Constant-temperature and constant-humidity control method and system for shell making process of aviation engine

Abstract

The invention belongs to the technical field of smart factories. The invention provides a constant-temperature and constant-humidity control method and system for an aviation engine shell making process. The method comprises the following steps: controlling a high-definition camera to shoot a high-definition live-action image of a manufacturing workshop, and extracting a plurality of key images related to the shell of the aviation engine from the high-definition live-action image; performing semantic understanding on the key image by using a large language model to obtain the type of the aero-engine shell, and determining a target temperature and a target humidity according to the type of the aero-engine shell; and controlling the constant-temperature and constant-humidity control system to regulate and control the temperature in the manufacturing workshop to be the target temperature and regulate and control the humidity in the manufacturing workshop to be the target humidity. According to the scheme, the target temperature and the target humidity suitable for the manufacturing type of the current aero-engine shell can be automatically determined through the image recognition technology and the semantic analysis technology, so that automatic regulation and control of the temperature and the humidity are achieved, and the intelligent level of constant-temperature and constant-humidity regulation and control of a manufacturing workshop is greatly improved.

Description

Technical Field

[0001] The present invention relates to the field of smart factory technology, and in particular to a constant temperature and humidity control method and system for an aircraft engine shell manufacturing process. Background Art

[0002] The aircraft engine casing is an important component of the aircraft engine. It not only carries various components inside the engine, such as the fuel system, lubricating oil system, control system, etc., but also has a direct impact on the performance and safety of the engine.

[0003] In the manufacturing process of aircraft engine casings, the temperature and humidity of the manufacturing environment need to be strictly controlled, because these factors will directly affect the performance and processing quality of the materials. In the existing aircraft engine casing manufacturing workshop, a constant temperature and humidity control system is installed, which can maintain the appropriate temperature and humidity in the manufacturing workshop. However, the control parameters in the constant temperature and humidity control system are set based on a specific type of aircraft engine casing. When manufacturing other types of aircraft engine casings in the manufacturing workshop, the control parameters in the constant temperature and humidity control system need to be manually adjusted, which requires a lot of manpower and has a very low control efficiency. Summary of the invention

[0004] In order to solve at least one of the above-mentioned technical problems, the present invention specifically provides a constant temperature and humidity control method, system, electronic equipment, computer storage medium and computer program product for an aircraft engine casing manufacturing process, so as to improve the constant temperature and humidity control efficiency of an aircraft engine casing manufacturing workshop.

[0005] The present invention provides a method for controlling constant temperature and humidity in a casing manufacturing process of an aero-engine, comprising the following steps: Controlling a high-definition camera to capture a high-definition real-scene image of a manufacturing workshop, and extracting several key images related to aircraft engine casing manufacturing from the high-definition real-scene image; Using a large language model to perform semantic understanding on the key image, obtain the type of the aircraft engine casing, and determine the target temperature and target humidity according to the type of the aircraft engine casing; The constant temperature and humidity control system is controlled to adjust the temperature in the manufacturing workshop to the target temperature, and the humidity in the manufacturing workshop to the target humidity.

[0006] Furthermore, controlling the high-definition camera to capture a high-definition real-life image of the manufacturing workshop includes: Acquire historical data and extract the positions of each historical key image therefrom, map each of the positions to a first high-definition real-scene image of a manufacturing workshop, and obtain corresponding mapping positions; According to the distribution of each of the mapping positions in the first high-definition real-scene image, a closed figure surrounding all the mapping positions is drawn, and a second high-definition real-scene image is delineated from the first high-definition real-scene image based on the closed figure, and the second high-definition real-scene image is determined as the high-definition real-scene image of the manufacturing workshop.

[0007] Furthermore, the extraction of several key images related to the aero-engine casing from the high-definition real-scene image includes: Retrieve product appearance features, raw material appearance features, and equipment appearance features related to aircraft engine casing manufacturing corresponding to the manufacturing workshop from the database; Based on the product appearance features, the raw material appearance features and the equipment appearance features, a number of objects are identified from the high-definition real-scene image, and the regional image where each of the objects is located is determined as the key image.

