A method for continuously extruding and preparing copper and copper alloy microchannel flat tubes

Abstract

The present invention relates to the technical field of copper product preparation, and in particular to a continuous extrusion preparation method for copper and copper alloy microchannel flat tubes. When extrusion welding is performed on a microchannel flat tube by an extrusion welding device, real-time welding parameters of the welding interface are collected at several preset time nodes, and the collected real-time welding parameters are de-redundanted to obtain the real-time welding parameters after de-redundancy; the state of the welding interface of the microchannel flat tube after a preset time period in the future is obtained according to the real-time welding parameters after de-redundancy and in combination with a performance prediction model; if the state of the welding interface of the microchannel flat tube after the preset time period in the future is a sudden change state, the welding parameters are regulated and processed. The present invention can effectively improve the intelligence level of the microchannel flat tube extrusion welding preparation process, reduce product quality problems caused by sudden changes in welding interface performance, and improve production efficiency and product quality stability.

Description

Technical Field

[0001] The invention relates to the technical field of copper product preparation, in particular to a method for continuously extruding and preparing a copper and copper alloy microchannel flat tube. Background Art

[0002] In recent years, with the growing demand for high-performance heat dissipation materials in the fields of electronic information, aerospace, etc., copper and copper alloy microchannel flat tubes have become a highly-regarded heat dissipation solution due to their excellent thermal conductivity, good processing performance and high strength. Traditional microchannel flat tube preparation methods, such as welding and tube expansion, have problems such as difficult to control weld quality and easy to produce stress concentration, which are difficult to meet the needs of high-performance heat dissipation. Continuous extrusion technology has become a very promising method for preparing microchannel flat tubes because it can achieve efficient, continuous and automated production and can effectively control the quality of the welding interface. However, in the continuous extrusion process, the influence of welding parameters on the quality of the welding interface is complex, and a little carelessness may cause defects in the welding interface, such as lack of fusion, pores, cracks, etc., thereby affecting the performance of the microchannel flat tube. Therefore, how to monitor and predict the state of the welding interface in real time, and adjust the welding parameters in time according to the prediction results to ensure the quality of the welding interface, has become the key to improving the efficiency and quality of continuous extrusion preparation of copper and copper alloy microchannel flat tubes.

[0003] At present, the monitoring of the state of the welding interface mainly relies on offline detection methods, such as metallographic microscopes, scanning electron microscopes, etc., which makes the detection efficiency low and difficult to meet the real-time requirements of continuous extrusion production. In addition, most of the existing methods lack the ability to predict the future state of the welding interface, and cannot predict in advance the impact of small changes in welding parameters on the quality of the welding interface, making it difficult to take effective preventive measures. Therefore, it is urgent to develop an intelligent control method that can predict the future state of the welding interface in real time and automatically adjust the welding parameters according to the prediction results, so as to ensure the welding quality of copper and copper alloy microchannel flat tubes, improve production efficiency, reduce production costs, and meet the growing market demand. Summary of the invention

[0004] The invention overcomes the shortcomings of the prior art and provides a method for continuously extruding and preparing a copper and copper alloy microchannel flat tube.

[0005] To achieve the above-mentioned purpose, the technical solution adopted by the present invention is:

[0006] The invention discloses a method for continuously extruding and preparing a copper and copper alloy microchannel flat tube, comprising the following steps:

[0007] Acquire performance change data of the welding interface under various historical welding parameter combinations, and build a performance prediction model of the welding interface according to the performance change data of the welding interface under various historical welding parameter combinations;

[0008] When extrusion welding is performed on the microchannel flat tube by the extrusion welding equipment, real-time welding parameters of the welding interface are collected at a number of preset time nodes, and the collected real-time welding parameters are de-redundanted to obtain the real-time welding parameters after de-redundancy.

[0009] According to the real-time welding parameters after redundancy removal and in combination with the performance prediction model, the state of the welding interface of the microchannel flat tube after a preset time period in the future is obtained;

[0010] If the state of the welding interface of the microchannel flat tube is normal after a preset time period in the future, no adjustment or control is performed on the welding parameters;

[0011] If the state of the welding interface of the microchannel flat tube after a preset time period in the future is a sudden change state, the welding parameters are adjusted and processed.

[0012] Furthermore, the performance change data of the welding interface under various historical welding parameter combinations are obtained, and a performance prediction model of the welding interface is constructed according to the performance change data of the welding interface under various historical welding parameter combinations, specifically:

[0013] Acquire performance change data of the welding interface under various historical welding parameter combinations through a big data network, and acquire the status of the performance change data;

[0014] Constructing a conditional random field, importing the performance change data of the welding interface under various historical welding parameter combinations into the conditional random field; and taking various historical welding parameter combinations as quantitative nodes and the performance change data of each time stamp as variable nodes;

[0015] According to the state of the performance change data, the conditional probability of each variable node transferring from a normal state to a mutation state under the conditions of each quantitative node is calculated;

[0016] When the conditional probability is greater than the preset probability threshold, the corresponding variable node is marked as a mutation state node; when the conditional probability is not greater than the preset probability threshold, the corresponding variable node is marked as a normal state node;

[0017] Directly connect each mutation state node, normal state node and quantitative node to obtain a topological structure diagram of the conditional random field; construct a graph embedding model based on a neural network, and embed the topological structure diagram into the graph embedding model;

[0018] Using the neuron structure of the neural network, based on the directed connection relationship between quantitative nodes, mutation state nodes and normal state nodes, the neuron connection weights are continuously adjusted through the forward propagation process of multi-layer neurons to encode the topological structure; until the learning parameters meet the preset requirements, the performance prediction model of the welding interface is obtained;

[0019] Among them, welding parameters include temperature, pressure and extrusion speed; state conditions include normal state and sudden change state; performance change data include tensile strength, yield strength, hardness, grain size, defect concentration, thermal conductivity and electrical conductivity.

