Early warning method and device for transporting and packaging TFT (Thin Film Transistor) semi-finished glass

Abstract

The invention discloses an early warning method and device for TFT (Thin Film Transistor) semi-finished glass carrying and packaging. The early warning method comprises the steps that operation parameters of a servo, a frequency converter, a motor, an air cylinder and a robot are collected in real time through a PLC, and the operation parameters comprise any one or more of the operation time, the operation frequency, the operation load intensity, the action state and the compressed air pressure; based on the operation parameters, establishing a historical data model associated with any equipment for identifying a normal threshold range of any one or more of time, acceleration, deceleration and pressure of each station and equipment during normal work; and comparing the operation parameters acquired in real time with the historical data model, and if deviation of the target parameters is detected, determining that a fault hidden danger exists. According to the technical scheme, the production line is maintained and repaired in advance before a fault occurs, the downtime is shortened, and the production efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent production, and in particular to an early warning method and device for transporting and packaging TFT semi-finished glass. Background Art

[0002] In the production process of TFT semi-finished substrate glass, it is generally necessary to first cross-cut the glass, and then transport it to various workstations through a handling system to perform weighing, longitudinal cutting, inspection and packaging processes. In order to achieve efficient glass handling and precise processing control, a variety of equipment such as inverters, motors, cylinders, servos and sensors are usually used to work together. However, these devices often have varying degrees of failure during long-term operation. In the prior art, when a failure occurs, the entire production line must often be stopped so that operators can troubleshoot and solve the problem. This approach not only leads to a significant increase in production line downtime, but also may cause a large amount of product waste, which is not conducive to improving large-scale production efficiency and product quality. Therefore, how to effectively avoid or prevent these equipment failures while reducing downtime has become a topic that the industry needs to solve urgently. Summary of the invention

[0003] The present invention provides an early warning method and device for transporting and packaging semi-finished TFT glass products, so as to enable a production line to be pre-maintained and repaired before a failure occurs, thereby reducing downtime and improving production efficiency.

[0004] According to a first aspect of the present invention, there is provided an early warning method for handling and packaging of semi-finished TFT glass products, the early warning method for handling and packaging of semi-finished TFT glass products comprising:

[0005] The operating parameters of the servo, inverter, motor, cylinder and robot are collected in real time through the PLC, wherein the operating parameters include any one or more of the operating time, the number of operations, the operating load intensity, the action state and the compressed air pressure;

[0006] Based on the operating parameters, a historical data model associated with any equipment is established to identify normal threshold ranges of any one or more of time, acceleration, deceleration and pressure for each workstation and equipment during normal operation;

[0007] Compare the real-time collected operating parameters with the historical data model. If a deviation from the target parameter is detected, it is determined that there is a potential fault. If the deviation from the target parameter exceeds the preset threshold, an early warning signal is issued.

[0008] Analyze the frequency or duration of historical failures, evaluate and predict the time or probability of potential failures, adjust transportation parameters, repair or replace worn parts, adjust compressed air pressure, and adjust software algorithms based on early warning signals, so that the production line can be pre-maintained and repaired before failure occurs, reducing downtime and improving production efficiency.

[0009] In one embodiment, it further includes:

[0010] The operating time, temperature, and pressure fluctuation range when different types of faults occur are classified and counted, and an independent analysis model is established for each type of fault in order to more accurately identify the fault mode.

[0011] In one embodiment, it further includes:

[0012] In abnormality identification and early warning, pattern recognition algorithms are used to compare the trend differences between historical data and current real-time data, and machine learning is combined to conduct a comprehensive analysis of the equipment's startup, acceleration and deceleration time, and load curve. If the superposition of multi-dimensional abnormal signals is detected, the warning level is increased.

[0013] In one embodiment, it further includes:

[0014] In the fault trend analysis, by comparing the transportation time and equipment load of similar workstations under the same production cycle, if the operating time of a certain workstation significantly exceeds the standard or slippage, chain loosening, etc. occurs multiple times, the key pre-inspection instructions for the workstation will be automatically output and the relevant information will be stored in the system database.

