Aircraft engine casing process constant temperature and humidity control method and system thereof

Abstract

This invention belongs to the field of smart factory technology. It provides a method and system for constant temperature and humidity control in the manufacturing process of aero-engine casings. The method includes: controlling a high-definition camera to capture high-definition real-scene images of the manufacturing workshop; extracting several key images related to aero-engine casing manufacturing from the high-definition real-scene images; using a large language model to perform semantic understanding on the key images to obtain the type of aero-engine casing; determining the target temperature and target humidity based on the type of aero-engine casing; and controlling the constant temperature and humidity control system to adjust the temperature and humidity in the manufacturing workshop to the target temperature and humidity. The solution of this invention can automatically determine the target temperature and target humidity suitable for the current manufacturing type of aero-engine casing through image recognition technology and semantic analysis technology, thereby achieving automatic temperature and humidity control and greatly improving the intelligence level of constant temperature and humidity control in the manufacturing workshop.

Description

Technical Field

[0001] This invention relates to the field of smart factory technology, and more specifically, to a method and system for constant temperature and humidity control in the shell manufacturing process of aero-engines. Background Technology

[0002] The aircraft engine casing is an important component of an aircraft engine. It not only supports various internal components such as the fuel system, lubrication system, and control system, but also has a direct impact on the engine's performance and safety.

[0003] In the manufacturing process of aero-engine casings, strict control of the manufacturing environment's temperature and humidity is required, as these factors directly affect material properties and processing quality. Existing aero-engine casing manufacturing workshops are equipped with constant temperature and humidity control systems. These systems maintain suitable temperature and humidity levels within the workshop. However, the control parameters in these systems are set based on a specific type of aero-engine casing. When manufacturing other types of aero-engine casings in the same workshop, the control parameters in the constant temperature and humidity control system need to be manually adjusted, which is labor-intensive and inefficient. Summary of the Invention

[0004] To address at least one of the aforementioned technical problems, this invention specifically provides a method, system, electronic device, computer storage medium, and computer program product for constant temperature and humidity control in aero-engine casing manufacturing processes, thereby improving the efficiency of constant temperature and humidity control in aero-engine casing manufacturing workshops.

[0005] This invention provides a method for controlling the temperature and humidity during the manufacturing process of an aero-engine casing, comprising the following steps:

[0006] Control a high-definition camera to capture high-definition real-scene images of the manufacturing workshop, and extract several key images related to the shell manufacturing of aero-engines from the high-definition real-scene images;

[0007] The key images are semantically understood using a large language model to obtain the type of aircraft engine casing, and the target temperature and target humidity are determined based on the type of aircraft engine casing.

[0008] The constant temperature and humidity control system regulates the temperature in the manufacturing workshop to the target temperature and the humidity in the manufacturing workshop to the target humidity.

[0009] Furthermore, the control of the high-definition camera to capture high-definition real-scene images of the manufacturing workshop includes:

[0010] Historical data is acquired and the locations of each key historical image are extracted from it. Each of these locations is then mapped onto a first high-definition real-scene image of the manufacturing workshop to obtain the corresponding mapped locations.

[0011] Based on the distribution of each of the mapping positions in the first high-definition real-scene image, a closed shape enclosing all the mapping positions is drawn. A second high-definition real-scene image is delineated from the first high-definition real-scene image based on the closed shape, and the second high-definition real-scene image is determined as the high-definition real-scene image of the manufacturing workshop.

[0012] Furthermore, the extraction of several key images related to aircraft engine casing manufacturing from the high-definition real-scene images includes:

[0013] Retrieve from the database the product appearance characteristics, raw material appearance characteristics, and equipment appearance characteristics related to aero-engine shell manufacturing for this manufacturing workshop;

[0014] Based on the product appearance features, the raw material appearance features, and the equipment appearance features, several objects are identified from the high-definition real-scene image, and the area image where each object is located is determined as the key image.

[0015] Furthermore, the step of using a large language model to perform semantic understanding on the key images to obtain the type of aircraft engine casing includes:

[0016] The large language model is used to perform semantic understanding on the key images to obtain the object attributes of each object.

[0017] If each of the object attributes contains attribute information of an aircraft engine housing product, then the first aircraft engine housing type is determined based on the attribute information of the aircraft engine housing product. Then, the first aircraft engine housing type is matched and analyzed with the attributes of other objects. If the matching analysis is successful, the first aircraft engine housing type is determined as the aircraft engine housing type.

