Aluminum alloy production temperature intelligent control method based on Internet of Things

Abstract

The invention relates to the technical field of aluminum alloy production temperature control through computer aided design, in particular to an intelligent aluminum alloy production temperature control method based on the Internet of Things, and the method comprises the steps: obtaining aluminum alloy production operation data, extracting characteristic parameters of the aluminum alloy production operation data, and calculating the aluminum alloy production temperature according to the characteristic parameters; the characteristic parameters comprise the smelting furnace temperature, the energy consumption and the product quality score, and carrying out standardization processing on the aluminum alloy production operation data; an aluminum alloy production temperature control model is constructed, the aluminum alloy production temperature control model is defined by taking product quality and energy efficiency maximization as optimization targets, and meanwhile, multiple constraint conditions of the aluminum alloy production temperature control model are defined; and inputting the characteristic parameters of the aluminum alloy production operation data into the aluminum alloy production temperature control model for calculation, solving an optimal adjustment strategy of the aluminum alloy production temperature, and completing accurate control of the aluminum alloy production temperature.

Description

Technical Field

[0001] The present invention relates to the technical field of temperature control in aluminum alloy production by computer-aided design, and in particular to an intelligent temperature control method for aluminum alloy production based on the Internet of Things. Background Art

[0002] Aluminum alloy production is a complex industrial process, in which temperature control is crucial to product quality and energy efficiency. At present, traditional aluminum alloy production temperature control technology has many limitations. On the one hand, the strategy of temperature control based on staff experience is difficult to adapt to the complex and changing production environment, which easily leads to insufficient control accuracy and product quality fluctuations. On the other hand, due to the lack of real-time monitoring and optimization capabilities of energy consumption, it is impossible to dynamically adjust energy use strategies according to production needs, which not only increases production costs, but also reduces the environmental performance and sustainable development capabilities of enterprises. In the context of energy price fluctuations and increasingly stringent environmental protection requirements, this problem has become particularly prominent. Based on this, in response to the above problems, we designed an intelligent temperature control method for aluminum alloy production based on the Internet of Things. Summary of the invention

[0003] The purpose of the present invention is to provide an intelligent temperature control method for aluminum alloy production based on the Internet of Things. It constructs a temperature control model based on data-driven, combined with the dual optimization of product quality and energy efficiency, not only to achieve precise temperature control in the aluminum alloy production process, but also to adapt to complex production environments, thereby improving product quality and energy efficiency.

[0004] The embodiments of the present invention are implemented by the following technical solutions:

[0005] An intelligent temperature control method for aluminum alloy production based on the Internet of Things, the method comprising the following steps:

[0006] Acquire aluminum alloy production and operation data, extract characteristic parameters of the aluminum alloy production and operation data, the characteristic parameters include: furnace temperature, energy consumption and product quality score, and perform standardization on the aluminum alloy production and operation data;

[0007] An aluminum alloy production temperature control model is constructed. The aluminum alloy production temperature control model defines maximizing product quality and energy efficiency as optimization goals, and also defines a variety of constraints of the aluminum alloy production temperature control model. The characteristic parameters of the aluminum alloy production operation data are input into the aluminum alloy production temperature control model for calculation, and the optimal adjustment strategy for the aluminum alloy production temperature is solved to complete the precise control of the aluminum alloy production temperature.

[0008] Optionally, the characteristic parameters of the extracted aluminum alloy production operation data are calculated using the following formula:

[0009] Tt =f T (t)

[0010]

[0011] Q t =w 1 C t +w 2 S t +w 3 M t

[0012] Among them, T t is the furnace temperature at time t, f T (t) is the temperature measurement function, E t is the cumulative energy consumption at time t, P(τ) is the power function, Δt is the statistical time interval, Q t is the product quality score at time t, C t , S t 、M t are the scores of composition, strength and microstructure, respectively, and w 1 、w 2 、w 3 is the weight coefficient.

[0013] Optionally, the energy efficiency index is calculated by the energy consumption and product quality score, and the calculation formula is:

[0014]

[0015] Among them, EEI t is the energy efficiency index at time t.

