Process and system for treating silane waste gas in photovoltaic cell production process

Abstract

The invention discloses a process and a system for treating silane waste gas in a photovoltaic cell production process. The system comprises a waste gas adsorption tank, a direct-fired incinerator, a preheater, a cyclone dust collector, a post-treatment unit and a control unit which are connected in sequence, to-be-treated silane waste gas enters the waste gas adsorption tank to be treated, then is input into the preheater to be preheated and then enters the direct-fired incinerator to be mixed with fuel and air entering the direct-fired incinerator to be subjected to oxidative incineration, and incineration tail gas enters the preheater to be subjected to heat exchange with the silane waste gas discharged from the waste gas adsorption tank and then enters the cyclone dust collector to be subjected to dust removal. And the dedusted waste gas finally enters a post-treatment unit. The silane removal efficiency is high, and up-to-standard discharge can be realized; according to the invention, the anti-clogging capability is strong, the use of TO effectively replaces the RTO treatment mode, the SiO2 does not cause the clogging condition to the TO furnace, and the problem that the silane oxidation product is easy to clog the equipment is solved.

Description

Technical Field

[0001] The present invention relates to the field of waste gas treatment, and in particular to a treatment process and system for silane waste gas in the production process of photovoltaic cells. Background Art

[0002] Photovoltaic power generation, as a new energy power generation technology, is widely recognized by the society for its green and clean characteristics. In order to reduce the cost of electricity, achieve grid parity, and meet the needs of global energy transformation, solar cell technology and market have been developing rapidly.

[0003] Monocrystalline silicon solar cells, represented by passivated emitter and rear cell (PERC), heterojunction with intrinsic thin-layer (HJT) solar cells and tunnel oxide passivated contact (TOPCon) solar cells, have attracted widespread attention. TOPCon cells are a type of photovoltaic crystalline silicon cells. In recent years, they have been gradually adopted by industry enterprises due to their obvious advantages such as high conversion efficiency, low attenuation performance, and high mass production cost performance. The theoretical limit efficiency of TOPCon cells is as high as 28.7%, which is the technology closest to the theoretical limit efficiency of crystalline silicon solar cells (29.43%), much higher than PERC (24.5%), and has great research and development potential. These technologies currently occupy more than 90% of the market share. At the same time, new perovskite solar cells (PSCs) are also in the commercial verification stage. With the proposal of China's "dual carbon" goals, it is urgent to establish reasonable evaluation standards and certification systems to promote the healthy development of the photovoltaic industry. Therefore, the impact of the photovoltaic industry on the environment needs further research and investigation.

[0004] The core processes required for TOPCon technology are tunnel oxide layer preparation and polysilicon deposition, which require LPCVD. The process gases of LPCVD include O2, SiH4 and N2. There are multiple pipes for exhaust gas discharge, and O2 and SiH4 exist simultaneously in the exhaust gas pipeline during operation. Silane is a colorless gas with a foul odor at room temperature and pressure. It is easy to ignite at room temperature and can burn explosively in air or halogen gas. Even if it is diluted with other gases, it can still spontaneously combust if the concentration is not low enough. Silane can still ignite when it contains 2% in argon, 2.5% in nitrogen, and 1% in hydrogen. Silane is non-flammable when the concentration is less than 1%, spontaneously combusts when it is greater than 3%, and may burn when it is 1%-3%. Therefore, how to effectively reduce the emission of LPCVD exhaust gas has become a major issue in the development of photovoltaic cell production at this stage.

[0005] Incineration treatment technology is currently the most advanced, thoroughly effective and highly recognized harmless treatment technology, which has great advantages in both environmental protection and safety, including direct-fired incinerator (TO), heat exchange catalytic oxidizer (CO), regenerative high-temperature incinerator (RTO), and regenerative catalytic oxidizer (RCO). Since the catalyst in the catalytic oxidizer is easily poisoned and loses its activity under certain specific conditions, the equipment maintenance cost is high during operation. Therefore, when treating organic waste gas, TO and RTO are mostly used for incineration technology. In addition, because RTO has the characteristics of high oxidation temperature and high purification efficiency, it also makes up for the shortcomings of TO with high energy consumption and low heat recovery efficiency due to the presence of ceramic heat storage body, so it is widely used in the treatment of organic waste gas in various industries. However, when treating waste gas containing organic silicon such as silane, the shortcomings of RTO technology are gradually exposed. Analysis of the reasons: The products of silane during high-temperature oxidation are CO2, H2O and SiO2. SiO2 exists in solid form and is easy to form crystals on the surface of ceramic thermal storage bodies. Microscopically, the aluminosilicates that constitute the ceramic thermal storage bodies are similar to SiO2 crystals, which make the two tightly combined. Macroscopically, SiO2 grows and accumulates layer by layer on the surface of the ceramic thermal storage bodies, occupying the heat transfer channels of the thermal storage bodies, resulting in serious consequences such as increased pressure in the RTO system, poor heat transfer effect, and higher exhaust temperature. After the disadvantages of RTO treatment of silane waste gas were exposed, the industry no longer recommends the use of RTO incineration technology for the treatment of waste gas containing silane, but prefers TO, which is not easily blocked by silicon powder.

