Intelligent casting method and system based on multi-dimensional parameter detection

Abstract

The present application relates to the technical field of metal casting, and particularly relates to an intelligent casting method and system based on multi-dimensional parameter detection, which comprises the following steps: monitoring the content of raw material elements at multiple points in a molten pool in real time, obtaining a composition uniformity index by calculating the ratio of the content standard deviation to an adaptively updated standard deviation threshold, and combining the raw material element deviation rate to determine whether to perform compensation; determining a flow stability index by monitoring the flow rate of a direct sprue, a cross sprue and an inner gate, and adjusting the pouring speed and pressure in coordination accordingly; and calculating a stress gradient based on the real-time collected multi-point surface stress values, and dynamically adjusting the cooling waterway to eliminate stress concentration. The present application realizes closed-loop intelligent control of multiple key parameters in the whole casting process, effectively improves the composition uniformity, flow stability and suppresses the cooling stress of the castings, thereby significantly improving the stability of the casting quality and the yield.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of metal casting, in particular to an intelligent casting method based on multi-dimensional parameter detection and a system thereof. BACKGROUND

[0002] As a basic and core process indispensable to the equipment manufacturing industry, metal casting is used in many key fields such as aerospace, automobile manufacturing, engineering machinery, and energy equipment. The maturity and execution precision of the process directly affect the development quality of the downstream industry. In this complex manufacturing process, the quality of the casting is not a single dimension indicator, but a comprehensive reflection of multiple core elements including chemical composition uniformity, mechanical property stability, dimensional accuracy compliance, internal defect control, and surface quality smoothness.

[0003] Chinese patent CN114888274A discloses an intelligent casting method based on mold casting, which includes the following steps: preparing casting raw materials, intelligent pouring casting process, casting part forming processing operation, blank surface processing operation, and mold transportation and protection. Although this patent can intelligently control, reduce casting intensity, improve casting efficiency, and ensure casting stability, it still has the following problems:

[0004] Melting stage: The uniformity of alloy composition and the accuracy of element content depend on manual sampling and offline analysis, with feedback lag, which cannot realize real-time closed-loop control of the melting process, and is prone to composition segregation or element over-standard.

[0005] Pouring stage: The flow field and pressure field parameters are controlled in isolation, lacking a comprehensive index to characterize the stability of filling, making it difficult to avoid defects such as air entrapment and slag inclusion.

[0006] Cooling stage: There is a lack of means to monitor the stress distribution of the casting, and the cooling strategy is fixed, which cannot realize dynamic adjustment based on real-time stress distribution, and is prone to quality problems such as thermal cracking and deformation.

[0007] Overall process: The process parameter thresholds in each stage are fixed, lacking self-adaptive ability to raw material fluctuations and equipment performance degradation, resulting in poor process stability and difficulty in continuously improving product qualification rate. SUMMARY

[0008] Therefore, the present application provides an intelligent casting method based on multi-dimensional parameter detection to overcome the problems of unstable casting performance caused by uneven composition in the melt pool, air entrapment or slag inclusion defects caused by unstable flow during pouring, and deformation or cracking of the casting caused by stress concentration during cooling.

[0009] To achieve the above-mentioned purpose, the present application provides an intelligent casting method based on multi-dimensional parameter detection, comprising the following steps:

[0010] Step S1, in the smelting stage, based on the real-time acquisition of the content of each raw material element at several points in the molten pool, the content standard deviation of the content of the raw material element is determined, and the standard deviation threshold corresponding to the content standard deviation is adaptively updated to determine the composition uniformity index of the raw material element, wherein,

[0011] The composition uniformity index of the raw material element is the ratio of the content standard deviation to the standard deviation threshold;

[0012] Step S2, based on the content of each raw material element, the raw material element deviation rate of each raw material element is determined, and according to the composition uniformity index and the raw material element deviation rate, the raw material element is determined to be compensated or directly enters the pouring stage;

[0013] Step S3, based on the Si content deviation rate in each raw material element deviation rate, the pouring speed is adjusted;

[0014] Step S4, in the pouring stage, the flow rate of the pouring process is detected at multiple points, and the flow stability index is determined based on the flow rate detected at the multiple points, wherein,

[0015] The multiple point detection positions include the sprue inlet, the cross gate turning point and the ingate outlet;

[0016] Step S5, based on the flow stability index, the pouring speed and the pouring pressure are adjusted coordinately;

[0017] Step S6, in the cooling stage, based on the real-time acquisition of the multi-point surface stress value, the plane grid stress distribution is obtained to determine the stress gradient;

[0018] Step S7, based on the stress gradient, the dynamic adjustment of the cooling waterway is determined until the casting is formed.

