Method, device and computer equipment for monitoring engine operating state

Abstract

The application relates to an engine operation state monitoring method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: acquiring a plurality of historical images of an engine in a historical time period, corresponding historical operation parameter values, and corresponding historical alarm information; sorting and interpolating the historical operation parameter values and the historical images to obtain intermediate operation parameter values and intermediate images; updating the historical image sequence through the intermediate images to obtain a sample image sequence; determining the historical operation state of the engine according to at least one of the historical alarm information, the historical operation parameter values or the intermediate operation parameter values; taking the sample image as the input of an initial model, taking the historical operation state of the engine as the training label of the initial model, training the initial model to obtain an operation state evaluation model. The method can improve the monitoring efficiency of the engine operation state.

Description

Technical Field

[0001] This application relates to the field of engine technology, and in particular to a method, apparatus, computer equipment, storage medium, and computer program product for monitoring the operating status of an engine. Background Technology

[0002] With the development of engine technology, engine testing technology has emerged. Before a car leaves the factory, the engine must undergo extensive durability tests on a test bench to ensure that its emissions performance, reliability, and durability meet the requirements.

[0003] Traditional engine test bench monitoring methods involve assigning operators to manually monitor the engines' operating status on the test bench. In scenarios where multiple engines are being tested simultaneously, this traditional method requires operators to move between different test benches to observe the operating status of each engine. Therefore, this traditional method suffers from low monitoring efficiency. Summary of the Invention

[0004] Therefore, it is necessary to provide a method, device, computer equipment, computer-readable storage medium, and computer program product for monitoring engine operating status that can improve monitoring efficiency in response to the above-mentioned technical problems.

[0005] Firstly, this application provides a method for monitoring the operating status of an engine. The method includes:

[0006] Acquire multiple historical images of the engine within a historical time period, corresponding sets of historical operating parameter values, and corresponding multiple historical alarm information;

[0007] Multiple sets of historical operating parameter values ​​and multiple historical images of the engine are sorted to obtain a sequence of historical operating parameter values ​​and a corresponding sequence of historical images;

[0008] Interpolation is performed on any two adjacent sets of historical operating parameter values ​​in the historical operating parameter value sequence to obtain multiple sets of intermediate operating parameter values. Interpolation is also performed on any two adjacent historical images in the historical image sequence to obtain multiple intermediate images.

[0009] The historical image sequence is updated using multiple intermediate images to obtain the sample image sequence;

[0010] Based on at least one of multiple historical alarm information, multiple sets of historical operating parameter values, or multiple sets of intermediate operating parameter values, determine the historical operating status of the engine corresponding to each sample image in the sample image sequence.

[0011] The sample images are used as input to the initial model, and the historical operating states of the engine corresponding to the sample images are used as training labels for the initial model. The initial model is trained to obtain the operating state evaluation model, which is used to monitor the operating state of the engine.

[0012] In one embodiment, the types of historical operating parameter values ​​include at least one of speed, torque, exhaust temperature, oil pressure, or power efficiency. Interpolation processing is performed on any two adjacent sets of historical operating parameter values ​​in the historical operating parameter value sequence to obtain multiple sets of intermediate operating parameter values. This includes calculating the comprehensive value corresponding to each type of any two adjacent sets of historical operating parameter values ​​in the historical operating parameter value sequence according to the type of historical operating parameter values, and determining multiple sets of intermediate operating parameter values ​​based on the combination of the comprehensive values ​​corresponding to each type. Interpolation processing is also performed on any two adjacent historical images in the historical image sequence to obtain multiple intermediate images. This includes calculating the comprehensive value of the brightness corresponding to each color channel of any two adjacent historical images in the historical image sequence according to the brightness of the color channels, and determining multiple intermediate images based on the comprehensive value of the brightness corresponding to each color channel.

[0013] In one embodiment, according to the brightness of the color channels, the comprehensive value of the brightness corresponding to each color channel of any two adjacent historical images in the historical image sequence is calculated. Based on the comprehensive value of the brightness corresponding to each color channel, multiple intermediate images are determined, including: segmenting each historical image in the historical image sequence to obtain a historical bitmap image corresponding to each historical image, the historical bitmap image including multiple pixel blocks; determining the historical bitmap images of any two adjacent historical images in the historical image sequence; obtaining the comprehensive value of the brightness of the pixel blocks corresponding to the same position in the two determined historical bitmap images; and obtaining an intermediate image based on the comprehensive value corresponding to each position.

[0014] In one embodiment, the sample image is a historical image or an intermediate image, and the historical alarm information is used to characterize whether the engine has experienced a routine fault, and the historical operating state is normal operation or abnormal operation; the historical operating state of the engine corresponding to each sample image in the sample image sequence is determined based on at least one of multiple historical alarm information, multiple sets of historical operating parameter values, or multiple sets of intermediate operating parameter values, including determining the historical operating state of the engine corresponding to each historical image in the sample image sequence based on at least one of multiple historical alarm information or multiple sets of historical operating parameter values; and determining the historical operating state of the engine corresponding to each intermediate image in the sample image sequence based on multiple sets of intermediate operating parameter values.

[0015] In one embodiment, the method further includes acquiring target images of the surfaces of multiple engines at a target time using an infrared camera; evaluating the target image of the current engine using an operating status evaluation model to determine whether the operating status of the current engine at the target time is abnormal; and in the case that the operating status of the current engine is abnormal, instructing the user terminal to perform fault handling on the current engine through a microcontroller.

[0016] In one embodiment, when the current engine is in an abnormal operating state, the user terminal is instructed to perform fault handling on the current engine through the microcontroller. This includes instructing the user terminal to send control commands to the microcontroller when the current engine is in an abnormal operating state, and sending the control commands to the local area network controller through the microcontroller, and then sending the control commands to the electronic control unit of the current engine through the local area network controller, so as to control the current engine to return to idle speed or stop.

[0017] Secondly, this application also provides a monitoring device for engine operating status. The device includes:

[0018] The acquisition module is used to acquire multiple historical images of the engine within a historical time period, multiple sets of corresponding historical operating parameter values, and multiple corresponding historical alarm information.

[0019] The sorting module is used to sort multiple sets of historical operating parameter values ​​and multiple historical images of the engine to obtain a sequence of historical operating parameter values ​​and a corresponding sequence of historical images.

[0020] The interpolation module is used to interpolate any two adjacent sets of historical operating parameter values ​​in the historical operating parameter value sequence to obtain multiple sets of intermediate operating parameter values, and to interpolate any two adjacent historical images in the historical image sequence to obtain multiple intermediate images.

