Alloy die-casting forming method and system based on intelligent parameter optimization

Abstract

According to the alloy die-casting forming method and system based on intelligent parameter optimization, dynamic data streams in the die-casting process are collected in real time by introducing a sensor network, die-casting parameters are dynamically adjusted through a feedback control system, and the alloy die-casting forming method and system based on intelligent parameter optimization can automatically adapt to different alloy components and die design conditions; and it is ensured that each time of die-casting operation can be conducted under the optimal condition. According to the method, the consistency and the stability of the product quality are improved, and the production efficiency is remarkably improved. And through accurate control over the die-casting process, the quality problem caused by improper parameter setting is reduced, and high quality of each batch of products is guaranteed. The dynamic data flow is analyzed in real time, the factor fluctuation mode influencing the product quality is recognized, the die-casting parameters are adjusted in time, the stable product performance is maintained, the limitation caused by constant parameters in the prior art is overcome, and remarkable technical progress is brought to the manufacturing industry.

Description

Technical Field

[0001] The present invention belongs to the technical field of alloy die-casting, and in particular relates to an alloy die-casting forming method and system based on intelligent parameter optimization. Background Art

[0002] In the traditional alloy die-casting process, manufacturers usually rely on preset fixed parameters to control the die-casting process, including temperature, pressure, and speed. However, due to changes in alloy composition and mold design, as well as unforeseen factors in the production process (such as ambient temperature fluctuations and equipment aging), this static method is difficult to ensure the consistency and stability of product quality. In addition, traditional methods often lack the ability to effectively monitor and adjust the dynamic changes in the die-casting process in real time, resulting in low production efficiency.

[0003] A major problem in the prior art is that it is impossible to automatically adjust the die-casting parameters according to the specific conditions of the alloy composition and mold design, which makes the product quality subject to the initial settings and prone to defects such as pores, cracks and dimensional inconsistencies. Especially when faced with differences in the properties of different batches of alloy materials, fixed die-casting parameters may no longer be applicable, thus affecting the final quality of the product. Summary of the invention

[0004] The purpose of the present invention is to provide an alloy die-casting forming method and system based on intelligent parameter optimization, which not only improves the consistency and stability of product quality, but also significantly improves production efficiency, so as to solve the problems in the prior art raised in the above background technology.

[0005] To achieve the above object, the present invention provides an alloy die-casting method based on intelligent parameter optimization, comprising the following steps:

[0006] Step 1: Determine the type of alloy to be processed and the structural characteristics of the mold, and set the initial die-casting conditions according to the alloy characteristics. Under the set initial die-casting conditions, use the sensor network to collect dynamic data streams during the die-casting process, and the dynamic data streams include temperature, pressure and speed change information;

[0007] Step 2: Analyze the acquired dynamic data stream in real time to identify the fluctuation pattern of factors affecting product quality, and adjust the pressure level applied during the die-casting process through a feedback control system according to the identified fluctuation pattern of factors;

[0008] Step 3: Combined with the adjusted pressure level, the cooling rate is adjusted in time to adapt to the solidification characteristics of different alloys. At the same time, the injection volume is monitored and controlled to ensure that the material consumption is stable and consistent for each die casting operation;

[0009] Step 4: Based on the material usage, evaluate and correct the start timing of the subsequent die-casting cycle, optimize the production rhythm, summarize the results of the production rhythm, and continuously improve the die-casting process.

[0010] Preferably, the step of determining the type of alloy to be processed and the structural characteristics of the mold, and setting the initial die-casting conditions according to the alloy characteristics, includes:

[0011] The initial temperature T0 is determined according to the thermophysical properties of the alloy, where T0 is calculated by the formula T0 = (C*D+E) / F, where C represents the specific heat capacity of the alloy, D is the expected die-casting speed, E is the ambient temperature compensation value, and F is the heat dissipation coefficient;

[0012] Based on the calculated T0, the mold is preheated to the target temperature T1, which is calculated by the formula T1=T0+G, where G represents the additional temperature increment.

[0013] Based on the achieved mold temperature, the required pressure P0 is calculated using the formula P0 = H*I^J where H is the pressure base related to the alloy type, I is the temperature T1, and J is the exponential factor of the effect of temperature on pressure;

[0014] In combination with the calculated pressure P0, the injection port size S is adjusted according to the formula S=K*sqrt(L / P0), where K is a fixed proportionality coefficient and L is the expected fluid flow rate.

[0015] Preferably, under the set initial die-casting conditions, using a sensor network to collect dynamic data streams during the die-casting process includes:

[0016] Deploy multiple sensing units on the die-casting equipment to collect real-time temperature Ta data. The data recorded by each sensing unit is marked with a timestamp as Ta(n), where n represents the time series number.

[0017] Based on the collected temperature Ta(n) information, calculate the temperature change rate ΔTa using the formula ΔTa=Ta(n)-Ta(n-1);

[0018] Based on the obtained temperature change rate, the change of pressure Pa is monitored and recorded synchronously, expressed as Pa(n), and then the ratio Ra reflecting the material flow resistance is calculated by the formula Ra=Pa(n) / (ΔTa+1);

[0019] Combined with the obtained ratio Ra, the change of the speed Va is analyzed, and the speed setting is adjusted using the formula Va(n)=Ra*Ma+Na, where Ma is the preset speed adjustment coefficient and Na is the basic speed value.