[0019] Further, in the step S1, the process of determining the content standard deviation of the content of the raw material element includes:

[0020] Step S111, continuously acquiring the content of the raw material element for multiple times to determine the mean value of the content of the raw material element;

[0021] Step S112, calculating the square of the content difference value of the content of each point and the mean value of the content of the raw material element;

[0022] Step S113, determining the mean value of the square as the content standard deviation.

[0023] Further, in the step S1, the step of adaptively updating the standard deviation threshold corresponding to the content standard deviation includes:

[0024] Step S121: The ratio of the content standard deviation to the historical average standard deviation is determined as the elemental fluctuation value of the raw material element;

[0025] Step S122: Determine the aging coefficient of the testing equipment based on the cumulative detection time of the raw material element content;

[0026] Step S123: The weighted sum of the element fluctuation value and the aging coefficient of the detection equipment is determined as the dynamic adjustment parameter of the standard deviation threshold.

[0027] Furthermore, in step S2, the process of determining whether to compensate for the addition of the raw material elements or to directly proceed to the casting stage includes:

[0028] Step S21: Compare and analyze the component uniformity index with the preset component uniformity index;

[0029] Step S22: Compare and analyze the deviation rate of the raw material elements with the preset deviation rate of the raw material elements;

[0030] Step S23: Based on the results that the component uniformity index is less than or equal to the preset component uniformity index and the raw material element deviation rate is less than or equal to the preset raw material element deviation rate, determine the process of directly entering the casting stage.

[0031] Step S24: Based on the result that the component uniformity index is greater than the preset component uniformity index, or the raw material element deviation rate is greater than the preset raw material element deviation rate, determine to compensate for the addition of the raw material element.

[0032] Further, in step S3, the process of adjusting the casting speed based on the Si content deviation rate among the deviation rates of each of the raw material elements includes:

[0033] Step S31: Calculate the average Si content in each of the raw material elements to determine the Si content rate;

[0034] Step S32: Compare and analyze the Si content deviation rate with the preset Si content deviation rate;

[0035] Step S33: Based on the result that the Si content deviation rate is greater than the preset Si content deviation rate, it is determined that the pouring speed should be adjusted.

[0036] Further, in step S4, the process of determining the flow stability index based on the flow velocity detected at multiple points includes:

[0037] Step S41: Obtain the flow rates at the inlet of the sprue, the turning point of the runner, and the outlet of the ingate, respectively.

[0038] Step S42, determining a flow rate average based on the flow rates;

[0039] Step S43, determining a maximum difference based on a difference between the flow rates and the flow rate average;

[0040] Step S44, determining a flow stability index as a ratio of the flow rate average and the maximum difference.

[0041] Further, in the step S5, the process of determining a coordinated adjustment of the pouring speed and the pouring pressure based on the flow stability index comprises:

[0042] Step S51, comparing and analyzing the flow stability index with a preset flow stability index;

[0043] Step S52, determining a coordinated adjustment of the pouring speed and the pouring pressure based on a result that the flow stability index is less than the preset flow stability index.

[0044] Further, in the step S6, the process of determining the stress gradient comprises:

[0045] Step S61, obtaining the multi-point surface stress values to calculate a stress difference value of adjacent points;

[0046] Step S62, determining the stress gradient based on a ratio of the stress difference value and a distance of the adjacent points.

[0047] Further, in the step S7, the process of determining a dynamic adjustment of the cooling water path based on the stress gradient comprises:

[0048] Step S71, determining the stress gradient as a stress concentration area;

[0049] Step S72, comparing and analyzing the stress gradient of the stress concentration area with a preset stress gradient;

[0050] Step S73, determining a dynamic adjustment of the cooling water path based on a result that the stress gradient of the stress concentration area is greater than the preset stress gradient.

