Intelligent balance control method and system for temperature of die-casting die

Abstract

The invention discloses an intelligent balance control method and system for the temperature of a die-casting die, and relates to the technical field of temperature control, and the method comprises the steps: collecting the temperature monitoring time sequence information of the die-casting die; performing anomaly analysis on the die-casting die temperature monitoring time sequence information based on the die-casting die baseline temperature time sequence information, and when a die-casting die temperature anomaly coefficient is greater than or equal to a temperature anomaly coefficient threshold, optimizing a medium temperature attribute and a medium flow attribute to generate a first medium optimization temperature and a first medium optimization flow, and the medium temperature control assembly and the medium flow control assembly are controlled. The technical problem that in the prior art, the temperature and flow of an output medium of a traditional water temperature machine are fixed values, temperature changes in actual production cannot be met, and consequently the die temperature control precision is low is solved, flexible control over the die-casting die temperature through the interactive water temperature machine is achieved, and the die-casting efficiency is improved. And the die temperature control precision of the die-casting die is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of temperature control, and in particular to a method and system for intelligently balancing the temperature of a die-casting mold. Background Art

[0002] With the global emphasis on energy conservation, emission reduction and product lightweighting technologies, light alloy materials such as aluminum and magnesium and their forming technologies have been rapidly developed and widely used. Due to its unique advantages, the die-casting process has become the main means of manufacturing large, complex and precision die-castings. Die-casting mold temperature control is a key link in the die-casting process, which directly affects the quality and production efficiency of the castings. As a mold temperature controller with water as the medium, the water temperature controller controls the temperature of the die-casting mold by controlling the temperature and flow of water. However, the temperature of the output medium of the traditional water temperature controller is a fixed temperature, and the flow rate is a fixed flow rate, which cannot meet the temperature changes in the actual production process of the mold, resulting in low temperature control accuracy and affecting product quality. Summary of the invention

[0003] The present application provides a method and system for intelligent temperature balance control of a die-casting mold, which is used to solve the technical problem in the prior art that the temperature and flow rate of the output medium of a traditional water temperature machine are fixed values ​​and cannot meet the temperature changes in actual production, resulting in low mold temperature control accuracy.

[0004] In a first aspect of the present application, a method for intelligent temperature balance control of a die-casting mold is provided, the method comprising: receiving a baseline temperature timing information of the die-casting mold; when the die-casting mold is started and the temperature collection cycle is satisfied, collecting the temperature monitoring timing information of the die-casting mold through a mold temperature detection component; based on the baseline temperature timing information of the die-casting mold, performing an abnormality analysis on the temperature monitoring timing information of the die-casting mold to obtain a temperature abnormality coefficient of the die-casting mold; when the temperature abnormality coefficient of the die-casting mold is greater than or equal to a temperature abnormality coefficient threshold, optimizing a medium temperature attribute and a medium flow attribute to generate a first medium optimized temperature and a first medium optimized flow; controlling the medium temperature control component according to the first medium optimized temperature, and controlling the medium flow control component according to the first medium optimized flow.

[0005] According to a second aspect of the present application, there is provided an intelligent temperature balance control system for a die-casting mold, the system comprising: a baseline temperature timing information acquisition module, the baseline temperature timing information acquisition module being used to receive the baseline temperature timing information of the die-casting mold; a temperature monitoring timing information acquisition module, the temperature monitoring timing information acquisition module being used to collect the temperature monitoring timing information of the die-casting mold through a mold temperature detection component when the die-casting mold is started and the temperature acquisition cycle is satisfied; a temperature anomaly coefficient acquisition module, the temperature anomaly coefficient acquisition module being used to perform an anomaly analysis on the temperature monitoring timing information of the die-casting mold based on the baseline temperature timing information of the die-casting mold to obtain the temperature anomaly coefficient of the die-casting mold; a medium attribute optimization module, the medium attribute optimization module being used to optimize the medium temperature attribute and the medium flow attribute when the temperature anomaly coefficient of the die-casting mold is greater than or equal to the temperature anomaly coefficient threshold, and generate a first medium optimized temperature and a first medium optimized flow; a component control module, the component control module being used to control the medium temperature control component according to the first medium optimized temperature, and to control the medium flow control component according to the first medium optimized flow.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] The present application provides an intelligent temperature balancing control method for a die-casting mold, which relates to the field of temperature control technology. The method uses the die-casting mold baseline temperature timing information to perform an abnormal analysis on the die-casting mold temperature monitoring timing information. When the generated die-casting mold temperature anomaly coefficient is greater than or equal to the temperature anomaly coefficient threshold, the medium temperature attribute and the medium flow attribute are optimized, and the medium temperature control component and the medium flow control component are controlled according to the optimized medium optimization temperature and medium optimization flow. This solves the technical problem in the prior art that the temperature and flow of the medium output by the traditional water temperature machine are fixed values ​​and cannot meet the temperature changes in actual production, resulting in low mold temperature control accuracy. This achieves the technical effect of flexible control of the die-casting mold temperature through an interactive water temperature machine, improving the temperature control accuracy of the die-casting mold, and thereby improving work efficiency and product quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0009] Figure 1 A schematic diagram of a process flow of an intelligent temperature balance control method for a die casting mold provided in an embodiment of the present application;

[0010] Figure 2 A schematic diagram of a flow chart of obtaining a temperature anomaly coefficient of a die-casting die in a die-casting die temperature intelligent balance control method provided in an embodiment of the present application;

[0011] Figure 3 A schematic diagram of the structure of an intelligent temperature balancing control system for a die-casting mold provided in an embodiment of the present application.