[0016] Optionally, the aluminum alloy production temperature control model is constructed, which specifically includes: an input layer, a hidden layer and an output layer; wherein the calculation formula of the input layer is:

[0017] a (1) =[T t ,E t ,Q t ,EEI t ]

[0018] Among them, a (1) is the activation value of the input layer;

[0019] The calculation formula of the hidden layer is:

[0020] z (l) =W (l) a (l-1) +b (l)

[0021] a (l) =g(z (l) )

[0022] Among them, z (l) is the linear combination output of the lth layer, W (l) is the weight matrix of the lth layer, b (l) is the bias of the lth layer, a (l) is the activation value of the lth layer, g() is the activation function;

[0023] The calculation formula of the output layer is:

[0024] ΔT=W (L) a (L-1) +b (L)

[0025] Among them, ΔT is the temperature adjustment amount, which represents the optimal adjustment strategy of aluminum alloy production temperature, W (L) is the weight matrix of the output layer, b (L) is the bias of the output layer, a (L-1) is the activation value of the last hidden layer, and L is the total number of layers in the network.

[0026] Optionally, the aluminum alloy production temperature control model is defined to maximize product quality and energy efficiency as the optimization goal, and its calculation formula is:

[0027]

[0028] Among them, maxJ is the objective function, N is the cycle length, Q base To benchmark product quality, EEI ref is the reference energy efficiency level, ΔQ t =Q t -Q t-1 is the mass change at adjacent moments, ΔEEI t =EEI t -EEI t-1 is the change of energy efficiency at adjacent moments, is the average product quality, is the average energy efficiency, E target is the target energy consumption level, and k is the energy consumption sensitivity parameter.

[0029] Optionally, the multiple constraints defining the aluminum alloy production temperature control model include: temperature constraints, temperature change rate constraints, energy consumption constraints, instantaneous energy consumption constraints, energy efficiency constraints, product quality constraints, quality stability constraints, comprehensive performance lower limit constraints, energy efficiency improvement constraints and quality and energy efficiency balance constraints.

[0030] Optionally, the calculation formula of the temperature constraint is:

[0031] T min ≤T t ≤T max

[0032] The calculation formula for the temperature change rate constraint is:

[0033] |ΔT t |=|T t -T t-1 |≤ΔT max

[0034] The calculation formula for energy consumption constraint is:

[0035]

[0036] The calculation formula for the instantaneous energy consumption constraint is:

[0037] E t ≤E max

[0038] The calculation formula of energy efficiency constraint is:

[0039] EEI t ≥EEI min

[0040] The calculation formula for product quality constraints is:

[0041] Q t ≥Q min

[0042] The calculation formula for the quality stability constraint is:

[0043] |ΔQ t |=|Q t -Q t-1 |≤ΔQ max

[0044] The calculation formula for the lower limit constraint of comprehensive performance is:

[0045] J≥J min

[0046] The calculation formula for energy efficiency improvement constraint is:

[0047]

[0048] The calculation formula for the quality and energy efficiency balance constraint is:

[0049]

[0050] Among them, T min , T maxare the lower and upper temperature limits, ΔT t is the temperature difference between time t and time t-1, ΔT max is the maximum temperature change rate, E t is the energy consumption at time t, E target is the average energy consumption level, E max is the maximum instantaneous energy consumption, EEI min is the minimum energy efficiency requirement, Q t is the product quality score at time t, Q min is the minimum product quality standard, ΔQ t is the quality score difference between time t and time t-1, ΔQ max is the maximum mass change, J min EEI is the lowest comprehensive performance index. target is the average energy efficiency level, ∈ is the maximum imbalance.

[0051] Optionally, the aluminum alloy production operation data is standardized, and the calculation formula is:

[0052]

[0053] Among them, x norm is the standardized eigenvalue, x is the original eigenvalue, M is the total number of samples, x i is the eigenvalue of the i-th sample.

[0054] The technical solution of the embodiment of the present invention has at least the following advantages and beneficial effects:

[0055] The embodiment of the present invention constructs a data-driven temperature control model, combined with the dual optimization of product quality and energy efficiency, not only to achieve precise temperature control in the aluminum alloy production process, but also to adapt to complex production environments, thereby improving product quality and energy efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 A schematic flow chart of an intelligent temperature control method for aluminum alloy production based on the Internet of Things provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0057] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0058] like Figure 1As shown, Figure 1 A schematic flow chart of an intelligent temperature control method for aluminum alloy production based on the Internet of Things provided in an embodiment of the present invention.

[0059] In one embodiment, a method for intelligently controlling temperature of aluminum alloy production based on the Internet of Things comprises the following steps:

[0060] Acquire aluminum alloy production and operation data, extract characteristic parameters of the aluminum alloy production and operation data, the characteristic parameters include: furnace temperature, energy consumption and product quality score, and perform standardization on the aluminum alloy production and operation data;

[0061] An aluminum alloy production temperature control model is constructed. The aluminum alloy production temperature control model defines maximizing product quality and energy efficiency as optimization goals, and also defines a variety of constraints of the aluminum alloy production temperature control model. The characteristic parameters of the aluminum alloy production operation data are input into the aluminum alloy production temperature control model for calculation, and the optimal adjustment strategy for the aluminum alloy production temperature is solved to complete the precise control of the aluminum alloy production temperature.

