Optimization method, device and equipment for blade casting process and storage medium

Abstract

The invention provides an optimization method and device for a blade casting process, equipment and a storage medium, and the method comprises the steps that process parameters of at least one process of blade casting are obtained; generating input sequence data based on the process parameters; inputting the input sequence data into a pre-trained process quality prediction model to obtain a predicted casting qualification rate and a forging defect occurrence probability output by the process quality prediction model; wherein the process quality prediction model is a transformation neural network model, and the process quality prediction model has learned in advance to obtain process parameters based on a blade casting process, and has the capability of predicting the qualification rate of castings and the occurrence probability of forging defects; and optimizing the process parameters based on the predicted qualified rate of the casting and the occurrence probability of the forging defects. According to the technical scheme, the forging qualification rate of the blade can be increased, and the development iteration frequency and period of the turbine blade casting process are reduced.

Description

Technical Field

[0001] The present application relates to the field of blade forging technology, and in particular to an optimization method, device, equipment and storage medium for a blade casting process. Background Art

[0002] In the related art, in order to obtain a blade casting process that meets mass production conditions, multiple iterative verifications are required. Each round of iterative verification requires a long cycle and consumes a lot of manpower and resource costs. Summary of the invention

[0003] The present application aims to solve one of the technical problems in the related art at least to some extent.

[0004] In a first aspect, the present application proposes a method for optimizing a blade casting process, the method comprising: obtaining process parameters of at least one process of blade casting; generating input sequence data based on the process parameters; inputting the input sequence data into a pre-trained process quality prediction model to obtain predicted casting qualification rate and forging defect occurrence probability output by the process quality prediction model; wherein the process quality prediction model is a transformation neural network model, and the process quality prediction model has pre-learned the ability to predict the casting qualification rate and the forging defect occurrence probability based on the process parameters of the blade casting process; based on the predicted casting qualification rate and the forging defect occurrence probability, the process parameters are optimized.

[0005] In one implementation, generating the input sequence data based on the process parameters includes: arranging the process parameters in a sequence of the processes to obtain the input sequence data.

[0006] In one implementation, the process quality prediction model is pre-trained through the following steps: obtaining multiple sample process parameters corresponding to each process in at least one process of blade casting; arranging and combining the sample process parameters corresponding to different processes to obtain multiple sample input sequence data; based on prior knowledge, obtaining the forging qualified sample probability and the casting defect occurrence sample probability corresponding to each of the sample input sequence data; inputting the sample input sequence data into the initial process quality prediction model to obtain the initial predicted casting qualification rate and initial forging defect occurrence probability output by the initial process quality prediction model; obtaining the first difference between the initial casting qualification rate and the forging qualified sample probability, and the second difference between the initial forging defect occurrence probability and the casting defect occurrence sample probability; using the back propagation algorithm in combination with the first difference, the second difference and a preset loss function to optimize the weights and bias values ​​of the initial process quality prediction model to obtain the process quality prediction model.

[0007] In one implementation, the process includes at least one of the following: mold design; ceramic core preparation; wax pressing; tree assembly; shell making; dewaxing; firing; and pouring.

[0008] In an optional implementation, the process parameters corresponding to the mold design include at least one of the following: material shrinkage, comprehensive wax shrinkage, casting shrinkage; the process parameters corresponding to the ceramic core preparation include at least one of the following: strength, deflection, size, porosity; the process parameters corresponding to the wax pressing include at least one of the following: wax liquid temperature, template temperature, wax injection amount, wax injection flow, wax pressing time, wax pressing pressure, holding time, holding pressure; the process parameters corresponding to the group tree include at least one of the following: free end parameters, blade root orientation, seeding bar size, platinum wire core support parameters; the process parameters corresponding to the shell making include at least one of the following: mold shell strength, mold shell layer number, mold shell composition, drying time; the process parameters corresponding to the dewaxing include at least one of the following: dewaxing temperature, pressure, dewaxing time, wax discharge port parameters; the process parameters corresponding to the firing include at least one of the following: temperature curve, firing temperature, firing time; the process parameters corresponding to the pouring include at least one of the following: pouring temperature, pulling speed, insulation baffle gap, preheating temperature, pouring time, cooling time.

[0009] In an optional implementation, the forging defects include at least one of the following: recrystallization; broken core; leaking core; eccentric core; iron inclusion; steel leakage; and cracks.