[0020] Preferably, the real-time analysis of the acquired dynamic data stream to identify the fluctuation pattern of factors affecting product quality includes:

[0021] Receive dynamic data streams and extract time series information of temperature Ta(n), pressure Pa(n) and velocity Va(n);

[0022] Based on the extracted data, the fluctuation characteristic vector Fa is constructed by the formula Fa = (Ta(n), Pa(n), Va(n));

[0023] Using the generated fluctuation characteristic vector Fa, calculate the difference Da between two adjacent die castings using the formula Da = sqrt((Fa(n)-Fa(n-1))^2);

[0024] Combined with the obtained difference Da, the main fluctuation mode Ma that affects product quality is determined, and the formula Ma=Da*Wa+Ba is used for pattern recognition, where Wa is the weight coefficient and Ba is the bias value.

[0025] Preferably, the step of adjusting the pressure level applied during the die casting process by a feedback control system according to the identified fluctuation pattern of the factors comprises:

[0026] According to the identified main fluctuation mode Ma, determine the pressure correction coefficient Kp that needs to be adjusted, using the formula Kp = 1 / (1+|Ma|);

[0027] Based on the calculated pressure correction coefficient Kp, the target pressure Pt in the die casting process is updated by the formula Pt = Pi*Kp, where Pi is the initially set pressure value;

[0028] Based on the set new target pressure Pt, the feedback control system is started to perform real-time monitoring and collect data points of the actual applied pressure Pa;

[0029] Combined with the actual pressure Pa obtained, the pressure error Ep is calculated using the formula Ep=Pt-Pa, and then the final applied pressure is adjusted using the formula Padj=Pa+α*Ep, where α is a pre-calibrated proportional factor.

[0030] Preferably, the cooling rate is adjusted in time to adapt to the solidification characteristics of different alloys in combination with the adjusted pressure level, including:

[0031] Based on the adjusted final applied pressure Padj, determine the alloy solidification characteristic parameter Cadj, using the formula Cadj = Padj * β, β is a proportional factor related to the alloy type;

[0032] According to the obtained solidification characteristic parameter Cadj, the initial cooling rate Rc is set and calculated by the formula Rc = Cadj / Tm, where Tm represents the melting point temperature of the alloy;

[0033] Based on the set initial cooling rate Rc, the temperature change ΔTc in the mold is monitored in real time, and the cooling rate increment ΔRc is updated using the formula ΔRc=γ*ΔTc, where γ is the proportional coefficient of the effect of temperature change on cooling rate;

[0034] Combined with the calculated cooling rate increment ΔRc, the final cooling rate Rcf is adjusted using the formula Rcf=Rc+ΔRc. At the same time, the product size deviation δc is monitored and the formula δc=|Sc_measured-Sc_target| is used to ensure that the size meets the design requirements, where Sc_measured is the actual measured product size and Sc_target is the target size.

[0035] Preferably, the monitoring and regulating of the injection volume to ensure a stable and consistent amount of material for each die-casting operation includes:

[0036] According to the set final cooling rate Rcf, determine the initial injection volume Q0, using the formula Q0 = Vm*(1+ε), Vm is the volume of the mold cavity, and ε is the additional percentage reserved to account for material shrinkage and underfilling;

[0037] Based on the obtained initial injection volume Q0, at the beginning of each die casting operation, the actual injection volume Qa is recorded by the flow sensor;

[0038] Combined with Qa, calculate the injection amount deviation ΔQa, using the formula ΔQa = Q0-Qa, and then adjust the preset injection amount Qn for the next die casting according to this deviation, using the formula Qn = Q0 + ζ * ΔQa, ζ is a proportional factor used to balance the injection amount fluctuation;

[0039] On the basis of the adjusted Qn, the amount of remaining material Rm after each die-casting process is monitored and calculated through the formula Rm=Qn-Qu, where Qu represents the actual amount of material used. Subsequently, the impact of the remaining material on the next die-casting is evaluated, and the final injection amount is fine-tuned using the formula Qadj=Qn-ω*Rm, where ω is a coefficient reflecting the degree of impact of the remaining material.

[0040] Preferably, the method of evaluating and correcting the start timing of subsequent die-casting cycles according to the material usage to optimize the production rhythm includes:

[0041] Based on the final adjusted injection volume Qadj, the completion time Tend of each die-casting operation is recorded, and the average operation cycle Cavg is calculated using the formula Cavg = Σ(Tend) / N, where N is the number of die-casting times during the observation period;

[0042] Combined with the obtained average operation cycle Cavg, the ideal production rhythm Pid is set, through the formula Pid = Cavg*(1-η), η represents the time buffer ratio reserved to adapt to equipment preparation and maintenance;

[0043] According to the determined ideal production rhythm Pi d, the difference ΔPd between the current actual production rhythm Pact and the ideal value is analyzed, using the formula ΔPd = Pi d-Pact, and then the influence factor Id of this difference on the timing of the start of the subsequent die-casting cycle is evaluated, using the formula I d = ΔPd / Pi d;

[0044] Combined with the influencing factor I d, the start time Tstart of the subsequent die-casting cycle is adjusted using the formula Tstart = Tprev + Pid + ψ*Id, where Tprev is the start time of the previous die-casting operation and ψ is a proportional coefficient used to adjust the response speed of the production rhythm.

