Metal profile extrusion parameter determination method and device and readable storage medium

Abstract

The invention provides a metal profile extrusion parameter determination method and device and a readable storage medium, and the method comprises the steps: obtaining a target characteristic parameter of a target metal profile and a corresponding historical process parameter in a historical extrusion process; according to the historical process parameters, a knowledge graph of the metal profile extrusion process is determined; determining a first extrusion parameter of the target metal profile according to the target characteristic parameter and the knowledge graph; inputting the target characteristic parameter into a trained metal profile extrusion parameter prediction model for prediction, and determining a second extrusion parameter of the target metal profile; the metal profile extrusion parameter prediction model is obtained by training a preset neural network based on an improved zebra optimization algorithm and historical process parameters; and according to the first extrusion parameter and the second extrusion parameter, determining a target extrusion parameter corresponding to the target metal profile. According to the scheme, the determination efficiency and accuracy of the profile extrusion parameters are improved, then the profile extrusion quality is improved, and the extrusion energy consumption is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of metal material extrusion processing, in particular to a metal profile extrusion parameter determination method and device and a readable storage medium. BACKGROUND

[0002] Traditional process optimization mainly relies on the method combining finite element simulation and orthogonal test, which not only has high calculation cost and long cycle, but also is difficult to respond to the rapid response demand of new aluminum profile production. In actual production, the setting of key process parameters such as extrusion speed and temperature parameters directly affects the energy consumption level and the product quality stability. Unreasonable parameter combination is easy to cause profile deformation, surface defects and other problems. Although numerical simulation and machine learning technology have been gradually applied in this field, the existing methods still have defects such as low calculation efficiency, insufficient interpretability, limited multi-objective optimization ability, etc., which makes enterprises still highly rely on experience parameters and it is difficult to achieve the optimal balance between energy consumption and quality. SUMMARY

[0003] The technical problem to be solved by the present application is to provide a metal profile extrusion parameter determination method and device and a readable storage medium to improve the accuracy of the extrusion parameters in the metal profile extrusion process, thereby improving the extrusion efficiency and quality, and reducing the extrusion energy consumption.

[0004] To solve the above technical problems, an embodiment of the present application provides a metal profile extrusion parameter determination method, comprising:

[0005] Obtaining target characteristic parameters of a target metal profile and corresponding historical process parameters in a historical extrusion process, the historical process parameters including historical models of a plurality of metal profiles and historical characteristic parameters, historical extrusion parameters and historical extrusion results corresponding to the historical models one by one;

[0006] According to the historical process parameters, a knowledge graph of the metal profile extrusion process is determined, and the knowledge graph is a relationship structure diagram among the historical models, the historical characteristic parameters, the historical extrusion parameters and the historical extrusion results;

[0007] According to the target characteristic parameters and the knowledge graph, the first extrusion parameters of the target metal profile are determined;

[0008] The target characteristic parameters are input into a trained metal profile extrusion parameter prediction model for prediction to determine the second extrusion parameters of the target metal profile; the metal profile extrusion parameter prediction model is obtained by training a preset neural network based on an improved zebra optimization algorithm and the historical process parameters;

[0009] According to the first extrusion parameter and the second extrusion parameter, a target extrusion parameter corresponding to the target metal profile is determined.

[0010] In one embodiment, according to the historical process parameters, a knowledge graph of a metal profile extrusion process is determined, including:

[0011] According to the historical model, the historical characteristic parameters, the historical extrusion parameters and the historical extrusion results, an ontology framework of the knowledge graph is determined;

[0012] According to the historical model, the historical characteristic parameters, the historical extrusion parameters and the historical extrusion results, an ontology framework of the knowledge graph is determined;

[0013] According to the historical model, the historical characteristic parameters, the historical extrusion parameters and the historical extrusion results, an ontology framework of the knowledge graph is determined;

[0014] In one embodiment, according to the historical model, the historical characteristic parameters, the historical extrusion parameters and the historical extrusion results, an ontology framework of the knowledge graph is determined, including:

[0015] According to the historical model, the historical characteristic parameters, the historical extrusion parameters and the historical extrusion results, a profile model entity, a characteristic parameter entity, an extrusion parameter entity and an extrusion result entity are determined;

[0016] According to a preset hierarchical structure sequence, the profile model entity, the characteristic parameter entity, the extrusion parameter entity and the extrusion result entity are top-down sorted to determine the ontology framework.

[0017] In one embodiment, according to the target characteristic parameters and the knowledge graph, a first extrusion parameter of the target metal profile is determined, including:

[0018] The similarity between the target characteristic parameters and the historical characteristic parameters corresponding to each historical model in the knowledge graph is determined.

[0019] According to the similarity, a candidate historical model in the knowledge graph is confirmed, and a first extrusion parameter is determined according to the historical extrusion parameter corresponding to the candidate historical model.

[0020] In one embodiment, the similarity between the target characteristic parameters and the historical characteristic parameters corresponding to each historical model in the knowledge graph is determined, including:

[0021] The similarity is determined by the following formula:

[0022]

[0023] wherein, D j represents the similarity between the jth historical existing metal profile and the target metal profile characteristic parameter in the knowledge graph, j = 1, 2, …, 3, m; x i represents the ith target characteristic parameter of the target metal profile, y ij represents the ith historical characteristic parameter of the jth historical existing metal profile in the knowledge graph; n represents the type of characteristic parameter.

