Intelligent control method and system for die casting machine

Abstract

The invention relates to an intelligent control method and system for a die casting machine, and relates to the field of intelligent injection molding technologies, the method comprises the steps that rear-end detection data are obtained, and the rear-end detection data comprise the overall detection number, the defect existing number and the defect existing type; performing calculation according to the defect existence number and the overall detection number to determine a defect existence proportion, and determining type stability according to each defect existence type when the defect existence proportion is greater than a preset abnormal demand proportion; when the type stability is greater than a preset type demand degree, determining a demand adjustment direction according to the defect existence type; and determining a theoretical demand position according to the demand adjustment direction, a preset original switching position and a preset monomer adjustment distance, updating the theoretical demand position to a new original switching position, and controlling the punch to perform speed switching at the updated original switching position. The device has the effect of facilitating effective production of products.

Description

Technical Field

[0001] This application relates to the field of intelligent injection molding technology, and in particular to an intelligent control method and system for a die casting machine. Background Technology

[0002] In the die-casting industry, structural components such as inverter housings are typically manufactured using die-casting machines. During operation, the injection speed is a key process parameter affecting product quality, directly related to the flow state of molten metal filling the mold cavity and the molding quality. Currently, the industry commonly uses displacement sensors installed on the injection punch to calculate the injection speed by monitoring changes in the punch displacement in real time, thereby achieving precise control of the injection process.

[0003] However, in actual production and operation, it has been found that due to the harsh working environment of the die-casting machine, which is under high temperature and vibration conditions for a long time, the displacement sensor is prone to problems such as loose installation and insecure fixing. Once such a situation occurs, it will cause the collected displacement data to be distorted, which may result in the punch showing that it has reached the speed switching position when it is not actually in that position. This measurement error will directly affect the accurate control of the die-casting process parameters, causing quality defects such as insufficient filling, cold shut, and porosity in the product, which seriously affects the product qualification rate of the inverter cabinet.

[0004] In modern manufacturing production sites, there are often urgent production tasks and continuous equipment operation requirements. When a displacement sensor becomes loose, maintenance requires machine downtime, and troubleshooting and tightening take time. When rushing to complete urgent orders, production units often find it difficult to arrange maintenance work in a timely manner, which is not conducive to the effective production of products and there is still room for improvement. Summary of the Invention

[0005] To facilitate efficient product production, this application provides an intelligent control method and system for die-casting machines.

[0006] Firstly, this application provides an intelligent control method for a die-casting machine, employing the following technical solution: A method for intelligent control of a die-casting machine, comprising: Obtain backend detection data, which includes the total number of detections, the number of defects, and the types of defects. The proportion of defects is determined by calculating the number of defects and the total number of inspections. When the proportion of defects exceeds the preset proportion of abnormal demands, the stability of each defect type is determined. When the type stability is greater than the preset type demand, the direction of demand adjustment is determined based on the type of defect. The theoretical required position is determined based on the required adjustment direction, the preset original switching position, and the preset single-unit adjustment distance. This theoretical required position is then updated to the new original switching position, and the speed of the punch is controlled to switch at the updated original switching position.

[0007] Optionally, it also includes a step for determining the individual unit adjustment distance, which includes: The percentage of defects for each product is determined based on backend testing data, and the average percentage of defects is calculated based on the percentage of all defects. Construct a historical interval on a preset timeline with the current time point as the endpoint and a preset historical duration as the width, and obtain the percentage of defective history within the historical interval; The degree of similarity is determined by calculating the average percentage of defects and the historical percentage of defects at the same original switching position, and the time point when the degree of similarity is greater than the preset benchmark similarity is defined as the similar time point; The effective adjustment distance is obtained at similar time points, and the individual adjustment distance is determined by calculation based on all effective adjustment distances.

[0008] Optionally, the step of calculating and determining the individual unit adjustment distance based on all valid adjustment distances includes: Construct similar adjustment ranges based on each effective adjustment distance and preset similar distances; The number within the range is determined by counting the effective adjustment distances within similar adjustment ranges; The number of values ​​within the range with the largest value is determined according to the preset sorting rules, and the similar adjustment range corresponding to the number of values ​​within this range is defined as the central range of the data set. The individual adjustment distance is determined by calculating the effective adjustment distance within the dataset range.

