Multi-machine cooperative control system based on injection molding

Abstract

The invention discloses a multi-machine cooperative control system based on injection molding, which relates to the technical field of intelligent control, comprises an acquisition module, an analysis module and a control module, and is characterized in that a first similarity is calculated, a first operation is executed, a change gradient of problem parameters is set, and the problem parameters are continuously controlled according to the change gradient; and continuously obtaining a regulated second similarity, and executing a second operation. By obtaining the standard production data and the current product model, the number of times of new product mold testing is reduced, the production efficiency is improved, the process parameters are automatically calculated and recommended, the accuracy and efficiency of process parameter setting are improved, and by simulating production and calculating the similarity between the finished product image and the standard defect image, abnormity in the production process can be found in time, and the production efficiency is improved. Through continuous control and timely adjustment, defective products are reduced, and the product quality is improved, so that injection molding control has relatively good decoupling capability, anti-interference capability and robustness, and the product quality problem is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent control, and in particular to a multi-machine collaborative control system based on injection molding. Background Art

[0002] In recent years, with the continuous development and improvement of control technology, injection molding machines will develop in the direction of automation, energy saving, intelligence and unmanned operation. For example, computer digital control and programmed control will be adopted to enable injection molding machines to have automatic control, automatic diagnosis, automatic adjustment and automatic compensation functions; the control system will be modularized and integrated, and group technology will be used to implement group control of multiple injection molding machines.

[0003] At present, a Chinese invention patent with publication number CN106671369B discloses an injection molding machine control system and method. The method collects sensor information of each component by arranging a number of sensors on an injection molding machine including at least two ejectors, and controls each ejector to advance and retreat respectively according to a preset control sequence, a judgment threshold and each of the sensor information, thereby achieving control of at least two groups of ejectors to perform injection molding on products that require ejector demolding. However, the related art does not make detailed judgments and adjustments on the mechanical problems of the injection molding machine itself and the control problems, which may easily lead to erroneous production and waste of resources. The injection molding machine is not analyzed based on historical defect data and production data, and the data analysis lacks scientificity and accuracy. Summary of the invention

[0004] The technical problem solved by the present invention is: the related technology does not make detailed judgments and adjustments on the mechanical problems and control problems of the injection molding machine itself, which may easily lead to erroneous production and waste of resources. The injection molding machine is not analyzed based on historical defect data and production data, and the data analysis lacks scientificity and accuracy.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: a multi-machine collaborative control system based on injection molding, comprising a collection module, an analysis module and a control module; The acquisition module acquires standard production data and the current product model; The analysis module compares the current product model with the standard production data to obtain a first comparison result, screens valid data according to the first comparison result, performs simulated production according to the valid data, obtains a finished product image, obtains a standard defect image and a corresponding standard cause, calculates a first similarity between the finished product image and the standard defect image, and performs a first operation according to the first similarity; In response to the first operation, the control module sets the corresponding valid data as the problem parameter, sets the change gradient of the problem parameter, continuously controls the problem parameter according to the change gradient, continuously obtains the second similarity after regulation, sets the second similarity threshold, compares the second similarity with the second similarity threshold, and performs the second operation according to the comparison result.

[0006] As a preferred solution of the multi-machine cooperative control system based on injection molding described in the present invention, wherein: the acquisition module obtains the coded image of the injection molding machine, obtains the current product model, connects to the network, scans the coded image of the injection molding machine, and obtains the standard production data of the injection molding machine, the standard production data is represented by the data corresponding to the injection molding machine for producing any model of products under an ideal state, the ideal state is represented by the various parts of the injection molding machine without failure or wear, and the current product model is represented by the product model waiting to be produced; The acquisition logic of the standard production data includes: Retrieving a production database, inputting the injection molding machine coded image into the production database, and matching standard production data corresponding to the injection molding machine coded image; The standard production data includes a standard product model, a standard gate sequence number, a corresponding standard gate pressure, a corresponding standard gate conversion time, a corresponding standard mold temperature, a corresponding standard holding time and a corresponding standard injection speed. The standard gate conversion time is expressed as the interval time for switching between gates in adjacent order, and the standard gate sequence number is a natural number.

