CN117557082B

CN117557082B - Process processing method, device, equipment and storage medium for electronic components

Info

Publication number: CN117557082B
Application number: CN202311527947.3A
Authority: CN
Inventors: 李晓军; 尹玉涛; 雷红阳
Original assignee: Shenzhen Hangsheng Electronic Co Ltd
Current assignee: Shenzhen Hangsheng Electronic Co Ltd
Priority date: 2023-11-16
Filing date: 2023-11-16
Publication date: 2024-04-19
Anticipated expiration: 2043-11-16
Also published as: CN117557082A

Abstract

The invention discloses a process treatment method, a process treatment device, process treatment equipment and a storage medium for electronic components, and belongs to the technical field of electric digital data processing. According to the invention, the industrial data of production equipment and raw materials are collected, the industrial data are subjected to data preprocessing to obtain the preprocessed industrial data, the preprocessed industrial data are subjected to data analysis and modeling to obtain production adjustment data, and the technological parameters of the surface mount technology and/or the packaging flow of the production equipment are adjusted according to the production adjustment data, so that the automation and the intelligence degree of the packaging and SMT surface mount technology flow of electronic components are improved, and the yield and the production efficiency of products produced by the packaging and surface mount technology are improved.

Description

Process processing method, device, equipment and storage medium for electronic components

Technical Field

The present invention relates to the field of electronic digital data processing, and in particular, to a method, an apparatus, a device, and a storage medium for processing electronic components.

Background

The two most important manufacturing processes of electronic products are packaging and pasting processes, wherein the packaging is used for packaging single components, and pasting is used for assembling various electronic components on a Printed Circuit Board (PCB).

The existing electronic related products and various electronic components on the control board card thereof are mostly assembled in the form of Surface Mount Technology (SMT) patches, such as various electronic components of LED lamp beads, driving chips, resistors, capacitors, inductors and the like, on a PCB, and the electronic components mostly need to be packaged to improve reliability and assemblability, such as LED packaging, sensor packaging, chip packaging and the like, but the existing packaging technology of devices such as photoelectric devices, semiconductor devices and the like and the SMT patch technology of the electronic components have the problems of low intelligent degree, difficult control of yield, difficult real-time monitoring of equipment, difficult online screening of sample flaws and the like.

The foregoing is provided merely for the purpose of facilitating understanding of the technical solutions of the present invention and is not intended to represent an admission that the foregoing is prior art.

Disclosure of Invention

The invention mainly aims to provide a process treatment method, device and equipment for electronic components and a storage medium, aiming at improving the automation and the intellectualization degree of the electronic component packaging and SMT (surface mount technology) process treatment, thereby improving the yield and the production efficiency of products produced by the packaging and the SMT process.

In order to achieve the above object, the present invention provides a method, an apparatus, a device, and a storage medium for processing an electronic component, including:

Industrial data of production equipment and raw materials are collected, wherein the production equipment is used for carrying out surface mounting and/or packaging on electronic components;

Carrying out data preprocessing on the industrial data to obtain preprocessed industrial data;

establishing a process parameter analysis model based on the preprocessed industrial data;

Generating optimized process parameters based on the process parameter analysis model;

And adjusting the technological parameters of the production equipment patch and/or the packaging electronic component according to the optimized technological parameters.

Optionally, the industrial data of the production apparatus and the raw material include physical information change data of the production apparatus and the raw material, image data of the production apparatus and the raw material, and the step of collecting the industrial data of the production apparatus and the raw material includes:

sensing a change signal of physical information of the production equipment and the raw material and an image light signal;

And after the change signals and the image light signals are subjected to photoelectric analysis processing, converting the change signals and the image light signals into physical information change data of production equipment and raw materials and image data of the production equipment and the raw materials.

Optionally, the step of performing data preprocessing on the industrial data to obtain preprocessed industrial data includes:

Performing abnormality detection on the industrial data, and performing data cleaning processing based on the abnormality detection result;

And carrying out data classification processing on the industrial data after the data cleaning processing to obtain the industrial data after the pretreatment.

Optionally, the preprocessed industrial data includes preprocessed production plant data and preprocessed raw material data, and the step of building a process parameter analysis model based on the preprocessed industrial data includes:

establishing a production equipment process parameter analysis model based on the preprocessed production equipment data;

and establishing a raw material process parameter analysis model based on the pretreated raw material data.

Optionally, the step of performing data analysis and modeling on the preprocessed industrial data to obtain production adjustment data further includes:

forming an industrial microservice component library based on the preprocessed industrial data;

and constructing a data visualization billboard and a production application platform based on the industrial micro-service component library.

Optionally, the step of generating optimized process parameters based on the process parameter analysis model includes:

Generating optimized equipment process parameters based on the production equipment process parameter analysis model, wherein the optimized equipment process parameters are used for the production application platform to regulate and control the process parameters of production equipment;

Generating optimized raw material process parameters based on the raw material process parameter analysis model, wherein the optimized raw material process parameters are used for the production application platform to regulate and control the process parameters of the raw materials.

Optionally, the system further comprises a data acquisition layer, wherein the data acquisition layer comprises an industrial gateway, an edge gateway, an industrial personal computer and an intelligent controller, and the method further comprises:

Constructing an acquisition-network layer transmission protocol through the industrial gateway and the edge gateway;

Transmitting industrial data of the production equipment and raw materials to the network layer through the acquisition-network layer transmission protocol;

And carrying out state monitoring and fault prediction on the production equipment through the industrial personal computer and the intelligent controller.

Optionally, the system includes a software layer, and the step of adjusting the process parameters of the production equipment patch and/or the packaged electronic component according to the optimized process parameters includes:

And sending control instructions to corresponding production equipment according to the optimized process parameters by combining the production application platform with industrial control software and/or a system preset in the software layer, so that the production equipment executes the control instructions to adjust the process parameters of the production equipment patch and/or the packaged electronic components.

In addition, in order to achieve the above object, the present invention also provides a process treatment apparatus for an electronic component, the process treatment apparatus for an electronic component comprising:

and the acquisition module is used for: the electronic component packaging system comprises a production device and a raw material collection device, wherein the production device is used for carrying out surface mounting and/or packaging on the electronic component;

and a pretreatment module: the data preprocessing module is used for preprocessing the industrial data to obtain preprocessed industrial data;

and an analysis module: the process parameter analysis model is established based on the preprocessed industrial data;

The generation module is used for: generating optimized process parameters based on the process parameter analysis model;

and an adjustment module: and the process parameters for producing the equipment patch and/or packaging the electronic components are adjusted according to the optimized process parameters.

In addition, in order to achieve the above object, the present invention also provides a process treatment apparatus for electronic components, the apparatus comprising: the electronic component processing system comprises a memory, a processor and an electronic component processing program stored on the memory and capable of running on the processor, wherein the electronic component processing program is configured to realize the steps of the electronic component processing method.

In addition, in order to achieve the above object, the present invention also provides a storage medium having stored thereon a process program of an electronic component, which when executed by a processor, implements the steps of the process method of an electronic component as described above.

According to the process treatment method, the device, the equipment and the storage medium for the electronic components, the industrial data of the production equipment and the raw materials are collected, the industrial data are subjected to data preprocessing to obtain the preprocessed industrial data, the preprocessed industrial data are subjected to data analysis and modeling to obtain production adjustment data, and the process parameters of the surface mounting and/or packaging process of the production equipment are adjusted according to the production adjustment data, so that the automation and the intellectualization degree of the process flow for packaging the electronic components and SMT (surface mounting technology) are improved, and the yield and the production efficiency of products produced by the packaging and surface mounting technology are improved.