[0009] Optionally, the step of calculating the individual adjustment distance based on the effective adjustment distance within the dataset includes: The adjustment distance corresponding to the degree of similarity is determined based on the preset change matching relationship, and an equivalent coverage area is constructed based on the effective adjustment distance and the adjustment change distance. A numerical value is randomly selected from the dataset range and defined as the simulated selection distance. The effective representative coefficient is determined based on the simulated selection distance and each equivalent coverage area. The effective representative coefficient with the largest value is determined according to the sorting rules, and the simulation selection distance corresponding to the effective representative coefficient is determined as the single-unit adjustment distance.

[0010] Optionally, after the quantity within the range is determined, the intelligent control method for the die-casting machine also includes: Determine whether there are at least two similar adjustment ranges with the same and largest internal quantity; If there are no two closely related adjustment ranges with the same maximum number of elements in their middle ranges, then the closely related adjustment range corresponding to the maximum number of elements in the middle range is defined as the data center range. If there are at least two similar adjustment ranges with the same and largest internal quantity, then the similar adjustment range corresponding to the largest internal quantity is defined as the candidate adjustment range. Within the alternative adjustment range, the time interval between data points is determined based on similar time points of each effective adjustment distance and the current time point; The reliability coefficient of the data is determined by calculating and analyzing the time interval between data and the degree of similarity. The range reliability coefficient is determined by calculating the reliability coefficient of each data point, and the alternative adjustment range corresponding to the largest range reliability coefficient is defined as the data central range.

[0011] Optionally, after the range reliability coefficient is determined, the intelligent control method for the die-casting machine may also include: Determine whether there are at least two alternative adjustment ranges with the same and largest range reliability coefficients; If there are no at least two candidate adjustment ranges with the same and largest range reliability coefficients, then the candidate adjustment range corresponding to the largest range reliability coefficient is defined as the data central range. If there are at least two candidate adjustment ranges with the same and largest range reliability coefficients, then the candidate adjustment range corresponding to the largest range reliability coefficient is defined as the selected adjustment range. Within the selected adjustment range, a data reliability coefficient is randomly selected and defined as the primary reliability coefficient, and the remaining data reliability coefficients are defined as secondary reliability coefficients. The primary representative parameter is determined by calculation based on the primary reliability coefficient and all secondary reliability coefficients, and the primary reliability coefficient corresponding to the largest primary representative parameter is defined as the representative reliability coefficient. The reliability deviation coefficient is determined by calculating the difference between the representative reliability coefficient and the range reliability coefficient, and the selected adjustment range corresponding to the minimum reliability deviation coefficient is defined as the data central range.

[0012] Optional, also includes: Get the number of consecutive updates; The average number of adjustments is calculated based on all consecutive update counts, and then output to the management console.

[0013] Secondly, this application provides an intelligent control system for a die-casting machine, which adopts the following technical solution: An intelligent control system for a die-casting machine includes: The acquisition module is used to acquire backend detection data, which includes the total number of detections, the number of defects, and the types of defects. The processing module, connected to the acquisition and judgment modules, is used for information storage and processing; The judgment module, connected to the acquisition and processing modules, is used for judging information. The processing module calculates the defect percentage based on the number of defects and the total number of detections. When the judgment module determines that the defect percentage is greater than the preset abnormal demand percentage, it determines the type stability based on the defect type. When the judgment module determines that the type stability is greater than the preset type requirement, the processing module determines the direction of requirement adjustment based on the type of defect. The processing module determines the theoretical required position based on the required adjustment direction, the preset original switching position, and the preset single-unit adjustment distance. It then updates the theoretical required position to the new original switching position and controls the punch to switch speeds at the updated original switching position.

[0014] In summary, this application includes at least one of the following beneficial technical effects: During the die-casting process of the inverter housing, when a large number of defects are detected in the downstream products, the defect situation can be analyzed in a comprehensive manner to adjust the speed and position of the punch, thereby reducing the impact on product production caused by the loosening of the displacement sensor and facilitating effective production of the product. By analyzing various loosening situations under historical conditions, the required adjustment distance of the punch can be determined more accurately, thereby reducing the number of tests, improving the overall correction efficiency, and facilitating normal product production. Attached Figure Description

[0015] Figure 1 This is a flowchart of the intelligent control method for die-casting machines.