[0008] Furthermore, the using of a large language model to perform semantic understanding on the key image to obtain the type of the aircraft engine casing includes: Using the large language model to perform semantic understanding on the key image to obtain object attributes of each of the objects; If each of the object attributes includes attribute information of an aircraft engine casing product, a first aircraft engine casing type is determined based on the attribute information of the aircraft engine casing product, and then the first aircraft engine casing type is matched and analyzed with the other object attributes. If the matching analysis passes, the first aircraft engine casing type is determined as the aircraft engine casing type. If the object attributes do not include an aircraft engine casing product or the matching analysis fails, each of the object attributes is packaged as a question statement, and the question statement is submitted to the large language model. The large language model outputs several second aircraft engine casing types and corresponding prediction probabilities, and the second aircraft engine casing type with the largest prediction probability is determined as the aircraft engine casing type.

[0009] Further, the determining of the target temperature and the target humidity according to the type of the aircraft engine casing includes: The aircraft engine casing type is compared with a preset comparison table, and the matching target temperature and target humidity are obtained from the comparison table.

[0010] Furthermore, before determining the target temperature and the target humidity according to the type of the aircraft engine casing, the method further includes: Outputting the aircraft engine casing type to relevant personnel, and outputting it again after receiving confirmation from the relevant personnel, until the number of confirmations received from the relevant personnel reaches a preset number; The preset number of times is determined by obtaining the number of groups of the target temperature and the target humidity executed by the constant temperature and humidity control system of the manufacturing workshop, and calculating the preset number of times according to the number of groups and the corresponding negative correlation function.

[0011] The present invention provides a constant temperature and humidity control system for an aircraft engine casing manufacturing process, the system comprising a first control module, a second control module, and a regulation module; The first control module is used to control the high-definition camera to capture a high-definition real-scene image of the manufacturing workshop, and extract several key images related to the aircraft engine casing from the high-definition real-scene image; The second control module is used to use a large language model to perform semantic understanding on the key image, obtain the type of aircraft engine casing, and determine the target temperature and target humidity according to 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 to adjust the humidity in the manufacturing workshop to the target humidity.

[0012] The present invention provides an electronic device, comprising: a memory storing executable program code; a processor coupled to the memory; the processor calls the executable program code stored in the memory to execute any of the methods described in the preceding items.

[0013] The present invention provides a computer storage medium, on which a computer program is stored. When the computer program is run by a processor, any of the above methods is executed.

[0014] The present invention provides a computer program product, wherein a computer program in the computer program product implements any of the above methods when the computer program is executed.

[0015] Compared with the background technology involved in switching the target temperature and target humidity of the constant temperature and humidity control system through manual adjustment, the solution of the present invention can automatically determine the target temperature and target humidity suitable for the current manufacturing type of the aircraft engine casing through image recognition technology and semantic analysis technology, thereby realizing automatic control of temperature and humidity, greatly improving the intelligence level of constant temperature and humidity control in the manufacturing workshop. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 The invention discloses a flow chart of a method for controlling constant temperature and humidity in a casing manufacturing process of an aero-engine.

[0018] Figure 2 The invention is a schematic structural diagram of a constant temperature and humidity control system for an aircraft engine casing manufacturing process disclosed in an embodiment of the invention. DETAILED DESCRIPTION

[0019] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0020] like Figure 1 As shown, the embodiment of the present invention provides a method for controlling constant temperature and humidity in a casing manufacturing process of an aircraft engine, comprising the following steps: Controlling a high-definition camera to capture a high-definition real-scene image of a manufacturing workshop, and extracting several key images related to aircraft engine casing manufacturing from the high-definition real-scene image; Using a large language model to perform semantic understanding on the key image, obtain the type of the aircraft engine casing, and determine the target temperature and target humidity according to the type of the aircraft engine casing; The constant temperature and humidity control system is controlled to adjust the temperature in the manufacturing workshop to the target temperature, and the humidity in the manufacturing workshop to the target humidity.

[0021] The present invention arranges a high-definition camera in an aeroengine casing manufacturing workshop. When the aeroengine casing manufacturing workshop needs to be controlled at a constant temperature and humidity, the high-definition camera is controlled to shoot a high-definition real-life image of the manufacturing workshop, and a number of key images related to the aeroengine casing are extracted from the images. These key images may be images related to the aeroengine casing products, manufacturing raw materials, manufacturing machinery, etc. Then, a large language model is used to perform semantic understanding on the extracted key images, so as to obtain the type of aeroengine casing that is about to be or is being produced in the manufacturing workshop. Since the temperature and humidity corresponding to different aeroengine casing types are preset to be most conducive to ensuring the quality of the aeroengine casing, the above-mentioned target temperature and target humidity can be quickly determined by comparison calculation. Finally, the constant temperature and humidity control system arranged in the manufacturing workshop is controlled to adjust the temperature to the target temperature and the humidity to the target humidity, so as to ensure that the temperature and humidity environment in the manufacturing workshop can meet the environmental requirements corresponding to the aeroengine casing type.

