Temperature regulation and control method in photovoltaic glass annealing process

Abstract

The invention provides a temperature regulation and control method in a photovoltaic glass annealing process, relates to the technical field of photovoltaic glass processing, and aims to obtain photovoltaic glass composition structure information, retrieve a frequent annealing curve based on the glass composition structure information and determine an annealing furnace for annealing treatment. Inputting the reference annealing temperature curve into a controller of the annealing furnace for annealing control, monitoring in real time, comparing the multi-point temperature time sequence with the reference annealing temperature curve, identifying a transverse temperature difference gradient and a longitudinal temperature difference gradient, and performing annealing quality influence analysis based on the transverse temperature difference gradient and the longitudinal temperature difference gradient. And regulating and controlling the annealing temperature according to the annealing quality influence index. The technical problems that in the prior art, the photovoltaic glass annealing temperature is lack of flexible regulation and control, so that the temperature accuracy and uniformity are poor, and the annealing quality defect exists are solved. The technical effects of ensuring the accuracy and uniformity of the annealing temperature and improving the annealing quality and performance of the photovoltaic glass are achieved.

Description

Technical Field

[0001] The invention relates to the technical field of photovoltaic glass processing, and in particular to a temperature control method in a photovoltaic glass annealing process. Background Art

[0002] As an important component of solar panels, the quality of photovoltaic glass directly affects the photovoltaic conversion efficiency and service life of the panels. The annealing process is a key link in the production of photovoltaic glass. By controlling the temperature distribution and changes in the heating, insulation and cooling stages, the thermal stress inside the glass can be eliminated and its mechanical strength and impact resistance can be improved. Traditional annealing temperature control methods usually rely on manual or simple program control of heating and cooling devices to maintain overall temperature uniformity. However, due to the differences in thickness, size and composition of photovoltaic glass, traditional methods are difficult to flexibly adjust for specific types of photovoltaic glass, and are prone to local overheating or too-fast cooling, resulting in uneven stress release, which in turn causes problems such as glass warping, microcracks or reduced mechanical properties.

[0003] The existing technology lacks flexible control of the annealing temperature of photovoltaic glass, resulting in poor temperature accuracy and uniformity, and technical problems such as annealing quality defects. Summary of the invention

[0004] The present application provides a temperature control method for the photovoltaic glass annealing process, which is used to solve the technical problems in the prior art that the photovoltaic glass annealing temperature lacks flexible control, resulting in poor temperature accuracy and uniformity, and annealing quality defects.

[0005] In view of the above problems, the present application provides a temperature control method for the annealing process of photovoltaic glass, the method comprising: obtaining glass composition structure information of the target photovoltaic glass; searching for frequent annealing curves in a preset shared database based on the glass composition structure information to generate a reference annealing temperature curve; determining an annealing furnace for annealing the target photovoltaic glass, inputting the reference annealing temperature curve into the controller of the annealing furnace for annealing control, and real-time monitoring to obtain multi-point temperature time series; comparing the multi-point temperature time series with the reference annealing temperature curve to identify the transverse temperature difference gradient and the longitudinal temperature difference gradient; performing annealing quality impact analysis based on the transverse temperature difference gradient and the longitudinal temperature difference gradient, and controlling the annealing temperature according to the annealing quality impact index.

[0006] In a possible implementation, the following processing is performed: timing alignment, interception mapping, and interception mapping curve are performed on the multi-point temperature timing and the reference annealing temperature curve to generate the interception mapping curve; the multi-point temperature timing and the interception mapping curve are compared horizontally to generate the horizontal temperature difference gradient; the multi-point temperature timing and the interception mapping curve are compared vertically to generate the vertical temperature difference gradient.

[0007] In a possible implementation, the following processing is performed: extracting multiple first-point temperatures corresponding to the first time series from the multi-point temperature time series, and obtaining the first reference temperature corresponding to the first time series from the intercepted mapping curve; identifying the temperature difference in the furnace between the multiple first-point temperatures and the first reference temperature in the same time series to generate the lateral temperature difference gradient.

[0008] In a possible implementation, the following processing is performed: performing concentrated value analysis on multiple point temperatures corresponding to any time sequence in the multi-point temperature time sequence to generate a multi-point temperature concentrated value time sequence; calculating the temperature deviation between any two adjacent time sequences in the multi-point temperature concentrated value time sequence to generate a multi-point concentrated temperature deviation time sequence; performing a longitudinal temperature difference comparison based on the multi-point concentrated temperature deviation time sequence and the intercepted mapping curve to generate the longitudinal temperature difference gradient.