[0016] Figure 2 This is a flowchart of the module of the intelligent control method for die-casting machines. Detailed Implementation

[0017] To make the purpose, technical solution, and advantages of this application clearer, the following is combined with Figures 1-2 The present application will be further described in detail below with reference to embodiments. It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the application.

[0018] The embodiments of this application will now be described in further detail with reference to the accompanying drawings.

[0019] This application discloses an intelligent control method for a die-casting machine, referring to... Figure 1The method flow of the intelligent control method for die-casting machines includes the following steps: Step S100: Obtain backend detection data, which includes the total number of detections, the number of defects, and the types of defects.

[0020] The backend inspection data is the inspection data obtained after the die-casting station performs defect inspection on the produced products. This data includes the total number of inspections, the number of defects, and the types of defects. The total number of inspections is the number of products inspected within a preset unit of time. This unit of time is the time during which data can only be acquired from products within the current short period of time, such as 3 minutes. The number of defects is the number of defective products among the total number of products inspected. The types of defects are the types of defects that exist, such as the presence of porosity, flow marks, etc.

[0021] Step S101: Calculate the defect presence ratio based on the number of defects and the total number of inspections, and determine the type stability based on the defect presence type when the defect presence ratio is greater than the preset abnormal demand ratio.

[0022] The defect prevalence ratio is the value obtained by dividing the number of defects by the total number of products inspected. The abnormal demand ratio is the minimum defect prevalence ratio that must be achieved when the speed switching position of the punch is deemed to be problematic, resulting in a batch of product abnormalities. When the defect prevalence ratio is greater than the abnormal demand ratio, it indicates that there is currently a batch of abnormalities, that is, the speed switching position of the punch is inaccurate, and therefore analysis is required. The type stability is a parameter value that reflects the stability of the current defect type, that is, the ratio of the most frequent defect type to the products with defects.

[0023] Step S102: When the type stability is greater than the preset type requirement, determine the direction of requirement adjustment based on the type of defect.

[0024] Type requirement is the minimum type stability required when the types of defects identified by the staff are mostly consistent. Generally, all defective products need to be of the same type, so it can be set to 99%. Requirement adjustment direction refers to the direction in which the speed of the die-casting machine punch needs to be adjusted. There are two directions: towards the ingate and away from the ingate.

[0025] Step S103: Determine the theoretical required position based on the required adjustment direction, the preset original switching position, and the preset single-unit adjustment distance, update the theoretical required position to the new original switching position, and control the punch to switch speed at the updated original switching position.

[0026] The original switching position is the position where the speed is switched after the punch reaches its destination. The unit adjustment distance is the distance the punch moves. By moving the unit by the adjustment distance in the desired adjustment direction from the original switching position, the theoretical required position can be obtained. This position is then updated to the new original switching position. Only when the displacement sensor detects that the punch has reached the theoretical required position can the actual position of the punch possibly reach the preset theoretical required position. At this point, controlling the punch to switch speed has a higher probability of achieving accurate punch speed switching position, which can improve product yield and benefit product production.

[0027] It also includes a step for determining the individual unit adjustment distance, which includes: Step S200: Determine the defect presentation percentage of each product based on the backend detection data, and calculate the average defect percentage based on the total defect presentation percentage.

[0028] The defect presentation percentage refers to the severity of defects exhibited by defective products, which can be directly obtained through back-end inspection data. The average defect presentation percentage reflects the average percentage of defects caused by inaccurate positioning of the punch, and is calculated by averaging all defect presentation percentages.

[0029] Step S201: Construct a historical interval on the preset timeline with the current time point as the endpoint and the width as the preset historical duration, and obtain the percentage of defective history in the historical interval.

[0030] The time axis is a coordinate axis formed by combining various time points. This coordinate axis points from the time points that have been passed to the time points that have not yet been reached. The time points that have been passed are on the left side of the coordinate axis, and the left side of the coordinate axis is defined as the front side of the time axis. The historical duration is the total duration since the die-casting machine was put into use. Historical intervals are constructed to facilitate the acquisition and analysis of data within the historical duration. The historical defect percentage is the average percentage of defects determined when there are cases of inaccurate punch positions in the historical interval.

[0031] Step S202: Under the same original switching position, calculate the comparison similarity based on the average defect ratio and the historical defect ratio, and define the time point where the comparison similarity is greater than the preset benchmark similarity as the similar time point.