[0006] Therefore, it is necessary to improve the existing technology to provide a more reliable solution. Summary of the invention

[0007] The technical problem to be solved by the present invention is to provide a treatment process and system for silane waste gas in the production process of photovoltaic cells in view of the deficiencies in the above-mentioned prior art.

[0008] In order to solve the above technical problems, the technical solution adopted by the present invention is as follows: In a first aspect of the present invention, a system for treating silane waste gas in the production process of photovoltaic cells is provided, comprising a waste gas adsorption tank, a direct-fired incinerator, a preheater, a cyclone dust collector, a post-treatment unit and a control unit connected in sequence;

[0009] The silane waste gas to be treated enters the waste gas adsorption tank for treatment, is input into the preheater for preheating, and then enters the direct-fired incinerator, where it is mixed with the fuel and air entering the direct-fired incinerator and oxidized and incinerated. The incineration exhaust gas enters the preheater, exchanges heat with the silane waste gas discharged from the waste gas adsorption tank, and then enters the cyclone dust collector for dust removal. The waste gas after dust removal finally enters the post-processing unit.

[0010] Preferably, the adsorbent filled in the exhaust gas adsorption tank is activated carbon.

[0011] Preferably, the post-processing unit comprises a fan and a chimney which are sequentially connected to the cyclone dust collector.

[0012] Preferably, the direct-fired incinerator is provided with a fuel delivery pipe and an air delivery pipe for inputting fuel and air respectively, and the fuel delivery pipe and the air delivery pipe are provided with a fuel supply solenoid valve and an air supply solenoid valve respectively.

[0013] Preferably, the preheater is provided with a heat medium inlet pipe, a heat medium outlet pipe, a refrigerant inlet pipe and a refrigerant outlet pipe; the silane waste gas enters the preheater through the refrigerant inlet pipe, is then discharged through the refrigerant outlet pipe and enters the direct-fired incinerator; the combustion exhaust gas in the direct-fired incinerator enters the preheater through the heat medium inlet pipe, is then discharged through the heat medium outlet pipe and enters the cyclone dust collector.

[0014] Preferably, a temperature sensor and a flow meter are provided on the refrigerant outlet pipe;

[0015] The control unit is connected to the temperature sensor, the flow meter, the fuel supply solenoid valve, and the air supply solenoid valve.

[0016] Preferably, the control unit includes a control module and an incineration parameter optimization module. The incineration parameter optimization module obtains optimization results of the furnace temperature in the direct-fired incinerator, the fuel flow rate and the air flow rate entering the direct-fired incinerator based on the detection results of the temperature sensor and the flow meter. The control module controls the fuel supply solenoid valve and the air supply solenoid valve based on the optimization results.

[0017] In a second aspect of the present invention, a process for treating silane waste gas in the production process of photovoltaic cells is provided, wherein the silane waste gas is treated using the system as described above, and the process comprises the following steps:

[0018] S1. Inputting the silane waste gas to be treated into the waste gas adsorption tank at a gas velocity lower than 0.6 m / s for adsorption treatment;

[0019] S2. The silane waste gas discharged from the waste gas adsorption tank enters the preheater for preheating, and then enters the direct-fired incinerator. Fuel and air are simultaneously input into the direct-fired incinerator through the fuel delivery pipe and the air delivery pipe. The silane waste gas is mixed with the fuel and air and burned in the direct-fired incinerator. The combustion tail gas enters the preheater, exchanges heat with the incoming silane waste gas, and then enters the cyclone dust collector for dust removal;

[0020] S3. The exhaust gas discharged from the cyclone dust collector enters the chimney and is discharged under the action of the fan.