[0062] In practice, the temperature control of aluminum alloy production in this embodiment is mainly designed based on the melting and casting process of aluminum alloy, and its specific data collection is carried out through the Internet of Things. Among them, the temperature of the furnace is mainly measured by temperature sensors, which are respectively arranged inside the furnace and on the outer wall of the furnace. Energy consumption is mainly measured by power monitoring equipment and / or gas flow meters, etc. The power monitoring equipment mainly includes current and voltage sensors, etc., which are mainly installed in the power supply area of ​​the furnace to measure the power consumption. The gas flow meter is mainly installed at the gas supply pipeline. It can be understood that the product in this embodiment is characterized as a finished product of aluminum alloy, and its quality score mainly depends on the evaluation of the composition, strength and microstructure of the finished aluminum alloy. The test results of each aspect will be given a certain weight according to its importance, and finally summarized to form a comprehensive quality score.

[0063] Specifically, the characteristic parameters of the aluminum alloy production operation data are extracted, wherein the calculation formula of the furnace temperature is:

[0064] T t =f T (t)

[0065] The energy consumption is calculated as:

[0066]

[0067] The product quality score is calculated as follows:

[0068] Q t =w 1 C t +w 2 St +w 3 M t

[0069] Among them, T t is the furnace temperature at time t, f T (t) is the temperature measurement function, which is a discrete data point directly obtained from the temperature sensor in this embodiment, E t is the cumulative energy consumption at time t, P(τ) is the power function, which is obtained by the power monitoring device in this embodiment, Δt is the statistical time interval, Q t is the product quality score at time t, C t , S t 、M t are the scores of composition, strength and microstructure, respectively, and w 1 、w 2 、w 3 is the weight coefficient.

[0070] In practical applications, the composition directly affects the performance and processability of aluminum alloys; the strength (including but not limited to tensile strength, hardness, etc.) is related to the performance and safety of aluminum alloys; the microstructure affects the comprehensive performance of aluminum alloys. Therefore, this embodiment assigns weight coefficients w 1 is 0.45; w 2 =0.35; microstructure is 0.2. Assuming that the scores of a batch of aluminum alloy products are as follows: composition score: 90 points; strength score: 85 points; microstructure score: 80 points; the final quality score is: 90*45%+85*35%+80*20%=86.75. It can not only fully reflect the core quality characteristics of aluminum alloy products, but also facilitate rapid evaluation and quality control in the production process. It is understandable that the specific weights can be appropriately adjusted according to actual requirements and application scenarios.

[0071] Furthermore, the energy efficiency index is calculated by the energy consumption and product quality score, and the calculation formula is:

[0072]

[0073] Among them, EEI t is the energy efficiency index at time t.

[0074] In practice, the introduction of energy efficiency indicators in this embodiment can make the subsequent construction of an aluminum alloy production temperature control model more sensitive to the balance between quality and energy consumption, and help find a better balance between the two.

[0075] In the specific application of this embodiment, the aluminum alloy production temperature control model is constructed. The aluminum alloy production temperature control model of this embodiment is mainly an MLP (multi-layer perceptron) model, which specifically includes: an input layer, a hidden layer and an output layer. It can be understood that the aluminum alloy production temperature control model is mainly trained based on historical data, which will not be described in detail in this embodiment.

[0076] Among them, the calculation formula of the input layer is:

[0077] a (1) =[T t ,E t ,Q t ,EEI t ]

[0078] Among them, a (1) is the activation value of the input layer;

[0079] The calculation formula of the hidden layer is:

[0080] z (l) =W (l) a (l-1) +b (l)

[0081] a (l) =g(z (l) )

[0082] Among them, z (l) is the linear combination output of the lth layer, W (l) is the weight matrix of the lth layer, b (l) is the bias of the lth layer, a (l) is the activation value of the lth layer, g() is the activation function;

[0083] The calculation formula of the output layer is:

[0084] ΔT=W (L) a (L-1) +b (L)

[0085] Among them, ΔT is the temperature adjustment amount, which represents the optimal adjustment strategy of aluminum alloy production temperature, W (L) is the weight matrix of the output layer, b (L) is the bias of the output layer, a (L-1) is the activation value of the last hidden layer, and L is the total number of layers in the network.

