Method, system and medium for identifying abnormalities of coarse screen equipment based on AI model

Abstract

The present invention relates to the technical field of sewage treatment equipment monitoring, and discloses a method, system, and medium for identifying abnormalities of coarse screen equipment based on an AI model. By inputting an optimized coarse screen image of the coarse screen equipment into an optimized target detection model for processing, target position data corresponding to the detection target is obtained, the optimized coarse screen image is segmented according to the target position data to obtain a target image, and then image feature data is extracted and obtained. The image feature data is processed to obtain a preliminary evaluation index of the operation of the coarse screen equipment, and the preliminary evaluation status of the coarse screen equipment is obtained through threshold comparison. If it is suspected abnormal, the image feature data is input into a preset abnormality detection model for evaluation processing to obtain a comprehensive operation index of the coarse screen equipment, and finally the final evaluation status of the coarse screen equipment is determined through threshold comparison; thus, by combining the large and small models, accurate judgment of abnormalities of the coarse screen equipment is achieved, while improving judgment efficiency and reducing the misjudgment rate.

Description

Technical Field

[0001] The present invention relates to the technical field of sewage treatment equipment monitoring, and more specifically, to a method, system, and medium for identifying anomalies of coarse screen equipment based on an AI model. Background Art

[0002] Coarse screen equipment undertakes the important task of intercepting larger suspended and floating objects in sewage. The stability of its operating status directly affects the effectiveness and efficiency of subsequent treatment processes. Traditional coarse screen equipment monitoring methods mainly rely on regular manual inspections; however, this method has the disadvantages of low inspection efficiency and relatively long inspection cycles, making it difficult to achieve real-time monitoring, which may result in equipment abnormalities not being discovered in a timely manner. Manual judgment is prone to errors, affecting the accuracy of judgment. In addition, inspectors need to come into close contact with sewage and equipment, which poses safety risks of slipping, poisoning, and electric shock, and the operation is highly dangerous. Intelligent monitoring technology based on computer vision and deep learning can achieve real-time and accurate monitoring of equipment, and improve the intelligent management level of sewage treatment plants; related technologies have been explored in some fields, for example, patent CN202411283204.0 involves a sewage treatment coarse screen equipment operation monitoring and control system, but further optimization is needed in terms of the accuracy of coarse screen equipment abnormality identification and judgment. Summary of the Invention

[0003] In view of the above problems, the purpose of the present invention is to provide a method, system and medium for identifying abnormalities of coarse grid equipment based on an AI model.

[0004] In order to solve the above technical problems, the technical solutions of the present invention are as follows:

[0005] A first aspect of the present invention provides a method for identifying abnormalities in coarse grid equipment based on an AI model, comprising the following steps:

[0006] Acquire an initial coarse grid image of the coarse grid device, and perform preprocessing to obtain an optimized coarse grid image;

[0007] Obtaining an initial target detection model and performing optimization processing to obtain an optimized target detection model;

[0008] Inputting the optimized coarse grid image into the optimized target detection model for processing to obtain target position data corresponding to the detection target;

[0009] Segmenting the optimized coarse grid image according to the target position data to obtain a target image, and extracting the image feature data of the target image;

[0010] Processing the image feature data to obtain a preliminary evaluation index of the coarse grid device operation, and performing a threshold comparison with a preset preliminary evaluation threshold of the device operation to obtain a preliminary evaluation status of the coarse grid device;

[0011] If the initial evaluation status is suspected abnormal, the image feature data is input into a preset abnormality detection model for evaluation and processing to obtain a comprehensive operation index of the coarse grid equipment;

[0012] The operation comprehensive measurement index is compared with the preset equipment calibration operation evaluation threshold, and the final evaluation status of the coarse grid equipment is determined according to the comparison result.

[0013] Optionally, in the method for identifying coarse grid equipment anomalies based on an AI model described in the present application, obtaining an initial target detection model and performing optimization processing to obtain an optimized target detection model includes:

[0014] Obtain the initial target detection model;

[0015] The FPN module in the initial target detection model is optimized by an adaptive weighted fusion method to obtain a weighted optimized target detection model.

[0016] The channel attention module and the spatial attention module are used to optimize the network structure in the weighted optimization target detection model to obtain an optimized target detection model.

