Photovoltaic automatic low-carbon production process, device and method

Abstract

The invention relates to the field of information automation, and discloses a photovoltaic automatic low-carbon production process and device. The device comprises cutting, preparing and packaging equipment and an intelligent control system, and the process covers energy consumption optimization, production scheduling, carbon emission control and the like. Energy consumption is optimized through deep learning, PID regulation and control parameters are fuzzy, and dynamic scheduling and automatic cooperation are combined. Based on a convolutional neural network and a fuzzy control formula, automation and low carbon of a production process are realized. Compared with a traditional process, the energy consumption of a unit product is reduced by 25%-35%, the efficiency is improved by 40%-50%, the carbon emission is reduced by 30%-40%, the product reject ratio is lower than 1%, and sustainable development of the photovoltaic industry is promoted.

Description

Technical Field

[0001] The invention belongs to the field of photovoltaic automation and low carbon, and specifically relates to a photovoltaic automation and low carbon production process and device. Through innovative technical means and intelligent control methods, it achieves low energy consumption, high efficiency and low carbon emissions in the photovoltaic production process, and enhances the sustainable development capabilities of the photovoltaic industry. Background Art

[0002] Against the backdrop of growing global demand for clean energy, the photovoltaic industry is developing rapidly. However, many problems still exist in the current photovoltaic production process, hindering the industry's progress towards low-carbonization and automation:

[0003] Excessive energy consumption: Traditional photovoltaic production equipment, such as those involved in wafer cutting, cell preparation, and module packaging, has low energy efficiency. For example, during the wafer cutting process, the motor drive system and cooling system of the multi-wire saw continuously consume a large amount of electricity, resulting in energy waste and high energy consumption per unit of product.

[0004] Insufficient production efficiency: The links between various production processes are not tightly connected, and the degree of automation needs to be improved. In the cell printing process, traditional printing equipment has a slow printing speed, and when the equipment switches to produce cells of different specifications, it requires a long adjustment time, which makes it difficult to meet the needs of large-scale production.

[0005] High carbon emissions: Photovoltaic production processes involve high temperatures and the use of chemical reagents, which generate large amounts of greenhouse gases such as carbon dioxide and nitrogen oxides. For example, the high-temperature sintering process for solar cells not only consumes a large amount of energy but also produces significant carbon emissions due to fuel combustion.

[0006] Lack of intelligent control: Existing production systems lack the ability to monitor and control production parameters in real time. During the component lamination process, parameters such as lamination temperature, pressure, and time cannot be automatically adjusted based on ambient temperature and humidity, as well as the actual operating status of the laminating equipment. This leads to unstable product quality and potential energy waste. Summary of the Invention

[0007] The object of the present invention is to provide a photovoltaic automated low-carbon production device, comprising:

[0008] Intelligent and efficient cutting device for high-precision cutting of silicon wafers, including a high-precision multi-wire cutting host, an intelligent cutting wire tension control unit, and a cooling circulation system that uses waste heat recovery technology;

[0009] Automated cell production line for cell preparation, including automatic loading mechanism, screen printing unit, high-temperature sintering furnace and online testing equipment;

[0010] Low-carbon component packaging equipment for photovoltaic module packaging, including laminating equipment, automatic glue machines and frame installation robots;

[0011] An intelligent control system, used for intelligent control and production scheduling of the above-mentioned equipment, includes an industrial computer, a data acquisition module, a control execution module and a communication module. The industrial computer runs intelligent control software based on deep learning and fuzzy control algorithms.

[0012] Furthermore, the high-precision multi-wire cutting main machine is equipped with an energy-saving servo motor drive system, and the energy efficiency of the servo motor is more than 30% higher than that of traditional motors.

[0013] Furthermore, the screen printing unit adopts a high-precision printing head and is equipped with an intelligent ink supply system; the high-temperature sintering furnace adopts a new energy-saving heating element combined with an intelligent temperature control system.

[0014] Furthermore, the laminating equipment adopts vacuum insulation technology and intelligent pressure and temperature control systems; the automatic gluing machine is equipped with an intelligent glue quantity control system.

[0015] Furthermore, the sampling frequency of the data acquisition module of the intelligent control system is [10-100] kHz, the response time of the control execution module is less than

[10] ms, and the communication module supports multiple communication protocols such as Ethernet and industrial field bus.