[0009] In a possible implementation, the following processing is performed: calculating the temperature deviation between any two adjacent time series in the intercepted mapping curve to generate a reference temperature deviation time series; comparing the temperature deviation values ​​in the multi-point concentrated temperature deviation time series with the reference temperature deviation time series to generate the longitudinal temperature difference gradient.

[0010] In a possible implementation, the following processing is performed: the transverse temperature difference gradient and the longitudinal temperature difference gradient are input into a temperature difference influence model for analysis, and an annealing quality influence index is output, wherein the annealing quality influence index represents the degree of negative impact on the annealing quality caused by the transverse temperature difference gradient and the longitudinal temperature difference gradient; when the annealing quality influence index is greater than or equal to a preset influence index, an optimization instruction is generated; the temperature control optimization module is activated with the optimization instruction, and the transverse gradient and the longitudinal gradient are compensated by the temperature control optimization module to complete the annealing temperature control.

[0011] In a possible implementation, the following processing is performed: configuring a temperature difference influence database, wherein the temperature difference influence database includes multiple groups of temperature difference influence samples, any group of temperature difference influence samples includes transverse temperature difference gradient samples, longitudinal temperature difference gradient samples and identification samples identified with corresponding annealing quality influence indicators, and the temperature difference influence database is connected to the temperature difference influence model; calling the temperature difference influence database through the temperature difference influence model, traversing the multiple groups of temperature difference influence samples to perform sample similarity comparison, obtaining identification information corresponding to the temperature difference influence samples whose transverse temperature difference gradient similarity and longitudinal temperature difference gradient similarity are both greater than the preset similarity, and generating the annealing quality influence index.

[0012] In a possible implementation, the following processing is performed: configuring a temperature control optimization memory library, wherein the temperature control optimization memory library includes compensation parameters corresponding to different transverse temperature difference gradients and longitudinal temperature difference gradients in historical time, and the compensation parameters include control parameters corresponding to multiple heating devices and multiple cooling devices in the annealing furnace, and the air flow circulation device in the annealing furnace; matching compensation parameters in the temperature control optimization memory library according to the transverse temperature difference gradient and the longitudinal temperature difference gradient to generate target compensation parameters; and controlling the annealing temperature with the target compensation parameters.

[0013] One or more technical solutions provided in this application have at least the following technical effects or advantages: The method provided by the embodiment of the present application obtains the glass composition structure information of the target photovoltaic glass; retrieves the frequent annealing curves in the preset shared database based on the glass composition structure information to generate a reference annealing temperature curve; determines the annealing furnace used to anneal the target photovoltaic glass, inputs the reference annealing temperature curve into the controller of the annealing furnace for annealing control, and monitors and obtains the multi-point temperature sequence in real time; compares the multi-point temperature sequence with the reference annealing temperature curve to identify the transverse temperature gradient and the longitudinal temperature gradient; performs annealing quality impact analysis based on the transverse temperature gradient and the longitudinal temperature gradient, and adjusts the annealing temperature according to the annealing quality impact index. The technical effect of ensuring the accuracy and uniformity of the annealing temperature and improving the annealing quality and performance of the photovoltaic glass is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0015] Figure 1 A schematic flow chart of the temperature control method for the photovoltaic glass annealing process provided in this application.

[0016] Figure 2 A schematic diagram of the process of annealing temperature control in the temperature control method of the photovoltaic glass annealing process provided in the present application. DETAILED DESCRIPTION

[0017] The present application provides a temperature control method for the photovoltaic glass annealing process, which is used to solve the technical problem that the existing technology lacks flexible control of the photovoltaic glass annealing temperature, resulting in poor temperature accuracy and uniformity, and annealing quality defects. The technical effect of ensuring the accuracy and uniformity of the annealing temperature and improving the annealing quality and performance of the photovoltaic glass is achieved.

[0018] Below, the technical solutions in the present invention will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments of the present invention. It should be understood that the present invention is not limited to the example embodiments described herein. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. It should also be noted that, for the convenience of description, only the parts related to the present invention are shown in the accompanying drawings, rather than all of them.

[0019] like Figure 1 As shown, the present application provides a temperature control method for a photovoltaic glass annealing process, the method comprising: Obtain the glass composition structure information of the target photovoltaic glass.