[0051] In another aspect, the present application provides an intelligent casting system based on multi-dimensional parameter detection, comprising:

[0052] a data acquisition module comprising a LIBS spectrometer for monitoring the content of raw material elements in the molten pool in real time, an LDV flowmeter for monitoring the flow rate during pouring, a pressure sensor for monitoring the pressure during pouring, and a distributed optical fiber sensor for monitoring the stress distribution during casting.

[0053] a control module connected with the data acquisition module, configured to calculate a composition uniformity index and a raw material element deviation rate based on the raw material element content, to control raw material feeding compensation, to calculate a flow stability index based on the flow rate, to cooperatively adjust the pouring speed and the pouring pressure, and to calculate a stress gradient based on the stress distribution, to dynamically adjust the cooling water path parameters;

[0054] an actuator including an automatic feeding system, a servo valve and a cooling water path adjusting device, controlled by the control module to realize compensation and adjustment operations.

[0055] Compared with the prior art, the present application has the following beneficial effects:

[0056] By collecting the raw material element content of several points in the molten pool in real time during the smelting stage, calculating the standard deviation of the content, and introducing an adaptive updating mechanism based on historical data and equipment state to dynamically set the standard deviation threshold, the composition uniformity index is calculated, realizing the quantitative evaluation and real-time monitoring of the macroscopic and microscopic uniformity of the chemical composition in the molten pool, thereby ensuring the consistency of the mechanical properties of the castings from the source, and significantly reducing the performance fluctuations caused by composition segregation.

[0057] Further, by jointly comparing and analyzing the composition uniformity index and the raw material element deviation rate, and intelligently deciding whether to perform raw material feeding compensation based on the comparison result, the hysteresis of traditional offline sampling analysis is overcome, realizing online, real-time and precise closed-loop control of the smelting composition, thereby effectively improving the smelting quality stability and reducing the scrap rate.

[0058] Further, by specially extracting the Si content deviation rate and comparing it with the preset threshold, the pouring speed is adjusted accordingly, which can actively compensate for the change in metal fluidity caused by the change in the content of key elements, maintaining the ideal filling capacity, thereby avoiding defects such as insufficient pouring or cold separation caused by insufficient or excessive fluidity.

[0059] Further, by synchronously monitoring the flow rate at key points such as the sprue inlet, the runner transition and the ingate outlet during the pouring stage, and constructing a flow stability index based on the maximum difference between the flow rate at each point and the average flow rate, the quantitative evaluation of the flow field stability in the runner system is realized, thereby improving the accuracy of active intervention based on early identification of turbulent flow or dead zone risk.

[0060] Further, by cooperatively adjusting the pouring speed and the pouring pressure according to the flow stability index, the flow kinetic energy and state of the metal liquid can be dynamically optimized, guiding it to fill the cavity in a smooth laminar flow manner, thereby significantly reducing the occurrence rate of flow defects such as air entrapment and slag inclusion, and improving the internal quality of the castings.

[0061] Further, by collecting stress values of multiple points on the surface of the casting in real time during the cooling stage and constructing a planar grid stress distribution map, and then calculating the stress gradient between adjacent points, the precise positioning and quantitative perception of the stress concentration area during the cooling process of the casting are realized, and the purpose of real-time regulation and control is achieved.

[0062] Further, by comparing the stress gradient with the preset threshold value and dynamically adjusting the cooling water path accordingly, differentiated and refined thermal management of different cooling areas of the casting can be achieved, and the cooling rate can be uniformized, thereby actively reducing internal thermal stress and fundamentally preventing deformation and cracking of the casting.

[0063] Further, by constructing a system technical principle integrated by a special sensor group (LIBS, LDV, etc.), a control module and an execution mechanism (automatic feeding, servo valve, etc.), the synchronous monitoring and intelligent closed-loop control of multi-dimensional parameters such as composition, flow and stress are realized, so that the whole casting process is upgraded from relying on artificial experience to data-driven transparent and intelligent production, and a complete solution for industry upgrading is provided. BRIEF DESCRIPTION OF DRAWINGS

[0064] Figure 1 The step flow chart of the intelligent casting method based on multi-dimensional parameter detection of the embodiment of the application is shown in the figure.