[0017] Optionally, in the method for identifying coarse grid equipment anomalies based on an AI model described in the present application, inputting the optimized coarse grid image into the optimized target detection model for processing to obtain target position data corresponding to the detection target includes:

[0018] Inputting the optimized coarse grid image into the optimized target detection model for processing to obtain target position data corresponding to the detection target;

[0019] The target location data includes coarse screen equipment location data, rake bucket location data and garbage location data.

[0020] Optionally, in the method for identifying abnormalities of coarse grid equipment based on an AI model described in the present application, segmenting the optimized coarse grid image according to the target position data to obtain a target image, and performing extraction processing to obtain image feature data of the target image includes:

[0021] Segmenting the optimized coarse grid image according to the coarse grid device position data, the rake bucket position data, and the garbage position data to obtain a target image;

[0022] The target images include a coarse grid equipment image, a rake bucket image, and a garbage image;

[0023] Extracting image feature data from the coarse grid device image to obtain coarse grid device feature data, including coarse grid shape feature data, coarse grid color feature data, and coarse grid texture feature data;

[0024] Image feature data of the bucket image is extracted to obtain bucket image feature data, including bucket shape feature data, bucket color feature data, bucket texture feature data and bucket inclination angle.

[0025] Optionally, the method for identifying abnormalities of coarse grid equipment based on an AI model described in the present application further includes:

[0026] Perform pixel counting on the garbage image to obtain the number of pixels in the garbage area;

[0027] Perform pixel statistics based on the optimized coarse grid image to obtain the number of pixels in the monitoring area;

[0028] The number of pixels in the garbage area is compared with the number of pixels in the monitoring area to obtain the garbage ratio.

[0029] Optionally, in the method for identifying abnormalities of coarse grid equipment based on an AI model described in the present application, the processing according to the image feature data to obtain a preliminary evaluation index of the coarse grid equipment operation, and performing a threshold comparison with a preset preliminary evaluation threshold of the equipment operation to obtain a preliminary evaluation status of the coarse grid equipment, includes:

[0030] Comparing the bucket inclination angle with the preset bucket design inclination angle to obtain the bucket inclination angle deviation rate;

[0031] Comparing the garbage percentage with a preset allowable garbage percentage to obtain a garbage excess rate;

[0032] A weighted summation process is performed based on the bucket inclination deviation rate and the garbage overcapacity rate to obtain a preliminary evaluation index of the operation of the coarse screen equipment;

[0033] Comparing the operation preliminary evaluation index with a preset equipment operation preliminary evaluation threshold to obtain a preliminary evaluation status of the coarse grid equipment;

[0034] If the operation preliminary evaluation index is less than or equal to the preset equipment operation preliminary evaluation threshold, the preliminary evaluation status is determined to be normal;

[0035] If the operation preliminary evaluation index is greater than the preset equipment operation preliminary evaluation threshold, the preliminary evaluation status is determined to be suspected abnormality.

[0036] Optionally, in the method for identifying abnormalities of coarse grid equipment based on an AI model described in the present application, if the initial assessment status is suspected abnormality, the image feature data is input into a preset abnormality detection model for evaluation processing to obtain a comprehensive operation index of the coarse grid equipment, including:

[0037] If the initial evaluation status is suspected abnormality, the coarse grid shape feature data, the coarse grid color feature data, and the coarse grid texture feature data are input into a preset coarse grid abnormality detection model for evaluation and processing to obtain a coarse grid quality evaluation index;

[0038] Inputting the bucket shape feature data, bucket color feature data and bucket texture feature data into a preset bucket anomaly detection model for evaluation and processing to obtain a bucket quality evaluation index;

[0039] The coarse screen quality evaluation index and the bucket quality evaluation index are processed in combination with the bucket inclination deviation rate and the garbage overcapacity rate to obtain the comprehensive operation index of the coarse screen equipment.