[0021] The update module is used to update the historical image sequence using multiple intermediate images to obtain the sample image sequence;

[0022] The determination module is used to determine the historical operating status of the engine corresponding to each sample image in the sample image sequence based on at least one of multiple historical alarm information, multiple sets of historical operating parameter values, or multiple sets of intermediate operating parameter values.

[0023] The training module is used to take sample images as input to the initial model and the historical operating states of the engine corresponding to the sample images as training labels for the initial model. The initial model is trained to obtain the operating state evaluation model, which is used to monitor the operating state of the engine.

[0024] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to perform the following steps:

[0025] Acquire multiple historical images of the engine within a historical time period, corresponding sets of historical operating parameter values, and corresponding multiple historical alarm information;

[0026] Multiple sets of historical operating parameter values ​​and multiple historical images of the engine are sorted to obtain a sequence of historical operating parameter values ​​and a corresponding sequence of historical images;

[0027] Interpolation is performed on any two adjacent sets of historical operating parameter values ​​in the historical operating parameter value sequence to obtain multiple sets of intermediate operating parameter values. Interpolation is also performed on any two adjacent historical images in the historical image sequence to obtain multiple intermediate images.

[0028] The historical image sequence is updated using multiple intermediate images to obtain the sample image sequence;

[0029] Based on at least one of multiple historical alarm information, multiple sets of historical operating parameter values, or multiple sets of intermediate operating parameter values, determine the historical operating status of the engine corresponding to each sample image in the sample image sequence.

[0030] The sample images are used as input to the initial model, and the historical operating states of the engine corresponding to the sample images are used as training labels for the initial model. The initial model is trained to obtain the operating state evaluation model, which is used to monitor the operating state of the engine.

[0031] Fourthly, this application also provides a computer-readable storage medium. This computer-readable storage medium stores a computer program thereon, which, when executed by a processor, performs the following steps:

[0032] Acquire multiple historical images of the engine within a historical time period, corresponding sets of historical operating parameter values, and corresponding multiple historical alarm information;

[0033] Multiple sets of historical operating parameter values ​​and multiple historical images of the engine are sorted to obtain a sequence of historical operating parameter values ​​and a corresponding sequence of historical images;

[0034] Interpolation is performed on any two adjacent sets of historical operating parameter values ​​in the historical operating parameter value sequence to obtain multiple sets of intermediate operating parameter values. Interpolation is also performed on any two adjacent historical images in the historical image sequence to obtain multiple intermediate images.

[0035] The historical image sequence is updated using multiple intermediate images to obtain the sample image sequence;

[0036] Based on at least one of multiple historical alarm information, multiple sets of historical operating parameter values, or multiple sets of intermediate operating parameter values, determine the historical operating status of the engine corresponding to each sample image in the sample image sequence.

[0037] The sample images are used as input to the initial model, and the historical operating states of the engine corresponding to the sample images are used as training labels for the initial model. The initial model is trained to obtain the operating state evaluation model, which is used to monitor the operating state of the engine.

[0038] Fifthly, this application also provides a computer program product. This computer program product includes a computer program that, when executed by a processor, performs the following steps:

[0039] Acquire multiple historical images of the engine within a historical time period, corresponding sets of historical operating parameter values, and corresponding multiple historical alarm information;

[0040] Multiple sets of historical operating parameter values ​​and multiple historical images of the engine are sorted to obtain a sequence of historical operating parameter values ​​and a corresponding sequence of historical images;

[0041] Interpolation is performed on any two adjacent sets of historical operating parameter values ​​in the historical operating parameter value sequence to obtain multiple sets of intermediate operating parameter values. Interpolation is also performed on any two adjacent historical images in the historical image sequence to obtain multiple intermediate images.

[0042] The historical image sequence is updated using multiple intermediate images to obtain the sample image sequence;

[0043] Based on at least one of multiple historical alarm information, multiple sets of historical operating parameter values, or multiple sets of intermediate operating parameter values, determine the historical operating status of the engine corresponding to each sample image in the sample image sequence.

[0044] The sample images are used as input to the initial model, and the historical operating states of the engine corresponding to the sample images are used as training labels for the initial model. The initial model is trained to obtain the operating state evaluation model, which is used to monitor the operating state of the engine.

[0045] The aforementioned engine operation status monitoring method, device, computer equipment, storage medium, and computer program product acquire multiple historical images of the engine, corresponding sets of historical operating parameter values, and corresponding sets of historical alarm information within a historical time period. They then sort and interpolate the multiple sets of historical operating parameter values ​​and the multiple historical images to obtain multiple sets of intermediate operating parameter values ​​and a sequence of sample images. Based on at least one of the multiple historical alarm information, multiple sets of historical operating parameter values, or multiple sets of intermediate operating parameter values, they determine the historical operating status of the engine corresponding to each sample image in the sample image sequence. Based on each sample image in the sample image sequence and its corresponding historical operating status, they train an initial model to obtain an operation status evaluation model. This operation status evaluation model is used to monitor the engine's operation status. Compared to manual monitoring, this method can automatically monitor the engine's operation status through the operation status evaluation model, thus improving the monitoring efficiency of the engine's operation status. Attached Figure Description

[0046] Figure 1 This is an application environment diagram of a method for monitoring engine operating status in one embodiment;

[0047] Figure 2 This is a flowchart illustrating a method for monitoring engine operating status in one embodiment;

[0048] Figure 3 This is a flowchart illustrating the step of determining an intermediate image in one embodiment;

[0049] Figure 4 This is a schematic diagram of the structure of a monitoring system for engine operating status in one embodiment;

[0050] Figure 5 This is a flowchart illustrating a method for monitoring engine operating status in another embodiment;

[0051] Figure 6 This is a structural block diagram of a monitoring device for engine operating status in one embodiment;

[0052] Figure 7 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0053] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0054] The engine operation status monitoring method provided in this application embodiment can be applied to, for example, Figure 1In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104 or placed on a cloud or other network server. Terminal 102 can independently execute the engine operation status monitoring method provided in this application embodiment, and terminal 102 and server 104 can also collaboratively execute the engine operation status monitoring method provided in this application embodiment.