[0010] In the second aspect, the present application proposes an optimization device for a blade casting process, the device comprising: an acquisition module for acquiring process parameters of at least one process of blade casting; a first processing module for generating input sequence data based on the process parameters; a second processing module for inputting the input sequence data into a pre-trained process quality prediction model to obtain the predicted casting qualification rate and the probability of occurrence of forging defects output by the process quality prediction model; wherein the process quality prediction model is a transformation neural network model, and the process quality prediction model has pre-learned to obtain the ability to predict the casting qualification rate and the probability of occurrence of forging defects based on the process parameters of the blade casting process; a third processing module for optimizing the process parameters based on the predicted casting qualification rate and the probability of occurrence of the forging defects.

[0011] In one implementation, the first processing module may be used to: arrange the process parameters according to the sequence of the processes to obtain the input sequence data.

[0012] In one implementation, the process quality prediction model is pre-trained through the following steps: obtaining multiple sample process parameters corresponding to each process in at least one process of blade casting; arranging and combining the sample process parameters corresponding to different processes to obtain multiple sample input sequence data; based on prior knowledge, obtaining the forging qualified sample probability and the casting defect occurrence sample probability corresponding to each of the sample input sequence data; inputting the sample input sequence data into the initial process quality prediction model to obtain the initial predicted casting qualification rate and initial forging defect occurrence probability output by the initial process quality prediction model; obtaining the first difference between the initial casting qualification rate and the forging qualified sample probability, and the second difference between the initial forging defect occurrence probability and the casting defect occurrence sample probability; using the back propagation algorithm in combination with the first difference, the second difference and a preset loss function to optimize the weights and bias values ​​of the initial process quality prediction model to obtain the process quality prediction model.

[0013] In one implementation, the process includes at least one of the following: mold design; ceramic core preparation; wax pressing; tree assembly; shell making; dewaxing; firing; and pouring.

[0014] In an optional implementation, the process parameters corresponding to the mold design include at least one of the following: material shrinkage, comprehensive wax shrinkage, casting shrinkage; the process parameters corresponding to the ceramic core preparation include at least one of the following: strength, deflection, size, porosity; the process parameters corresponding to the wax pressing include at least one of the following: wax liquid temperature, template temperature, wax injection amount, wax injection flow, wax pressing time, wax pressing pressure, holding time, holding pressure; the process parameters corresponding to the group tree include at least one of the following: free end parameters, blade root orientation, seeding bar size, platinum wire core support parameters; the process parameters corresponding to the shell making include at least one of the following: mold shell strength, mold shell layer number, mold shell composition, drying time; the process parameters corresponding to the dewaxing include at least one of the following: dewaxing temperature, pressure, dewaxing time, wax discharge port parameters; the process parameters corresponding to the firing include at least one of the following: temperature curve, firing temperature, firing time; the process parameters corresponding to the pouring include at least one of the following: pouring temperature, pulling speed, insulation baffle gap, preheating temperature, pouring time, cooling time.

[0015] In an optional implementation, the forging defects include at least one of the following: recrystallization; broken core; leaking core; eccentric core; iron inclusion; steel leakage; and cracks.

[0016] In a third aspect, the present application proposes an electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the optimization method of the blade casting process as described in the first aspect.

[0017] In a fourth aspect, the present application proposes a computer-readable storage medium for storing instructions, which, when executed, enables the method described in the first aspect to be implemented.

[0018] In a fifth aspect, the present application proposes a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the method for optimizing the blade casting process as described in the first aspect.

[0019] The blade casting process optimization method, device, equipment and storage medium provided in the present application can generate input sequence data based on the process parameters corresponding to the blade forging process, and input the input sequence data into a pre-trained process quality prediction model to obtain the corresponding predicted casting qualification rate and forging defect occurrence probability, so as to optimize the process parameters based on the predicted casting qualification rate and forging defect occurrence probability. It can improve the forging qualification rate of blades and reduce the iteration frequency and cycle of turbine blade casting process development.

[0020] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0022] Figure 1 It is a schematic flow chart of a blade casting process optimization method provided in an embodiment of the present application;

[0023] Figure 2 It is a structural schematic diagram of a process quality prediction model provided in an embodiment of the present application;

[0024] Figure 3 It is a flowchart of a process quality prediction model training method provided in an embodiment of the present application;

[0025] Figure 4 It is a structural schematic diagram of an optimization device for a blade casting process provided in an embodiment of the present application;

[0026] Figure 5 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0027] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0028] The following describes the optimization method and device of the blade casting process according to the embodiment of the present application with reference to the accompanying drawings.

