SMT solder paste production control method and system based on multi-source data

Abstract

The invention discloses an SMT solder paste production control method and system based on multi-source data, belongs to the field of SMT production solder paste control, and solves the technical problem of how to accurately, reliably and intelligently discover solder paste problems of pads in the production process of SMT printing process, so as to avoid more serious problems caused by solder paste problems in other subsequent production processes; the method and system comprise: obtaining solder paste printing data sets and solder pad defect data sets of printed circuit boards of corresponding models and corresponding batches in the printing process; respectively analyzing the solder paste printing data sets and solder pad defect data sets, respectively calculating the first solder paste state evaluation coefficient and the second solder paste state evaluation coefficient of the printed circuit boards of corresponding models and corresponding batches in the printing process, respectively judging whether the state of the used solder paste is normal, obtaining the first judgment result and the second judgment result, comparing the first judgment result and the second judgment result, and finally judging whether the current state of the solder paste is normal.

Description

Technical Field

[0001] The present invention belongs to the field of SMT solder paste production control, and specifically relates to an SMT solder paste production control method and system based on multi-source data. Background Art

[0002] SMT refers to surface mount technology, which is an electronic manufacturing technology used to install and connect electronic components on circuit boards without using traditional plug-in assembly methods. With this technology, the pins of components are directly soldered to the surface of the printed circuit board (PCB); timely detection of solder paste-related data during the SMT printing process can promptly detect printing problems with the pads of the printed circuit board.

[0003] The prior art uses automatic optical inspection technology to detect pad defects after the printing process is completed. However, considering light problems or other problems, the judgment of whether some pads in the printing process have defects may become unreliable. In order to accurately, reliably and intelligently detect solder paste problems of pads during the production process of SMT printing process and avoid more serious problems in subsequent production processes due to solder paste problems, the present invention proposes an SMT solder paste production control method and system based on multi-source data. Summary of the invention

[0004] The present invention aims to solve at least one of the technical problems existing in the prior art. To this end, the present invention proposes a SMT solder paste production control method and system based on multi-source data, which solves the technical problem of how to accurately, reliably and intelligently discover solder paste problems of pads during the production process of SMT printing process, and avoid more serious problems caused by solder paste problems in subsequent other production processes.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] The SMT solder paste production control method and system based on multi-source data include: a multi-source data acquisition module, a data storage module, a first state evaluation module, a second state evaluation module, an intelligent decision-making module and a background management module;

[0007] The multi-source data acquisition module is used to collect solder paste printing data sets and pad defect data sets in the SMT printing process of the printed circuit board, and the collected solder paste printing data sets and pad defect data sets are labeled with model and batch and sent to the data storage module for storage;

[0008] The first state evaluation module is used to analyze the solder paste printing data set, calculate the first solder paste state evaluation coefficient of the corresponding model and the corresponding batch of printed circuit boards in the printing process based on the solder paste printing data set, judge whether the state of the solder paste used in the printing process of the corresponding model and the corresponding batch of printed circuit boards is normal according to the first solder paste state evaluation coefficient obtained by calculation, mark the judgment result as the first judgment result and send it to the intelligent decision-making module;

[0009] The second state evaluation module is used to analyze the pad defect data set, obtain the number of pads with different pad defect types based on the pad defect data set, calculate the second solder paste state evaluation coefficient of the corresponding model and the corresponding batch of printed circuit boards in the printing process based on the number of pads with different pad defect types, judge whether the state of the solder paste used in the printing process of the corresponding model and the corresponding batch of printed circuit boards is normal according to the calculated second solder paste state evaluation coefficient, and mark the judgment result as the second judgment result and send it to the intelligent decision module;

[0010] The intelligent decision-making module is used to compare the first judgment result and the second judgment result of whether the state of the solder paste used in the printing process of the printed circuit board of the corresponding model and the corresponding batch is normal, and generate an instruction to continue or suspend operation according to the comparison result and send it to the printing equipment, and at the same time generate normal feedback information or warning information and send it to the background management module.

[0011] Furthermore, the method for acquiring the solder paste printing data set is: respectively setting a pressure sensor, a speed sensor, a viscosity sensor, a fluidity sensor and a tension sensor at corresponding positions of the SMT printing equipment; the pressure sensor is used to detect the scraper pressure on the steel mesh and the solder paste; the speed sensor is used to detect the printing speed of the printing equipment; the viscosity sensor and the fluidity sensor are respectively used to detect the viscosity and fluidity of the solder paste during printing; the tension sensor is used to detect the overall tension value of the steel mesh; the detection is performed once at preset intervals, and a group of solder paste printing data of scraper pressure, printing speed, viscosity, fluidity and overall tension value are obtained each time the detection is performed, and multiple groups of solder paste printing data of printed circuit boards of corresponding models and corresponding batches in the printing process constitute a solder paste printing data set.