[0045] Preferably, the results of summarizing the production rhythm and continuously improving the die casting process include:

[0046] According to the adjusted start time Tstart, record the complete cycle data of each die-casting operation, including but not limited to the material consumption Qadj, cooling rate Rcf and actual production rhythm Pact, to form a comprehensive performance index Sp, using the formula Sp = (Qadj + Rcf + Pact) / 3;

[0047] Based on the calculated comprehensive performance index Sp, a historical performance database Dp is constructed, the data of each die-casting is stored in chronological order, and a continuous data set is formed through the formula Dp = {Sp(1), Sp(2), ..., Sp(n)}, where n represents the cumulative number of die-casting times;

[0048] Utilize the established historical performance database Dp to analyze the long-term trend and determine the performance improvement factor F imp, using the formula F imp = (Sp_max-Sp_min) / Sp_avg, where Sp_max is the highest performance indicator, Sp_min is the minimum performance indicator, and Sp_avg is the average performance indicator;

[0049] Combined with the obtained performance improvement factor F imp, an optimization strategy is formulated and a new target performance indicator Starget is set using the formula Starget = Sp_avg*(1+λ*F imp), where λ is a coefficient used to balance the improvement speed and stability. Subsequently, the die-casting parameters are adjusted according to the new target to ensure simultaneous improvement of product quality consistency and maximum production efficiency.

[0050] Another aspect of the present invention provides an alloy die-casting system based on intelligent parameter optimization, comprising:

[0051] Alloy and mold characteristic setting and initial condition configuration module, used to determine the type of alloy to be processed and the structural characteristics of the mold, and set the initial die-casting conditions according to the alloy characteristics. Under the set initial die-casting conditions, the sensor network is used to collect dynamic data streams during the die-casting process, and the dynamic data streams include temperature, pressure and speed change information;

[0052] A data analysis and pressure adjustment module, used to analyze the acquired dynamic data stream in real time, identify the fluctuation pattern of factors affecting product quality, and adjust the pressure level applied during the die-casting process through a feedback control system according to the identified fluctuation pattern of factors;

[0053] The cooling rate adjustment and material dosage control module is used to adjust the cooling rate in time to adapt to the solidification characteristics of different alloys in combination with the adjusted pressure level. At the same time, it monitors and controls the injection volume to ensure that the material dosage of each die-casting operation is stable and consistent;

[0054] The production rhythm optimization and process improvement module is used to evaluate and correct the start timing of subsequent die-casting cycles according to material usage, optimize the production rhythm, summarize the results of the production rhythm, and continuously improve the die-casting process.

[0055] Technical effects and advantages of the present invention: Compared with the prior art, the alloy die-casting forming method and system based on intelligent parameter optimization proposed by the present invention has the following advantages:

[0056] The present invention introduces a sensor network to collect the dynamic data stream in the die-casting process in real time, and uses a feedback control system to dynamically adjust the die-casting parameters. The present invention can automatically adapt to different alloy compositions and mold design conditions to ensure that each die-casting operation can be performed under optimal conditions. This method not only improves the consistency and stability of product quality, but also significantly improves production efficiency. Through precise control of the die-casting process, quality problems caused by improper parameter settings are reduced, and the high quality of each batch of products is guaranteed. The dynamic data stream is analyzed in real time and the fluctuation pattern of factors affecting product quality is identified, and the die-casting parameters are adjusted in time to maintain stable product performance. The optimized die-casting process reduces the scrap rate, shortens the production cycle, and maximizes the use of the production rhythm, overcoming the limitations of fixed parameters in the prior art, and bringing significant technological progress to the manufacturing industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 It is a flow chart of the alloy die-casting method based on intelligent parameter optimization of the present invention;

[0058] Figure 2 It is a block diagram of the alloy die-casting molding system based on intelligent parameter optimization of the present invention. DETAILED DESCRIPTION

[0059] The following will be combined with the accompanying drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. The specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0060] The present invention provides Figure 1 An alloy die-casting method based on intelligent parameter optimization is shown, comprising the following steps:

[0061] Step 1: Determine the type of alloy to be processed and the structural characteristics of the mold, and set the initial die-casting conditions according to the alloy characteristics. Under the set initial die-casting conditions, use the sensor network to collect dynamic data streams during the die-casting process, and the dynamic data streams contain information on changes in temperature, pressure and speed; specifically include:

[0062] The initial temperature T0 is determined according to the thermophysical properties of the alloy, where T0 is calculated by the formula T0=(C*D+E) / F, C represents the specific heat capacity of the alloy, D is the expected die-casting speed, E is the ambient temperature compensation value, and F is the heat dissipation coefficient; ensuring that the initial temperature setting is scientific and reasonable, fully considering the characteristics of the alloy material and the influence of the external environment, and providing a reliable temperature basis for the subsequent die-casting process.

[0063] Based on the calculated T0, the mold is preheated to the target temperature T1. T1 is calculated by the formula T1=T0+G, where G represents the additional temperature increment. By appropriately increasing the mold temperature, the alloy liquid can quickly reach the ideal working temperature when entering the mold, reducing the cooling time and improving production efficiency and product quality.

[0064] Based on the achieved mold temperature, calculate the required pressure P0, using the formula P0 = H*I^J where H is the pressure base related to the alloy type, I is the temperature T1, and J is the exponential factor of the temperature effect on pressure; accurately control the applied pressure to ensure that the alloy liquid can fill the mold cavity under appropriate conditions to avoid product defects caused by insufficient or excessive pressure.

[0065] Combined with the calculated pressure P0, the injection port size S is adjusted according to the formula S = K*sqrt(L / P0), where K is a fixed proportional coefficient and L is the expected fluid flow rate. Optimizing the injection port size ensures that the alloy liquid enters the mold at an appropriate flow rate, which not only avoids turbulence and pores caused by too fast injection, but also prevents condensation problems caused by too slow injection speed.

