribution degree can be evaluated by comparing the proportion of the deviation degree of the parameter in the total abnormal index deviation degree, and the consistency of its change trend and historical template, for example, the contribution degree of the parameters with the same trend is improved; Analysis of the coupling influence between parameters: considering the mutual relationship between parameters, such as temperature and evaporation rate, pressure and vibration, etc., by observing the interaction of joint deviation index and time trend, identify the parameter combination that plays a amplifying role or triggering role in the fault occurrence process, and include the coupling relationship in the key parameter evaluation, so that the output result not only contains single key parameter, but also includes key parameter combination reflecting the synergistic influence of multiple parameters; Generating a list of key influence parameters and influence scores: the single parameter contribution and the key parameter combination analysis results are integrated to generate a complete list of key influence parameters for the fault type, and each parameter is identified with a quantitative abnormal contribution to reflect its sensitivity and importance in the current fault mode, and is sorted by the size of the abnormal contribution. The list can be directly used for remote monitoring visualization display to guide the priority of maintenance or control operation.

[0042] S5, performing remote abnormal diagnosis according to the key influence parameters to obtain a diagnosis result.

[0043] In this embodiment, the remote abnormal diagnosis includes: Although the possibility of fault type is determined and the key influence parameter analysis based on the fault type is performed in steps S3 and S4, the device fault often involves the coupling of multiple parameters, and the abnormal index or deviation information cannot directly determine the specific state of the device fault. If the real-time state of these parameters is not further comprehensively judged, a clear abnormal diagnosis conclusion cannot be drawn, and some faults may be caused by the deviation of multiple key parameters, that is, the coupling path of multiple parameters. Some parameters are important in the historical template, but the deviation is not obvious in the current running state, while some secondary parameters may be abnormal and trigger risks. Therefore, the real-time changes of these parameters need to be comprehensively diagnosed to determine whether each key parameter is abnormal, and to analyze the contribution of the joint abnormality of multiple key parameters to the overall fault mode.

[0044] According to the obtained key influence parameters, the real-time state of the key parameters is compared with the historical fault template to judge the fault risk level and obtain a clear abnormal diagnosis result, thereby improving the fault matching efficiency, avoiding redundant calculation of full parameter comparison, improving the diagnosis accuracy and operability, and supporting the online health management and remote maintenance decision of the device.

[0045] The implementation method of the remote abnormal diagnosis includes: Matching key parameter state with historical failure mode: According to the key influence parameters of the failure type obtained in S4, compare them with the historical failure template to determine whether the current real-time state exhibits the typical characteristics of the corresponding failure mode, i.e., whether the key parameters exhibit similar deviation combinations and trend changes as the template, and based on this degree of correspondence, calculate the single-parameter matching degree and perform a weighted sum (the single-parameter matching degree can be determined by whether the parameter deviation falls within the parameter deviation interval defined by the historical failure template; if it falls within the interval, the matching degree is 1; if it exceeds, it is calculated in a linear decreasing manner, e.g., when the deviation exceeds the upper limit by 5%, the matching degree is 0.8, and the minimum matching degree is 0), and the weighting weight can be set according to the parameter contribution degree in step S4, and the weighted sum result is added by score in combination with the coupling effect of the parameters (e.g., in the combination of temperature and evaporation rate, if both matching degrees are 1, add 10% to the score, and for each additional combination of this kind, add 10% more, if the final matching degree score exceeds 1, take 1), to obtain the preliminary matching degree score for the failure type, and label the possible abnormal trigger point, so as to only match the key parameters and failure types, improve the matching efficiency, avoid redundant calculation of full parameter comparison, and at the same time identify potential abnormalities caused by the synergistic effect of parameters; Generating abnormal diagnosis results: According to the matching degree score, as the initial confidence, dynamically calculate the confidence for each possible abnormal type, and combine the trend changes of the key parameters, i.e., if the key parameters exhibit consistent rising or falling trends with the historical failure template within a certain time window, the initial confidence is modified (e.g., each parameter with a consistent trend can increase the confidence by 0.02 to 0.05, and if not, the confidence is reduced, and the modification amplitude can be set according to actual conditions), to obtain the final confidence (ranging from 0 to 1, and values exceeding 1 are taken as 1), convert the confidence into a risk level (e.g., a confidence greater than 0.75 is a high risk level, 0.4 to 0.75 is a medium risk level, and less than 0.4 is a low risk level), indicate which abnormal parameters need to be prioritized, and output the diagnosis results including abnormal type, key trigger parameter and contribution explanation; Dynamic adjustment and real-time update: In continuous operation of the equipment, the key parameter state may change, resulting in the need for dynamic adjustment of the diagnosis results, real-time updating of the matching score and confidence based on abnormal indicators and key parameter trends, automatic refreshing of the diagnosis results, and smoothing of the confidence change trend through a time sliding window to avoid misjudgment caused by instantaneous fluctuations, ensuring that the remote monitoring terminal always obtains the latest and most accurate judgment; Outputting remote diagnosis results and decision basis: The final diagnosis results are sent or displayed through the remote monitoring terminal, including failure type, key parameters, confidence, risk level and recommended attention points (such as key parameters triggering abnormalities), which are used to guide maintenance priority, process adjustment or control strategy triggering.