[0012] Explanation of the reference numerals: baseline temperature time series information acquisition module 11 , temperature monitoring time series information acquisition module 12 , temperature anomaly coefficient acquisition module 13 , medium property optimization module 14 , component control module 15 . DETAILED DESCRIPTION

[0013] The present application provides a method for intelligently balancing the temperature of a die-casting mold, which is used to solve the technical problem in the prior art that the temperature and flow rate of the output medium of a traditional water temperature machine are fixed values ​​and cannot meet the temperature changes in actual production, resulting in low mold temperature control accuracy.

[0014] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0015] It should be noted that the terms "first", "second", etc. in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices.

[0016] Embodiment 1

[0017] like Figure 1As shown, the present application provides a method for intelligent balancing control of die casting mold temperature, which is applied to a server, wherein the server is deployed on an interactive water temperature machine, wherein the interactive water temperature machine includes a medium temperature control component, a medium flow control component and a mold temperature detection component, wherein the mold temperature detection component includes a plurality of temperature detection terminals, and the plurality of temperature detection terminals are installed at preset positions of the die casting mold, wherein the method includes:

[0018] P10: Receive die-casting mold baseline temperature timing information.

[0019] Specifically, the present application provides a method for intelligent balancing control of the temperature of a die-casting mold, the core of which is to realize intelligent monitoring and adjustment of the temperature of the die-casting mold through the collaborative work of a server and an interactive water temperature machine. This method is applied to a server, and the server, as the center of the control method, is deployed on an interactive water temperature machine and is responsible for receiving data, performing calculations and sending control instructions. At the same time, the interactive water temperature machine includes a medium temperature control component, a medium flow control component and a mold temperature detection component. Among them, the medium temperature control component is used to adjust the temperature of the medium (which may be water or other liquids). The medium flow control component is used to control the flow of the medium, that is, the amount of medium flowing through the mold per unit time. The mold temperature detection component includes a plurality of temperature detection terminals, which are installed at a preset position of the die-casting mold for real-time monitoring of the mold temperature.

[0020] First, it is necessary to obtain the baseline temperature time series information of the die-casting mold. The baseline temperature time series information refers to the range of temperature changes over time of the die-casting mold under normal working conditions. It can be used as a temperature reference value for subsequent temperature anomaly analysis to determine whether the mold temperature exceeds the normal working range. In addition, the baseline temperature time series information can be obtained by collecting historical temperature change data of the target die-casting mold under normal working conditions and performing a central trend analysis. Exemplarily, based on the temperature monitoring log of the die-casting mold under normal working conditions, multiple temperature monitoring values ​​of the mold at different positions at multiple times can be obtained, and the temperature monitoring values ​​at different times can be subjected to a central trend analysis. For example, after calculating the average value, the concentrated value of temperature monitoring at different times is obtained, and the baseline temperature time series information is obtained after fitting based on the time sequence.

[0021] P20: When the die-casting mold is started and the temperature collection cycle is met, the die-casting mold temperature monitoring timing information is collected through the mold temperature detection component.

[0022] Furthermore, step P20 of the embodiment of the present application further includes:

[0023] P21: obtaining, through the mold temperature detection component, a plurality of temperature detection values ​​at the first moment, a plurality of temperature detection values ​​at the second moment, and a plurality of temperature detection values ​​at the Nth moment of a plurality of temperature detection terminals within the temperature acquisition cycle, and resetting the temperature acquisition cycle at the same time;

[0024] P22: Traverse the multiple temperature detection values ​​at the first moment, the multiple temperature detection values ​​at the second moment, and then perform central trend fitting on the multiple temperature detection values ​​at the Nth moment to generate the die-casting mold temperature monitoring timing information.

[0025] It should be understood that when the die-casting mold is started, that is, the die-casting machine starts running and the mold enters the working state, the mold temperature is collected according to the temperature collection cycle. The temperature collection cycle can be set by professionals according to the temperature monitoring accuracy requirements. For example, it is set to collect temperature every 30 seconds. The die-casting mold temperature monitoring timing information can be collected through the mold temperature detection component. The mold temperature detection component is a device or system for real-time monitoring of the mold temperature, including multiple temperature detection terminals, which are located at different positions of the mold and are used to measure the temperature at different positions of the mold.

[0026] Specifically, through the mold temperature detection component, the temperature detection values ​​of multiple temperature detection terminals at different times within the temperature acquisition cycle are obtained, including multiple temperature detection values ​​at the first moment, multiple temperature detection values ​​at the second moment, and multiple temperature detection values ​​at the Nth moment. Among them, the first moment, the second moment...the Nth moment represent different time points within the temperature acquisition cycle. At each time point, the mold temperature detection component will obtain temperature values ​​from multiple temperature detection terminals. These values ​​can form a two-dimensional array or list, in which the first dimension represents the time point and the second dimension represents the temperature detection terminal. After completing the data acquisition of a temperature acquisition cycle, the system will reset the temperature acquisition cycle so as to continue collecting data in the next cycle.

[0027] Furthermore, all the collected temperature detection values ​​at different moments are traversed, that is, multiple temperature detection values ​​at the first moment, multiple temperature detection values ​​at the second moment, and multiple temperature detection values ​​at the Nth moment are traversed, and central trend fitting is performed on them. The central trend fitting is a data analysis method for extracting the main trend or pattern from a set of data. In the present application, first, a central trend analysis is performed on multiple temperature detection values ​​at each moment. Central trend analysis generally includes calculating statistics such as mean, median, mode, etc. to describe the overall level of mold temperature at that moment. Further, the statistics of central trend analysis (usually mean) are used for fitting. Various mathematical methods, such as linear fitting, polynomial fitting, curve fitting, etc., are used to depict the trend of mold temperature changing over time, and generate one or more curves of temperature changing over time as die-casting mold temperature monitoring timing information.