[0020] Specifically, the glass composition and structure information of the target photovoltaic glass is obtained through online measurement or process records of the glass production stage. The glass composition and structure information includes basic information such as glass composition, proportion and glass thickness. For example, the target photovoltaic glass is measured using professional chemical analysis instruments and X-ray fluorescence spectrometers. The glass composition and proportion refer to the types of chemical materials that constitute the photovoltaic glass and their percentage content, such as silicon dioxide, calcium oxide, sodium oxide and other main chemical components and their content ratios. These components will significantly affect the thermal properties of the glass, such as the thermal expansion coefficient and annealing point temperature. The glass thickness can be measured using precision measuring tools such as laser rangefinders or micrometers. The glass thickness affects the distribution characteristics of the temperature gradient during the annealing process. By comprehensively acquiring the composition and structure of the target photovoltaic glass, the foundation is laid for the subsequent annealing temperature control process.

[0021] Based on the glass composition structure information, frequent annealing curves are retrieved in a preset shared database to generate a reference annealing temperature curve.

[0022] Specifically, the obtained glass composition structure information is used as a search condition to search for frequent annealing curves in the preset shared database. The preset shared database is a centralized database specifically used to store photovoltaic glass annealing process data. It not only contains a large number of historical annealing curves, but also associates the applicable scope of these curves, such as specific glass thickness, component ratio, etc. The shared database is characterized by high-frequency updates and diverse coverage. It can store the latest annealing data in the industry in real time, and cover curve samples under different process conditions. Frequent annealing curves refer to multiple typical annealing curves stored in the shared database based on historical data and experience summaries. These typical annealing curves cover the annealing parameters of different types of photovoltaic glass under different composition structures, thicknesses, uses, etc. The annealing curve is a curve that describes the temperature change of glass over time during the annealing process. According to the target photovoltaic glass composition and structure information, the benchmark annealing temperature curve that best matches the target photovoltaic glass composition and structure is screened and extracted from the frequent annealing curves. The benchmark annealing temperature curve is a temperature control reference curve for actual annealing operations, which is screened from the frequent annealing curves according to the target photovoltaic glass composition and structure information, including the heating stage, the insulation stage and the cooling stage, covering the entire timeline. Based on the rich samples of the shared database and the characteristics of the glass composition and structure information, the generated benchmark annealing temperature curve can accurately reflect the thermal performance requirements of the target glass.

[0023] An annealing furnace for annealing the target photovoltaic glass is determined, the reference annealing temperature curve is input into a controller of the annealing furnace for annealing control, and a multi-point temperature sequence is acquired through real-time monitoring.

[0024] Specifically, according to the glass composition structure information and annealing requirements of the target photovoltaic glass, a suitable annealing furnace is selected. Annealing furnace types include continuous annealing furnace and intermittent annealing furnace. Among them, the continuous annealing furnace is suitable for mass production, the glass moves at a fixed speed in the furnace, and the temperature partition is accurate. The intermittent annealing furnace is suitable for multi-variety and small batch production, and has high flexibility. The reference annealing temperature curve is input into the controller of the annealing furnace through the interface. The annealing furnace controller is the core management unit of the annealing process. Its function is to dynamically control the heating and cooling equipment according to the set parameters of the curve, such as heating rate, holding time and cooling rate. In the annealing process, the temperature data of multiple points are monitored and obtained in real time by installing a multi-point temperature sensor in the annealing furnace to form a multi-point temperature time series. The multi-point temperature time series can reflect the temperature change of different positions in the furnace over time during the annealing process. Multi-point refers to the deployment of multiple temperature sensors in the annealing furnace. These sensors are evenly distributed at key positions in the furnace, such as around the glass, the top, bottom, and edge of the annealing furnace, forming multiple monitoring points to ensure coverage of the entire furnace. By implementing the temperature control requirements of the benchmark annealing temperature curve and performing multi-point monitoring, possible temperature deviations can be discovered and corrected in a timely manner to ensure the uniformity and consistency of the target glass annealing process.

[0025] The multi-point temperature sequence is compared with the reference annealing temperature curve to identify the transverse temperature difference gradient and the longitudinal temperature difference gradient.

[0026] Furthermore, the multi-point temperature sequence is compared with the reference annealing temperature curve to identify the transverse temperature difference gradient and the longitudinal temperature difference gradient, including: performing timing alignment, interception and mapping of the multi-point temperature sequence and the reference annealing temperature curve to generate an interception mapping curve; performing transverse comparison of the multi-point temperature sequence and the interception mapping curve to generate the transverse temperature difference gradient; performing longitudinal comparison of the multi-point temperature sequence and the interception mapping curve to generate the longitudinal temperature difference gradient.