[0015] In one embodiment, it further includes:

[0016] During the intervention and problem handling stage, when the early warning signal indicates that the compressed air pressure is insufficient, the host computer or the corresponding control module is automatically linked to check or adjust the air supply valve to ensure that the cylinder clamping force meets the requirements and reduce production line shutdowns caused by paper deviation or loose clamps.

[0017] In one embodiment, it further includes:

[0018] Conduct regular revisit tests on workstations or equipment that have been processed for early warning: record the occurrence of failures in the subsequent period of time, and feed this information back to the data model for continuous optimization, so as to dynamically update the fault identification threshold and improve the accuracy of early warning.

[0019] According to a second aspect of the present invention, there is provided an early warning device for handling and packaging semi-finished TFT glass, comprising:

[0020] A collection module is used to collect the operating parameters of the servo, inverter, motor, cylinder and robot in real time through the PLC, wherein the operating parameters include any one or more of the operating time, the number of operations, the operating load intensity, the action state and the compressed air pressure;

[0021] An establishment module for establishing a historical data model associated with any equipment based on the operating parameters, for identifying normal threshold ranges of any one or more of time, acceleration, deceleration and pressure for each station and equipment during normal operation;

[0022] The comparison module is used to compare the real-time collected operating parameters with the historical data model. If a deviation of the target parameter is detected, it is determined that there is a potential fault. If the deviation of the target parameter exceeds the preset threshold, an early warning signal is issued;

[0023] The analysis module is used to analyze the frequency or duration of historical failures, evaluate and predict the time or probability of potential failures, adjust transportation parameters, repair or replace worn parts, adjust compressed air pressure, and adjust software algorithms based on early warning signals, so that the production line can be pre-maintained and repaired before a failure occurs, reducing downtime and improving production efficiency.

[0024] According to a third aspect of the present invention, there is provided an electronic device, the electronic device comprising: a communication interface, a processor, and a memory;

[0025] The memory is used to store program instructions, and when the program instructions are executed by the processor that is communicatively connected to the memory through the communication interface, any of the above-mentioned early warning methods for handling and packaging TFT semi-finished glass is implemented.

[0026] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, on which computer program instructions are stored. When the computer program instructions are executed by a computer (e.g., a processor in the computer), any of the above-mentioned early warning methods for handling and packaging TFT semi-finished glass is implemented.

[0027] In summary, the present invention provides an early warning method and device for handling and packaging TFT semi-finished glass, the method comprising: collecting the operating parameters of servo, inverter, motor, cylinder and robot in real time through PLC, the operating parameters including any one or more of the operating time, number of operations, operating load intensity, action state and compressed air pressure; based on the operating parameters, establishing a historical data model associated with any device, for identifying the normal threshold range of any one or more of the time, acceleration, deceleration and pressure of each station and equipment during normal operation; comparing the operating parameters collected in real time with the historical data model, if a deviation of the target parameter is detected, it is determined that there is a hidden fault, if the deviation of the target parameter is detected to exceed the preset threshold, a warning signal is issued; analyzing the frequency or duration of historical faults, evaluating and predicting the time or probability of occurrence of potential faults. The technical solution of the present application enables the production line to be pre-maintained and repaired before a fault occurs, reducing downtime and improving production efficiency.

[0028] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0029] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0031] Figure 1 A flow chart of an early warning method for transporting and packaging semi-finished TFT glass provided by an embodiment of the present invention;

[0032] Figure 2 A structural diagram of an early warning device for transporting and packaging semi-finished TFT glass provided by an embodiment of the present invention;

[0033] Figure 3 A structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0034] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating the examples of the present application.

[0035] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0036] like Figure 1 As shown, the present invention provides an early warning method for transporting and packaging semi-finished TFT glass, and the early warning method for transporting and packaging semi-finished TFT glass includes:

[0037] In step S11, the operating parameters of the servo, inverter, motor, cylinder and robot are collected in real time through the PLC, and the operating parameters include any one or more of the operating time, the number of operations, the operating load intensity, the action state and the compressed air pressure;

[0038] In step S12, based on the operating parameters, a historical data model associated with any device is established to identify normal threshold ranges of any one or more of time, acceleration, deceleration and pressure of each workstation and device during normal operation;

[0039] In step S13, the real-time collected operating parameters are compared with the historical data model. If a deviation of the target parameters is detected, it is determined that there is a potential fault. If the deviation of the target parameters exceeds a preset threshold, an early warning signal is issued;

[0040] In step S14, the frequency or duration of historical faults is analyzed, the time or probability of potential faults is evaluated and predicted, and transportation parameters are adjusted, worn parts are repaired or replaced, compressed air pressure is adjusted, and software algorithms are adjusted according to early warning signals, so that the production line can be pre-maintained and repaired before the fault occurs, reducing downtime and improving production efficiency.