[0028] The die-casting mold temperature monitoring time series information can be used to analyze the change pattern of the mold temperature. For example, the fluctuation of the temperature curve can be observed to determine whether the mold is overheated or overcooled. The temperature differences in different time periods or different locations can be compared to understand the temperature distribution of the mold. The future temperature state can also be predicted based on the temperature change trend, so as to take corresponding control measures in advance.

[0029] P30: Based on the die-casting mold baseline temperature timing information, perform an abnormal analysis on the die-casting mold temperature monitoring timing information to obtain the die-casting mold temperature abnormality coefficient.

[0030] Further, such as Figure 2 As shown, step P30 of the embodiment of the present application also includes:

[0031] P31: obtaining the monitoring time zone of the die-casting mold temperature monitoring time series information, and extracting segment baseline temperature time series information from the die-casting mold baseline temperature time series information;

[0032] P32: configuring the temperature deviation threshold timing information, wherein the temperature deviation threshold timing information corresponds one-to-one to the die-casting mold baseline temperature timing information;

[0033] P33: Count the time zone step ratios in which the segment baseline temperature timing information and the die-casting mold baseline temperature timing information do not meet the temperature deviation threshold, and set it as the die-casting mold temperature anomaly coefficient.

[0034] Optionally, based on the die-casting mold baseline temperature timing information, the die-casting mold temperature monitoring timing information is analyzed for abnormality to determine whether the current temperature state of the die-casting mold is normal, and to obtain the die-casting mold temperature abnormality coefficient.

[0035] Specifically, first, the monitoring time zone of the die-casting mold temperature monitoring timing information is obtained, that is, the monitoring time period or time window of the die-casting mold temperature monitoring timing information, and then according to the monitoring time zone, the segment baseline temperature timing information corresponding to the time is extracted from the die-casting mold baseline temperature timing information.

[0036] Furthermore, according to the process requirements, material characteristics and other factors of the die-casting mold, the temperature deviation threshold timing information is configured. The temperature deviation threshold timing information is a set of preset temperature deviation thresholds, which represents the maximum temperature deviation allowed at each time point or time period in the baseline temperature timing information, and can be used to determine whether the actual temperature data exceeds the normal range. In addition, the temperature deviation threshold timing information corresponds to the die-casting mold baseline temperature timing information one by one, ensuring that there is a corresponding temperature deviation threshold as a reference at each time point or time period.

[0037] Furthermore, the extracted fragment baseline temperature timing information is compared point by point with the die-casting mold temperature monitoring timing information. The time zone step length, that is, the number of time points or time periods, in which the actual temperature data exceeds the temperature deviation threshold within the monitoring time zone is counted. And the ratio of the time zone step length to the entire monitoring time zone step length is calculated and set as the die-casting mold temperature anomaly coefficient. The die-casting mold temperature anomaly coefficient can be used to evaluate whether the temperature state of the die-casting mold is normal. For example, if the temperature anomaly coefficient exceeds a preset threshold, it may mean that the die-casting mold has an abnormal condition and needs to be handled in time.

[0038] Furthermore, step P32 of the embodiment of the present application also includes:

[0039] P32-1: extracting the die-casting mold baseline temperature in the first time zone according to the die-casting mold baseline temperature time series information;

[0040] P32-2: Based on the die-casting mold baseline temperature in the first time zone and with a step length of 0.5°C, a first deviation mold temperature gradient sequence is configured which is less than the die-casting mold baseline temperature in the first time zone;

[0041] P32-3: Based on the die-casting mold baseline temperature in the first time zone and with a step length of 0.5°C, a second deviation mold temperature gradient sequence is configured that is greater than the die-casting mold baseline temperature in the first time zone;

[0042] P32-4: traverse the first deviation mold temperature gradient sequence to sample the die-casting qualified rate of the die-casting mold model, and generate a first die-casting qualified rate set;

[0043] P32-5: traverse the second deviation mold temperature gradient sequence to sample the die-casting qualified rate of the die-casting mold model, and generate a second die-casting qualified rate set;

[0044] P32-6: Based on the first die-casting qualified rate set and the second die-casting qualified rate set, analyze the temperature deviation threshold of the die-casting mold in the first time zone, and add the temperature deviation threshold timing information.

[0045] Specifically, the specific process of configuring the temperature deviation threshold timing information may be to first extract the first time zone die casting mold baseline temperature corresponding to the first time zone from the die casting mold baseline temperature timing information. This baseline temperature represents the normal operating temperature of the die casting mold in the time zone.

[0046] Furthermore, starting from the die-casting mold baseline temperature in the first time zone, a series of temperature values ​​are configured downward (i.e., in the direction of lower temperature) with a step length of 0.5°C to form a first deviation mold temperature gradient sequence, and the first deviation mold temperature gradient sequence includes multiple possible temperature points lower than the baseline temperature. Similarly, starting from the die-casting mold baseline temperature in the first time zone, but upward (i.e., in the direction of higher temperature) with a step length of 0.5°C, a series of temperature values ​​are configured to form a second deviation mold temperature gradient sequence. The second deviation mold temperature gradient sequence includes multiple possible temperature points higher than the baseline temperature.

[0047] Furthermore, in the actual production process, the die-casting qualified rate of the die-casting die model is sampled for the temperature value in each first deviation die temperature gradient sequence. That is, the qualified rate of the die-casting die is tested under different low temperature conditions, and the results are recorded in the first die-casting qualified rate set. Similarly, the second deviation die temperature gradient sequence is traversed, and the die-casting qualified rate of the die-casting die model is sampled under high temperature conditions, and the results are recorded in the second die-casting qualified rate set.