[0065] Figure 2 The step flow chart of determining the content standard deviation of the content of the raw material elements of the embodiment of the application is shown in the figure.

[0066] Figure 3 The step flow chart of adaptively updating the standard deviation threshold value corresponding to the content standard deviation of the embodiment of the application is shown in the figure.

[0067] Figure 4 The step flow chart of determining whether to compensate the raw material elements or directly enter the pouring stage of the embodiment of the application is shown in the figure.

[0068] Figure 5 The module connection relationship diagram of the intelligent casting system based on multi-dimensional parameter detection of the embodiment of the application is shown in the figure. DETAILED DESCRIPTION

[0069] In order to make the purpose and advantages of the application clearer and more apparent, the application will be further described below with reference to the embodiments. It should be understood that the specific embodiments described herein are only used to explain the application and do not limit the protection scope of the application.

[0070] The preferred embodiments of the application will be described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principles of the application and do not limit the protection scope of the application.

[0071] Please refer toFigure 1 As shown, Figure 1 This is a flowchart illustrating the steps of the intelligent casting method based on multi-dimensional parameter detection in an embodiment of the present invention.

[0072] This invention provides an intelligent casting method based on multi-dimensional parameter detection, specifically including the following steps:

[0073] Step S1: During the smelting stage, based on real-time acquisition of the content of each raw material element at several points within the molten pool, the standard deviation of the raw material element content is determined, and the standard deviation threshold corresponding to the content standard deviation is adaptively updated to determine the compositional uniformity index of the raw material elements.

[0074] The uniformity index of raw material elements is the ratio of the standard deviation of content to the standard deviation threshold;

[0075] Step S2: Based on the content of each raw material element, determine the raw material element deviation rate of each raw material element, and based on the component uniformity index and the raw material element deviation rate, determine whether to add compensation to the raw material element or directly enter the casting stage.

[0076] Step S3: Adjust the pouring speed based on the Si content deviation rate among the deviation rates of each raw material element;

[0077] Step S4: During the casting stage, the flow velocity during the casting process is monitored at multiple points. Based on the flow velocity data from these multiple points, the flow stability index is determined.

[0078] The locations for multi-point inspection include the inlet of the sprue, the turning point of the runner, and the outlet of the ingate.

[0079] Step S5: Based on the flow stability index, determine the coordinated adjustment of pouring speed and pouring pressure;

[0080] Step S6: During the cooling stage, a planar grid-like stress distribution is obtained based on the real-time collected multi-point surface stress values ​​to determine the stress gradient;

[0081] Step S7: Based on the stress gradient, dynamically adjust the cooling water path until the casting is completed.

[0082] Please see Figure 2 As shown, Figure 2 A flowchart illustrating the steps for determining the standard deviation of the elemental content of raw materials in an embodiment of the present invention.

[0083] Specifically, in step S1, the process of determining the standard deviation of the elemental content of the raw materials includes:

[0084] Step S111: Receive the element content of the raw materials multiple times consecutively to determine the average element content of the raw materials;

[0085] Step S112: Calculate the square of the difference between the content of raw material elements at each point and the average content of raw material elements;

[0086] Step S113: The mean of the squares is determined as the content standard deviation.

[0087] In step S111 of this embodiment of the invention, the element content of the raw material is obtained 5 times in a row. The number of points is 5, and the arrangement is 1 point at the center of the molten pool and 1 point at each of the four sides, with a spacing of 100mm.

[0088] Calculate the standard deviation of elemental content using the following formula. :

[0089]

[0090] Where n is the number of times the element content is obtained. Let be the element content value at the i-th detection point. This represents the average elemental content.

[0091] Please see Figure 3 As shown, Figure 3 This is a flowchart illustrating the steps of adaptively updating the standard deviation threshold corresponding to the content standard deviation in an embodiment of the present invention.