[0066] Multiple sensing units are deployed on the die-casting equipment to collect real-time temperature Ta data. The data recorded by each sensing unit is marked with a timestamp as Ta(n), where n represents the time series number. This enables real-time monitoring of temperature changes during the die-casting process, provides accurate data support, and facilitates subsequent dynamic adjustment of parameters.

[0067] Based on the collected temperature Ta(n) information, the temperature change rate ΔTa is calculated using the formula ΔTa=Ta(n)-Ta(n-1); this accurately captures the temperature change trend over time, provides a basis for evaluating the heat conduction efficiency in the die-casting process, and helps to detect abnormal conditions in a timely manner.

[0068] Based on the obtained temperature change rate, the change of pressure Pa is synchronously monitored and recorded, expressed as Pa(n), and then the ratio Ra reflecting the material flow resistance is calculated through the formula Ra=Pa(n) / (ΔTa+1); the change of material flow resistance in the die-casting process is dynamically understood to ensure that the pressure adjustment can adapt to actual needs and maintain stable product quality.

[0069] Combined with the obtained ratio Ra, the change of speed Va is analyzed, and the speed setting is adjusted using the formula Va(n)=Ra*Ma+Na, where Ma is the preset speed adjustment coefficient and Na is the basic speed value. Through dynamic adjustment of speed, the fluidity in the die casting process is ensured to be optimal, internal defects of the product, such as bubbles and cracks, are reduced, and the quality of the final product is improved.

[0070] By setting and optimizing specific process parameters, we can ensure that every detail from alloy selection, mold preheating to the actual die casting process can be precisely controlled. This method not only improves the quality and consistency of the product, but also significantly improves production efficiency and reduces scrap rate.

[0071] Step 2: Analyze the acquired dynamic data stream in real time to identify the fluctuation pattern of factors affecting product quality, and adjust the pressure level applied during the die-casting process through a feedback control system according to the identified fluctuation pattern of factors; specifically including:

[0072] Receive dynamic data streams and extract time series information of temperature Ta(n), pressure Pa(n) and speed Va(n); ensure that the collected data is comprehensive and accurate, providing a reliable basis for subsequent analysis and adjustment. These data directly reflect the real-time changes in the die-casting process and help to detect potential problems in a timely manner.

[0073] Based on the extracted data, the fluctuation characteristic vector Fa is constructed, and the multi-dimensional data is integrated into a characteristic vector through the formula Fa=(Ta(n), Pa(n), Va(n)), which is convenient for subsequent analysis and processing. This representation method simplifies the data analysis process and improves the calculation efficiency.

[0074] The generated fluctuation feature vector Fa is used to calculate the difference Da between two adjacent die castings, using the formula Da = sqrt((Fa(n)-Fa(n-1))^2); the degree of change between each die casting is quantified, and significant fluctuation points are identified. This helps to understand the trend of parameter changes during the die casting process and warn of possible quality problems in advance.

[0075] Combined with the obtained difference Da, the main fluctuation mode Ma that affects product quality is determined, and the formula Ma=Da*Wa+Ba is used for pattern recognition, where Wa is the weight coefficient and Ba is the bias value. The mathematical model identifies the fluctuation mode that has a significant impact on product quality and provides a clear adjustment direction. This method can more accurately locate the root cause of the problem and improve the pertinence of problem solving.

[0076] According to the identified main fluctuation mode Ma, determine the pressure correction coefficient Kp that needs to be adjusted, using the formula Kp = 1 / (1+|Ma|); automatically adjust the pressure correction coefficient according to the fluctuation mode to ensure that the adjustment range matches the actual needs. This method avoids over- or under-adjustment and improves the accuracy of adjustment.

[0077] Based on the calculated pressure correction coefficient Kp, the target pressure Pt in the die-casting process is updated, and the formula Pt = Pi*Kp, where Pi is the initially set pressure value, is used to dynamically adjust the target pressure to ensure that each die-casting can be carried out under optimal conditions. This method improves the density uniformity and geometric accuracy of the product and reduces the scrap rate.

[0078] Based on the set new target pressure Pt, the feedback control system is started for real-time monitoring to collect data points of the actual applied pressure Pa; closed-loop control of the die-casting process is achieved to ensure that the actual pressure is always close to the target value. Real-time monitoring helps to respond quickly to abnormal situations and maintain stable product quality.

[0079] Combined with the actual pressure Pa obtained in the calculation, the pressure error Ep is calculated, using the formula Ep = Pt-Pa, and then the final applied pressure is adjusted using the formula Padj = Pa + α*Ep, where α is a pre-calibrated proportional factor. The pressure error is eliminated through the proportional control algorithm to ensure that the final applied pressure reaches the set target value. This method improves the response speed and stability of the system and further ensures the consistency of product quality.

[0080] By analyzing and controlling the dynamic data flow, the entire process from data acquisition, fluctuation pattern recognition to final pressure adjustment can be precisely controlled. This method not only improves the automation and intelligence level of the die-casting process, but also significantly improves the consistency and stability of product quality, and reduces production costs and scrap rates.