[0029] It should be noted that the blade casting process optimization method and device provided in the embodiments of the present application can be used to optimize the forging process of heavy-duty gas turbine turbine blades.

[0030] Figure 1 FIG. 1 is a flow chart of a blade casting process optimization method provided in an embodiment of the present application. Figure 1 As shown, the method may include but is not limited to the following steps:

[0031] Step S101: obtaining process parameters of at least one process of blade casting.

[0032] Exemplarily, process parameters of the steps that affect the casting qualification rate and may cause casting defects in the blade casting process are obtained.

[0033] In some embodiments, the above process includes at least one of the following: mold design; ceramic core preparation; wax pressing; tree assembly; shell making; dewaxing; firing; and pouring.

[0034] In an optional implementation, the process parameters corresponding to the mold design include at least one of the following: material shrinkage, comprehensive wax shrinkage, casting shrinkage, and dimensional accuracy.

[0035] Exemplarily, by considering the shrinkage rate of the material, the shrinkage rate of the wax, the shrinkage rate of casting, etc., the total shrinkage rate is obtained, so as to design a suitable mold size according to the above shrinkage rate, so as to obtain a casting of suitable size and determine whether the dimensional accuracy meets the requirements of the subsequent casting dimensional accuracy.

[0036] In an optional implementation, the process parameters corresponding to the preparation of the ceramic core include at least one of the following: strength, deflection, size, and porosity.

[0037] In an optional implementation, the process parameters corresponding to wax compression include at least one of the following: wax liquid temperature, template temperature, wax injection amount, wax injection flow rate, wax compression time, wax compression pressure, holding time, and holding pressure.

[0038] In an optional implementation, the process parameters corresponding to the group tree include at least one of the following: free end parameters, blade root orientation, seeding bar size, and platinum wire core support parameters.

[0039] The above-mentioned free end parameters include the free end position, the number of free ends and the free end gap distance.

[0040] Among them, the above-mentioned platinum wire core support parameters include platinum wire core support size, platinum wire core support position and the number of platinum wire core supports.

[0041] In an optional implementation, the process parameters corresponding to shell making include at least one of the following: shell strength, shell layer number, shell composition, and drying time.

[0042] In an optional implementation, the process parameters corresponding to dewaxing include at least one of the following: dewaxing temperature, pressure, dewaxing time, and wax outlet parameters.

[0043] In an optional implementation, the process parameters corresponding to the calcination include at least one of the following: a temperature curve, a calcination temperature, and a calcination time.

[0044] The temperature curve includes a temperature rise curve and a temperature drop curve.

[0045] In an optional implementation, the process parameters corresponding to the pouring include at least one of the following: pouring temperature, pulling speed, insulation baffle gap, preheating temperature, pouring time, and cooling time.

[0046] Step S102: Generate input sequence data based on process parameters.

[0047] In some embodiments, the process parameters may be arranged in a sequence between the processes to obtain input sequence data.

[0048] Exemplarily, according to the sequence of different processes in the blade casting process, the process parameters corresponding to different processes are arranged to obtain input sequence data.

[0049] Step S103: inputting the input sequence data into a pre-trained process quality prediction model to obtain the predicted casting qualification rate and forging defect occurrence probability output by the process quality prediction model.

[0050] Among them, the process quality prediction model is a transformation neural network model. The process quality prediction model has pre-learned the process parameters based on the blade casting process and has the ability to predict the casting qualification rate and the probability of forging defects.

[0051] Among them, the forging defects include at least one of the following: recrystallization, broken core, leaking core, eccentric core, iron inclusion, steel leakage, and cracks.

[0052] As an example, see Figure 2 , Figure 2 Schematic diagram of a process quality prediction model provided in an embodiment of the present application. Figure 2 As shown, an input data sequence consisting of process parameters can be input into a yield prediction model, so that each process parameter in the input data sequence is input into a node of the model input layer for processing.

[0053] Step S104: Optimizing process parameters based on the predicted casting qualification rate and the probability of occurrence of forging defects.

[0054] Exemplarily, the process parameters are optimized and adjusted based on the predicted casting qualification rate and the probability of occurrence of forging defects, and the optimized and adjusted process parameters are input into the process quality prediction model again to obtain new predicted casting qualification rate and the probability of occurrence of forging defects, and the above steps are repeated until the predicted casting qualification rate and the probability of occurrence of forging defects meet the requirements.

[0055] It is understandable that the process parameters of different processes may lead to the occurrence of different forging defects. Therefore, the process parameters of the corresponding processes can be adjusted according to the probability of occurrence of different forging defects.