[0024] In one embodiment, the metal profile extrusion parameter prediction model is obtained by training a preset neural network based on an improved zebra optimization algorithm and the historical process parameters, comprising:

[0025] determining an initial parameter population of the preset neural network; the initial parameter population contains multiple groups of parameters, each group of parameters includes an initial weight and an initial threshold parameter, and the initial parameter population corresponds to an initial individual population containing multiple zebra individuals, each group of parameters corresponds to the position of each zebra individual one by one;

[0026] determining a first fitness value of each zebra individual in the initial individual population according to the historical process parameters, each group of parameters in the initial parameter population, and the preset neural network;

[0027] iteratively updating the position of the zebra individual in the initial individual population according to the first fitness value and a preset optimization strategy to determine the target position of the zebra individual in the initial individual population;

[0028] determining the parameter value corresponding to the target position as the target parameter of the preset neural network, and iteratively training the preset neural network according to the target parameter and the historical process parameters until a preset convergence condition or a first preset iteration number is reached to obtain the metal profile extrusion parameter prediction model.

[0029] In one embodiment, iteratively updating the position of the zebra individual in the initial individual population according to the first fitness value and a preset optimization strategy to determine the target position of the zebra individual in the initial individual population, comprises:

[0030] determining the current optimal position in the initial individual population and the first fitness value corresponding to the current optimal position according to the first fitness value;

[0031] iteratively updating the position of the zebra individual in the initial individual population according to a preset Levy flight exploration strategy, a preset nonlinear convergence factor, and the optimal position until a second preset iteration number is reached to obtain the target position.

[0032] In one embodiment, the target extrusion parameter corresponding to the target metal profile is determined according to the first extrusion parameter and the second extrusion parameter, including:

[0033] The first extrusion parameter and the second extrusion parameter are weighted and fused according to a preset weight value to obtain the target extrusion parameter.

[0034] Embodiments of the present application also provide a metal profile extrusion parameter determination device, including:

[0035] The acquisition module is configured to acquire a target feature parameter of a target metal profile and a corresponding historical process parameter in a historical extrusion process, the historical process parameter including historical models of a plurality of metal profiles and historical feature parameters, historical extrusion parameters and historical extrusion results corresponding to the historical models one by one.

[0036] The processing module is configured to determine a knowledge graph of a metal profile extrusion process according to the historical process parameter, the knowledge graph being a relationship structure diagram among the historical models, the historical feature parameters, the historical extrusion parameters and the historical extrusion results; determine a first extrusion parameter of the target metal profile according to the target feature parameter and the knowledge graph; input the target feature parameter into a trained metal profile extrusion parameter prediction model for prediction to determine a second extrusion parameter of the target metal profile; the metal profile extrusion parameter prediction model is obtained by training a preset neural network based on an improved zebra optimization algorithm and the historical process parameter; and determine a target extrusion parameter corresponding to the target metal profile according to the first extrusion parameter and the second extrusion parameter.

[0037] Embodiments of the present application also provide a computer readable storage medium, the computer readable storage medium storing a program, the program being executed by a processor to implement the method described above.

[0038] The above scheme of the present application at least includes the following beneficial effects:

[0039] The scheme of the present application obtains target characteristic parameters of a target metal profile and corresponding historical process parameters in a historical extrusion process, the historical process parameters including historical models of a plurality of metal profiles and historical characteristic parameters, historical extrusion parameters and historical extrusion results corresponding to the historical models one by one; according to the historical process parameters, a knowledge graph of a metal profile extrusion process is determined, the knowledge graph being a relationship structure diagram among the historical models, the historical characteristic parameters, the historical extrusion parameters and the historical extrusion results; according to the target characteristic parameters and the knowledge graph, first extrusion parameters of the target metal profile are determined; the target characteristic parameters are input into a trained metal profile extrusion parameter prediction model for prediction to determine second extrusion parameters of the target metal profile; the metal profile extrusion parameter prediction model is obtained by training a preset neural network based on an improved zebra optimization algorithm and the historical process parameters; according to the first extrusion parameters and the second extrusion parameters, target extrusion parameters corresponding to the target metal profile are determined, so as to quickly and accurately provide an optimal extrusion parameter combination for profiles with different cross-sectional characteristics, significantly reduce extrusion energy consumption while ensuring product quality, and effectively solve the problems of high calculation cost, long cycle and difficulty in coping with new material production demand of traditional optimization methods. An efficient and reliable technical solution is provided for energy saving and emission reduction and process optimization of profile production BRIEF DESCRIPTION OF DRAWINGS

[0040] Figure 1 is a metal profile extrusion parameter determination method flowchart provided by an embodiment of the present application;

[0041] Figure 2 is a knowledge graph of a metal profile extrusion process provided by an optional embodiment of the present application;

[0042] Figure 3 is a 4040g aluminum profile extrusion parameter determination method flowchart provided by an optional embodiment of the present application;

[0043] Figure 4 is a flowchart of an improved zebra optimization algorithm optimizing a BP neural network provided by an optional embodiment of the present application;

[0044] Figure 5 is a module block schematic block diagram of a metal profile extrusion parameter determination device provided by an embodiment of the present application;

[0045] Figure 6 is a schematic block diagram of an electronic device provided by an embodiment of the present application;

[0046] Figure 7 is a schematic block diagram of a computing device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0047] Exemplary embodiments of the present disclosure will be described in greater detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it is understood that the present disclosure can be embodied in various forms without being limited by the embodiments set forth herein. Rather, these embodiments are provided so that the present disclosure will be thorough and complete, and will fully convey the scope of the present disclosure to those skilled in the art.

[0048] In the following description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of various disclosed embodiments. It will be apparent, however, to one skilled in the art that embodiments can be practiced without one or more of these specific details. In other instances, well-known structures and devices are not shown or described in order to avoid unnecessarily obscuring the description of embodiments.

[0049] Reference throughout this specification to "an embodiment" or "the embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment. Thus, the appearances of the phrase "in one embodiment" or "in an embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures, or characteristics can be combined in any suitable manner in one or more embodiments.