[0027] Specifically, the multi-point temperature time series is the temperature data collected in real time from multiple sensors in the annealing furnace, which is dynamically updated over time to reflect the actual temperature status of each point at the moment. The reference annealing temperature curve is the temperature control reference curve for the complete annealing process, including the heating stage, the insulation stage and the cooling stage, covering the entire time axis. According to the real-time monitoring value, the current time is monitored, and the data interval of the corresponding time period is intercepted from the reference annealing temperature curve to form a target curve within a short time range, that is, the intercepted mapping curve. When intercepting, ensure that the real-time monitoring value corresponds to the time point of the reference curve one by one. Then, the multi-point temperature time series is compared horizontally with the intercepted mapping curve, and the temperature difference between different points at the same time is analyzed to obtain the horizontal temperature gradient. And the multi-point temperature time series is compared vertically with the intercepted mapping curve, and the temperature difference between the adjacent time periods of the concentrated temperature deviation time series and the intercepted mapping curve is compared to generate the vertical temperature difference gradient. Through time series alignment, horizontal and vertical comparison, a comprehensive analysis of the annealing temperature control accuracy is achieved.

[0028] Furthermore, the multi-point temperature time series is compared horizontally with the intercepted mapping curve to generate the horizontal temperature difference gradient, including: extracting multiple first-point temperatures corresponding to a first time series in the multi-point temperature time series, and obtaining a first reference temperature corresponding to the first time series in the intercepted mapping curve; identifying the temperature difference in the furnace under the same time series between the multiple first-point temperatures and the first reference temperature to generate the horizontal temperature difference gradient.

[0029] Specifically, first, the temperature values ​​of multiple points corresponding to a specific time point, i.e., the first time sequence, are extracted from the multi-point temperature time sequence monitored in real time. These points are distributed at different positions of the photovoltaic glass in the annealing furnace, such as the top, bottom, edge, etc., to cover the entire heated area of ​​the glass. Then, the temperature value corresponding to the first time sequence, i.e., the first reference temperature, is obtained from the intercepted mapping curve, and the first reference temperature represents the temperature data of the reference annealing temperature curve in the first time sequence. Then, the difference between the first point temperature of each point and the first reference temperature is calculated to identify the temperature distribution of different positions in the same time sequence in the furnace at the current moment, and finally, all the differences are combined to form a transverse temperature difference gradient. The transverse temperature difference gradient is an indicator of the temperature uniformity in the furnace, indicating the consistency of the temperature distribution of each position of the photovoltaic glass at the same moment. Under normal circumstances, the temperature in the furnace should be kept uniformly distributed, and the temperature difference of each point should be close to zero. If the temperature difference is large, it means that there may be local overheating or overcooling problems. By extracting real-time temperatures at multiple points, comparing them with reference temperatures, calculating differences and generating transverse temperature gradients, the temperature distribution state in the annealing furnace can be accurately reflected. This not only enables the temperature control deviation during the annealing process to be identified, but also provides a clear control basis for optimizing the annealing process, thereby ensuring the consistency of the temperature distribution of photovoltaic glass and the stability of the annealing quality.

[0030] Furthermore, the multi-point temperature time series is longitudinally compared with the intercepted mapping curve to generate the longitudinal temperature difference gradient, including: performing concentrated value analysis on multiple point temperatures corresponding to any time series in the multi-point temperature time series to generate a multi-point temperature concentrated value time series; calculating the temperature deviation between any two adjacent time series in the multi-point temperature concentrated value time series to generate a multi-point concentrated temperature deviation time series; performing longitudinal temperature difference comparison based on the multi-point concentrated temperature deviation time series and the intercepted mapping curve to generate the longitudinal temperature difference gradient.