[0012] Furthermore, the pad defect data set is obtained in the following manner: an optical detector is set at a corresponding position of the SMT printing equipment, and the optical detector is used to detect the pad defects of the printed circuit board after the printing process is completed, and the detection results of whether all the pads of the printed circuit boards of the corresponding models and batches after the printing process are completed are obtained to determine whether there are defects, and generate a pad defect data set; wherein the pad defect detection is implemented by AOI technology.

[0013] Furthermore, the process of analyzing the solder paste printing data set by the first state assessment module includes:

[0014] Extracting a solder paste printing data set of a corresponding model and a corresponding batch from a data storage module, wherein the solder paste printing data set includes multiple groups of solder paste printing data, and one group of solder paste printing data includes a scraper pressure Si, a printing speed Vi, a viscosity Ci, a fluidity Li, and an overall tension value Zi; wherein i represents a number of each group of solder paste printing data in the solder paste printing data set, i=1,2…n; and n represents a total number of groups of solder paste printing data in the solder paste printing data set;

[0015] Based on the obtained solder paste printing data set, the first solder paste state evaluation coefficient PZ1 of the corresponding model and batch of printed circuit boards in the printing process is calculated. The calculation formula is as follows:

[0016]

[0017] Wherein, SS, VS, CS, LS and ZS respectively represent the standard values ​​of scraper pressure, printing speed, viscosity, fluidity and overall tension value corresponding to the corresponding model of printed circuit board in the printing process; a1, a2, a3, a4 and a5 are preset proportional coefficients of relative deviation values ​​of scraper pressure, printing speed, viscosity, fluidity and overall tension value, respectively, and 0<a1<1, 0<a2<1, 0<a3<1, 0<a4<1, 0<a5<1, a1+a2+a3+a4+a5=1;

[0018] Compare the calculated first solder paste state evaluation coefficient PZ1 of the corresponding model and the corresponding batch of printed circuit boards in the printing process with the preset first solder paste state evaluation coefficient threshold PZS1 to determine whether the state of the solder paste used in the printing process of the corresponding model and the corresponding batch of printed circuit boards is normal;

[0019] If PZ1<PZS1, the state of the solder paste used in the printing process of the corresponding model and batch of printed circuit boards is marked as normal;

[0020] If PZ1 ≥ PZS1, the state of the solder paste used in the printing process of the corresponding model and batch of printed circuit boards is marked as abnormal;

[0021] The judgment result of whether the state of the solder paste used in the printing process of the printed circuit board of the corresponding model and the corresponding batch is normal is marked as the second judgment result and sent to the intelligent decision-making module.

[0022] Furthermore, the process of analyzing the pad defect data set by the second state assessment module includes:

[0023] Extracting a pad defect dataset of a corresponding model and a corresponding batch from a data storage module; the pad defect dataset is a sequence of pad coordinates marked with various pad defect types;

[0024] The number of pads with different pad defect types in the acquired pad defect data set is counted to obtain the number of pads with insufficient solder paste (NL), the number of pads with excessive solder paste (NO), the number of pads with poor solder paste overlap (NM), and the number of pads with solder paste bridging (NC);

[0025] Based on the number of pads with different pad defect types, the second solder paste state evaluation coefficient PZ2 of the corresponding model and batch of printed circuit boards in the printing process is calculated. The calculation formula is as follows:

[0026]

[0027] Wherein, NH represents the total number of pads of the corresponding model and batch of printed circuit boards, b1, b2, b3 and b4 are preset proportional coefficients of the number of pads with insufficient solder paste, the number of pads with excessive solder paste, the number of pads with poor solder paste overlap and the number of pads with solder paste bridging, 0<b1<1, 0<b2<1, 0<b3<1, 0<b4<1, and b1+b2+b3+b4=1;

[0028] Compare the calculated second solder paste state evaluation coefficient PZ2 of the corresponding model and the corresponding batch of printed circuit boards in the printing process with the preset second solder paste state evaluation coefficient threshold PZS2 to determine whether the state of the solder paste used in the printing process of the corresponding model and the corresponding batch of printed circuit boards is normal;

[0029] If PZ2<PZS2, the state of the solder paste used in the printing process of the corresponding model and batch of printed circuit boards is marked as normal;

[0030] If PZ2 ≥ PZS2, the state of the solder paste used in the printing process of the corresponding model and batch of printed circuit boards is marked as abnormal;

[0031] The judgment result of whether the state of the solder paste used in the printing process of the printed circuit board of the corresponding model and the corresponding batch is normal is marked as the second judgment result and sent to the intelligent decision-making module.