[0048] Furthermore, by analyzing the data in the first die-casting qualified rate set and the second die-casting qualified rate set, the temperature points at which the die-casting qualified rate begins to drop significantly can be found by drawing a temperature-qualified rate change curve, and these temperature points are used as the temperature deviation thresholds of the die-casting mold in the time zone. The generated multiple temperature deviation thresholds in different time zones are added to the temperature deviation threshold time series information as a basis for judging whether the temperature of the die-casting mold is abnormal.

[0049] Furthermore, step P32-6 of the embodiment of the present application also includes:

[0050] P32-61: When the first temperature die casting qualified rate of the first deviation mold temperature gradient sequence is greater than or equal to the die casting qualified rate threshold, the second temperature die casting qualified rate is less than the die casting qualified rate threshold, the second temperature is less than the first temperature, and the second temperature is a temperature adjacent to the first temperature;

[0051] P32-62: constructing a first temperature deviation threshold value according to the first temperature and the die-casting mold baseline temperature in the first time zone;

[0052] P32-63: When the third temperature die casting qualified rate of the second deviation mold temperature gradient sequence is greater than or equal to the die casting qualified rate threshold, the fourth temperature die casting qualified rate is less than the die casting qualified rate threshold, the fourth temperature is greater than the third temperature, and the fourth temperature is a temperature adjacent to the third temperature;

[0053] P32-64: constructing a second temperature deviation threshold value according to the third temperature and the die-casting mold baseline temperature in the first time zone;

[0054] P32-65: Take the smaller value of the first temperature deviation threshold and the second temperature deviation threshold, and set it as the temperature deviation threshold of the die-casting mold in the first time zone.

[0055] Optionally, when traversing the first deviation mold temperature gradient sequence, if the die-casting pass rate at a certain temperature (e.g., the first temperature) is still greater than or equal to the preset die-casting pass rate threshold, but the die-casting pass rate at the next lower temperature (e.g., the second temperature) is already lower than the threshold, and the second temperature is lower than the first temperature, then the first temperature can be considered to be a key point. Since the first temperature is the key point at which the die-casting pass rate begins to decline, the difference between the first temperature and the baseline temperature of the die-casting mold in the first time zone can be used as the first temperature deviation threshold. The first temperature deviation threshold represents how much the mold temperature is lower than the baseline temperature, and the die-casting pass rate will begin to decline significantly.

[0056] Further, when traversing the second deviation mold temperature gradient sequence (i.e., a sequence higher than the baseline temperature), when the die-casting pass rate at a certain temperature (e.g., the third temperature) is still greater than or equal to the preset die-casting pass rate threshold, but the die-casting pass rate at the next higher temperature (e.g., the fourth temperature) is lower than the threshold, the third temperature is used as the key point. And the difference between the third temperature and the die-casting mold baseline temperature in the first time zone is used as the second temperature deviation threshold.

[0057] Furthermore, considering that the impact of temperature deviation on the die-casting pass rate may vary in different directions, for example, lower temperature may have a greater impact on the die-casting pass rate, the smaller value of the first temperature deviation threshold and the second temperature deviation threshold is selected as the final temperature deviation threshold of the die-casting mold in the first time zone for subsequent temperature anomaly detection.

[0058] P40: When the temperature anomaly coefficient of the die-casting mold is greater than or equal to the temperature anomaly coefficient threshold, the medium temperature attribute and the medium flow attribute are optimized to generate a first medium optimized temperature and a first medium optimized flow.

[0059] It should be understood that when the temperature anomaly coefficient of the die-casting mold is greater than or equal to the temperature anomaly coefficient threshold, it is considered that the temperature of the die-casting mold is abnormal and needs to be adjusted. In order to adjust the temperature of the die-casting mold, it is necessary to adjust the temperature and flow of the medium. Among them, the medium, i.e., the temperature control medium, can be cooling water, hot oil or other temperature control medium. Exemplarily, through optimization algorithms such as gradient descent, genetic algorithm, particle swarm optimization, etc., considering the influencing factors such as the material, structure, production process requirements, and ambient temperature of the die-casting mold, the medium temperature properties and the medium flow properties are adjusted and optimized to find the best medium temperature and flow combination. After the optimization process, a set of optimized medium temperature and flow values, i.e., the first medium optimized temperature and the first medium optimized flow, are output as new medium temperature and flow set values, which are used to adjust the temperature of the die-casting mold to ensure the smooth progress of the die-casting process and the stability of product quality.

[0060] P50: Control the medium temperature control component according to the first medium optimized temperature, and control the medium flow control component according to the first medium optimized flow.

[0061] In a possible embodiment of the present application, the corresponding control components are controlled according to the first medium optimized temperature and the first medium optimized flow rate. First, components related to medium temperature control are identified, including heaters, coolers, temperature regulating valves, etc. Further, according to the first medium optimized temperature, control instructions are sent to the medium temperature control components. For example, if the first medium optimized temperature is lower than the current medium temperature, the cooler is instructed to increase the working intensity or the heater is instructed to reduce the working intensity. And during the control process, the changes in the medium temperature are monitored in real time to ensure that the medium temperature gradually approaches and stabilizes at the optimized temperature.

[0062] Similarly, components related to medium flow control, such as flow control valves, pumps, etc., are identified. Based on the first medium optimized flow, control instructions are sent to the medium flow control component. If the first medium optimized flow is less than the current flow, the pump is instructed to reduce the speed or the flow control valve is instructed to reduce the opening. Similarly, the changes in medium flow are monitored in real time to ensure that the medium flow gradually approaches and stabilizes at the optimized flow.