[0020] Furthermore, the collected real-time welding parameters are de-redundanted to obtain the real-time welding parameters after de-redundancy, which are specifically:

[0021] The wavelet transform algorithm is introduced to perform discrete wavelet decomposition on the collected real-time welding parameters according to the preset wavelet basis and decomposition layer number to obtain the wavelet coefficients of each real-time welding parameter;

[0022] Construct a wavelet coefficient matrix according to the wavelet coefficients of each real-time welding parameter; calculate the coefficient difference between every two wavelet coefficients in the wavelet coefficient matrix;

[0023] Preset a deviation value threshold, and compare the coefficient difference between every two wavelet coefficients in the wavelet coefficient matrix with the preset deviation value threshold;

[0024] If the coefficient difference between two wavelet coefficients in the wavelet coefficient matrix is ​​not greater than the preset deviation value threshold, it means that the real-time welding parameters corresponding to the two wavelet coefficients are redundant, and any redundant real-time welding parameter is screened out;

[0025] The iteration is stopped until all the wavelet coefficient pairs in the wavelet coefficient matrix are judged and analyzed, and the real-time welding parameters after redundancy removal are obtained.

[0026] Furthermore, the state of the welding interface of the microchannel flat tube after a preset time period in the future is obtained based on the real-time welding parameters after redundancy removal and combined with the performance prediction model, specifically:

[0027] The real-time welding parameters after redundancy removal are sorted based on the acquisition timestamp to obtain the real-time welding parameters based on the time sequence;

[0028] Importing the real-time welding parameters based on the time series into the performance prediction model for prediction, and obtaining the predicted performance change data of the welding interface of the microchannel flat tube after a preset time period in the future;

[0029] Acquire preset preparation process information of the microchannel flat tube, and acquire the state of the welding interface of the microchannel flat tube after a preset time period in the future according to the preset preparation process information;

[0030] The state of the welding interface after a preset time period in the future includes a normal state and a sudden change state.

[0031] Furthermore, if the state of the welding interface of the microchannel flat tube after a preset time period in the future is a sudden change state, the welding parameters are regulated, specifically:

[0032] If the state of the welding interface of the microchannel flat tube after a preset time period in the future is a sudden change state, then the preset extrusion welding process information of the microchannel flat tube is obtained;

[0033] Acquire preset performance change data of the welding interface of the microchannel flat tube after a preset time period in the future according to the preset extrusion welding process information;

[0034] Calculate the absolute value of the data difference between each preset performance change data and the corresponding predicted performance change data of the welding interface of the microchannel flat tube after a preset time period in the future, and obtain the data deviation value between each preset performance change data and the corresponding predicted performance change data;

[0035] Preset the deviation value range of various performance change data; determine whether the data deviation value between each preset performance change data and the corresponding predicted performance change data is within the corresponding deviation value range;

[0036] If the data deviation value between a certain preset performance change data and the corresponding predicted performance change data is not within the corresponding deviation value range, the corresponding performance change data of the welding interface is calibrated as the sudden performance change data after the preset time period in the future, and the sudden performance change data of the welding interface of the microchannel flat tube after the preset time period in the future is obtained;

[0037] If the data deviation value between a certain preset performance change data and the corresponding predicted performance change data is within the corresponding deviation value range, the corresponding performance change data of the welding interface is calibrated as the normal performance change data after the future preset time period.

[0038] Furthermore, if the state of the welding interface of the microchannel flat tube after a preset time period in the future is a sudden change state, the welding parameters are regulated, and the following steps are also included:

[0039] Prefabricate in advance the welding parameter control scheme corresponding to various sudden performance change data of the welding interface after a preset time period in the future;

[0040] Constructing a control scheme pairing database, and importing the welding parameter control schemes corresponding to various sudden performance change data of the welding interface that are prefabricated in advance after a preset time period in the future into the control scheme pairing database; and regularly updating the control scheme pairing database;

[0041] Obtaining sudden performance change data of the welding interface of the microchannel flat tube after a preset time period in the future, importing the sudden performance change data of the welding interface of the microchannel flat tube after the preset time period in the future into the control scheme pairing database for matching, and obtaining a corresponding welding parameter control scheme;

[0042] The acquired welding parameter control scheme is transmitted to the control terminal of the extrusion welding equipment, so as to control the corresponding real-time welding parameters of the welding chamber based on the welding parameter control scheme to avoid sudden performance change data at the welding interface.

[0043] Furthermore, in the process of adjusting the welding parameters, the temperature and pressure in the welding chamber need to meet the following conditions: in, is the pressure in the welding chamber, is the temperature in the welding chamber; is a constant.

[0044] The present invention also discloses a continuous extrusion preparation system for copper and copper alloy microchannel flat tubes, which comprises a memory and a processor. A program for the continuous extrusion preparation method for copper and copper alloy microchannel flat tubes is stored in the memory. When the program for the continuous extrusion preparation method for copper and copper alloy microchannel flat tubes is executed by the processor, any one of the steps of the continuous extrusion preparation method for copper and copper alloy microchannel flat tubes is implemented.

[0045] The present invention solves the technical defects existing in the background technology, and has the following beneficial effects: obtaining the performance change data of the welding interface under various historical welding parameter combinations, and constructing the performance prediction model of the welding interface according to the performance change data of the welding interface under various historical welding parameter combinations; when the microchannel flat tube is extruded and welded by the extrusion welding equipment, the real-time welding parameters of the welding interface are collected at several preset time nodes, and the collected real-time welding parameters are de-redundanted to obtain the real-time welding parameters after de-redundancy; according to the real-time welding parameters after de-redundancy and combined with the performance prediction model, the state of the welding interface of the microchannel flat tube after the preset time period in the future is obtained; if the state of the welding interface of the microchannel flat tube after the preset time period in the future is a sudden change state, the welding parameters are regulated and processed. The present invention can effectively improve the intelligence level of the microchannel flat tube extrusion welding preparation process, reduce product quality problems caused by sudden changes in the performance of the welding interface, and improve production efficiency and product quality stability. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, drawings of other embodiments can be obtained based on these drawings without paying creative work.