[0055] When terminal 102 executes the engine operation status monitoring method alone, terminal 102 acquires multiple historical images of the engine within a historical time period, multiple sets of corresponding historical operation parameter values, and multiple historical alarm information; sorts the multiple sets of historical operation parameter values ​​and multiple historical images of the engine to obtain a historical operation parameter value sequence and a corresponding historical image sequence; interpolates any two adjacent sets of historical operation parameter values ​​in the historical operation parameter value sequence to obtain multiple sets of intermediate operation parameter values, and interpolates any two adjacent historical images in the historical image sequence to obtain multiple intermediate images; updates the historical image sequence with multiple intermediate images to obtain a sample image sequence; determines the historical operation status of the engine corresponding to each sample image in the sample image sequence based on at least one of multiple historical alarm information, multiple sets of historical operation parameter values, or multiple sets of intermediate operation parameter values; uses the sample images as input to the initial model, uses the historical operation status of the engine corresponding to the sample images as training labels for the initial model, trains the initial model to obtain an operation status evaluation model, and uses the operation status evaluation model to monitor the engine operation status.

[0056] When terminal 102 and server 104 work together to execute the engine operation status monitoring method, terminal 102 acquires multiple historical images of the engine within a historical time period, multiple sets of corresponding historical operating parameter values, and multiple corresponding historical alarm information, and sends the multiple historical images, multiple sets of corresponding historical operating parameter values, and multiple corresponding historical alarm information to server 104. Server 104 sorts multiple sets of historical operating parameter values ​​and multiple historical images of the engine to obtain a sequence of historical operating parameter values ​​and a corresponding sequence of historical images. It then interpolates any two adjacent sets of historical operating parameter values ​​in the sequence to obtain multiple sets of intermediate operating parameter values, and interpolates any two adjacent historical images in the sequence to obtain multiple intermediate images. The server updates the historical image sequence using these intermediate images to obtain a sample image sequence. Based on at least one of multiple historical alarm messages, multiple sets of historical operating parameter values, or multiple sets of intermediate operating parameter values, the server determines the historical operating state of the engine corresponding to each sample image in the sample image sequence. The server uses the sample images as input to the initial model and the historical operating state of the engine corresponding to the sample images as the training label for the initial model, training the initial model to obtain an operating state evaluation model. This operating state evaluation model is used to monitor the operating state of the engine.

[0057] The terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, and smart in-vehicle systems. Portable wearable devices can include smartwatches, smart bracelets, and head-mounted devices. The server 104 can be implemented using a standalone server or a server cluster consisting of multiple servers.

[0058] In one embodiment, such as Figure 2 As shown, a method for monitoring engine operating status is provided. This method can be executed by a terminal or server alone, or by both a terminal and server collaboratively. This method is applied to... Figure 1 Taking terminal 102 as an example, the explanation includes the following steps:

[0059] Step 202: Obtain multiple historical images of the engine within the historical time period, multiple sets of corresponding historical operating parameter values, and multiple corresponding historical alarm information.

[0060] The engine in question is the test engine on the engine test bench during the testing phase. The historical time period includes many historical moments, each corresponding to a historical image, a set of historical operating parameter values, and a historical alarm message. Therefore, there is a correspondence between each historical image, each set of historical operating parameter values, and each historical alarm message.

[0061] Historical images are infrared images taken by infrared cameras at historical moments in the test chamber where the engine is located, including images of the engine surface.

[0062] Because the wavelength range of infrared light radiated from the engine and other objects in the engine testing chamber (approximately 0.75 micrometers to 1000 micrometers) is much larger than that of visible light (approximately 390 nanometers to 760 nanometers), problems that are difficult to distinguish with the naked eye or ordinary cameras, such as fuel leaks, intake and exhaust leaks, overheating of certain parts of the engine, and cracks in certain parts of the engine, are clearly visible in infrared images. Therefore, by acquiring infrared images of the engine surface, the accuracy of monitoring the engine's operating status can be improved, thereby increasing the efficiency of engine operating status monitoring.

[0063] Historical operating parameter values ​​are engine operating parameter values ​​obtained through the engine's electronic control unit at historical moments, including at least one type of historical operating parameter values ​​such as engine speed, torque, throttle, coolant temperature, exhaust temperature, oil pressure, intercooler pressure, or power output. If the historical operating parameter values ​​include one type (i.e., engine speed, torque, throttle, coolant temperature, exhaust temperature, oil pressure, intercooler pressure, or power output), then that type of historical operating parameter value is considered as a set of historical operating parameter values. If the historical operating parameter values ​​include at least two types (i.e., engine speed, torque, throttle, coolant temperature, exhaust temperature, oil pressure, intercooler pressure, or power output), then the historical operating parameter values ​​of at least two types are considered as a set of historical operating parameter values.

[0064] Historical alarm information is alarm information obtained through the engine electronic control unit at historical moments. It is used to characterize whether the engine experienced a routine fault at a historical moment, such as excessively high water temperature.

[0065] For example, an infrared camera captures images of the engine surface during the testing phase on an engine test bench within a historical time period, obtaining multiple historical images, and sends these images to a terminal. The engine's electronic control unit acquires the operating parameter values ​​and alarm information of the engine during the testing phase on the engine test bench within the historical time period, obtaining multiple sets of historical operating parameter values ​​and multiple historical alarm messages, and sends these to the terminal. The terminal acquires multiple historical images, multiple sets of historical operating parameter values, and multiple historical alarm messages of the engine within the historical time period, and associates a historical image, a set of historical operating parameter values, and a historical alarm message corresponding to the same historical moment, obtaining multiple historical images of the engine within the historical time period, corresponding multiple sets of historical operating parameter values, and corresponding multiple historical alarm messages.

[0066] Step 204: Sort the multiple sets of historical operating parameter values ​​and multiple historical images of the engine to obtain the historical operating parameter value sequence and the corresponding historical image sequence.

[0067] Since each historical image, each set of historical operating parameter values, and each historical alarm message are associated, the order of each set of historical operating parameter values ​​in the historical operating parameter value sequence is consistent with the order of each historical image in the historical image sequence.

[0068] For example, the terminal sorts multiple sets of historical operating parameter values ​​of the engine according to their numerical values ​​to obtain a sequence of historical operating parameter values. Since each historical image and each set of historical operating parameter values ​​are associated, a sequence of historical images corresponding to the historical operating parameter value sequence is also obtained at the same time.

[0069] When the historical operating parameter values ​​include at least two types, such as a set of historical operating parameter values ​​including historical operating speed (speed value) and historical operating torque (torque value), the terminal first determines the magnitude of multiple speed values ​​in the multiple sets of historical operating parameter values, and sorts the multiple sets of historical operating parameter values ​​of the engine in descending order of speed value to obtain an initial sequence of historical operating parameter values; and when at least two speed values ​​are the same, the magnitude of the torque value corresponding to the speed value is determined, and the initial sequence of historical operating parameter values ​​is sorted in descending order of torque value to obtain a sequence of historical operating parameter values.