[0007] As a preferred solution of the multi-machine collaborative control system based on injection molding described in the present invention, wherein: the analysis module compares the current product model with the standard production data to obtain a first comparison result, and the first comparison result includes that the current product model is the same as the standard product model, and the current product model is different from the standard product model; Valid data is screened according to the first comparison result, and the valid data screening logic includes: Obtaining a first comparison result, when the first comparison result is that the current product model is the same as the standard product model, setting the standard gate sequence number, the corresponding standard gate pressure, the corresponding standard gate conversion time, the corresponding standard mold temperature, the corresponding standard holding time and the corresponding standard injection speed corresponding to the standard product model as valid data; when the first comparison result is that the current product model is different from the standard product model, deleting the marked data and jumping to the next standard data; The valid data is set as the production parameters of the current product model, the injection molding machine is started, and simulated production is performed according to the valid data.

[0008] As a preferred solution of the multi-machine collaborative control system based on injection molding described in the present invention, wherein: after the simulated production is completed, the analysis module obtains the finished product image, retrieves the defect database, inputs the current product model into the defect database, and matches the standard defect image and standard cause corresponding to the current product model; The standard defect images include standard shrinkage images, standard surface bright printing images, standard burr images, standard heat shrinkage images and standard warping images; The standard reason for the standard shrinkage image is that the holding time is too short, the standard reason for the standard surface bright printing image is that the injection speed is too fast, the standard reason for the standard burr image is that the gate pressure is too small, the standard reason for the standard heat shrinkage image is that the mold temperature is too high, and the standard reason for the standard warping image is that the gate pressure is too large; Obtain any standard defect image and a finished product image, extract the shape feature of the standard defect image, record it as a first feature, extract the shape feature of the finished product image, record it as a second feature, and calculate the first similarity between the first feature and the second feature by using a cosine similarity formula; A first operation is performed according to the first similarity, wherein the first operation includes valid data adjustment or maintenance, and setting the corresponding valid data as an operating parameter of the injection molding machine.

[0009] As a preferred solution of the multi-machine collaborative control system based on injection molding according to the present invention, the setting logic of the first operation includes: Setting the first value as a first similarity threshold, traversing the first similarities, comparing the first similarities with the first value, and obtaining a second comparison result, wherein the second comparison result includes that all the first similarities are less than the first value, and one of the first similarities is greater than or equal to the first value; When the second comparison result is that the first similarities are all smaller than the first value, the first operation is set to set the corresponding valid data as the operating parameters of the injection molding machine; When the second comparison result is that one of the first similarities is greater than or equal to the first value, the first operation is set to effective data regulation or maintenance. When the first operation is effective data regulation or maintenance, the first operation is divided into a first sub-operation, and the first sub-operation includes increasing the holding time, reducing the injection speed, reducing the mold temperature, reducing the gate pressure, increasing the gate pressure, and acquiring the gate image, performing a first analysis, and executing the third operation according to the first analysis result.

[0010] As a preferred solution of the multi-machine collaborative control system based on injection molding according to the present invention, the setting logic of the first sub-operation includes: Acquire a standard defect image having a first similarity greater than or equal to a first value; When the standard defect image is a standard shrinkage image, the first sub-operation is set to increase the holding time; When the standard defect image is a standard surface bright print image, the first sub-operation is set to reduce the injection speed; When the standard defect image is a standard burr image, the first sub-operation is set to acquire a gate image, perform a first analysis, and perform a third operation according to the first analysis result; When the standard defect image is a standard heat shrink image, the first sub-operation is set to reduce the mold temperature; When the standard defect image is a standard warpage image, the first sub-operation is set to reduce the gate pressure.

[0011] As a preferred solution of the multi-machine collaborative control system based on injection molding described in the present invention, the analysis logic of the first analysis includes: Obtain a gate image of any number, call up a device database, input the injection molding machine model and the gate number into the device database, match the corresponding gate defect image, extract the shape feature of the gate image, record it as the third feature, extract the shape feature of the gate defect image, record it as the fourth feature, and calculate the second similarity between the third feature and the fourth feature by using the cosine similarity formula; Setting the second value as a second similarity threshold, traversing the second similarity, comparing the second similarity with the second value to obtain a first analysis result, and performing a third operation according to the first analysis result; The gate defect image includes a first wear image, a second wear image and a third wear image, wherein the first wear image, the second wear image and the third wear image represent that the gate wear degree gradually increases; The third operation includes: The first analysis result includes that all the second similarities are less than the second value, and one of the second similarities is greater than or equal to the second value; When the first analysis result is that all the second similarities are less than the second value, the third operation is set to detect the screw displacement; when the first analysis result is that one of the second similarities is greater than or equal to the second value, the third operation is set to set the current gate defect image and send a first maintenance signal; When the third operation is set to set the current gate defect image and the first maintenance signal is sent, the gate defect image corresponding to the second similarity being greater than or equal to the second value is set as the current gate defect image; The first maintenance signal includes a gate number, a current gate defect image, and a first maintenance status, and the maintenance status includes a first completed maintenance and a first uncompleted maintenance.