[0063] In practical applications, medium temperature control and medium flow control are often interrelated. Therefore, in the control process, it is necessary to comprehensively consider the changes of both and make corresponding adjustments. For example, if the medium temperature drops too quickly after increasing the medium flow, it is necessary to appropriately increase the medium temperature or reduce the flow to maintain a stable die-casting mold temperature. Through the above control operations, the system can effectively adjust the temperature of the die-casting mold to ensure the stability of the die-casting process and product quality.

[0064] Furthermore, the embodiment of the present application further includes step P60, and step P60 further includes:

[0065] P61: When the temperature anomaly coefficient of the die-casting mold is less than the temperature anomaly coefficient threshold, the medium temperature control component is interacted to obtain the real-time temperature of the medium, and the medium flow control component is interacted to obtain the real-time flow of the medium;

[0066] P62: According to the real-time temperature of the medium and the real-time flow rate of the medium, temperature prediction is performed based on the die-casting mold temperature monitoring time series information to generate die-casting mold temperature prediction time series information for a preset future time zone;

[0067] P63: Based on the die-casting mold baseline temperature time series information, perform an abnormal analysis on the die-casting mold temperature prediction time series information to obtain a die-casting mold prediction temperature abnormality coefficient;

[0068] P64: When the predicted temperature anomaly coefficient of the die-casting mold is greater than or equal to the temperature anomaly coefficient threshold, optimizing the medium temperature attribute and the medium flow attribute to generate a second medium optimized temperature and a second medium optimized flow;

[0069] P65: Preset the future time zone configuration for the medium temperature control component according to the second medium optimized temperature, and configure the medium flow control component according to the second medium optimized flow.

[0070] It should be understood that step P60 of this embodiment provides a prediction mechanism for the die-casting mold temperature, which can optimize the medium temperature and flow in advance when it is predicted that the temperature may be abnormal. Specifically, when the die-casting mold temperature anomaly coefficient is less than the temperature anomaly coefficient threshold, that is, the current die-casting mold temperature is within the normal range, the interactive medium temperature control component and the medium flow control component are used to obtain the real-time temperature and real-time flow data of the medium.

[0071] Furthermore, the obtained real-time temperature and real-time flow data of the medium are used in combination with the die-casting mold temperature monitoring timing information for temperature prediction. A variety of prediction algorithms can be used, such as time series analysis, machine learning models (such as neural networks, decision trees, etc.) or other statistical methods to generate die-casting mold temperature prediction timing information for a preset future time zone (such as the next one or more hours, shifts, etc.).

[0072] Furthermore, the die-casting mold temperature prediction time series information is used as a reference, and the die-casting mold temperature prediction time series information is analyzed for abnormalities. By comparing the predicted temperature with the baseline temperature, the die-casting mold predicted temperature abnormality coefficient is calculated, and the coefficient can reflect the degree to which the predicted temperature deviates from the normal temperature range. When the die-casting mold predicted temperature abnormality coefficient is greater than or equal to the temperature abnormality coefficient threshold, it is considered that the die-casting mold temperature may be abnormal in a certain period of time in the future. Then, the above method can be referred to to optimize the medium temperature attribute and the medium flow attribute in advance to find the best medium temperature and flow combination that can prevent or alleviate temperature abnormalities, and generate the second medium optimized temperature and the second medium optimized flow.

[0073] Furthermore, based on the second medium optimized temperature and the second medium optimized flow rate obtained through optimization, the medium temperature control component and the medium flow control component are configured for preset future time zones to prevent or reduce the impact of actual temperature anomalies on the die-casting process, thereby improving the stability of the die-casting process and product quality.

[0074] Furthermore, step P62 of the embodiment of the present application also includes:

[0075] P62-1: Collect die-casting mold temperature test data, wherein the die-casting mold temperature test data includes a medium real-time temperature record data set, a medium real-time flow record data set and a die-casting mold temperature timing information record data set;

[0076] P62-2: cutting the die-casting mold temperature timing information record data set to generate a die-casting mold temperature timing information input record data set and a die-casting mold temperature timing information output record data set;

[0077] P62-3: Based on the medium real-time temperature record data set, the medium real-time flow record data set and the die-casting mold temperature timing information input record data set as input, and through the die-casting mold temperature timing information output record data set as supervision, a long short-term memory neural network is configured to generate a temperature prediction model;

[0078] P62-4: According to the temperature prediction model, according to the real-time temperature of the medium and the real-time flow rate of the medium, temperature prediction is performed based on the die-casting mold temperature monitoring timing information to generate the die-casting mold temperature prediction timing information of the preset future time zone.

[0079] Specifically, the specific process of predicting the die-casting mold temperature in a preset future time zone may be to first collect die-casting mold temperature test data related to die-casting mold temperature prediction, including collecting media real-time temperature record data sets, media real-time flow record data sets and die-casting mold temperature time series information record data sets. Furthermore, in order to configure and train the temperature prediction model, it is necessary to cut the die-casting mold temperature time series information record data set into an input record data set and an output record data set. The input record data set contains historical data for predicting the die-casting mold temperature, and the output record data set contains the actual temperature value corresponding to the input data, which is used to supervise the model training process.

[0080] Furthermore, the medium real-time temperature record data set, the medium real-time flow record data set and the die-casting mold temperature time series information input record data set are used as input, and the die-casting mold temperature time series information output record data set is used as supervision to configure a long short-term memory neural network (LSTM). LSTM is a neural network structure that is particularly suitable for processing time series data and can capture long-term dependencies in data. Therefore, it is suitable for time series prediction tasks such as temperature prediction. When configuring the LSTM model, it is necessary to define the structure of the network, such as the number of hidden layers, the number of neurons in each layer, etc., as well as hyperparameters in the training process, such as learning rate, batch size, number of iterations, etc. The selection of these parameters will affect the performance and prediction accuracy of the model.