[0032] Furthermore, the analysis of the intelligent decision-making module includes:

[0033] If both the first judgment result and the second judgment result show that the state of the solder paste used in the printing process of the corresponding model and the corresponding batch of printed circuit boards is normal, an instruction to continue operation is generated and sent to the printing device; at the same time, normal feedback information is generated and sent to the background management module; after receiving the instruction to continue operation, the printing device passes the currently processed printed circuit board to the next process, and prepares to print the next batch of printed circuit boards; the relevant staff receives the normal feedback information through the background management module without further processing;

[0034] If both the first judgment result and the second judgment result show that the state of the solder paste used in the printing process of the corresponding model and the corresponding batch of printed circuit boards is abnormal, a command to suspend operation is generated and sent to the printing device, and an early warning message is generated and sent to the background management module; after the printing device receives the command to suspend operation, it suspends work, and the relevant staff receives the early warning message through the background management module and comes to handle it in time;

[0035] If any one of the first judgment result and the second judgment result shows that the status of the solder paste used in the printing process of the printed circuit board of the corresponding model and the corresponding batch is normal or abnormal, an early warning message is generated and sent to the background management module. After receiving the early warning message through the background management module, the relevant staff will come to handle it in time; the relevant staff will determine whether it is abnormal through manual judgment.

[0036] Further, the SMT solder paste production control method based on multi-source data, according to the SMT solder paste production control system based on multi-source data, the method includes:

[0037] The solder paste printing data set and pad defect data set of the corresponding model and corresponding batch of printed circuit boards in the printing process are obtained through the multi-source data acquisition module;

[0038] Analyze the solder paste printing data set through the first state evaluation module to determine whether the state of the solder paste used in the printing process of the corresponding model and the corresponding batch of printed circuit boards is normal, mark the judgment result as the first judgment result and send it to the intelligent decision-making module;

[0039] The pad defect data set is analyzed by the second state evaluation module to determine whether the state of the solder paste used in the printing process of the corresponding model and the corresponding batch of printed circuit boards is normal, and the determination result is marked as the second determination result and sent to the intelligent decision module;

[0040] The intelligent decision-making module compares the first judgment result of whether the status of the solder paste used in the printing process of the printed circuit board of the corresponding model and the corresponding batch is normal with the second judgment result, and generates an instruction to continue or suspend operation according to the comparison result and sends it to the printing equipment. At the same time, normal feedback information or warning information is generated and sent to the background management module.

[0041] Compared with the prior art, the present invention has the following beneficial effects:

[0042] 1. In the present invention, the solder paste printing data set and the pad defect data set of the corresponding model and the corresponding batch of printed circuit boards in the printing process are collected through a multi-source data acquisition module, that is, a variety of sensors or detection devices are set at the corresponding positions of the printing equipment, and various data are obtained through these sensors or detection devices to provide a data basis for the subsequent evaluation of the state of the solder paste in the printing process, and the obtained solder paste printing data set and pad defect data set are labeled with model and batch, which is convenient for the data storage module to classify and store, and also provides convenience for subsequent data analysis and subsequent quality traceability of printed circuit boards.

[0043] 2. In the present invention, the solder paste printing data set and the pad defect data set are analyzed respectively by the first state evaluation module and the second state evaluation module, and the first solder paste state evaluation coefficient and the second solder paste state evaluation coefficient of the printed circuit board of the corresponding model and the corresponding batch in the printing process are calculated respectively, and it is judged whether the state of the solder paste used is normal, and the first judgment result and the second judgment result are obtained. The first judgment result and the second judgment result are compared by the intelligent decision-making module, so as to more accurately and reliably judge whether the current state of the solder paste is normal, and send different control instructions to the printing equipment according to different comparison results, which helps to reduce the subjectivity of human judgment and improve the level of production automation; if an abnormality occurs or the comparison results are inconsistent, an early warning can be given, and the relevant staff can rush to deal with it in time, supporting higher-level decision-making and management, thereby avoiding more serious problems in other subsequent production processes due to solder paste problems. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 It is a structural schematic diagram of the SMT solder paste production control system based on multi-source data of the present invention;