[0018] If none of the object attributes contain an aircraft engine casing product or the matching analysis fails, then each object attribute is packaged into a query statement, and the query statement is submitted to the large language model. The large language model outputs several second aircraft engine casing types and their corresponding predicted probabilities, and the second aircraft engine casing type with the highest predicted probability is determined as the aircraft engine casing type.

[0019] Further, determining the target temperature and target humidity based on the type of the aircraft engine casing includes:

[0020] The type of aircraft engine casing is compared with a preset lookup table to obtain the matching target temperature and target humidity.

[0021] Furthermore, before determining the target temperature and target humidity based on the type of the aircraft engine casing, the method further includes:

[0022] The type of aircraft engine casing is output to the relevant personnel, and after receiving confirmation from the relevant personnel, it is output again until the number of confirmations received from the relevant personnel reaches a preset number.

[0023] The preset number of times is determined as follows: the number of sets of target temperature and target humidity executed by the constant temperature and humidity control system of the manufacturing workshop is obtained, and the preset number of times is calculated based on the number of sets and the corresponding negative correlation function.

[0024] This invention provides a constant temperature and humidity control system for the shell manufacturing process of aero-engines, the system comprising a first control module, a second control module, and a regulation module;

[0025] The first control module is used to control a high-definition camera to capture high-definition real-scene images of the manufacturing workshop, and extract several key images related to the shell manufacturing of aero-engines from the high-definition real-scene images.

[0026] The second control module is used to perform semantic understanding on the key image using a large language model to obtain the type of aircraft engine casing, and determine the target temperature and target humidity based on the type of aircraft engine casing.

[0027] The control module is used to control the constant temperature and humidity control system to adjust the temperature in the manufacturing workshop to the target temperature and the humidity in the manufacturing workshop to the target humidity.

[0028] The present invention provides an electronic device, comprising: a memory storing executable program code; a processor coupled to the memory; the processor calling the executable program code stored in the memory to execute the method as described in any of the preceding claims.

[0029] The present invention provides a computer storage medium storing a computer program, which is executed by a processor as described in any of the preceding methods.

[0030] The present invention provides a computer program product in which the computer program, when executed, implements the method described in any of the preceding claims.

[0031] Compared to the method of manually adjusting the target temperature and humidity of the constant temperature and humidity control system involved in the background technology, the solution of the present invention can automatically determine the target temperature and humidity suitable for the current manufacturing type of the aero-engine casing through image recognition technology and semantic analysis technology, thereby realizing automatic temperature and humidity control and greatly improving the intelligence level of constant temperature and humidity control in the manufacturing workshop. Attached Figure Description

[0032] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0033] Figure 1 This is a schematic flowchart of a method for controlling the constant temperature and humidity in the shell manufacturing process of an aero-engine, as disclosed in an embodiment of the present invention.

[0034] Figure 2 This is a schematic diagram of the structure of a constant temperature and humidity control system for the shell manufacturing process of an aero-engine, as disclosed in an embodiment of the present invention. Detailed Implementation

[0035] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0036] like Figure 1 As shown, this embodiment of the invention provides a method for controlling the constant temperature and humidity in the shell manufacturing process of an aero-engine, including the following steps:

[0037] Control a high-definition camera to capture high-definition real-scene images of the manufacturing workshop, and extract several key images related to the shell manufacturing of aero-engines from the high-definition real-scene images;

[0038] The key images are semantically understood using a large language model to obtain the type of aircraft engine casing, and the target temperature and target humidity are determined based on the type of aircraft engine casing.

[0039] The constant temperature and humidity control system regulates the temperature in the manufacturing workshop to the target temperature and the humidity in the manufacturing workshop to the target humidity.

[0040] This invention deploys high-definition cameras in an aero-engine casing manufacturing workshop. When temperature and humidity control is required, the cameras capture high-definition real-world images of the workshop, extracting key images related to the aero-engine casing production. These key images can be related to the aero-engine casing product, manufacturing raw materials, manufacturing machinery, etc. Next, a large language model is used to perform semantic understanding on these key images, thereby determining the type of aero-engine casing that the workshop is about to produce or is currently producing. Since the optimal temperature and humidity for ensuring the quality of different aero-engine casing types are preset, the target temperature and humidity can be quickly determined through comparative calculations. Finally, the temperature and humidity control system deployed in the manufacturing workshop is controlled to adjust the temperature to the target temperature and humidity to the target humidity, thereby ensuring that the temperature and humidity environment in the manufacturing workshop meets the environmental requirements corresponding to the type of aero-engine casing.