Drawings

FIG. 1 is a schematic diagram of a process processing apparatus for electronic components of a hardware operating environment according to an embodiment of the present invention;

FIG. 2 is a schematic diagram of a system architecture of an intelligent patch package system according to various embodiments of a process for processing electronic components of the present invention;

FIG. 3 is a flow chart of a first embodiment of a process for processing electronic components according to the present invention;

FIG. 4 is a functional block diagram and a flow chart of an intelligent manufacturing system for LED package based on industrial Internet according to a first embodiment of a process treatment method of electronic components of the present invention;

FIG. 5 is a flow chart of a second embodiment of a process for processing electronic components according to the present invention;

FIG. 6 is a flow chart of an intelligent manufacturing system for LED packages according to a second embodiment of the process for electronic components of the present invention;

FIG. 7 is a flow chart of an SMT chip intelligent manufacturing system according to a third embodiment of a method for processing electronic components according to the present invention;

fig. 8 is a schematic diagram of functional modules of a process treatment apparatus for electronic components of the present invention.

The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.

Detailed Description

It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.

The main solutions of the embodiments of the present application are: the intelligent degree, the production efficiency and the yield of the patch package manufacturing production are improved by designing specific compositions and working relations of the data acquisition layer, the network layer, the platform layer, the software layer and the application layer. The method comprises the steps of specifically collecting data of production equipment, raw materials, process parameters, industrial field environments and the like through a sensor, a camera and the like of a data collection layer, transmitting the data to a network layer through a transmission protocol, then storing and backing up the data by the network layer, transmitting the data to a platform layer for processing, cleaning, classifying, managing, analyzing and visualizing the data transmitted by the network layer by the platform layer, then analyzing and modeling the data, establishing different production application platforms, generating optimized process parameters according to the established model, combining industrial control software and systems of the different production application platforms, PLC, DSC, MES, SCADA and the like, and monitoring, controlling and optimizing a production control system formed by the production control equipment, the raw materials, the process parameters and the like according to the optimized process parameters, thereby realizing the establishment of an intelligent manufacturing system based on the industrial Internet in the specific industries of packaging, SMT (surface mount technology) and the like of specific devices such as LEDs, chips and sensors.

The embodiment of the application considers that most of the current electronic components need to be packaged to improve the reliability and the assemblability, such as the packaging of LEDs, the packaging of sensors, the packaging of chips and the like. The electronic related products and the control board card thereof are mostly assembled in the form of Surface Mount Technology (SMT) patches, such as assembling various electronic components such as LED lamp beads, driving chips, resistors, capacitors, inductors and the like on a PCB, but the existing packaging processes of devices such as photoelectric devices and semiconductor devices and SMT patches of electronic components have the problems of low intelligent degree, difficult control of yield, difficult real-time monitoring of equipment, online screening of sample flaws and the like.

Based on the above, the embodiment of the application provides a solution, by collecting industrial data of production equipment and raw materials, the production equipment is used for carrying out surface mounting and/or packaging on electronic components, carrying out data preprocessing on the industrial data to obtain preprocessed industrial data, establishing a process parameter analysis model based on the preprocessed industrial data, generating optimized process parameters based on the process parameter analysis model, and adjusting the process parameters of the surface mounting and/or packaging of the electronic components of the production equipment according to the optimized process parameters, thereby improving the automation and intelligent degree of the process flow of packaging and SMT surface mounting on the electronic components, and further improving the yield and production efficiency of products produced by the packaging and surface mounting processes.

Specifically, referring to fig. 1, fig. 1 is a schematic diagram of functional modules of a terminal device to which a process treatment apparatus for electronic components of the present application belongs.

In this embodiment, the terminal device of the process processing apparatus of the electronic component at least includes an output module 110, a processor 120, a memory 130 and a communication module 140.

The memory 130 stores therein an operating system and a process program of the electronic component; the output module 110 may be a display screen, a speaker, etc., and the communication module 140 may include a WIFI module, a mobile communication module, a bluetooth module, etc., and communicate with an external device or a server through the communication module 140.

Wherein, the process program of the electronic component in the memory 130 when executed by the processor implements the following steps:

Further, the process program of the electronic component in the memory 130 when executed by the processor further realizes the following steps:

receiving and storing the obtained industrial data of the production equipment and the raw materials through a network layer;

The industrial data of the production equipment and raw materials are transmitted to the platform layer through a pre-built platform layer wired and/or wireless network.

According to the technical scheme, the industrial data of the production equipment and the raw materials are collected, the industrial data are subjected to data preprocessing to obtain the preprocessed industrial data, the preprocessed industrial data are subjected to data analysis and modeling to obtain the production adjustment data, and the technological parameters of the surface mounting and/or packaging processes of the production equipment are adjusted according to the production adjustment data, so that the automation and the intelligentization degree of the surface mounting and packaging process of the electronic components are improved, and the yield and the efficiency of the surface mounting and packaging production are improved.

The method embodiment of the application is proposed based on the above-mentioned terminal equipment architecture but not limited to the above-mentioned architecture.

Referring to fig. 2, fig. 2 is a schematic diagram of a process treatment system (i.e., an intelligent manufacturing system for LED package based on industrial internet, hereinafter referred to as a system or an intelligent manufacturing system) of an electronic component according to the process treatment method of an electronic component of the present invention, where the system is composed of a data acquisition layer, a network layer, a platform layer, a software layer and an application layer.

Referring to fig. 3, fig. 3 is a flow chart of a first embodiment of a process treatment method for an electronic component according to the present invention, where the process treatment method for an electronic component includes:

step S1000: industrial data of production equipment and raw materials are collected, wherein the production equipment is used for carrying out surface mounting and/or packaging on electronic components;

Specifically, in order to solve the problems of low intelligent degree, difficult control of yield, difficult real-time monitoring of equipment, online screening of sample flaws and the like in the existing packaging process of devices such as photoelectric devices, semiconductor devices and the like and SMT (surface mounted technology) paster process of electronic components, the efficiency and the product yield of the electronic component packaging and SMT paster process flow can be improved by collecting, analyzing and adjusting relevant process parameters of production equipment.

Firstly, the data acquisition layer of the system can be used for acquiring related data and parameters (i.e. industrial data), the object of data acquisition can be production equipment and raw materials for electronic component packaging and/or chip mounting process treatment, for example, the production flow and related equipment and materials for LED packaging, the production equipment can comprise a die bonder, a wire bonder, a dispensing machine, an ultraviolet or high-temperature curing device, a taping machine and testing equipment, and the production raw materials can comprise a bracket, an LED chip, an adhesive, gold wires and fluorescent powder (used when white light LEDs are involved).

For example, in the packaging process and related devices and materials of the chip, the production device may include grinding device, dicing saw, dispensing machine, die bonder, wire bonding machine, AOI (Automated optical inspection, also called machine vision) inspection device, curing device, plastic packaging machine, laser marking machine, electroplating device, bar forming device, testing device, the production raw materials may include substrate, wafer, lead frame, wire (gold wire, copper wire, aluminum wire, etc.), silver paste, plastic package/epoxy, etc., or the chip, tin, PCB, FPC or flexible printed circuit board (FPC) patch process and related devices and raw materials, the production device may include printer, solder paste inspection device, chip mounter, AOI inspection device, reflow soldering high temperature furnace, glue filling machine (may be available), testing device, the production raw materials may include passive electronic components (resistor, capacitor, inductor, radio frequency device, etc.), discrete devices (diode, transistor, sensor, adhesive, etc.), chip, tin, PCB or FPC circuit board.