[0040] Optionally, in the method for identifying coarse grid equipment anomalies based on an AI model described in the present application, the operation comprehensive measurement index is compared with a preset equipment calibration operation evaluation threshold, and the final evaluation status of the coarse grid equipment is determined according to the comparison result, including:

[0041] Comparing the comprehensive operation index with a preset operation parameter index to obtain a relative value of the operation index;

[0042] Comparing the relative value of the operating index with a preset equipment calibration operating evaluation threshold to obtain a final evaluation status of the coarse grid equipment;

[0043] If the relative value of the operation index is less than or equal to the preset equipment calibration operation evaluation threshold, the final evaluation status is determined to be an abnormal state, and an early warning response is output;

[0044] If the relative value of the operation index is greater than the preset equipment calibration operation evaluation threshold, the final evaluation status is determined to be normal.

[0045] A second aspect of the present invention provides a system for identifying abnormalities of coarse grid equipment based on an AI model. The system includes: a memory and a processor. The memory includes a program for identifying abnormalities of coarse grid equipment based on an AI model. When the program is executed by the processor, the following steps are implemented:

[0046] Acquire an initial coarse grid image of the coarse grid device, and perform preprocessing to obtain an optimized coarse grid image;

[0047] Obtaining an initial target detection model and performing optimization processing to obtain an optimized target detection model;

[0048] Inputting the optimized coarse grid image into the optimized target detection model for processing to obtain target position data corresponding to the detection target;

[0049] Segmenting the optimized coarse grid image according to the target position data to obtain a target image, and extracting the image feature data of the target image;

[0050] Processing the image feature data to obtain a preliminary evaluation index of the coarse grid device operation, and performing a threshold comparison with a preset preliminary evaluation threshold of the device operation to obtain a preliminary evaluation status of the coarse grid device;

[0051] If the initial evaluation status is suspected abnormal, the image feature data is input into a preset abnormality detection model for evaluation and processing to obtain a comprehensive operation index of the coarse grid equipment;

[0052] The operation comprehensive measurement index is compared with the preset equipment calibration operation evaluation threshold, and the final evaluation status of the coarse grid equipment is determined according to the comparison result.

[0053] The third aspect of the present invention provides a computer-readable storage medium, which stores a program for a method for identifying abnormalities of coarse grid equipment based on an AI model. When the program for identifying abnormalities of coarse grid equipment based on an AI model is executed by a processor, the steps of the method for identifying abnormalities of coarse grid equipment based on an AI model as described in any one of the above items are implemented.

[0054] By optimizing the coarse grid image and optimizing the target detection model based on the coarse grid equipment, the preliminary evaluation index of the operation of the coarse grid equipment is calculated. The preliminary evaluation status of the coarse grid equipment is obtained through threshold comparison. If it is suspected to be abnormal, the image feature data is input into the preset abnormality detection model for evaluation and processing to obtain the comprehensive operation index of the coarse grid equipment. Finally, the final evaluation status of the coarse grid equipment is determined through threshold comparison. By combining the large and small models, accurate judgment of the abnormality of the coarse grid equipment is achieved, which improves the judgment efficiency and reduces the misjudgment rate.

[0055] Compared with the prior art, the beneficial effects of the technical solution of the present invention are:

[0056] Improved monitoring efficiency: Compared with manual inspection, this method can realize real-time monitoring of coarse grid equipment, greatly improving monitoring efficiency.

[0057] Reduced false alarm rate: By combining large and small models, the accuracy of anomaly judgment is improved and the false alarm rate is reduced.

[0058] Reduced safety risks: The number of times personnel go down to the pool for inspection is reduced, which reduces the safety risks of operators. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 A flowchart of a method for identifying coarse grid equipment anomalies based on an AI model provided in an embodiment of the present invention;

[0060] Figure 2 A flowchart of obtaining an optimized target detection model based on an AI model combined with a method for identifying anomalies in coarse grid equipment provided in an embodiment of the present invention;

[0061] Figure 3 A flowchart of obtaining a preliminary evaluation status of a coarse grid device based on an AI model combined with a method for identifying coarse grid device anomalies provided in an embodiment of the present invention;

[0062] Figure 4 A flowchart of obtaining a comprehensive operating index of a coarse grid device based on an AI model combined with a method for identifying anomalies of the coarse grid device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0063] In order to more clearly understand the above-mentioned objects, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that, in the absence of conflict, the embodiments of the present application and the features therein can be combined with each other.

[0064] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the scope of protection of the present invention is not limited to the specific embodiments disclosed below.