[0041] Compared to the method of manually adjusting the target temperature and humidity of the constant temperature and humidity control system involved in the background technology, the solution of the present invention can automatically determine the target temperature and humidity suitable for the current manufacturing type of the aero-engine casing through image recognition technology and semantic analysis technology, thereby realizing automatic temperature and humidity control and greatly improving the intelligence level of constant temperature and humidity control in the manufacturing workshop.

[0042] The aforementioned large language model refers to an artificial intelligence model with a large number of parameters, trained using deep learning methods, especially the Transformer architecture, to understand and generate natural language text. Large language models have made significant progress in the field of Natural Language Processing (NLP), capable of performing various complex language tasks such as text understanding, generation, translation, summarization, and question answering. Therefore, this invention employs a large language model to perform semantic understanding on the aforementioned key images. Specifically, the large language model can be any of the following: OpenAI's GPT series models (GPT-3, GPT-4), Google's BERT model, or Meta's Llama series models (e.g., Llama 3.1 405B), etc. This invention does not impose a specific limitation on these models.

[0043] Furthermore, the control of the high-definition camera to capture high-definition real-scene images of the manufacturing workshop includes:

[0044] Historical data is acquired and the locations of each key historical image are extracted from it. Each of these locations is then mapped onto a first high-definition real-scene image of the manufacturing workshop to obtain the corresponding mapped locations.

[0045] Based on the distribution of each of the mapping positions in the first high-definition real-scene image, a closed shape enclosing all the mapping positions is drawn. A second high-definition real-scene image is delineated from the first high-definition real-scene image based on the closed shape, and the second high-definition real-scene image is determined as the high-definition real-scene image of the manufacturing workshop.

[0046] In this embodiment, high-definition cameras are typically deployed at a high position in the manufacturing workshop, allowing for a top-down view of the entire workshop. However, certain areas within the manufacturing workshop do not actually contain critical objects such as aircraft engine casings, raw materials, or manufacturing machinery, and therefore, key images will not be detected in these areas. Therefore, this invention involves segmenting the first high-definition real-scene image to obtain a second high-definition real-scene image. Subsequent key image extraction is based solely on this second high-definition real-scene image, reducing the computational load.

[0047] Specifically, historical data of key image extraction is obtained, which includes the location of each historical key image extracted during each temperature and humidity control operation. These locations are mapped one by one onto the first high-definition real-scene image. Then, based on the distribution of each mapped location, a line is drawn that encloses all mapped locations, forming a closed figure. This closed figure represents the possible placement area of ​​the aforementioned key objects in the manufacturing workshop. This closed figure is then appropriately enlarged (e.g., enlarged by 1.2 times) to obtain the second high-definition real-scene image. This second high-definition real-scene image is separated from the first high-definition real-scene image to serve as the high-definition real-scene image of the manufacturing workshop.

[0048] Furthermore, the extraction of several key images related to aircraft engine casing manufacturing from the high-definition real-scene images includes:

[0049] Retrieve from the database the product appearance characteristics, raw material appearance characteristics, and equipment appearance characteristics related to aero-engine shell manufacturing for this manufacturing workshop;

[0050] Based on the product appearance features, the raw material appearance features, and the equipment appearance features, several objects are identified from the high-definition real-scene image, and the area image where each object is located is determined as the key image.

[0051] In this embodiment, different manufacturing workshops undertake the production tasks of different types of aircraft engine casings. Objects related to the production of different types of aircraft engine casings are pre-determined. These objects include aircraft engine casing products, manufacturing raw materials, and manufacturing machinery. The appearance features of these objects are extracted using image recognition technology and constructed as product appearance features, raw material appearance features, and equipment appearance features, respectively. During use, the aforementioned product appearance features, raw material appearance features, and equipment appearance features corresponding to the manufacturing workshop are retrieved from the database. Based on these appearance features, object recognition is performed in high-definition real-scene images, and the areas where each recognized object is located are determined as key images.

[0052] Furthermore, the step of using a large language model to perform semantic understanding on the key images to obtain the type of aircraft engine casing includes:

[0053] The large language model is used to perform semantic understanding on the key images to obtain the object attributes of each object.

[0054] If each of the object attributes contains attribute information of an aircraft engine housing product, then the first aircraft engine housing type is determined based on the attribute information of the aircraft engine housing product. Then, the first aircraft engine housing type is matched and analyzed with the attributes of other objects. If the matching analysis is successful, the first aircraft engine housing type is determined as the aircraft engine housing type.