[0021] Preferably, in step S2, the incineration parameter optimization module in the control unit adopts a method based on machine learning to obtain the optimized value Tly of the furnace temperature in the direct-fired incinerator, the optimized value Qry of the fuel flow entering the direct-fired incinerator, and the optimized value Qay of the air flow entering the direct-fired incinerator according to the temperature value T0 of the silane waste gas detected by the temperature sensor and the flow rate Q0 of the silane waste gas detected by the flowmeter. The control module controls the furnace temperature in the direct-fired incinerator to reach Tly, and controls the fuel supply solenoid valve and the air supply solenoid valve to make the fuel flow entering the direct-fired incinerator Qry and the air flow Qay.

[0022] Preferably, the incineration parameter optimization module is constructed by the following method:

[0023] 1) Construct training dataset V:

[0024] 1-1) Define the raw material parameters including: P the temperature value T and flow rate Q of the silane waste gas entering the direct-fired incinerator, the incineration parameters O including: the furnace temperature Tl of the direct-fired incinerator, the fuel flow rate Qr entering the direct-fired incinerator, and the air flow rate Qa entering the direct-fired incinerator;

[0025] Fix the raw material parameter P, change the value of the incineration parameter O, obtain the silane concentration in the incineration tail gas of the direct-fired incinerator corresponding to each incineration parameter under the current raw material parameters, and then obtain the incineration parameter corresponding to the minimum silane concentration, recorded as Oy, Oy is the optimized incineration parameter corresponding to the raw material parameter P, combine P and Oy to obtain a training data v;

[0026] 1-2) According to the method of 1-1), the raw material parameter P is changed to obtain the corresponding optimized incineration parameters under each raw material parameter P, and each raw material parameter P is combined with the corresponding optimized incineration parameter into a training data, and all the training data are combined to obtain a training data set V;

[0027] 2) Using the training data set V, taking the raw material parameter P as input and the corresponding optimized incineration parameter as output, the RBF network model is trained, and after the training is completed, the incineration parameter optimization module is obtained.

[0028] The beneficial effects of the present invention are:

[0029] (1) The silane removal efficiency of the present invention is high and can achieve standard emission;

[0030] (2) Strong anti-clogging ability. The use of TO effectively replaces the RTO treatment method. SiO2 will not cause clogging of the TO furnace, solving the problem that silane oxidation products are easy to clog the equipment;

[0031] (3) The waste heat recovery efficiency is considerable and the resource utilization is reasonable. Heat recovery measures are adopted at the TO furnace outlet. The heat recovered by its preheater is directly used to preheat the TO furnace inlet flue gas, which can effectively reduce the heating fuel consumption.

[0032] (4) Rational use of existing energy sources, such as biogas, for heating in the plant area can reduce the consumption of natural gas and other energy sources, reduce system operating costs, and improve the economic benefits of the system.

[0033] (5) The present invention adopts an incineration parameter optimization module based on a machine learning algorithm, which can obtain the incineration parameters required to achieve a relatively optimal incineration efficiency according to the actual values ​​of the temperature and flow rate of the silane waste gas entering the direct-fired incinerator, thereby improving the silane removal rate; the present invention can well adapt to the fluctuations in the flow rate and temperature of the silane waste gas, and can timely optimize and adjust the incineration parameters according to the actual situation to ensure the replacement of the incineration effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 It is a structural schematic diagram of a system for treating silane waste gas in a photovoltaic cell production process of the present invention;

[0035] Figure 2 It is a schematic diagram of the principle structure of the control unit of the present invention;

[0036] Figure 3 The present invention is a flow chart of a process for treating silane waste gas in the production process of photovoltaic cells;

[0037] Figure 4 It is a flow chart for constructing the incineration parameter optimization module in the present invention;

[0038] Figure 5 This is a flow chart for constructing the training data set V in the present invention.

[0039] Description of reference numerals:

[0040] 1—waste gas adsorption tank; 2—direct-fired incinerator; 3—preheater; 4—cyclone dust collector; 5—fan; 6—chimney; 7—control unit;

[0041] 21 - fuel delivery pipe; 22 - air delivery pipe; 23 - fuel supply solenoid valve; 24 - air supply solenoid valve;

[0042] 31—heat medium inlet pipe; 32—heat medium outlet pipe; 33—refrigerant inlet pipe; 34—refrigerant outlet pipe; 35—temperature sensor; 36—flow meter;

[0043] 71—control module; 72—incineration parameter optimization module. DETAILED DESCRIPTION

[0044] The present invention is further described in detail below in conjunction with embodiments so that those skilled in the art can implement the invention with reference to the description.

[0045] It should be understood that the terms such as “having”, “including” and “comprising” used herein do not exclude the existence or addition of one or more other elements or combinations thereof.