[0031] Specifically, in a multi-point temperature time series, all point temperature data corresponding to a certain time series are extracted, and these temperature values ​​are calculated by centralized value. For example, the average value or median of all point temperature data is taken to obtain a multi-point temperature centralized value. The multi-point temperature centralized value is a single value used to represent the overall temperature level under a certain time series, avoiding the interference of abnormal temperature of local points on the overall trend analysis. Then, the centralized values ​​of all time series are arranged in sequence to generate a multi-point temperature centralized value time series, which reflects the dynamic change of the overall temperature during the annealing process. Next, in the multi-point temperature centralized value time series, the temperature deviation between any two adjacent time series is calculated, and the deviation values ​​of all adjacent time series are arranged to form a multi-point centralized temperature deviation time series, which is used to analyze the stability of temperature change during the annealing process. The generated multi-point concentrated temperature deviation time series is compared one by one with the reference temperature deviation of the same time period in the intercepted mapping curve to generate a longitudinal temperature difference gradient, which is used to evaluate whether the temperature change trend of the annealing process meets the reference requirements. If the longitudinal temperature difference gradient should be close to zero, it means that the actual temperature change is consistent with the reference trend. If the gradient is large, it indicates that there may be delays or instability in the temperature control during the annealing process. Through the calculation of the multi-point temperature concentration value time series, the concentrated temperature deviation time series, and the longitudinal comparison with the reference temperature deviation, the generated longitudinal temperature difference gradient not only reflects the dynamic temperature control performance during the annealing process, but also provides accurate data support for further optimizing the annealing process, thereby improving the annealing quality and stability of photovoltaic glass.

[0032] Furthermore, the longitudinal temperature difference gradient is generated based on the longitudinal temperature difference comparison between the multi-point concentrated temperature deviation timing and the intercepted mapping curve, including: calculating the temperature deviation between any two adjacent timings in the intercepted mapping curve to generate a reference temperature deviation timing; comparing the temperature deviation values ​​in the multi-point concentrated temperature deviation timing with those in the reference temperature deviation timing to generate the longitudinal temperature difference gradient.

[0033] Specifically, for the temperature deviation between any two adjacent time series in the intercepted mapping curve, the reference temperature deviation is calculated, such as the temperature value of the intercepted mapping curve at the k+1th time series minus the temperature value of the intercepted mapping curve at the kth time series to obtain a reference temperature deviation. The reference temperature deviation time series of all adjacent time series is arranged to form a reference temperature deviation time series, and the generated reference temperature deviation time series reflects the temperature rise and fall rate under the reference state. Then, the multi-point concentrated temperature deviation time series is compared with the reference temperature deviation time series, and the difference in the temperature change rate between the two at each time series is calculated to generate a longitudinal temperature difference gradient. The longitudinal temperature difference gradient is the difference between the actual temperature change rate and the reference temperature change rate. Normal heating or cooling needs to be carried out slowly to avoid heating or cooling too fast to affect the annealing quality and defects, that is, the normal longitudinal temperature gradient should be very small. When the longitudinal temperature difference gradient should be close to zero, it indicates that the actual temperature control rate is basically the same as the reference rate. If the gradient is large, it may mean that the heating or cooling is too fast, which will have a negative impact on the annealing quality of photovoltaic glass. By generating multi-point concentrated temperature deviation time series and reference temperature deviation time series respectively, and comparing the temperature change rates of the two, a longitudinal temperature difference gradient is generated. This can effectively evaluate the stability and accuracy of the actual temperature control rate during the annealing process, and provide a reliable basis for the dynamic optimization of annealing temperature control, thereby improving the overall annealing effect of photovoltaic glass.

[0034] An annealing quality impact analysis is performed based on the transverse temperature difference gradient and the longitudinal temperature difference gradient, and the annealing temperature is regulated according to the annealing quality impact index.

[0035] In one embodiment, Figure 2 As shown, an annealing quality impact analysis is performed based on the transverse temperature difference gradient and the longitudinal temperature difference gradient, and the annealing temperature is controlled according to the annealing quality impact index, including: inputting the transverse temperature difference gradient and the longitudinal temperature difference gradient into a temperature difference impact model for analysis, and outputting an annealing quality impact index, wherein the annealing quality impact index represents the degree of negative impact on the annealing quality caused by the transverse temperature difference gradient and the longitudinal temperature difference gradient; when the annealing quality impact index is greater than or equal to a preset impact index, an optimization instruction is generated; and a temperature control optimization module is activated with the optimization instruction, and the transverse gradient and the longitudinal gradient are compensated by the temperature control optimization module to complete the annealing temperature control.