[0065] Example 1

[0066] like Figure 1 As shown, this embodiment discloses a method for identifying abnormalities of coarse grid equipment based on an AI model, which is characterized by comprising the following steps:

[0067] S11, obtaining an initial coarse grid image of the coarse grid device and performing preprocessing to obtain an optimized coarse grid image;

[0068] S12, obtaining an initial target detection model and performing optimization processing to obtain an optimized target detection model;

[0069] S13, inputting the optimized coarse grid image into the optimized target detection model for processing to obtain target position data corresponding to the detection target;

[0070] S14, segmenting the optimized coarse grid image according to the target position data to obtain a target image, and performing extraction processing to obtain image feature data of the target image;

[0071] S15. Process the image feature data to obtain a preliminary evaluation index of the coarse grid device, and compare the index with a preset preliminary evaluation threshold of the device operation to obtain a preliminary evaluation status of the coarse grid device;

[0072] S16. If the initial evaluation status is suspected abnormal, the image feature data is input into a preset abnormality detection model for evaluation and processing to obtain a comprehensive operation index of the coarse grid equipment;

[0073] S17: performing a threshold comparison between the comprehensive operation measurement index and a preset equipment calibration operation evaluation threshold, and determining a final evaluation status of the coarse grid equipment according to the comparison result.

[0074] It should be noted that in order to achieve accurate judgment of abnormalities in coarse screen equipment, the initial coarse screen image is first captured at predetermined intervals by a shooting device arranged in the coarse screen equipment area, and denoising, sharpening and grayscale preprocessing are performed. At the same time, in order to improve the accuracy of target detection, the initial target detection model is optimized, and the preprocessed optimized coarse screen image is input into the optimized optimized target detection model for processing to obtain the target position data corresponding to the detection target. The optimized coarse screen image is then segmented based on the target position data to identify the regional images of the coarse screen equipment, bucket and garbage, and the image feature data of the target image is extracted for subsequent abnormality judgment. In order to improve judgment efficiency and reduce unnecessary computing resources, the possible abnormalities are first judged based on the bucket inclination angle and garbage proportion in the image feature data to obtain the initial evaluation status of the coarse screen equipment. If it is a suspected abnormality, the final judgment is made through multiple large models to further improve the judgment accuracy and reduce the misjudgment rate.

[0075] Example 2

[0076] like Figure 2 As shown, this embodiment discloses a flow chart for obtaining an optimized target detection model based on an AI model combined with a method for identifying anomalies in coarse grid equipment. According to an embodiment of the present invention, the process of obtaining an initial target detection model and performing optimization processing to obtain an optimized target detection model includes:

[0077] S21, obtaining an initial target detection model;

[0078] S22, optimizing the FPN module in the initial target detection model by an adaptive weighted fusion method to obtain a weighted optimized target detection model;

[0079] S23. Use a channel attention module and a spatial attention module to optimize the network structure in the weighted optimization target detection model to obtain an optimized target detection model.

[0080] It should be noted that, in the target detection stage, this embodiment adopts YOLOv5 as the basic model, which has the characteristics of strong real-time performance and high precision and is suitable for real-time monitoring scenarios. Since the coarse grid equipment has multi-scale targets of different sizes, the basic model is first optimized in terms of feature fusion by using an adaptive weighted fusion method to optimize the traditional FPN module with a simple addition operation. The FPN module is a feature pyramid network module. The optimized FPN assigns a learnable weight to the feature map of each scale, and automatically adjusts these weights by training the network, so that the network can more reasonably fuse feature information according to the contribution of feature maps of different scales to target detection; then the channel attention module is introduced to allow the model to automatically learn the importance of each channel and assign different weights to each channel according to the importance. In the detection of coarse grid equipment, different channels may contain different types of information. For example, some Channels may be sensitive to the edge features of the coarse grid, while other channels may be sensitive to the color features of the bucket. The channel attention module allows the model to automatically assign weights according to the importance of these channels, so that the model pays more attention to the channels containing key information, suppresses the interference of irrelevant channels, and improves the model's ability to extract key features of the coarse grid equipment, thereby improving detection accuracy; at the same time, the spatial attention module is introduced to allow the model to focus on key spatial areas in the image. In the image of the coarse grid equipment, different spatial areas may have different importance. For example, the working area of ​​the coarse grid, the motion trajectory area of ​​the bucket, etc. are areas that need to be focused on. The spatial attention module enables the model to automatically identify these key spatial areas and enhance the features of these areas, while suppressing the features of non-key areas, improving the model's attention to the key areas of the coarse grid equipment, thereby more accurately detecting the target and further improving the detection accuracy.