[0012] As a preferred solution of the multi-machine collaborative control system based on injection molding described in the present invention, wherein: when the third operation is to detect the screw displacement, the detected screw displacement is set as the actual displacement, the production database is called, the corresponding standard screw displacement is matched, the difference between the actual displacement and the standard screw displacement is calculated, recorded as the first difference, the third value is set as the first difference threshold, when the first difference is less than or equal to the third value, the first operation is set to increase the gate pressure, when the first difference is greater than the third value, the first operation is set to send a second maintenance signal, the second maintenance signal includes the first difference and the second maintenance status, the second maintenance status includes the first maintenance completed and the second incomplete maintenance.

[0013] As a preferred solution of the multi-machine cooperative control system based on injection molding described in the present invention, when the first operation is to increase the holding time, reduce the injection speed, reduce the mold temperature, reduce the gate pressure or increase the gate pressure, the control module responds to the first operation and sets the corresponding valid data as the problem parameter; When the first operation is to increase the holding time, the problem parameter is set to the holding time; when the first operation is to reduce the injection speed, the problem parameter is set to the injection speed; when the first operation is to reduce the mold temperature, the problem parameter is set to the mold temperature; when the first operation is to reduce the gate pressure or increase the gate pressure, the problem parameter is set to the gate pressure; The change gradient of the problem parameters is set, and the fourth value, the fifth value, the sixth value and the seventh value are set as the change gradients of the holding time, the injection speed, the mold temperature and the gate pressure respectively.

[0014] As a preferred solution of the multi-machine cooperative control system based on injection molding described in the present invention, wherein: the control module continuously controls the problem parameters according to the change gradient, and continuously obtains the second similarity after regulation, and the continuous control is represented by continuous increase or continuous decrease; Setting the eighth value as a second similarity threshold, comparing the second similarity with the eighth value to obtain a third comparison result, and performing a second operation according to the third comparison result, wherein the third comparison result includes that the second similarity is less than or equal to the eighth value, and the second similarity is greater than the eighth value; The second operation includes updating and changing the gradient and continuously controlling, and updating the valid data according to the regulated problem parameters; When the third comparison result is that the second similarity is less than or equal to the eighth value, stop continuously controlling the problem parameters and update the valid data according to the adjusted problem parameters; otherwise, set half of the change gradient value as the new change gradient, and continuously control the problem parameters according to the new change gradient until the third comparison result is that the second similarity is less than or equal to the eighth value, stop continuously controlling the problem parameters and update the valid data according to the adjusted problem parameters.

[0015] The beneficial effects of the present invention are as follows: by acquiring standard production data and current product models, the analysis module compares the data and simulates production, and the control module performs continuous control according to the analysis results, thereby reducing the number of new product mold trials and improving production efficiency. By comparing the similarity between the finished product image and the standard defect image, the process parameters are automatically calculated and recommended, reducing human trial and error, and improving the accuracy and efficiency of process parameter setting. By simulating production and calculating the similarity between the finished product image and the standard defect image, anomalies in the production process can be discovered in time, and timely adjustments can be made through continuous control to reduce defective products and improve product quality, so that the injection molding control has better decoupling ability, anti-interference ability and robustness, and reduces product quality problems. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A schematic diagram of the basic flow of a multi-machine collaborative control system based on injection molding provided for one embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, but not all of the embodiments.

[0018] Example, see Figure 1 , is an embodiment of the present invention, providing a multi-machine collaborative control system based on injection molding, including a collection module, an analysis module and a control module; The acquisition module acquires standard production data and the current product model; The analysis module compares the current product model with the standard production data to obtain a first comparison result, screens valid data according to the first comparison result, performs simulated production according to the valid data, obtains a finished product image, obtains a standard defect image and a corresponding standard cause, calculates a first similarity between the finished product image and the standard defect image, and performs a first operation according to the first similarity; In response to the first operation, the control module sets the corresponding valid data as the problem parameter, sets the change gradient of the problem parameter, continuously controls the problem parameter according to the change gradient, continuously obtains the second similarity after regulation, sets the second similarity threshold, compares the second similarity with the second similarity threshold, and performs the second operation according to the comparison result.