[0045] Figure 2 It is a flow chart of the SMT solder paste production control method based on multi-source data of the present invention. DETAILED DESCRIPTION

[0046] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0047] like Figure 1 As shown, the SMT solder paste production control system based on multi-source data includes: a multi-source data acquisition module, a data storage module, a first state evaluation module, a second state evaluation module, an intelligent decision-making module and a background management module;

[0048] The multi-source data acquisition module is used to collect solder paste printing data sets and pad defect data sets in the SMT printing process of the printed circuit board, and the collected solder paste printing data sets and pad defect data sets are labeled with model and batch and sent to the data storage module for storage;

[0049] It is understandable that SMT is generally used for surface mounting of printed circuit boards. SMT surface mounting of printed circuit boards includes multiple processes, among which the printing process, which ranks first, is particularly important. The main process of the SMT printing process is to first prepare the substrate of the corresponding model of printed circuit boards, and cover the corresponding steel mesh of the corresponding model of printed circuit boards on the substrate, and use printing equipment to evenly apply appropriate solder paste on the surface of the substrate and steel mesh of the corresponding model of printed circuit boards, and by applying a certain pressure and printing speed on the steel mesh, the solder paste is transferred to the corresponding pad position on the substrate of the corresponding model of printed circuit boards through the mesh holes of the steel mesh;

[0050] In this embodiment, pressure sensors, speed sensors, viscosity sensors, fluidity sensors, tension sensors and optical detectors are respectively arranged at corresponding positions of the SMT printing equipment;

[0051] The pressure sensor is used to detect the scraper pressure on the steel mesh and the solder paste; the speed sensor is used to detect the printing speed of the printing equipment; the viscosity sensor and the fluidity sensor are used to detect the viscosity and fluidity of the solder paste during printing respectively; the tension sensor is used to detect the overall tension value of the steel mesh; the detection is performed once every preset time, and each detection obtains a set of solder paste printing data of scraper pressure, printing speed, viscosity, fluidity and overall tension value, and multiple sets of solder paste printing data of printed circuit boards of corresponding models and corresponding batches in the printing process constitute a solder paste printing data set;

[0052] The optical detector is used to detect pad defects of the printed circuit board after the printing process is completed, obtain the detection results of whether all pads of the printed circuit board of the corresponding model and the corresponding batch after the printing process are completed have defects, and generate a pad defect data set; wherein, the pad defect detection is generally implemented by AOI technology, which will not be elaborated in detail here;

[0053] In the present invention, the solder paste printing data set and the pad defect data set of the corresponding model and batch of printed circuit boards in the printing process are collected through a multi-source data collection module, that is, a variety of sensors or detection devices are set at the corresponding positions of the printing equipment, and various data are obtained through these sensors or detection devices to provide a data basis for the subsequent evaluation of the state of the solder paste in the printing process, and the obtained solder paste printing data set and pad defect data set are labeled with model and batch, which is convenient for the data storage module to classify and store, and also provides convenience for subsequent data analysis and subsequent quality traceability of printed circuit boards.

[0054] The first state evaluation module is used to analyze the solder paste printing data set, calculate the first solder paste state evaluation coefficient of the corresponding model and the corresponding batch of printed circuit boards in the printing process based on the solder paste printing data set, judge whether the state of the solder paste used in the printing process of the corresponding model and the corresponding batch of printed circuit boards is normal according to the calculated first solder paste state evaluation coefficient, mark the judgment result as the first judgment result and send it to the intelligent decision module; including:

[0055] Extracting a solder paste printing data set of a corresponding model and a corresponding batch from a data storage module, wherein the solder paste printing data set includes multiple groups of solder paste printing data, and one group of solder paste printing data includes a scraper pressure Si, a printing speed Vi, a viscosity Ci, a fluidity Li, and an overall tension value Zi; wherein i represents a number of each group of solder paste printing data in the solder paste printing data set, i=1,2…n; and n represents a total number of groups of solder paste printing data in the solder paste printing data set;

[0056] Based on the obtained solder paste printing data set, the first solder paste state evaluation coefficient PZ1 of the corresponding model and batch of printed circuit boards in the printing process is calculated. The calculation formula is as follows:

[0057]