[0046] S6, performing abnormal trend analysis according to the diagnosis result to obtain the device health state.

[0047] In the embodiment, the abnormal trend analysis comprises: The OLED production device usually has the characteristics of long-time continuous operation, and many key components such as evaporation source, film thickness control device, vacuum pump and the like, the failure of which is not instantaneous, but gradually evolves through parameter accumulation deviation. Only relying on the instant diagnosis conclusion of S5, it is impossible to determine whether the abnormality is temporary fluctuation or continuous deterioration of failure precursor, and it is also impossible to determine whether the device needs to be shut down for maintenance.

[0048] According to the obtained diagnosis result, the change trend of the device health state is evaluated through the result collection of the continuous time period, the instant abnormal diagnosis is converted into long-term health evaluation, the device health state is obtained, so that the potential risks are found in advance, the maintenance and adjustment can be targeted, and the understanding of the device reliability and stability is improved.

[0049] The implementation of the step comprises: Collecting diagnosis results of continuous time periods: recording the diagnosis results output by S5 in chronological order (for example, recording once every hour), forming continuous time series data, and providing data basis for trend analysis; Calculating the change trend of the abnormal index with time: performing trend analysis on the continuous diagnosis results, for example, calculating the change rate (the difference between the current value and the value at the last time point), the change direction and the fluctuation amplitude (the difference between the maximum value and the minimum value) of the confidence degree with time, to observe whether it presents an upward, downward or stable trend, and record the duration, which can use statistical methods such as moving average, smooth data and quantify the trend change; Evaluating the device health state: according to the trend analysis result, the device health state is classified into health, warning or risk state, if the failure confidence degree continuously rises, the health state is determined to be degraded, and the health state is determined to be “warning” or “risk” according to the confidence degree, if the abnormal intensity decreases or remains stable, the health state is determined to be good, that is, “normal”, the health state can be comprehensively evaluated in combination with the historical maximum value and fluctuation of the failure confidence degree, the grading standard is set, and the health state quantization is realized; Outputting the device health state information: displaying the change of the abnormal intensity with time and the current health state through the remote monitoring terminal or recording the health state and trend change information.

[0050] Embodiment two: Referring to Figure 2 For the second embodiment of the application, the embodiment provides a remote monitoring OLED production device fault diagnosis terminal, comprising the following functional modules: Data acquisition module: Obtain real-time key process parameter data from sensors of OLED production equipment, standardize collection, timestamp marking and data arrangement to provide basic data for subsequent diagnosis; Running analysis module: Real-time calculation and analysis of collected key parameter data, quantification of parameter deviation, and generation of abnormal index; Fault identification module: Compare abnormal index with historical fault template to identify current possible fault type of the equipment; Parameter analysis module: According to fault type and abnormal index, analyze the contribution of each key parameter to the fault, and determine which parameter is the key factor causing the current abnormality; Abnormal diagnosis module: Combine key influencing parameters with abnormal index to generate diagnosis result of current abnormality of the equipment, realize remote visual diagnosis output; Health assessment module: Time series analysis of remote diagnosis result, quantification of abnormal trend, assessment of overall health status of the equipment, output of health level and trend change, and provision of decision basis for equipment maintenance and production management.