[0016] Furthermore, a photovoltaic automated low-carbon production process, using the device, includes the following steps:

[0017] Adopting a deep learning-based energy consumption optimization process, we collect equipment operating parameters, production environment parameters, and energy consumption data, build a deep learning model, establish a mapping relationship between equipment operating parameters and energy consumption through model training, and automatically adjust equipment operating parameters based on the prediction results;

[0018] Use dynamic adaptive production scheduling technology to adjust production plans and equipment operation strategies in real time based on order demand, equipment status, raw material supply, etc.

[0019] Implement low-carbon emission control processes to reduce carbon emissions during the production process;

[0020] Utilizing the intelligent parameter control process based on fuzzy PID, the temperature deviation and deviation change rate are used as the input of the fuzzy inference system. After fuzzy inference and defuzzification processing, the proportional coefficient Kp, integral coefficient Ki and differential coefficient Kd of the PID controller are adjusted in real time to achieve precise control of key parameters of production equipment.

[0021] Realize full-process automated collaborative technology to ensure automated collaborative operations in all production links.

[0022] Further, in the low carbon emission control process,

[0023] Network part, in the first layer convolution layer, feature map F l The calculation is as follows: Wherein, is the i-th convolution kernel weight of the l-th layer, is the i-th bias of the l-th layer, n l is the number of convolution kernels of the l-th layer, * represents convolution operation, and sigma is an activation function, F l-1 is the feature map of the previous layer; by training the model, a mapping relationship Y=f(X) between the input device operation parameters and the output energy consumption is established, so that the optimal device operation parameters are predicted to optimize the energy consumption.

[0024] 8. The process according to claim 6, wherein in the fuzzy PID-based parameter intelligent regulation process, the output u(t) formula of the traditional PID control is:

[0025] Take K p for example, let the error e and the error change rate be the input of the fuzzy inference system, and the adjustment amount Delta K p be the output, and the adjusted proportional coefficient K p (t) be: K p (t) = K p + Delta K p0 p

[0026] Similarly, the adjustment formula of the integral coefficient K i (t) and the differential coefficient K d (t) can be obtained, so that the adaptive adjustment of the key parameters of the production equipment is realized.

[0027] Further, in the dynamic adaptive production scheduling process, a production scheduling model is established, the production task is decomposed into a plurality of subtasks, and an optimal production scheduling scheme is found through an optimization algorithm such as a genetic algorithm.

[0028] The present application has the following beneficial effects:

[0029] ​1: Energy consumption optimization process based on deep learning: In each link of photovoltaic production, deep learning algorithms are used to analyze energy consumption data in the production process. Equipment operating parameters (such as motor speed, heating temperature, pressure, etc.), production environment parameters (such as temperature, humidity) and energy consumption data are collected to build a deep learning model. Through model training, a mapping relationship between equipment operating parameters and energy consumption is established to predict energy consumption under different parameter combinations. In actual production, the equipment operating parameters are automatically adjusted according to the prediction results to achieve energy consumption optimization. For example, in the silicon wafer cutting process, according to factors such as silicon wafer thickness and material, the cutting line speed, tension and other parameters are optimized through deep learning models to reduce cutting energy consumption.

[0030] 2. Dynamic Adaptive Production Scheduling: A dynamic adaptive production scheduling algorithm is used to adjust production plans and equipment operation strategies in real time based on order demand, equipment status, and raw material availability. A production scheduling model is established, which breaks down production tasks into multiple subtasks. Optimization algorithms, such as genetic algorithms, are used to find the optimal production scheduling solution. When equipment fails or raw material supply is delayed, the system automatically reschedules production tasks to ensure continuous and efficient production. Furthermore, the algorithm adjusts the operating sequence and timing of each device based on real-time data from the production process, reducing equipment idle time and improving overall production efficiency.

[0031] 3. Low-carbon emission control process: A series of control measures are implemented to address carbon emissions in the photovoltaic production process. During the high-temperature sintering of solar cells, the combustion system of the sintering furnace is optimized, and oxygen-enriched combustion technology is adopted to improve fuel combustion efficiency and reduce emissions of greenhouse gases such as carbon dioxide. In the chemical reagent use process, recycling technology is adopted to recover and reuse chemical reagents such as cleaning and etching solutions, reducing chemical reagent consumption and waste liquid emissions. Furthermore, waste gas treatment equipment is installed in the production workshop to purify waste gas generated during the production process to ensure that emissions meet standards.