[0019] The present invention obtains standard production data and current product models, and the analysis module compares the data and simulates production. The control module performs continuous control according to the analysis results, thereby reducing the number of new product trial molds and improving production efficiency. By comparing the similarity between the finished product image and the standard defect image, the process parameters are automatically calculated and recommended, reducing human trial and error, and improving the accuracy and efficiency of process parameter setting. By simulating production and calculating the similarity between the finished product image and the standard defect image, anomalies in the production process can be discovered in time, and timely adjustments can be made through continuous control to reduce defective products and improve product quality, so that the injection molding control has better decoupling ability, anti-interference ability and robustness, and reduces product quality problems.

[0020] The acquisition module acquires the coded image of the injection molding machine, acquires the current product model, connects to the network, scans the coded image of the injection molding machine, and obtains the standard production data of the injection molding machine, wherein the standard production data is represented by the data corresponding to the injection molding machine used to produce any model of products under an ideal state, wherein the ideal state is represented by the various parts of the injection molding machine having no failure or wear, and the current product model is represented by the product model waiting to be produced; The acquisition logic of the standard production data includes: Retrieving a production database, inputting the injection molding machine coded image into the production database, and matching standard production data corresponding to the injection molding machine coded image; The standard production data includes a standard product model, a standard gate sequence number, a corresponding standard gate pressure, a corresponding standard gate conversion time, a corresponding standard mold temperature, a corresponding standard holding time and a corresponding standard injection speed. The standard gate conversion time is expressed as the interval time for switching between gates in adjacent order, and the standard gate sequence number is a natural number.

[0021] In specific implementation, the standard production data obtained by the acquisition module, including key parameters such as standard product model, gate sequence number, gate pressure, etc., provide accurate process parameters for injection molding production, realize intelligent production management, and timely discover and deal with product defects and mold abnormalities through real-time monitoring of the injection molding machine status, reduce production losses caused by defective products and scrapping, improve equipment utilization rate, use a unified coding format for data collection and storage, improve data consistency and readability, and facilitate data analysis and problem tracking.

[0022] The analysis module compares the current product model with the standard production data to obtain a first comparison result, wherein the first comparison result includes that the current product model is the same as the standard product model, and that the current product model is different from the standard product model; Valid data is screened according to the first comparison result, and the valid data screening logic includes: Obtaining a first comparison result, when the first comparison result is that the current product model is the same as the standard product model, setting the standard gate sequence number, the corresponding standard gate pressure, the corresponding standard gate conversion time, the corresponding standard mold temperature, the corresponding standard holding time and the corresponding standard injection speed corresponding to the standard product model as valid data; when the first comparison result is that the current product model is different from the standard product model, deleting the marked data and jumping to the next standard data; The valid data is set as the production parameters of the current product model, the injection molding machine is started, and simulated production is performed according to the valid data.

[0023] In specific implementation, it is possible to automatically screen out production parameters suitable for the current product based on the comparison results between the current product model and the standard production data, thereby improving the adaptability and flexibility of production, automatically screening valid data and setting them as production parameters, reducing production preparation time, and improving production efficiency. It ensures that only standard production data that matches the current product model is used for production, which helps to maintain consistency and high standards of product quality, records the matching process of product models and production data, and provides reliable data support for product quality control and problem tracking.

[0024] After the simulated production is completed, the analysis module obtains the finished product image, retrieves the defect database, inputs the current product model into the defect database, and matches the standard defect image and standard cause corresponding to the current product model; The standard defect images include standard shrinkage images, standard surface bright printing images, standard burr images, standard heat shrinkage images and standard warping images; The standard reason for the standard shrinkage image is that the holding time is too short, the standard reason for the standard surface bright printing image is that the injection speed is too fast, the standard reason for the standard burr image is that the gate pressure is too small, the standard reason for the standard heat shrinkage image is that the mold temperature is too high, and the standard reason for the standard warping image is that the gate pressure is too large; Obtain any standard defect image and a finished product image, extract the shape feature of the standard defect image, record it as a first feature, extract the shape feature of the finished product image, record it as a second feature, and calculate the first similarity between the first feature and the second feature by using a cosine similarity formula; A first operation is performed according to the first similarity, wherein the first operation includes valid data adjustment or maintenance, and setting the corresponding valid data as an operating parameter of the injection molding machine.