[0046] The test methods used in the following examples are conventional methods unless otherwise specified. The materials and reagents used in the following examples are all commercially available unless otherwise specified. In the following examples, if no specific conditions are specified, the experiments were carried out under conventional conditions or conditions recommended by the manufacturer. The reagents or instruments used, if the manufacturer is not specified, are all conventional products that can be purchased commercially.

[0047] The present invention provides a silane waste gas treatment system in the photovoltaic cell production process, comprising a waste gas adsorption tank 1, a direct-fired incinerator 2, a preheater 3, a cyclone dust collector 4, a post-processing unit and a control unit 7 connected in sequence;

[0048] The silane waste gas to be treated enters the waste gas adsorption tank 1 for treatment, is input into the preheater 3 for preheating, and then enters the direct-fired incinerator 2, is mixed with the fuel and air entering the direct-fired incinerator 2, and is oxidized and incinerated. The incineration tail gas enters the preheater 3, exchanges heat with the silane waste gas discharged from the waste gas adsorption tank 1, and then enters the cyclone dust collector 4 for dust removal. The waste gas after dust removal finally enters the post-processing unit.

[0049] In a preferred embodiment, the adsorbent filled in the exhaust gas adsorption tank 1 is granular activated carbon. The front end of the system uses activated carbon to adsorb dust and harmful gases in the exhaust gas, reducing the impact of harmful gases in the system on silane combustion, and can extend the service life of the entire process.

[0050] In a preferred embodiment, the post-processing unit includes a fan 5 and a chimney 6 which are sequentially connected to the cyclone dust collector 4 .

[0051] In a preferred embodiment, natural gas and biogas are selected as heating fuels.

[0052] The silane waste gas enters the preheater 3 for preheating, and then enters the direct-fired incinerator 2, which saves the fuel consumption of the burner; a cyclone dust collector 4 is used at the tail to treat the SiO2 powder produced after combustion, and then the treated waste gas enters the chimney 6 through the fan 5 and is discharged into the atmosphere.

[0053] The use of cyclone dust collector 4 can greatly reduce the impact of SiO2 dust on the pipeline, improve the heat recovery efficiency, make the oxidation system of silane and air more stable, control the combustion temperature, and also improve the safety performance of the entire process, further improving the purification rate of silane waste gas.

[0054] In a preferred embodiment, the direct-fired incinerator 2 is provided with a fuel delivery pipe 21 and an air delivery pipe 22 for inputting fuel and air respectively, and the fuel delivery pipe 21 and the air delivery pipe 22 are provided with a fuel supply solenoid valve 23 and an air supply solenoid valve 24 respectively.

[0055] In a preferred embodiment, the preheater 3 is provided with a heat medium inlet pipe 31, a heat medium outlet pipe 32, a refrigerant inlet pipe 33 and a refrigerant outlet pipe 34. The silane waste gas enters the preheater 3 through the refrigerant inlet pipe 33, and then is discharged through the refrigerant outlet pipe 34 and enters the direct-fired incinerator 2; the combustion exhaust gas in the direct-fired incinerator 2 enters the preheater 3 through the heat medium inlet pipe 31, and then is discharged through the heat medium outlet pipe 32 and enters the cyclone dust collector 4.

[0056] In a preferred embodiment, a temperature sensor 35 and a flow meter 36 are provided on the refrigerant outlet pipe 34;

[0057] The control unit 7 is connected to the temperature sensor 35 , the flow meter 36 , the fuel supply solenoid valve 23 , and the air supply solenoid valve 24 .

[0058] In a preferred embodiment, the control unit 7 includes a control module 71 and an incineration parameter optimization module 72. The incineration parameter optimization module 72 obtains the optimization results of the furnace temperature in the direct-fired incinerator 2, the fuel flow rate and the air flow rate entering the direct-fired incinerator 2 based on the detection results of the temperature sensor 35 and the flow meter 36. The control module 71 controls the fuel supply solenoid valve 23 and the air supply solenoid valve 24 based on the optimization results.

[0059] The present invention also provides a process for treating silane waste gas in the production process of photovoltaic cells, which uses the above system to treat the silane waste gas. The process includes the following steps:

[0060] S1, inputting the silane waste gas to be treated into the waste gas adsorption tank 1 at a gas velocity lower than 0.6 m / s for adsorption treatment;

[0061] S2, the silane waste gas discharged from the waste gas adsorption tank 1 enters the preheater 3 for preheating, and then enters the direct-fired incinerator 2, and the fuel and air are synchronously input into the direct-fired incinerator 2 through the fuel delivery pipe 21 and the air delivery pipe 22, and the silane waste gas is mixed with the fuel and the air, and is incinerated in the direct-fired incinerator 2. The incineration tail gas enters the preheater 3, and after heat exchange with the incoming silane waste gas, enters the cyclone dust collector 4 for dust removal;

[0062] S3. The exhaust gas discharged from the cyclone dust collector 4 enters the chimney 6 under the action of the fan 5 and is discharged.