[0050] As shown in Figure 1 An embodiment of the present disclosure provides a method for determining extrusion parameters of a metal profile, comprising the following steps:

[0051] Step 11, obtaining a target characteristic parameter of a target metal profile and corresponding historical process parameters in a historical extrusion process, the historical process parameters comprising historical models of a plurality of metal profiles and historical characteristic parameters, historical extrusion parameters and historical extrusion results corresponding to the historical models one by one;

[0052] Step 12, determining a knowledge graph of the metal profile extrusion process according to the historical process parameters, the knowledge graph being a relationship structure diagram among the historical models, the historical characteristic parameters, the historical extrusion parameters and the historical extrusion results;

[0053] Step 13, determining a first extrusion parameter of the target metal profile according to the target characteristic parameter and the knowledge graph;

[0054] Step 14, inputting the target characteristic parameter into a trained metal profile extrusion parameter prediction model for prediction to determine a second extrusion parameter of the target metal profile; the metal profile extrusion parameter prediction model being obtained by training a preset neural network based on an improved zebra optimization algorithm and the historical process parameters;

[0055] Step 15, determining the target extrusion parameter corresponding to the target metal profile according to the first extrusion parameter and the second extrusion parameter.

[0056] In this embodiment, the target feature parameter and the historical feature parameter both include the cross-sectional perimeter L (unit: mm), the cross-sectional area A (unit: mm 2 ), the perimeter-area ratio R (R = L / A) and the maximum size (the diameter of the circumscribed circle of the profile, unit: mm) of the metal profile; the first extrusion parameter, the second extrusion parameter, the target extrusion parameter and the historical extrusion parameter all include the extrusion speed, the profile preheating temperature, the die preheating temperature and the extrusion cylinder preheating temperature; the historical extrusion result includes the extrusion energy consumption and the outlet cross-sectional temperature standard deviation;

[0057] According to the historical process parameters, a knowledge graph of the metal profile extrusion process is constructed to realize effective processing, handling and integration of the complex historical process parameters, to convert the historical data of the extrusion process into a simple and clear network structure and to aggregate a large amount of historical data of the extrusion process, so as to realize fast response and reasoning of the historical data of the extrusion process; the knowledge graph contains the historical model of the profile, the historical feature parameters corresponding to the historical model, the historical extrusion parameters and the historical extrusion results; the knowledge graph is stored in the form of triplets, and the historical extrusion parameters and the historical extrusion results corresponding to each model of the profile stored in the graph are all the optimal historical process parameters. After the target feature parameter of the target metal profile is determined, the first extrusion parameter of the target metal profile can be recommended from the knowledge graph according to the similarity degree between the target feature parameter and the historical feature parameters in the knowledge graph.

[0058] Further, the preset neural network is trained according to the historical feature parameters and the historical extrusion parameters in the historical process parameters, and the model parameters of the preset neural network are optimized by the improved zebra optimization algorithm in the training process of the preset neural network to obtain the trained metal profile extrusion parameter prediction model; here, the preset neural network model can be a BP neural network model; preferably, the key parameters of the BP neural network are: 4 nodes in the input layer, 25 nodes in the hidden layer, 4 nodes in the output layer, and the activation function is selected as the sigmoid function; by optimizing the model parameters of the BP neural network through the improved zebra optimization algorithm, the BP neural network can have the smallest error and the highest fitness on the training data, while the efficiency and accuracy of the model parameter optimization are improved, thereby ensuring the accuracy of the prediction processing of the target feature parameter based on the trained metal profile extrusion parameter prediction model to obtain a more accurate second extrusion parameter;

[0059] Further, the first extrusion parameter and the second extrusion parameter are fused to obtain a target extrusion parameter of a target profile extrusion process; the scheme provided in the above embodiments can quickly and accurately provide an optimal target extrusion parameter for metal profiles with different cross-sectional characteristics, significantly reduce extrusion energy consumption while ensuring product quality, and effectively solve the problems of high calculation cost, long cycle and difficulty in meeting the production needs of new materials of traditional optimization methods; it should be known that the material of the metal profile in the above embodiments has ductility and good plasticity, such as aluminum profiles and corresponding aluminum alloy profiles.

[0060] In an optional embodiment of the present application, the above step 12 can include:

[0061] Step 121, determining an ontology framework of a knowledge graph according to historical models, historical characteristic parameters, historical extrusion parameters and historical extrusion results.

[0062] Specifically, step 121 can include:

[0063] Step 1211, determining profile model entities, characteristic parameter entities, extrusion parameter entities and extrusion result entities according to historical models, historical characteristic parameters, historical extrusion parameters and historical extrusion results.

[0064] Step 1212, top-down sorting the profile model entities, characteristic parameter entities, extrusion parameter entities and extrusion result entities according to a preset hierarchical structure sequence to determine the ontology framework.

[0065] In this embodiment, the historical models, historical characteristic parameters (the circumference, cross-sectional area, circumference-to-area ratio and maximum dimension of the metal profile), historical extrusion parameters (extrusion speed, profile preheating temperature, mold preheating temperature and extrusion cylinder preheating temperature) and historical extrusion results (extrusion energy consumption and outlet cross-sectional temperature standard deviation) are identified as corresponding entities; preferably, the entity recognition here can be through regular expression or named entity algorithm to extract the names of corresponding entities; for each entity, a unique identifier can be determined to facilitate association and reference in the knowledge graph;

[0066] Further, each entity can be arranged in a top-down order according to a preset hierarchical structure sequence, such as arranging the profile model entities as the top layer, the characteristic parameter entities as the second layer, the extrusion parameter entities as the third layer, and the extrusion result entities as the fourth layer; here, the entities on each layer represent a node in the knowledge graph, and the connection edges (connection relationships) between the nodes represent the association relationships between the corresponding entities. It should be known that the profile model can also be taken as the first layer here, and the remaining entities are directly connected to the profile model as the second layer to simplify the knowledge graph structure.