Industrial data (production related data and parameters) of the production equipment and raw materials involved in these patch and/or packaging process flows are collected so that the relevant processing modules of the system can either further process the collected data to obtain the required data or further process it.

Further, the industrial data of the production apparatus and the raw material in the present embodiment includes physical information change data of the production apparatus and the raw material, image data of the production apparatus and the raw material, specifically, step S1000 in the present embodiment: the collecting industrial data of the production equipment and raw materials may include:

Step S1010: sensing a change signal of physical information of the production equipment and the raw material and an image light signal;

step S1020: and after the change signals and the image light signals are subjected to photoelectric analysis processing, converting the change signals and the image light signals into physical information change data of production equipment and raw materials and image data of the production equipment and the raw materials.

Specifically, in this embodiment, the data acquisition manner of industrial data acquisition on the production equipment and the raw materials may be that the edge sensor and the industrial camera arranged at the production equipment end collect and capture the changes of the information such as light, temperature, force, image, position, distance, resistance, voltage, magnetism and the like of the production equipment and the raw materials in the production process, and in addition, the data acquisition manner may further include the operation speed of the equipment components such as a mechanical arm or a mechanical gripper for grasping and directly operating the raw materials, or the operation end temperature of the components, the temperature of the heating component, the internal gear speed of the operation component, the inclination of the blade, the temperature of the platform for placing the raw materials, the pressure value of the raw materials on the platform, the image data of each component of the production equipment, the image data of the raw materials and the like capable of reflecting the physical state of each component of the production equipment and the raw materials, and the relevant information data of the equipment and the raw materials in the production process are collected and captured, and the data are subjected to a subsequent series of processing, so as to generate various direct effects, which are helpful for improving the production quality, efficiency and maintainability, and the most direct generating effect, that the process parameters are set up according to the industrial data in this embodiment, and the process parameter is output to the process parameter analysis and the process parameter analysis.

The specific effects of these data may include various aspects, such as monitoring changes in temperature, resistance, voltage, etc., and real-time monitoring and correction of quality problems in production, and, for example, monitoring solder joint temperature and resistance during electronic component manufacturing may allow early detection of solder joint problems to reduce production of defective products.

Or the collection of process parameter variation information can be used for process optimization, for example, by tracking image data captured by an industrial camera, the machine vision system can be adjusted in real time to improve assembly accuracy.

Or fault detection and prediction, early detection and prediction of equipment faults can be achieved by monitoring the force, position and voltage changes of the equipment. This helps to reduce downtime and maintenance costs. For example, if the voltage and current of the motor suddenly deviate from normal ranges, the system may automatically alert for maintenance.

And (3) resource management: monitoring the location, resistance, and other property changes of the raw materials can help better manage inventory and logistics, for example, tracking the location and temperature of raw materials can prevent raw materials from being damaged or expired, product tracking: using the location, distance and image data, the manufacturing process of the product can be tracked, ensuring that it meets specifications and providing data support for quality control, e.g. in the food industry, the appearance and quality of the product can be checked using industrial cameras, energy efficiency: by monitoring the resistance, voltage and temperature of the device, the energy efficiency of the device can be assessed and measures taken to reduce the energy consumption, which is very important for the sustainability of manufacturing.

Step S2000: carrying out data preprocessing on the industrial data to obtain preprocessed industrial data;

Specifically, in this embodiment, in order to obtain data suitable for establishing a process parameter analysis model, noise and abnormal values in the original industrial data need to be removed, so that data quality is ensured, and further classification, management and analysis of the data are facilitated.

Further, the data acquisition layer of the intelligent manufacturing system based on the electronic component package and the patch of the industrial internet in this embodiment may include an industrial gateway, an edge gateway, an industrial personal computer and an intelligent controller, and step S2000 in this embodiment: the step of carrying out data preprocessing on the industrial data to obtain preprocessed industrial data can further comprise the following steps:

step S1030: constructing an acquisition-network layer transmission protocol through the industrial gateway and the edge gateway;

step S1040: transmitting industrial data of the production equipment and raw materials to the network layer through the acquisition-network layer transmission protocol;

Specifically, the industrial gateway and the edge gateway are two key hardware devices used in the fields of information technology and industrial automation, which play an important role in connection, management and processing of data, the industrial gateway (Industrial Gateway) is a hardware device commonly used for connecting different kinds of industrial devices and sensors into a network so as to enable data communication and remote monitoring, the devices can be various production devices, sensors, plcs (programmable logic controllers) and the like, the industrial gateway serves as a bridge for data communication, and can convert data collected from the devices into data of standard network protocols, such as MODBUS, OPC UA and the like, and then send the data into a network layer of the system through a transmission protocol so that the data can be used for monitoring, analysis and decision making, and in addition, the industrial gateway generally has security and data processing functions so as to ensure confidentiality and integrity of the data and perform a certain degree of data preprocessing when required.

Edge gateway (EDGE GATEWAY) is a special purpose hardware device for performing data processing and analysis in an edge computing environment, which is a distributed computing model that pushes data processing to locations close to the data sources to reduce latency and reduce network bandwidth requirements, is typically located near production facilities or sensors, can collect, analyze and make decisions locally without having to send all data to remote data centers or cloud platforms, is useful for applications requiring low latency decisions, such as industrial automation, internet of things (IoT) applications, etc., and can communicate with various protocols and devices and often has storage, computing and communication capabilities to meet local processing requirements. The edge gateway may also execute a machine learning model to enable real-time prediction and optimization.

Establishing a data transmission protocol between the data acquisition layer and the network layer is a very critical step in intelligent packaging and patch systems, and the transmission protocol allows data to be transmitted from the data acquisition layer (including an industrial gateway and an edge gateway) to the network layer for further processing and analysis, in this embodiment, the establishment of the transmission protocol may adopt the following procedures:

determining transmission requirements and protocol types: first, the requirements of the transmission, including data type, transmission frequency, security requirements, etc., need to be well defined, and then the protocol type is selected to suit these requirements.

Selecting a transmission protocol: at the data acquisition layer, the industrial gateway and edge gateway may need to select an appropriate transmission protocol, which may be a standard industrial communication protocol, such as MODBUS, OPC UA, or may be a custom protocol, depending on the specific requirements.

And (3) protocol design: if the custom protocol is needed, the data packet structure, the communication rules and the data processing rules of the protocol are designed. This includes defining a header, a packet body, a checksum and other control information.

Data acquisition and packaging: the industrial gateway and the edge gateway are responsible for collecting various data, including temperature, resistance, force, images, etc., and at this stage, the collected data is encapsulated according to the data packet format specified by the protocol.

And (3) data transmission: the encapsulated packets will be transmitted via the network layer communication protocol, which may be ethernet, wi-Fi, loRaWAN, MQTT, etc., depending on the physical connection and communication requirements of the system.

Data reception and parsing: at the network layer, after receiving the data, parsing is required to restore the data to a usable format, which includes decapsulating the data packets, error detection, and correction.

Data storage and processing: the parsed data may be stored in a database or further processed and analyzed, which may include aggregation, statistics, graphical presentation of the data, and the like.