[0036] Specifically, the transverse temperature gradient and the longitudinal temperature gradient reflect the uniformity of temperature distribution at different points in the furnace and the consistency of temperature change rate on the time axis respectively. The transverse temperature gradient and the longitudinal temperature gradient are passed as input parameters to the temperature difference influence model. The model analyzes these gradient data, evaluates the degree of influence on the annealing quality, and outputs the annealing quality influence index. The annealing quality influence index is the output result of the temperature difference influence model, which is used to quantify the negative impact of the transverse temperature gradient and the longitudinal temperature gradient on the annealing quality. It can be expressed by a score or grade. The higher the index, the greater the potential threat of the current annealing temperature control state to the quality. The lower the index, the better the temperature control state and the annealing process meets the requirements. The temperature difference influence model is a similarity recognition model, which is used to evaluate the similarity between the input transverse temperature gradient and the longitudinal temperature gradient and the historical temperature difference influence samples, so as to predict the impact of the annealing process on the quality of photovoltaic glass. That is, through accurate similarity calculation and sample comparison capabilities, it is evaluated whether the temperature control state under the current process conditions meets the quality requirements. The similarity calculation method is a common technical means used by technicians in this field, such as Manhattan distance, Euclidean distance, cosine similarity, etc., which will not be repeated here. The annealing quality influencing index is compared with the preset influencing index. The preset influencing index is the quality tolerance threshold in the process standard. When the annealing quality influencing index is less than the preset influencing index, it indicates that the temperature control deviation has negligible influence on the annealing quality and does not need to be adjusted. When the annealing quality influencing index is greater than or equal to the preset influencing index, it indicates that the current temperature difference gradient may cause quality defects, and an optimization instruction is generated to instruct the annealing furnace to enter the temperature control optimization mode. The optimization instruction is such as adjusting the heating power of a certain area, starting or increasing the airflow circulation rate, etc. Based on the optimization instruction, the temperature control optimization module is activated to compensate for the lateral gradient and the longitudinal gradient, and the heating device, cooling device and airflow circulation system in the annealing furnace are adjusted to make the temperature distribution tend to be uniform and the rate of change tend to be stable. The annealing temperature control is completed to ensure the temperature uniformity and stability of the annealing process and improve the annealing quality of photovoltaic glass.

[0037] Furthermore, the transverse temperature difference gradient and the longitudinal temperature difference gradient are input into the temperature difference influence model for analysis, and the annealing quality influence index is output, including: configuring a temperature difference influence database, wherein the temperature difference influence database includes multiple groups of temperature difference influence samples, any group of temperature difference influence samples includes transverse temperature difference gradient samples, longitudinal temperature difference gradient samples and identification samples marked with corresponding annealing quality influence indicators, and the temperature difference influence database is connected to the temperature difference influence model; calling the temperature difference influence database through the temperature difference influence model, traversing the multiple groups of temperature difference influence samples to compare sample similarities, obtaining identification information corresponding to the temperature difference influence samples whose transverse temperature difference gradient similarity and longitudinal temperature difference gradient similarity are both greater than the preset similarity, and generating the annealing quality influence index.

[0038] Specifically, a temperature difference influence database is constructed, which contains a large number of historical data samples that have been verified by actual production and experiments. Each group of temperature difference influence samples consists of the following parts: transverse temperature difference gradient samples, longitudinal temperature difference gradient samples, and identification samples with corresponding annealing quality influence indicators. The transverse temperature difference gradient samples reflect the unevenness of the temperature distribution of different positions of the glass at the same time, the longitudinal temperature difference gradient samples represent the inconsistency of the glass temperature change rate on the time axis, and the identification samples of the annealing quality influence indicators are used to quantify the negative impact of the above gradients on the annealing quality, usually expressed in numerical or graded form, such as low impact, medium impact, and high impact. In addition, the temperature difference influence database is connected to the temperature difference influence model, so that the temperature difference influence model can call the sample data in real time for analysis and comparison. The transverse temperature difference gradient and longitudinal temperature difference gradient collected in real time are passed as input parameters to the temperature difference influence model. The temperature difference influence model automatically calls the sample data in the temperature difference influence database, traverses each group of samples, extracts its transverse and longitudinal gradient values, and the corresponding annealing quality influence indicators, and calculates the similarity between the real-time gradient value and the historical sample gradient value, and evaluates the matching degree between the current temperature control state and the historical data. For example, to calculate the similarity of the lateral temperature gradient: , calculate the similarity of the longitudinal temperature gradient: , filter out samples that meet the similarity requirements, that is, temperature difference-affected samples whose lateral and longitudinal gradient similarities are greater than a preset threshold, such as 90%. For the filtered high-similarity temperature difference-affected samples, extract the corresponding annealing quality-affecting index identification information, and generate the annealing quality-affecting index of the current annealing state. The annealing quality-affecting index reflects the potential threat degree of the temperature difference gradient to the annealing quality. By configuring the temperature difference-affected database, the temperature difference-affected model can call and traverse historical samples, use similarity comparison to filter out the most matching temperature difference-affected samples, and generate the quality-affecting index of the current annealing process. It can accurately evaluate the impact of the temperature control state on the annealing quality, and also provide a basis for optimizing the temperature control strategy, ensuring the stability of the annealing process and the reliability of the glass product quality.