[0067] Further, in an optional embodiment of the present application, the step 12 can further include:

[0068] Step 122, determining the correlation between entities in the ontology framework according to the historical model, the historical characteristic parameter, the historical extrusion parameter and the historical extrusion result corresponding to the structured historical process parameter;

[0069] Step 123, storing the ontology framework, the entity and the correlation between entities according to the preset graph database to determine the knowledge graph corresponding to the metal profile extrusion process.

[0070] In this embodiment, the historical model, the historical characteristic parameter, the historical extrusion parameter and the historical extrusion result are integrated into a csv structure file and knowledge extraction is performed using the transform_to_triples statement, and the historical model and the historical characteristic parameter, the historical model and the historical extrusion parameter, the historical extrusion parameter and the historical extrusion result having a connection relationship are determined, and the corresponding entities are connected after the corresponding connection relationship is determined; further, the Neo4j graph database can be used to store the constructed knowledge graph in the form of triples.

[0071] In an optional embodiment of the present application, the step 13 can include:

[0072] Step 131, determining the similarity between the target characteristic parameter and the historical characteristic parameter corresponding to each historical model in the knowledge graph.

[0073] Specifically, the similarity can be determined by the following formula:

[0074]

[0075] wherein D j represents the similarity between the jth historical existing metal profile in the knowledge graph and the target metal profile characteristic parameter, j = 1, 2,..., 3, m; x i represents the ith target characteristic parameter of the target metal profile, y ij represents the ith historical characteristic parameter of the jth historical existing metal profile in the knowledge graph; n represents the type of characteristic parameter; here, the type of target characteristic parameter of the target metal profile and the type of historical characteristic parameter of the existing metal profile corresponding to each historical model in the knowledge graph are the same, n = 1, 2, 3, 4. It should be understood that there are multiple similarities in this embodiment, and the similarity corresponds to the number of historical models in the knowledge graph.

[0076] Preferably, before the similarity calculation is performed, the target feature parameters of the target metal profile and the historical feature parameters in the knowledge graph need to be normalized to ensure the accuracy of determining the first extrusion parameters; more preferably, the target feature parameters and the historical feature parameters can be normalized by the following formula:

[0077]

[0078] wherein, Normalized Value i represents the normalized i-th target feature parameter or historical feature parameter; Value i represents the original data corresponding to the i-th target feature parameter or historical feature parameter; Min i represents the minimum value of the i-th historical feature parameter in the knowledge graph, Max i represents the maximum value of the i-th historical feature parameter in the knowledge graph. It should be understood that x i , y i in the above similarity calculation formula both represent normalized feature parameters.

[0079] In an optional embodiment of the present application, the above step 13 can further include:

[0080] Step 132, confirming the candidate historical model in the knowledge graph according to the similarity, and determining the first extrusion parameters according to the historical extrusion parameters corresponding to the candidate historical model.

[0081] In this embodiment, the plurality of similarities are arranged in order from small to large, and the historical models corresponding to the top pre-set number of similarities are determined as the candidate historical models;

[0082] Further, the first extrusion parameters are determined according to the historical extrusion parameters corresponding to the candidate historical models; preferably, the first extrusion parameters can be determined based on the following formula and the historical extrusion parameters corresponding to the candidate historical models:

[0083]

[0084] wherein, P KGt represents the t-th extrusion parameter of the first extrusion parameters, t = 1, 2, 3, 4 respectively corresponding to the first extrusion speed, the first profile preheating temperature, the first die preheating temperature and the first extrusion cylinder preheating temperature; p tk represents the t-th historical extrusion parameter of the k-th historical existing metal profile in the pre-set number l with the smallest similarity, k k is the weight, and D kThe similarity between the kth historical existing metal profile in the preset number l of the smallest similarities and the target metal profile (D j The calculation method is the same.

[0085] In an optional embodiment of the present application, the metal profile extrusion parameter prediction model is obtained by training the preset neural network based on the improved zebra optimization algorithm and the historical process parameters, which can include the following steps:

[0086] Step 21, determining an initial parameter population of the preset neural network; the initial parameter population contains multiple groups of parameters, each group of parameters includes initial weights and initial threshold parameters, and the initial parameter population corresponds to an initial individual population containing multiple zebra individuals, each group of parameters corresponds to the position of each zebra individual one by one;

[0087] Step 22, determining a first fitness value of each zebra individual in the initial individual population according to the historical process parameters, each group of parameters in the initial parameter population, and the preset neural network;

[0088] Step 23, iteratively updating the position of the zebra individual in the initial individual population according to the first fitness value and a preset optimization strategy to determine the target position of the zebra individual in the initial individual population;

[0089] Step 24, determining the parameter value corresponding to the target position as the target parameter of the preset neural network, and iteratively training the preset neural network according to the target parameter and the historical process parameters until a preset convergence condition is reached or a first preset iteration number is reached to obtain the metal profile extrusion parameter prediction model.