[0025] The setting logic of the first operation includes: Setting the first value as a first similarity threshold, traversing the first similarities, comparing the first similarities with the first value, and obtaining a second comparison result, wherein the second comparison result includes that all the first similarities are less than the first value, and one of the first similarities is greater than or equal to the first value; When the second comparison result is that the first similarities are all smaller than the first value, the first operation is set to set the corresponding valid data as the operating parameters of the injection molding machine; When the second comparison result is that one of the first similarities is greater than or equal to the first value, the first operation is set to effective data regulation or maintenance. When the first operation is effective data regulation or maintenance, the first operation is divided into a first sub-operation, and the first sub-operation includes increasing the holding time, reducing the injection speed, reducing the mold temperature, reducing the gate pressure, increasing the gate pressure, and acquiring the gate image, performing a first analysis, and executing the third operation according to the first analysis result.

[0026] In the specific implementation, by extracting the shape features of the finished product image and the standard defect image and using the cosine similarity formula to calculate the similarity, defects can be identified and classified more accurately. The first operation is performed according to the result of the first similarity, including effective data adjustment or maintenance, and setting the corresponding effective data as the operating parameters of the injection molding machine, which helps to optimize the production process and improve product quality. Based on digital intelligent algorithms and molding theories, an intelligent injection molding machine adjustment system is established, which realizes the automatic recommendation of the optimal process parameters for the first mold and the automatic optimization of process parameters for molding defects.

[0027] The setting logic of the first sub-operation includes: Acquire a standard defect image having a first similarity greater than or equal to a first value; When the standard defect image is a standard shrinkage image, the first sub-operation is set to increase the holding time; When the standard defect image is a standard surface bright print image, the first sub-operation is set to reduce the injection speed; When the standard defect image is a standard burr image, the first sub-operation is set to acquire a gate image, perform a first analysis, and perform a third operation according to the first analysis result; When the standard defect image is a standard heat shrink image, the first sub-operation is set to reduce the mold temperature; When the standard defect image is a standard warpage image, the first sub-operation is set to reduce the gate pressure.

[0028] In specific implementation, by comparing the first similarity between the finished product image and the standard defect image, the specific defect type can be accurately identified, so as to locate the problem in a targeted manner, and the identified defects can be corrected in time, such as increasing the holding time, reducing the injection speed, etc., thereby reducing production delays and cost increases caused by defective products, responding quickly to defect problems, reducing downtime caused by defect handling, and improving overall production efficiency.

[0029] The analysis logic of the first analysis includes: Obtain a gate image of any number, call up a device database, input the injection molding machine model and the gate number into the device database, match the corresponding gate defect image, extract the shape feature of the gate image, record it as the third feature, extract the shape feature of the gate defect image, record it as the fourth feature, and calculate the second similarity between the third feature and the fourth feature by using the cosine similarity formula; Setting the second value as a second similarity threshold, traversing the second similarity, comparing the second similarity with the second value to obtain a first analysis result, and performing a third operation according to the first analysis result; The gate defect image includes a first wear image, a second wear image and a third wear image, wherein the first wear image, the second wear image and the third wear image represent that the gate wear degree gradually increases; The third operation includes: The first analysis result includes that all the second similarities are less than the second value, and one of the second similarities is greater than or equal to the second value; When the first analysis result is that all the second similarities are less than the second value, the third operation is set to detect the screw displacement; when the first analysis result is that one of the second similarities is greater than or equal to the second value, the third operation is set to set the current gate defect image and send a first maintenance signal; When the third operation is set to set the current gate defect image and the first maintenance signal is sent, the gate defect image corresponding to the second similarity being greater than or equal to the second value is set as the current gate defect image; The first maintenance signal includes a gate number, a current gate defect image, and a first maintenance status, and the maintenance status includes a first completed maintenance and a first uncompleted maintenance.

[0030] When the third operation is to detect the screw displacement, the detected screw displacement is set as the actual displacement, the production database is called, the corresponding standard screw displacement is matched, the difference between the actual displacement and the standard screw displacement is calculated and recorded as the first difference, the third value is set as the first difference threshold, when the first difference is less than or equal to the third value, the first operation is set to increase the gate pressure, when the first difference is greater than the third value, the first operation is set to send a second maintenance signal, the second maintenance signal includes the first difference and the second maintenance status, the second maintenance status includes the first maintenance completed and the second incomplete maintenance.