[0081] Step 3: Combined with the adjusted pressure level, the cooling rate is adjusted in time to adapt to the solidification characteristics of different alloys. At the same time, the injection volume is monitored and controlled to ensure that the material consumption is stable and consistent for each die casting operation; specifically, it includes:

[0082] Based on the adjusted final applied pressure Padj, the alloy solidification characteristic parameter Cadj is determined using the formula Cadj = Padj*β, where β is a proportional factor related to the alloy type; by considering the final applied pressure, the alloy solidification characteristic parameters under specific conditions are accurately calculated. This provides a scientific basis for the subsequent cooling rate setting and ensures that the cooling process matches the alloy characteristics.

[0083] According to the obtained solidification characteristic parameter Cadj, the initial cooling rate Rc is set and calculated by the formula Rc = Cadj / Tm, where Tm represents the melting point of the alloy; ensure that the cooling rate adapts to the specific solidification requirements of the alloy to avoid defects (such as cracks or pores) caused by too fast or too slow cooling. This customized cooling strategy improves the geometric accuracy and internal quality of the product.

[0084] Based on the set initial cooling rate Rc, the temperature change ΔTc in the mold is monitored in real time, and the cooling rate increment ΔRc is updated using the formula ΔRc=γ*ΔTc, where γ is the proportional coefficient of the temperature change on the cooling rate; the cooling rate is dynamically adjusted to cope with the impact of temperature fluctuations in the actual production process. This method ensures the stability of the cooling process and reduces product defects caused by temperature changes.

[0085] Combined with the calculated cooling rate increment ΔRc, the final cooling rate Rcf is adjusted using the formula Rcf=Rc+ΔRc. At the same time, the product dimensional deviation δc is monitored, and the formula δc=|Sc_measured-Sc_target| is used to ensure that the dimensions meet the design requirements. Sc_measured is the actual measured product dimension, and Sc_target is the target dimension. Ensure that the final cooling rate can adapt to changes in actual production conditions and maintain the geometric accuracy of the product. Through dimensional deviation monitoring, potential quality problems can be discovered and corrected in a timely manner, improving the consistency of product quality.

[0086] According to the set final cooling rate Rcf, determine the initial injection volume Q0, using the formula Q0 = Vm*(1+ε), Vm is the volume of the mold cavity, ε is the additional percentage reserved to take into account material shrinkage and insufficient filling; reasonably set the initial injection volume to ensure that each die-casting operation can fully fill the mold, while reserving enough material to compensate for shrinkage and avoid product defects caused by insufficient material.

[0087] Based on the obtained initial injection volume Q0, at the beginning of each die-casting operation, the actual injection volume Qa is recorded by a flow sensor; the actual injection volume of each die-casting is monitored in real time to ensure that the data is accurate and reliable, providing a basis for subsequent injection volume adjustments and helping to maintain consistency in material usage.

[0088] Combined with Qa, the injection amount deviation ΔQa is calculated, using the formula ΔQa=Q0-Qa. Then, the preset injection amount Qn for the next die-casting is adjusted according to this deviation, using the formula Qn=Q0+ζ*ΔQa, where ζ is a proportional factor used to balance the injection amount fluctuation. The injection amount is automatically adjusted through the feedback mechanism to reduce product differences caused by material usage fluctuations, ensure that the material usage for each die-casting operation is stable and consistent, and improve production reliability.

[0089] Based on the adjusted Qn, the remaining material amount Rm after each die-casting process is monitored and calculated using the formula Rm = Qn-Qu, where Qu represents the actual amount of material used. Subsequently, the impact of the remaining material amount on the next die-casting is evaluated, and the final injection amount is fine-tuned using the formula Qadj = Qn-ω*Rm, where ω is a coefficient reflecting the impact of the remaining material. By evaluating the remaining material amount, the injection amount setting for the next die-casting is optimized to avoid wasting materials while ensuring the accurate amount of material used for each die-casting, further improving production efficiency and product quality.

[0090] By precisely controlling the cooling rate and injection volume, the entire process from alloy solidification characteristics to final injection volume can be optimized. This method not only improves the geometric accuracy and internal quality of the product, but also significantly improves material utilization and production efficiency, reduces scrap rate, and achieves high-quality and efficient die-casting production.

[0091] Step 4: According to the material usage, evaluate and correct the start time of the subsequent die-casting cycle, optimize the production rhythm, summarize the results of the production rhythm, and continuously improve the die-casting process; specifically include:

[0092] Based on the final adjusted injection volume Qadj, the completion time Tend of each die-casting operation is recorded, and the average operation cycle Cavg is calculated using the formula Cavg = Σ(Tend) / N, where N is the number of die-casting operations during the observation period; the average operation cycle is obtained through statistical methods, providing a quantitative assessment of the efficiency of the die-casting process. This helps identify bottlenecks and inefficient links in production and provides a basis for subsequent optimization.

[0093] Combined with the average operation cycle Cavg, the ideal production rhythm Pid is set, through the formula Pid = Cavg*(1-η), η represents the time buffer ratio reserved to adapt to equipment preparation and maintenance; setting a realistic and feasible ideal production rhythm takes into account the time required for equipment preparation and maintenance, ensuring the flexibility and executability of the production plan. This approach avoids equipment failure or quality problems caused by overly compact arrangements.

[0094] According to the determined ideal production rhythm Pid, ​​the difference ΔPd between the current actual production rhythm Pact and the ideal value is analyzed, and the formula ΔPd=Pid-Pact is used. Then, the influence factor Id of this difference on the start timing of the subsequent die-casting cycle is evaluated, and the formula Id=ΔPd / Pid is used to quantify the actual deviation of the production rhythm, which provides a scientific basis for adjusting the production plan. Through the calculation of the influence factor Id, the start timing of the subsequent die-casting cycle can be predicted and adjusted more accurately, improving the stability of production.