[0041] In one embodiment, the production process of TFT semi-finished glass usually includes multiple process links such as glass cross-cutting, longitudinal cutting, weighing, appearance inspection and packaging. Each link requires the use of mechatronic equipment such as frequency converters, motors, cylinders, servos, robots and various sensors to achieve accurate handling and positioning. However, if there is a lack of effective preventive maintenance and early warning mechanism, once the equipment fails, the entire production line may be forced to stop and conduct manual troubleshooting. Such "after-the-fact troubleshooting" often leads to long downtime and reduces production efficiency. When products such as glass are in a semi-finished state, large-scale shutdowns are also prone to cause high scrap rates or waste. In order to overcome the above problems, this technical solution proposes an early warning method for handling and packaging of TFT semi-finished glass around the core concept of "fault prevention". By deploying a programmable logic controller (PLC) in the production line, the operating parameters of key equipment (such as the speed of the motor and servo, acceleration and deceleration time, number of operations, load intensity, air pressure state of the cylinder, etc.) are collected in real time, and on this basis, compared and analyzed with the historical data model to determine whether there are hidden dangers of failure. Once it is detected that certain parameters deviate from the normal range, an early warning signal will be issued and corresponding intervention measures will be given according to the fault type to deal with the fault before it actually causes a shutdown. In this way, the production line can maintain a higher operating stability, reduce the losses caused by unplanned shutdowns, and also improve the production capacity utilization rate and product qualification rate of the entire line.

[0042] In the embodiment of the present technical solution, PLC, as the core data acquisition and control device of the production line, can obtain operating parameters from various electromechanical devices (such as frequency converters, motors, cylinders, servos, robot control units, etc.) in real time. The operating parameters include at least but are not limited to: the running time and number of running of the motor or servo; the running load intensity, torque change and speed information; the compressed air pressure state during the cylinder movement, the cylinder opening / closing or clamping / relaxing signals; the robot operation cycle, joint angle or load state, etc.

[0043] After the above operating parameters are collected in real time, they are automatically timestamped and stored in a database or industrial server, ensuring that any anomalies can be traced back to specific time periods and operation links. In actual production, the frequency of data collection can be set according to the importance or failure rate of different equipment. For example, for a double-speed chain conveyor station where transportation slippage often occurs, the sampling frequency can be increased; for a more stable packaging transmission section, the sampling can be moderately slowed down, so as to balance data accuracy and load.

[0044] In order to accurately identify equipment failures, it is necessary to first use a large amount of historical data to extract the key parameter range of each device or workstation in a "healthy" state. For example, for a motor-driven roller conveyor, when fully loaded with a piece of glass of a specified size, the running time, motor current and acceleration required to complete a conveying operation all have a relatively stable range. This technical solution uses statistical methods (such as calculating the mean, variance, median, etc.) or other big data methods (such as clustering algorithms) to derive this healthy range. When the real-time data collected in the future falls within or near this range, it can be considered that it is still in normal working condition; once there is a significant deviation, a potential fault can be suspected. Separate analysis models can also be established for different fault types. Slipping, chain slack, insufficient compressed air, paper offset, etc. are all common fault problems in glass handling and packaging, but the reasons behind them and the associated parameters are not exactly the same. For example, the main factors causing slippage include roller wear, insufficient motor output or excessive load; and the factors causing paper offset in the packaging process are often more closely related to the mismatch between cylinder pressure, servo speed and clamping action.