[0092] Specifically, in step S1, the step of adaptively updating the standard deviation threshold corresponding to the content standard deviation includes:

[0093] Step S121: The ratio of the content standard deviation to the historical average standard deviation is determined as the elemental fluctuation value of the raw material element;

[0094] Step S122: Determine the aging coefficient of the testing equipment based on the cumulative detection time of the raw material element content;

[0095] Step S123: The weighted sum of the element fluctuation value and the aging coefficient of the detection equipment is determined as the dynamic adjustment parameter of the standard deviation threshold.

[0096] In this embodiment of the invention, the elemental fluctuation value of the raw material elements is calculated using the following formula. :

[0097]

[0098] in, Based on historical qualified casting production data, this embodiment uses the arithmetic mean of the standard deviation of material element content calculated from the most recent 100 heats, and updates it every 50 heats to reflect process changes.

[0099] The aging coefficient of the testing equipment is calculated using the following formula. :

[0100]

[0101] in, The aging factor is set to 0.01 in this embodiment, which means that the deviation introduced by the equipment is expected to be 1% every year.

[0102] The dynamic adjustment parameter ΔT for the standard deviation threshold is calculated using the following formula:

[0103]

[0104] in, for The weighting coefficients, for The weighting coefficients are set in this embodiment. =0.3, =0.2;

[0105] The standard deviation threshold corresponding to the content standard deviation is adaptively updated using the following formula. :

[0106]

[0107] in, This is the current standard deviation threshold;

[0108] The component uniformity index U is calculated using the following formula:

[0109]

[0110] In this embodiment of the invention, the element deviation rate E is calculated using the following formula:

[0111]

[0112] in, It is the arithmetic mean of 5 samples. The standard values ​​required for casting grades, such as 3.2% C for HT300 cast iron.

[0113] Understandably, when calculating the dynamic adjustment parameter ΔT for the standard deviation threshold, the weighting coefficients α = 0.3 and β = 0.2. This weighting allocation indicates that the present invention pays more attention to the volatility of the raw materials themselves, and assigns a higher weight α in this embodiment. At the same time, the aging effect of the detection equipment is considered as a necessary correction term, and is assigned a lower weight β in this embodiment. This weighting combination, through regression analysis on a large amount of historical production data, using the least squares method for fitting in this embodiment, and verified through actual production, can achieve stable and excellent control effects under the normal operating conditions of the casting process.

[0114] The equipment aging factor K is set to 0.01, which means that the measurement deviation introduced by the spectral detection equipment due to device aging is expected to be about 1% per year during its effective detection life. This factor can be fine-tuned according to the calibration cycle and maintenance records provided by the equipment manufacturer.

[0115] Please see Figure 4 As shown, Figure 4 This is a flowchart illustrating the steps for determining whether to compensate for the addition of raw material elements or directly proceed to the casting stage in an embodiment of the present invention.

[0116] Specifically, in step S2, the process of determining whether to compensate for the addition of raw material elements or to directly proceed to the casting stage includes:

[0117] Step S21: Compare and analyze the component uniformity index with the preset component uniformity index;

[0118] Step S22: Compare and analyze the raw material element deviation rate with the preset raw material element deviation rate;

[0119] Step S23: Based on the results that the component uniformity index is less than or equal to the preset component uniformity index and the raw material element deviation rate is less than or equal to the preset raw material element deviation rate, determine the process of directly entering the casting stage.

[0120] Step S24: Based on the result that the component uniformity index is greater than the preset component uniformity index, or the raw material element deviation rate is greater than the preset raw material element deviation rate, determine to compensate for the addition of raw material elements.

[0121] In this embodiment of the invention, the preset raw material element deviation rate is |0.1%|, and the compensation amount △M for the addition of raw material elements is calculated using the following formula:

[0122]

[0123] in, For the quality of the molten pool, To adjust the elemental purity of the raw materials, To adjust the mass fraction of the target element in the raw materials.

[0124] It is understandable that the preset composition uniformity index is set to 0.8 based on statistical analysis of a large amount of historical qualified casting production data. Those skilled in the art can adjust it around the above typical value according to the casting material and precision requirements (such as higher-strength castings requiring a more stringent threshold). When the composition uniformity index U≤0.8, the performance uniformity qualification rate of each part of the casting exceeds 99%.

