MULTI-PROCESS PARAMETER OPTIMIZATION METHOD FOR LOW-PRESSURE CASTING OF ALUMINUM ALLOY WHEEL HUBS

Abstract

A multi-process parameter optimization method for low-pressure casting of aluminum alloy wheel hubs is disclosed, relating to the technical field of low-pressure casting of automobile wheel hubs. The method includes: building a three-dimensional model of an aluminum alloy wheel hub; setting initial production process parameters; numerically simulating a low-pressure casting process; analyzing temperature distribution in key points of a mold; adjusting the production process parameters based on temperature distribution; repeating the above steps to further optimize the production process parameters and obtain an optimal combination of process parameters; collecting and analyzing actual production data and building a model; and optimizing the process parameters by using a dynamic multi-objective particle swarm.

Claims

1. A multi-process parameter optimization method for low-pressure casting of aluminum alloy wheel hubs, comprising: step S1: building a three-dimensional model of an aluminum alloy wheel hub, wherein information contained in the three-dimensional model comprises a geometric shape and a size of the aluminum alloy wheel hub; step S2: setting initial production process parameters, wherein the initial production process parameters comprise a quantity of cooling channels, a type of a cooling medium, and a flow rate in the cooling channels; step S3: numerically simulating a low-pressure casting process, wherein the low-pressure casting process is numerically simulated by using computer-aided software and inputting attributes of an aluminum alloy material, a casting temperature, and a pre-heating temperature of a mold; step S4: analyzing temperature distribution in key points of the mold, observing an isolated liquid phase region and temperature distribution in the aluminum alloy wheel hub based on simulated porosity defects and temperature distribution results, adjusting the initial production process parameters such as the casting temperature of the aluminum alloy wheel hub and the pre-heating temperature of the mold, and designating the process parameters for simulated aluminum alloy wheel hub castings with minimum defects for actual production; step S5: adjusting the production process parameters based on the temperature distribution; step S6: repeating steps S3 to S5 to further optimize the production process parameters and obtain an optimal combination of process parameters; step S7: collecting and analyzing actual production data and building a model; and step S8: optimizing the process parameters by using a dynamic multi-objective particle swarm.

2. The multi-process parameter optimization method for low-pressure casting of aluminum alloy wheel hubs according to claim 1, wherein in step S1, the three-dimensional model is built by means of SolidWorks or UG modeling software.

3. The multi-process parameter optimization method for low-pressure casting of aluminum alloy wheel hubs according to claim 1, wherein in step S2, structural features of the aluminum alloy wheel hub are determined by on-site production, and 17 cooling channels are set.

4. The multi-process parameter optimization method for low-pressure casting of aluminum alloy wheel hubs according to claim 1, wherein in step S2, the type of the cooling medium is at least one of water cooling or air cooling.

5. The multi-process parameter optimization method for low-pressure casting of aluminum alloy wheel hubs according to claim 1, wherein in step S2, the flow rate in the cooling channels is 8 to 10 L/min when a water cooling medium is used and 60 to 80 m.sup.3/h when an air cooling medium is used.

6. The multi-process parameter optimization method for low-pressure casting of aluminum alloy wheel hubs according to claim 1, wherein in step S5, if the regional temperature is too high, the quantity of cooling channels is increased or the flow rate in the cooling channels is increased; if the cooling effect is poor, the cooling medium is changed, such as from air cooling to water cooling; if the temperature distribution is non-uniform, the positions of the cooling channels are adjusted or the flow allocation in the cooling channels is adjusted.

7. The multi-process parameter optimization method for low-pressure casting of aluminum alloy wheel hubs according to claim 1, wherein in step S6, the optimal combination of process parameters has the characteristics of uniform temperature distribution in each key point of the mold, moderate temperature gradient, and high cooling efficiency.

8. The multi-process parameter optimization method for low-pressure casting of aluminum alloy wheel hubs according to claim 1, wherein in step S7, low-pressure casting is carried out by using initially set production process parameters, wherein thermocouples are arranged at the key points of the mold to collect process parameters of equipment and temperatures of the key points of the mold during the production process; a relationship among the opening and closing time of the mold cooling channels, the flow rate in the cooling channels, and the temperatures of the key points of the mold is built by using the collected process parameters; and an LSTM time series prediction model is built based on time series characteristics of the collected parameters.

9. The multi-process parameter optimization method for low-pressure casting of aluminum alloy wheel hubs according to claim 1, wherein in step S8, after the LSTM time series prediction model is built, the temperature of each key point of the mold for the qualified casting as a standard temperature of the key point of the mold, and the process parameters such as the initial cooling channels as initial particles, are input into the built LSTM model to obtain a predicted temperature of each key point of the mold, an absolute value of the difference between the predicted temperature of each key point and the standard temperature is designated as an objective function of the dynamic multi-objective particle swarm to seek each process parameter of the cooling channels, so as to obtain a plurality of optimized process parameters of the low-pressure casting of the aluminum alloy wheel hub.

Description

BRIEF DESCRIPTION OF THE DRAWINGS

[0023] FIG. 1 illustrates a flowchart of a multi-process parameter optimization method for low-pressure casting of aluminum alloy wheel hubs in the present invention;

[0024] FIG. 2 illustrates a schematic diagram of the multi-process parameter optimization method for low-pressure casting of aluminum alloy wheel hubs in the present invention;

[0025] FIG. 3 illustrates a three-dimensional model of an aluminum alloy wheel hub in the present invention;

[0026] FIG. 4 illustrates a test diagram of determining initial production process parameters based on orthogonal simulation results;

[0027] FIG. 5 illustrates a block diagram of building an LSTM time series prediction model; and

[0028] FIG. 6 illustrates a flowchart of building of the LSTM time series prediction model and a process parameter recommendation algorithm.