[0086] The aluminum alloy production temperature control model is defined to maximize product quality and energy efficiency as the optimization goal, and its calculation formula is:

[0087]

[0088] Among them, maxJ is the objective function, N is the cycle length, Q base To benchmark product quality, EEI ref is the reference energy efficiency level, ΔQ t =Q t -Q t-1 is the mass change at adjacent moments, ΔEEI t =EEI t -EEI t-1 is the change of energy efficiency at adjacent moments, is the average product quality, is the average energy efficiency, E target is the target energy consumption level, and k is the energy consumption sensitivity parameter.

[0089] More specifically, the various constraints defining the aluminum alloy production temperature control model include: temperature constraints, temperature change rate constraints, energy consumption constraints, instantaneous energy consumption constraints, energy efficiency constraints, product quality constraints, quality stability constraints, comprehensive performance lower limit constraints, energy efficiency improvement constraints and quality and energy efficiency balance constraints.

[0090] The calculation formula of the temperature constraint is:

[0091] T min ≤T t ≤T max

[0092] The calculation formula of the temperature change rate constraint is:

[0093] |ΔT t |=|T t -T t-1 |≤ΔT max

[0094] The calculation formula of the energy consumption constraint is:

[0095]

[0096] The calculation formula of the instantaneous energy consumption constraint is:

[0097] E t ≤E max

[0098] The calculation formula of the energy efficiency constraint is:

[0099] EEI t ≥EEI min

[0100] The calculation formula of the product quality constraint is:

[0101] Q t ≥Q min

[0102] The calculation formula of the mass stability constraint is:

[0103] |ΔQ t |=|Q t -Q t-1 |≤ΔQ max

[0104] The calculation formula of the comprehensive performance lower limit constraint is:

[0105] J≥J min

[0106] The calculation formula of the energy efficiency improvement constraint is:

[0107]

[0108] The calculation formula for the quality and energy efficiency balance constraint is:

[0109]

[0110] Among them, T min , T max are the lower and upper temperature limits, ΔT t is the temperature difference between time t and time t-1, ΔT max is the maximum temperature change rate, E t is the energy consumption at time t, E target is the average energy consumption level, E max is the maximum instantaneous energy consumption, EEI min is the minimum energy efficiency requirement, Q t is the product quality score at time t, Q min is the minimum product quality standard, ΔQ t is the quality score difference between time t and time t-1, ΔQ max is the maximum mass change, J min EEI is the lowest comprehensive performance index. target is the average energy efficiency level, ∈ is the maximum imbalance.

[0111] In practice, the constraints set in this embodiment cover temperature control, energy consumption, product quality, energy efficiency and the balance between them to jointly ensure the stability, efficiency and quality of the aluminum alloy production process.

[0112] Furthermore, the aluminum alloy production operation data is standardized, and the calculation formula is:

[0113]

[0114] Among them, x norm is the standardized eigenvalue, x is the original eigenvalue, M is the total number of samples, x i is the eigenvalue of the i-th sample.

[0115] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An intelligent temperature control method for aluminum alloy production based on the Internet of Things, characterized in that: The steps of the method include: Acquire aluminum alloy production and operation data, extract characteristic parameters of the aluminum alloy production and operation data, the characteristic parameters include: furnace temperature, energy consumption and product quality score, and perform standardization on the aluminum alloy production and operation data; An aluminum alloy production temperature control model is constructed. The aluminum alloy production temperature control model defines maximizing product quality and energy efficiency as optimization goals, and also defines a variety of constraints of the aluminum alloy production temperature control model. The characteristic parameters of the aluminum alloy production operation data are input into the aluminum alloy production temperature control model for calculation, and the optimal adjustment strategy for the aluminum alloy production temperature is solved to complete the precise control of the aluminum alloy production temperature.

2. The intelligent temperature control method for aluminum alloy production based on the Internet of Things according to claim 1 is characterized in that: The calculation formula for extracting the characteristic parameters of the aluminum alloy production operation data is: T t =f T (t) <h2 style=";text-align:left;direction:ltr">Q<h2 style=";text-align:left;direction:ltr"> t <h2 style=";text-align:left;direction:ltr"> =w1C<h2 style=";text-align:left;direction:ltr"> t <h2 style=";text-align:left;direction:ltr"> +w2S<h2 style=";text-align:left;direction:ltr"> t <h2 style=";text-align:left;direction:ltr"> +w3M<h2 style=";text-align:left;direction:ltr"> t Among them, T t is the furnace temperature at time t, f T (t) is the temperature measurement function, E t is the cumulative energy consumption at time t, P(τ) is the power function, Δt is the statistical time interval, Q t is the product quality score at time t, C t , S t 、M t are the scores of composition, strength and microstructure respectively, and w1, w2 and w3 are weight coefficients.