[0090] In this embodiment, the initial parameter population corresponds to the initial zebra population of the improved zebra optimization algorithm, and each group of parameters in the initial parameter population corresponds to the position vector of each zebra individual in the initial zebra population; further, the preset neural network is trained according to the historical process parameters and the initial weights and initial threshold parameters (the bias of the preset neural network) in each group of parameters; here, the historical extrusion parameters in the historical process parameters are taken as input values, and the extrusion result output by the model is taken as a prediction value; the actual historical extrusion result corresponding to the historical extrusion parameters is taken as a true value, the error between the true value and the prediction value is calculated, and the error is taken as a first fitness value; it should be known that each group of parameters in the initial parameter population corresponds to a first fitness value, each first fitness value represents the initial fitness value of each zebra individual in the initial zebra population, and the smaller the initial fitness value, the better the position of the corresponding zebra individual;

[0091] Further, in an optional embodiment of the present application, the above step 23 can include:

[0092] Step 231, according to the first fitness value, determine the initial individual population in the current optimal position and the first fitness value corresponding to the current optimal position;

[0093] Step 232, according to the preset Levy flight exploration strategy, the preset nonlinear convergence factor and the optimal position, the position of the initial individual population in the zebra individual is updated iteratively until the second preset iteration number is reached, so as to obtain the target position.

[0094] Here, according to the initial fitness value (the first fitness value) of the zebra individual, the zebra individual with the minimum initial fitness value (the minimum error) is selected from the initial zebra population as the current optimal individual, and the position corresponding to the optimal individual is the current optimal position (the optimal solution), and the position of the zebra individual in the initial population is updated iteratively according to the current optimal position to obtain the optimal individual after iteration and the corresponding target position; Specifically:

[0095] In the exploration stage of the improved zebra optimization algorithm: other zebra individuals in the population move according to the current optimal position corresponding to the current optimal individual to update their corresponding initial positions; wherein the step length of other zebra individuals in the population in the moving process can adopt the preset Levy flight exploration strategy (alternating long and short steps) to enhance the global search ability; here, the initial position of the zebra individual is updated by the preset Levy flight exploration strategy, which can be represented as:

[0096]

[0097] Wherein, represents the first updated position of the a-th zebra in the initial zebra population after the preset Levy flight exploration strategy is updated; represents the initial position of the a-th zebra in the initial zebra population; Levy(β) represents a random step length subject to Levy distribution; β represents the parameter of Levy distribution; X best represents the current optimal position.

[0098] In the development stage of the improved zebra optimization algorithm, a preset nonlinear convergence factor can be used to make a small random disturbance to the first updated position of the zebra after the preset Levy flight exploration strategy is updated, so as to update the first updated position and obtain the second updated position, so as to avoid falling into local optimum; here, the first updated position is updated by the preset nonlinear convergence factor, which can be represented as:

[0099]

[0100] Wherein, represents the second updated position after the preset nonlinear convergence factor is updated; F(b) represents the disturbance amplitude factor at the b-th iteration; represents the random disturbance vector generated corresponding to the a-th zebra in the b-th iteration; here, the introduction of Cauchy variation can also be selected to increase randomness and prevent premature convergence;

[0101] Further, the second updated position of the zebra individual is converted into the weight and threshold parameters of the preset neural network, and the preset neural network is trained again, and the corresponding error is calculated as a second fitness value; at this time, the first fitness value and the second fitness value are compared, the second updated position corresponding to the second fitness value smaller than the first fitness value is reserved, and the above-mentioned position iterative updating process through the preset optimization strategy is repeated for the reserved second updated position, until the maximum iteration number is reached; after the iteration is completed, the final updated position corresponding to the zebra individual with the minimum fitness value is selected as the target position, and the target position is decoded into target weight and target threshold parameters in the preset neural network target parameters, and the target weight and target threshold parameters are used to initialize the preset neural network, to obtain a final metal profile extrusion parameter prediction model. In an optional embodiment of the present application, the above-mentioned step 15 can comprise:

[0102] Step 151, the first extrusion parameter and the second extrusion parameter are weighted and fused according to the preset weight value to obtain a target extrusion parameter.

[0103] In this embodiment, the double-channel fusion strategy of the first extrusion parameter recommended based on the feature similarity knowledge reasoning and the model predicted second extrusion parameter not only retains the explainability of the metal profile extrusion field knowledge, but also fully plays the generalization ability of the data model, and guarantees the accuracy and efficiency of obtaining the target extrusion parameter;

[0104] Preferably, the first extrusion parameter and the second extrusion parameter can be weighted and fused by the following formula:

[0105] P fin = ω1×P KGt + ω2×P NNt ;

[0106] Wherein, t=1, 2, 3, 4 represents the first extrusion parameter or the t-th extrusion parameter in the first extrusion parameter; P fin represents the target extrusion parameter; ω1, ω2 represents the preset weight; preferably, equal weight strategy is adopted here, that is, ω1= ω2= 0.5; P KGt =(P KG1 , P KG2 , P KG3 , P KG4 ) respectively correspond to the first extrusion speed, the first profile preheating temperature, the first mold preheating temperature and the first extrusion cylinder preheating temperature in the first extrusion parameter; P NNt =(P KG1P NN2 P NN3 P NN4 ) respectively correspond to the second extrusion speed, the second profile preheating temperature, the second mold preheating temperature and the second extrusion cylinder preheating temperature in the second extrusion parameter.

[0107] As Figure 3 shown, in an optional embodiment of the present application, the method provided in the above embodiment is further illustrated taking 4040g aluminum profile as an example. Wherein, the target feature parameters corresponding to the 4040g aluminum profile are L = 460.01mm, A = 657.1mm 2 , R = 0.7, D = 53.3mm; the specific process is as follows:

[0108] Step 31, using the acquired aluminum profile extrusion energy consumption optimal process parameters and structural feature parameters, an aluminum profile extrusion process knowledge graph is constructed.

[0109] Specifically, the knowledge graph ontology is constructed: defining four entity types of aluminum profile model, feature parameters, process parameters and extrusion results; at the same time, using the relationship to connect the aluminum profile model and the feature parameters; using the relationship to connect the aluminum profile model and the process parameters; using the born relationship to connect the process parameters and the extrusion results.