Security and authentication: throughout the transmission, it is necessary to ensure confidentiality and integrity of the data. Thus, security measures such as encryption and digital signature may be considered to prevent data leakage or tampering.

Real-time monitoring and fault handling: after the transport protocol is established, the transport process needs to be monitored in real time to detect any errors or faults. If a problem occurs, the system should be able to take appropriate action, such as retransmitting the data or notifying an administrator.

For example, if the system needs to transmit temperature sensor data, a custom transmission protocol may be used, where the protocol defines a data packet format, including information such as temperature values, sensor IDs, time stamps, etc. After the industrial gateway and the edge gateway collect temperature data, the data are packaged according to a protocol format and then transmitted to a network layer through an Ethernet protocol. At the network layer, the data packets are received, unpacked, and stored in a database, and the data can be used for applications such as monitoring temperature in real time, drawing trend graphs, or performing temperature control.

In summary, establishing a transmission protocol is a key step in ensuring efficient, reliable and secure transmission of data in intelligent packaging and patch systems, and corresponding protocols need to be selected and designed according to specific requirements and characteristics of the system.

In addition, referring to fig. 2, the system network layer in this embodiment is mainly responsible for networking production devices, data network transmission, data storage, and transmission protocol construction, including several or all of workshop transmission network (5G, wireless), MEC (Multi-ACCESS EDGE computing Multi-access edge computing) edge cloud, data center, local area network, server, industrial internet identification analysis, data uplink synchronization, and model downlink synchronization, where the network layer connects the data acquisition layer and the platform layer, and transmits the data acquired and processed by the data acquisition layer to the platform layer through wireless or wired network, and stores the data in the server to avoid data loss.

Step S1050: and carrying out state monitoring and fault prediction on the production equipment through the industrial personal computer and the intelligent controller.

Industrial personal computers and intelligent controllers in the field of intelligent manufacturing are two key hardware devices for automating, monitoring and controlling the manufacturing process, which play an important role in industrial automation and intelligent manufacturing.

Industrial PC (IPC): industrial personal computers are a special purpose computer commonly used to monitor and control industrial processes. Industrial computers typically have higher durability, reliability, and tamper resistance than ordinary desktop computers to accommodate the needs of an industrial environment, are typically installed on production lines, can perform a number of tasks such as data acquisition, monitoring, data processing, control system operation, human-machine interface (HMI), etc., are typically industry-level standards such as IP65 protection, vibration resistance, and shock resistance to accommodate the harsh conditions of a factory environment, are typically run specific industrial control software such as SCADA (Supervisory Control and Data Acquisition) systems to monitor and control production processes by operators, and plcs (programmable logic controllers), etc.

And (3) an intelligent controller: an intelligent controller is an embedded control device for real-time monitoring, analysis and control of a production process, which is commonly used in large automation systems, such as factory automation, machine control, process control, etc., and generally comprises a microprocessor, a memory, an input/output interface, and a specific control algorithm. They are designed to be high performance, real-time response and programmable to meet complex control requirements, with intelligent controllers ranging in application from traditional plcs to more advanced industrial controllers such as Distributed Control Systems (DCS) and Programmable Automation Controllers (PAC).

The industrial personal computer and the intelligent controller work cooperatively, the industrial personal computer can provide a human-computer interface for monitoring and controlling operators, and meanwhile, the intelligent controller is responsible for real-time control and data processing of the bottom layer.

In short, the industrial personal computer and the intelligent controller are key devices in the intelligent manufacturing field, and work cooperatively to realize automation and intelligent control, so that the production efficiency and quality are improved.

Step S3000: establishing a process parameter analysis model based on the preprocessed industrial data;

specifically, in this embodiment, in order to more specifically adjust the process parameters of the production equipment and adjust the materials or the materials for the raw materials, a process parameter analysis model of the production equipment and a process parameter analysis model of the raw materials are respectively established to generate the corresponding optimized process parameters of the production equipment and the optimized process parameters of the raw materials, and the process parameter analysis model of the production equipment is used for example, after the original industrial data of the production equipment collected by the data collection layer is subjected to data cleaning (identifying and processing missing data, abnormal values and repeated data), key features related to the performance of the production equipment are selected first. This may include parameters such as temperature, voltage and speed at specific operating conditions, and then feature engineering to further improve the availability of data, as target variables for process parameter analysis models after determining production efficiency metrics such as production speed, yield or energy consumption that need to be optimized.

The data is then divided into different categories, e.g., different types of production equipment or different production conditions, and a regression model is built for each production equipment category to predict the relationship between the target variable (production efficiency) and the process parameters, linear regression, multiple linear regression, or other regression methods may be used.

Model training: the model is trained using historical data, which refers to industrial data collected by the data collection layer prior to modeling, which is transmitted to the network layer for storage, to learn the relationship between process parameters and production efficiency.

Model evaluation: test data is used to evaluate the performance of the model, including indicators of mean square error, decision coefficients, etc. Ensuring that the predictions of the model are consistent with the actual results.

Optimizing process parameters: once the model is validated, you can use it to generate optimized process parameters. The influence of different parameter combinations on the production efficiency is analyzed through a model, and parameters capable of maximizing the efficiency are selected.

Implementation and monitoring: the optimized parameters are applied to production equipment, and a real-time monitoring mechanism is established to ensure that the improvement of the efficiency is continuously and effectively. The model is updated periodically to accommodate the changes.

Through the steps, the process parameter analysis model of the production equipment is established to optimize the process parameters so as to improve the production efficiency, the optimized process parameters are generated according to the process parameter analysis model, and then the related parameters of the production equipment are adjusted according to the optimized process parameters, so that the production cost is reduced, the yield is improved, the equipment is ensured to operate in an optimal state, and the higher production efficiency is realized.

Further, step S3000 in the present embodiment: the process parameter analysis model established based on the preprocessed industrial data can further comprise:

Step S3020: forming an industrial microservice component library based on the preprocessed industrial data;

step S3030: and constructing a data visualization billboard and a production application platform based on the industrial micro-service component library.

Specifically, referring to fig. 2, a system on which an embodiment of a process treatment method for an electronic component depends includes a platform layer, wherein main operations of the platform layer include forming different industrial microservices component libraries (industrial knowledge, algorithms, mechanism model components) based on various collected data, then constructing different platforms including an information sharing platform (data visualization signboard), a collaborative manufacturing platform, a fault treatment platform, a resource management platform, a big data analysis platform, and an application development platform (development tool: compiling, packing, deploying, microservice), specifically, the platform construction method includes accessing industrial data collected from a data collection layer into the platform through an industrial big data system, performing cleaning, classifying, managing, analyzing, visualizing, and the like, and then performing machine learning, model training (experience model, process parameter model, mechanism model, and the like), defect identification, intelligent sorting, and the like through a data analysis and modeling system, so as to realize functions of process optimization, energy consumption optimization, parameter regulation, safety inspection, equipment maintenance and the like.

Step S4000: generating optimized process parameters based on the process parameter analysis model;

step S5000: and adjusting the technological parameters of the production equipment patch and/or the packaging electronic component according to the optimized technological parameters.