[0095] Combined with the influencing factor Id, adjust the start time Tstart of the subsequent die-casting cycle, using the formula Tstart = Tprev + Pid + ψ * Id, Tprev is the start time of the previous die-casting operation, ψ is a proportional coefficient used to adjust the response speed of the production rhythm. Dynamically adjust the start time of the die-casting cycle to ensure that each die-casting can be carried out under the best conditions. This method improves the continuity and efficiency of production, reduces unnecessary waiting time, and improves the overall production rhythm.

[0096] According to the adjusted start time Tstart, the complete cycle data of each die-casting operation is recorded, including but not limited to the material consumption Qadj, cooling rate Rcf and actual production rhythm Pact, to form a comprehensive performance index Sp, using the formula Sp = (Qadj + Rcf + Pact) / 3; multiple key parameters are integrated into a comprehensive performance index to facilitate a comprehensive assessment of the quality and efficiency of each die-casting operation. This method simplifies data analysis and provides an intuitive means of performance evaluation.

[0097] Based on the calculated comprehensive performance index Sp, a historical performance database Dp is constructed to store the data of each die-casting in chronological order and form a continuous data set through the formula Dp = {Sp(1), Sp(2), ..., Sp(n)}, where n represents the cumulative number of die-casting times; long-term historical data records are established to provide rich data support for subsequent trend analysis and process optimization. This helps to discover potential problems, take preventive measures in advance, and improve the predictability and controllability of production.

[0098] By using the established historical performance database Dp, we analyze the long-term trend and determine the performance improvement factor F imp. The formula F imp = (Sp_max-Sp_min) / Sp_avg is used. Sp_max is the highest performance indicator, Sp_min is the minimum performance indicator, and Sp_avg is the average performance indicator. Through long-term trend analysis, we can quantify the space and potential for performance improvement. This approach not only helps identify the direction of improvement, but also provides a scientific basis for formulating specific optimization strategies.

[0099] Combined with the obtained performance improvement factor F imp, an optimization strategy is formulated to set a new target performance indicator Starget, using the formula Starget = Sp_avg*(1+λ*F imp), where λ is a coefficient used to balance the improvement speed and stability. Subsequently, the die-casting parameters are adjusted according to the new target to ensure the simultaneous improvement of product quality consistency and maximum production efficiency. Through scientific and reasonable optimization strategies, the overall performance of the die-casting process is gradually improved. This approach not only improves the consistency of product quality, but also significantly improves production efficiency and achieves sustainable performance improvement.

[0100] By optimizing the production rhythm and continuously improving it, we ensure that the whole process from operation cycle statistics to final die casting parameter adjustment can be managed in a refined manner. This method not only improves the continuity and efficiency of production, but also significantly improves the consistency and stability of product quality, reduces the scrap rate, and realizes efficient and high-quality die casting production.

[0101] On the other hand, the present invention proposes an alloy die-casting molding system based on intelligent parameter optimization, such as Figure 2 As shown, it includes: alloy and mold characteristic setting and initial condition configuration module, data analysis and pressure adjustment module, cooling rate regulation and material consumption control module and production rhythm optimization and process improvement module.

[0102] Alloy and mold characteristic setting and initial condition configuration module, used to determine the type of alloy to be processed and the structural characteristics of the mold, and set the initial die-casting conditions according to the alloy characteristics. Under the set initial die-casting conditions, the sensor network is used to collect dynamic data streams during the die-casting process, and the dynamic data streams include temperature, pressure and speed change information;

[0103] A data analysis and pressure adjustment module, used to analyze the acquired dynamic data stream in real time, identify the fluctuation pattern of factors affecting product quality, and adjust the pressure level applied during the die-casting process through a feedback control system according to the identified fluctuation pattern of factors;

[0104] The cooling rate adjustment and material dosage control module is used to adjust the cooling rate in time to adapt to the solidification characteristics of different alloys in combination with the adjusted pressure level. At the same time, it monitors and controls the injection volume to ensure that the material dosage of each die-casting operation is stable and consistent;

[0105] The production rhythm optimization and process improvement module is used to evaluate and correct the start timing of subsequent die-casting cycles according to material usage, optimize the production rhythm, summarize the results of the production rhythm, and continuously improve the die-casting process.

[0106] In addition, the above-mentioned alloy and mold characteristic setting and initial condition configuration module, data analysis and pressure adjustment module, cooling rate adjustment and material usage control module, and production rhythm optimization and process improvement module are also used to implement the other steps of the above-mentioned alloy die-casting molding method based on intelligent parameter optimization when executed, which will not be described one by one here.

[0107] In summary, the present invention can automatically adapt to different alloy compositions and mold design conditions by introducing a sensor network to collect dynamic data streams in the die-casting process in real time, and dynamically adjust die-casting parameters using a feedback control system, ensuring that each die-casting operation can be performed under optimal conditions. This method not only improves the consistency and stability of product quality, but also significantly improves production efficiency.

[0108] Through precise control of the die-casting process, quality problems caused by improper parameter settings are reduced, ensuring the high quality of each batch of products. Real-time analysis of dynamic data streams and identification of fluctuation patterns of factors affecting product quality, timely adjustment of die-casting parameters, and maintenance of stable product performance. The optimized die-casting process reduces scrap rates, shortens production cycles, and maximizes the use of production rhythms, overcoming the limitations of fixed parameters in existing technologies and bringing significant technological progress to the manufacturing industry.