[0039] Furthermore, the temperature control optimization module is activated with the optimization instruction, and the lateral gradient and the longitudinal gradient are compensated by the temperature control optimization module to complete the annealing temperature control, including: configuring a temperature control optimization memory library, wherein the temperature control optimization memory library includes compensation parameters corresponding to different lateral temperature difference gradients and longitudinal temperature difference gradients in the historical time, and the compensation parameters include control parameters corresponding to multiple heating devices and multiple cooling devices in the annealing furnace, and the airflow circulation device in the annealing furnace; matching the compensation parameters in the temperature control optimization memory library according to the lateral temperature difference gradient and the longitudinal temperature difference gradient to generate target compensation parameters; and controlling the annealing temperature with the target compensation parameters.

[0040] Specifically, a temperature control optimization memory is configured, and the temperature control optimization memory is a data storage module, including the optimal compensation parameter combination corresponding to different temperature gradients in the historical annealing process. The compensation parameters include the control parameters corresponding to the multiple heating devices and multiple cooling devices in the annealing furnace, and the airflow circulation device in the annealing furnace. The heating device control parameters include the power adjustment value of each heating element, which is used to compensate for the insufficient temperature of the local area in the transverse temperature gradient. The cooling device control parameters include the wind speed or cooling intensity adjustment value of the cooling device, which is used to correct the area with too high temperature. The airflow circulation device control parameters include the airflow speed, direction and cycle frequency, which are used to improve the uniformity of the overall temperature distribution in the furnace. The transverse temperature gradient and the longitudinal temperature gradient are used as indexes, input into the temperature control optimization memory, and query the historical records similar to the current annealing state. And the corresponding compensation parameters in the matched historical records are extracted as the target compensation parameters of the current annealing process. The target compensation parameters include: heating device control, cooling device control and / or airflow circulation control. The target compensation parameters are sent to the annealing furnace control system for annealing temperature control, including: dynamically adjusting the power distribution of the heating equipment, accurately controlling the temperature rise rate of the local area, adjusting the strength of the cooling device in real time, balancing the problem of overheating or overcooling, and optimizing the operation mode of the air circulation device to ensure that the heat is evenly distributed in the furnace. After the compensation is performed, the new temperature difference gradient is monitored in real time. If the gradient drops significantly and meets expectations, the compensation is completed. If the gradient does not reach the target value, continue to adjust the compensation parameters until a stable state is reached. The compensation results of the current transverse and longitudinal gradients are recorded in the temperature control optimization memory library to form a new compensation parameter sample. Through the temperature control optimization module, using the historical experience in the temperature control optimization memory library, the optimal compensation parameters can be quickly matched and dynamic and flexible regulation can be implemented, thereby effectively compensating for the transverse and longitudinal temperature difference gradients, ensuring the accuracy and uniformity of the annealing temperature, and improving the annealing quality and performance of photovoltaic glass.

[0041] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0042] This specification and the drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A temperature control method for photovoltaic glass annealing process, characterized in that: include: Obtaining glass composition structure information of target photovoltaic glass; Retrieving frequent annealing curves in a preset shared database based on the glass composition structure information to generate a reference annealing temperature curve; Determine an annealing furnace for annealing the target photovoltaic glass, input the reference annealing temperature curve into a controller of the annealing furnace for annealing control, and monitor and obtain a multi-point temperature sequence in real time; Comparing the multi-point temperature time series with the reference annealing temperature curve to identify the transverse temperature difference gradient and the longitudinal temperature difference gradient; An annealing quality impact analysis is performed based on the transverse temperature difference gradient and the longitudinal temperature difference gradient, and the annealing temperature is regulated according to the annealing quality impact index.

2. The temperature control method for photovoltaic glass annealing process according to claim 1, characterized in that: Comparing the multi-point temperature time series with the reference annealing temperature curve to identify the transverse temperature difference gradient and the longitudinal temperature difference gradient includes: Performing timing alignment, interception and mapping on the multi-point temperature timing and the reference annealing temperature curve to generate an interception mapping curve; Comparing the multi-point temperature time series with the intercepted mapping curve horizontally to generate the horizontal temperature difference gradient; The multi-point temperature time series is compared longitudinally with the intercepted mapping curve to generate the longitudinal temperature difference gradient.