[0081] Furthermore, based on the real-time temperature and real-time flow data of the medium, and the monitoring time series information of the die-casting mold temperature (i.e., historical temperature data), these data are input into the trained temperature prediction model to perform temperature prediction, and the die-casting mold temperature prediction time series information for the preset future time zone is generated to provide forward-looking guidance for temperature control of the die-casting process.

[0082] In summary, the embodiments of the present application have at least the following technical effects:

[0083] The present application performs an abnormal analysis on the die-casting mold temperature monitoring timing information through the die-casting mold baseline temperature timing information. When the generated die-casting mold temperature anomaly coefficient is greater than or equal to the temperature anomaly coefficient threshold, the medium temperature properties and the medium flow properties are optimized, and the medium temperature control component and the medium flow control component are controlled according to the optimized medium optimization temperature and medium optimization flow.

[0084] The technical effect of flexibly controlling the temperature of the die-casting mold through the interactive water temperature machine and improving the mold temperature control accuracy of the die-casting mold is achieved.

[0085] Embodiment 2

[0086] Based on the same inventive concept as the method for intelligent temperature balance control of a die casting mold in the aforementioned embodiment, Figure 3 As shown, the present application provides an intelligent temperature balance control system for a die casting mold, and the system and method embodiments in the present application are based on the same inventive concept. The system includes:

[0087] A baseline temperature timing information acquisition module 11, wherein the baseline temperature timing information acquisition module 11 is used to receive the baseline temperature timing information of the die-casting mold;

[0088] A temperature monitoring timing information acquisition module 12, wherein the temperature monitoring timing information acquisition module 12 is used to collect the die-casting mold temperature monitoring timing information through the mold temperature detection component when the die-casting mold is started and the temperature acquisition cycle is met;

[0089] A temperature anomaly coefficient acquisition module 13, wherein the temperature anomaly coefficient acquisition module 13 is used to perform an anomaly analysis on the die-casting mold temperature monitoring time series information based on the die-casting mold baseline temperature time series information to obtain the die-casting mold temperature anomaly coefficient;

[0090] A medium property optimization module 14, wherein the medium property optimization module 14 is used to optimize the medium temperature property and the medium flow property when the temperature anomaly coefficient of the die-casting mold is greater than or equal to the temperature anomaly coefficient threshold, and generate a first medium optimized temperature and a first medium optimized flow;

[0091] The component control module 15 is used to control the medium temperature control component according to the first medium optimized temperature, and to control the medium flow control component according to the first medium optimized flow.

[0092] Furthermore, the temperature monitoring timing information acquisition module 12 is also used to perform the following steps:

[0093] Through the mold temperature detection component, a plurality of temperature detection values ​​at the first moment, a plurality of temperature detection values ​​at the second moment, and a plurality of temperature detection values ​​at the Nth moment of a plurality of temperature detection terminals within the temperature acquisition cycle are obtained, and the temperature acquisition cycle is reset at the same time;

[0094] The plurality of temperature detection values ​​at the first moment, the plurality of temperature detection values ​​at the second moment, and the plurality of temperature detection values ​​at the Nth moment are traversed to perform central trend fitting to generate the die-casting mold temperature monitoring timing information.

[0095] Furthermore, the temperature anomaly coefficient acquisition module 13 is also used to perform the following steps:

[0096] Obtaining a monitoring time zone of the die-casting mold temperature monitoring time series information, and extracting segment baseline temperature time series information from the die-casting mold baseline temperature time series information;

[0097] Configuring temperature deviation threshold timing information, wherein the temperature deviation threshold timing information corresponds one-to-one to the die-casting mold baseline temperature timing information;

[0098] The proportion of time zone steps in which the segment baseline temperature timing information and the die-casting mold baseline temperature timing information do not meet the temperature deviation threshold is counted and set as the die-casting mold temperature anomaly coefficient.

[0099] Furthermore, the temperature anomaly coefficient acquisition module 13 is also used to perform the following steps:

[0100] Extracting the die-casting mold baseline temperature in the first time zone according to the die-casting mold baseline temperature time series information;

[0101] Taking the die-casting die baseline temperature in the first time zone as a reference and taking 0.5° C. as a step length, configuring a first deviation die temperature gradient sequence that is less than the die-casting die baseline temperature in the first time zone;

[0102] Taking the die-casting die baseline temperature in the first time zone as a reference and taking 0.5° C. as a step length, configuring a second deviation die temperature gradient sequence that is greater than the die-casting die baseline temperature in the first time zone;

[0103] Traversing the first deviation mold temperature gradient sequence to sample the die-casting qualified rate of the die-casting mold model, and generating a first die-casting qualified rate set;

[0104] Traversing the second deviation mold temperature gradient sequence to sample the die-casting qualified rate of the die-casting mold model, and generating a second die-casting qualified rate set;

[0105] Based on the first die-casting qualified rate set and the second die-casting qualified rate set, the temperature deviation threshold of the die-casting mold in the first time zone is analyzed, and the temperature deviation threshold timing information is added.