[0058] Wherein, SS, VS, CS, LS and ZS respectively represent the standard values ​​of scraper pressure, printing speed, viscosity, fluidity and overall tension value corresponding to the corresponding model of printed circuit board in the printing process; a1, a2, a3, a4 and a5 are preset proportional coefficients of relative deviation values ​​of scraper pressure, printing speed, viscosity, fluidity and overall tension value, respectively, and 0<a1<1, 0<a2<1, 0<a3<1, 0<a4<1, 0<a5<1, a1+a2+a3+a4+a5=1;

[0059] It can be understood that when the relative deviation value of the scraper pressure is smaller, the relative deviation value of the printing speed is smaller, the relative deviation value of the viscosity is smaller, the relative deviation value of the fluidity is smaller, and the relative deviation value of the overall tension value is smaller, the first solder paste state evaluation coefficient is smaller, indicating that the state of the solder paste used in the printing process of the printed circuit board is better;

[0060] Compare the calculated first solder paste state evaluation coefficient PZ1 of the corresponding model and the corresponding batch of printed circuit boards in the printing process with the preset first solder paste state evaluation coefficient threshold PZS1 to determine whether the state of the solder paste used in the printing process of the corresponding model and the corresponding batch of printed circuit boards is normal;

[0061] If PZ1<PZS1, the state of the solder paste used in the printing process of the corresponding model and batch of printed circuit boards is marked as normal;

[0062] If PZ1 ≥ PZS1, the state of the solder paste used in the printing process of the corresponding model and batch of printed circuit boards is marked as abnormal;

[0063] Marking the judgment result of whether the state of the solder paste used in the printing process of the corresponding model and the corresponding batch of printed circuit boards is normal as the second judgment result, and sending it to the intelligent decision-making module;

[0064] The second state evaluation module is used to analyze the pad defect data set, obtain the number of pads with different pad defect types based on the pad defect data set, calculate the second solder paste state evaluation coefficient of the corresponding model and the corresponding batch of printed circuit boards in the printing process based on the number of pads with different pad defect types, judge whether the state of the solder paste used in the printing process of the corresponding model and the corresponding batch of printed circuit boards is normal according to the calculated second solder paste state evaluation coefficient, and mark the judgment result as the second judgment result and send it to the intelligent decision module; including:

[0065] Extracting a pad defect dataset of a corresponding model and a corresponding batch from a data storage module; it can be understood that the pad defect dataset is obtained through imaging recognition and is a sequence of pad coordinates marked with various pad defect types;

[0066] The number of pads with different pad defect types in the acquired pad defect data set is counted to obtain the number of pads with insufficient solder paste (NL), the number of pads with excessive solder paste (NO), the number of pads with poor solder paste overlap (NM), and the number of pads with solder paste bridging (NC);

[0067] Based on the number of pads with different pad defect types, the second solder paste state evaluation coefficient PZ2 of the corresponding model and batch of printed circuit boards in the printing process is calculated. The calculation formula is as follows:

[0068]

[0069] Wherein, NH represents the total number of pads of the corresponding model and batch of printed circuit boards, b1, b2, b3 and b4 are preset proportional coefficients of the number of pads with insufficient solder paste, the number of pads with excessive solder paste, the number of pads with poor solder paste overlap and the number of pads with solder paste bridging, 0<b1<1, 0<b2<1, 0<b3<1, 0<b4<1, and b1+b2+b3+b4=1;

[0070] Compare the calculated second solder paste state evaluation coefficient PZ2 of the corresponding model and the corresponding batch of printed circuit boards in the printing process with the preset second solder paste state evaluation coefficient threshold PZS2 to determine whether the state of the solder paste used in the printing process of the corresponding model and the corresponding batch of printed circuit boards is normal;

[0071] If PZ2<PZS2, the state of the solder paste used in the printing process of the corresponding model and batch of printed circuit boards is marked as normal;

[0072] If PZ2 ≥ PZS2, the state of the solder paste used in the printing process of the corresponding model and batch of printed circuit boards is marked as abnormal;

[0073] Marking the judgment result of whether the state of the solder paste used in the printing process of the corresponding model and the corresponding batch of printed circuit boards is normal as the second judgment result, and sending it to the intelligent decision-making module;

[0074] The intelligent decision-making module is used to compare the first judgment result and the second judgment result of whether the state of the solder paste used in the printing process of the corresponding model and the corresponding batch of printed circuit boards is normal, generate an instruction to continue or suspend operation according to the comparison result and send it to the printing equipment, and generate normal feedback information or warning information and send it to the background management module; including:

[0075] If both the first judgment result and the second judgment result show that the state of the solder paste used in the printing process of the corresponding model and the corresponding batch of printed circuit boards is normal, an instruction to continue operation is generated and sent to the printing device; at the same time, normal feedback information is generated and sent to the background management module; after receiving the instruction to continue operation, the printing device passes the currently processed printed circuit board to the next process, and prepares to print the next batch of printed circuit boards; the relevant staff receives the normal feedback information through the background management module without further processing;

[0076] If both the first judgment result and the second judgment result show that the state of the solder paste used in the printing process of the corresponding model and the corresponding batch of printed circuit boards is abnormal, a command to suspend operation is generated and sent to the printing device, and an early warning message is generated and sent to the background management module; after the printing device receives the command to suspend operation, it suspends work, and the relevant staff receives the early warning message through the background management module and comes to handle it in time;

[0077] If any one of the first judgment result and the second judgment result shows that the state of the solder paste used in the printing process of the corresponding model and the corresponding batch of printed circuit boards is normal or abnormal, an early warning message is generated and sent to the background management module. After receiving the early warning message through the background management module, the relevant staff will come to handle it in time; the relevant staff will determine whether it is abnormal through manual judgment;

[0078] Among them, the first state evaluation module and the second evaluation module can also send the evaluation coefficients and judgment results obtained by their respective calculations to the data storage module for associated storage with the corresponding data sets; and the intelligent decision-making module sends the obtained comparison results to the data storage module for associated storage with the corresponding solder paste printing data set and pad defect data set; to facilitate the subsequent analysis and optimization setting of the relevant preset proportional coefficients and thresholds involved in the first state evaluation module and the second evaluation module;

[0079] In the present invention, the solder paste printing data set and the pad defect data set are analyzed respectively by the first state evaluation module and the second state evaluation module, and the first solder paste state evaluation coefficient and the second solder paste state evaluation coefficient of the corresponding model and the corresponding batch of printed circuit boards in the printing process are calculated respectively, and whether the state of the used solder paste is normal is judged respectively, and the first judgment result and the second judgment result are obtained. The first judgment result and the second judgment result are compared by the intelligent decision-making module, so as to more accurately and reliably judge whether the current state of the solder paste is normal, and send different control instructions to the printing equipment according to different comparison results, which helps to reduce the subjectivity of human judgment and improve the automation level of production; if an abnormality occurs or the comparison results are inconsistent, an early warning can be issued, and the relevant staff rushes to deal with it in time, supporting higher-level decision-making and management, thereby avoiding more serious problems caused by solder paste problems in other subsequent production processes;

[0080] like Figure 2 As shown, the SMT solder paste production control method based on multi-source data, according to the SMT solder paste production control system based on multi-source data, includes:

[0081] The solder paste printing data set and pad defect data set of the corresponding model and corresponding batch of printed circuit boards in the printing process are obtained through the multi-source data acquisition module;

[0082] Analyze the solder paste printing data set through the first state evaluation module to determine whether the state of the solder paste used in the printing process of the corresponding model and the corresponding batch of printed circuit boards is normal, mark the judgment result as the first judgment result and send it to the intelligent decision-making module;

[0083] The pad defect data set is analyzed by the second state evaluation module to determine whether the state of the solder paste used in the printing process of the corresponding model and the corresponding batch of printed circuit boards is normal, and the determination result is marked as the second determination result and sent to the intelligent decision module;

[0084] The intelligent decision-making module compares the first judgment result of whether the status of the solder paste used in the printing process of the printed circuit board of the corresponding model and the corresponding batch is normal with the second judgment result, and generates an instruction to continue or suspend operation according to the comparison result and sends it to the printing equipment. At the same time, normal feedback information or warning information is generated and sent to the background management module.

[0085] The above formulas are all calculated by removing dimensions and taking numerical values. The formula is a formula that is closest to the actual situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained by simulating a large amount of data.

[0086] In the embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation; the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the method of this embodiment.