[0110] Step 32, the acquired aluminum profile extrusion energy consumption optimal process parameters and structural feature parameters and extrusion results are integrated into a csv structure file and knowledge extraction is performed using the transform_to_triples statement, and the Neo4j graph database is used to store the constructed knowledge graph in the form of triples. Note that before starting to construct and store, the required software environment and dependent libraries have been correctly installed, including the neo4j local database.

[0111] Step 33, using the improved zebra optimization algorithm to optimize the BP neural network. Wherein, the key parameters of the BP neural network are: 4 nodes in the input layer, 25 nodes in the hidden layer, 4 nodes in the output layer, the activation function is selected as the sigmoid function, the zebra population number is 20, and the training round is 1000 times. As Figure 4 shown, the specific optimization process is as follows:

[0112] Step 331, initialization: first, a group of zebra positions and speeds need to be initialized to initialize the initial weight and initial threshold parameters of the BP neural network. The position of each zebra represents a set of values of the parameters in the neural network, and the speed represents the update amplitude of the parameters.

[0113] Step 332, fitness evaluation: for the position of each zebra, the fitness of the corresponding neural network needs to be calculated. The fitness is calculated by using the BP neural network to perform forward propagation and error back propagation on the training data, and then evaluated according to the performance loss function of the network.

[0114] Step 333, update the optimal position: according to the fitness evaluation of the zebra, the current optimal position and fitness value are determined. Step 334, update the speed and position: according to the improved behavior pattern of the zebra optimization algorithm, the speed and position of the zebra are updated. This includes updating the speed with the optimal position to move towards the optimal position, and updating the position by the speed.

[0115] Step 335, reach the stop condition: repeat steps 332 to 334 until the stop condition of reaching the maximum number of iterations is met.

[0116] Step 336, optimization result: when the optimization algorithm ends, the parameter value can be extracted from the optimal position and applied to the BP neural network.

[0117] Here, the mean absolute error (MAE), mean square error (MSE), and root mean square error (RMSE) are selected to evaluate the prediction results of the metal profile extrusion parameter prediction model in the present application and the existing BP neural network model, as shown in Table 1. As can be seen from Table 1, the metal profile extrusion parameter prediction model in the present application and the existing BP neural network model have smaller loss and higher convergence accuracy on the data set of the extrusion parameters in the experiment. The MAE, MSE, and RMSE indicators are smaller, and the performance indicators are better than the existing BP neural network model.

[0118] Table 1, evaluation index corresponding to the metal profile extrusion parameter prediction model (model one) in the present application and the existing BP neural network model (model two).

[0119]

[0120] Further, by processing the target feature parameters through multiple different schemes, the recommended target extrusion parameters and the extrusion result parameters determined after the target extrusion parameters are processed are obtained as shown in Table 2. Through experimental verification, the scheme of the present application can reduce energy consumption by more than 6.5% and reduce the standard deviation of the outlet cross-section temperature by more than 16.4% compared with the traditional method, providing an efficient and reliable technical solution for energy saving and emission reduction and process optimization of aluminum profile production.

[0121] Table 2, target extrusion parameters and extrusion results corresponding to each scheme of 4040g

[0122]

[0123]

[0124] The application realizes intelligent optimization and recommendation of new aluminum profile extrusion process parameters by constructing a metal profile extrusion process knowledge graph, combining an improved zebra optimization algorithm to optimize a BP neural network model, and adopting a recommendation strategy that combines feature similarity matching and data-driven prediction. This method can quickly and accurately provide optimal process parameter combinations for aluminum profiles with different cross-sectional features, significantly reducing extrusion energy consumption while ensuring product quality, and effectively solving the problems of high calculation cost, long cycle, and difficulty in meeting the production needs of new materials of traditional optimization methods. It provides an efficient and reliable technical solution for energy saving and emission reduction and process optimization of aluminum profile production.

[0125] The technical advantages of the application mainly lie in three aspects: first, at the method level, the organic unification of knowledge representation and data modeling is realized, and through the synergistic effect of the semantic association network of the knowledge graph and the nonlinear mapping ability of the neural network, a hybrid intelligent recommendation framework with interpretability and predictability is constructed; second, through the improved zebra optimization algorithm, the preset neural network model is optimized through the synergy of the Levy flight strategy, the nonlinear convergence factor and the Cauchy mutation operator, which significantly improves the efficiency and accuracy of neural network parameter optimization; finally, at the application level, a complete technical chain from feature extraction to parameter recommendation is established, forming an extensible process knowledge accumulation and application closed loop, which is suitable for metal profile extrusion process optimization and has wide application prospects

[0126] As shown in Figure 5 The embodiment of the application also provides an extrusion parameter determination device 40 for a metal profile, which comprises:

[0127] An acquisition module 41 is configured to acquire target feature parameters of a target metal profile and corresponding historical process parameters in a historical extrusion process, wherein the historical process parameters comprise historical models of a plurality of metal profiles and historical feature parameters, historical extrusion parameters and historical extrusion results corresponding to the historical models in a one-to-one manner;

[0128] A processing module 42 is configured to determine a knowledge graph of the metal profile extrusion process according to the historical process parameters, wherein the knowledge graph is a relationship structure diagram among the historical models, the historical feature parameters, the historical extrusion parameters and the historical extrusion results; determine a first extrusion parameter of the target metal profile according to the target feature parameters and the knowledge graph; input the target feature parameters into a trained metal profile extrusion parameter prediction model for prediction to determine a second extrusion parameter of the target metal profile; the metal profile extrusion parameter prediction model is obtained by training a preset neural network based on an improved zebra optimization algorithm and the historical process parameters; and determine a target extrusion parameter corresponding to the target metal profile according to the first extrusion parameter and the second extrusion parameter.

[0129] It should be noted that the device is a device corresponding to the metal profile extrusion parameter determination method described above, and all implementation manners in the method embodiment are applicable to this embodiment, and the same technical effects can also be achieved.