[0109] Finally, it should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An alloy die-casting method based on intelligent parameter optimization, characterized in that: The following steps are involved: Step 1: Determine the type of alloy to be processed and the structural characteristics of the mold, and set the initial die-casting conditions according to the alloy characteristics. Under the set initial die-casting conditions, use the sensor network to collect dynamic data streams during the die-casting process, and the dynamic data streams include temperature, pressure and speed change information; Step 2: Analyze the acquired dynamic data stream in real time to identify the fluctuation pattern of factors affecting product quality, and adjust the pressure level applied during the die-casting process through a feedback control system according to the identified fluctuation pattern of factors; Step 3: Combined with the adjusted pressure level, the cooling rate is adjusted in time to adapt to the solidification characteristics of different alloys. At the same time, the injection volume is monitored and controlled to ensure that the material consumption is stable and consistent for each die casting operation; Step 4: Based on the material usage, evaluate and correct the start timing of the subsequent die-casting cycle, optimize the production rhythm, summarize the results of the production rhythm, and continuously improve the die-casting process.

2. The alloy die-casting method based on intelligent parameter optimization according to claim 1, characterized in that: Determining the type of alloy to be processed and the structural characteristics of the mold, and setting the initial die-casting conditions according to the alloy characteristics, includes: The initial temperature T0 is determined according to the thermophysical properties of the alloy, where T0 is calculated by the formula T0 = (C*D+E) / F, where C represents the specific heat capacity of the alloy, D is the expected die-casting speed, E is the ambient temperature compensation value, and F is the heat dissipation coefficient; Based on the calculated T0, the mold is preheated to the target temperature T1, which is calculated by the formula T1=T0+G, where G represents the additional temperature increment. Based on the achieved mold temperature, the required pressure P0 is calculated using the formula P0 = H*I^J where H is the pressure base related to the alloy type, I is the temperature T1, and J is the exponential factor of the effect of temperature on pressure; In combination with the calculated pressure P0, the injection port size S is adjusted according to the formula S=K*sqrt(L / P0), where K is a fixed proportionality coefficient and L is the expected fluid flow rate.

3. The alloy die-casting method based on intelligent parameter optimization according to claim 2, characterized in that: The method of collecting dynamic data flow in the die-casting process by using a sensor network under the set initial die-casting conditions includes: Deploy multiple sensing units on the die-casting equipment to collect real-time temperature Ta data. The data recorded by each sensing unit is marked with a timestamp as Ta(n), where n represents the time series number. Based on the collected temperature Ta(n) information, calculate the temperature change rate ΔTa using the formula ΔTa=Ta(n)-Ta(n-1); Based on the obtained temperature change rate, the change of pressure Pa is monitored and recorded synchronously, expressed as Pa(n), and then the ratio Ra reflecting the material flow resistance is calculated by the formula Ra=Pa(n) / (ΔTa+1); Combined with the obtained ratio Ra, the change of the speed Va is analyzed, and the speed setting is adjusted using the formula Va(n)=Ra*Ma+Na, where Ma is the preset speed adjustment coefficient and Na is the basic speed value.

4. The alloy die-casting method based on intelligent parameter optimization according to claim 3, characterized in that: The real-time analysis of the acquired dynamic data stream to identify the fluctuation pattern of factors affecting product quality includes: Receive dynamic data streams and extract time series information of temperature Ta(n), pressure Pa(n) and velocity Va(n); Based on the extracted data, the fluctuation characteristic vector Fa is constructed by the formula Fa = (Ta(n), Pa(n), Va(n)); Using the generated fluctuation characteristic vector Fa, calculate the difference Da between two adjacent die castings using the formula Da = sqrt((Fa(n)-Fa(n-1))^2); Combined with the obtained difference Da, the main fluctuation mode Ma that affects product quality is determined, and the formula Ma=Da*Wa+Ba is used for pattern recognition, where Wa is the weight coefficient and Ba is the bias value.

5. The alloy die-casting method based on intelligent parameter optimization according to claim 4, characterized in that: The method of adjusting the pressure level applied during the die casting process by a feedback control system according to the fluctuation pattern of the factors identified comprises: According to the identified main fluctuation mode Ma, determine the pressure correction coefficient Kp that needs to be adjusted, using the formula Kp = 1 / (1+|Ma|); Based on the calculated pressure correction coefficient Kp, the target pressure Pt in the die casting process is updated by the formula Pt = Pi*Kp, where Pi is the initially set pressure value; Based on the set new target pressure Pt, the feedback control system is started to perform real-time monitoring and collect data points of the actual applied pressure Pa; Combined with the actual pressure Pa obtained, the pressure error Ep is calculated using the formula Ep=Pt-Pa, and then the final applied pressure is adjusted using the formula Padj=Pa+α*Ep, where α is a pre-calibrated proportional factor.

6. The alloy die-casting method based on intelligent parameter optimization according to claim 5, characterized in that: The combined adjusted pressure level and timely adjustment of the cooling rate to suit the solidification characteristics of different alloys include: Based on the adjusted final applied pressure Padj, determine the alloy solidification characteristic parameter Cadj, using the formula Cadj = Padj * β, β is a proportional factor related to the alloy type; According to the obtained solidification characteristic parameter Cadj, the initial cooling rate Rc is set and calculated by the formula Rc = Cadj / Tm, where Tm represents the melting point temperature of the alloy; Based on the set initial cooling rate Rc, the temperature change ΔTc in the mold is monitored in real time, and the cooling rate increment ΔRc is updated using the formula ΔRc=γ*ΔTc, where γ is the proportional coefficient of the effect of temperature change on cooling rate; Combined with the calculated cooling rate increment ΔRc, the final cooling rate Rcf is adjusted using the formula Rcf=Rc+ΔRc. At the same time, the product size deviation δc is monitored and the formula δc=|Sc_measured-Sc_target| is used to ensure that the size meets the design requirements, where Sc_measured is the actual measured product size and Sc_target is the target size.