[0032] 4: Parameter intelligent control process based on fuzzy PID: In the parameter control of photovoltaic production equipment, the fuzzy PID control algorithm is introduced. Taking the temperature control of laminating equipment as an example, the traditional PID control has poor control effect when facing complex changes in the production environment. The present invention uses the temperature deviation and the deviation change rate as the input of the fuzzy inference system, fuzzifies them through the membership function, and performs fuzzy reasoning according to the established fuzzy rule table to obtain the adjustment amount of the PID parameters. After defuzzification, precise control of the lamination temperature is achieved. Similarly, this method is also used to intelligently control the key parameters of other equipment to ensure the stability of the production process and product quality.

[0033] Invention Point 5: Fully Automated Collaborative Process: This technology enables automated collaborative operations throughout the entire photovoltaic production process. Starting with wafer loading, automatic conveying equipment sequentially transports the wafers through various stages, including cutting, cell preparation, and module packaging. Communication protocols enable data exchange and collaborative control between devices in each stage. For example, after cell preparation, automated inspection equipment transmits the test results to the module packaging equipment. The packaging equipment automatically adjusts the packaging parameters based on the cell specifications and quality to ensure the quality and efficiency of module packaging. Furthermore, the entire production process can be remotely monitored and managed from a central control room, enabling visualization and intelligent production processes. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 Overall process flow chart. DETAILED DESCRIPTION

[0035] The following embodiments of the present invention are described in further detail with reference to the accompanying drawings and examples. The following examples are used to illustrate the present invention but are not intended to limit the scope of the present invention.

[0036] Example 1

[0037] (1) Equipment preparation

[0038] Intelligent and efficient cutting device: A high-precision multi-wire cutting host is selected, and its energy-saving servo motor is equipped with a rated power of [X] kW and an energy efficiency level of one, which is 32% higher than that of traditional motors; the cutting wire tension intelligent control unit adopts a high-precision pressure sensor and servo drive system, with a tension control accuracy of ± [0.5] N; the waste heat recovery device of the cooling circulation system has a heat recovery efficiency of more than 60%, and can recover the heat generated during the cutting process to preheat the cleaning fluid to [40-50] ℃.

[0039] Automated cell preparation production line: The automatic loading mechanism uses a six-axis robot with a gripping speed of [10-15] pieces / minute; the high-precision printing head of the screen printing unit has a printing accuracy of ±

[20] μm and a printing speed of [80-100] pieces / minute. The intelligent ink supply system can automatically adjust the ink volume according to the printing pattern, and the ink volume control accuracy is ±[2]%; the high-temperature sintering furnace uses a new silicon carbide heating element, which heats up 30% faster than traditional heating elements. Combined with the intelligent temperature control system, the temperature control accuracy is ±[1]℃; the online detection equipment is equipped with a high-resolution industrial camera and an electrical performance detection module, which can complete the appearance and electrical performance detection of a cell within [5-8] seconds.

[0040] Low-carbon component packaging equipment: The lamination equipment adopts vacuum insulation technology, and the vacuum degree can reach [10^-2-10^-3]Pa. It is equipped with an intelligent pressure and temperature control system, with a pressure control accuracy of ±[0.01]MPa and a temperature control accuracy of ±[1]℃; the automatic gluing machine's glue quantity intelligent control system adopts a screw metering pump, and the glue quantity control accuracy is ±[0.1]g; the frame installation robot is equipped with a visual recognition system, with a positioning accuracy of ±[0.5]mm and an installation speed of [3-5] pieces / minute.

[0041] Intelligent control system: The industrial computer uses a high-performance multi-core processor with a main frequency of [3.5-4.0] GHz and a memory of [16-32] GB; the sampling frequency of the data acquisition module is [10-100] kHz and can be connected to various types of sensors; the control execution module uses servo drives and pneumatic actuators with a response time of less than

[10] ms; the communication module supports multiple communication protocols such as Ethernet and industrial field bus to achieve high-speed data transmission between devices.

[0042] (2) Process steps

[0043] Silicon wafer cutting

[0044] Silicon wafer loading: The silicon rods to be cut are placed on the automatic loading table, and the robotic arm accurately transports the silicon rods to the cutting station of the high-precision multi-wire cutting host.

[0045] Parameter setting: The intelligent control system automatically sets cutting parameters such as cutting line speed to [2-5] m / min and tension to [15-25] N based on information such as the material and thickness of the silicon wafer through an energy consumption optimization process based on deep learning.