[0022] Compared with the background technology involved in switching the target temperature and target humidity of the constant temperature and humidity control system through manual adjustment, the solution of the present invention can automatically determine the target temperature and target humidity suitable for the current manufacturing type of the aircraft engine casing through image recognition technology and semantic analysis technology, thereby realizing automatic control of temperature and humidity, greatly improving the intelligence level of constant temperature and humidity control in the manufacturing workshop.

[0023] The above-mentioned large language model refers to an artificial intelligence model with a large number of parameters, which is trained through deep learning methods, especially the Transformer architecture, to understand and generate natural language text. The large language model has made significant progress in the field of natural language processing (NLP) and can perform a variety of complex language tasks, such as text understanding, generation, translation, summarization, question answering, etc. Therefore, the present invention uses a large language model to perform semantic understanding on the above-mentioned key images. The large language model can specifically use the GPT series model (GPT-3, GPT-4) developed by OpenAI, the BERT model developed by Google, the Llama series model developed by Meta (such as Llama 3.1 405B), etc., and the present invention does not specifically limit this.

[0024] Furthermore, controlling the high-definition camera to capture a high-definition real-life image of the manufacturing workshop includes: Acquire historical data and extract the positions of each historical key image therefrom, map each of the positions to a first high-definition real-scene image of a manufacturing workshop, and obtain corresponding mapping positions; According to the distribution of each of the mapping positions in the first high-definition real-scene image, a closed figure surrounding all the mapping positions is drawn, and a second high-definition real-scene image is delineated from the first high-definition real-scene image based on the closed figure, and the second high-definition real-scene image is determined as the high-definition real-scene image of the manufacturing workshop.

[0025] In this embodiment, the high-definition camera is generally arranged at a certain position at a high place in the manufacturing workshop, and can take a bird's-eye view of the manufacturing workshop from a bird's-eye view. However, some areas in the manufacturing workshop do not actually place key objects such as aircraft engine casing products, manufacturing materials, and manufacturing machinery, so key images will not be detected in these areas. Therefore, the present invention is configured to segment the first high-definition real-scene image, and obtain the second high-definition real-scene image from the segmentation. Subsequently, the key image is extracted only based on the second high-definition real-scene image, which can reduce the computational load.

[0026] Specifically, the recorded extraction history data of the key images is obtained, and the history data includes the positions of each historical key image extracted each time the constant temperature and humidity control is performed. These positions are mapped one by one to the first high-definition real scene image, and then according to the distribution of each mapping position, a line that can surround all mapping positions is drawn. The line forms a closed figure, and the closed figure represents the possible placement area of ​​the above-mentioned key objects in the manufacturing workshop. Then, the closed figure is appropriately enlarged (for example, enlarged by 1.2 times) to obtain a second high-definition real scene image, and the second high-definition real scene image is divided from the first high-definition real scene image as the high-definition real scene image of the manufacturing workshop.

[0027] Furthermore, the extraction of several key images related to the aero-engine casing from the high-definition real-scene image includes: Retrieve product appearance features, raw material appearance features, and equipment appearance features related to aircraft engine casing manufacturing corresponding to the manufacturing workshop from the database; Based on the product appearance features, the raw material appearance features and the equipment appearance features, a number of objects are identified from the high-definition real-scene image, and the regional image where each of the objects is located is determined as the key image.

[0028] In this embodiment, different manufacturing workshops undertake different types of aircraft engine casing production tasks, and predetermine objects related to the production of different types of aircraft engine casings. These objects include aircraft engine casing products, manufacturing materials, and manufacturing machinery. The appearance features of these objects are extracted through image recognition technology, and they are respectively constructed into product appearance features, raw material appearance features, and equipment appearance features. When in use, the above-mentioned product appearance features, raw material appearance features, and equipment appearance features corresponding to the manufacturing workshop are retrieved from the database, and objects are identified in high-definition real-life images based on these appearance features, and the regional images where each identified object is located are determined as key images.