[0045] In some preferred implementations of the present technical solution, after collecting historical fault data, the characteristic parameters (such as temperature rise, acceleration change, excessive running time, air pressure fluctuation, etc.) when different types of faults occur will be counted separately. Then, based on the characteristic distribution law, an independent characteristic model for each type of fault is constructed. For example: Slip model: focus on "actual transportation time is longer than normal", "current or load curve changes are unstable", "chain / roller friction is insufficient", etc. Paper offset model: mainly strongly associated with features such as "insufficient cylinder or vacuum adsorption pressure", "abnormal servo acceleration and deceleration time" or "delayed clamping action". Compressed air shortage model: map the relationship between air pressure detection data and the air consumption and air source pressure fluctuations of each workstation. Once "multiple clamping action failures" or "frequently below the set threshold" are observed, an early warning is triggered. This type of multi-model parallel design enables stronger targeted analysis capabilities on complex production lines and greatly improves the accuracy of fault identification.

[0046] The real-time comparison process is monitored by the PLC or the upper level, and the parameters collected by the current equipment are compared with the corresponding historical health model. If the degree of deviation is small and only at the edge of the set threshold, it can be identified as a slight abnormality or normal fluctuation; if the deviation exceeds the established threshold, it is determined to be a potential fault and an early warning signal is issued. At the same time, in order to avoid unnecessary false alarms or frequent alarms, a multi-level threshold strategy can be set. For example: Level 1 warning (mild deviation): prompts the operator to pay attention and may focus on observation during the next maintenance; Level 2 warning (moderate deviation): automatically pops up a message, suggesting to check the relevant components and perform necessary debugging or maintenance; Level 3 warning (serious deviation): immediately instruct the production dispatcher or the automatic linkage program to start emergency disposal, such as reducing the production line speed, switching to backup equipment, or immediately suspending the workstation for maintenance.

[0047] Pattern recognition algorithms and machine learning techniques are used to identify anomalies. In the preferred implementation of the present technical solution, a large amount of labeled data may be used in advance to train machine learning models (such as deep neural networks, random forests, or support vector machines, etc.). These models will extract characteristic patterns corresponding to the fault type during the learning phase and store them in the feature space. When the production line is running, new data (start-up time, load curve, pressure change trend, etc.) are continuously input into the model and compared with the stored fault patterns for similarity. If abnormal signals are detected in multiple dimensions at the same time (such as air pressure fluctuations + reduced motor acceleration + extended workstation transportation time), the warning level will be greatly increased, and it is considered that the possibility of a fault is high. At this time, the warning information will be immediately sent to the maintenance team or the automation management platform for more timely intervention.

[0048] In the embodiment, the technical solution is not only for monitoring a single device, but also for horizontal comparison of the same or similar workstations. If most workstations can complete the handling within the agreed time under the same production rhythm, but only a certain workstation often has the situation that the transportation time exceeds the threshold or slips multiple times, the workstation will be marked as high risk. Through such trend analysis, key pre-inspection instructions can be automatically output to the operation and maintenance personnel, and even maintenance orders or maintenance plans can be generated. The comparative analysis can be based on the following indicators: transportation time, acceleration curve, load condition, temperature or friction coefficient estimation, etc. If a workstation repeatedly has abnormal data, and the gap is significant compared with other workstations, it means that the equipment may be worn, loose or aged, and needs to be paid attention to. In order to improve the accuracy of the analysis, the technical solution will also record the time, type and duration of each abnormal event, and review the statistical results periodically. If it is found that a certain workstation repeatedly fails after a fixed period, or is prone to problems in a specific load range, this feature can be used for accurate inference. Compared with judgments based solely on single parameter fluctuations, this trend observation can provide deeper insights, enabling a more comprehensive understanding of the wear patterns or aging mechanisms of different equipment.

[0049] When an early warning signal is issued, different intervention measures are taken according to the nature of the fault. The most common measures include: repairing or replacing worn parts: such as chains, rollers, drive belts, seals, etc.; adjusting the compressed air pressure: if the air source pressure is detected to be low or the cylinder action is abnormal, immediately report and link the air source valve module; software algorithm adjustment: fine-tune certain servo parameters or inverter frequency curves to alleviate equipment overload or unstable operation. The essential goal of early warning is to intervene in time before the fault breaks out completely. This can effectively reduce the risk of sudden shutdown of the production line and ensure that most work-in-progress products can successfully complete their processing flow.

