Beer production equipment image intelligent detection method and system based on unmanned vehicle and edge calculation

Abstract

The invention discloses a beer production equipment image intelligent detection method and system based on an unmanned vehicle and edge calculation, and belongs to the technical field of target detection. According to the method, the unmanned vehicle is controlled to collect image information of beer factory production equipment according to a preset inspection route, the equipment state is recognized in real time through an equipment anomaly detection model carried by an edge calculation module, and anomaly detection comprises angle steel falling, bolt falling, pipeline leakage and the like. When abnormity is detected, the system sends abnormity information and position to a monitoring end and triggers alarm. The model is trained by adopting equipment image data under multi-period and multi-weather conditions, and the detection precision is continuously optimized and improved. The problems that traditional manual inspection is low in efficiency and high in omission ratio are solved, efficient and safe equipment anomaly detection is achieved, and the production and management efficiency of a beer factory is remarkably improved.

Description

Technical Field

[0001] This invention belongs to the field of target detection technology for unmanned vehicles, specifically relating to an intelligent image detection method and system for beer production equipment based on unmanned vehicles and edge computing. Background Technology

[0002] As brewery equipment ages, problems such as aging, detachment, leaks, and sealing issues often arise. These problems can even lead to equipment tilting and collapse, causing safety accidents and injuries. Traditional manual inspection methods for addressing these issues also have many limitations. For example, inspectors may miss items when inspecting areas with numerous pipes. These limitations result in high risks, long processing times, low efficiency, and safety hazards associated with manual maintenance. Therefore, to improve the efficiency, quality, and safety of traditional breweries, ensure beer product quality control, and mitigate the impact of external factors on beer production, timely detection of equipment abnormalities and appropriate countermeasures are crucial.

[0003] Autonomous vehicles, with their flexibility, have demonstrated enormous potential in fields such as equipment inspection. Equipped with advanced sensors and cameras, they can capture high-resolution images in real time, supporting accurate target identification. Compared to traditional manual inspection systems, autonomous vehicles can more efficiently detect equipment anomalies, reduce manpower requirements, improve monitoring flexibility and coverage, and minimize personnel casualties in the event of safety accidents caused by equipment malfunctions. Summary of the Invention

[0004] To address the problems existing in the prior art, this invention provides an intelligent image detection method and system for beer production equipment based on unmanned vehicles and edge computing. This system can utilize unmanned vehicles to quickly detect and identify beer factory production equipment and send equipment anomaly information to a monitoring terminal, significantly improving inspection efficiency and enhancing the efficiency, quality, and safety of traditional beer factories.

[0005] To achieve the above objectives, the present invention provides the following technical solution:

[0006] Firstly, an intelligent image detection method for beer production equipment based on unmanned vehicles and edge computing is provided, the method comprising:

[0007] According to the preset beer factory inspection plan, the inspection unmanned vehicle is controlled to perform beer factory inspection tasks according to the preset inspection route, which includes preset equipment inspection sections.

[0008] When the unmanned inspection vehicle enters the equipment inspection section, it continuously collects image information of the beer factory production equipment using the image acquisition module, reads the equipment image information using the edge computing module, and uses the equipment anomaly detection model to identify anomalies in the image information.

[0009] When the edge computing module detects abnormal information, it sends the abnormal information to the monitoring terminal and generates an alarm message.

[0010] Preferably, training the device anomaly detection model includes the following steps:

[0011] Obtain the dataset and label the devices in the dataset;

[0012] Set training parameters and train the model using training and test sets. In each training round, the model extracts device features from the training set images and associates these features with the target labels. After each training round, the model performance is evaluated using a validation set. The evaluation focuses on the average accuracy when the ratio of the overlap area of ​​the predicted bounding box to the union area of ​​the ground truth bounding box is 0.5. After the evaluation, the model parameters are optimized. The model completes training after reaching the set number of training rounds. The best model and the last model are saved during training, with the best model serving as the final device anomaly detection model.

[0013] Obtaining the dataset and labeling the devices in the dataset includes:

[0014] The unmanned vehicle uses the image acquisition module to collect images of the beer factory production equipment on the preset equipment inspection section, and collects image data at different times including daytime, noon, and evening, as well as data on different weather conditions including sunny and rainy days.