Specifically, referring to fig. 2, the intelligent manufacturing system for packaging and mounting electronic components based on industrial internet in the embodiment of the process processing method for electronic components of the present invention includes a software layer and an application layer, where production control software and a production control system are preset in the software layer, and these software and systems monitor, control and optimize production process parameters and equipment states of a production device together by cooperating with an application platform formed by processed industrial data in the above steps, where the method adopted for controlling and optimizing generates corresponding optimized process parameters, such as optimized operation speed parameters of the production device, by using a process parameter analysis model of the production device and raw materials, and sends the optimized parameters to the corresponding production application platform and industrial control software, and new parameters are adopted for operation of the production device corresponding to coordinated control of the production application platform and the industrial control software, so as to perform production operation.

More specifically, development design software and information management software in the software layer are generally used or run alone and are not directly related to the intelligent manufacturing system, while production control software in the software layer is generally used for production site management and control and has a direct close relationship with the intelligent manufacturing system, such as storing instructions for performing operations of logical operations, sequential control, timing, counting, arithmetic operations and the like in the software layer through Programmable Logic Control (PLC) design, and controlling the execution of actions of various types of mechanical devices through digital or analog input and output.

For example, more complex industrial processes with longer transmission distances are performed by a distributed control system DSC, different areas of the whole industrial process are controlled by different dedicated controllers, the controllers are interconnected by a high-speed communication network and are connected to an industrial control computer, and field devices communicate with the controllers of the specific control areas, and overall control, monitoring, data recording and alarm functions are performed on the industrial control computer.

The manufacturing execution system MES is a manufacturing collaborative management platform and a production informatization management system, and can provide the functions of management modules such as manufacturing data management, planning scheduling management, production scheduling management, inventory management, quality management, human resource management, work center/equipment management, tool tooling management, purchasing management, cost management, project billboard management, production process control, bottom data integration analysis, upper layer data integration decomposition and the like.

The human-computer interaction interface HMI is used for providing the functions of visual management, on-site instruction operation, fault monitoring, equipment control software touch operation and the like.

The SCADA is a software interface, can be used for executing data acquisition and indirectly controlling and monitoring various devices and parameters in a factory, is matched with a PLC, cannot directly communicate with the field device, and sends a command to the field device through the PLC, industrial field device data enter an I/O module in the PLC and are stored in a specific memory position or a register, the SCADA reads or writes the memory position, and then the PLC realizes specific control of the device.

The application layer is based on the application of the data acquisition layer, the network layer, the platform layer and the software layer, and comprises application of research and development of APP running of specific businesses such as design, production, management, sales service and the like, application of industrial data analysis such as equipment monitoring, energy consumption analysis, intelligent diagnosis, supply chain management and the like, and application of specific device packaging such as LEDs, chips, sensors and the like and specific industries such as SMT (surface mounted technology) patches and the like.

Further, referring to fig. 4, fig. 4 is a schematic diagram of a functional module and a flow chart of an industrial internet-based LED package intelligent manufacturing system according to the present embodiment, in an industrial internet-based electronic component package and patch intelligent manufacturing system, the industrial internet-based electronic component package and patch intelligent manufacturing system includes a data acquisition layer, a network layer, a platform layer, a software layer and an application layer, wherein the data acquisition layer acquires data of production equipment, raw materials, process parameters, an industrial site environment and the like through a sensor, a camera and the like, and then transmits the data to the network layer through a transmission protocol, and then the network layer stores and backs up the data and then transmits the data to a platform layer for processing, and the platform layer cleans, classifies, manages and analyzes the data transmitted by the network layer, then performs data analysis and modeling, includes results of big data analysis, model training, defect identification, component library establishment, model algorithm and the like, process optimization, energy consumption optimization, parameter regulation, safety inspection, equipment maintenance monitoring and the like, and then forms different application platforms of data visualization board, collaborative manufacturing platform, fault processing platform, resource management platform and the like, and industrial control software of different application platforms and PLC, DSC, MES, SCADA and the like, and the industrial control software of the control platform and the system are combined, and the industrial control system is implemented, and the control system is implemented to implement the production control equipment, the SMT control system, the production chip manufacturing system and the chip and the specific control system is based on the industrial chip, the industrial chip and the manufacturing system is optimized and the specific and the chip-based on the manufacturing system.

In this embodiment, the industrial data is acquired and preprocessed to obtain preprocessed industrial data, and the preprocessed industrial data is subjected to data analysis and modeling to obtain production adjustment data, and the technological parameters of the surface mount technology and/or the packaging process of the production equipment are adjusted according to the production adjustment data, so that the automation and the intelligence degree of the surface mount technology and the packaging technology of the electronic components are improved, and the yield and the efficiency of packaging and surface mount technology are improved.

Further, referring to fig. 5, fig. 5 is a flow chart of a second embodiment of the process treatment method for electronic components according to the present invention, based on the embodiment shown in the foregoing fig. S2000: the step of performing data preprocessing on the industrial data to obtain preprocessed industrial data may include:

step S2010: performing abnormality detection on the industrial data, and performing data cleaning processing based on the abnormality detection result;

Step S2020: and carrying out data classification processing on the industrial data after the data cleaning processing to obtain the industrial data after the pretreatment.

Specifically, to ensure the quality, accuracy and availability of data so that the subsequent data analysis and modeling process can be performed efficiently, the raw industrial data first needs to be subjected to data preprocessing, which may include the following processes:

Noise and error removal: various noise, outliers, errors, or inconsistencies may be included in the raw industrial data. Data cleansing can identify and reject these problems, ensure data reliability, and the presence of noise and errors can unnecessarily interfere with subsequent analysis, leading to erroneous conclusions.

Missing data processing: in raw data, there may be missing data points that may be due to equipment failure, sensor failure, or other reasons, and data cleansing includes processing the missing data to ensure the integrity and accuracy of the analysis process.

Reduction of duplicate data: the original data may contain duplicate records, which may be caused by duplicate acquisition, storage or data transmission problems, and the removal of duplicate data helps to reduce the size of the data set and improve analysis efficiency.

Data consistency: data cleansing helps ensure consistency of data among different fields or data sources, including ensuring date format consistency, unit standard consistency, and data naming consistency, among others.

And (3) checking a data format: data cleansing may check whether the format and structure of the data is compliant to ensure the integrity of the data. This includes verifying the correct format of the date, time, number and text fields.

And (3) improving data quality: through data cleaning, the data quality can be improved, so that the accuracy of subsequent analysis and modeling is improved, and the high-quality data is helpful for better understanding and predicting the production process.

The analysis efficiency is improved: removing invalid data and erroneous data can reduce the computational burden of analysis and modeling, improve analysis efficiency, and in addition, the cleaned data is easier to process and understand.

Among them, the most critical preprocessing, i.e., data cleaning process, is different from the conventional data cleaning in terms of method and object in the industrial manufacturing field of data cleaning, compared with the conventional data cleaning, mainly due to the data characteristics and requirements in the industrial manufacturing field, for example, the following aspects may be included:

Data type: the field of industrial manufacturing generally involves time series data generated by sensors, such as temperature, humidity, pressure, vibration, etc., which are different from conventional structured data (e.g., database records), and thus, in the field of industrial manufacturing, data cleansing may involve specific techniques such as time series data processing, anomaly detection, and data interpolation.

Real-time requirements: industrial manufacturing typically requires real-time monitoring and responding to the production process, and therefore, data cleaning requires greater real-time in an industrial environment to ensure that problems are detected and actions taken in a timely manner. This is different from the more static processing approach in conventional data cleansing.

Noise and outliers: noise and outliers, such as vibrations or sudden events in the sensor data, often exist in industrial manufacturing environments, and data cleansing requires special consideration of these circumstances and appropriate techniques to process or filter them.