[0070] Step 206: Interpolate any two adjacent sets of historical operating parameter values ​​in the historical operating parameter value sequence to obtain multiple sets of intermediate operating parameter values, and interpolate any two adjacent historical images in the historical image sequence to obtain multiple intermediate images.

[0071] The intermediate operating parameter values ​​are a set of operating parameter values ​​obtained through interpolation, and the intermediate image is an image obtained through interpolation.

[0072] For example, the terminal performs interpolation processing on any two adjacent sets of historical operating parameter values ​​in the historical operating parameter value sequence to obtain multiple sets of intermediate operating parameter values, and performs interpolation processing on any two adjacent historical images in the historical image sequence to obtain multiple intermediate images.

[0073] Taking a historical operation parameter value sequence consisting of 4 sets of historical operation parameter values ​​and a corresponding historical image sequence consisting of 4 sets of historical images as an example, interpolation is performed on any two adjacent sets of historical operation parameter values ​​in the historical operation parameter value sequence to obtain 3 sets of intermediate operation parameter values, and interpolation is performed on any two adjacent historical images in the historical image sequence to obtain 3 intermediate images.

[0074] Step 208: Update the historical image sequence with multiple intermediate images to obtain the sample image sequence.

[0075] The sample image sequence is an image sequence obtained by adding multiple intermediate images to the historical image sequence. The sample image sequence includes multiple sample images, which can be intermediate images or historical images.

[0076] For example, the terminal uses multiple intermediate images and historical image sequences together as a sample image sequence.

[0077] Step 210: Determine the historical operating status of the engine corresponding to each sample image in the sample image sequence based on at least one of multiple historical alarm information, multiple sets of historical operating parameter values, or multiple sets of intermediate operating parameter values.

[0078] The historical operating status is either normal operation or abnormal operation.

[0079] For example, the terminal determines whether the historical operating status of the engine corresponding to each sample image in the sample image sequence is normal operation or abnormal operation based on at least one of multiple historical alarm information, multiple sets of historical operating parameter values, or multiple sets of intermediate operating parameter values.

[0080] Step 212: Use the sample image as input to the initial model, and use the historical operating status of the engine corresponding to the sample image as the training label of the initial model to train the initial model to obtain the operating status evaluation model. The operating status evaluation model is used to monitor the operating status of the engine.

[0081] The initial model can be a neural network model used to evaluate the historical operating status of the engine corresponding to the sample image. The operating status evaluation model can be a trained neural network model used to evaluate the engine's operating status in order to monitor the engine's operating status.

[0082] For example, the terminal inputs a sample image into the initial model, and the initial model extracts features from the sample image to obtain multiple feature information of the sample image, including shape, brightness of color channels, texture, image spectrum, and image histogram; based on the multiple feature information of the sample image, the predicted operating state of the engine corresponding to the sample image is determined; based on the predicted operating state and historical operating state of the engine corresponding to the sample image, the initial model is trained to obtain an operating state evaluation model.

[0083] In the aforementioned method for monitoring engine operating status, multiple historical images of the engine, corresponding sets of historical operating parameter values, and corresponding sets of historical alarm information within a historical time period are acquired. The multiple sets of historical operating parameter values ​​and the multiple historical images are then sorted and interpolated to obtain multiple sets of intermediate operating parameter values ​​and a sequence of sample images. Based on at least one of the multiple historical alarm information, multiple sets of historical operating parameter values, or multiple sets of intermediate operating parameter values, the historical operating status of the engine corresponding to each sample image in the sample image sequence is determined. Based on each sample image in the sample image sequence and its corresponding historical operating status, an initial model is trained to obtain an operating status evaluation model. This operating status evaluation model is used to monitor the engine's operating status. Compared to manual monitoring, this method can automatically monitor the engine's operating status through the operating status evaluation model, thus improving the monitoring efficiency of engine operating status.

[0084] In one embodiment, the types of historical operating parameter values ​​include at least one of speed, torque, exhaust temperature, oil pressure, or power efficiency. Interpolation processing is performed on any two adjacent sets of historical operating parameter values ​​in the historical operating parameter value sequence to obtain multiple sets of intermediate operating parameter values. This includes calculating the comprehensive value corresponding to each type of any two adjacent sets of historical operating parameter values ​​in the historical operating parameter value sequence according to the type of historical operating parameter values, and determining multiple sets of intermediate operating parameter values ​​based on the combination of comprehensive values ​​corresponding to each type.

[0085] The comprehensive value is obtained by weighting and summing two historical operating parameter values ​​of the same type from any two adjacent sets of historical operating parameter values ​​according to a preset weight. The preset weight is set in advance according to monitoring requirements, and this embodiment does not limit it. When the preset weight of both historical operating parameter values ​​is 0.5, the comprehensive value is the average of the two historical operating parameter values.

[0086] For example, the types of historical operating parameter values ​​include speed and torque. In this case, a set of historical operating parameter values ​​includes speed value and torque value. For the current two adjacent historical operating parameter values ​​in the multiple sets of two adjacent historical operating parameter values ​​included in the historical operating parameter value sequence, the terminal performs a weighted summation of the speed value and torque value in the current two adjacent historical operating parameter values ​​to obtain a comprehensive value of speed and a comprehensive value of torque. The comprehensive value of speed and the comprehensive value of torque are associated to obtain a set of intermediate operating parameter values.

[0087] Interpolation processing is performed on any two adjacent historical images in the historical image sequence to obtain multiple intermediate images. This includes calculating the comprehensive value of the brightness of each color channel of any two adjacent historical images in the historical image sequence according to the brightness of each color channel, and determining multiple intermediate images based on the comprehensive value of the brightness of each color channel.

[0088] The color channels include three color channels: red (R), green (G), and blue (B). Each of the three color channels has 256 levels of brightness from 0 to 255, with the brightness being weakest at 0 and strongest at 255.

[0089] For example, for the current two adjacent historical images among multiple adjacent historical images included in the historical image sequence, the terminal performs a weighted summation of the brightness corresponding to the red, green, and blue channels of the current two adjacent historical images to obtain a comprehensive value of the brightness corresponding to the red channel, the comprehensive value of the brightness corresponding to the green channel, and the comprehensive value of the brightness corresponding to the blue channel; and associates the comprehensive values ​​of the brightness corresponding to the red channel, the comprehensive value of the brightness corresponding to the green channel, and the comprehensive value of the brightness corresponding to the blue channel to obtain an intermediate image.