[0063] The process of the present invention firstly allows the tail gas in the production process of photovoltaic cells to enter the waste gas adsorption tank 1, and after the waste gas is adsorbed by activated carbon, the remaining silane waste gas enters the preheater 3 for preheating, and then is sent to TO oxidation incineration; the silane enters the incinerator and is fully mixed with nitrogen, and is in contact with the introduced compressed air to burn, and the silicon dioxide dust is burned to form a deposition and discharged from the slag discharge port at the bottom of the combustion chamber; after the system is in operation, the silane waste gas can be effectively and safely treated, and the waste gas treatment can meet the relevant local standards.

[0064] In a preferred embodiment, in step S2, the incineration parameter optimization module 72 in the control unit 7 adopts a method based on machine learning to obtain the optimized value Tly of the furnace temperature in the direct-fired incinerator 2, the optimized value Qry of the fuel flow entering the direct-fired incinerator 2, and the optimized value Qay of the air flow entering the direct-fired incinerator 2 according to the temperature value T0 of the silane waste gas detected by the temperature sensor 35 and the flow rate Q0 of the silane waste gas detected by the flowmeter 36. The control module 71 controls the furnace temperature in the direct-fired incinerator 2 to reach Tly, and controls the fuel supply solenoid valve 23 and the air supply solenoid valve 24 to make the fuel flow entering the direct-fired incinerator 2 Qry and the air flow Qay.

[0065] In a preferred embodiment, the incineration parameter optimization module 72 is constructed by the following method:

[0066] 1) Construct training dataset V:

[0067] 1-1) Define the raw material parameters including: P the temperature value T and flow rate Q of the silane waste gas entering the direct-fired incinerator 2, the incineration parameters O including: the furnace temperature Tl of the direct-fired incinerator 2, the fuel flow rate Qr entering the direct-fired incinerator 2, and the air flow rate Qa entering the direct-fired incinerator 2;

[0068] Fix the raw material parameter P, change the value of the incineration parameter O, obtain the silane concentration in the incineration tail gas of the direct-fired incinerator 2 corresponding to each incineration parameter under the current raw material parameters, and then obtain the incineration parameter corresponding to the minimum silane concentration, recorded as Oy, Oy is the optimized incineration parameter corresponding to the raw material parameter P, combine P and Oy to obtain a training data v;

[0069] 1-2) According to the method of 1-1), the raw material parameter P is changed to obtain the corresponding optimized incineration parameters under each raw material parameter P, and each raw material parameter P is combined with the corresponding optimized incineration parameter into a training data, and all the training data are combined to obtain a training data set V;

[0070] 2) Using the training data set V, taking the raw material parameters P as input and the corresponding optimized incineration parameters as output, the RBF network model is trained, and after the training is completed, an incineration parameter optimization module 72 is obtained.

[0071] Since the flow rate of silane waste gas in the production process of photovoltaic cells will fluctuate to a certain extent, the temperature of the silane waste gas after preheating by the preheater 3 is also prone to fluctuations. These fluctuations will affect the incineration effect of the direct-fired incinerator 2. In order to cope with these effects, it is necessary to adjust the relevant incineration parameters, such as the furnace temperature of the direct-fired incinerator 2, the fuel flow rate entering the direct-fired incinerator 2, and the air flow rate entering the direct-fired incinerator 2. The control and adjustment of these parameters are easy to achieve, but how to adjust these parameters to obtain a higher incineration efficiency is a difficult point. The reason is that the relationship between the furnace temperature of the direct-fired incinerator 2, the fuel flow rate entering the direct-fired incinerator 2, the air flow rate entering the direct-fired incinerator 2, the temperature and flow rate of the silane waste gas after preheating by the preheater 3 and the incineration efficiency is nonlinear and difficult to summarize through mathematical expressions. In the present invention, by adopting the incineration parameter optimization module 72 based on the machine learning algorithm, according to the study of previous data, it is possible to obtain the incineration parameters required to achieve the relatively optimal incineration efficiency according to the actual values ​​of the temperature and flow rate of the silane waste gas entering the direct-fired incinerator 2: the furnace temperature of the direct-fired incinerator 2, the fuel flow rate entering the direct-fired incinerator 2, and the air flow rate entering the direct-fired incinerator 2, and then control the operation with the optimized incineration parameters through the control module 71, so as to achieve the relatively optimal incineration efficiency and improve the silane removal rate; therefore, the present invention can adapt well to the fluctuations in the flow rate and temperature of the silane waste gas, and can timely optimize and adjust the incineration parameters according to the actual situation to ensure the replacement of the incineration effect.