3. The intelligent temperature control method for aluminum alloy production based on the Internet of Things according to claim 2 is characterized in that: The energy efficiency index is calculated by the energy consumption and product quality score, and the calculation formula is: Among them, EEI t is the energy efficiency index at time t.

4. The intelligent temperature control method for aluminum alloy production based on the Internet of Things according to claim 3 is characterized in that: The aluminum alloy production temperature control model is constructed, which specifically includes: an input layer, a hidden layer and an output layer; wherein the calculation formula of the input layer is: a (1) =[T t ,HAVE BEEN t ,Q t , t ] Among them, a (1) is the activation value of the input layer; The calculation formula of the hidden layer is: z (l) =W (l) a (l-1) +b (l) a (l) =g(z (l) ) Among them, z (l) is the linear combination output of the lth layer, W (l) is the weight matrix of the lth layer, b (l) is the bias of the lth layer, a (l) is the activation value of the lth layer, g() is the activation function; The calculation formula of the output layer is: ΔT=W (L) a (L-1) +b (L) Among them, ΔT is the temperature adjustment amount, which represents the optimal adjustment strategy of aluminum alloy production temperature, W (L) is the weight matrix of the output layer, b (L) is the bias of the output layer, a (L-1) is the activation value of the last hidden layer, and L is the total number of layers in the network.

5. The intelligent temperature control method for aluminum alloy production based on the Internet of Things according to claim 4 is characterized in that: The aluminum alloy production temperature control model is defined to maximize product quality and energy efficiency as the optimization goal, and its calculation formula is: Among them, maxJ is the objective function, N is the cycle length, Q base To benchmark product quality, EEI ref is the reference energy efficiency level, ΔQ t =Q t -Q t-1 is the mass change at adjacent moments, ΔEEI t =EEI t -EEI t-1 is the change of energy efficiency at adjacent moments, is the average product quality, is the average energy efficiency, E target is the target energy consumption level, and k is the energy consumption sensitivity parameter.

6. The intelligent temperature control method for aluminum alloy production based on the Internet of Things according to claim 5 is characterized in that: The various constraints defining the aluminum alloy production temperature control model include: temperature constraints, temperature change rate constraints, energy consumption constraints, instantaneous energy consumption constraints, energy efficiency constraints, product quality constraints, quality stability constraints, comprehensive performance lower limit constraints, energy efficiency improvement constraints and quality and energy efficiency balance constraints.

7. The intelligent temperature control method for aluminum alloy production based on Internet of Things according to claim 6 is characterized in that: The calculation formula of the temperature constraint is: T min ≤T t ≤T max The calculation formula for the temperature change rate constraint is: |ΔT t |=|T t -T t-1 |≤ΔT max The calculation formula for energy consumption constraint is: The calculation formula for the instantaneous energy consumption constraint is: AND t ≤E max The calculation formula of energy efficiency constraint is: EEI t ≥EEI min The calculation formula for product quality constraints is: Q t ≥Q min The calculation formula for the quality stability constraint is: |ΔQ t |=|Q t -Q t-1 |≤ΔQ max The calculation formula for the lower limit constraint of comprehensive performance is: J≥J min The calculation formula for energy efficiency improvement constraint is: The calculation formula for the quality and energy efficiency balance constraint is: Among them, T min 、T max are the lower and upper temperature limits, ΔT t is the temperature difference between time t and time t-1, ΔT max is the maximum temperature change rate, E t is the energy consumption at time t, E target is the average energy consumption level, E max is the maximum instantaneous energy consumption, EEI min is the minimum energy efficiency requirement, Q t is the product quality score at time t, Q min is the minimum product quality standard, ΔQ t is the quality score difference between time t and time t-1, ΔQ max is the maximum mass change, J min EEI is the lowest comprehensive performance index. target is the average energy efficiency level, ∈ is the maximum imbalance.

8. The method for intelligent temperature control of aluminum alloy production based on the Internet of Things according to any one of claims 1 to 7, characterized in that: The calculation formula for the standardized processing of aluminum alloy production operation data is as follows: Among them, x norm is the standardized eigenvalue, x is the original eigenvalue, M is the total number of samples, x i is the eigenvalue of the i-th sample.

Images