[0090] In this embodiment, by calculating the comprehensive value corresponding to each type in any two adjacent sets of historical operating parameter values ​​in the historical operating parameter value sequence, and the comprehensive value of the brightness corresponding to each color channel in any two adjacent historical images in the historical image sequence, the purpose of determining multiple sets of intermediate operating parameter values ​​can be achieved based on the comprehensive value corresponding to each type in any two adjacent sets of historical operating parameter values, and the purpose of determining multiple intermediate images can be achieved based on the comprehensive value of the brightness corresponding to each color channel in any two adjacent historical images.

[0091] In one embodiment, such as Figure 3 As shown, based on the brightness of each color channel, the combined brightness value of each color channel of any two adjacent historical images in the historical image sequence is calculated. Based on the combined brightness value of each color channel, multiple intermediate images are determined, including:

[0092] Step 302: Segment each historical image in the historical image sequence to obtain a historical bitmap image corresponding to each historical image. The historical bitmap image includes multiple pixel blocks.

[0093] The historical bitmap image is a segmented historical image, and the historical bitmap image and the historical image have the same size. Each historical bitmap image consists of M*N (M and N are both positive integers) pixel blocks. For example, a historical image with a size of 40cm*40cm is segmented into 2 rows and 2 columns to obtain a historical bitmap image, which consists of 4 pixel blocks, and each pixel block has a size of 20cm*20cm.

[0094] For example, the terminal segments each historical image in the historical image sequence to obtain the historical bitmap image corresponding to each historical image.

[0095] Step 304: Determine the historical bitmap images of any two adjacent historical images in the historical image sequence.

[0096] For example, the terminal determines the historical bitmap images of any two adjacent historical images in the historical image sequence.

[0097] Step 306: Obtain the combined brightness value of the pixel blocks at the same position in the two determined historical bitmap images, and obtain an intermediate image based on the combined value corresponding to each position.

[0098] For example, a historical bitmap image includes four pixel blocks. The terminal obtains the brightness corresponding to the red channel, the brightness corresponding to the green channel, and the brightness corresponding to the blue channel of the four pixel blocks in two determined historical bitmap images. Then, it performs a weighted summation on the brightness corresponding to the red channel, the brightness corresponding to the green channel, and the brightness corresponding to the blue channel of four pixel blocks at the same position in the two historical bitmap images (e.g., in a Cartesian coordinate system with the lower left corner of the image as the origin, the pixel block located in the first row and first column, the pixel block in the first row and second column, the pixel block in the second row and first column, and the pixel block in the second row and second column), to obtain a combined value of the brightness corresponding to the red channel, the combined value of the green channel, and the combined value of the blue channel of the four pixel blocks. The combined values ​​of the red channel, the green channel, and the blue channel are associated to obtain four intermediate pixel blocks. Based on the four intermediate pixel blocks, an intermediate image is obtained.

[0099] In this embodiment, by segmenting historical images, multiple pixel blocks corresponding to the historical images are obtained. The combined brightness value of the pixel blocks at the same position in the historical dot matrix images of any two adjacent historical images is calculated. Based on the combined values ​​corresponding to each position, an intermediate image is obtained. Since the historical images are segmented into multiple pixel blocks, the accuracy of the brightness corresponding to each color channel of the intermediate image can be improved by interpolating the pixel blocks. This helps to improve the accuracy of monitoring the engine operating status, and thus improves the monitoring efficiency of the engine operating status.

[0100] In one embodiment, the sample image is a historical image or an intermediate image, and the historical alarm information is used to characterize whether the engine has experienced a routine fault, and the historical operating state is normal operation or abnormal operation; the historical operating state of the engine corresponding to each sample image in the sample image sequence is determined based on at least one of multiple historical alarm information, multiple sets of historical operating parameter values, or multiple sets of intermediate operating parameter values, including determining the historical operating state of the engine corresponding to each historical image in the sample image sequence based on at least one of multiple historical alarm information or multiple sets of historical operating parameter values; and determining the historical operating state of the engine corresponding to each intermediate image in the sample image sequence based on multiple sets of intermediate operating parameter values.

[0101] For example, the terminal determines the historical operating status of the engine corresponding to each historical image in the sample image sequence based on at least one of multiple historical alarm information or multiple sets of historical operating parameter values; if the intermediate operating parameter value corresponding to any type of the current set of intermediate operating parameter values ​​exceeds a preset range, the historical operating status of the engine corresponding to the current intermediate image in the sample image sequence associated with the current set of intermediate operating parameter values ​​is determined to be abnormal operation; if the intermediate operating parameter values ​​corresponding to each type of the current set of intermediate operating parameter values ​​do not exceed the preset range, the historical operating status of the engine corresponding to the current intermediate image is determined to be normal operation.

[0102] In one embodiment, the historical operating state of the engine corresponding to each historical image in the sample image sequence is determined based on at least one of multiple historical alarm information or multiple sets of historical operating parameter values. This includes determining the historical operating state of the engine corresponding to the current historical image associated with the current historical alarm information as abnormal operation when the current historical alarm information indicates that the engine has experienced a conventional fault; determining the historical operating state of the engine corresponding to the current historical image as abnormal operation when the current historical alarm information indicates that the engine has not experienced a conventional fault and the historical operating parameter value corresponding to any type of the current set of historical operating parameter values ​​associated with the current historical alarm information exceeds a preset range; and determining the historical operating state of the engine corresponding to the current historical image as normal operation when the current historical alarm information indicates that the engine has not experienced a conventional fault and the historical operating parameter values ​​corresponding to each type of the current set of historical operating parameter values ​​do not exceed a preset range.

[0103] In this embodiment, by analyzing the historical operating status of the engine corresponding to each sample image according to different values ​​of historical alarm information, historical operating parameter values, or intermediate operating parameter values, it is possible to determine the historical operating status of the engine corresponding to each sample image based on at least one of multiple historical alarm information, multiple sets of historical operating parameter values, or multiple sets of intermediate operating parameter values.

[0104] In one embodiment, the method further includes acquiring target images of the surfaces of multiple engines at a target time using an infrared camera; evaluating the target image of the current engine using an operating status evaluation model to determine whether the operating status of the current engine at the target time is abnormal; and in the case that the current engine is operating abnormally, instructing the user terminal to perform fault handling on the current engine through a microcontroller.

[0105] The infrared cameras are installed diagonally across the test chamber where multiple engines are located, and each engine is deployed on a different engine test bench. The current engine is any one of these multiple engines.

[0106] Figure 4 This is a schematic diagram of a monitoring system for the operating status of two engines within a test chamber. (For example...) Figure 4 As shown, test bench A and test bench B are arranged in the test chamber. The engine on test bench A is connected to the dynamometer, and the engine on test bench B is connected to the dynamometer.