[0050] If problems such as insufficient compressed air pressure are found, instructions will be automatically sent to the host computer or control module to check or adjust the air supply valve. This can quickly restore the air source parameters to the normal range to prevent the collateral consequences such as paper deviation and unstable glass gripping caused by insufficient cylinder clamping. In some highly automated factories, this technical solution can be further expanded to link the early warning with MES (manufacturing execution) or ERP (enterprise resource planning). When certain serious early warnings are triggered, the production schedule will be automatically updated, or the relevant equipment will be placed in a pending inspection state, allowing other backup equipment to take over the production capacity to ensure the continuity of the overall production line operation.

[0051] This technical solution encourages continuous monitoring and revisit testing of the target workstation or equipment for a period of time after completing the early warning intervention or fault handling. The purpose is to verify whether the previous maintenance or adjustment measures are effective and to further accumulate the operation data of the equipment. If the fault frequency drops significantly during the revisit period, it means that the intervention measures are effective; if the fault still occurs frequently or new abnormalities occur, it is necessary to deepen the investigation or correct the model. One advantage is the data-driven adaptive ability. With the dynamic changes in the production environment and equipment conditions, the originally set thresholds or feature ranges may no longer be fully applicable. After collecting new equipment operation data through revisit testing, these data will be input into the fault analysis model again, and the weight and threshold settings of the model will be updated through machine learning or statistical algorithms. For example: Motor aging: With the increase in service life, the acceleration or time control of the motor will change to a certain extent under the same load. If the revisit finds that this decline is linear or nonlinear, the "normal" judgment interval for the motor can be automatically adjusted; Cylinder seal life: The same cylinder or vacuum adsorption may experience a slight loss of pressure after long-term use, and the "normal pressure range" needs to be appropriately lowered. Through such continuous iterations, the early warning method of this technical solution can continue to maintain high accuracy and high adaptability as the production line ages and is transformed, truly realizing intelligent predictive maintenance.

[0052] The core of this technical solution is to significantly reduce the whole line shutdown caused by sudden failures through real-time early warning and early intervention. Compared with the traditional passive method of post-investigation, this technical solution can shorten the time for equipment restart or replacement and keep the production line stable. When the signs of failure appear, immediate intervention can prevent the glass from being scratched, broken or mispositioned during handling or packaging, thereby improving the product qualification rate and reducing the scrap rate. At the same time, it also avoids excessive production line pauses to ensure the maximum utilization of production capacity. The early warning method has good scalability and can be used in a single production line or expanded to multiple parallel production lines for centralized management. And this method is not limited to the handling and packaging of TFT semi-finished glass, but also has strong versatility for other industries that require high-precision handling and packaging (such as semiconductors, flexible screens, precision device assembly, etc.). With the accumulation of data and iteration of models, it can further develop in the direction of deep learning to achieve more complex fault type identification. Through linkage with PLC and other industrial control equipment, functions such as automatic pressure adjustment, software and hardware configuration optimization, and equipment switching can be realized; combined with remote monitoring platforms and data visualization tools, managers can timely understand production conditions and fault warnings in remote locations, realizing true digital management of Industry 4.0. Since this technical solution emphasizes revisit testing and automatic iteration mechanisms, once the equipment status changes, the fault analysis model will be captured and updated to maximize the effective life of the equipment. At the same time, it also provides opportunities for timely modeling and compensation for new problems that may arise in different equipment or workstations during different periods of use.

[0053] This technical solution can be widely used in the intelligent production lines of TFT glass production plants and other related manufacturing industries. From the perspective of implementation cost, most of the hardware (such as PLC, sensors or industrial PCs) required for the implementation of this technical solution are already available or easy to deploy in modern factories; in terms of software and algorithms, this technical solution provides a general model construction idea and multi-level early warning strategy, which can be implemented independently by existing technicians or integrated with the help of third-party industrial software platforms. For automated production lines that already have a certain scale, this data-driven predictive maintenance solution can bring significant economic returns, specifically in terms of reducing maintenance costs, reducing downtime, stabilizing product quality, and optimizing human resource allocation. If the factory is larger or has higher requirements for production capacity reliability, this technical solution can be further connected to the cloud big data center to centrally manage the operating status of each production line and each workstation, and carry out data mining on a larger scale. For example, the equipment health status of factories in different regions can be evaluated at the enterprise level, the production efficiency of each factory can be compared, the bottleneck workstation or equipment type can be quickly found, and cross-factory early warning and maintenance strategies can be formulated accordingly.