[0015] Label the equipment in the image using a rectangle to select the brewery production equipment to be inspected and label its status.

[0016] The equipment status includes one or more of the following: normal equipment, detached angle steel, detached bolts, spilled alcohol, leaking pressure reducing valve, detached conduit, dripping pipe, abnormal wiring, and damaged pressure gauge.

[0017] Preferably, the trained device anomaly detection model is deployed to the unmanned vehicle, and the detection of device image information acquired by the image acquisition module on the unmanned vehicle includes:

[0018] First, the environment configuration and necessary plugins for running the device anomaly detection model are set up on the edge computing module on the unmanned vehicle; after installation, the device anomaly detection model is uploaded to the edge computing module on the unmanned vehicle.

[0019] Secondly, the image acquisition module communicates with the edge computing module. The unmanned vehicle can read the device image information acquired by the image acquisition module in real time and detect the device status in the read device image information. If the device is abnormal, the device abnormal information is output and the target is marked with a rectangle.

[0020] Preferably, if the equipment image is determined to include one or more of the following: equipment angle steel detachment, bolt detachment, spilled liquor, pressure reducing valve leakage, conduit detachment, pipe dripping, wiring abnormality, and pressure gauge damage, then equipment abnormality information is directly generated, including the specific details of the equipment abnormality.

[0021] Preferably, the resolution of the input image for the device anomaly detection model is 640*640.

[0022] Secondly, this application provides an intelligent image detection system for beer production equipment based on unmanned vehicles and edge computing, comprising:

[0023] Memory, used to store instructions;

[0024] A processor is configured to call instructions in memory and, when executed, implement the method for intelligent image detection of beer production equipment based on unmanned vehicles and edge computing as described in any one of claims 1 to 7.

[0025] Compared with the prior art, the present invention has the following beneficial effects:

[0026] This invention can acquire image information of beer factory production equipment based on unmanned vehicles, and identify whether the equipment is abnormal based on the equipment anomaly detection model inside the edge computing module, so as to quickly determine whether the equipment is abnormal, generate corresponding anomaly information, and send the anomaly information to the monitoring terminal to help resolve the impact of equipment anomalies. Attached Figure Description

[0027] Figure 1 This is a flowchart illustrating the steps of the intelligent image detection method for beer production equipment based on unmanned vehicles and edge computing in this invention.

[0028] Figure 2 This is a diagram showing the results of detecting equipment anomalies from equipment image information in this invention;

[0029] Figure 3 This refers to the real-time image information of the equipment acquired by the unmanned vehicle in this invention; Detailed Implementation

[0030] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0031] Example 1:

[0032] like Figure 1 As shown, this embodiment provides an intelligent image detection method for beer production equipment based on unmanned vehicles and edge computing, which includes the following steps:

[0033] According to the preset beer factory inspection plan, the inspection unmanned vehicle is controlled to perform beer factory inspection tasks according to the preset inspection route, which includes preset equipment inspection sections.

[0034] Once the unmanned inspection vehicle enters the equipment inspection section, it continuously collects image information of the brewery production equipment using the image acquisition module (e.g., ...). Figure 3 As shown in the figure, the edge computing module is used to read the image information of the device and the device anomaly detection model is used to identify anomalies in the image information; in this embodiment, the imaging device acquires the image information of the beer factory production equipment at an angle of 30°-90° upward to obtain a clear and complete image;

[0035] When the edge computing module detects abnormal information, it sends the abnormal information to the monitoring terminal and generates an alarm message for the monitoring terminal administrator to handle in a timely manner, such as promptly dispatching maintenance personnel to the site for repairs. The monitoring terminal includes smart terminals such as smartphones, tablets, and PCs. Furthermore, the abnormal equipment information includes: an image of the abnormal equipment, the location of the abnormal equipment (such as preset coordinates), and specific abnormal information about the equipment (such as detached angle iron).

[0036] The preset coordinate information can be established by setting the initial position of the unmanned vehicle inspection as the origin, taking the north direction of the beer factory location as the y-axis and the east direction of the beer factory location as the x-axis, and establishing a rectangular coordinate system. During the unmanned vehicle inspection, the coordinates of the unmanned vehicle in the established rectangular coordinate system will be updated in real time. When an equipment abnormality is detected, the coordinates of the unmanned vehicle at this time will be sent to the monitoring terminal as the coordinates of the abnormal equipment.