[0081] According to an embodiment of the present invention, the step of inputting the optimized coarse grid image into the optimized target detection model for processing to obtain target position data corresponding to the detected target includes:

[0082] Inputting the optimized coarse grid image into the optimized target detection model for processing to obtain target position data corresponding to the detection target;

[0083] The target location data includes coarse screen equipment location data, rake bucket location data and garbage location data.

[0084] It should be noted that the optimized coarse grid image obtained after preprocessing is input into the optimized and improved optimized target detection model for processing, and target position data including coarse grid equipment position data, rake bucket position data and garbage position data are obtained as the basis for subsequent image segmentation processing.

[0085] According to an embodiment of the present invention, segmenting the optimized coarse grid image according to the target position data to obtain a target image, and extracting the image feature data of the target image includes:

[0086] Segmenting the optimized coarse grid image according to the coarse grid device position data, the rake bucket position data, and the garbage position data to obtain a target image;

[0087] The target images include a coarse grid equipment image, a rake bucket image, and a garbage image;

[0088] Extracting image feature data from the coarse grid device image to obtain coarse grid device feature data, including coarse grid shape feature data, coarse grid color feature data, and coarse grid texture feature data;

[0089] Image feature data of the bucket image is extracted to obtain bucket image feature data, including bucket shape feature data, bucket color feature data, bucket texture feature data and bucket inclination angle.

[0090] It should be noted that in order to facilitate the extraction of image feature data from different areas, the optimized coarse grid image is segmented into a target image including a coarse grid equipment image, a rake bucket image and a garbage image according to the determined coarse grid equipment position data, the rake bucket position data and the garbage position data, and then the image feature data of the coarse grid equipment image and the rake bucket image are extracted, where the rake bucket inclination angle is the angle between the rake bucket and the horizontal line, providing data support for abnormality judgment.

[0091] According to an embodiment of the present invention, the present invention further comprises:

[0092] Perform pixel counting on the garbage image to obtain the number of pixels in the garbage area;

[0093] Perform pixel statistics based on the optimized coarse grid image to obtain the number of pixels in the monitoring area;

[0094] The number of pixels in the garbage area is compared with the number of pixels in the monitoring area to obtain the garbage ratio.

[0095] It should be noted that in order to determine the garbage situation on the coarse screen equipment, the garbage ratio is determined by pixel statistics. For example, the number of pixels in the garbage area obtained by statistics is 30, and the number of pixels in the monitoring area obtained by statistics is 100, then 30 / 100=0.3 is the garbage ratio.

[0096] Example 3

[0097] like Figure 3As shown, this embodiment discloses a flow chart for obtaining a preliminary evaluation status of a coarse grid device based on an AI model combined with a method for identifying abnormalities of a coarse grid device. According to an example of the present invention, the processing of the image feature data to obtain a preliminary evaluation index of the coarse grid device operation and comparing the index with a preset threshold for preliminary evaluation of the device operation to obtain the preliminary evaluation status of the coarse grid device includes:

[0098] S31, comparing the bucket inclination angle with a preset bucket design inclination angle to obtain a bucket inclination angle deviation rate;

[0099] S32. Compare the garbage percentage with a preset allowable garbage percentage to obtain a garbage excess rate;

[0100] S33, performing weighted summation processing based on the bucket inclination deviation rate and the garbage overload rate to obtain a preliminary evaluation index of the coarse screen equipment operation;

[0101] S34, comparing the preliminary operation evaluation index with a preset equipment preliminary operation evaluation threshold to obtain a preliminary evaluation status of the coarse grid equipment;

[0102] S35. If the operation preliminary evaluation index is less than or equal to the preset equipment operation preliminary evaluation threshold, the preliminary evaluation status is determined to be normal;

[0103] S36. If the operation preliminary evaluation index is greater than the preset equipment operation preliminary evaluation threshold, the preliminary evaluation status is determined to be suspected abnormality.