[0106] Furthermore, the temperature anomaly coefficient acquisition module 13 is also used to perform the following steps:

[0107] When the first temperature die casting qualified rate of the first deviation mold temperature gradient sequence is greater than or equal to the die casting qualified rate threshold, the second temperature die casting qualified rate is less than the die casting qualified rate threshold, the second temperature is less than the first temperature, and the second temperature is a temperature adjacent to the first temperature;

[0108] constructing a first temperature deviation threshold value according to the first temperature and the die-casting mold baseline temperature in the first time zone;

[0109] When the third temperature die casting qualified rate of the second deviation mold temperature gradient sequence is greater than or equal to the die casting qualified rate threshold, the fourth temperature die casting qualified rate is less than the die casting qualified rate threshold, the fourth temperature is greater than the third temperature, and the fourth temperature is a temperature adjacent to the third temperature;

[0110] constructing a second temperature deviation threshold value according to the third temperature and the die-casting mold baseline temperature in the first time zone;

[0111] The smaller value between the first temperature deviation threshold and the second temperature deviation threshold is taken as the temperature deviation threshold of the die-casting mold in the first time zone.

[0112] Furthermore, the system also includes:

[0113] A medium real-time attribute acquisition module, wherein the medium real-time attribute acquisition module is used to interact with the medium temperature control component to obtain the medium real-time temperature and the medium flow control component to obtain the medium real-time flow when the temperature anomaly coefficient of the die-casting mold is less than the temperature anomaly coefficient threshold;

[0114] A temperature prediction module, the temperature prediction module is used to perform temperature prediction based on the die-casting mold temperature monitoring time series information according to the real-time temperature of the medium and the real-time flow rate of the medium, and generate die-casting mold temperature prediction time series information for a preset future time zone;

[0115] A predicted temperature anomaly analysis module, the predicted temperature anomaly analysis module is used to perform an anomaly analysis on the predicted temperature time series information of the die-casting mold based on the baseline temperature time series information of the die-casting mold, and obtain a predicted temperature anomaly coefficient of the die-casting mold;

[0116] A medium property optimization module, wherein the medium property optimization module is used to optimize the medium temperature property and the medium flow property when the predicted temperature anomaly coefficient of the die-casting mold is greater than or equal to the temperature anomaly coefficient threshold, and generate a second medium optimized temperature and a second medium optimized flow;

[0117] A control component configuration module, the control component configuration module is used to configure the medium temperature control component in a preset future time zone according to the second medium optimized temperature, and configure the medium flow control component according to the second medium optimized flow.

[0118] Furthermore, the temperature prediction module is also used to perform the following steps:

[0119] Collecting die-casting mold temperature test data, wherein the die-casting mold temperature test data includes a medium real-time temperature record data set, a medium real-time flow record data set, and a die-casting mold temperature timing information record data set;

[0120] Cutting the die-casting mold temperature timing information record data set to generate a die-casting mold temperature timing information input record data set and a die-casting mold temperature timing information output record data set;

[0121] According to the medium real-time temperature record data set, the medium real-time flow record data set and the die-casting mold temperature time series information input record data set as input, and through the die-casting mold temperature time series information output record data set as supervision, a long short-term memory neural network is configured to generate a temperature prediction model;

[0122] According to the temperature prediction model, according to the real-time temperature of the medium and the real-time flow rate of the medium, temperature prediction is performed based on the die-casting mold temperature monitoring timing information to generate the die-casting mold temperature prediction timing information of the preset future time zone.

[0123] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0124] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

[0125] This specification and the drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A method for intelligent temperature balance control of a die casting mold, characterized in that: Applied to a server, the server is deployed on an interactive water temperature machine, the interactive water temperature machine includes a medium temperature control component, a medium flow control component and a mold temperature detection component, the mold temperature detection component includes a plurality of temperature detection terminals, the plurality of temperature detection terminals are installed at preset positions of the die-casting mold, including: Receive die-casting mold baseline temperature timing information; When the die-casting mold is started and the temperature collection cycle is met, the die-casting mold temperature monitoring timing information is collected through the mold temperature detection component; Based on the die-casting mold baseline temperature time series information, performing an abnormal analysis on the die-casting mold temperature monitoring time series information to obtain a die-casting mold temperature abnormality coefficient; When the temperature anomaly coefficient of the die-casting mold is greater than or equal to the temperature anomaly coefficient threshold, optimizing the medium temperature attribute and the medium flow attribute to generate a first medium optimized temperature and a first medium optimized flow; The medium temperature control component is controlled according to the first medium optimized temperature, and the medium flow control component is controlled according to the first medium optimized flow.

2. The method according to claim 1, characterized in that Also includes: When the temperature anomaly coefficient of the die-casting mold is less than the temperature anomaly coefficient threshold, the medium temperature control component is interacted to obtain the real-time temperature of the medium, and the medium flow control component is interacted to obtain the real-time flow of the medium; According to the real-time temperature of the medium and the real-time flow rate of the medium, temperature prediction is performed based on the die-casting mold temperature monitoring time series information to generate die-casting mold temperature prediction time series information for a preset future time zone; Based on the die-casting die baseline temperature time series information, performing an abnormality analysis on the die-casting die temperature prediction time series information to obtain a die-casting die prediction temperature abnormality coefficient; When the predicted temperature anomaly coefficient of the die-casting mold is greater than or equal to the temperature anomaly coefficient threshold, optimizing the medium temperature attribute and the medium flow attribute to generate a second medium optimized temperature and a second medium optimized flow; The medium temperature control component is configured in a preset future time zone according to the second medium optimized temperature, and the medium flow control component is configured according to the second medium optimized flow.