[0051] Example three: In practical application, the present application can be applied to OLED display production line for real-time monitoring of equipment running state and fault diagnosis, and key process parameter fluctuation monitoring and abnormal trend analysis are used as typical scenes for illustration.

[0052] In this scene, first, through sensors installed on evaporation machines, packaging machines and substrate conveying equipment, key process parameters such as temperature, evaporation rate, vacuum degree, gas flow and substrate moving speed are collected, and these data are transmitted to remote monitoring terminal in real time. Then, the collected running data are analyzed, the deviation of each parameter from normal range is quantified, and abnormal index is generated to evaluate whether the equipment running state deviates.

[0053] Based on the generated abnormal index, further identification of possible fault modes of the equipment is carried out, the real-time data are matched with historical fault template, the matching degree score and confidence are calculated, and thus the nature and severity of the abnormality are confirmed. Then, key influencing parameters are analyzed, main process factors causing the current abnormality are identified, and these information are used for remote diagnosis to generate complete diagnosis result, including abnormal existence, abnormal intensity and risk level.

[0054] The time series analysis is performed on the remote diagnosis result, the change trend of the abnormal intensity of the key parameters with time is observed, the equipment health state is evaluated according to the trend change, and the health level and trend information are generated. Through the implementation, the operator and the remote monitoring center can clearly master the current running state, potential risks and development trend of the equipment, so as to realize the timely maintenance, production scheduling optimization and quality control, and ensure the stability and high yield of the OLED production line.

[0055] Embodiment Four The embodiment also provides a computer device suitable for the case of the remote-monitorable OLED production equipment fault diagnosis terminal, including a memory and a processor; the memory is used for storing computer executable instructions, and the processor is used for executing the computer executable instructions to realize the remote-monitorable OLED production equipment fault diagnosis terminal as proposed in the above embodiment.

[0056] The embodiment also provides a storage medium having a computer program stored thereon, and the program is executed by a processor to realize the remote-monitorable OLED production equipment fault diagnosis terminal as proposed in the above embodiment.

[0057] The computer device can be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. The processor of the computer device is used for providing computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used for wired or wireless communication with external terminals. The wireless communication can be realized through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or a key, trackball or touchpad arranged on the shell of the computer device, or an external keyboard, touchpad or mouse, etc.

[0058] If the functions are implemented in software, the functions can be stored in or implemented as one or more instructions or code on a computer-readable medium. Computer-readable media include both computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A storage medium can be any available medium that can be accessed by a computer. By way of example, and not limitation, such computer-readable media can comprise RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer. Also, any connection is properly termed a computer-readable medium. For example, if the software is transmitted from a website, server, or other remote source using a coaxial cable, fiber optic cable, or twisted pair, then the coaxial cable, fiber optic cable, or twisted pair are included in the definition of medium. Disk and disc, as used herein, include compact disc (CD), laser disc, optical disc, digital versatile disc (DVD), and Blu-Ray® disc where disks usually reproduce data magnetically, while discs reproduce data optically with lasers. Combinations of the above should also be included within the scope of computer-readable media.

[0059] In other words, like a human driver of a vehicle, the autonomous vehicle 100 can be programmed to follow traffic laws and rules of the road, and to make decisions based on its programming and the information it receives from its sensors and other sources. The autonomous vehicle 100 can also be programmed to make decisions based on its programming and the information it receives from its sensors and other sources, even if those decisions are not in accordance with traffic laws and rules of the road. For example, the autonomous vehicle 100 can be programmed to avoid a collision with another vehicle, even if doing so would violate a traffic law or rule of the road.

[0060] In other words, like a human driver of a vehicle, the autonomous vehicle 100 can be programmed to follow traffic laws and rules of the road, and to make decisions based on its programming and the information it receives from its sensors and other sources. The autonomous vehicle 100 can also be programmed to make decisions based on its programming and the information it receives from its sensors and other sources, even if those decisions are not in accordance with traffic laws and rules of the road. For example, the autonomous vehicle 100 can be programmed to avoid a collision with another vehicle, even if doing so would violate a traffic law or rule of the road.