[0046] Cutting Process: An energy-saving servo motor drives the cutting wire at high speed to cut the silicon ingots. An intelligent wire tension control unit monitors wire tension in real time and automatically adjusts it according to preset parameters to ensure stable and precise cutting. A cooling circulation system cools the cutting area and recovers heat generated during the cutting process.

[0047] Silicon wafer collection: After cutting is completed, the automatic unloading mechanism collects the silicon wafers and places them on the designated rack.

[0048] Cell preparation

[0049] Automatic loading: The automatic loading mechanism grabs the silicon wafer from the rack and transports it to the loading station of the screen printing unit.

[0050] Screen printing: A high-precision print head applies silver paste and other printing materials to the surface of the silicon wafer according to a preset printing pattern, forming the cell's electrodes and other structures. An intelligent ink supply system automatically adjusts the ink level based on the printed pattern to ensure printing quality and efficiency.

[0051] High-temperature sintering: The printed silicon wafers are transported to a high-temperature sintering furnace via a transmission device. The intelligent temperature control system controls the sintering temperature at [800-950]°C according to the type of cell and process requirements, and precisely controls the heating, insulation, and cooling processes to ensure good ohmic contact between the cell electrodes and the silicon wafer surface, while reducing energy consumption.

[0052] Online Inspection: After sintering, cells pass through online inspection equipment. A high-resolution industrial camera detects cosmetic defects, while an electrical performance testing module measures short-circuit current, open-circuit voltage, and other electrical parameters. This data is transmitted in real time to an intelligent control system, which classifies cells based on the test results. Qualified cells proceed to the next process, while unqualified cells are sorted out for processing.

[0053] Component packaging

[0054] Cell layout: Qualified cells are arranged according to design requirements and placed on the module backplane.

[0055] Lamination: The laid-out cell modules are transported to the lamination equipment via a conveyor. An intelligent control system, based on cell specifications and ambient temperature, utilizes fuzzy PID-based parameter control to automatically adjust the lamination temperature to [130-150]°C, the pressure to [0.8-1.2] MPa, and the lamination time to [10-15] minutes. During the lamination process, vacuum insulation technology effectively reduces heat loss, improving lamination efficiency and quality.

[0056] Gluing and frame installation: After lamination is complete, an automatic glue dispenser precisely controls the amount of glue applied to the edge of the component, based on the component size and design requirements. A frame installation robot uses a visual recognition system to accurately install the frame on the component, completing the assembly process.

[0057] Production scheduling and monitoring

[0058] Dynamic Adaptive Production Scheduling: The intelligent control system receives real-time information on order requirements, equipment status, and raw material inventory. Through dynamic adaptive production scheduling, it utilizes optimization algorithms such as genetic algorithms to generate an optimal production scheduling plan. Based on this plan, it adjusts the operating sequence, timing, and production task allocation of each device to ensure efficient production.

[0059] Real-time Monitoring and Adjustment: Throughout the production process, the data acquisition module collects operating parameters and production data from each device in real time and transmits it to an industrial computer. The intelligent control system displays production status in real time via a monitoring interface, allowing operators to remotely monitor the production process. In the event of an abnormality, such as equipment failure or parameter deviation, the system automatically issues an alarm and makes adjustments based on pre-set processing strategies, or prompts the operator to intervene.

[0060] Measures such as waste heat recovery from intelligent and efficient cutting devices, energy-saving heating elements in automated cell preparation production lines, and energy consumption optimization processes in intelligent control systems have reduced unit product energy consumption by 25%-35% in the photovoltaic production process, effectively reducing energy consumption.

[0061] Improved production efficiency: The high-speed printing of the automated cell preparation production line, the real-time optimization of the dynamic adaptive production scheduling process, and the seamless connection of the full-process automated collaborative process have increased overall production efficiency by 40%-50%, meeting the needs of large-scale production.

[0062] Reducing carbon emissions: Measures such as optimization of the combustion system, recycling of chemical reagents, and purification of waste gas in the low-carbon emission control process have reduced carbon emissions in the photovoltaic production process by 30%-40%, helping to achieve the low-carbon development goals of the photovoltaic industry.

[0063] Improve product quality: The fuzzy PID-based intelligent parameter control process ensures precise control of equipment operating parameters. The real-time monitoring of online detection equipment and the automated collaborative operation of the entire process effectively improve the stability of product quality and reduce the product defect rate to below 1%.