[0072] The above is the overall concept of the present invention, and detailed embodiments and comparative examples are provided below on the basis of the overall concept of the present invention to further illustrate the present invention.

[0073] Example 1

[0074] A silane waste gas treatment system in the production process of photovoltaic cells, comprising a waste gas adsorption tank 1, a direct-fired incinerator 2, a preheater 3, a cyclone dust collector 4, a post-processing unit and a control unit 7 connected in sequence;

[0075] In this embodiment, the adsorbent filled in the exhaust gas adsorption tank 1 is activated carbon. The post-processing unit includes a fan 5 and a chimney 6 which are sequentially connected to the cyclone dust collector 4.

[0076] In this embodiment, the direct-fired incinerator 2 is provided with a fuel delivery pipe 21 and an air delivery pipe 22 for inputting fuel and air respectively. The fuel delivery pipe 21 and the air delivery pipe 22 are provided with a fuel supply solenoid valve 23 and an air supply solenoid valve 24 respectively.

[0077] In this embodiment, the preheater 3 is provided with a heat medium inlet pipe 31, a heat medium outlet pipe 32, a refrigerant inlet pipe 33 and a refrigerant outlet pipe 34. The silane waste gas enters the preheater 3 through the refrigerant inlet pipe 33, and then is discharged from the refrigerant outlet pipe 34 and enters the direct-fired incinerator 2; the combustion exhaust gas in the direct-fired incinerator 2 enters the preheater 3 through the heat medium inlet pipe 31, and then is discharged from the heat medium outlet pipe 32 and enters the cyclone dust collector 4.

[0078] In this embodiment, a temperature sensor 35 and a flow meter 36 are provided on the refrigerant outlet pipe 34;

[0079] The control unit 7 is connected to the temperature sensor 35 , the flow meter 36 , the fuel supply solenoid valve 23 , and the air supply solenoid valve 24 .

[0080] In this embodiment, the control unit 7 includes a control module 71 and an incineration parameter optimization module 72. The incineration parameter optimization module 72 obtains the optimization results of the furnace temperature in the direct-fired incinerator 2, the fuel flow rate and the air flow rate entering the direct-fired incinerator 2 based on the detection results of the temperature sensor 35 and the flow meter 36. The control module 71 controls the fuel supply solenoid valve 23 and the air supply solenoid valve 24 based on the optimization results.

[0081] In this embodiment, a process for treating silane waste gas in the production process of photovoltaic cells is also provided, which uses the above system to treat the silane waste gas, and the process includes the following steps:

[0082] S1, inputting the silane waste gas to be treated into the waste gas adsorption tank 1 at a gas velocity lower than 0.6 m / s for adsorption treatment;

[0083] S2, the silane waste gas discharged from the waste gas adsorption tank 1 enters the preheater 3 for preheating, and then enters the direct-fired incinerator 2, and the fuel and air are synchronously input into the direct-fired incinerator 2 through the fuel delivery pipe 21 and the air delivery pipe 22, and the silane waste gas is mixed with the fuel and the air, and is incinerated in the direct-fired incinerator 2. The incineration tail gas enters the preheater 3, and after heat exchange with the incoming silane waste gas, enters the cyclone dust collector 4 for dust removal; the silica dust generated by the incineration is discharged from the slag discharge port at the bottom of the combustion chamber of the direct-fired incinerator 2;

[0084] S3. The exhaust gas discharged from the cyclone dust collector 4 enters the chimney 6 under the action of the fan 5 and is discharged.

[0085] In this embodiment, in step S2, the incineration parameter optimization module 72 in the control unit 7 adopts a method based on machine learning to obtain the optimized value Tly of the furnace temperature in the direct-fired incinerator 2, the optimized value Qry of the fuel flow entering the direct-fired incinerator 2, and the optimized value Qay of the air flow entering the direct-fired incinerator 2 according to the temperature value T0 of the silane waste gas detected by the temperature sensor 35 and the flow rate Q0 of the silane waste gas detected by the flowmeter 36. The control module 71 controls the furnace temperature in the direct-fired incinerator 2 to reach Tly, and controls the fuel supply solenoid valve 23 and the air supply solenoid valve 24 to make the fuel flow entering the direct-fired incinerator 2 Qry and the air flow Qay.