[0047] Figure 1 This is a flow chart of the first method of the continuous extrusion preparation method of copper and copper alloy microchannel flat tubes;

[0048] Figure 2 This is a flow chart of the second method of the continuous extrusion preparation method of copper and copper alloy microchannel flat tubes;

[0049] Figure 3 This is the system block diagram of the continuous extrusion preparation system for copper and copper alloy microchannel flat tubes. DETAILED DESCRIPTION

[0050] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0051] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0052] The present invention discloses a method for continuously extruding and preparing a copper and copper alloy microchannel flat tube. Figure 1 As shown, the following steps are included:

[0053] S102: Acquire performance change data of the welding interface under various historical welding parameter combinations, and construct a performance prediction model of the welding interface according to the performance change data of the welding interface under various historical welding parameter combinations;

[0054] S104: when extrusion welding is performed on the microchannel flat tube by the extrusion welding equipment, real-time welding parameters of the welding interface are collected at a plurality of preset time nodes, and the collected real-time welding parameters are de-redundanted to obtain the real-time welding parameters after de-redundancy;

[0055] S106: Obtaining the state of the welding interface of the microchannel flat tube after a preset time period in the future according to the real-time welding parameters after redundancy removal and in combination with the performance prediction model;

[0056] S108: If the state of the welding interface of the microchannel flat tube after a preset time period in the future is normal, no adjustment or control is performed on the welding parameters;

[0057] S110: If the state of the welding interface of the microchannel flat tube after a preset time period in the future is a sudden change state, the welding parameters are adjusted.

[0058] It should be noted that if the predicted state of the welding interface after a preset time period in the future is a normal state, it means that the current welding process is proceeding normally within the expected range, and there is no need to adjust the welding parameters, so as to maintain the continuity and stability of the production process. On the contrary, if the predicted result is a sudden change, it means that the performance of the welding interface may undergo sudden and undesirable changes. At this time, it is necessary to adjust the welding parameters to avoid quality problems and ensure the welding quality of the microchannel flat tube. Through the continuous extrusion preparation method of copper and copper alloy microchannel flat tubes, historical data is used to construct a performance prediction model, real-time welding parameters are collected and processed to predict the future state of the welding interface, and whether to adjust the welding parameters is determined according to the prediction results. It can effectively improve the intelligence level of the microchannel flat tube extrusion welding preparation process, reduce product quality problems caused by sudden changes in the performance of the welding interface, improve production efficiency and product quality stability, and reduce production costs at the same time, making the entire production process more controllable and efficient.

[0059] Furthermore, the performance change data of the welding interface under various historical welding parameter combinations are obtained, and a performance prediction model of the welding interface is constructed according to the performance change data of the welding interface under various historical welding parameter combinations, specifically:

[0060] Acquire performance change data of the welding interface under various historical welding parameter combinations through a big data network, and acquire the status of the performance change data;

[0061] Constructing a conditional random field, importing the performance change data of the welding interface under various historical welding parameter combinations into the conditional random field; and taking various historical welding parameter combinations as quantitative nodes and the performance change data of each time stamp as variable nodes;

[0062] According to the state of the performance change data, the conditional probability of each variable node transferring from a normal state to a mutation state under the conditions of each quantitative node is calculated;

[0063] When the conditional probability is greater than the preset probability threshold, the corresponding variable node is marked as a mutation state node; when the conditional probability is not greater than the preset probability threshold, the corresponding variable node is marked as a normal state node;

[0064] Directly connect each mutation state node, normal state node and quantitative node to obtain a topological structure diagram of the conditional random field; construct a graph embedding model based on a neural network, and embed the topological structure diagram into the graph embedding model;

[0065] Among them, according to the association logic between the mutation state node and the normal state node under each quantitative node, taking the quantitative node as the starting point, according to the state transfer relationship of the performance change data, the mutation state node and the normal state node are respectively connected to the quantitative node in a directed manner, thereby constructing a topological structure diagram of the conditional random field;

[0066] Using the neuron structure of the neural network, based on the directed connection relationship between quantitative nodes, mutation state nodes and normal state nodes, the neuron connection weights are continuously adjusted through the forward propagation process of multi-layer neurons to encode the topological structure; until the learning parameters meet the preset requirements, the performance prediction model of the welding interface is obtained;

[0067] Among them, welding parameters include temperature, pressure and extrusion speed; state conditions include normal state and sudden change state; performance change data include tensile strength, yield strength, hardness, grain size, defect concentration, thermal conductivity and electrical conductivity.

[0068] It should be noted that the performance change data of the welding interface under different historical welding parameter combinations (temperature, pressure, extrusion speed) are first collected using the big data network, such as tensile strength, yield strength and other performance data. At the same time, the state conditions (normal or mutation) corresponding to these performance data are obtained. This step provides basic data for the subsequent model construction. The big data network can cover rich historical information and help to comprehensively analyze various situations in the welding process. Construct a conditional random field and import the performance change data into it. Set the historical welding parameter combination as a quantitative node, and set the performance change data corresponding to the timestamp as a variable node. This setting method reasonably associates the welding parameters and performance data in the model structure, which can reflect the relationship between performance changes over time under different parameter combinations. According to the state of the performance data, the conditional probability of the variable node changing from the normal state to the mutation state under each quantitative node is calculated. By comparing with the preset probability threshold, the variable node is marked as a mutation state node or a normal state node. This helps to identify situations where performance data may mutate under a specific welding parameter combination, and provides a basis for the subsequent construction of the topological structure of the model. The mutation state node, the normal state node and the quantitative node are connected in a directed manner to obtain the topological structure diagram of the conditional random field. This topological structure reflects the logical relationship between nodes and is an abstract representation of the relationship between various factors in the welding process. A graph embedding model is constructed based on a neural network, and the topological structure graph is embedded in it. This process allows the model to learn the rules behind the node relationship, continuously optimize the model parameters until the preset requirements are met, and finally obtain a performance prediction model.

[0069] Through the above series of steps, a welding interface performance prediction model based on big data and neural network was constructed. The model can make full use of the parameter combination, performance change data and its status in the historical welding data, and mine the potential law of performance change under different welding parameter combinations. Through the construction and learning of conditional random fields and graph embedding models, the model can accurately predict the performance status of the welding interface under different welding parameters, and warn of possible performance mutations in advance, thereby providing strong technical support for optimizing welding processes and improving product quality.