[0087] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. The SMT solder paste production control system based on multi-source data is characterized by: include: Multi-source data acquisition module, data storage module, first state evaluation module, second state evaluation module, intelligent decision-making module and background management module; The multi-source data acquisition module is used to collect solder paste printing data sets and pad defect data sets in the SMT printing process of the printed circuit board, and the collected solder paste printing data sets and pad defect data sets are labeled with model and batch and sent to the data storage module for storage; The first state evaluation module is used to analyze the solder paste printing data set, calculate the first solder paste state evaluation coefficient of the corresponding model and the corresponding batch of printed circuit boards in the printing process based on the solder paste printing data set, judge whether the state of the solder paste used in the printing process of the corresponding model and the corresponding batch of printed circuit boards is normal according to the first solder paste state evaluation coefficient obtained by calculation, mark the judgment result as the first judgment result and send it to the intelligent decision-making module; The second state evaluation module is used to analyze the pad defect data set, obtain the number of pads with different pad defect types based on the pad defect data set, calculate the second solder paste state evaluation coefficient of the corresponding model and the corresponding batch of printed circuit boards in the printing process based on the number of pads with different pad defect types, judge whether the state of the solder paste used in the printing process of the corresponding model and the corresponding batch of printed circuit boards is normal according to the calculated second solder paste state evaluation coefficient, and mark the judgment result as the second judgment result and send it to the intelligent decision module; The intelligent decision-making module is used to compare the first judgment result of whether the state of the solder paste used in the printing process of the corresponding model and the corresponding batch of printed circuit boards is normal with the second judgment result, and generate an instruction to continue or suspend operation according to the comparison result and send it to the printing device, and at the same time generate normal feedback information or warning information and send it to the background management module; The method for acquiring the solder paste printing data set is as follows: a pressure sensor, a speed sensor, a viscosity sensor, a fluidity sensor and a tension sensor are respectively arranged at corresponding positions of the SMT printing equipment; the pressure sensor is used to detect the scraper pressure on the steel mesh and the solder paste; the speed sensor is used to detect the printing speed of the printing equipment; the viscosity sensor and the fluidity sensor are respectively used to detect the viscosity and fluidity of the solder paste during printing; the tension sensor is used to detect the overall tension value of the steel mesh; the detection is performed once at a preset time interval, and a set of solder paste printing data of scraper pressure, printing speed, viscosity, fluidity and overall tension value is obtained each time the detection is performed, and multiple sets of solder paste printing data of printed circuit boards of corresponding models and corresponding batches in the printing process constitute a solder paste printing data set; The pad defect data set is obtained by: setting an optical detector at the corresponding position of the SMT printing equipment, the optical detector is used to detect the pad defects of the printed circuit board after the printing process is completed, and obtaining the detection results of whether all pads of the printed circuit boards of the corresponding models and batches after the printing process are completed have defects, and generating the pad defect data set; Among them, pad defect detection is implemented through AOI technology; The process of analyzing the solder paste printing data set by the first state assessment module includes: Extracting a solder paste printing data set of a corresponding model and a corresponding batch from a data storage module, wherein the solder paste printing data set includes multiple groups of solder paste printing data, and one group of solder paste printing data includes a scraper pressure Si, a printing speed Vi, a viscosity Ci, a fluidity Li, and an overall tension value Zi; wherein i represents a number of each group of solder paste printing data in the solder paste printing data set, i=1,2…n; and n represents a total number of groups of solder paste printing data in the solder paste printing data set; Based on the obtained solder paste printing data set, the first solder paste state evaluation coefficient PZ1 of the corresponding model and batch of printed circuit boards in the printing process is calculated. The calculation formula is as follows: Wherein, SS, VS, CS, LS and ZS respectively represent the standard values ​​of scraper pressure, printing speed, viscosity, fluidity and overall tension value corresponding to the corresponding model of printed circuit board in the printing process; a1, a2, a3, a4 and a5 are preset proportional coefficients of relative deviation values ​​of scraper pressure, printing speed, viscosity, fluidity and overall tension value, respectively, and 0<a1<1, 0<a2<1, 0<a3<1, 0<a4<1, 0<a5<1, a1+a2+a3+a4+a5=1; Compare the calculated first solder paste state evaluation coefficient PZ1 of the corresponding model and the corresponding batch of printed circuit boards in the printing process with the preset first solder paste state evaluation coefficient threshold PZS1 to determine whether the state of the solder paste used in the printing process of the corresponding model and the corresponding batch of printed circuit boards is normal; If PZ1<PZS1, the state of the solder paste used in the printing process of the corresponding model and batch of printed circuit boards is marked as normal; If PZ1 ≥ PZS1, the state of the solder paste used in the printing process of the corresponding model and batch of printed circuit boards is marked as abnormal; Marking the judgment result of whether the state of the solder paste used in the printing process of the printed circuit board of the corresponding model and the corresponding batch is normal as the second judgment result, and sending it to the intelligent decision module; The process of analyzing the pad defect data set by the second state assessment module includes: Extracting a pad defect dataset of a corresponding model and a corresponding batch from a data storage module; the pad defect dataset is a sequence of pad coordinates marked with various pad defect types; The number of pads with different pad defect types in the acquired pad defect data set is counted to obtain the number of pads with insufficient solder paste (NL), the number of pads with excessive solder paste (NO), the number of pads with poor solder paste overlap (NM), and the number of pads with solder paste bridging (NC); Based on the number of pads with different pad defect types, the second solder paste state evaluation coefficient PZ2 of the corresponding model and batch of printed circuit boards in the printing process is calculated. The calculation formula is as follows: Wherein, NH represents the total number of pads of the corresponding model and batch of printed circuit boards, b1, b2, b3 and b4 are preset proportional coefficients of the number of pads with insufficient solder paste, the number of pads with excessive solder paste, the number of pads with poor solder paste overlap and the number of pads with solder paste bridging, 0<b1<1, 0<b2<1, 0<b3<1, 0<b4<1, and b1+b2+b3+b4=1; Compare the calculated second solder paste state evaluation coefficient PZ2 of the corresponding model and the corresponding batch of printed circuit boards in the printing process with the preset second solder paste state evaluation coefficient threshold PZS2 to determine whether the state of the solder paste used in the printing process of the corresponding model and the corresponding batch of printed circuit boards is normal; If PZ2<PZS2, the state of the solder paste used in the printing process of the corresponding model and batch of printed circuit boards is marked as normal; If PZ2 ≥ PZS2, the state of the solder paste used in the printing process of the corresponding model and batch of printed circuit boards is marked as abnormal; The judgment result of whether the state of the solder paste used in the printing process of the printed circuit board of the corresponding model and the corresponding batch is normal is marked as the second judgment result and sent to the intelligent decision-making module.