[0107] Test bench A is an engine test bench that cannot provide data in various formats. Therefore, it is necessary to obtain the engine's operating data through the engine's Electronic Control Unit (ECU) and transmit the engine's operating data to the Controller Area Network (CAN) controller. The CAN controller then obtains the engine's operating data according to the communication protocol corresponding to test bench A and transmits the engine's operating data to the Microcontroller Unit (MCU). The MCU then converts the engine's operating data to obtain the engine's operating parameters and transmits the engine's operating parameters to the main control computer (i.e., the terminal).

[0108] Test bench B is an engine test bench that can provide data in various formats. Therefore, the engine's operating parameters can be directly obtained through test bench B and transmitted to the main control computer.

[0109] like Figure 4 As shown, infrared camera 1 and infrared camera 2 are also arranged at opposite corners of the test chamber. Infrared camera 1 and infrared camera 2 respectively capture images of the engine surface on test bench A and test bench B.

[0110] The main control computer connects to the user terminal via a network to transmit the engine's operating parameters to the user terminal, enabling the user to monitor the engine's operating status in real time. It is also used to receive control commands sent by the user terminal when the engine is operating abnormally, and to send the control commands to the electronic control unit of the abnormally operating engine through the microcontroller and local area network controller.

[0111] For example, the terminal acquires target images of the surfaces of multiple engines at a target time using an infrared camera. For the current engine among all engines, the target image corresponding to the current engine is input into the operating status evaluation model to obtain the operating status evaluation result of the current engine at the target time. If the operating status evaluation result indicates abnormal operation, the terminal instructs the user terminal to perform fault handling on the current engine through the microcontroller. Here, the target time is the current time, and the target image is the image acquired by the infrared camera at the target time.

[0112] In this embodiment, target images of the surfaces of multiple engines are acquired using infrared cameras at a target time, and the target images are evaluated using an operational status assessment model to determine whether the operational status of each engine is abnormal at the target time, thus achieving the purpose of real-time monitoring of the engine's operational status. Furthermore, if the engine's operational status is abnormal, the user terminal is instructed to perform fault handling on the engine via a microcontroller, achieving the purpose of timely handling of faults in abnormally operating engines.

[0113] In one embodiment, when the current engine is operating abnormally, the user terminal is instructed to perform fault handling on the current engine through the microcontroller. This includes instructing the user terminal to send control commands to the microcontroller when the current engine is operating abnormally, and then sending the control commands to the local area network controller through the microcontroller, and finally sending the control commands to the electronic control unit of the current engine through the local area network controller, so as to control the current engine to return to idle speed or stop.

[0114] The local area network controller is used to transmit data in different formats between the engine's electronic control unit and microcontroller, thereby overcoming the problem that engine operating parameters cannot be centrally displayed on a main control computer due to different communication protocols of engine test benches provided by different manufacturers.

[0115] For example, when the current engine is operating abnormally, the terminal instructs the user terminal to send control commands to the microcontroller, and the microcontroller converts the control commands into a format corresponding to the engine test bench where the current engine is located. The converted control commands are then sent to the local area network controller, which in turn sends them to the electronic control unit of the current engine to control the current engine to return to idle or stop.

[0116] In this embodiment, by instructing the user terminal to send control commands to the microcontroller, it is possible to handle engine malfunctions when the engine is operating abnormally.

[0117] In one embodiment, such as Figure 5As shown, a method for monitoring engine operating status is also provided. On one hand, two independent infrared cameras are installed diagonally across the engine test chamber to receive infrared radiation waves emitted by the engine and other objects within the test chamber. The photoelectric signals are converted into digital infrared information and transmitted to the main control computer, which then converts the infrared information into infrared images. On the other hand, engine information is directly read from the engine's ECU, the real-time storage data table of the test bench, or the real-time value database of the test bench. This engine information is then transmitted to the main control computer via a network. After receiving the engine information and infrared images from each test bench, the main control computer performs machine learning by combining the infrared images and engine information to determine the infrared image characteristics of the engine during normal operation. Thus, after sufficient machine learning samples, the main control computer can accurately determine whether the current engine operating status is normal and whether there are any abnormal conditions, such as localized overheating, leaks, or engine cracks.

[0118] The specific method is as follows:

[0119] 1. For engine test benches that cannot provide data in various formats in real time, engine information, including fault conditions (i.e., alarm information in the above embodiments) and operating parameter values, is obtained through the engine ECU. These operating parameter values ​​include engine speed, torque, throttle opening, etc. It should be noted that an MCU microcontroller and a CAN controller are used, directly connected to the engine ECU, to obtain real-time engine operating parameters.

[0120] 2. The MCU microcontroller converts the engine information into a new format and sends the converted engine information to the main control computer, which then decodes the engine information.

[0121] 3. Diagonally mounted infrared cameras within the test chamber capture images of the chamber's condition, including the engine. Due to varying engine operating conditions, molecules on the engine surface and other surfaces within the test chamber undergo irregular motion, generating infrared radiation of different wavelengths and intensities. The infrared cameras receive these photoelectric signals, convert them into digital signals, and transmit them to the main control computer via a network. According to electromagnetic spectroscopy theory, the visible spectrum has a narrow range, while the infrared spectrum has a wide band; therefore, infrared images can capture more details of the test chamber.

[0122] 4. After receiving the infrared information and the engine information transmitted from the engine ECU, the main control computer correlates the two and stores the correlated infrared image and engine information in the main control computer. A database is used for storage, with one data table created for each test bench. Engine information (including operating parameters such as speed, torque, and power, as well as alarm information) and the corresponding infrared image (binary digital information) are used as columns in the data table, serving as samples for the main control computer to train an artificial intelligence (AI) model for machine learning.

[0123] There are three ways to determine if the engine is currently malfunctioning, i.e., to identify the training label: The first way is through alarm information directly provided by the ECU via CAN signal, such as an alarm indicating excessively high coolant temperature. The second way is to determine if the engine operating parameters are within a reasonable range, such as whether the engine exhaust temperature exceeds a preset range. This method complements the first. The third way is based on the operator's experience, such as observing malfunctions like exhaust leaks in the test chamber.

[0124] 5. The main control computer preprocesses the samples stored in the database, including sorting the operating parameter values, alarm information and infrared images in the data table according to the values ​​of engine speed, torque and other values. Then, it enhances the infrared images to sharpen the edges and boundaries of the images. After that, it segments the infrared images, dividing an image into multiple rows and columns of pixel blocks (the dot matrix of the pixel blocks can be customized). Finally, it uses interpolation to obtain intermediate images under different speeds and torques.