[0055] If none of the object attributes contain an aircraft engine casing product or the matching analysis fails, then each object attribute is packaged into a query statement, and the query statement is submitted to the large language model. The large language model outputs several second aircraft engine casing types and their corresponding predicted probabilities, and the second aircraft engine casing type with the highest predicted probability is determined as the aircraft engine casing type.

[0056] In this embodiment, the large language model can perform semantic understanding of the object information in each key image, thereby determining the object attributes of each object. The object attributes include the attribute information of the aero-engine casing product, the attribute information of the manufacturing raw materials, and the attribute information of the manufacturing machinery. For example, the attribute information of the aero-engine casing product may include integral casing, split casing, complex aluminum alloy casing of fuel control system, casing with rectifier support plate, turbojet / turbofan engine casing, piston engine casing, etc. The attribute information of the manufacturing raw materials may include aluminum alloy, titanium alloy, high temperature alloy, composite material (such as carbon fiber reinforced plastic (CFRP) and ceramic matrix composite (CMC)), etc. The attribute information of the manufacturing machinery may include casting machine, milling machine (single-axis, multi-axis), heat treatment equipment, electrical discharge machining equipment, etc.

[0057] If the large language model identifies object attributes that include those of an aircraft engine casing, then the type of the first aircraft engine casing can be directly determined based on these product attribute information. Examples include integral casings, split casings, and piston engine casings. However, it is also necessary to perform a secondary confirmation of the directly determined first aircraft engine casing type based on other identified attribute information. This involves matching the first aircraft engine casing type with other object attributes. If the matching analysis passes, the result is considered valid. An example is provided below:

[0058] 1) The manufacturing process of the piston engine casing includes casting, machining, and heat treatment. If other attribute information includes attribute information of the manufacturing machinery corresponding to the casting machine, machining equipment, and heat treatment equipment, then the matching analysis can be considered successful.

[0059] 2) The integral casing typically uses metal mold casting as the basic process. If other attribute information includes the attribute information of the manufacturing machinery corresponding to the casting machine, then the matching analysis can be considered successful.

[0060] 3) Turbojet / turbofan engine casings typically need to withstand high temperatures and pressures, therefore the manufacturing process usually includes the selection of special materials and precision machining techniques. Thus, if other attribute information includes the attribute information of manufacturing raw materials such as titanium alloys and composite materials, and the attribute information of manufacturing machinery corresponding to precision machining equipment, then the matching analysis can be considered successful.

[0061] 4) Complex aluminum alloy housing for fuel control systems: This type of housing is typically manufactured using metal mold casting. The casting process design incorporates tilt casting and grain refinement techniques to improve the internal quality and density of the casting. Therefore, if other attribute information includes the attribute information of the manufacturing raw materials corresponding to the aluminum alloy, and the attribute information of the tilt casting equipment and the manufacturing machinery corresponding to grain refinement, then the matching analysis can be considered successful.

[0062] If the attributes of each object do not include aircraft engine casing products, or if no aircraft engine casing products are placed in the manufacturing workshop, then the attributes of each object need to be packaged into a query statement. This query is then submitted to the large language model, which analyzes the query using a local knowledge database or online network, outputting several second aircraft engine casing types and their corresponding predicted probabilities. The second aircraft engine casing type with the highest predicted probability is then determined as the aircraft engine casing type. Alternatively, if the attributes do not include aircraft engine casing products, the aircraft engine casing type can be determined by directly querying the large language model. The specific process is the same as described above and will not be repeated here.

[0063] It should be noted that, due to actual manufacturing needs, the manufacturing workshop may be modified to manufacture other types of aircraft engine casings. This will result in changes to the casing products, manufacturing raw materials, and manufacturing machinery. Such changes may include alterations to all equipment in the manufacturing workshop or the covering up of "old" equipment.

[0064] Further, determining the target temperature and target humidity based on the type of the aircraft engine casing includes:

[0065] The type of aircraft engine casing is compared with a preset lookup table to obtain the matching target temperature and target humidity.

[0066] In this embodiment, the types of aero-engine housings include integral casings, split casings, complex aluminum alloy casings with fuel control systems, casings with fairings, turbojet / turbofan engine housings, and piston engine housings. Target temperatures and humidity levels are pre-configured for each type of aero-engine housing. Therefore, after determining the type of aero-engine housing to be manufactured in the current stage of the manufacturing workshop, the target temperature and humidity should be determined by comparing it with a pre-set reference table. Controlling the constant temperature and humidity system according to these target temperatures and humidity levels ensures that the temperature and humidity environment in the manufacturing workshop is suitable for the manufacture of the aero-engine housing.