[0125] The preset raw material element deviation rate is set to |0.1%|, which meets the strict requirements of the national standard GB / T 9439 "Gray Cast Iron Parts" for the allowable deviation of the content of major elements;

[0126] Those skilled in the art can make adjustments around the above typical values ​​according to the specific casting material and precision requirements.

[0127] The preset flow stability index is set to 5. This threshold was determined through a combination of water simulation experiments and CFD flow field analysis. When S≥5, the flow field within the gating system is stable with a low risk of air entrapment; when S<5, significant turbulence or velocity dead zones appear, requiring immediate adjustment.

[0128] Specifically, in step S3, the process of adjusting the pouring speed based on the Si content deviation rate among the deviation rates of each raw material element includes:

[0129] Step S31: Calculate the average Si content in each of the raw material elements to determine the Si content rate;

[0130] Step S32: Compare and analyze the Si content deviation rate with the preset Si content deviation rate;

[0131] Step S33: Based on the result that the Si content deviation rate is greater than the preset Si content deviation rate, the pouring speed is adjusted.

[0132] Specifically, in step S3, the pouring speed is adjusted based on the Si content deviation rate among the deviation rates of each of the raw material elements. It should be noted that in casting materials such as gray cast iron, Si is one of the key elements affecting the fluidity of molten metal; therefore, this invention uses Si as an example. However, this invention is not limited to this. For other casting materials (such as ductile iron, aluminum alloys, etc.), the deviation rates of other key elements (such as C, Mg, etc.) can be selected according to the material characteristics for similar adjustments to achieve compensatory control of the pouring speed.

[0133] In this embodiment of the invention, the preset Si content deviation rate is |0.005%|, and the adjusted pouring speed is calculated using the following formula. :

[0134]

[0135] Wherein, k is the linkage coefficient determined through process data optimization. In this embodiment, k is set to 0.5. This adjustment is intended to compensate for the change in the fluidity of the molten metal caused by the change in Si content.

[0136] Understandably, the preset Si content deviation rate of 0.005% is determined based on process experiments demonstrating the sensitivity of Si to the fluidity of molten iron. When the Si content deviation exceeds this range, it will significantly affect the casting and filling capacity, necessitating adjustments to the casting speed to compensate.

[0137] Specifically, in step S4, the process of determining the flow stability index based on the flow velocity detected at multiple points includes:

[0138] Step S41: Obtain the flow rates at the inlet of the sprue, the turning point of the runner, and the outlet of the ingate, respectively.

[0139] Step S42: Determine the average flow velocity based on each flow velocity;

[0140] Step S43: Determine the maximum difference based on the difference between each flow velocity and the average flow velocity;

[0141] Step S44: The ratio of the average flow velocity to the maximum difference is determined as the flow stability index.

[0142] In this embodiment of the invention, the flow stability index S is calculated using the following formula:

[0143]

[0144] in, The arithmetic mean of the flow velocities in the three channels (sprue, runner, and ingate) is given. The measured speeds for each channel.

[0145] Specifically, in step S5, the process of determining the coordinated adjustment of pouring speed and pouring pressure based on the flow stability index includes:

[0146] Step S51: Compare and analyze the flow stability index with the preset flow stability index.

[0147] Step S52: Based on the result that the flow stability index is less than the preset flow stability index, determine to coordinately adjust the pouring speed and pouring pressure.

[0148] In step S52 of this embodiment of the invention, based on the result that the flow stability index is less than the preset flow stability index, the pouring speed and pouring pressure are adjusted in a coordinated manner, specifically including:

[0149] The adjustment amount is calculated using the following formula:

[0150]

[0151] in, and These are the adjustment amounts for pouring speed and pouring pressure, respectively. and To adjust the coefficients, in this embodiment, they are taken as 0.1 and 0.05 respectively;

[0152] and The current reference pouring speed and reference pouring pressure are set.

[0153] The adjustment strategy is as follows:

[0154] When S decreases, the pouring speed is increased slightly at the same time. and pouring pressure This enhances the kinetic energy of the molten metal flow, suppresses turbulence, and restores the flow field to stability.

[0155] Specifically, in step S6, the process of determining the stress gradient includes:

[0156] Step S61: Obtain surface stress values ​​at multiple points to calculate the stress difference between adjacent points;

[0157] Step S62: Determine the stress gradient based on the ratio of the stress difference to the distance between adjacent points.