[0070] Furthermore, the collected real-time welding parameters are de-redundanted to obtain the real-time welding parameters after de-redundancy, such as Figure 2 As shown, specifically:

[0071] S202: introducing a wavelet transform algorithm, performing discrete wavelet decomposition on the collected real-time welding parameters according to a preset wavelet basis and decomposition layer number, and obtaining wavelet coefficients of each real-time welding parameter;

[0072] S204: constructing a wavelet coefficient matrix according to the wavelet coefficients of each real-time welding parameter; calculating the coefficient difference between every two wavelet coefficients in the wavelet coefficient matrix;

[0073] S206: Preset a deviation value threshold, and compare the coefficient difference between every two wavelet coefficients in the wavelet coefficient matrix with the preset deviation value threshold;

[0074] S208: If the coefficient difference between two wavelet coefficients in the wavelet coefficient matrix is ​​not greater than the preset deviation value threshold, it means that the real-time welding parameters corresponding to the two wavelet coefficients are redundant, and any redundant real-time welding parameter is screened out;

[0075] S210: until all the wavelet coefficient pairs in the wavelet coefficient matrix are judged and analyzed, the iteration is stopped to obtain the real-time welding parameters after redundancy removal.

[0076] It should be noted that the selection of wavelet basis and the setting of the number of decomposition layers are determined according to the characteristics of welding parameters and the subsequent analysis requirements. Through this decomposition, the welding parameters can be converted from the time domain to multi-scale spaces such as the frequency domain to obtain the wavelet coefficients of each real-time welding parameter. These wavelet coefficients contain the information of the welding parameters at different scales. A wavelet coefficient matrix is ​​constructed based on the obtained wavelet coefficients of each real-time welding parameter. This matrix can comprehensively reflect the relationship between all real-time welding parameters at different scales. Then, the coefficient difference between each two wavelet coefficients in the matrix is ​​calculated, and these differences can be used to measure the similarity or difference between different wavelet coefficients. A deviation value threshold is preset, and the coefficient difference between each two wavelet coefficients is compared with the threshold. If the coefficient difference between two wavelet coefficients is not greater than the preset deviation value threshold, it means that the real-time welding parameters corresponding to the two wavelet coefficients are similar to some extent and there is redundancy. At this time, any real-time welding parameter with redundancy is screened out to reduce the redundancy of the data. According to the above method, each wavelet coefficient pair in the wavelet coefficient matrix is ​​judged and analyzed in turn until all wavelet coefficient pairs are processed, the iteration is stopped, and finally the real-time welding parameters after redundancy removal are obtained. This process ensures that all welding parameters that may have redundancy are comprehensively checked and processed.

[0077] Through the above steps, the collected real-time welding parameters are de-redundanted, which can effectively remove the redundant information in the real-time welding parameters. The wavelet transform algorithm is used to analyze the welding parameters at multiple scales, and the wavelet coefficient matrix is ​​constructed. The redundant parameters are accurately identified and screened out by comparing the coefficient difference with the threshold. It helps to reduce the amount of data, improve the efficiency and accuracy of subsequent analysis, prediction or control operations based on welding parameters, make the processing results better reflect the essential characteristics of the welding process, and avoid interference and misjudgment caused by redundant data.

[0078] Furthermore, the state of the welding interface of the microchannel flat tube after a preset time period in the future is obtained based on the real-time welding parameters after redundancy removal and combined with the performance prediction model, specifically:

[0079] The real-time welding parameters after redundancy removal are sorted based on the acquisition timestamp to obtain the real-time welding parameters based on the time sequence;

[0080] Importing the real-time welding parameters based on the time series into the performance prediction model for prediction, and obtaining the predicted performance change data of the welding interface of the microchannel flat tube after a preset time period in the future;

[0081] Acquire preset preparation process information of the microchannel flat tube, and acquire the state of the welding interface of the microchannel flat tube after a preset time period in the future according to the preset preparation process information;

[0082] The state of the welding interface after a preset time period in the future includes a normal state and a sudden change state.

[0083] It should be noted that, first, after obtaining the real-time welding parameters after redundancy removal, these parameters are sorted according to the acquisition timestamp. The acquisition timestamp records the acquisition order of each real-time welding parameter. By sorting, these parameters can be arranged in chronological order to obtain real-time welding parameters based on time series. This step is to make the order of data conform to the actual progress order of the welding process, so as to accurately perform subsequent prediction and analysis. The real-time welding parameters based on time series are imported into the pre-built performance prediction model. This performance prediction model is constructed based on the performance change data under the historical welding parameter combination. It can predict the predicted performance change data of the welding interface of the microchannel flat tube after a preset time period in the future according to the input real-time welding parameters through the algorithm and parameter relationship within the model. These predicted performance change data cover the changes in performance indicators such as tensile strength and yield strength. At the same time, the preset preparation process information of the microchannel flat tube is obtained. The preset preparation process information includes the process parameter requirements in the normal preparation process such as the ideal temperature range, pressure range, extrusion speed, etc. Based on these preset preparation process information and the predicted performance change data obtained previously, it is possible to determine the state of the welding interface of the microchannel flat tube after a preset time period in the future, that is, to determine whether it is in a normal state (meeting the preset process requirements and various performance indicators are stable) or a sudden state (performance indicators may suddenly change and deviate from the preset process requirements).

[0084] Through the above steps, the real-time welding parameters after redundancy removal, the performance prediction model and the preset preparation process information can be comprehensively considered to accurately judge the state of the welding interface of the microchannel flat tube after a preset time period in the future. This helps to know the state trend of the welding interface in advance during the continuous extrusion preparation of the microchannel flat tube, so as to timely discover possible abnormal situations (such as sudden changes), thereby providing a basis for adjusting the welding parameters or taking other intervention measures to ensure the preparation quality and production efficiency of the microchannel flat tube.