And (3) equipment fault treatment: in industrial manufacturing, equipment failure may result in inaccurate or incomplete data, and therefore, data cleansing needs to include detecting and handling data anomalies caused by equipment failure to maintain data quality.

Maintainability: industrial manufacturing facilities often require long-term operation, so the method of data cleaning requires consideration of data persistence and maintainability, and ensuring stability and repeatability of the data cleaning process is a key factor.

Networking equipment: devices in industrial manufacturing are typically interconnected using industrial internet of things (IIoT) technology, and thus data cleansing may involve processing data streams from multiple devices and sensors.

Unlike traditional data cleansing, which focuses more on structured data and data warehouses for business analysis and reporting, data cleansing in the field of industrial manufacturing is more specialized, focusing on real-time, equipment failure, noise and time series data, the goal of cleansing industrial data is to ensure stability, safety and quality of the production process.

Therefore, the data cleansing of the industrial data collected by the data collection layer in the present embodiment may involve cleansing of sensor data collected from the production process or production records, for example, data acquired by sensors for monitoring the temperature and humidity on the production line, the sensors collecting data once every second and saving it to a database, however, the following problems may occur in the data:

Noise and outliers: sensor data may be subject to noise, such as device vibration, electromagnetic interference, or sensor drift, which may lead to abnormal or unstable conditions in the temperature and humidity data.

Data loss: due to communication problems or sensor failures, certain data points may be lost, possibly resulting in incomplete data, which is difficult to analyze.

Repeat data: there may be duplicate data in the database due to duplicate data records that may occur due to multiple insertions of the same data or other reasons.

Unit conversion: the data may be expressed in different units, such as degrees celsius and degrees fahrenheit, humidity percentages, and relative humidity, and unit conversion is required during the data cleaning process to ensure consistency.

Specifically, the data cleaning in this embodiment may include the following steps:

Abnormal value detection: outliers are detected and processed using statistical methods or thresholds, such as replacing them with averages of previous and subsequent data points.

And (3) data interpolation: for missing data points, interpolation methods may be used to populate the data, such as linear interpolation or mean interpolation.

Duplicate data is removed: duplicate data records in the database are detected and removed to ensure the uniqueness of the data.

Unit standardization: the units of data are unified into one standard unit for consistent analysis.

Checking a data format: verifying that the data is in the correct format and type, e.g., ensuring that the temperature data is of a digital type, that the date is in the correct format, etc.

The quality of the finally obtained target industrial data can be ensured by cleaning the data, the error in analysis is reduced, the reliability and maintainability of the production process are improved, the cleaned data can be used for production optimization, quality control, fault detection and the like, and preconditions are provided for subsequent data classification, data management, data analysis and data visualization.

Further, step S3000 in the present embodiment: establishing a process parameter analysis model based on the preprocessed industrial data may include:

step S3010: establishing a production equipment process parameter analysis model based on the preprocessed production equipment data;

step S3020: establishing a raw material process parameter analysis model based on the pretreated raw material data;

Specifically, in the process of processing industrial data to obtain production adjustment data, a plurality of key links are involved, each link depends on different technologies and methods, firstly, large data analysis is performed on the industrial data after pretreatment, and distributed computation (such as Hadoop and Spark), data warehouse establishment, target data mining, machine learning, statistical analysis and the like can be included, so that a large amount of industrial data is processed, and key insights, detection trends and potential problems are extracted, which are key steps of decision making and production optimization.

Then data modeling and model training, including statistical modeling, machine learning modeling, deep learning, time series analysis, etc., are used to capture patterns and associations in the data for further prediction, classification and defect detection, and model training requires data preparation, feature engineering, cross validation, super parameter adjustment, and is a key step to ensure accuracy of the machine learning model, and data quality and applicability need to be considered.

Then defect identification, image processing techniques, deep learning, image classification, etc. can be used to detect product defects in production, ensure quality control and reduce waste.

And then may also include the creation of component libraries, possibly involving database management systems (DBMS), data warehouse, metadata management, and version control, for storing production parameters, models, algorithms, and other relevant information for reuse and maintenance.

Model algorithm design, including selecting proper machine learning algorithms, feature engineering, model evaluation and adjustment, directly affects the performance of the model, and requires the selection and adjustment of algorithms according to the requirements of the problem.

Finally, the intelligent data sorting and packaging process is performed, wherein the intelligent data sorting may involve automation equipment, machine vision, sensor technology and the like, and the intelligent data sorting may be used for sorting products into different categories so as to enable the products to meet quality standards, and production adjustment data required by a system for adjusting production process parameters of production equipment are obtained so as to perform subsequent processing.

Wherein big data analysis and data modeling provide key insights and models for decisions, and model training and model algorithms are designed to ensure that these models operate efficiently in an actual production environment, defect identification also helps to reduce the reject rate and improve product quality.

Further, step S4000 of the present embodiment: generating optimized process parameters based on the process parameter analysis model may include:

step S4010: generating optimized equipment process parameters based on the production equipment process parameter analysis model, wherein the optimized equipment process parameters are used for the production application platform to regulate and control the process parameters of production equipment;

Step S4020: generating optimized raw material process parameters based on the raw material process parameter analysis model, wherein the optimized raw material process parameters are used for the production application platform to regulate and control the process parameters of the raw materials.

Specifically, in this embodiment, in order to more specifically adjust the relevant parameters of the operation or production state of the production apparatus, such as the operation speed of the production apparatus, the temperature of the key components, etc., and the relevant parameters of the raw materials, such as the raw material consumption and the raw material addition speed, etc., a model needs to be built for the production apparatus and the raw materials to analyze their process parameters and generate optimized process parameters, respectively, so as to improve the efficiency of the production process.

First, data preprocessing, including data cleaning, sorting, and management, is required for the raw industrial data collected, including the industrial data of the production equipment and raw materials.

Then, a suitable analysis method such as regression analysis, decision tree or deep learning model is selected depending on the data and the target, for example, when there is a linear relationship between the production efficiency and the process parameters such as the production efficiency increases linearly with increasing temperature, a linear regression model may be used to establish the relationship.

When multiple process parameters affect production efficiency together, multiple linear regression may be used to capture the relationship between the multiple parameters, e.g., production efficiency is affected by a combination of temperature, voltage, and speed, multiple linear regression models may be used.

Support vector regression is applicable to complex nonlinear relationships that can be more flexibly adapted to different data distributions, e.g., the relationship between production efficiency and process parameters may not be linear, and support vector regression can be used to more accurately capture such relationships.

For another example, decision tree regression is applicable to the problem of interaction between nonlinear relationships and complex features, and if there is an interaction effect between process parameters, a model of the nonlinear relationships can be established by using decision tree regression.

Neural network regression is suitable for processing large amounts of data and complex patterns, it can learn nonlinear relationships, if the data is very complex, including multiple process parameters and complex interactions, and can be used to build models that fit complex data.

For a specific process of modeling process parameters, for example, regression analysis is selected to be used for modeling, the following are some key steps:

Data preparation: and (3) sorting the industrial data of the production equipment after cleaning, classifying and managing into a format suitable for analysis. This may include selecting appropriate features (parameters) and target variables.

Training data set: the data is divided into a training data set and a test data set. The training data set is used to train the model and the test data set is used to evaluate the model performance.