[0130] As Figure 6 shown, the embodiment of the present application also provides an electronic device 50, comprising: a memory 51 for storing one or more computer programs; one or more processors 52 for executing one or more computer programs, the computer program being executed by the processor, executing the metal profile extrusion parameter determination method as described above. All implementation manners in the method embodiment are applicable to this embodiment, and the same technical effects can also be achieved. The electronic device 50 is intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown in the present application, their connections and relationships, and their functions are only as examples, and are not intended to limit the implementation of the present application described and / or claimed in the present application.

[0131] As Figure 7 shown, the electronic device 50 is represented as a computing device, or computer system, which can include a CPU 501 (computing unit) that can perform various appropriate actions and processes according to a computer program stored in a ROM 502 (read only memory) or a computer program loaded into a random access RAM 503 (memory) from a storage unit 508. In the RAM 503, various programs and data required for the operation of the device 500 can also be stored. The CPU 501, the ROM 502, and the RAM 503 are connected to each other through a bus 504. An I / O interface 505 (input / output interface) is also connected to the bus 504.

[0132] A plurality of components in the electronic device 500 are connected to the I / O interface 505, including: an input unit 506, such as a keyboard, a mouse, etc.; an output unit 507, such as various types of displays, speakers, etc.; a storage unit 508, such as a magnetic disk, an optical disk, etc.; and a communication unit 509, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 509 allows the device 500 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunications networks.

[0133] The CPU 501 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the CPU 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The CPU 501 performs various methods and processes described above. For example, in some embodiments, the metal profile extrusion parameter determination method 10 can be implemented as a computer software program tangibly embodied in a computer readable storage medium, such as the storage unit 508. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 500 via the ROM 502 and / or the communication unit 509. When the computer program is loaded onto the RAM 503 and executed by the CPU 501, one or more steps of the metal profile extrusion parameter determination method 10 described above can be performed. Alternatively, in other embodiments, the CPU 501 can be configured to perform the metal profile extrusion parameter determination method 10 by any other appropriate means, for example, by means of firmware.

[0134] An embodiment of the present application also provides a computer readable storage medium storing instructions which, when executed on a computer, cause the computer to perform the metal profile extrusion parameter determination method as described above. All implementation manners in the above method embodiments are applicable to this embodiment and can achieve the same technical effects.

[0135] Those skilled in the art can appreciate that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether the functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. A person skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0136] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described system, device and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be described here.

[0137] In the embodiments of the present application, it should be understood that the disclosed apparatus and method can be implemented in other manners. For example, the embodiments of the apparatus described above are merely schematic; for example, the division of the units is only a logical function division; there can be another division manner in actual implementation; for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections between different units, or the among different units, can be indirect couplings or communication connections through some interfaces, devices or units, and can be in electric, mechanical or other forms.

[0138] The units described as separated components can or can not be physically separated, and the components displayed as units can or can not be physical units, i.e., can be located in one place, or can be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purposes of the embodiments of the present application.

[0139] In addition, each functional unit in the various embodiments of the present application can be integrated in a processing unit, or each unit can exist physically as a separate unit, or two or more units can be integrated in one unit.

[0140] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on such an understanding, the technical solutions of the present application essentially or partially contribute to the prior art, or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods in the various embodiments of the present application. The foregoing storage medium includes: U disk, mobile hard disk, ROM, RAM, magnetic disk or optical disk, and various other media that can store program codes.

[0141] Moreover, it is pointed out that in the device and method of the present application, obviously, the components or steps can be decomposed and / or recombined. These decompositions and / or recombination should be considered as equivalent solutions of the present application. Also, the steps of performing the above series of processes can naturally be executed in time sequence according to the order of description, but do not need to be necessarily executed in time sequence. Some steps can be executed in parallel or independently of each other. It can be understood by those skilled in the art that all or any steps or components of the method and device of the present application can be implemented in hardware, firmware, software or a combination thereof in any computing device (including processors, storage media, etc.) or network of computing devices, using the basic programming skills of those skilled in the art upon reading the description of the present application.

[0142] Therefore, the object of the present application can also be achieved by running a program or a set of programs on any computing device. The computing device can be a commonly known general-purpose device. Therefore, the object of the present application can also be achieved only by providing a program product containing program code for implementing the method or device. That is, such a program product also constitutes the present application, and a storage medium storing such a program product also constitutes the present application. Obviously, the storage medium can be any commonly known storage medium or any storage medium developed in the future. It is also pointed out that in the device and method of the present application, obviously, the components or steps can be decomposed and / or recombined. These decompositions and / or recombination should be considered as equivalent solutions of the present application. Also, the steps of performing the above series of processes can naturally be executed in time sequence according to the order of description, but do not need to be necessarily executed in time sequence. Some steps can be executed in parallel or independently of each other.

[0143] The above is the preferred embodiment of the present application. It should be pointed out that for those skilled in the art, several improvements and refinements can be made without departing from the principles of the present application, and these improvements and refinements should also be considered as the protection scope of the present application.

Claims

1. A method for determining extrusion parameters of a metal profile, characterized in that: include: Obtain target characteristic parameters of a target metal profile and corresponding historical process parameters in a historical extrusion process, wherein the historical process parameters include historical models of multiple metal profiles and historical characteristic parameters, historical extrusion parameters, and historical extrusion results corresponding to the historical models; Determine a knowledge graph of the metal profile extrusion process based on the historical process parameters, wherein the knowledge graph is a relationship structure diagram among the historical models, the historical characteristic parameters, the historical extrusion parameters, and the historical extrusion results; Determining a first extrusion parameter of the target metal profile according to the target characteristic parameter and the knowledge graph; Inputting the target characteristic parameters into a trained metal profile extrusion parameter prediction model for prediction to determine the second extrusion parameter of the target metal profile; the metal profile extrusion parameter prediction model is obtained by training a preset neural network based on an improved zebra optimization algorithm and the historical process parameters; A target extrusion parameter corresponding to the target metal profile is determined according to the first extrusion parameter and the second extrusion parameter.