7. The alloy die-casting method based on intelligent parameter optimization according to claim 6, characterized in that: The monitoring and control of injection volume ensures a stable and consistent amount of material for each die casting operation, including: According to the set final cooling rate Rcf, determine the initial injection volume Q0, using the formula Q0 = Vm*(1+ε), Vm is the volume of the mold cavity, and ε is the additional percentage reserved to account for material shrinkage and underfilling; Based on the obtained initial injection volume Q0, at the beginning of each die casting operation, the actual injection volume Qa is recorded by the flow sensor; Combined with Qa, calculate the injection amount deviation ΔQa, using the formula ΔQa = Q0-Qa, and then adjust the preset injection amount Qn for the next die casting according to this deviation, using the formula Qn = Q0 + ζ * ΔQa, ζ is a proportional factor used to balance the injection amount fluctuation; On the basis of the adjusted Qn, the amount of remaining material Rm after each die-casting process is monitored and calculated through the formula Rm=Qn-Qu, where Qu represents the actual amount of material used. Subsequently, the impact of the remaining material on the next die-casting is evaluated, and the final injection amount is fine-tuned using the formula Qadj=Qn-ω*Rm, where ω is a coefficient reflecting the degree of impact of the remaining material.

8. The alloy die-casting method based on intelligent parameter optimization according to claim 7, characterized in that: According to the material usage, the start time of the subsequent die-casting cycle is evaluated and corrected to optimize the production rhythm, including: Based on the final adjusted injection volume Qadj, the completion time Tend of each die-casting operation is recorded, and the average operation cycle Cavg is calculated using the formula Cavg = Σ(Tend) / N, where N is the number of die-casting times during the observation period; Combined with the obtained average operation cycle Cavg, set the ideal production rhythm Pid, ​​through the formula Pid = Cavg*(1-η), η represents the time buffer ratio reserved to adapt to equipment preparation and maintenance; According to the determined ideal production rhythm Pid, ​​analyze the difference ΔPd between the current actual production rhythm Pact and the ideal value, using the formula ΔPd=Pid-Pact. Then, evaluate the impact factor Id of this difference on the timing of starting the subsequent die-casting cycle, using the formula Id=ΔPd / Pid. Combined with the influencing factor Id, adjust the start time Tstart of the subsequent die-casting cycle, using the formula Tstart = Tprev + Pid + ψ * Id, Tprev is the start time of the previous die-casting operation, ψ is a proportional coefficient used to adjust the production rhythm response speed.

9. The alloy die-casting method based on intelligent parameter optimization according to claim 8, characterized in that: The results of the production rhythm are summarized to continuously improve the die casting process, including: According to the adjusted start time Tstart, record the complete cycle data of each die-casting operation, including but not limited to the material consumption Qadj, cooling rate Rcf and actual production rhythm Pact, to form a comprehensive performance index Sp, using the formula Sp = (Qadj + Rcf + Pact) / 3; Based on the calculated comprehensive performance index Sp, a historical performance database Dp is constructed, the data of each die-casting is stored in chronological order, and a continuous data set is formed through the formula Dp = {Sp(1), Sp(2), ..., Sp(n)}, where n represents the cumulative number of die-casting times; Using the established historical performance database Dp, analyze the long-term trend and determine the performance improvement factor Fimp, using the formula Fimp = (Sp_max-Sp_min) / Sp_avg, where Sp_max is the highest performance indicator, Sp_min is the minimum performance indicator, and Sp_avg is the average performance indicator; Based on the obtained performance improvement factor Fimp, an optimization strategy is formulated and a new target performance indicator Starget is set using the formula Starget = Sp_avg*(1+λ*Fimp), where λ is a coefficient used to balance the improvement speed and stability. Subsequently, the die-casting parameters are adjusted according to the new target to ensure simultaneous improvement of product quality consistency and maximum production efficiency.

10. An alloy die-casting system based on intelligent parameter optimization for implementing the method according to any one of claims 1 to 9, characterized in that: include: Alloy and mold characteristic setting and initial condition configuration module, used to determine the type of alloy to be processed and the structural characteristics of the mold, and set the initial die-casting conditions according to the alloy characteristics. Under the set initial die-casting conditions, the sensor network is used to collect dynamic data streams during the die-casting process, and the dynamic data streams include temperature, pressure and speed change information; A data analysis and pressure adjustment module, used to analyze the acquired dynamic data stream in real time, identify the fluctuation pattern of factors affecting product quality, and adjust the pressure level applied during the die-casting process through a feedback control system according to the identified fluctuation pattern of factors; The cooling rate adjustment and material dosage control module is used to adjust the cooling rate in time to adapt to the solidification characteristics of different alloys in combination with the adjusted pressure level. At the same time, it monitors and controls the injection volume to ensure that the material dosage of each die-casting operation is stable and consistent; The production rhythm optimization and process improvement module is used to evaluate and correct the start timing of subsequent die-casting cycles according to material usage, optimize the production rhythm, summarize the results of the production rhythm, and continuously improve the die-casting process.

Images