[0056] For example, when the strength of the ceramic core is too high, it is easy to cause recrystallization in the inner cavity of the casting, making it difficult to remove the core. If the strength of the ceramic core is low, it is easy to cause wax core breakage, dewaxing cracks, baking core breakage, and pouring core breakage; excessive deflection is easy to cause core deviation and core leakage after pouring, and it is difficult to control the size. If the deflection is too small, it is easy to break the core during pouring. If the process quality prediction model predicts a high probability of core breakage, the strength of the ceramic core can be adjusted.

[0057] It is understandable that the above-mentioned blade casting process optimization method can be executed in multiple cycles to optimize the process parameters of the forging process for multiple iterations until the predicted casting qualification rate and the probability of occurrence of forging defects meet the requirements.

[0058] By implementing the embodiments of the present application, input sequence data can be generated based on the process parameters corresponding to the blade forging process, and the input sequence data can be input into the pre-trained process quality prediction model to obtain the corresponding predicted casting qualification rate and forging defect occurrence probability, so as to optimize the process parameters based on the predicted casting qualification rate and forging defect occurrence probability. It can improve the forging qualification rate of blades and reduce the iteration frequency and cycle of turbine blade casting process development.

[0059] See also Figure 3 , Figure 3 is a flow chart of a process quality prediction model training method provided in an embodiment of the present application, such as Figure 3 As shown, the method may include but is not limited to the following steps:

[0060] Step S301: obtaining a plurality of sample process parameters corresponding to each process in at least one process of blade casting.

[0061] Exemplarily, the processes that affect the casting qualification rate and may cause casting defects in the blade casting process are determined, and a plurality of different process parameters corresponding to each process are obtained as sample process parameters.

[0062] Step S302: Arrange and combine sample process parameters corresponding to different processes to obtain a plurality of sample input sequence data.

[0063] Exemplarily, one sample process parameter corresponding to each process step is selected respectively, and arranged in the order of the processes to obtain a sample input sequence data, thereby obtaining a plurality of sample data sequence data.

[0064] It should be noted that the sample process parameters contained in different sample input sequence data are not completely the same.

[0065] Step S303: Based on prior knowledge, the probability of qualified forging samples and the probability of casting defect occurrence samples corresponding to each sample input sequence data are obtained.

[0066] Exemplarily, based on the prior knowledge accumulated in the blade casting history, the probability of a qualified forging sample and the probability of a casting defect occurring sample corresponding to each sample input sequence data are obtained.

[0067] Step S304: inputting the sample input sequence data into the initial process quality prediction model to obtain the initial predicted casting qualification rate and initial forging defect occurrence probability output by the initial process quality prediction model.

[0068] Step S305: obtaining a first difference between the initial casting qualification rate and the forging qualified sample probability, and a second difference between the initial forging defect occurrence probability and the casting defect occurrence sample probability.

[0069] It can be understood that the above-mentioned second difference is at least one, and each forging defect corresponds to a second difference.

[0070] Step S306: using a back propagation algorithm in combination with the first difference, the second difference and a preset loss function to optimize the weights and bias values ​​of the initial process quality prediction model to obtain a process quality prediction model.

[0071] Exemplarily, the square sum of the first difference and the second difference is obtained as the loss function, the loss function is passed into the back propagation process, and the partial derivative of the loss function with respect to each neuron weight is obtained layer by layer as the gradient of the objective function with respect to the weight. The weight of each neuron is optimized according to the gradient, and the above steps are repeated again based on the optimized model until the error reaches the expected value, and the initial process quality prediction model when the error reaches the expected value is used as the above process quality prediction model.

[0072] By implementing the embodiments of the present application, multiple sample input sequence data can be generated based on sample process parameters corresponding to different processes, so that the sample input sequence data can be used as training data, and the initial forging pass rate prediction model can be trained using the back propagation method to obtain the forging pass rate prediction model, so as to optimize the blade forging process based on the forging pass rate prediction model, thereby reducing the iteration frequency and cycle of turbine blade casting process development.

[0073] See also Figure 4 , Figure 4 Schematic diagram of the structure of an optimization device for blade casting process provided in an embodiment of the present application. Figure 4 As shown, the device 400 includes: an acquisition module 401, which is used to acquire process parameters of at least one process of blade casting; a first processing module 402, which is used to generate input sequence data based on the process parameters; a second processing module 403, which is used to input the input sequence data into a pre-trained process quality prediction model to obtain the predicted casting qualification rate and the probability of forging defect occurrence output by the process quality prediction model; wherein the process quality prediction model is a transformation neural network model, and the process quality prediction model has pre-learned to obtain the process parameters based on the blade casting process, and the ability to predict the casting qualification rate and the probability of forging defect occurrence; a third processing module 404, which is used to optimize the process parameters based on the predicted casting qualification rate and the probability of forging defect occurrence.