2. The method for determining extrusion parameters of a metal profile according to claim 1, wherein: According to the historical process parameters, a knowledge graph of the metal profile extrusion process is determined, including: Determining an ontology framework of the knowledge graph according to the historical model, the historical feature parameters, the historical extrusion parameters, and the historical extrusion results; Determining the association relationship between entities in the ontology framework according to the historical model, the historical characteristic parameters, the historical extrusion parameters, and the structured historical process parameters corresponding to the historical extrusion results; The ontology framework, the entities, and the relationships between entities are stored according to a preset graph database to determine the knowledge graph corresponding to the metal profile extrusion process.

3. The method for determining extrusion parameters of a metal profile according to claim 2, wherein: Determining an ontology framework of the knowledge graph according to the historical model, the historical feature parameter, the historical extrusion parameter, and the historical extrusion result includes: Determine a profile model entity, a feature parameter entity, an extrusion parameter entity, and an extrusion result entity according to the historical model, the historical feature parameters, the historical extrusion parameters, and the historical extrusion results; According to a preset hierarchical structure order, the profile model entity, the characteristic parameter entity, the extrusion parameter entity and the extrusion result entity are sorted from top to bottom to determine the body framework.

4. The method for determining extrusion parameters of a metal profile according to claim 1, wherein: Determining a first extrusion parameter of the target metal profile according to the target characteristic parameter and the knowledge graph includes: Determining the similarity between the target feature parameter and the historical feature parameter corresponding to each historical model in the knowledge graph; The candidate historical models in the knowledge graph are confirmed according to the similarity, and the first extrusion parameter is determined according to the historical extrusion parameters corresponding to the candidate historical models.

5. The method for determining extrusion parameters of a metal profile according to claim 4, characterized in that: Determining the similarity between the target feature parameter and the historical feature parameter corresponding to each historical model in the knowledge graph includes: The similarity is determined by the following formula: Among them, D j represents the similarity between the characteristic parameters of the j-th historical metal profile and the target metal profile in the knowledge graph, j = 1, 2, ..., 3, m; x i represents the i-th target characteristic parameter of the target metal profile, y ij represents the i-th historical feature parameter of the j-th historical metal profile in the knowledge graph; n represents the type of feature parameter.

6. The method for determining extrusion parameters of a metal profile according to claim 1, wherein: The metal profile extrusion parameter prediction model is obtained by training a preset neural network based on the improved zebra optimization algorithm and the historical process parameters, including: Determine an initial parameter population of the preset neural network; the initial parameter population includes multiple groups of parameters, each group of parameters includes an initial weight and an initial threshold parameter, and the initial parameter population corresponds to an initial individual population including multiple zebra individuals, and each group of parameters corresponds to the position of each zebra individual one-to-one; Determining a first fitness value of each zebra individual in the initial individual population according to the historical process parameters, each set of parameters in the initial parameter population, and the preset neural network; Iteratively updating the positions of the zebra individuals in the initial individual population according to the first fitness value and a preset optimization strategy to determine the target positions of the zebra individuals in the initial individual population; The parameter value corresponding to the target position is determined as the target parameter of the preset neural network, and the preset neural network is iteratively trained according to the target parameter and the historical process parameters until the preset convergence condition or the first preset number of iterations is reached, so as to obtain the metal profile extrusion parameter prediction model.

7. The method for determining extrusion parameters of a metal profile according to claim 6, wherein: Iteratively updating the positions of the zebra individuals in the initial individual population according to the first fitness value and a preset optimization strategy to determine target positions of the zebra individuals in the initial individual population includes: Determining, according to the first fitness value, a current optimal position in the initial individual population and a first fitness value corresponding to the current optimal position; The positions of the zebra individuals in the initial individual population are iteratively updated according to a preset Levy flight exploration strategy, a preset nonlinear convergence factor and the optimal position until a second preset number of iterations is reached to obtain the target position.

8. The method for determining extrusion parameters of a metal profile according to claim 1, wherein: Determining target extrusion parameters corresponding to the target metal profile according to the first extrusion parameters and the second extrusion parameters includes: According to a preset weight value, a weighted fusion process is performed on the first extrusion parameter and the second extrusion parameter to obtain the target extrusion parameter.

9. A device for determining extrusion parameters of metal profiles, characterized in that: include: an acquisition module, configured to acquire target characteristic parameters of a target metal profile and corresponding historical process parameters in a historical extrusion process, wherein the historical process parameters include historical models of multiple metal profiles and historical characteristic parameters, historical extrusion parameters, and historical extrusion results corresponding to the historical models; A processing module is used to determine a knowledge graph of the metal profile extrusion process based on the historical process parameters, where the knowledge graph is a relationship structure diagram among the historical models, the historical characteristic parameters, the historical extrusion parameters, and the historical extrusion results; determine a first extrusion parameter of the target metal profile based on the target characteristic parameters and the knowledge graph; input the target characteristic parameters into a trained metal profile extrusion parameter prediction model for prediction to determine a second extrusion parameter of the target metal profile; the metal profile extrusion parameter prediction model is obtained by training a preset neural network based on an improved zebra optimization algorithm and the historical process parameters; and determine a target extrusion parameter corresponding to the target metal profile based on the first extrusion parameter and the second extrusion parameter.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a program, which implements the method according to any one of claims 1 to 8 when executed by a processor.

Images