[0031] In the specific implementation, by extracting the shape features of the gate image and the gate defect image and using the cosine similarity formula to calculate the similarity, the system can more accurately identify the type and degree of gate defects. When the system identifies a gate defect, it can send a maintenance signal in time, reducing production delays and cost increases caused by defects, reducing dependence on operator experience and skills, making the production process more stable, and reducing product quality problems caused by improper operation.

[0032] When the first operation is to increase the holding time, reduce the injection speed, reduce the mold temperature, reduce the gate pressure, or increase the gate pressure, the control module sets the corresponding valid data as the problem parameter in response to the first operation; When the first operation is to increase the holding time, the problem parameter is set to the holding time; when the first operation is to reduce the injection speed, the problem parameter is set to the injection speed; when the first operation is to reduce the mold temperature, the problem parameter is set to the mold temperature; when the first operation is to reduce the gate pressure or increase the gate pressure, the problem parameter is set to the gate pressure; The change gradient of the problem parameters is set, and the fourth value, the fifth value, the sixth value and the seventh value are set as the change gradients of the holding time, the injection speed, the mold temperature and the gate pressure respectively.

[0033] In specific implementation, by mapping specific operations (such as increasing the holding time, reducing the injection speed, etc.) to specific problem parameters (such as holding time, injection speed, etc.), the system can achieve precise control of the injection molding process.

[0034] The control module continuously controls the problem parameters according to the change gradient, and continuously obtains the second similarity after regulation, wherein the continuous control is represented by continuous increase or continuous decrease; Setting the eighth value as a second similarity threshold, comparing the second similarity with the eighth value to obtain a third comparison result, and performing a second operation according to the third comparison result, wherein the third comparison result includes that the second similarity is less than or equal to the eighth value, and the second similarity is greater than the eighth value; The second operation includes updating and changing the gradient and continuously controlling, and updating the valid data according to the regulated problem parameters; When the third comparison result is that the second similarity is less than or equal to the eighth value, stop continuously controlling the problem parameters and update the valid data according to the adjusted problem parameters; otherwise, set half of the change gradient value as the new change gradient, and continuously control the problem parameters according to the new change gradient until the third comparison result is that the second similarity is less than or equal to the eighth value, stop continuously controlling the problem parameters and update the valid data according to the adjusted problem parameters.

[0035] In the specific implementation, the control strategy can be dynamically adjusted according to the comparison result between the real-time second similarity and the second similarity threshold, which improves the response speed and flexibility of the system. By setting the change gradient and continuous control, the system avoids the risk of over-adjustment caused by excessive one-time adjustment, thereby ensuring the stability of the production process.

[0036] The present invention obtains standard production data and current product models, and the analysis module compares the data and simulates production. The control module performs continuous control according to the analysis results, thereby reducing the number of new product trial molds and improving production efficiency. By comparing the similarity between the finished product image and the standard defect image, the process parameters are automatically calculated and recommended, reducing human trial and error, and improving the accuracy and efficiency of process parameter setting. By simulating production and calculating the similarity between the finished product image and the standard defect image, anomalies in the production process can be discovered in time, and timely adjustments can be made through continuous control to reduce defective products and improve product quality, so that the injection molding control has better decoupling ability, anti-interference ability and robustness, and reduces product quality problems.

[0037] It should be understood by those skilled in the art that the embodiments of the present invention may be provided as methods, systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware aspects. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program codes. Among them, the storage medium may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red Only Memory, referred to as PROM), read-only memory (Read Only Memory, referred to as ROM), magnetic memory, flash memory, magnetic disk or optical disk. These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0038] It should be noted that the above embodiments are only used to illustrate the technical solutions 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 solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. Multi-machine collaborative control system based on injection molding, characterized in that: It includes an acquisition module, an analysis module and a control module; The acquisition module acquires standard production data and the current product model; The analysis module compares the current product model with the standard production data to obtain a first comparison result, screens valid data according to the first comparison result, performs simulated production according to the valid data, obtains a finished product image, obtains a standard defect image and a corresponding standard cause, calculates a first similarity between the finished product image and the standard defect image, and performs a first operation according to the first similarity; In response to the first operation, the control module sets the corresponding valid data as the problem parameter, sets the change gradient of the problem parameter, continuously controls the problem parameter according to the change gradient, continuously obtains the second similarity after regulation, sets the second similarity threshold, compares the second similarity with the second similarity threshold, and performs the second operation according to the comparison result.