[0064] The embodiments of the present invention are presented for purposes of illustration and description and are not intended to be exhaustive or to limit the invention to the disclosed forms. Many modifications and variations will be apparent to those skilled in the art. The embodiments are chosen and described in order to better illustrate the principles of the invention and its practical application and to enable those skilled in the art to understand the invention and design various embodiments with various modifications as suited for specific applications.

Claims

1. A photovoltaic automated low-carbon production device, characterized in that: include: Intelligent and efficient cutting device for high-precision cutting of silicon wafers, including a high-precision multi-wire cutting host, an intelligent cutting wire tension control unit, and a cooling circulation system that uses waste heat recovery technology; Automated cell production line for cell preparation, including automatic loading mechanism, screen printing unit, high-temperature sintering furnace and online testing equipment; Low-carbon component packaging equipment for photovoltaic module packaging, including laminating equipment, automatic glue machines and frame installation robots; An intelligent control system, used for intelligent control and production scheduling of the above-mentioned equipment, includes an industrial computer, a data acquisition module, a control execution module and a communication module. The industrial computer runs intelligent control software based on deep learning and fuzzy control algorithms.

2. The device according to claim 1, characterized in that The high-precision multi-wire cutting main machine is equipped with an energy-saving servo motor drive system, and the energy efficiency of the servo motor is improved by more than 30% compared with traditional motors.

3. The device according to claim 1, characterized in that The screen printing unit adopts a high-precision printing head and is equipped with an intelligent ink supply system; the high-temperature sintering furnace adopts a new energy-saving heating element combined with an intelligent temperature control system.

4. The device according to claim 1, characterized in that The laminating equipment adopts vacuum insulation technology and intelligent pressure and temperature control systems; the automatic gluing machine is equipped with an intelligent glue quantity control system.

5. The device according to claim 1, characterized in that The sampling frequency of the data acquisition module of the intelligent control system is [10-100] kHz, the response time of the control execution module is less than [10] ms, and the communication module supports multiple communication protocols such as Ethernet and industrial field bus.

6. A photovoltaic automated low-carbon production process, characterized in that: The device according to any one of claims 1 to 5 comprises the following steps: Adopting a deep learning-based energy consumption optimization process, we collect equipment operating parameters, production environment parameters, and energy consumption data, build a deep learning model, establish a mapping relationship between equipment operating parameters and energy consumption through model training, and automatically adjust equipment operating parameters based on the prediction results; Use dynamic adaptive production scheduling technology to adjust production plans and equipment operation strategies in real time based on order demand, equipment status, raw material supply, etc. Implement low-carbon emission control processes to reduce carbon emissions during the production process; Utilizing the intelligent parameter control process based on fuzzy PID, the temperature deviation and deviation change rate are used as the input of the fuzzy inference system. After fuzzy inference and defuzzification processing, the proportional coefficient Kp, integral coefficient Ki and differential coefficient Kd of the PID controller are adjusted in real time to achieve precise control of key parameters of production equipment. Realize full-process automated collaborative technology to ensure automated collaborative operations in all production links.

7. The process according to claim 6, characterized in that In the low carbon emission control process, In the network part, at the lth convolution layer, the feature map F l The calculation is as follows: in, is the weight of the i-th convolution kernel in the l-th layer, is the i-th bias of the l-th layer, n l is the number of convolution kernels in the first layer, * represents the convolution operation, σ is the activation function, F l-1 is the feature map of the previous layer; by training the model, a mapping relationship Y = f(X) between the input device operating parameters and the output energy consumption is established, thereby predicting the optimal device operating parameters to optimize energy consumption.

8. The process according to claim 6, characterized in that In the parameter intelligent control process based on fuzzy PID, the traditional PID control output u(t) formula is: K p For example, let the error e and the error change rate is the input of the fuzzy inference system, K p Adjustment amount ΔK p For output, the adjusted proportional coefficient K p (t) is: K p (t) = K p0 +ΔK p Similarly, the integral coefficient K can be obtained i (t) and differential coefficient K d (t) is used to adjust the key parameters of the production equipment to achieve adaptive adjustment.

9. The process according to claim 6, characterized in that In the dynamic adaptive production scheduling process, a production scheduling model is established, the production task is decomposed into multiple subtasks, and the optimal production scheduling solution is found through optimization algorithms such as genetic algorithms.

Images