[0086] In this embodiment, the incineration parameter optimization module 72 is constructed by the following method:

[0087] 1) Construct training dataset V:

[0088] 1-1) Define the raw material parameters including: P the temperature value T and flow rate Q of the silane waste gas entering the direct-fired incinerator 2, the incineration parameters O including: the furnace temperature Tl of the direct-fired incinerator 2, the fuel flow rate Qr entering the direct-fired incinerator 2, and the air flow rate Qa entering the direct-fired incinerator 2;

[0089] Fix the raw material parameter P, change the value of the incineration parameter O, obtain the silane concentration in the incineration tail gas of the direct-fired incinerator 2 corresponding to each incineration parameter under the current raw material parameters, and then obtain the incineration parameter corresponding to the minimum silane concentration, recorded as Oy, Oy is the optimized incineration parameter corresponding to the raw material parameter P, combine P and Oy to obtain a training data v;

[0090] 1-2) According to the method of 1-1), the raw material parameter P is changed to obtain the corresponding optimized incineration parameters under each raw material parameter P, and each raw material parameter P is combined with the corresponding optimized incineration parameter into a training data, and all the training data are combined to obtain a training data set V;

[0091] 2) Using the training data set V, taking the raw material parameters P as input and the corresponding optimized incineration parameters as output, the RBF network model is trained, and after the training is completed, an incineration parameter optimization module 72 is obtained.

[0092] Processing performance test:

[0093] 1. Test example:

[0094] The silane waste gas from the production process of photovoltaic cells of a certain company was used, and the silane concentration was 3000mgC / m 3 , as the treatment object, the process in Example 1 is applied for treatment, and the initial process parameters are as follows:

[0095] Silane exhaust gas intake volume 20000Nm 3 / h, the gas velocity entering the exhaust gas adsorption tank 1 is controlled to be 0.5m / s, the exhaust gas temperature after the waste heat of the preheater 3 fluctuates within the range of 350-400℃, and the furnace temperature is set to fluctuate within the range of 850-900℃, and the residence time is 1.5s. After stable operation, the incineration parameters are optimized by the incineration parameter optimization module 72 in the control unit 7, and the control module 71 controls according to the optimization results; after stable operation for 12h, the silane concentration in the exhaust gas discharged by the cyclone dust collector 4 is measured, and the silane removal rate is calculated to be 99.7%.

[0096] 2. Comparative Example

[0097] The only difference from the test example is that the above initial process parameters are always used for operation, the control unit 7 does not work, and after stable operation for 12 hours, the silane concentration in the exhaust gas discharged by the cyclone dust collector 4 is measured, and the silane removal rate is calculated to be 98.2%. It can be seen that the optimization of the incineration parameters through the incineration parameter optimization model can effectively improve the optimization of the incineration parameters.

[0098] Although the embodiments of the present invention have been disclosed as above, they are not limited to the applications listed in the specification and the implementation modes. They can be fully applied to various fields suitable for the present invention. For those familiar with the art, additional modifications can be easily implemented. Therefore, without departing from the general concept defined by the claims and the scope of equivalents, the present invention is not limited to specific details.

Claims

1. A system for treating silane waste gas in the production process of photovoltaic cells, characterized in that: It includes an exhaust gas adsorption tank, a direct-fired incinerator, a preheater, a cyclone dust collector, a post-processing unit and a control unit connected in sequence; The silane waste gas to be treated enters the waste gas adsorption tank for treatment, is input into the preheater for preheating, and then enters the direct-fired incinerator, where it is mixed with the fuel and air entering the direct-fired incinerator and oxidized and incinerated. The incineration exhaust gas enters the preheater, exchanges heat with the silane waste gas discharged from the waste gas adsorption tank, and then enters the cyclone dust collector for dust removal. The waste gas after dust removal finally enters the post-processing unit.

2. The silane waste gas treatment system in the photovoltaic cell production process according to claim 1 is characterized in that: The adsorbent filled in the exhaust gas adsorption tank is activated carbon.

3. The silane waste gas treatment system in the photovoltaic cell production process according to claim 2, characterized in that: The post-processing unit includes a fan and a chimney which are sequentially connected to the cyclone dust collector.