DETAILED DESCRIPTION

[0029] The following clearly and completely describes the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some of the embodiments of the present invention, not all of them. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without any creative efforts fall within the scope of protection of the present invention.

[0030] Refer to FIG. 1 and FIG. 2. FIG. 1 illustrates a flowchart of a multi-process parameter optimization method for low-pressure casting of aluminum alloy wheel hubs in the present invention. FIG. 2 illustrates a schematic diagram of the multi-process parameter optimization method for low-pressure casting of aluminum alloy wheel hubs in the present invention. The multi-process parameter optimization method for low-pressure casting of aluminum alloy wheel hubs includes:

[0031] Step S1: Build a three-dimensional model of an aluminum alloy wheel hub;

[0032] Refer to FIG. 3. FIG. 3 illustrates a three-dimensional model of an aluminum alloy wheel hub in the present invention. The three-dimensional model may be built by means of SolidWorks or UG modeling software. Information contained in the three-dimensional model includes, but is not limited to, a geometric shape and a size of the aluminum alloy wheel hub.

[0033] Step S2: Set initial production process parameters;

[0034] The initial production process parameters include a quantity of cooling channels, a type of a cooling medium, and a flow rate in the cooling channels. More specifically, structural features of the aluminum alloy wheel hub are determined by on-site production, and 17 cooling channels are set. The type of the cooling medium is at least one of water cooling or air cooling. The flow rate in the cooling channels is 8 to 10 L/min when a water cooling medium is used and 60 to 80 m3/h when an air cooling medium is used.

[0035] Step S3: Numerically simulate a low-pressure casting process;

[0036] Non-restrictively, the low-pressure casting process is numerically simulated by using Huazhu computer-aided engineering (CAE) software and inputting attributes of an A356.2 aluminum alloy material, a casting temperature, and a pre-heating temperature of a mold.

[0037] Step S4: Analyze temperature distribution in key points of the mold;

[0038] Refer to FIG. 4. FIG. 4 illustrates a test diagram of determining initial production process parameters based on orthogonal simulation results. An isolated liquid phase region and temperature distribution in the aluminum alloy wheel hub are observed based on simulated porosity defects and temperature distribution results, the initial production process parameters such as the casting temperature of the aluminum alloy wheel hub and the pre-heating temperature of the mold are adjusted, and the process parameters for simulated aluminum alloy wheel hub castings with minimum defects are designated for actual production.

[0039] Step S5: Adjust the production process parameters based on the temperature distribution;

[0040] More specifically, if the regional temperature is too high, the quantity of cooling channels is increased or the flow rate in the cooling channels is increased; if the cooling effect is poor, the cooling medium is changed, such as from air cooling to water cooling; if the temperature distribution is non-uniform, the positions of the cooling channels are adjusted or the flow allocation in the cooling channels is adjusted.

[0041] Step S6: Repeat steps S3 to S5 to further optimize the production process parameters and obtain an optimal combination of process parameters;

[0042] The optimal combination of process parameters has the characteristics of uniform temperature distribution in each key point of the mold, moderate temperature gradient, and high cooling efficiency. Non-restrictively, based on this, it is determined that the mold-filling pressure in first stage is 0.02 MPa and lasts for 10 seconds; the mold-filling pressure in second stage is 0.035 MPa and lasts for 30 seconds; the mold-filling pressure in third stage is 0.095 MPa and lasts for 40 seconds; subsequently, the pressure is held at 0.095 MPa; the initial casting temperature is 695 C. to 705 C., and the setting time is 125 to 135 seconds.

[0043] Step S7: Collect and analyze actual production data and build a model;

[0044] Refer to FIG. 5. FIG. 5 illustrates a block diagram of building an LSTM time series prediction model. Low-pressure casting is carried out by using initially set production process parameters, where thermocouples are arranged at the key points of the mold to collect process parameters of equipment and temperatures of the key points of the mold during the production process; a relationship among the opening and closing time of the mold cooling channels, the flow rate in the cooling channels, and the temperatures of the key points of the mold is built by using the collected process parameters; and an LSTM time series prediction model is built based on time series characteristics of the collected parameters;

[0045] Step S8: Optimize the process parameters by using a dynamic multi-objective particle swarm.

[0046] Refer to FIG. 6. FIG. 6 illustrates a flowchart of building of the LSTM time series prediction model and a process parameter recommendation algorithm. After the LSTM time series prediction model is built, the temperature of each key point of the mold for the qualified casting as a standard temperature of the key point of the mold, and the process parameters such as the initial cooling channels as initial particles, are input into the built LSTM model to obtain a predicted temperature of each key point of the mold, an absolute value of the difference between the predicted temperature of each key point and the standard temperature is designated as an objective function of the dynamic multi-objective particle swarm to seek each process parameter of the cooling channels, so as to obtain a plurality of optimized process parameters of the low-pressure casting of the aluminum alloy wheel hub.

[0047] A person skilled in the art can easily know that the multi-process parameter optimization method for low-pressure casting of aluminum alloy wheel hubs in the present invention can achieve optimization and real-time recommendation of equipment control process parameters in the production process of low-pressure castings of aluminum alloy wheel hubs, prevent casting defects in castings being produced, improve the quality of castings, further achieve intelligent optimization and recommendation of process parameters of production equipment, effectively reduce costs of experimental trial production, shorten a production cycle, and improve production efficiency. Meanwhile, the multi-process parameter optimization method for low-pressure casting of aluminum alloy wheel hubs in the present invention is particularly suitable for the low-pressure casting production of aluminum alloy wheel hubs, and can also be promoted and applied to the production processes of other types of castings.