Characteristic engineering: feature engineering is performed, including feature selection, scaling, and conversion. This helps to improve the performance of the model.

And (3) establishing a regression model: an appropriate regression model, such as linear regression, multiple linear regression, or support vector regression, is selected and the model is trained using training data.

Model evaluation: the test dataset is used to evaluate the performance of the model, including indicators of Mean Square Error (MSE), decision coefficients (R), etc.

Optimizing a model: and adjusting and optimizing the model according to the evaluation result to obtain the optimal process parameter analysis model.

Model deployment: the model is deployed into the actual production environment to analyze and optimize the process parameters in real time.

With respect to the process parameter analysis model of the raw material, for example, a model is built to analyze the process parameters of the raw material to improve the quality of the raw material, the following steps are performed:

Data preprocessing: raw material industry data is cleaned, missing data and outliers are processed, and the data is classified into different categories (e.g., different types of raw materials).

Characteristic engineering: characteristics for analysis, such as chemical composition, size, temperature, etc., of the raw materials are determined. Feature selection may also be performed to exclude irrelevant features.

Data classification: the data is divided into different categories according to the type of raw material to build a separate analytical model for each raw material.

Establishing an analysis model: a corresponding analytical model is built for each raw material class. This may include statistical analysis, data mining, or machine learning methods, depending on the nature of the problem.

Model evaluation: the performance of each model is evaluated using the test dataset to ensure its effectiveness.

Model optimization: and adjusting and optimizing the model according to the evaluation result to obtain the optimal raw material process parameter analysis model.

Model deployment: the model is deployed into a raw material production flow to analyze raw material quality in real time and provide feedback to improve process parameters.

In this embodiment, the anomaly detection is performed on the industrial data, the data cleaning process is performed based on the result of the anomaly detection, the data classification process is performed on the industrial data after the data cleaning process, the pretreated industrial data is obtained, the production equipment process parameter analysis model is built based on the pretreated production equipment data, the raw material process parameter analysis model is built based on the pretreated raw material data, so that the data quality and the reliability are improved, the accuracy of subsequent analysis and modeling is ensured, in addition, the relation between the process parameters and the production efficiency is accurately reflected, and the optimal parameter combination of the analysis model is used for improving the production efficiency, so that the yield and the production efficiency of products produced by the packaging and pasting process are improved.

Further, referring to fig. 6, fig. 6 is a schematic diagram of functional modules and a flow of an intelligent manufacturing system according to a first embodiment of a process for processing an electronic component according to the present invention, and referring to the embodiment shown in fig. 3, one implementation manner of the present invention is an industrial internet-based LED package intelligent manufacturing system, and as shown in fig. 5, LED packages may be divided into SMD (Surface mounted devices) packages and COB (Chips on board) packages according to different package types.

The SMD package generally uses a bracket as a substrate, and finally obtains discrete LED single beads, which belong to point light sources, and the beads are then made into lighting, display or backlight products by using a surface mount technology, wherein the SMD package technology comprises die bonding, wire bonding, dispensing, testing, curing, sorting, taping and testing.

The COB package generally adopts a ceramic substrate or PCB with printed wiring as a substrate, and wire bonding is not needed, so that the LED lamp surface is finally obtained, a surface light source is formed, and the COB package process comprises dispensing, die bonding, testing, curing, glue filling and packaging and testing.

The LED packaging intelligent manufacturing system based on the industrial Internet is characterized in that a displacement sensor, a speed sensor and an industrial camera are arranged at the end of equipment, data and image information are collected by the industrial camera, and the data collected by the sensor and the industrial camera, process parameter data of the equipment, environment data and LED lamp bead performance test data are collected and stored through a network layer and then transmitted to a platform layer in the data collecting and transmitting process.

The platform layer processes (cleans, classifies, manages, analyzes and visualizes) the received data, and then performs data modeling, model training, defect recognition, algorithm design, intelligent sorting and packaging based on the processed data to obtain parameters and data required by process optimization, parameter adjustment and equipment detection.

PLC, DSC, MES, SCADA and other industrial control software and systems send control instructions to equipment in corresponding control areas according to the parameters and data after the optimization of the platform layer, the corresponding equipment executes instruction operation to complete adjustment and optimization of technological parameters, and meanwhile, a visual billboard monitors all technological parameters in real time, ensures consistency with the designed optimal technological parameters, and ensures that all technical indexes of semi-finished products and finished LED lamp beads obtained through encapsulation reach standards.

When the visual billboard monitors that the technological parameters are inconsistent with the designed optimal technological parameters in real time or the technical indexes of the semi-finished product and the finished product LED lamp bead obtained by encapsulation are not up to the standard, the platform layer is required to process and optimize the received data again, the previous actions are repeated, and the technological parameters of the corresponding equipment are regulated until the optimal technological parameters are reached and the technical indexes of the semi-finished product and the finished product LED lamp bead obtained by encapsulation are ensured to be up to the standard.

In the embodiment, the key industrial data of the LED package production equipment and raw materials, the environmental data, the test data and other data are collected, analyzed and processed, so that parameters and data required by process optimization, parameter adjustment and equipment monitoring are obtained, and then control instructions are sent out by combining equipment in corresponding control areas such as industrial control software to adjust the equipment parameters and the flow of data control production, so that the efficiency of LED package production and the product yield are improved.

Further, referring to fig. 7, fig. 7 is a schematic diagram of functional modules and a flow of an intelligent manufacturing system according to a second embodiment of a process for processing electronic components of the present invention, and referring to the embodiment shown in fig. 5, one implementation of the process is an SMT chip intelligent manufacturing system based on the industrial internet, as shown in fig. 6, an SMT chip process is generally used for assembling a printed circuit board and related components (PCBA, printed circuit board assembly), and a designed circuit is manufactured on the PCB.

The SMT chip mounting process comprises solder paste printing, online solder paste detection (SPI, solder paste inspection), electronic component chip mounting, AOI detection, reflow soldering, testing, glue filling (a small part of products may be available) and testing.

An SMT paster intelligent manufacturing system based on industrial Internet is characterized in that displacement sensors, speed sensors and cameras are deployed on a printer and a paster machine, an on-line solder paste detection SPI and a machine vision AOI detection procedure are added, technological parameters are controlled, temperature and humidity are controlled, intelligent sorting and selection are performed, and intelligent carrying and feeding and discharging are set as data acquisition sources. The data acquisition and transmission process is to collect and store the data acquired by the sensor and the camera, the data and the image detected by the SPI and the AOI on line, the process parameter data of the equipment, the environment data and the electrical performance test data of the PCBA after being pasted to the platform layer through the network layer. The platform layer cleans, classifies, manages, analyzes and visualizes the received data, and then carries out data modeling, model training, defect identification, algorithm design, intelligent sorting and packaging based on the processed data to obtain parameters and data required by process optimization, parameter adjustment and equipment detection.

PLC, DSC, MES, SCADA and other industrial control software and systems send control instructions to equipment in corresponding control areas according to the parameters and data after the platform layer is optimized, the corresponding equipment executes instruction operation to complete adjustment and optimization of technological parameters, and meanwhile, a visual billboard monitors all technological parameters in real time, ensures consistency with the designed optimal technological parameters, and ensures that all technical indexes of semi-finished products and finished PCBA obtained by SMT patches reach standards.