[0032] The comparison similarity reflects the similarity of the average defect percentage obtained at two time points when the punch is in the same original switching position under actual conditions. When the average defect percentage is completely consistent with the historical defect percentage, the corresponding comparison similarity is 100%. The benchmark similarity is the minimum comparison similarity set by the staff to determine that two processing situations are relatively similar. By defining similar time points, time points that are close to the current time point are identified and distinguished to facilitate subsequent analysis.

[0033] Step S203: Obtain the effective adjustment distance at similar time points, and calculate the individual adjustment distance based on all effective adjustment distances.

[0034] The effective adjustment distance is the total distance the punch has adjusted from the start of adjustment at similar time points until the die-casting machine is producing products normally. The adjustment distance of a single unit can be calculated by using all the effective adjustment distances. It can be obtained by calculating the average value or by using the method in steps S300-S303.

[0035] The steps for determining the individual unit adjustment distance based on all valid adjustment distances include: Step S300: Construct similar adjustment ranges based on each effective adjustment distance and preset similar distances.

[0036] The proximity distance is the maximum allowable difference between two distance values ​​set by the staff when they are considered to be close. The proximity adjustment range is the range of values ​​that the values ​​that are close to the effective adjustment distance need to be in. It is determined by adding and subtracting the proximity distance from the effective adjustment distance. That is, one effective adjustment distance corresponds to one proximity adjustment range.

[0037] Step S301: Count the effective adjustment distances within the same adjustment range to determine the number of items within the range.

[0038] The number within the range is the total number of effective adjustment distances within similar adjustment ranges.

[0039] Step S302: Determine the number of items in the range with the largest value according to the preset sorting rules, and define the similar adjustment range corresponding to the number of items in the range as the central range of the data.

[0040] The sorting rule is a method set by the staff to sort numerical values, such as the bubble sort algorithm. The sorting rule can determine the number of values ​​in the middle of the range with the largest value. In other words, the effective adjustment distance appears in the current corresponding close adjustment range, which means that the data is the most concentrated. Therefore, it is defined as the data concentration range to distinguish different close adjustment ranges, which is convenient for subsequent analysis.

[0041] Step S303: Calculate the individual unit adjustment distance based on the effective adjustment distance within the dataset range.

[0042] At this point, the average value of the effective adjustment distance within the data set range can be used to eliminate error data, thereby determining a more accurate individual adjustment distance. Alternatively, the individual adjustment distance can be calculated and determined using the methods in steps S400-S402.

[0043] The steps for calculating and determining the individual adjustment distance based on the effective adjustment distance within the dataset include: Step S400: Determine the adjustment distance corresponding to the degree of similarity based on the preset change matching relationship, and construct an equivalent coverage area based on the effective adjustment distance and the adjustment change distance.

[0044] The adjustment variation distance is the maximum allowable difference between the value that has the same effect as the effective adjustment distance and the effective adjustment distance. The greater the similarity between the two values, the more accurate the currently determined effective adjustment distance value is, and therefore the smaller the corresponding adjustment variation distance is. The variation matching relationship between the two is determined by the staff in advance through multiple tests. Equivalent coverage can be constructed by adding the adjustment variation distance to the effective adjustment distance and subtracting the adjustment variation distance from it.

[0045] Step S401: Randomly select a value from the range of the dataset and define it as the simulated selection distance. Calculate the effective representative coefficient based on the simulated selection distance and each equivalent coverage area.

[0046] By randomly defining the simulated selection distance, various situations can be simulated. The effective representative coefficient is a parameter value that reflects the feasibility of adjusting the simulated selection distance as a single unit. The distance between the simulated selection distance and the equivalent coverage area can be determined. Different distances correspond to different coefficients, with the coefficient decreasing as the distance increases. The effective representative coefficient is obtained by adding all the coefficients together. The relationship between distance and coefficient is determined in advance by the staff.

[0047] Step S402: Determine the effective representative coefficient with the largest value according to the sorting rules, and determine the simulation selection distance corresponding to the effective representative coefficient as the single-unit adjustment distance.

[0048] The sorting rules can determine the effective representative coefficient with the largest value, thus indicating that the corresponding simulated selection distance is the most accurate when adjusting the distance of a single unit.

[0049] Once the quantity within the range is determined, the intelligent control method for die-casting machines also includes: Step S500: Determine whether there are at least two similar adjustment ranges with the same and largest number of elements within each range.