[0054] The early warning method for the handling and packaging of TFT semi-finished glass provided by this technical solution, based on the full exploitation of the data potential of real-time collection and historical models, realizes all-round health monitoring of the main equipment in the handling and packaging links through multi-dimensional indicator fusion, fault trend analysis and automated linkage mechanism. Compared with the traditional post-maintenance model, this technical solution can intervene in time before the failure occurs, and supplemented by follow-up tests for model self-learning and continuous optimization, greatly reducing the unplanned downtime of the production line and improving production efficiency and product quality. At the same time, this technical solution is not limited to the transportation and packaging of TFT substrate glass, but can also be extended to similar high-precision production and packaging processes, providing a feasible and efficient technical approach for the transformation of modern manufacturing industry to digitalization and intelligence.

[0055] In one embodiment, Figure 2 FIG. 1 is a block diagram of an early warning device for transporting and packaging semi-finished TFT glass according to an exemplary embodiment. Figure 2 As shown, the early warning device for transporting and packaging semi-finished TFT glass includes a collection module 21, a creation module 22, a comparison module 23 and an analysis module 24.

[0056] The acquisition module 21 is used to collect the operating parameters of the servo, inverter, motor, cylinder and robot in real time through the PLC, and the operating parameters include any one or more of the operating time, the number of operations, the operating load intensity, the action state and the compressed air pressure;

[0057] The establishment module 22 is used to establish a historical data model associated with any equipment based on the operating parameters, and is used to identify the normal threshold range of any one or more of time, acceleration, deceleration and pressure of each workstation and equipment during normal operation;

[0058] The comparison module 23 is used to compare the real-time collected operating parameters with the historical data model. If a deviation of the target parameter is detected, it is determined that there is a potential fault. If the deviation of the target parameter exceeds a preset threshold, an early warning signal is issued;

[0059] The analysis module 24 is used to analyze the frequency or duration of historical failures, evaluate and predict the time or probability of potential failures, adjust transportation parameters, repair or replace worn parts, adjust compressed air pressure, and adjust software algorithms based on early warning signals, so that the production line can be pre-maintained and repaired before the failure occurs, thereby reducing downtime and improving production efficiency.

[0060] The acquisition module 21, the establishment module 22, the comparison module 23 and the analysis module 24 included in the block diagram of the early warning device for handling and packaging of semi-finished TFT glass are controlled to execute the early warning method for handling and packaging of semi-finished TFT glass described in any of the above embodiments.

[0061] like Figure 3 As shown, the present invention provides an electronic device 300, the electronic device includes: a communication interface, a processor 301, and a memory 302;

[0062] Among them, the memory 302 is used to store program instructions. When the program instructions are executed by the processor 301 that is communicatively connected to the memory 302 through the communication interface, the operating parameters of the servo, inverter, motor, cylinder and robot are collected in real time through the PLC, and the operating parameters include any one or more of the operating time, number of operations, operating load intensity, action state and compressed air pressure; based on the operating parameters, a historical data model associated with any device is established to identify the normal threshold range of any one or more of the time, acceleration, deceleration and pressure of each workstation and equipment during normal operation; the real-time collected operating parameters are compared with the historical data model. If a deviation of the target parameter is detected, it is determined that there is a hidden danger of failure. If the deviation of the target parameter is detected to exceed the preset threshold, an early warning signal is issued; the frequency or duration of historical failures is analyzed, and the time or probability of occurrence of potential failures is evaluated and predicted.