[0158] In this embodiment of the invention, the stress gradient is calculated using the following formula. :

[0159]

[0160] Specifically, in step S7, the process of dynamically adjusting the cooling water circuit based on the stress gradient includes:

[0161] Step S71: Determine the stress gradient as the stress concentration region;

[0162] Step S72: Compare and analyze the stress gradient in the stress concentration region with the preset stress gradient;

[0163] Step S73: Based on the result that the stress gradient in the stress concentration area is greater than the preset stress gradient, determine to dynamically adjust the cooling water circuit.

[0164] In step S73 of this embodiment of the invention, based on the result that the stress gradient in the stress concentration region is greater than the preset stress gradient, the cooling water circuit is dynamically adjusted. The specific strategy is as follows:

[0165] Identify the control zones of the cooling water circuit corresponding to the stress concentration areas.

[0166] Increase the flow rate of cooling water to this zone and / or decrease the temperature of the cooling water in this zone to enhance the cooling intensity of this area, reduce the difference in cooling rate with the surrounding areas, and thus reduce the stress gradient.

[0167] The cooling water circuit regulating device consists of multiple independently controlled solenoid valves and temperature regulating units, controlled by the control module, to achieve precise and dynamic management of the cooling intensity of each zone.

[0168] Please see Figure 5 As shown, Figure 5This is a module connection diagram of the intelligent casting system based on multi-dimensional parameter detection according to an embodiment of the present invention.

[0169] On the other hand, embodiments of the present invention provide an intelligent casting system based on multi-dimensional parameter detection, comprising:

[0170] The data acquisition module includes a LIBS spectrometer for real-time monitoring of the elemental content of raw materials in the molten pool, an LDV velocimeter for monitoring the flow rate during the casting process, a pressure sensor for monitoring the pressure during the casting process, and a distributed fiber optic sensor for monitoring the stress distribution during the casting cooling process.

[0171] The control module, which is connected to the data acquisition module, is used to calculate the component uniformity index and raw material element deviation rate based on the raw material element content to control the raw material feeding compensation; calculate the flow stability index based on the flow rate to coordinate the adjustment of the pouring speed and pouring pressure; and calculate the stress gradient based on the stress distribution to dynamically adjust the cooling water circuit parameters.

[0172] The actuators, including the automatic feeding system, servo valves, and cooling water circuit regulating devices, are controlled by the control module to achieve compensation and adjustment operations.