[0125] 6. The main control computer performs machine learning based on the infrared images and intermediate images. Through genetic algorithms or neural network algorithms, the main control computer can initially grasp the infrared image characteristics of engine malfunctions and normal operation. These infrared features are automatically stored in a separate table in the database. As the number of samples increases and training is continuously strengthened, the main control computer can master the infrared image characteristics of each pixel block under normal engine operating conditions, as well as the infrared image characteristics of each pixel block under various fault conditions, thus establishing the correlation between operating status (including various faults) and the infrared image characteristics.

[0126] 7. Once the main control computer understands the correlation between the engine's operating status and infrared image characteristics, it can automatically monitor the engine's operation. Monitoring is based on the infrared image characteristics during normal operation. When each pixel block in the test chamber matches the infrared image characteristics during normal operation (e.g., pixel brightness, color, texture, image spectrum, image histogram, etc.), meaning the vast majority of pixel blocks match those trained under a certain operating condition, the main control computer can automatically infer the current engine's operating parameters (speed, torque, etc.). When most pixel blocks match the characteristic image, but some individual areas show significant deviations from normal image characteristics, it can be considered that the current engine is abnormal. When infrared image characteristics inconsistent with normal operation appear, the main control computer will issue an alarm and simultaneously search the fault feature database to see if this state is included in the known fault features. If the fault is included in the known fault characteristics, the main control computer will directly give the fault name. If it does not exist in the known fault characteristics, the fault will be displayed as unknown. At this time, the operator will analyze the fault and inform the main control computer of the current problem or fault in the engine operation. In this way, the model can learn from new samples and correct the model's feature values.

[0127] 8. After model training is complete, the main control computer can fully grasp the infrared image characteristics of the engine and the surfaces and space of the test chamber. Since infrared light is invisible, it is unaffected by visible light. For example, when engine exhaust leaks, due to current high emission control levels, the leak is invisible to the naked eye. However, through infrared imaging, it can be clearly seen that a beam of light generated by the flow of high-temperature gas is produced within the pixel block of the leak area. Fuel leaks, oil leaks, etc., can also produce similar characteristic images in their respective surrounding pixel blocks. Therefore, when fuel, oil, coolant, exhaust gas, or engine intake leaks occur in the test chamber, as well as when the engine temperature is excessively high or low, or when cracks appear in the engine block or cylinder head, clear infrared characteristic images will appear in the pixel blocks. The presence of these characteristic images allows the main control computer to determine the cause of the abnormal test operation. Infrared image characteristics include image shape, brightness, color, texture, image spectrum, and image histogram.

[0128] 9. If any abnormal operation is detected, the engine can be stopped or returned to idle speed remotely. Remote control can be achieved by sending CAN information from the main control computer to the engine ECU.

[0129] In this embodiment, by employing different information acquisition methods on the test bench, engine operation information can be obtained. Furthermore, diagonally mounted infrared cameras capture omnidirectional infrared images of the test chamber. The infrared information, after photoelectric conversion, is transmitted via the network. The main control computer uses an AI model for intelligent analysis to obtain infrared images of the test chamber during engine operation, enabling centralized monitoring of engine operation based on these images. This improves the efficiency of monitoring engine operation. Moreover, it overcomes the problem of different manufacturers' test benches using different communication protocols, preventing centralized display and control from a single client.

[0130] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0131] Based on the same inventive concept, this application also provides an engine operating state monitoring device for implementing the engine operating state monitoring method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations of one or more engine operating state monitoring device embodiments provided below can be found in the limitations of the engine operating state monitoring method described above, and will not be repeated here.

[0132] In one embodiment, such as Figure 6 As shown, an engine operating status monitoring device 600 is provided, including: an acquisition module 601, a sorting module 602, an interpolation module 603, an update module 604, a determination module 605, and a training module 606, wherein:

[0133] The acquisition module 601 is used to acquire multiple historical images of the engine, multiple sets of corresponding historical operating parameter values, and multiple corresponding historical alarm information within a historical time period.

[0134] The sorting module 602 is used to sort multiple sets of historical operating parameter values ​​and multiple historical images of the engine to obtain a sequence of historical operating parameter values ​​and a corresponding sequence of historical images.

[0135] The interpolation module 603 is used to interpolate any two adjacent sets of historical operating parameter values ​​in the historical operating parameter value sequence to obtain multiple sets of intermediate operating parameter values, and to interpolate any two adjacent historical images in the historical image sequence to obtain multiple intermediate images.

[0136] The update module 604 is used to update the historical image sequence using multiple intermediate images to obtain the sample image sequence.

[0137] The determination module 605 is used to determine the historical operating status of the engine corresponding to each sample image in the sample image sequence based on at least one of multiple historical alarm information, multiple sets of historical operating parameter values, or multiple sets of intermediate operating parameter values.

[0138] The training module 606 is used to take sample images as input to the initial model, use the historical operating states of the engine corresponding to the sample images as training labels for the initial model, train the initial model to obtain the operating state evaluation model, and use the operating state evaluation model to monitor the operating state of the engine.

[0139] In one embodiment, the types of historical operating parameter values ​​include at least one of speed, torque, exhaust temperature, oil pressure, or power. The interpolation module 603 is further configured to calculate the comprehensive value corresponding to each type in any two adjacent sets of historical operating parameter values ​​in the historical operating parameter value sequence according to the type of historical operating parameter values, and determine multiple sets of intermediate operating parameter values ​​based on the combination of comprehensive values ​​corresponding to each type; and calculate the comprehensive value of the brightness corresponding to each color channel of any two adjacent historical images in the historical image sequence according to the brightness of the color channel, and determine multiple intermediate images based on the comprehensive value of the brightness corresponding to each color channel.

[0140] In one embodiment, the interpolation module 603 is further configured to segment each historical image in the historical image sequence to obtain a historical bitmap image corresponding to each historical image, wherein the historical bitmap image includes multiple pixel blocks; determine the historical bitmap images of any two adjacent historical images in the historical image sequence; obtain the comprehensive value of the brightness of the pixel blocks at the same position in the two determined historical bitmap images; and obtain an intermediate image based on the comprehensive value corresponding to each position.

[0141] In one embodiment, the sample image is a historical image or an intermediate image, and the historical alarm information is used to characterize whether the engine has a regular fault, and the historical operating state is normal operation or abnormal operation; the determining module 605 is also used to determine the historical operating state of the engine corresponding to each historical image in the sample image sequence based on at least one of multiple historical alarm information or multiple sets of historical operating parameter values; and to determine the historical operating state of the engine corresponding to each intermediate image in the sample image sequence based on multiple sets of intermediate operating parameter values.