2. The multi-machine collaborative control system based on injection molding according to claim 1, characterized in that: The acquisition module acquires the coded image of the injection molding machine, acquires the current product model, connects to the network, scans the coded image of the injection molding machine, and obtains the standard production data of the injection molding machine, wherein the standard production data is represented by the data corresponding to the injection molding machine used to produce any model of products under an ideal state, wherein the ideal state is represented by the various parts of the injection molding machine having no failure or wear, and the current product model is represented by the product model waiting to be produced; The acquisition logic of the standard production data includes: Retrieving a production database, inputting the injection molding machine coded image into the production database, and matching standard production data corresponding to the injection molding machine coded image; The standard production data includes a standard product model, a standard gate sequence number, a corresponding standard gate pressure, a corresponding standard gate conversion time, a corresponding standard mold temperature, a corresponding standard holding time and a corresponding standard injection speed. The standard gate conversion time is expressed as the interval time for switching between gates in adjacent order, and the standard gate sequence number is a natural number.

3. The multi-machine collaborative control system based on injection molding according to claim 1, characterized in that: The analysis module compares the current product model with the standard production data to obtain a first comparison result, wherein the first comparison result includes that the current product model is the same as the standard product model, and that the current product model is different from the standard product model; Valid data is screened according to the first comparison result, and the valid data screening logic includes: Obtaining a first comparison result, when the first comparison result is that the current product model is the same as the standard product model, setting the standard gate sequence number, the corresponding standard gate pressure, the corresponding standard gate conversion time, the corresponding standard mold temperature, the corresponding standard holding time and the corresponding standard injection speed corresponding to the standard product model as valid data; when the first comparison result is that the current product model is different from the standard product model, deleting the marked data and jumping to the next standard data; The valid data is set as the production parameters of the current product model, the injection molding machine is started, and simulated production is performed according to the valid data.

4. The multi-machine collaborative control system based on injection molding as claimed in claim 3, characterized in that: After the simulated production is completed, the analysis module obtains the finished product image, retrieves the defect database, inputs the current product model into the defect database, and matches the standard defect image and standard cause corresponding to the current product model; The standard defect images include standard shrinkage images, standard surface bright printing images, standard burr images, standard heat shrinkage images and standard warping images; The standard reason for the standard shrinkage image is that the holding time is too short, the standard reason for the standard surface bright printing image is that the injection speed is too fast, the standard reason for the standard burr image is that the gate pressure is too small, the standard reason for the standard heat shrinkage image is that the mold temperature is too high, and the standard reason for the standard warping image is that the gate pressure is too large; Obtain any standard defect image and a finished product image, extract the shape feature of the standard defect image, record it as a first feature, extract the shape feature of the finished product image, record it as a second feature, and calculate the first similarity between the first feature and the second feature by using a cosine similarity formula; A first operation is performed according to the first similarity, wherein the first operation includes valid data adjustment or maintenance, and setting the corresponding valid data as an operating parameter of the injection molding machine.

5. The multi-machine collaborative control system based on injection molding according to claim 4, characterized in that: The setting logic of the first operation includes: Setting the first value as a first similarity threshold, traversing the first similarities, comparing the first similarities with the first value, and obtaining a second comparison result, wherein the second comparison result includes that all the first similarities are less than the first value, and one of the first similarities is greater than or equal to the first value; When the second comparison result is that the first similarities are all smaller than the first value, the first operation is set to set the corresponding valid data as the operating parameters of the injection molding machine; When the second comparison result is that one of the first similarities is greater than or equal to the first value, the first operation is set to effective data regulation or maintenance. When the first operation is effective data regulation or maintenance, the first operation is divided into a first sub-operation, and the first sub-operation includes increasing the holding time, reducing the injection speed, reducing the mold temperature, reducing the gate pressure, increasing the gate pressure, and acquiring the gate image, performing a first analysis, and executing the third operation according to the first analysis result.