[0029] Furthermore, the using of a large language model to perform semantic understanding on the key image to obtain the type of the aircraft engine casing includes: Using the large language model to perform semantic understanding on the key image to obtain object attributes of each of the objects; If each of the object attributes includes attribute information of an aircraft engine casing product, a first aircraft engine casing type is determined based on the attribute information of the aircraft engine casing product, and then the first aircraft engine casing type is matched and analyzed with the other object attributes. If the matching analysis passes, the first aircraft engine casing type is determined as the aircraft engine casing type. If the object attributes do not include an aircraft engine casing product or the matching analysis fails, each of the object attributes is packaged as a question statement, and the question statement is submitted to the large language model. The large language model outputs several second aircraft engine casing types and corresponding prediction probabilities, and the second aircraft engine casing type with the largest prediction probability is determined as the aircraft engine casing type.

[0030] In this embodiment, the large language model can semantically understand the object information in each key image, so as to determine the object attributes of each object, and the object attributes include the attribute information of the aircraft 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 aircraft engine casing product may include the integral casing, the split casing, the complex aluminum alloy casing of the fuel control system, the casing with the rectifier support plate, the turbojet / turbofan engine casing, the piston engine casing, etc. The attribute information of the manufacturing raw materials may include aluminum alloy, titanium alloy, high temperature alloy, composite materials (such as carbon fiber reinforced plastic (CFRP) and ceramic matrix composite material (CMC)), etc., and the attribute information of the manufacturing machinery may include casting machine, milling machine (single axis, multi-axis), heat treatment equipment, electric spark machining equipment, etc.

[0031] If the object attributes identified by the large language model contain the attribute information of the aircraft engine casing product, the first aircraft engine casing type can be directly determined based on the product attribute information, such as the above-mentioned integral casing, split casing, piston engine casing, etc. At the same time, it is also necessary to conduct a secondary confirmation of the first aircraft engine casing type directly determined above based on other identified attribute information, that is, to match and analyze the first aircraft engine casing type with other object attributes. If the matching analysis passes. An example is as follows: 1) The manufacturing process of the piston engine housing includes casting, machining and heat treatment. If the other attribute information contains the attribute information of the manufacturing machinery corresponding to the casting machine, machining equipment and heat treatment equipment, it can be determined that the matching analysis has passed.

[0032] 2) The integral casing usually adopts metal mold casting as the basic process solution. If the other attribute information contains the attribute information of the manufacturing machinery corresponding to the casting machine, it can be determined that the matching analysis has passed.

[0033] 3) Turbojet / turbofan engine casings usually need to withstand high temperatures and high pressures, so the manufacturing process usually includes the selection of special materials and precision machining technology. Therefore, if other attribute information includes the attribute information of manufacturing materials corresponding to titanium alloys, composite materials, etc., and the attribute information of manufacturing machinery corresponding to precision machining equipment, it can be determined that the matching analysis has passed.

[0034] 4) Complex aluminum alloy housing of fuel control system: This housing is usually cast by metal mold, and tilt casting and grain refinement technology are used in the casting process design to improve the internal quality and structural density of the casting. Therefore, if other attribute information includes the attribute information of the manufacturing raw materials corresponding to the aluminum alloy, the attribute information of the tilt casting equipment and the manufacturing machinery corresponding to the grain refinement, it can be determined that the matching analysis has passed.

[0035] If the attributes of each object do not contain aircraft engine casing products or, that is, no aircraft engine casing products are placed in the manufacturing workshop, it is necessary to package the attributes of each object into question statements, and ask questions to the large language model accordingly. The large language model then analyzes through the local knowledge database or online network, outputs several second aircraft engine casing types and corresponding prediction probabilities, and determines the second aircraft engine casing type with the largest prediction probability as the aircraft engine casing type. In addition, if, the aircraft engine casing type can also be determined by directly asking questions to the large language model. The specific process is the same as above and will not be repeated.

[0036] It should be noted that due to actual manufacturing needs, the manufacturing workshop may be converted to manufacture other types of aircraft engine casings, which will result in changes in casing products, manufacturing materials, and manufacturing machinery. Such changes can be the change of all equipment in the manufacturing workshop or the covering of "old" equipment.

[0037] Further, the determining of the target temperature and the target humidity according to the type of the aircraft engine casing includes: The aircraft engine casing type is compared with a preset comparison table, and the matching target temperature and target humidity are obtained from the comparison table.