[0037] Specifically, training the device anomaly detection model includes the following steps:

[0038] Specifically, the unmanned vehicle acquires images containing beer factory production equipment, including image data at different times of day, noon, and evening, as well as data under different weather conditions such as sunny and rainy days. The equipment in the dataset is labeled, and the equipment status includes one or more of the following: equipment is normal, angle steel is detached, bolts are detached, beer is spilled from the steel, pressure reducing valve is leaking, conduit is detached, pipe is dripping, wiring is abnormal, and pressure gauge is damaged.

[0039] Set training parameters and train the model using training and test sets. In each training round, the model extracts device features from the training set images and associates these features with the target labels. After each training round, the model performance is evaluated using a validation set. The evaluation focuses on the average accuracy when the ratio of the overlap area of ​​the predicted bounding box to the union area of ​​the ground truth bounding box is 0.5. After the evaluation, the model parameters are optimized. The model completes training after reaching the set number of training rounds. The best model and the last model are saved during training, with the best model serving as the final device anomaly detection model.

[0040] The trained device anomaly detection model is deployed to the autonomous vehicle, and the detection of device image information acquired by the image acquisition module on the autonomous vehicle includes:

[0041] First, the environment configuration and necessary plugins for running the device anomaly detection model are set up on the edge computing module on the unmanned vehicle; after installation, the device anomaly detection model is uploaded to the edge computing module on the unmanned vehicle.

[0042] Secondly, the image acquisition module communicates with the edge computing module, allowing the unmanned vehicle to read the device image information acquired by the image acquisition module in real time and perform detection on the read device image information to check the device status. If the device is abnormal (e.g....), the vehicle will detect the device status in the image information. Figure 2 (As shown) the output device error information, and the target is marked with a rectangle.

[0043] If the equipment image is determined to contain one or more of the following: detached angle steel, detached bolts, spilled liquor, leaking pressure reducing valve, detached conduit, dripping pipe, abnormal wiring, or damaged pressure gauge, then equipment abnormality information will be generated directly, including the specific details of the equipment abnormality.

[0044] The resolution of the input image for the device anomaly detection model is 640*640.

[0045] This application also discloses an intelligent image detection system for beer production equipment based on unmanned vehicles and edge computing, including:

[0046] Memory, used to store instructions;

[0047] A processor is configured to call instructions in memory and, when executed, implement the method for intelligent image detection of beer production equipment based on unmanned vehicles and edge computing as described in any one of claims 1 to 7.

[0048] The processor can be a central processing unit (CPU). Of course, depending on the actual use, other general-purpose processors can also be used. The general-purpose processor can be a microprocessor or any conventional processor. This application does not limit this.

[0049] The memory can be an internal storage unit of a computer device, such as a hard disk or RAM, or an external storage device of a computer device, such as a plug-in hard disk, a smart memory card (SMC), a secure digital card (SD), or a flash memory card (FC). Furthermore, the memory can be a combination of internal storage units and external storage devices of a computer device, and this application does not limit this.

[0050] This application also provides a machine-readable storage medium storing instructions that cause a machine to execute the above-described intelligent image detection method for beer production equipment based on unmanned vehicles and edge computing.

[0051] Those skilled in the art will understand that embodiments of this application may be provided as methods, systems, or computer program products. Therefore, this application may take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application may take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0052] This application describes methods, apparatus (systems), and computer program products of embodiments using flowcharts and / or block diagrams. Computer program instructions are available to implement each block of the flowcharts and / or block diagrams, as well as combinations of blocks in the flowcharts and / or block diagrams. These computer program instructions can be provided to a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which are executed by its processor, generate instructions for implementing the flowcharts and block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0053] These computer program instructions can be stored in a computer-readable storage medium, causing the instructions stored in the computer-readable storage medium to produce an article of manufacture including an instruction means, which is implemented in a process. Figure 1 a process or multiple processes and / or boxes Figure 1The function specified in one or more boxes.

[0054] These computer program instructions can be loaded onto a computer or other programmable data processing equipment to perform a series of operational steps to produce a computer-implemented process, thereby providing instructions that execute on a computer or other programmable equipment for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0055] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0056] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash memory. Memory is an example of computer-readable media.