[0085] Furthermore, if the state of the welding interface of the microchannel flat tube after a preset time period in the future is a sudden change state, the welding parameters are regulated, specifically:

[0086] If the state of the welding interface of the microchannel flat tube after a preset time period in the future is a sudden change state, obtaining preset extrusion welding process information of the microchannel flat tube; obtaining preset performance change data of the welding interface of the microchannel flat tube after a preset time period in the future according to the preset extrusion welding process information;

[0087] Calculate the absolute value of the data difference between each preset performance change data and the corresponding predicted performance change data of the welding interface of the microchannel flat tube after a preset time period in the future, and obtain the data deviation value between each preset performance change data and the corresponding predicted performance change data;

[0088] Preset the deviation value range of various performance change data; determine whether the data deviation value between each preset performance change data and the corresponding predicted performance change data is within the corresponding deviation value range;

[0089] If the data deviation value between a certain preset performance change data and the corresponding predicted performance change data is not within the corresponding deviation value range, the corresponding performance change data of the welding interface is calibrated as the sudden performance change data after the preset time period in the future, and the sudden performance change data of the welding interface of the microchannel flat tube after the preset time period in the future is obtained;

[0090] If the data deviation value between a certain preset performance change data and the corresponding predicted performance change data is within the corresponding deviation value range, the corresponding performance change data of the welding interface is calibrated as the normal performance change data after the future preset time period.

[0091] It should be noted that when it is determined that the welding interface of the microchannel flat tube is in a sudden change state after a preset time period in the future, the preset extrusion welding process information of the microchannel flat tube is first obtained. This information includes various process parameter requirements for the welding interface of the microchannel flat tube in the ideal extrusion welding process, such as a suitable temperature range, pressure range, extrusion speed, etc., and the ideal performance change data corresponding to these process parameters, that is, the preset performance change data. These preset performance change data are expected to be obtained under normal process conditions, covering performance indicators such as tensile strength and yield strength. Next, the absolute value of the data difference between each preset performance change data and the corresponding predicted performance change data after the preset time period in the future is calculated to obtain the data deviation value. This deviation value reflects the degree of deviation between the predicted performance and the ideal performance. The predicted performance change data is obtained by the performance prediction model before, and the preset performance change data is obtained based on the ideal process. The deviation between the two can reflect the difference between the actual situation and the expected situation. The deviation value range of various performance change data is preset. Different performance change data may have different acceptable deviation ranges, which depends on factors such as process requirements and product quality standards. Then determine whether the data deviation value between each preset performance change data and the corresponding predicted performance change data is within the corresponding deviation value range. This step is to more accurately determine which performance change data deviate greatly from the normal range and which are within the acceptable range. If the data deviation value between a certain preset performance change data and the corresponding predicted performance change data is not within the corresponding deviation value range, the corresponding performance change data of the welding interface is calibrated as the sudden performance change data after the preset time period in the future. This indicates that the performance indicator may undergo a large abnormal change after the preset time period in the future. On the contrary, if the deviation value is within the corresponding deviation value range, it is calibrated as the normal performance change data after the preset time period in the future, indicating that the performance indicator is within an acceptable fluctuation range.

[0092] Through the above steps, it is possible to accurately find out which performance change data of the microchannel flat tube welding interface may have a sudden change after a preset time period in the future, and which are within the normal range. This helps to accurately identify the specific performance factors that cause the welding interface to be in a sudden state, and provides a detailed basis for the subsequent targeted regulation and control of welding parameters, so that the welding parameters can be adjusted more effectively, avoiding undesirable performance changes in the welding interface, and ensuring the extrusion welding quality of the microchannel flat tube.

[0093] Furthermore, if the state of the welding interface of the microchannel flat tube after a preset time period in the future is a sudden change state, the welding parameters are regulated, and the following steps are also included:

[0094] Prefabricate in advance the welding parameter control scheme corresponding to various sudden performance change data of the welding interface after a preset time period in the future;

[0095] Constructing a control scheme pairing database, and importing the welding parameter control schemes corresponding to various sudden performance change data of the welding interface that are prefabricated in advance after a preset time period in the future into the control scheme pairing database; and regularly updating the control scheme pairing database;

[0096] Obtaining sudden performance change data of the welding interface of the microchannel flat tube after a preset time period in the future, importing the sudden performance change data of the welding interface of the microchannel flat tube after the preset time period in the future into the control scheme pairing database for matching, and obtaining a corresponding welding parameter control scheme;

[0097] The acquired welding parameter control scheme is transmitted to the control terminal of the extrusion welding equipment, so as to control the corresponding real-time welding parameters of the welding chamber based on the welding parameter control scheme to avoid sudden performance change data at the welding interface.

[0098] It should be noted that, first of all, the relevant technical personnel formulate corresponding welding parameter control schemes in advance for various sudden performance change data that may appear in the welding interface after a preset time period in the future. This requires an in-depth understanding of the relationship between various performance changes and welding parameters during the welding process. For example, if it is predicted that the tensile strength may decrease suddenly, possible control schemes include adjusting parameters such as welding temperature, pressure or extrusion speed to improve the tensile strength. These control schemes are based on the experience and theoretical knowledge of the continuous extrusion preparation process of copper and copper alloy microchannel flat tubes.

[0099] A control scheme matching database is constructed, and the prefabricated control scheme is imported into it. The function of this database is to establish the correspondence between the sudden performance change data and the welding parameter control scheme, so as to facilitate subsequent rapid query and matching. The control scheme matching database is regularly updated to adapt to the changing production conditions, raw material characteristics or more precise process requirements. For example, with the application of new copper alloy materials or the upgrade of extrusion equipment, the original control scheme may need to be adjusted, and updating the database can ensure that it always contains the most effective control scheme. After obtaining the sudden performance change data of the welding interface of the microchannel flat tube after a preset time period in the future, these data are imported into the control scheme matching database for matching. Through the preset correspondence in the database, the corresponding welding parameter control scheme can be quickly and accurately obtained. This process realizes the rapid conversion from problem (sudden performance change data) to solution (welding parameter control scheme), and improves the efficiency of dealing with sudden changes in the welding interface. Finally, the obtained welding parameter control scheme is transmitted to the control terminal of the extrusion welding equipment. The extrusion welding equipment controls the corresponding real-time welding parameters of the welding chamber according to the received control scheme. For example, if the control plan requires an increase in the welding temperature, the equipment will adjust the power and other parameters of the heating device accordingly. The purpose of this is to avoid sudden changes in the performance of the welding interface, thereby ensuring the welding quality of the microchannel flat tube and improving the stability and reliability of the product.