[0063] The present invention provides a computer-readable storage medium, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the operating parameters of a servo, a frequency converter, a motor, a cylinder and a robot are collected in real time through a PLC, wherein the operating parameters include any one or more of operating time, operating times, operating load intensity, action state and compressed air pressure; based on the operating parameters, a historical data model associated with any device is established to identify the normal threshold range of any one or more of time, acceleration, deceleration and pressure of each workstation and device during normal operation; the operating parameters collected in real time are compared with the historical data model, and if a deviation of a target parameter is detected, it is determined that there is a hidden danger of failure, and if it is detected that the deviation of the target parameter exceeds a preset threshold, an early warning signal is issued; the frequency or duration of historical failures is analyzed, and the time or probability of occurrence of potential failures is evaluated and predicted.

[0064] It should be understood that the specific features, operations and details described hereinabove about the method of the present invention may also be similarly applied to the device and system of the present invention, or, vice versa. In addition, each step of the method of the present invention described above may be performed by the corresponding parts or units of the device or system of the present invention.

[0065] It should be understood that each module / unit of the device of the present invention can be implemented in whole or in part by software, hardware, firmware or a combination thereof. Each module / unit can be embedded in the processor of the computer device in the form of hardware or firmware or independent of the processor, or can be stored in the memory of the computer device in the form of software for the processor to call to perform the operation of each module / unit. Each module / unit can be implemented as an independent component or module, or two or more modules / units can be implemented as a single component or module.

[0066] In one embodiment, a computer device is provided, which includes a memory and a processor, and the memory stores computer instructions executable by the processor, and the computer instructions instruct the processor to execute each step of the method of the embodiment of the present invention when executed by the processor. The computer device can be a server, a terminal, or any other electronic device with necessary computing and / or processing capabilities in a broad sense. In one embodiment, the computer device may include a processor, a memory, a network interface, a communication interface, etc. connected through a system bus. The processor of the computer device can be used to provide necessary computing, processing and / or control capabilities. The memory of the computer device may include a non-volatile storage medium and an internal memory. An operating system, a computer program, etc. may be stored in or on the non-volatile storage medium. The internal memory can provide an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface and the communication interface of the computer device can be used to connect and communicate with external devices through a network. The steps of the method of the present invention are executed by the processor.

[0067] The present invention may be implemented as a computer-readable storage medium having a computer program stored thereon, which causes the steps of the method of an embodiment of the present invention to be executed when executed by a processor. In one embodiment, the computer program is distributed on a plurality of computer devices or processors coupled to a network so that the computer program is stored, accessed, and executed in a distributed manner by one or more computer devices or processors. A single method step / operation, or two or more method steps / operations, may be performed by a single computer device or processor or by two or more computer devices or processors. One or more method steps / operations may be performed by one or more computer devices or processors, and one or more other method steps / operations may be performed by one or more other computer devices or processors. One or more computer devices or processors may perform a single method step / operation, or perform two or more method steps / operations.

[0068] It will be understood by those skilled in the art that the method steps of the present invention can be completed by instructing related hardware such as a computer device or a processor through a computer program, and the computer program can be stored in a non-temporary computer-readable storage medium, and the steps of the present invention are executed when the computer program is executed. Depending on the circumstances, any reference to memory, storage, database or other media herein may include non-volatile and / or volatile memory. Examples of non-volatile memory include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (enabling production lines to be pre-maintained and repaired before failures occur, reducing downtime and improving production efficiency PROM), flash memory, magnetic tape, floppy disk, magneto-optical data storage device, optical data storage device, hard disk, solid state disk, etc. Examples of volatile memory include random access memory (RAM), external cache memory, etc.

[0069] The various technical features described above can be combined arbitrarily. Although all possible combinations of these technical features are not described, any combination of these technical features should be considered to be covered by this specification as long as there is no contradiction in such combination.

[0070] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. An early warning method for handling and packaging semi-finished TFT glass, characterized in that: include: The operating parameters of the servo, inverter, motor, cylinder and robot are collected in real time through the PLC, wherein the operating parameters include any one or more of the operating time, the number of operations, the operating load intensity, the action state and the compressed air pressure; Based on the operating parameters, a historical data model associated with any equipment is established to identify normal threshold ranges of any one or more of time, acceleration, deceleration and pressure for each workstation and equipment during normal operation; Compare the real-time collected operating parameters with the historical data model. If a deviation from the target parameter is detected, it is determined that there is a potential fault. If the deviation from the target parameter exceeds the preset threshold, an early warning signal is issued. Analyze the frequency or duration of historical failures, evaluate and predict the time or probability of potential failures, adjust transportation parameters, repair or replace worn parts, adjust compressed air pressure, and adjust software algorithms based on early warning signals, so that the production line can be pre-maintained and repaired before failure occurs, reducing downtime and improving production efficiency.