[0142] In one embodiment, the engine operation status monitoring device 600 further includes a monitoring module, which is used to acquire target images of the surfaces of multiple engines at a target time through an infrared camera; for the current engine among each engine, the target image of the current engine is evaluated through an operation status evaluation model to determine whether the current engine's operation status at the target time is abnormal; if the current engine's operation status is abnormal, the user terminal is instructed to perform fault handling on the current engine through a microcontroller.

[0143] In one embodiment, the monitoring module is further configured to instruct the user terminal to send control commands to the microcontroller when the current engine is in an abnormal operating state, and then send the control commands to the local area network controller via the microcontroller, and then send the control commands to the electronic control unit of the current engine via the local area network controller, so as to control the current engine to return to idle speed or stop.

[0144] Each module in the aforementioned engine operation status monitoring device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the computer device's memory as software, so that the processor can call and execute the corresponding operations of each module.

[0145] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 7As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When executed by the processor, the computer program implements a method for monitoring engine operating status. The display unit is used to form a visually visible image and can be a display screen, projection device, or virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0146] Those skilled in the art will understand that Figure 7 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0147] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0148] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the above method embodiments.

[0149] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0150] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0151] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0152] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for monitoring the operating status of an engine, characterized in that, The method includes: Acquire multiple historical images of the engine within a historical time period, corresponding sets of historical operating parameter values, and corresponding multiple historical alarm information; The engine's multiple sets of historical operating parameter values ​​and multiple historical images are sorted to obtain a sequence of historical operating parameter values ​​and a corresponding sequence of historical images. Interpolation is performed on any two adjacent sets of historical operating parameter values ​​in the historical operating parameter value sequence to obtain multiple sets of intermediate operating parameter values, and interpolation is performed on any two adjacent historical images in the historical image sequence to obtain multiple intermediate images. The historical image sequence is updated using the multiple intermediate images to obtain the sample image sequence; Based on at least one of the multiple historical alarm information, the multiple sets of historical operating parameter values, or the multiple sets of intermediate operating parameter values, determine the historical operating status of the engine corresponding to each sample image in the sample image sequence. The sample images are used as input to the initial model, and the historical operating states of the engine corresponding to the sample images are used as training labels for the initial model. The initial model is then trained to obtain an operating state evaluation model, which is used to monitor the operating state of the engine.

2. The method according to claim 1, characterized in that, The types of the historical operating parameter values ​​include at least one of speed, torque, exhaust temperature, oil pressure, or power efficiency. The interpolation process performed on any two adjacent sets of historical operating parameter values ​​in the historical operating parameter value sequence yields multiple sets of intermediate operating parameter values, including: According to the type of historical operating parameter values, calculate the comprehensive value corresponding to each type in any two adjacent sets of historical operating parameter values ​​in the historical operating parameter value sequence, and determine multiple sets of intermediate operating parameter values ​​based on the combination of comprehensive values ​​corresponding to each type. The step of interpolating any two adjacent historical images in the historical image sequence to obtain multiple intermediate images includes: Based on the brightness of each color channel, calculate the combined brightness value of each color channel of any two adjacent historical images in the historical image sequence, and determine multiple intermediate images based on the combined brightness value of each color channel.

3. The method according to claim 2, characterized in that, The step involves calculating the combined brightness value of each color channel for any two adjacent historical images in the historical image sequence according to the brightness of each color channel, and determining multiple intermediate images based on the combined brightness value of each color channel, including: Each historical image in the historical image sequence is segmented to obtain a historical bitmap image corresponding to each historical image, and the historical bitmap image includes multiple pixel blocks; Determine the historical bitmap images of any two adjacent historical images in the historical image sequence; By obtaining the combined brightness values ​​of pixel blocks at the same location in two determined historical bitmap images, an intermediate image is obtained based on the combined values ​​corresponding to each location.

4. The method according to claim 1, characterized in that, The sample images are historical images or intermediate images, the historical alarm information is used to characterize whether the engine has experienced a routine fault, and the historical operating state is normal operation or abnormal operation; determining the historical operating state of the engine corresponding to each sample image in the sample image sequence based on at least one of the multiple historical alarm information, the multiple sets of historical operating parameter values, or the multiple sets of intermediate operating parameter values ​​includes: Based on at least one of the multiple historical alarm messages or the multiple sets of historical operating parameter values, determine the historical operating status of the engine corresponding to each historical image in the sample image sequence; Based on the multiple sets of intermediate operating parameter values, the historical operating state of the engine corresponding to each intermediate image in the sample image sequence is determined.

5. The method according to any one of claims 1 to 4, further comprising: Using infrared cameras, target images of the surfaces of multiple engines are captured at the target time. For the current engine among all engines, the target image of the current engine is evaluated using the operating status evaluation model to determine whether the operating status of the current engine at the target time is abnormal. If the current engine is operating abnormally, instruct the user terminal to handle the fault of the current engine through the microcontroller.

6. The method according to claim 5, characterized in that, When the current engine is operating abnormally, the user terminal is instructed to perform fault handling on the current engine via the microcontroller, including: If the current engine is operating abnormally, the user terminal is instructed to send a control command to the microcontroller, which then sends the control command to the local area network controller, which in turn sends the control command to the current engine's electronic control unit, in order to control the current engine to return to idle or stop.

7. A monitoring device for engine operating status, characterized in that, The device includes: The acquisition module is used to acquire multiple historical images of the engine within a historical time period, multiple sets of corresponding historical operating parameter values, and multiple corresponding historical alarm information. The sorting module is used to sort the multiple sets of historical operating parameter values ​​and multiple historical images of the engine to obtain a sequence of historical operating parameter values ​​and a corresponding sequence of historical images. The interpolation module is used to interpolate any two adjacent sets of historical operating parameter values ​​in the historical operating parameter value sequence to obtain multiple sets of intermediate operating parameter values, and to interpolate any two adjacent historical images in the historical image sequence to obtain multiple intermediate images. The update module is used to update the historical image sequence using the multiple intermediate images to obtain a sample image sequence; The determination module is used to determine the historical operating status of the engine corresponding to each sample image in the sample image sequence based on at least one of the multiple historical alarm information, the multiple sets of historical operating parameter values, or the multiple sets of intermediate operating parameter values. The training module is used to take the sample images as input to the initial model, use the historical operating states of the engine corresponding to the sample images as training labels for the initial model, train the initial model to obtain an operating state evaluation model, and use the operating state evaluation model to monitor the operating state of the engine.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

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

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images