[0061] It should be understood that aspects of the application can be implemented in hardware, software, firmware or combinations thereof. In the embodiments described above, various steps or methods can be implemented, for example, by software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, and in another embodiment, any of the following technology, known in the art, or combinations thereof, can be used: discrete logic circuitry having logic gates for implementing logic functions upon an application of data signals, application specific integrated circuits having appropriate combinational logic gates, programmable gate arrays (PGA), field programmable gate arrays (FPGA), and the like.

[0062] It should be noted that the above examples are only used to illustrate the technical solutions of the present application but not limit the present application. Although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or replaced by equivalents without departing from the spirit and scope of the present application, and all of them should be covered in the scope of the claims of the present application.

Claims

1. A fault diagnosis terminal for OLED production equipment capable of remote monitoring, characterized in that, Includes the following steps: S1. Acquire key process parameters of the equipment to obtain equipment operation data; S2. Analyze the operating status based on the equipment operating data to obtain abnormal indicators; S3. Based on abnormal indicators, identify fault modes to obtain the equipment fault type; S4. Conduct anomaly impact analysis based on equipment failure type to obtain key impact parameters; S5. Perform remote anomaly diagnosis based on key influencing parameters and obtain the diagnosis results; S6. Based on the diagnostic results, perform abnormal trend analysis to obtain the equipment health status.

2. The OLED production equipment fault diagnosis terminal capable of remote monitoring according to claim 1, characterized in that, The acquisition of key process parameters for the equipment in step S1 includes: By identifying key parameters and data collection points, deploying high-precision sensors, and continuously and in real-time collecting key parameters, a data archive is established to obtain equipment operation data.

3. The OLED production equipment fault diagnosis terminal capable of remote monitoring according to claim 1, characterized in that, The operational status analysis in step S2 includes: Based on the obtained equipment operation data, single-parameter anomalies and coupling anomalies are captured through parameter deviation calculation and multi-parameter correlation analysis, and anomaly indicators are obtained by combining trend analysis.

4. The OLED production equipment fault diagnosis terminal capable of remote monitoring according to claim 3, characterized in that, The parameter deviation calculation includes: in: :time Time parameters The degree of deviation; :time Time parameters The collected values; Parameters under normal historical conditions The average value; Parameters under normal historical conditions Standard deviation; Based on the collected parameter values, combined with the average and standard deviation of the parameters under historical normal conditions, the deviation of the parameters from the normal state is calculated.

5. A fault diagnosis terminal for remotely monitored OLED production equipment according to claim 4, characterized in that, The multi-parameter correlation analysis includes: in: :time Composite abnormal indicators at the time; The number of key parameters; :parameter The weights; By weighted combination calculation of the deviation of multiple parameters, a composite anomaly index under the same time window is obtained.

6. A fault diagnosis terminal for remotely monitored OLED production equipment according to claim 1, characterized in that, The fault mode identification in step S3 includes: Based on the obtained abnormal indicators, fault mode identification is achieved through historical fault mapping and probability assessment to obtain the equipment fault type.

7. A fault diagnosis terminal for remotely monitored OLED production equipment according to claim 1, characterized in that, The abnormal impact analysis in step S4 includes: Based on the obtained equipment failure type, the impact of the equipment parameters is analyzed to identify the key influencing factors that cause the equipment failure.

8. A fault diagnosis terminal for remotely monitored OLED production equipment according to claim 1, characterized in that, The remote anomaly diagnosis in step S5 includes: Based on the obtained key impact parameters, the real-time status of the key parameters is compared with the historical fault templates to determine the fault risk level and obtain the anomaly diagnosis results.

9. A fault diagnosis terminal for remotely monitored OLED production equipment according to claim 1, characterized in that, The abnormal trend analysis in step S6 includes: Based on the diagnostic results, the changing trend of equipment health status is assessed by collecting results over a continuous period of time, transforming instantaneous abnormality diagnosis into long-term health assessment, and thus obtaining the equipment health status.

10. A fault diagnosis terminal for remotely monitored OLED production equipment according to claim 1, characterized in that, Includes the following functional modules: The module includes a data acquisition module, an operation analysis module, a fault identification module, a parameter analysis module, an anomaly diagnosis module, and a health assessment module.

Images