2. The SMT solder paste production control system based on multi-source data according to claim 1, characterized in that: The analysis of the intelligent decision-making module includes: If both the first judgment result and the second judgment result show that the state of the solder paste used in the printing process of the corresponding model and the corresponding batch of printed circuit boards is normal, an instruction to continue operation is generated and sent to the printing device; at the same time, normal feedback information is generated and sent to the background management module; after receiving the instruction to continue operation, the printing device passes the currently processed printed circuit board to the next process, and prepares to print the next batch of printed circuit boards; the relevant staff receives the normal feedback information through the background management module without further processing; If both the first judgment result and the second judgment result show that the state of the solder paste used in the printing process of the corresponding model and the corresponding batch of printed circuit boards is abnormal, a command to suspend operation is generated and sent to the printing device, and an early warning message is generated and sent to the background management module; after the printing device receives the command to suspend operation, it suspends work, and the relevant staff receives the early warning message through the background management module and comes to handle it in time; If any one of the first judgment result and the second judgment result shows that the status of the solder paste used in the printing process of the printed circuit board of the corresponding model and the corresponding batch is normal or abnormal, an early warning message is generated and sent to the background management module. After receiving the early warning message through the background management module, the relevant staff will come to handle it in time; the relevant staff will determine whether it is abnormal through manual judgment.

3. A method for controlling the production of SMT solder paste based on multi-source data, according to a system for controlling the production of SMT solder paste based on multi-source data according to any one of claims 1 to 2, characterized in that: Methods include: The solder paste printing data set and pad defect data set of the corresponding model and corresponding batch of printed circuit boards in the printing process are obtained through the multi-source data acquisition module; Analyze the solder paste printing data set through the first state evaluation module to determine whether the state of the solder paste used in the printing process of the corresponding model and the corresponding batch of printed circuit boards is normal, mark the judgment result as the first judgment result and send it to the intelligent decision-making module; The pad defect data set is analyzed by the second state evaluation module to determine whether the state of the solder paste used in the printing process of the corresponding model and the corresponding batch of printed circuit boards is normal, and the determination result is marked as the second determination result and sent to the intelligent decision module; The intelligent decision-making module compares the first judgment result of whether the status of the solder paste used in the printing process of the printed circuit board of the corresponding model and the corresponding batch is normal with the second judgment result, and generates an instruction to continue or suspend operation according to the comparison result and sends it to the printing equipment. At the same time, normal feedback information or warning information is generated and sent to the background management module.

Images