[0067] Furthermore, before determining the target temperature and target humidity based on the type of the aircraft engine casing, the method further includes:

[0068] The type of aircraft engine casing is output to the relevant personnel, and after receiving confirmation from the relevant personnel, it is output again until the number of confirmations received from the relevant personnel reaches a preset number.

[0069] The preset number of times is determined in the following way:

[0070] The number of sets of target temperature and target humidity executed by the constant temperature and humidity control system of the manufacturing workshop is obtained, and the preset number of times is calculated based on the number of sets and the corresponding negative correlation function.

[0071] In this embodiment, after determining the type of aircraft engine casing, the present invention outputs the determined aircraft engine casing type to relevant personnel for confirmation, thereby avoiding errors in the previously predicted aircraft engine casing type. The improvement of the present invention lies in outputting the aircraft engine casing type to relevant personnel multiple times. Specifically, after the relevant personnel provide "affirmative" confirmation, the aircraft engine casing type is output again to prompt them to confirm again, until the number of confirmations received from the relevant personnel reaches a preset number. At this point, it can be confirmed that the relevant personnel indeed hold an affirmative attitude towards the previously predicted aircraft engine casing type, rather than a misconception. The target temperature and humidity can then be determined based on the aircraft engine casing type and controlled and executed by the constant temperature and humidity control system.

[0072] Furthermore, the preset number of times in this invention is a dynamic value, determined by obtaining the number of sets of target temperature and target humidity executed by the constant temperature and humidity control system of the manufacturing workshop, i.e., how many sets of [target temperature, target humidity] the constant temperature and humidity control system has executed for the manufacturing workshop. A higher number of sets indicates that the manufacturing workshop frequently undertakes manufacturing tasks for different types of aircraft engine casings, indirectly indicating a relatively low probability of error in the predicted aircraft engine casing type. In this case, the preset number of times should be appropriately reduced to decrease the confirmation load on relevant personnel. Conversely, a lower number of sets indicates that the manufacturing workshop does not frequently undertake manufacturing tasks for different types of aircraft engine casings, indirectly indicating a relatively high probability of error in the predicted aircraft engine casing type. In this case, the preset number of times should be appropriately increased to reduce the probability of incorrect confirmation by relevant personnel.

[0073] The present invention does not impose specific limitations on the specific functional form of the aforementioned negative correlation function, as long as it conforms to the negative correlation relationship.

[0074] like Figure 2 As shown in the figure, the present invention also discloses a constant temperature and humidity control system for the shell manufacturing process of an aero-engine, the system including a first control module, a second control module, and a regulation module;

[0075] The first control module is used to control a high-definition camera to capture high-definition real-scene images of the manufacturing workshop, and extract several key images related to the shell manufacturing of aero-engines from the high-definition real-scene images.

[0076] The second control module is used to perform semantic understanding on the key image using a large language model to obtain the type of aircraft engine casing, and determine the target temperature and target humidity based on the type of aircraft engine casing.

[0077] The control module is used to control the constant temperature and humidity control system to adjust the temperature in the manufacturing workshop to the target temperature and the humidity in the manufacturing workshop to the target humidity.

[0078] This invention also discloses an electronic device, comprising: a memory storing executable program code; a processor coupled to the memory; the processor calling the executable program code stored in the memory to execute the method described in the foregoing embodiments.

[0079] This invention also discloses a computer storage medium storing a computer program, which is executed by a processor to perform the methods described in the foregoing embodiments.

[0080] This invention also discloses a computer program product, wherein the computer program in the computer program product, when executed, implements the method described in the foregoing embodiments.

[0081] It should be noted that the processor described above may generally be referred to as a "data processing circuit" in this document. This data processing circuit may be implemented in whole or in part as software, hardware, firmware, or any other combination thereof.

[0082] This invention also discloses a computer storage medium storing a computer program, which is executed by a processor to perform the methods described in the foregoing embodiments.

[0083] The aforementioned storage media may include, but are not limited to: USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, optical disks, and other media capable of storing program code.

[0084] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims can be performed in a different order than that shown in the embodiments and still achieve the desired results. Additionally, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are also possible or may be advantageous.