[0050] The purpose of the judgment is to determine whether there are multiple similar adjustment ranges that meet the requirements.

[0051] Step S5001: If there are no at least two similar adjustment ranges with the same and largest internal quantity, then the similar adjustment range corresponding to the largest internal quantity is defined as the data center range.

[0052] When there are no at least two closely spaced adjustment ranges with the same maximum number of elements in their middle ranges, it means that there is only one closely spaced adjustment range that meets the requirements, so it can be defined as the data center range.

[0053] Step S5002: If there are at least two similar adjustment ranges with the same and largest internal quantity, then the similar adjustment range corresponding to the largest internal quantity is defined as the candidate adjustment range.

[0054] When there are at least two similar adjustment ranges with the same maximum number of values ​​within their ranges, it indicates that there are multiple similar adjustment ranges that meet the requirements. Therefore, these are defined as candidate adjustment ranges for identification and differentiation, which facilitates subsequent analysis.

[0055] Step S501: Under the alternative adjustment range, determine the data interval between similar time points of each effective adjustment distance and the current time point.

[0056] Data interval length refers to the time interval between similar time points and the current time point.

[0057] Step S502: Calculate and analyze the data based on the time interval between data points and the degree of similarity to determine the data reliability coefficient.

[0058] The data reliability coefficient is a parameter value that reflects the reliability of the currently acquired data. The shorter the time interval between data points, the higher the data reliability coefficient; the greater the similarity between comparisons, the higher the data reliability coefficient. Therefore, it can be approximated by the following formula: ,in For data reliability coefficient, To compare the degree of similarity, For the time interval of the data, These are parameter values ​​used to adjust for the time interval between data points and the multiples between comparisons of similarity.

[0059] Step S503: Calculate the range reliability coefficient based on the reliability coefficient of each data, and define the alternative adjustment range corresponding to the largest range reliability coefficient as the data central range.

[0060] The range reliability coefficient is the average of the data reliability coefficients for the effective adjustment distance within the current candidate adjustment range. The larger the value, the higher the reliability of the data within the corresponding range. Therefore, the candidate adjustment range corresponding to the largest range reliability coefficient can be defined as the data central range, which improves the accuracy of data analysis.

[0061] After the reliability coefficient is determined, the intelligent control method for die-casting machines also includes: Step S600: Determine whether there are at least two alternative adjustment ranges with the same and largest range reliability coefficients.

[0062] The purpose of this judgment is to determine whether there are multiple alternative adjustment ranges that satisfy the range reliability coefficient, so as to determine the range of the unique dataset.

[0063] Step S6001: If there are no at least two candidate adjustment ranges with the same and largest range reliability coefficients, then the candidate adjustment range corresponding to the largest range reliability coefficient is defined as the data central range.

[0064] When there are no at least two alternative adjustment ranges with the same and largest reliability coefficients, it means that there is only one alternative adjustment range that meets the requirements, so it can be defined as the data central range.

[0065] Step S6002: If there are at least two candidate adjustment ranges with the same and largest range reliability coefficients, then the candidate adjustment range corresponding to the largest range reliability coefficient is defined as the selected adjustment range.

[0066] When there are at least two alternative adjustment ranges with the same and largest range reliability coefficients, it indicates that there are multiple alternative adjustment ranges that meet the requirements. Therefore, these are defined as the selected adjustment ranges for subsequent analysis.

[0067] Step S601: Randomly select one data reliability coefficient from the selected adjustment range and define it as the primary reliability coefficient, and define the remaining data reliability coefficients as secondary reliability coefficients.

[0068] By defining primary and secondary reliability coefficients, different data reliability coefficients can be distinguished, which facilitates subsequent analysis.

[0069] Step S602: Calculate the main representative parameter based on the main reliability coefficient and all secondary reliability coefficients, and define the main reliability coefficient corresponding to the largest main representative parameter as the representative reliability coefficient.

[0070] The main representative parameter is the feasibility value of the main reliability coefficient when it represents the reliability coefficient of all data. The larger the value, the more representative the main reliability coefficient is of all data reliability coefficients. It is obtained by subtracting the main reliability coefficient from the secondary reliability coefficient, summing the absolute values, and taking the reciprocal. By defining the representative reliability coefficient, we can distinguish the most representative main reliability coefficient, which is convenient for subsequent analysis.