[0057] Computer-readable media include both permanent and non-permanent, removable and non-removable media that can store information by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media do not include transient computer-readable media, such as modulated data signals and carrier waves.

[0058] In summary, this invention can acquire image information of beer factory production equipment based on unmanned vehicles, and detect the acquired equipment image information based on edge computing modules and equipment anomaly detection models. If an equipment anomaly is detected, the anomaly information is sent to the monitoring terminal and an alarm is generated to help improve the management efficiency of beer factory production equipment.

[0059] It should be noted that in the above embodiments, terms such as "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0060] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A method and system for intelligent image detection of beer production equipment based on unmanned vehicles and edge computing, characterized in that, include: The inspection unmanned vehicle, which is applied to autonomous vehicles, includes an image acquisition module, an edge computing module, and an ultrasonic obstacle avoidance module. The image acquisition module is located on the top of the inspection unmanned vehicle, the edge computing module is located inside the inspection unmanned vehicle, and the ultrasonic module is located at the bottom of the inspection unmanned vehicle. According to the preset beer factory inspection plan, the inspection unmanned vehicle is controlled to perform beer factory inspection tasks according to the preset inspection route, which includes preset equipment inspection sections. When the unmanned inspection vehicle enters the equipment inspection section, it continuously collects image information of the beer factory production equipment using the image acquisition module, reads the equipment image information using the edge computing module, and uses the equipment anomaly detection model to identify anomalies in the image information. When the edge computing module detects abnormal information, it sends the abnormal information to the monitoring terminal and generates an alarm message.

2. The method according to claim 1, characterized in that, Training the device anomaly detection model includes the following steps: Obtain the dataset and label the devices in the dataset; Set training parameters and train the model using training and test sets. In each training round, the model extracts device features from the training set images and associates these features with the target labels. After each training round, the model performance is evaluated using a validation set. The evaluation focuses on the average accuracy when the ratio of the overlap area of ​​the predicted bounding box to the union area of ​​the ground truth bounding box is 0.

5. After the evaluation, the model parameters are optimized. The model completes training after reaching the set number of training rounds. The best model and the last model are saved during training, with the best model serving as the final device anomaly detection model.

3. The method according to claim 2, characterized in that, Obtaining the dataset and labeling the devices in the dataset includes: The unmanned vehicle uses the image acquisition module to collect images of the beer factory production equipment on the preset equipment inspection section, and collects image data at different times including daytime, noon, and evening, as well as data on different weather conditions including sunny and rainy days. Label the equipment in the image using a rectangle to select the brewery production equipment to be inspected and label its status.

4. The method as described in claim 3, characterized in that, The equipment status includes one or more of the following: normal equipment, detached angle steel, detached bolts, spilled alcohol, leaking pressure reducing valve, detached conduit, dripping pipe, abnormal wiring, and damaged pressure gauge.

5. The method according to claim 1, characterized in that, The trained device anomaly detection model is deployed to the autonomous vehicle, and the detection of device image information acquired by the image acquisition module on the autonomous vehicle includes: First, the environment configuration and necessary plugins for running the device anomaly detection model are set up on the edge computing module on the unmanned vehicle; after installation, the device anomaly detection model is uploaded to the edge computing module on the unmanned vehicle. Secondly, the image acquisition module communicates with the edge computing module. The unmanned vehicle can read the device image information acquired by the image acquisition module in real time and detect the device status in the read device image information. If the device is abnormal, the device abnormal information is output and the target is marked with a rectangle.

6. The method as described in claim 5, characterized in that, If the equipment image is determined to contain one or more of the following: detached angle steel, detached bolts, spilled liquor, leaking pressure reducing valve, detached conduit, dripping pipe, abnormal wiring, or damaged pressure gauge, then equipment abnormality information will be generated directly, including the specific details of the equipment abnormality.

7. The method as described in claim 2, characterized in that, The resolution of the input image for the device anomaly detection model is 640*640.

8. An intelligent image detection system for beer production equipment based on unmanned vehicles and edge computing, characterized in that, include: Memory, used to store instructions; A processor is configured to call instructions in memory and, when executed, implement the method for intelligent image detection of beer production equipment based on unmanned vehicles and edge computing as described in any one of claims 1 to 7.

Images