3. The method according to claim 1, characterized in that When the die-casting mold is started and meets the temperature collection cycle, the die-casting mold temperature monitoring timing information is collected through the mold temperature detection component, including: Through the mold temperature detection component, a plurality of temperature detection values ​​at the first moment, a plurality of temperature detection values ​​at the second moment, and a plurality of temperature detection values ​​at the Nth moment of a plurality of temperature detection terminals within the temperature acquisition cycle are obtained, and the temperature acquisition cycle is reset at the same time; The plurality of temperature detection values ​​at the first moment, the plurality of temperature detection values ​​at the second moment, and the plurality of temperature detection values ​​at the Nth moment are traversed to perform central trend fitting to generate the die-casting mold temperature monitoring timing information.

4. The method according to claim 1, characterized in that Based on the die-casting mold baseline temperature time series information, the die-casting mold temperature monitoring time series information is analyzed abnormally to obtain the die-casting mold temperature abnormality coefficient, including: Obtaining a monitoring time zone of the die-casting mold temperature monitoring time series information, and extracting segment baseline temperature time series information from the die-casting mold baseline temperature time series information; Configuring temperature deviation threshold timing information, wherein the temperature deviation threshold timing information corresponds one-to-one to the die-casting mold baseline temperature timing information; The proportion of time zone steps in which the segment baseline temperature timing information and the die-casting mold baseline temperature timing information do not meet the temperature deviation threshold is counted and set as the die-casting mold temperature anomaly coefficient.

5. The method according to claim 4, characterized in that Configure the temperature deviation threshold timing information, including: Extracting the die-casting mold baseline temperature in the first time zone according to the die-casting mold baseline temperature time series information; Taking the die-casting die baseline temperature in the first time zone as a reference and taking 0.5° C. as a step length, configuring a first deviation die temperature gradient sequence that is less than the die-casting die baseline temperature in the first time zone; Taking the die-casting die baseline temperature in the first time zone as a reference and taking 0.5° C. as a step length, configuring a second deviation die temperature gradient sequence that is greater than the die-casting die baseline temperature in the first time zone; Traversing the first deviation mold temperature gradient sequence to sample the die-casting qualified rate of the die-casting mold model, and generating a first die-casting qualified rate set; Traversing the second deviation mold temperature gradient sequence to sample the die-casting qualified rate of the die-casting mold model, and generating a second die-casting qualified rate set; Based on the first die-casting qualified rate set and the second die-casting qualified rate set, the temperature deviation threshold of the die-casting mold in the first time zone is analyzed, and the temperature deviation threshold timing information is added.

6. The method according to claim 5, characterized in that Analyzing the temperature deviation threshold of the die-casting mold in the first time zone based on the first die-casting qualified rate set and the second die-casting qualified rate set includes: When the first temperature die casting qualified rate of the first deviation mold temperature gradient sequence is greater than or equal to the die casting qualified rate threshold, the second temperature die casting qualified rate is less than the die casting qualified rate threshold, the second temperature is less than the first temperature, and the second temperature is a temperature adjacent to the first temperature; constructing a first temperature deviation threshold value according to the first temperature and the die-casting mold baseline temperature in the first time zone; When the third temperature die casting qualified rate of the second deviation mold temperature gradient sequence is greater than or equal to the die casting qualified rate threshold, the fourth temperature die casting qualified rate is less than the die casting qualified rate threshold, the fourth temperature is greater than the third temperature, and the fourth temperature is a temperature adjacent to the third temperature; constructing a second temperature deviation threshold value according to the third temperature and the die-casting mold baseline temperature in the first time zone; The smaller value between the first temperature deviation threshold and the second temperature deviation threshold is taken as the temperature deviation threshold of the die-casting mold in the first time zone.

7. The method according to claim 2, characterized in that According to the real-time temperature of the medium and the real-time flow rate of the medium, temperature prediction is performed based on the die-casting mold temperature monitoring time series information to generate die-casting mold temperature prediction time series information of a preset future time zone, including: Collecting die-casting mold temperature test data, wherein the die-casting mold temperature test data includes a medium real-time temperature record data set, a medium real-time flow record data set, and a die-casting mold temperature timing information record data set; Cutting the die-casting mold temperature timing information record data set to generate a die-casting mold temperature timing information input record data set and a die-casting mold temperature timing information output record data set; According to the medium real-time temperature record data set, the medium real-time flow record data set and the die-casting mold temperature time series information input record data set as input, and through the die-casting mold temperature time series information output record data set as supervision, a long short-term memory neural network is configured to generate a temperature prediction model; According to the temperature prediction model, according to the real-time temperature of the medium and the real-time flow rate of the medium, temperature prediction is performed based on the die-casting mold temperature monitoring timing information to generate the die-casting mold temperature prediction timing information of the preset future time zone.

8. An intelligent temperature balance control system for a die casting mold, characterized in that: The system comprises: A baseline temperature timing information acquisition module, wherein the baseline temperature timing information acquisition module is used to receive the baseline temperature timing information of the die-casting mold; A temperature monitoring timing information acquisition module, wherein the temperature monitoring timing information acquisition module is used to collect the die-casting mold temperature monitoring timing information through the mold temperature detection component when the die-casting mold is started and the temperature acquisition cycle is met; A temperature anomaly coefficient acquisition module, the temperature anomaly coefficient acquisition module is used to perform an anomaly analysis on the die-casting mold temperature monitoring time series information based on the die-casting mold baseline temperature time series information to obtain the die-casting mold temperature anomaly coefficient; A medium property optimization module, wherein the medium property optimization module is used to optimize the medium temperature property and the medium flow property when the temperature anomaly coefficient of the die-casting mold is greater than or equal to the temperature anomaly coefficient threshold, and generate a first medium optimized temperature and a first medium optimized flow; A component control module, wherein the component control module is used to control the medium temperature control component according to the first medium optimized temperature, and to control the medium flow control component according to the first medium optimized flow.

Images