[0085] The various embodiments in this application are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the device and apparatus embodiments are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0086] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

[0087] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for controlling the temperature and humidity during the manufacturing process of an aero-engine casing, characterized in that, Includes the following steps: Control a high-definition camera to capture high-definition real-scene images of the manufacturing workshop, and extract several key images related to the shell manufacturing of aero-engines from the high-definition real-scene images; The key images are semantically understood using a large language model to obtain the type of aircraft engine casing, and the target temperature and target humidity are determined based on the type of aircraft engine casing. The constant temperature and humidity control system regulates the temperature in the manufacturing workshop to the target temperature and the humidity in the manufacturing workshop to the target humidity. Several key images related to aircraft engine casing manufacturing were extracted from the high-definition real-view images, including: Retrieve from the database the product appearance characteristics, raw material appearance characteristics, and equipment appearance characteristics related to aero-engine shell manufacturing for this manufacturing workshop; Based on the product appearance features, the raw material appearance features, and the equipment appearance features, several objects are identified from the high-definition real-scene image, and the area image where each object is located is determined as the key image; The process of using a large language model to perform semantic understanding on the key images to obtain the type of aircraft engine casing includes: The large language model is used to perform semantic understanding on the key images to obtain the object attributes of each object. If each of the object attributes contains attribute information of an aircraft engine casing product, then the first aircraft engine casing type is determined based on the attribute information of the aircraft engine casing product. Then, the first aircraft engine casing type is matched with the attributes of other objects. If the matching analysis is successful, the first aircraft engine casing type is determined as the aircraft engine casing type. If the other attribute information contains the attribute information of the corresponding manufacturing machinery or the attribute information of the manufacturing raw materials, then the matching analysis is considered successful. If none of the object attributes contain an aircraft engine casing product or the matching analysis fails, then each object attribute is packaged into a query statement, and the query statement is submitted to the large language model. The large language model outputs several second aircraft engine casing types and their corresponding predicted probabilities, and the second aircraft engine casing type with the highest predicted probability is determined as the aircraft engine casing type.

2. The method for controlling constant temperature and humidity in the manufacturing process of an aero-engine casing according to claim 1, characterized in that: The control of the high-definition camera to capture high-definition real-scene images of the manufacturing workshop includes: Historical data is acquired and the locations of each key historical image are extracted from it. Each of these locations is then mapped onto a first high-definition real-scene image of the manufacturing workshop to obtain the corresponding mapped locations. Based on the distribution of each of the mapping positions in the first high-definition real-scene image, a closed shape enclosing all the mapping positions is drawn. A second high-definition real-scene image is delineated from the first high-definition real-scene image based on the closed shape, and the second high-definition real-scene image is determined as the high-definition real-scene image of the manufacturing workshop.

3. The method for controlling the temperature and humidity in the manufacturing process of an aero-engine casing according to claim 2, characterized in that: The determination of the target temperature and target humidity based on the type of the aircraft engine casing includes: The type of aircraft engine casing is compared with a preset lookup table to obtain the matching target temperature and target humidity.

4. The method for controlling the temperature and humidity in the manufacturing process of an aero-engine casing according to claim 3, characterized in that: Before determining the target temperature and target humidity based on the type of aircraft engine casing, the method further includes: The type of aircraft engine casing is output to the relevant personnel, and after receiving confirmation from the relevant personnel, it is output again until the number of confirmations received from the relevant personnel reaches a preset number. The preset number of times is determined as follows: the number of sets of target temperature and target humidity executed by the constant temperature and humidity control system of the manufacturing workshop is obtained, and the preset number of times is calculated based on the number of sets and the corresponding negative correlation function.

5. A constant temperature and humidity control system for aero-engine shell manufacturing process, the system being based on the method described in any one of claims 1-4, comprising a first control module, a second control module, and a regulation module; characterized in that: The first control module is used to control a high-definition camera to capture high-definition real-scene images of the manufacturing workshop, and extract several key images related to the shell making of aero-engines from the high-definition real-scene images. The second control module is used to perform semantic understanding on the key image using a large language model to obtain the type of aircraft engine casing, and determine the target temperature and target humidity based on the type of aircraft engine casing. The control module is used to control the constant temperature and humidity control system to adjust the temperature in the manufacturing workshop to the target temperature and the humidity in the manufacturing workshop to the target humidity.

6. An electronic device, comprising: Memory containing executable program code; A processor coupled to the memory; characterized in that: the processor calls the executable program code stored in the memory to perform the method as described in any one of claims 1-4.

7. A computer storage medium storing a computer program, characterized in that: The computer program is executed by the processor to perform the method as described in any one of claims 1-4.

8. A computer program product, characterized in that: When the computer program in the computer program product is executed, it implements the method described in any one of claims 1-4.

Images