3. The temperature control method for photovoltaic glass annealing process according to claim 2, characterized in that: Comparing the multi-point temperature time series with the intercepted mapping curve horizontally to generate the horizontal temperature difference gradient includes: Extracting a plurality of first point temperatures corresponding to a first time series from the multi-point temperature time series, and acquiring a first reference temperature corresponding to the first time series from the intercepted mapping curve; The temperature difference in the furnace is identified at the same time sequence between the multiple first point temperatures and the first reference temperature to generate the transverse temperature difference gradient.

4. The temperature control method for photovoltaic glass annealing process according to claim 3, characterized in that: The multi-point temperature time series is longitudinally compared with the intercepted mapping curve to generate the longitudinal temperature difference gradient, including: Performing concentrated value analysis on multiple point temperatures corresponding to any time series in the multi-point temperature time series to generate a multi-point temperature concentrated value time series; Calculating the temperature deviation between any two adjacent time series in the multi-point temperature concentration value time series to generate a multi-point concentrated temperature deviation time series; The longitudinal temperature difference gradient is generated by comparing the longitudinal temperature difference with the intercepted mapping curve according to the multi-point concentrated temperature deviation time sequence.

5. The temperature control method for photovoltaic glass annealing process according to claim 4, characterized in that: Comparing the longitudinal temperature difference with the intercepted mapping curve according to the multi-point concentrated temperature deviation time sequence to generate the longitudinal temperature difference gradient includes: Calculating the temperature deviation between any two adjacent time series in the intercepted mapping curve to generate a reference temperature deviation time series; The temperature deviation values ​​in the multi-point concentrated temperature deviation time series are compared with the reference temperature deviation time series to generate the longitudinal temperature difference gradient.

6. The temperature control method for photovoltaic glass annealing process according to claim 1, characterized in that: Performing annealing quality impact analysis based on the transverse temperature difference gradient and the longitudinal temperature difference gradient, and regulating the annealing temperature according to the annealing quality impact index, including: Input the transverse temperature difference gradient and the longitudinal temperature difference gradient into a temperature difference influence model for analysis, and output an annealing quality influence index, wherein the annealing quality influence index represents the degree of negative impact on annealing quality caused by the transverse temperature difference gradient and the longitudinal temperature difference gradient; When the annealing quality influence index is greater than or equal to the preset influence index, generating an optimization instruction; The temperature control optimization module is activated by the optimization instruction, and the lateral gradient and the longitudinal gradient are compensated by the temperature control optimization module to complete the annealing temperature control.

7. The temperature control method for photovoltaic glass annealing process according to claim 6, characterized in that: The transverse temperature difference gradient and the longitudinal temperature difference gradient are input into the temperature difference influence model for analysis, and the annealing quality influence index is output, including: Configuring a temperature difference influence database, wherein the temperature difference influence database includes multiple groups of temperature difference influence samples, any group of temperature difference influence samples includes a transverse temperature difference gradient sample, a longitudinal temperature difference gradient sample and an identification sample with a corresponding annealing quality influence index, and the temperature difference influence database is connected to the temperature difference influence model; The temperature difference influence database is called through the temperature difference influence model, and the multiple groups of temperature difference influence samples are traversed to compare sample similarities, and identification information corresponding to the temperature difference influence samples whose transverse temperature difference gradient similarity and longitudinal temperature difference gradient similarity are both greater than the preset similarity is obtained to generate the annealing quality influence index.

8. The temperature control method for photovoltaic glass annealing process according to claim 7, characterized in that: The temperature control optimization module is activated by the optimization instruction, and the lateral gradient and the longitudinal gradient are compensated by the temperature control optimization module to complete the annealing temperature control, including: Configure a temperature control optimization memory library, wherein the temperature control optimization memory library includes compensation parameters corresponding to different transverse temperature gradients and longitudinal temperature gradients in historical time, and the compensation parameters include control parameters corresponding to multiple heating devices and multiple cooling devices in the annealing furnace, and the airflow circulation device in the annealing furnace; Matching compensation parameters in the temperature control optimization memory base according to the transverse temperature difference gradient and the longitudinal temperature difference gradient to generate target compensation parameters; The annealing temperature is regulated according to the target compensation parameter.

Images