[0074] In one implementation, the first processing module 402 may be used to: arrange the process parameters according to the sequence of processes to obtain input sequence data.

[0075] In one implementation, the process quality prediction model is pre-trained through the following steps: obtaining multiple sample process parameters corresponding to each process in at least one process of blade casting; arranging and combining the sample process parameters corresponding to different processes to obtain multiple sample input sequence data; based on prior knowledge, obtaining the forging qualified sample probability and the casting defect occurrence sample probability corresponding to each sample input sequence data; inputting the sample input sequence data into the initial process quality prediction model to obtain the initial predicted casting qualification rate and the initial forging defect occurrence probability output by the initial process quality prediction model; obtaining the first difference between the initial casting qualification rate and the forging qualified sample probability, and the second difference between the initial forging defect occurrence probability and the casting defect occurrence sample probability; using a back propagation algorithm combined with the first difference, the second difference and a preset loss function to optimize the weights and bias values ​​of the initial process quality prediction model to obtain the process quality prediction model.

[0076] In one implementation, the process includes at least one of the following: mold design; ceramic core preparation; wax pressing; tree assembly; shell making; dewaxing; firing; and pouring.

[0077] In an optional implementation, the process parameters corresponding to the mold design include at least one of the following: material shrinkage, comprehensive wax shrinkage, and casting shrinkage; the process parameters corresponding to the ceramic core preparation include at least one of the following: strength, deflection, size, and porosity; the process parameters corresponding to wax pressing include at least one of the following: wax liquid temperature, template temperature, wax injection amount, wax injection flow, wax pressing time, wax pressing pressure, holding time, and holding pressure; the process parameters corresponding to the tree assembly include at least one of the following: free end parameters, blade root orientation, seeding bar size, and platinum wire core support parameters; the process parameters corresponding to shell making include at least one of the following: mold shell strength, number of mold shell layers, mold shell composition, and drying time; the process parameters corresponding to dewaxing include at least one of the following: dewaxing temperature, pressure, dewaxing time, and wax outlet parameters; the process parameters corresponding to firing include at least one of the following: temperature curve, firing temperature, and firing time; the process parameters corresponding to pouring include at least one of the following: pouring temperature, pulling speed, insulation baffle gap, preheating temperature, pouring time, and cooling time.

[0078] In an optional implementation, the forging defects include at least one of the following: recrystallization; broken core; leaking core; eccentric core; iron inclusion; steel leakage; and cracks.

[0079] Through the device of the embodiment of the present application, input sequence data can be generated based on the process parameters corresponding to the blade forging process, and the input sequence data can be input into the pre-trained process quality prediction model to obtain the corresponding predicted casting qualification rate and forging defect occurrence probability, so as to optimize the process parameters based on the predicted casting qualification rate and forging defect occurrence probability. It can improve the forging qualification rate of the blade and reduce the iteration frequency and cycle of turbine blade casting process development.

[0080] It should be noted that the aforementioned explanation of the embodiment of the method for optimizing the blade casting process is also applicable to the device for optimizing the blade casting process of this embodiment, and will not be repeated here.

[0081] In order to implement the above embodiment, the present application also proposes an electronic device. Figure 5 , Figure 5 Schematic diagram of the structure of the electronic device provided in the embodiment of the present application. Figure 5 As shown, the electronic device 500 includes: a processor 501, and a memory 502 communicatively connected to the processor 501; the memory 502 stores computer-executable instructions; the processor 501 executes the computer-executable instructions stored in the memory to implement the method provided in the aforementioned embodiment.

[0082] In order to implement the above embodiments, the present application also proposes a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the methods provided by the above embodiments.

[0083] In order to implement the above embodiments, the present application also proposes a computer program product, including a computer program, which implements the methods provided by the above embodiments when executed by a processor.

[0084] In the description of this application, unless otherwise specified, “ / ” means or, for example, A / B can mean A or B; “and / or” in this article is merely a way to describe the association relationship of associated objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone.