[0071] Step S603: Calculate the difference based on the representative reliability coefficient and the range reliability coefficient to determine the reliability deviation coefficient, and define the selected adjustment range corresponding to the smallest reliability deviation coefficient as the data central range.

[0072] The reliability deviation coefficient represents the difference between the reliability coefficient and the range reliability coefficient. This difference is an absolute value. The smallest reliability deviation coefficient indicates that the data within the corresponding selected adjustment range are relatively stable, without some data being larger and some data being smaller, which is more convincing and credible. Therefore, the corresponding selected adjustment range can be defined as the data central range to improve the accuracy of data analysis.

[0073] Intelligent control methods for die-casting machines also include: Step S700: Obtain the number of consecutive updates.

[0074] The number of consecutive updates is the number of adjustments required when the displacement sensor data is inaccurate and the original switching position needs to be changed to obtain a suitable original switching position. That is, each time the current situation occurs, only one number of consecutive updates will be recorded for data registration.

[0075] Step S701: Calculate the average number of adjustments based on all consecutive update counts, and output the average number of adjustments to the management terminal.

[0076] The average number of adjustments is the average of all consecutive updates. By observing the average number of adjustments, managers can easily understand the advantages of the system, and by observing the changes in the average number of adjustments in historical situations, they can understand the changes in system usage, providing data support for subsequent improvements.

[0077] Reference Figure 2 Based on the same inventive concept, embodiments of the present invention provide an intelligent control system for a die-casting machine, comprising: The acquisition module is used to acquire backend detection data, which includes the total number of detections, the number of defects, and the types of defects. The processing module, connected to the acquisition and judgment modules, is used for information storage and processing; The judgment module, connected to the acquisition and processing modules, is used for judging information. The processing module calculates the defect percentage based on the number of defects and the total number of detections. When the judgment module determines that the defect percentage is greater than the preset abnormal demand percentage, it determines the type stability based on the defect type. When the judgment module determines that the type stability is greater than the preset type requirement, the processing module determines the direction of requirement adjustment based on the type of defect. The processing module determines the theoretical required position based on the required adjustment direction, the preset original switching position, and the preset single-unit adjustment distance, and updates the theoretical required position to the new original switching position, and controls the punch to switch speed at the updated original switching position. The single-unit adjustment distance determination module is used to determine the single-unit adjustment distance that needs to be adjusted for the original switching position of the punch; The effective adjustment distance analysis module determines the individual unit adjustment distance by analyzing the effective adjustment distance. The data center range analysis module determines the individual unit adjustment distance by analyzing the data center range. The similar adjustment range filtering module is used to filter multiple similar adjustment ranges that meet the requirements. The alternative adjustment range filtering module is used to filter multiple alternative adjustment ranges that meet the requirements. The evaluation display module is used to evaluate and display the convenience achieved by using the current method, so as to highlight the rationality of this technology.

[0078] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional modules is used as an example. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. The specific working process of the system, device, and unit described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

Claims

1. A method for intelligent control of a die-casting machine, characterized in that, include: Obtain backend detection data, which includes the total number of detections, the number of defects, and the types of defects. The proportion of defects is determined by calculating the number of defects and the total number of inspections. When the proportion of defects exceeds the preset proportion of abnormal demands, the stability of each defect type is determined. When the type stability is greater than the preset type demand, the direction of demand adjustment is determined based on the type of defect. The theoretical required position is determined based on the required adjustment direction, the preset original switching position, and the preset single-unit adjustment distance. This theoretical required position is then updated to the new original switching position, and the speed of the punch is controlled to switch at the updated original switching position.

2. The intelligent control method for a die-casting machine according to claim 1, characterized in that, It also includes a step for determining the individual unit adjustment distance, which includes: The percentage of defects for each product is determined based on backend testing data, and the average percentage of defects is calculated based on the percentage of all defects. Construct a historical interval on a preset timeline with the current time point as the endpoint and a preset historical duration as the width, and obtain the percentage of defective history within the historical interval; The degree of similarity is determined by calculating the average percentage of defects and the historical percentage of defects at the same original switching position, and the time point when the degree of similarity is greater than the preset benchmark similarity is defined as the similar time point; The effective adjustment distance is obtained at similar time points, and the individual adjustment distance is determined by calculation based on all effective adjustment distances.