[0173] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

[0174] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A smart casting method based on multi-dimensional parameter detection, characterized in that, Includes the following steps: Step S1: During the smelting stage, based on real-time acquisition of the content of each raw material element at several points within the molten pool, the standard deviation of the raw material element content is determined, and the standard deviation threshold corresponding to the content standard deviation is adaptively updated to determine the compositional uniformity index of the raw material elements. The uniformity index of the raw material elements is the ratio of the content standard deviation to the standard deviation threshold. Step S2: Based on the content of each of the raw material elements, determine the raw material element deviation rate of each of the raw material elements, and determine whether to add compensation to the raw material elements or directly enter the casting stage according to the component uniformity index and the raw material element deviation rate. Step S3: Adjust the pouring speed based on the Si content deviation rate among the deviation rates of each of the raw material elements; Step S4: During the pouring stage, the flow rate during the pouring process is detected at multiple points, and the flow stability index is determined based on the flow rate detected at these multiple points. The locations of the multi-point detection include the inlet of the straight runner, the turning point of the horizontal runner, and the outlet of the ingate. Step S5: Based on the flow stability index, determine the coordinated adjustment of pouring speed and pouring pressure; Step S6: During the cooling stage, a planar grid-like stress distribution is obtained based on the real-time collected multi-point surface stress values ​​to determine the stress gradient; Step S7: Based on the stress gradient, dynamically adjust the cooling water path until the casting is completed; In step S1, the step of adaptively updating the standard deviation threshold corresponding to the content standard deviation includes: Step S121: The ratio of the content standard deviation to the historical average standard deviation is determined as the elemental fluctuation value of the raw material element; Step S122: Determine the aging coefficient of the testing equipment based on the cumulative detection time of the raw material element content; Step S123: The weighted sum of the element fluctuation value and the aging coefficient of the detection equipment is determined as the dynamic adjustment parameter of the standard deviation threshold. In step S2, the process of determining whether to compensate for the addition of the raw material elements or to directly proceed to the casting stage includes: Step S21: Compare and analyze the component uniformity index with the preset component uniformity index; Step S22: Compare and analyze the deviation rate of the raw material elements with the preset deviation rate of the raw material elements; Step S23: Based on the results that the component uniformity index is less than or equal to the preset component uniformity index and the raw material element deviation rate is less than or equal to the preset raw material element deviation rate, determine the process of directly entering the casting stage. Step S24: Based on the result that the component uniformity index is greater than the preset component uniformity index, or the raw material element deviation rate is greater than the preset raw material element deviation rate, determine to compensate for the addition of the raw material element. In step S4, the process of determining the flow stability index based on the flow velocity detected at multiple points includes: Step S41: Obtain the flow rates at the inlet of the sprue, the turning point of the runner, and the outlet of the ingate, respectively. Step S42: Determine the average flow velocity based on each of the stated flow velocities; Step S43: Determine the maximum difference based on the difference between each flow velocity and the average flow velocity; Step S44: The ratio of the average flow velocity to the maximum difference is determined as the flow stability index; In step S5, the process of determining the coordinated adjustment of pouring speed and pouring pressure based on the flow stability index includes: Step S51: Compare and analyze the flow stability index with the preset flow stability index; Step S52: Based on the result that the flow stability index is less than the preset flow stability index, determine to coordinately adjust the pouring speed and pouring pressure; In step S6, the process of determining the stress gradient includes: Step S61: Obtain the surface stress values ​​at multiple points to calculate the stress difference between adjacent points; Step S62: Determine the stress gradient based on the ratio of the stress difference to the distance between adjacent points; In step S7, the process of dynamically adjusting the cooling water circuit based on the stress gradient includes: Step S71: Determine the stress gradient as a stress concentration region; Step S72: Compare and analyze the stress gradient of the stress concentration region with the preset stress gradient; Step S73: Based on the result that the stress gradient in the stress concentration area is greater than the preset stress gradient, determine to dynamically adjust the cooling water circuit.

2. The intelligent casting method based on multi-dimensional parameter detection according to claim 1, characterized in that, In step S1, the process of determining the standard deviation of the elemental content of the raw material includes: Step S111: The element content of the raw material is obtained multiple times consecutively to determine the average element content of the raw material; Step S112: Calculate the square of the difference between the content of the raw material element at each point and the average content of the raw material element. Step S113: The mean of the squares is determined as the standard deviation of the content.

3. The intelligent casting method based on multi-dimensional parameter detection according to claim 2, characterized in that, In step S3, the process of adjusting the casting speed based on the Si content deviation rate among the deviation rates of each of the raw material elements includes: Step S31: Calculate the average Si content in each of the raw material elements to determine the Si content rate; Step S32: Compare and analyze the Si content deviation rate with the preset Si content deviation rate; Step S33: Based on the result that the Si content deviation rate is greater than the preset Si content deviation rate, it is determined that the pouring speed should be adjusted.

4. A system implemented using the intelligent casting method based on multi-dimensional parameter detection as described in any one of claims 1-3, characterized in that, include: The data acquisition module includes a LIBS spectrometer for real-time monitoring of the elemental content of raw materials in the molten pool, an LDV velocimeter for monitoring the flow rate during the casting process, a pressure sensor for monitoring the pressure during the casting process, and a distributed fiber optic sensor for monitoring the stress distribution during the casting cooling process. The control module, which is connected to the data acquisition module, is used to calculate the component uniformity index and raw material element deviation rate based on the raw material element content to control the raw material feeding compensation; calculate the flow stability index based on the flow rate to coordinate the adjustment of the pouring speed and pouring pressure; and calculate the stress gradient based on the stress distribution to dynamically adjust the cooling water circuit parameters. The actuator, which includes an automatic feeding system, a servo valve, and a cooling water circuit regulating device, is controlled by the control module to perform compensation and adjustment operations.

Images