[0085] It should be noted that personal information from users should be collected for legitimate and reasonable purposes and should not be shared or sold outside of these legitimate uses. In addition, such collection / sharing should be carried out after receiving the user's informed consent, including but not limited to notifying the user to read the user agreement / user notice and sign the agreement / authorization including authorization of relevant user information before the user uses the function. In addition, any necessary steps should be taken to protect and safeguard access to such personal information data and ensure that others who have access to personal information data comply with its privacy policy and procedures.

[0086] In the description of the aforementioned embodiments, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0087] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0088] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0089] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute the instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0090] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0091] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0092] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0093] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for optimizing a blade casting process, characterized in that: include: Acquiring process parameters of at least one step of blade casting; generating input sequence data based on the process parameters; Inputting the input sequence data into a pre-trained process quality prediction model to obtain the predicted casting qualification rate and forging defect occurrence probability output by the process quality prediction model; wherein the process quality prediction model is a transformation neural network model, and the process quality prediction model has been pre-learned to obtain the process parameters based on the blade casting process, and has the ability to predict the casting qualification rate and forging defect occurrence probability; The process parameters are optimized based on the predicted casting qualification rate and the occurrence probability of the forging defects.

2. The method according to claim 1, characterized in that The step of generating input sequence data based on the process parameters comprises: The process parameters are arranged in a sequence between the processes to obtain the input sequence data.

3. The method according to claim 1, characterized in that The process quality prediction model is pre-trained by the following steps: Acquire a plurality of sample process parameters corresponding to each process in at least one process of blade casting; Arrange and combine the sample process parameters corresponding to the different steps to obtain a plurality of sample input sequence data; Based on prior knowledge, obtaining the forging qualified sample probability and casting defect occurrence sample probability corresponding to each of the sample input sequence data; Inputting the sample input sequence data into an initial process quality prediction model to obtain an initial predicted casting qualification rate and an initial forging defect occurrence probability output by the initial process quality prediction model; Obtaining a first difference between the initial casting qualified rate and the forging qualified sample probability, and a second difference between the initial forging defect occurrence probability and the casting defect occurrence sample probability; A back propagation algorithm is used in combination with the first difference, the second difference and a preset loss function to optimize the weights and bias values ​​of the initial process quality prediction model to obtain the process quality prediction model.

4. The method according to any one of claims 1 to 3, characterized in that The process comprises at least one of the following: Mould design; Ceramic core preparation; Pressed wax; Group Tree; Shell making; Dewaxing; Roasting; pouring.

5. The method according to claim 4, characterized in that: The process parameters corresponding to the mold design include at least one of the following: material shrinkage, comprehensive wax shrinkage, and casting shrinkage; The process parameters corresponding to the preparation of the ceramic core include at least one of the following: strength, deflection, size, and porosity; The process parameters corresponding to the wax pressing include at least one of the following: wax liquid temperature, template temperature, wax injection amount, wax injection flow rate, wax pressing time, wax pressing pressure, holding time, and holding pressure; The process parameters corresponding to the group tree include at least one of the following: free end parameters, blade root orientation, seeding bar size, platinum wire core support parameters; The process parameters corresponding to the shell making include at least one of the following: shell strength, shell layer number, shell composition, and drying time; The process parameters corresponding to the dewaxing include at least one of the following: dewaxing temperature, pressure, dewaxing time, and wax outlet parameters; The process parameters corresponding to the calcination include at least one of the following: temperature curve, calcination temperature, calcination time; The process parameters corresponding to the pouring include at least one of the following: pouring temperature, pulling speed, insulation baffle gap, preheating temperature, pouring time, and cooling time.

6. The method according to claim 1, characterized in that The forging defects include at least one of the following: Recrystallization; Broken core; Leaky core; eccentric; Clamp iron; Steel leakage; crack.

7. An optimization device for blade casting process, characterized in that: include: An acquisition module, used for acquiring process parameters of at least one process of blade casting; A first processing module, configured to generate input sequence data based on the process parameters; The second processing module is used to input the input sequence data into a pre-trained process quality prediction model to obtain the predicted casting qualification rate and forging defect occurrence probability output by the process quality prediction model; wherein the process quality prediction model is a transformation neural network model, and the process quality prediction model has been pre-learned to obtain the process parameters based on the blade casting process, and has the ability to predict the casting qualification rate and forging defect occurrence probability; The third processing module is used to optimize the process parameters based on the predicted casting qualification rate and the occurrence probability of the forging defects.

8. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement the method according to any one of claims 1 to 6.

10. A computer program product, characterized in that The method comprises a computer program, which implements the method according to any one of claims 1 to 6 when being executed by a processor.

Images