3. The intelligent control method for a die-casting machine according to claim 2, characterized in that, The steps for determining the individual unit adjustment distance based on all valid adjustment distances include: Construct similar adjustment ranges based on each effective adjustment distance and preset similar distances; The number within the range is determined by counting the effective adjustment distances within similar adjustment ranges; The number of values ​​within the range with the largest value is determined according to the preset sorting rules, and the similar adjustment range corresponding to the number of values ​​within this range is defined as the central range of the data set. The individual adjustment distance is determined by calculating the effective adjustment distance within the dataset range.

4. The intelligent control method for a die-casting machine according to claim 3, characterized in that, The steps for calculating and determining the individual adjustment distance based on the effective adjustment distance within the dataset include: The adjustment distance corresponding to the degree of similarity is determined based on the preset change matching relationship, and an equivalent coverage area is constructed based on the effective adjustment distance and the adjustment change distance. A numerical value is randomly selected from the dataset range and defined as the simulated selection distance. The effective representative coefficient is determined based on the simulated selection distance and each equivalent coverage area. The effective representative coefficient with the largest value is determined according to the sorting rules, and the simulation selection distance corresponding to the effective representative coefficient is determined as the single-unit adjustment distance.

5. The intelligent control method for a die-casting machine according to claim 3, characterized in that, Once the quantity within the range is determined, the intelligent control method for die-casting machines also includes: Determine whether there are at least two similar adjustment ranges with the same and largest internal quantity; If there are no two closely related adjustment ranges with the same maximum number of elements in their middle ranges, then the closely related adjustment range corresponding to the maximum number of elements in the middle range is defined as the data center range. If there are at least two similar adjustment ranges with the same and largest internal quantity, then the similar adjustment range corresponding to the largest internal quantity is defined as the candidate adjustment range. Within the alternative adjustment range, the time interval between data points is determined based on similar time points of each effective adjustment distance and the current time point; The reliability coefficient of the data is determined by calculating and analyzing the time interval between data and the degree of similarity. The range reliability coefficient is determined by calculating the reliability coefficient of each data point, and the alternative adjustment range corresponding to the largest range reliability coefficient is defined as the data central range.

6. The intelligent control method for a die-casting machine according to claim 5, characterized in that, At After the reliability coefficient is determined, the intelligent control method for die-casting machines also includes: Determine whether there are at least two alternative adjustment ranges with the same and largest range reliability coefficients; If there are no at least two candidate adjustment ranges with the same and largest range reliability coefficients, then the candidate adjustment range corresponding to the largest range reliability coefficient is defined as the data central range. If there are at least two candidate adjustment ranges with the same and largest range reliability coefficients, then the candidate adjustment range corresponding to the largest range reliability coefficient is defined as the selected adjustment range. Within the selected adjustment range, a data reliability coefficient is randomly selected and defined as the primary reliability coefficient, and the remaining data reliability coefficients are defined as secondary reliability coefficients. The primary representative parameter is determined by calculation based on the primary reliability coefficient and all secondary reliability coefficients, and the primary reliability coefficient corresponding to the largest primary representative parameter is defined as the representative reliability coefficient. The reliability deviation coefficient is determined by calculating the difference between the representative reliability coefficient and the range reliability coefficient, and the selected adjustment range corresponding to the minimum reliability deviation coefficient is defined as the data central range.

7. The intelligent control method for a die-casting machine according to claim 1, characterized in that, Also includes: Get the number of consecutive updates; The average number of adjustments is calculated based on all consecutive update counts, and then output to the management console.

8. An intelligent control system for a die-casting machine, characterized in that, include: The acquisition module is used to acquire backend detection data, which includes the total number of detections, the number of defects, and the types of defects. The processing module, connected to the acquisition and judgment modules, is used for information storage and processing; The judgment module, connected to the acquisition and processing modules, is used for judging information. The processing module calculates the defect percentage based on the number of defects and the total number of detections. When the judgment module determines that the defect percentage is greater than the preset abnormal demand percentage, it determines the type stability based on the defect type. When the judgment module determines that the type stability is greater than the preset type requirement, the processing module determines the direction of requirement adjustment based on the type of defect. The processing module determines the theoretical required position based on the required adjustment direction, the preset original switching position, and the preset single-unit adjustment distance. It then updates the theoretical required position to the new original switching position and controls the punch to switch speeds at the updated original switching position.

Images