4. The silane waste gas treatment system in the photovoltaic cell production process according to claim 3, characterized in that: The direct-fired incinerator is provided with a fuel delivery pipe and an air delivery pipe for respectively inputting fuel and air. The fuel delivery pipe and the air delivery pipe are respectively provided with a fuel supply solenoid valve and an air supply solenoid valve.

5. The silane waste gas treatment system in the photovoltaic cell production process according to claim 4, characterized in that: The preheater is provided with a heat medium inlet pipe, a heat medium outlet pipe, a refrigerant inlet pipe and a refrigerant outlet pipe. The silane waste gas enters the preheater through the refrigerant inlet pipe, and is then discharged through the refrigerant outlet pipe and enters the direct-fired incinerator; the combustion exhaust gas in the direct-fired incinerator enters the preheater through the heat medium inlet pipe, and is then discharged through the heat medium outlet pipe and enters the cyclone dust collector.

6. The silane waste gas treatment system in the photovoltaic cell production process according to claim 5, characterized in that: The refrigerant outlet pipe is provided with a temperature sensor and a flow meter; The control unit is connected to the temperature sensor, the flow meter, the fuel supply solenoid valve, and the air supply solenoid valve.

7. The silane waste gas treatment system in the photovoltaic cell production process according to claim 6, characterized in that: The control unit includes a control module and an incineration parameter optimization module. The incineration parameter optimization module obtains the optimization results of the furnace temperature in the direct-fired incinerator, the fuel flow rate and the air flow rate entering the direct-fired incinerator according to the detection results of the temperature sensor and the flow meter. The control module controls the fuel supply solenoid valve and the air supply solenoid valve according to the optimization results.

8. A process for treating silane waste gas in the production process of photovoltaic cells, characterized in that: The silane waste gas is treated by a system as described in any one of claims 6 to 7, and the process comprises the following steps: S1. Inputting the silane waste gas to be treated into the waste gas adsorption tank at a gas velocity lower than 0.6 m / s for adsorption treatment; S2. The silane waste gas discharged from the waste gas adsorption tank enters the preheater for preheating, and then enters the direct-fired incinerator. Fuel and air are simultaneously input into the direct-fired incinerator through the fuel delivery pipe and the air delivery pipe. The silane waste gas is mixed with the fuel and air and burned in the direct-fired incinerator. The combustion tail gas enters the preheater, exchanges heat with the incoming silane waste gas, and then enters the cyclone dust collector for dust removal; S3. The exhaust gas discharged from the cyclone dust collector enters the chimney and is discharged under the action of the fan.

9. The process for treating silane waste gas in the production process of photovoltaic cells according to claim 8, characterized in that: In step S2, the incineration parameter optimization module in the control unit adopts a method based on machine learning to obtain the optimized value Tly of the furnace temperature in the direct-fired incinerator, the optimized value Qry of the fuel flow entering the direct-fired incinerator, and the optimized value Qay of the air flow entering the direct-fired incinerator according to the temperature value T0 of the silane waste gas detected by the temperature sensor and the flow rate Q0 of the silane waste gas detected by the flowmeter. The control module controls the furnace temperature in the direct-fired incinerator to reach Tly, and controls the fuel supply solenoid valve and the air supply solenoid valve to make the fuel flow entering the direct-fired incinerator Qry and the air flow Qay.

10. The process for treating silane waste gas in the production process of photovoltaic cells according to claim 9, characterized in that: The incineration parameter optimization module is constructed by the following method: 1) Construct training dataset V: 1-1) Define the raw material parameters including: P the temperature value T and flow rate Q of the silane waste gas entering the direct-fired incinerator, the incineration parameters O including: the furnace temperature Tl of the direct-fired incinerator, the fuel flow rate Qr entering the direct-fired incinerator, and the air flow rate Qa entering the direct-fired incinerator; Fix the raw material parameter P, change the value of the incineration parameter O, obtain the silane concentration in the incineration tail gas of the direct-fired incinerator corresponding to each incineration parameter under the current raw material parameters, and then obtain the incineration parameter corresponding to the minimum silane concentration, recorded as Oy, Oy is the optimized incineration parameter corresponding to the raw material parameter P, combine P and Oy to obtain a training data v; 1-2) According to the method of 1-1), the raw material parameter P is changed to obtain the corresponding optimized incineration parameters under each raw material parameter P, and each raw material parameter P is combined with the corresponding optimized incineration parameter into a training data, and all the training data are combined to obtain a training data set V; 2) Using the training data set V, taking the raw material parameter P as input and the corresponding optimized incineration parameter as output, the RBF network model is trained, and after the training is completed, the incineration parameter optimization module is obtained.

Images