2. The early warning method for transporting and packaging semi-finished TFT glass according to claim 1, characterized in that: Also includes: The operating time, temperature, and pressure fluctuation range when different types of faults occur are classified and counted, and an independent analysis model is established for each type of fault in order to more accurately identify the fault mode.

3. The early warning method for handling and packaging semi-finished TFT glass according to claim 1, characterized in that: Also includes: In abnormality identification and early warning, pattern recognition algorithms are used to compare the trend differences between historical data and current real-time data, and machine learning is combined to conduct a comprehensive analysis of the equipment's startup, acceleration and deceleration time, and load curve. If the superposition of multi-dimensional abnormal signals is detected, the warning level is increased.

4. The early warning method for handling and packaging semi-finished TFT glass according to claim 1, characterized in that: Also includes: In the fault trend analysis, by comparing the transportation time and equipment load of similar workstations under the same production cycle, if the operating time of a certain workstation significantly exceeds the standard or slippage, chain loosening, etc. occurs multiple times, the key pre-inspection instructions for the workstation will be automatically output and the relevant information will be stored in the system database.

5. The early warning method for handling and packaging semi-finished TFT glass according to claim 1, characterized in that: Also includes: During the intervention and problem handling stage, when the early warning signal indicates that the compressed air pressure is insufficient, the host computer or the corresponding control module is automatically linked to check or adjust the air supply valve to ensure that the cylinder clamping force meets the requirements and reduce production line shutdowns caused by paper deviation or loose clamps.

6. The early warning method for transporting and packaging semi-finished TFT glass according to claim 1, characterized in that: Also includes: Conduct regular revisit tests on workstations or equipment that have been processed for early warning: record the occurrence of failures in the subsequent period of time, and feed this information back to the data model for continuous optimization, so as to dynamically update the fault identification threshold and improve the accuracy of early warning.

7. An early warning device for transporting and packaging semi-finished TFT glass, characterized in that: include: A collection module is used to collect the operating parameters of the servo, inverter, motor, cylinder and robot in real time through the PLC, wherein the operating parameters include any one or more of the operating time, the number of operations, the operating load intensity, the action state and the compressed air pressure; An establishment module for establishing a historical data model associated with any equipment based on the operating parameters, for identifying normal threshold ranges of any one or more of time, acceleration, deceleration and pressure for each station and equipment during normal operation; The comparison module is used to compare the real-time collected operating parameters with the historical data model. If a deviation of the target parameter is detected, it is determined that there is a potential fault. If the deviation of the target parameter exceeds the preset threshold, an early warning signal is issued; The analysis module is used to analyze the frequency or duration of historical failures, evaluate and predict the time or probability of potential failures, adjust transportation parameters, repair or replace worn parts, adjust compressed air pressure, and adjust software algorithms based on early warning signals, so that the production line can be pre-maintained and repaired before a failure occurs, reducing downtime and improving production efficiency.

8. The early warning device for transporting and packaging semi-finished TFT glass according to claim 7, characterized in that: The acquisition module, the establishment module, the comparison module and the analysis module are controlled to execute the early warning method for transporting and packaging TFT semi-finished glass according to any one of claims 1 to 6.

9. An electronic device, characterized in that: include: Communication interface, processor, memory; Wherein, the memory is used to store program instructions, and when the program instructions are executed by the processor that is communicatively connected to the memory through the communication interface, the electronic device implements the early warning method for handling and packaging TFT semi-finished glass as described in any one of claims 1 to 6.

10. A computer-readable storage medium having program instructions stored thereon, characterized in that: When the program instructions are executed by a computer, the computer implements the early warning method for handling and packaging TFT semi-finished glass according to any one of claims 1 to 6.

Images