[0100] Through a series of steps such as prefabricating the control scheme in advance, building and updating the database, matching and obtaining the control scheme, and controlling the welding parameters, it is possible to quickly and effectively deal with the performance mutation that may occur at the welding interface during the continuous extrusion preparation of the microchannel flat tube. This method improves the controllability and stability of the production process, reduces product quality problems caused by the sudden change of the welding interface performance, and also improves production efficiency, reduces production costs, and ensures that the quality of the microchannel flat tube meets the requirements.

[0101] Furthermore, in the process of adjusting the welding parameters, the temperature and pressure in the welding chamber need to meet the following conditions: in, is the pressure in the welding chamber, is the temperature in the welding chamber; is a constant.

[0102] The method for continuously extruding and preparing copper and copper alloy microchannel flat tubes may further include the following steps:

[0103] After the extrusion welding of the microchannel flat tube is completed, the acoustic wave data fed back from the welding interface of the microchannel flat tube is obtained based on the acoustic wave equipment, and a characteristic three-dimensional model diagram of the welding interface is constructed according to the acoustic wave data;

[0104] Acquire preset welding engineering drawing information of the microchannel flat tube welding interface, and construct a preset three-dimensional model diagram of the welding interface according to the preset welding engineering drawing information;

[0105] Constructing a KD tree space, importing the characteristic three-dimensional model diagram and the preset three-dimensional model diagram into the KD tree space, and retrieving welding positioning references in the characteristic three-dimensional model diagram and the preset three-dimensional model diagram;

[0106] Integrate and pair the characteristic three-dimensional model diagram with the preset three-dimensional model diagram according to the welding positioning reference to obtain an integrated three-dimensional model diagram; and divide the integrated three-dimensional model diagram into a plurality of super-rectangular regions based on the KD tree space;

[0107] Determine whether there are characteristic three-dimensional model graphs and preset three-dimensional model graphs in each super-rectangular area one by one; if there is neither a characteristic three-dimensional model graph nor a preset three-dimensional model graph in a super-rectangular area, mark the super-rectangular area as a blank area;

[0108] If both a characteristic three-dimensional model image and a preset three-dimensional model image exist in a certain super-rectangular area, the super-rectangular area is marked as a normal area;

[0109] If only a characteristic three-dimensional model image exists in a certain super-rectangular area, or only a preset three-dimensional model image exists, the super-rectangular area is marked as a defective area; and the relative coordinate information between the defective area and the welding positioning reference is obtained;

[0110] Repeat the above steps until all super-rectangular regions are judged, and a number of defect regions of the welding interface and relative coordinate information between each defect region and the welding positioning reference are obtained;

[0111] The least squares curve fitting algorithm is introduced to obtain the defect distribution trend diagram of the welding interface according to the relative coordinate information between each defect area and the welding positioning reference and combined with the least squares curve fitting algorithm;

[0112] The welding parameters of the welding chamber are regulated and optimized according to the obtained defect distribution trend diagram.

[0113] It should be noted that after the extrusion welding is completed, a KD tree space is constructed and two three-dimensional model images are imported into it. KD tree space is a data structure for efficient storage and retrieval of multidimensional data. In this space, the welding positioning datum in the two model images is retrieved. The welding positioning datum is a key reference point for determining the position and direction in the model. Then, the two model images are integrated and paired according to this datum to obtain an integrated three-dimensional model image. Then, based on the KD tree space, the integrated three-dimensional model image is divided into several super-rectangular areas. This division method helps to analyze the model locally and check each super-rectangular area. If there is neither a characteristic three-dimensional model image nor a preset three-dimensional model image in the area, it is marked as a blank area. If both exist, it is a normal area, indicating that the welding of the area is as expected. The area where only one of the model images exists is marked as a defective area, and its relative coordinate information with the welding positioning datum is obtained. By judging all super-rectangular areas one by one, the defective area and its position information on the welding interface can be fully found. Using the least squares curve fitting algorithm, the defect distribution trend map is fitted according to the relative coordinate information of the defective area and the welding positioning datum. The least squares method finds the curve that best fits the data by minimizing the sum of squares of errors, thereby intuitively showing the distribution trend of defects at the welding interface. Finally, the welding parameters of the welding chamber are regulated and optimized according to this trend chart. For example, according to the defect distribution trend chart, the defect concentration area and direction are analyzed; if the trend chart shows that defects are concentrated in a certain area and close to the starting end of welding, the starting welding parameters (such as temperature and pressure) are inappropriate, and the temperature or pressure at the starting end is appropriately increased; if the defects are distributed linearly along a specific direction, it may be that the extrusion speed is uneven, and the extrusion speed is adjusted to make it stable; if the defects are concentrated at the edge of the welding interface, check the mold pressure distribution and adjust the edge pressure; according to different defect distribution characteristics, the welding parameters of the welding chamber are targeted for regulation and optimization in terms of temperature, pressure, extrusion speed, etc.

[0114] Through the above series of steps, the characteristic three-dimensional model diagram of the actual welding interface can be constructed using the acoustic wave data, and compared and analyzed with the preset three-dimensional model diagram. With the help of the KD tree space, the integrated model is efficiently divided and analyzed to accurately locate the defect area of ​​the welding interface and obtain its position information. Then, the defect distribution trend diagram is fitted by the least squares method, thereby providing an intuitive and accurate basis for the regulation and optimization of the welding parameters of the welding chamber, which is helpful to improve the welding quality in the continuous extrusion preparation process of copper and copper alloy microchannel flat tubes, reduce defects, and improve the overall performance of the product.