6. The multi-machine collaborative control system based on injection molding according to claim 5, characterized in that: The setting logic of the first sub-operation includes: Acquire a standard defect image having a first similarity greater than or equal to a first value; When the standard defect image is a standard shrinkage image, the first sub-operation is set to increase the holding time; When the standard defect image is a standard surface bright print image, the first sub-operation is set to reduce the injection speed; When the standard defect image is a standard burr image, the first sub-operation is set to acquire a gate image, perform a first analysis, and perform a third operation according to the first analysis result; When the standard defect image is a standard heat shrink image, the first sub-operation is set to reduce the mold temperature; When the standard defect image is a standard warpage image, the first sub-operation is set to reduce the gate pressure.

7. The multi-machine cooperative control system based on injection molding according to claim 6, characterized in that: The analysis logic of the first analysis includes: Obtain a gate image of any number, call up a device database, input the injection molding machine model and the gate number into the device database, match the corresponding gate defect image, extract the shape feature of the gate image, record it as the third feature, extract the shape feature of the gate defect image, record it as the fourth feature, and calculate the second similarity between the third feature and the fourth feature by using the cosine similarity formula; Setting the second value as a second similarity threshold, traversing the second similarity, comparing the second similarity with the second value to obtain a first analysis result, and performing a third operation according to the first analysis result; The gate defect image includes a first wear image, a second wear image and a third wear image, wherein the first wear image, the second wear image and the third wear image represent that the gate wear degree gradually increases; The third operation includes: The first analysis result includes that all the second similarities are less than the second value, and one of the second similarities is greater than or equal to the second value; When the first analysis result is that all the second similarities are less than the second value, the third operation is set to detect the screw displacement; when the first analysis result is that one of the second similarities is greater than or equal to the second value, the third operation is set to set the current gate defect image and send a first maintenance signal; When the third operation is set to set the current gate defect image and the first maintenance signal is sent, the gate defect image corresponding to the second similarity being greater than or equal to the second value is set as the current gate defect image; The first maintenance signal includes a gate number, a current gate defect image, and a first maintenance status, and the maintenance status includes a first completed maintenance and a first uncompleted maintenance.

8. The multi-machine collaborative control system based on injection molding according to claim 7, characterized in that: When the third operation is to detect the screw displacement, the detected screw displacement is set as the actual displacement, the production database is called, the corresponding standard screw displacement is matched, the difference between the actual displacement and the standard screw displacement is calculated and recorded as the first difference, the third value is set as the first difference threshold, when the first difference is less than or equal to the third value, the first operation is set to increase the gate pressure, when the first difference is greater than the third value, the first operation is set to send a second maintenance signal, the second maintenance signal includes the first difference and the second maintenance status, the second maintenance status includes the first maintenance completed and the second incomplete maintenance.

9. The multi-machine collaborative control system based on injection molding according to claim 1, characterized in that: When the first operation is to increase the holding time, reduce the injection speed, reduce the mold temperature, reduce the gate pressure, or increase the gate pressure, the control module sets the corresponding valid data as the problem parameter in response to the first operation; When the first operation is to increase the holding time, the problem parameter is set to the holding time; when the first operation is to reduce the injection speed, the problem parameter is set to the injection speed; when the first operation is to reduce the mold temperature, the problem parameter is set to the mold temperature; when the first operation is to reduce the gate pressure or increase the gate pressure, the problem parameter is set to the gate pressure; The change gradient of the problem parameters is set, and the fourth value, the fifth value, the sixth value and the seventh value are set as the change gradients of the holding time, the injection speed, the mold temperature and the gate pressure respectively.

10. The multi-machine collaborative control system based on injection molding according to claim 9, characterized in that: The control module continuously controls the problem parameters according to the change gradient, and continuously obtains the second similarity after regulation, wherein the continuous control is represented by continuous increase or continuous decrease; Setting the eighth value as a second similarity threshold, comparing the second similarity with the eighth value to obtain a third comparison result, and performing a second operation according to the third comparison result, wherein the third comparison result includes that the second similarity is less than or equal to the eighth value, and the second similarity is greater than the eighth value; The second operation includes updating and changing the gradient and continuously controlling, and updating the valid data according to the regulated problem parameters; When the third comparison result is that the second similarity is less than or equal to the eighth value, stop continuously controlling the problem parameters and update the valid data according to the adjusted problem parameters; otherwise, set half of the change gradient value as the new change gradient, and continuously control the problem parameters according to the new change gradient until the third comparison result is that the second similarity is less than or equal to the eighth value, stop continuously controlling the problem parameters and update the valid data according to the adjusted problem parameters.

Images