[0038] In this embodiment, the types of aircraft engine casings include integral casings, split casings, fuel control system complex aluminum alloy casings, casings with rectifier support plates, turbojet / turbofan engine casings, piston engine casings, etc., and corresponding target temperatures and target humidity are configured in advance for these types of aircraft engine casings. Therefore, after determining the type of aircraft engine casing to be manufactured in the current stage of the manufacturing workshop, by comparing and analyzing with the preset comparison table, the target temperature and target humidity that should be configured for the manufacturing workshop can be determined, and the constant temperature and humidity system can be controlled to perform constant temperature and humidity regulation according to the target temperature and target humidity to ensure that the temperature and humidity environment in the manufacturing workshop is suitable for the manufacturing of the aircraft engine casing.

[0039] Furthermore, before determining the target temperature and the target humidity according to the type of the aircraft engine casing, the method further includes: Outputting the aircraft engine casing type to relevant personnel, and outputting it again after receiving confirmation from the relevant personnel, until the number of confirmations received from the relevant personnel reaches a preset number; The preset number of times is determined in the following manner: The number of groups of the target temperature and the 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 according to the number of groups and the corresponding negative correlation function.

[0040] In this embodiment, after determining the aircraft engine casing type, the present invention also outputs the determined aircraft engine casing type to relevant personnel for confirmation, so as to avoid the aforementioned predicted aircraft engine casing type being incorrect. The improvement of the present invention is that the aircraft engine casing type is output to relevant personnel multiple times. Specifically, after the relevant personnel make an "affirmative" confirmation, the aircraft engine casing type is output again to prompt the relevant personnel to confirm again until the number of confirmations received from the relevant personnel reaches a preset number. At this point, it can be determined that the relevant personnel are indeed positive about the aircraft engine casing type obtained by the aforementioned prediction, rather than a wrong confirmation by the relevant personnel. At this time, the above-mentioned target temperature and target humidity can be determined based on the aircraft engine casing type, and the constant temperature and humidity control system can be used to control and execute them.

[0041] In addition, the preset number in the present invention is a dynamic value, which is determined by obtaining the number of target temperature and target humidity groups executed by the constant temperature and humidity control system of the manufacturing workshop, that is, how many groups of [target temperature, target humidity] the constant temperature and humidity control system has executed for the manufacturing workshop. The more the number of groups, the more it means that the manufacturing workshop often undertakes the manufacturing tasks of different types of aircraft engine casings, which indirectly indicates that the error probability of the aircraft engine casing type obtained by the above prediction is relatively low. At this time, the preset number is appropriately reduced to reduce the confirmation load of relevant personnel; on the contrary, it means that the manufacturing workshop does not often undertake the manufacturing tasks of different types of aircraft engine casings, which indirectly indicates that the error probability of the aircraft engine casing type obtained by the above prediction is relatively high. At this time, the preset number is appropriately increased to reduce the probability of erroneous confirmation by relevant personnel.

[0042] The present invention does not specifically limit the specific function form of the negative correlation function, as long as it conforms to the negative correlation relationship.

[0043] like Figure 2 As shown, the embodiment of the present invention also discloses a constant temperature and humidity control system for an aircraft engine casing manufacturing process, the system comprising a first control module, a second control module, and a control module; The first control module is used to control the high-definition camera to capture a high-definition real-scene image of the manufacturing workshop, and extract several key images related to the aircraft engine casing from the high-definition real-scene image; The second control module is used to use a large language model to perform semantic understanding on the key image, obtain the type of aircraft engine casing, and determine the target temperature and target humidity according to 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 to adjust the humidity in the manufacturing workshop to the target humidity.

[0044] An embodiment of the present invention further discloses an electronic device, comprising: a memory storing executable program code; a processor coupled to the memory; the processor calls the executable program code stored in the memory to execute the method described in the above embodiment.

[0045] The embodiment of the present invention further discloses a computer storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method described in the above embodiment is executed.

[0046] The embodiment of the present invention further discloses a computer program product, and when the computer program in the computer program product is executed, the method described in the above embodiment is implemented.

[0047] It should be noted that the above processor may generally be referred to herein as a “data processing circuit.” The data processing circuit may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof.

[0048] The embodiment of the present invention further discloses a computer storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method described in the above embodiment is executed.

[0049] The above storage medium may include but is not limited to: a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and other media that can store program codes.