[0115] The method for continuously extruding and preparing copper and copper alloy microchannel flat tubes may further include the following steps:

[0116] Acquire real-time welding temperature information of a plurality of preset position nodes of the welding interface, and construct a real-time temperature distribution diagram of the welding interface according to the real-time welding temperature information of each preset position node;

[0117] Obtaining a preset temperature distribution diagram of the welding interface at a current preset time node, and calculating a structural similarity index between the real-time temperature distribution diagram and the preset temperature distribution diagram;

[0118] If the structural similarity index is not greater than a preset index value, feature extraction processing is performed on the real-time temperature distribution map and the preset temperature distribution map to obtain a real-time isotherm map and a preset isotherm map;

[0119] Pairing and analyzing the real-time isotherm map with the preset isotherm map to obtain an area where the isotherms do not overlap, which is defined as a temperature singularity area;

[0120] Mark and control the temperature control device corresponding to the temperature singular area, and obtain the real-time working parameters of the marked temperature control device;

[0121] Introducing a Markov model, importing the real-time working parameters of the marked temperature control device into the Markov model for fault prediction, and obtaining a state transition probability value of the marked temperature control device;

[0122] If the state transition probability value of the marked temperature control device is greater than the preset probability value, the extrusion welding device is controlled to stop production and generate fault warning information;

[0123] If the state transition probability value of the marked temperature control device is not greater than the preset probability value, the preset working parameters of the marked temperature control device are obtained, the difference between the preset working parameters and the real-time working parameters is calculated to obtain the working parameter deviation value, and the real-time working parameters of the marked temperature control device are regulated according to the working parameter deviation value.

[0124] It should be noted that the real-time welding temperature information of multiple preset position nodes of the welding interface is first obtained to construct a real-time temperature distribution map, which can reflect the temperature distribution of the current welding interface. At the same time, the preset temperature distribution map of the same time node is obtained, which is a temperature distribution mode set based on the ideal welding process. Then the structural similarity index between the two is calculated, which can measure the similarity between the real-time temperature distribution and the ideal distribution. If the index is not greater than the preset index value, it means that there is a large difference between the real-time temperature distribution and the ideal situation. When the real-time temperature distribution is significantly different from the preset temperature distribution, feature extraction processing is performed to obtain a real-time isotherm map and a preset isotherm map. The isotherm map can more intuitively display the area with the same temperature. By pairing and analyzing the two isotherm maps, non-overlapping areas are found, which are defined as temperature singular areas. The temperature singular area is where the actual temperature is significantly different from the ideal temperature, which may be caused by equipment failure or process instability. Mark the temperature control equipment corresponding to the temperature singular area, because the temperature anomaly in these areas may be related to the working status of these devices. The real-time working parameters of the marked temperature control equipment are obtained. These parameters reflect the current working state of the equipment, such as heating power, cooling speed, etc. The Markov model is introduced, and the real-time working parameters are imported into it for fault prediction to obtain the state transition probability value. The Markov model can predict the possibility of future failure of the equipment based on the current working parameter state of the equipment. If the state transition probability value is greater than the preset probability value, it means that the equipment has a greater risk of failure. At this time, the extrusion welding equipment is controlled to stop production and generate fault warning information to avoid more serious problems that may occur. If the state transition probability value is not greater than the preset probability value, the preset working parameters of the equipment are obtained, and the difference with the real-time working parameters is calculated to obtain the working parameter deviation value. According to this deviation value, the real-time working parameters of the equipment are regulated and processed, so that the working state of the equipment is closer to the ideal state, and then the temperature distribution of the welding interface is adjusted. Through the above steps, the difference between the temperature distribution of the welding interface and the ideal situation can be found in time, the temperature singularity area can be located, and then the temperature control equipment with possible problems can be found. The Markov model is used to predict the risk of equipment failure, and corresponding measures such as shutdown warning or parameter regulation are taken according to the prediction results. This helps to improve the temperature control accuracy during the continuous extrusion preparation process of copper and copper alloy microchannel flat tubes, reduce product quality problems caused by abnormal temperature, and at the same time ensure the normal operation of the equipment and improve the stability and reliability of the production process.

[0125] The present invention also discloses a continuous extrusion preparation system for copper and copper alloy microchannel flat tubes. Figure 3As shown, the copper and copper alloy microchannel flat tube continuous extrusion preparation system includes a memory 50 and a processor 80. The memory 50 stores a copper and copper alloy microchannel flat tube continuous extrusion preparation method program. When the copper and copper alloy microchannel flat tube continuous extrusion preparation method program is executed by the processor 80, any one of the steps of the copper and copper alloy microchannel flat tube continuous extrusion preparation method is implemented.

[0126] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0127] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0128] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0129] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: a mobile storage device, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0130] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods of each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0131] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A method for continuously extruding and preparing copper and copper alloy microchannel flat tubes, characterized in that: The following steps are involved: Acquire performance change data of the welding interface under various historical welding parameter combinations, and build a performance prediction model of the welding interface according to the performance change data of the welding interface under various historical welding parameter combinations; When extrusion welding is performed on the microchannel flat tube by the extrusion welding equipment, real-time welding parameters of the welding interface are collected at a number of preset time nodes, and the collected real-time welding parameters are de-redundanted to obtain the real-time welding parameters after de-redundancy. According to the real-time welding parameters after redundancy removal and in combination with the performance prediction model, the state of the welding interface of the microchannel flat tube after a preset time period in the future is obtained; If the state of the welding interface of the microchannel flat tube is normal after a preset time period in the future, no adjustment or control is performed on the welding parameters; If the state of the welding interface of the microchannel flat tube after a preset time period in the future is a sudden change state, the welding parameters are adjusted; Among them, the performance change data of the welding interface under various historical welding parameter combinations are obtained, and the performance prediction model of the welding interface is constructed according to the performance change data of the welding interface under various historical welding parameter combinations, specifically: Acquire performance change data of the welding interface under various historical welding parameter combinations through a big data network, and acquire the status of the performance change data; Constructing a conditional random field, importing the performance change data of the welding interface under various historical welding parameter combinations into the conditional random field; and taking various historical welding parameter combinations as quantitative nodes and the performance change data of each time stamp as variable nodes; According to the state of the performance change data, the conditional probability of each variable node transferring from a normal state to a mutation state under the conditions of each quantitative node is calculated; When the conditional probability is greater than the preset probability threshold, the corresponding variable node is marked as a mutation state node; when the conditional probability is not greater than the preset probability threshold, the corresponding variable node is marked as a normal state node; Directly connect each mutation state node, normal state node and quantitative node to obtain a topological structure diagram of the conditional random field; construct a graph embedding model based on a neural network, and embed the topological structure diagram into the graph embedding model; Utilizing the neuron structure of the neural network and taking the directed connection relationship among quantitative nodes, mutation state nodes and normal state nodes as the basis, the neuron connection weights are continuously adjusted through the forward propagation process of multi-layer neurons to encode and learn the topological structure; until the learning parameters meet the preset requirements, the performance prediction model of the welding interface is obtained.