When the visual billboard real-time monitoring shows that each technological parameter is inconsistent with the designed optimal technological parameter or each technical index of the semi-finished product and the finished product PCBA obtained by the SMT paster is not up to the standard, the platform layer is required to be processed and optimized again, the previous actions are repeated, and the technological parameters of the corresponding equipment are regulated until the optimal technological parameter is reached and each technical index of the semi-finished product and the finished product PCBA obtained by the SMT paster is ensured to be up to the standard.

In this embodiment, the process optimization, parameter adjustment, and equipment monitoring are obtained by collecting, analyzing and processing the key industrial data of the SMT patch production equipment and raw materials, the environmental data, the test data, and other data, and then the equipment in the corresponding control area of the industrial control software is combined to send a control instruction to adjust the equipment parameters and the flow of the data control production, so that the SMT patch production efficiency and the product yield are improved.

In addition, referring to fig. 8, an embodiment of the present invention further provides a process processing apparatus 80 for an electronic component, where the system includes:

the acquisition module 81: the electronic component packaging system comprises a production device and a raw material collection device, wherein the production device is used for carrying out surface mounting and/or packaging on the electronic component;

The preprocessing module 82: the data preprocessing module is used for preprocessing the industrial data to obtain preprocessed industrial data;

Analysis module 83: the process parameter analysis model is established based on the preprocessed industrial data;

the generation module 84: generating optimized process parameters based on the process parameter analysis model;

the adjustment module 85: and the process parameters for producing the equipment patch and/or packaging the electronic components are adjusted according to the optimized process parameters.

In addition, the embodiment of the invention also provides process treatment equipment of the electronic component, which comprises the following steps: the processing system comprises a memory, a processor and a processing program of the electronic component, wherein the processing program of the electronic component is stored in the memory and can run on the processor, and the processing program of the electronic component is configured to realize the steps of the processing method of the electronic component.

In addition, the invention also provides a computer readable storage medium, wherein the storage medium stores a process processing program of the electronic component, and the process processing program of the electronic component realizes the steps of each embodiment of the process processing method of the electronic component when being executed by a processor.

In the embodiments of the system, the terminal device and the computer readable storage medium of the present invention, all technical features of each embodiment of the process treatment method of the electronic component are included, and the expansion and explanation contents of the description are substantially the same as each embodiment of the process treatment method of the electronic component, which are not described herein.

It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.

The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.

From the above description of embodiments, it will be clear to a person skilled in the art that the above embodiment method may be implemented by means of software plus a necessary general hardware platform, but may of course also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) as described above, comprising instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method according to the embodiments of the present invention.

The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.

Claims

1. A process treatment method for an electronic component, wherein the method is applied to a process treatment system for an electronic component, the method comprising the steps of:

adjusting the technological parameters of the production equipment patch and/or the packaged electronic component according to the optimized technological parameters;

The industrial data of the production equipment and the raw material include physical information change data of the production equipment and the raw material, image data of the production equipment and the raw material, and the step of collecting the industrial data of the production equipment and the raw material includes: sensing a change signal of physical information of the production equipment and the raw material and an image light signal; after the change signal and the image light signal are subjected to photoelectric analysis processing, the change signal and the image light signal are converted into physical information change data of production equipment and raw materials and image data of the production equipment and the raw materials;

The step of preprocessing the industrial data to obtain preprocessed industrial data comprises the following steps: performing abnormality detection on the industrial data, and performing data cleaning processing based on the abnormality detection result; carrying out data classification treatment on the industrial data after the data cleaning treatment to obtain the industrial data after the pretreatment;

The pretreated industrial data comprises pretreated production equipment data and pretreated raw material data, and the step of establishing a process parameter analysis model based on the pretreated industrial data comprises the following steps: establishing a production equipment process parameter analysis model based on the preprocessed production equipment data; establishing a raw material process parameter analysis model based on the pretreated raw material data;

The system comprises a data acquisition layer, wherein the data acquisition layer comprises an industrial gateway, an edge gateway, an industrial personal computer and an intelligent controller, and the step of preprocessing the industrial data to obtain preprocessed industrial data further comprises the following steps: constructing an acquisition-network layer transmission protocol through the industrial gateway and the edge gateway; transmitting industrial data of the production equipment and raw materials to a network layer through the acquisition-network layer transmission protocol; the industrial personal computer and the intelligent controller are used for carrying out state monitoring and fault prediction on the production equipment;

the step of preprocessing the industrial data to obtain preprocessed industrial data further comprises the following steps: forming an industrial microservice component library based on the preprocessed industrial data; constructing a data visualization billboard and a production application platform based on the industrial micro-service component library;

The system comprises a software layer, and the step of adjusting the process parameters of the production equipment patch and/or the packaged electronic component according to the optimized process parameters comprises the following steps: and sending control instructions to corresponding production equipment according to the optimized process parameters by combining the production application platform with industrial control software and/or a system preset in the software layer, so that the production equipment executes the control instructions to adjust the process parameters of the production equipment patch and/or the packaged electronic components.

2. The method of processing an electronic component according to claim 1, wherein the step of generating optimized process parameters based on the process parameter analysis model comprises:

3. A process processing system for electronic components, the system comprising:

And an adjustment module: the process parameters for the production equipment patch and/or the packaging electronic components are adjusted according to the optimized process parameters;

The industrial data of the production equipment and the raw materials comprise physical information change data of the production equipment and the raw materials and image data of the production equipment and the raw materials, and the acquisition module is also used for sensing change signals and image light signals of the physical information of the production equipment and the raw materials; after the change signal and the image light signal are subjected to photoelectric analysis processing, the change signal and the image light signal are converted into physical information change data of production equipment and raw materials and image data of the production equipment and the raw materials;

The pretreatment module is also used for carrying out abnormality detection on the industrial data and carrying out data cleaning treatment based on the result of the abnormality detection; carrying out data classification treatment on the industrial data after the data cleaning treatment to obtain the industrial data after the pretreatment;

The pretreated industrial data comprise pretreated production equipment data and pretreated raw material data, and the analysis module is further used for establishing a production equipment process parameter analysis model based on the pretreated production equipment data; establishing a raw material process parameter analysis model based on the pretreated raw material data;

the system comprises a data acquisition layer, wherein the data acquisition layer comprises an industrial gateway, an edge gateway, an industrial personal computer and an intelligent controller, and the acquisition module is also used for constructing an acquisition-network layer transmission protocol through the industrial gateway and the edge gateway; transmitting industrial data of the production equipment and raw materials to the network layer through the acquisition-network layer transmission protocol; the industrial personal computer and the intelligent controller are used for carrying out state monitoring and fault prediction on the production equipment;

the preprocessing module is further used for forming an industrial microservice component library based on the preprocessed industrial data; constructing a data visualization billboard and a production application platform based on the industrial micro-service component library;

The system further comprises a software layer, and the adjusting module is further used for sending control instructions to corresponding production equipment according to the optimized process parameters by combining the production application platform with industrial control software and/or a system preset in the software layer, so that the production equipment executes the control instructions to adjust the process parameters of the production equipment patch and/or the packaged electronic components.

4. A process treatment apparatus for electronic components, the apparatus comprising: a memory, a processor and a process program for an electronic component stored on the memory and executable on the processor, the process program for an electronic component being configured to implement the steps of the process method for an electronic component as claimed in any one of claims 1 to 2.

5. A storage medium, wherein a process program of an electronic component is stored on the storage medium, and the process program of the electronic component, when executed by a processor, implements the steps of the process method of an electronic component according to any one of claims 1 to 2.