[0050] It should be noted that the above-mentioned sequence of the embodiments of the present application is for description only and does not represent the advantages and disadvantages of the embodiments. The above-mentioned specific embodiments of the present application are described. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0051] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device and equipment embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0052] A person skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware or by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

[0053] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A method for controlling constant temperature and humidity in aeroengine casing manufacturing process, characterized in that: The steps include: Controlling a high-definition camera to capture a high-definition real-scene image of a manufacturing workshop, and extracting several key images related to aircraft engine casing manufacturing from the high-definition real-scene image; Using a large language model to perform semantic understanding on the key image, obtain the type of the aircraft engine casing, and determine the target temperature and target humidity according to the type of the aircraft engine casing; The constant temperature and humidity control system is controlled to adjust the temperature in the manufacturing workshop to the target temperature, and the humidity in the manufacturing workshop to the target humidity.

2. The method for controlling constant temperature and humidity in aero-engine casing manufacturing process according to claim 1, characterized in that: The controlling of the high-definition camera to capture a high-definition real-scene image of the manufacturing workshop includes: Acquire historical data and extract the positions of each historical key image therefrom, map each of the positions to a first high-definition real-scene image of a manufacturing workshop, and obtain corresponding mapping positions; According to the distribution of each of the mapping positions in the first high-definition real-scene image, a closed figure surrounding all the mapping positions is drawn, and a second high-definition real-scene image is delineated from the first high-definition real-scene image based on the closed figure, 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 constant temperature and humidity in aero-engine casing manufacturing process according to claim 1, characterized in that: Several key images related to aircraft engine casing manufacturing are extracted from the high-definition real-scene images, including: Retrieve product appearance features, raw material appearance features, and equipment appearance features related to aircraft engine casing manufacturing corresponding to the manufacturing workshop from the database; Based on the product appearance features, the raw material appearance features and the equipment appearance features, a number of objects are identified from the high-definition real-scene image, and the regional image where each of the objects is located is determined as the key image.

4. A method for controlling constant temperature and humidity in aero-engine casing manufacturing process according to claim 3, characterized in that: The using of a large language model to perform semantic understanding on the key image to obtain the type of the aircraft engine casing includes: Using the large language model to perform semantic understanding on the key image to obtain object attributes of each of the objects; If each of the object attributes includes attribute information of an aircraft engine casing product, a first aircraft engine casing type is determined based on the attribute information of the aircraft engine casing product, and then the first aircraft engine casing type is matched and analyzed with the other object attributes. If the matching analysis passes, the first aircraft engine casing type is determined as the aircraft engine casing type. If the object attributes do not include an aircraft engine casing product or the matching analysis fails, each of the object attributes is packaged as a question statement, and the question statement is submitted to the large language model. The large language model outputs several second aircraft engine casing types and corresponding prediction probabilities, and the second aircraft engine casing type with the largest prediction probability is determined as the aircraft engine casing type.

5. A method for controlling constant temperature and humidity in aero-engine casing manufacturing process according to claim 4, characterized in that: The step of determining the target temperature and the target humidity according to the type of the aircraft engine casing comprises: The aircraft engine casing type is compared with a preset comparison table, and the matching target temperature and target humidity are obtained from the comparison table.

6. A method for controlling constant temperature and humidity in aero-engine casing manufacturing process according to claim 5, characterized in that: Before determining the target temperature and the target humidity according to the aircraft engine casing type, the method further includes: Outputting the aircraft engine casing type to relevant personnel, and outputting it again after receiving confirmation from the relevant personnel, until the number of confirmations received from the relevant personnel reaches a preset number; The preset number of times is determined by obtaining the number of groups of the target temperature and the target humidity executed by the constant temperature and humidity control system of the manufacturing workshop, and calculating the preset number of times according to the number of groups and the corresponding negative correlation function.

7. A constant temperature and humidity control system for an aircraft engine shell manufacturing process, the system comprising a first control module, a second control module, and a control module; characterized in that: The first control module is used to control the high-definition camera to capture a high-definition real-scene image of the manufacturing workshop, and extract several key images related to the aircraft engine casing from the high-definition real-scene image; The second control module is used to use a large language model to perform semantic understanding on the key image, obtain the type of aircraft engine casing, and determine the target temperature and target humidity according to 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 to adjust the humidity in the manufacturing workshop to the target humidity.

8. An electronic device comprising: A memory storing executable program code; A processor coupled to the memory; characterized in that: the processor calls the executable program code stored in the memory to execute the method according to any one of claims 1-6.

9. A computer storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is executed.

10. A computer program product, characterized in that: When the computer program in the computer program product is executed, the method according to any one of claims 1 to 6 is implemented.

Images