2. The method for continuously extruding and preparing a copper and copper alloy microchannel flat tube according to claim 1, characterized in that: The welding parameters include temperature, pressure and extrusion speed; the state includes normal state and sudden change state; the performance change data includes tensile strength, yield strength, hardness, grain size, defect concentration, thermal conductivity and electrical conductivity.

3. The method for continuously extruding and preparing a copper and copper alloy microchannel flat tube according to claim 1, characterized in that: The collected real-time welding parameters are de-redundanted to obtain the real-time welding parameters after de-redundancy, which are specifically: The wavelet transform algorithm is introduced to perform discrete wavelet decomposition on the collected real-time welding parameters according to the preset wavelet basis and decomposition layer number to obtain the wavelet coefficients of each real-time welding parameter; Constructing a wavelet coefficient matrix according to the wavelet coefficients of each real-time welding parameter; Calculate the coefficient difference between every two wavelet coefficients in the wavelet coefficient matrix; Preset a deviation value threshold, and compare the coefficient difference between every two wavelet coefficients in the wavelet coefficient matrix with the preset deviation value threshold; If the coefficient difference between two wavelet coefficients in the wavelet coefficient matrix is ​​not greater than the preset deviation value threshold, it means that the real-time welding parameters corresponding to the two wavelet coefficients are redundant, and any redundant real-time welding parameter is screened out; The iteration is stopped until all the wavelet coefficient pairs in the wavelet coefficient matrix are judged and analyzed, and the real-time welding parameters after redundancy removal are obtained.

4. The method for continuously extruding and preparing a copper and copper alloy microchannel flat tube according to claim 1, characterized in that: According to the real-time welding parameters after redundancy removal and combined with the performance prediction model, the state of the welding interface of the microchannel flat tube after a preset time period in the future is obtained, specifically: The real-time welding parameters after redundancy removal are sorted based on the acquisition time stamp sequence of each preset time node to obtain the real-time welding parameters based on the time sequence; Importing the real-time welding parameters based on the time series into the performance prediction model for prediction, and obtaining the predicted performance change data of the welding interface of the microchannel flat tube after a preset time period in the future; Acquire preset preparation process information of the microchannel flat tube, and acquire the state of the welding interface of the microchannel flat tube after a preset time period in the future according to the preset preparation process information; The state of the welding interface after a preset time period in the future includes a normal state and a sudden change state.

5. The method for continuously extruding and preparing a copper and copper alloy microchannel flat tube according to claim 4, characterized in that: If the state of the welding interface of the microchannel flat tube after a preset time period in the future is a sudden change state, the welding parameters are adjusted and processed, specifically: If the state of the welding interface of the microchannel flat tube after a preset time period in the future is a sudden change state, then the preset extrusion welding process information of the microchannel flat tube is obtained; Acquire preset performance change data of the welding interface of the microchannel flat tube after a preset time period in the future according to the preset extrusion welding process information; Calculate the absolute value of the data difference between each preset performance change data and the corresponding predicted performance change data of the welding interface of the microchannel flat tube after a preset time period in the future, and obtain the data deviation value between each preset performance change data and the corresponding predicted performance change data; Preset the deviation value range of various performance change data; determine whether the data deviation value between each preset performance change data and the corresponding predicted performance change data is within the corresponding deviation value range; If the data deviation value between a certain preset performance change data and the corresponding predicted performance change data is not within the corresponding deviation value range, the corresponding performance change data of the welding interface is calibrated as the sudden performance change data after the preset time period in the future, and the sudden performance change data of the welding interface of the microchannel flat tube after the preset time period in the future is obtained; If the data deviation value between a certain preset performance change data and the corresponding predicted performance change data is within the corresponding deviation value range, the corresponding performance change data of the welding interface is calibrated as the normal performance change data after the future preset time period.

6. The method for continuously extruding and preparing a copper and copper alloy microchannel flat tube according to claim 5, characterized in that: If the state of the welding interface of the microchannel flat tube after a preset time period in the future is a sudden change state, the welding parameters are regulated, and the following steps are also included: Prefabricate in advance the welding parameter control scheme corresponding to various sudden performance change data of the welding interface after a preset time period in the future; Constructing a control scheme pairing database, and importing the welding parameter control schemes corresponding to various sudden performance change data of the welding interface that are prefabricated in advance after a preset time period in the future into the control scheme pairing database; and regularly updating the control scheme pairing database; Obtaining sudden performance change data of the welding interface of the microchannel flat tube after a preset time period in the future, importing the sudden performance change data of the welding interface of the microchannel flat tube after the preset time period in the future into the control scheme pairing database for matching, and obtaining a corresponding welding parameter control scheme; The acquired welding parameter control scheme is transmitted to the control terminal of the extrusion welding equipment, so as to control the corresponding real-time welding parameters of the welding chamber based on the welding parameter control scheme to avoid sudden performance change data at the welding interface.

7. The method for continuously extruding and preparing copper and copper alloy microchannel flat tubes according to claim 1, characterized in that: In the process of adjusting welding parameters, the temperature and pressure in the welding chamber need to meet the following conditions: is the pressure in the welding chamber, is the temperature in the welding chamber; is a constant.

Images