[0104] It should be noted that the bucket inclination deviation rate refers to the ratio of the absolute value of the difference between the bucket inclination and the preset bucket design inclination to the preset bucket design inclination; the garbage excess rate refers to the ratio of the difference between the garbage proportion and the preset garbage proportion allowable value to the preset garbage proportion allowable value. If the garbage excess rate is a negative value, it means that the garbage proportion is small. The garbage excess rate is eliminated, and a weighted summation process is performed based on the bucket inclination deviation rate and the garbage excess rate to obtain the preliminary evaluation index of the coarse screen equipment. The corresponding weight value is obtained by querying the third-party preset sewage treatment operation detection platform. Finally, the preliminary evaluation status of the coarse screen equipment is obtained by comparing the threshold with the preset equipment operation preliminary evaluation threshold.

[0105] Example 4

[0106] like Figure 4 As shown, this embodiment discloses a flow chart for obtaining a comprehensive operation index of a coarse grid device based on an AI model combined with a method for identifying anomalies of a coarse grid device. According to an example of the present invention, if the initial evaluation status is suspected to be abnormal, the image feature data is input into a preset abnormality detection model for evaluation and processing to obtain a comprehensive operation index of the coarse grid device, including:

[0107] S41. If the initial evaluation status is suspected abnormality, the coarse grid shape feature data, the coarse grid color feature data, and the coarse grid texture feature data are input into a preset coarse grid abnormality detection model for evaluation and processing to obtain a coarse grid quality evaluation index;

[0108] S42, inputting the bucket shape feature data, bucket color feature data, and bucket texture feature data into a preset bucket anomaly detection model for evaluation and processing to obtain a bucket quality evaluation index;

[0109] S43. Process the coarse screen quality evaluation index and the bucket quality evaluation index in combination with the bucket inclination deviation rate and the garbage overcapacity rate to obtain a comprehensive operation index of the coarse screen equipment.

[0110] It should be noted that in order to improve the accuracy of anomaly recognition and reduce the false alarm rate, after the initial evaluation status is suspected abnormal, the obtained coarse screen equipment feature data and bucket image feature data are respectively input into the preset large model for further judgment, such as Swin Transformer and CLIP, to obtain the coarse screen quality evaluation index and the bucket quality evaluation index. Among them, the preset coarse screen anomaly detection model is obtained by training by obtaining a large number of historical samples of coarse screen shape feature data, coarse screen color feature data and coarse screen texture feature data and the corresponding coarse screen quality evaluation index, and the preset bucket anomaly detection model is obtained by training by obtaining a large number of historical samples of bucket shape feature data, bucket color feature data and bucket texture feature data and the corresponding bucket quality evaluation index; then combined with the bucket inclination deviation rate and the garbage overload rate for processing, the comprehensive operation measurement index of the coarse screen equipment is obtained;

[0111] The calculation formula of the operation comprehensive measurement index is:

[0112]

[0113] Among them, c r is the comprehensive index of operation, e c 、e s , t a 、g a They are the coarse screen quality evaluation index, bucket quality evaluation index, bucket inclination deviation rate and garbage overcapacity rate respectively, and ε1, ε2, and χ are the preset characteristic coefficients (the characteristic coefficients are obtained by querying the preset sewage treatment operation detection platform).

[0114] According to an embodiment of the present invention, the operation comprehensive measurement index is compared with a preset equipment calibration operation evaluation threshold, and the final evaluation status of the coarse grid equipment is determined according to the comparison result, including:

[0115] Comparing the comprehensive operation index with a preset operation parameter index to obtain a relative value of the operation index;

[0116] Comparing the relative value of the operating index with a preset equipment calibration operating evaluation threshold to obtain a final evaluation status of the coarse grid equipment;

[0117] If the relative value of the operation index is less than or equal to the preset equipment calibration operation evaluation threshold, the final evaluation status is determined to be an abnormal state, and an early warning response is output;

[0118] If the relative value of the operation index is greater than the preset equipment calibration operation evaluation threshold, the final evaluation status is determined to be normal.

[0119] It should be noted that the obtained operation comprehensive measurement index is compared with the preset operation parameter index to obtain the relative value of the operation index. The preset operation parameter index refers to the operation comprehensive evaluation benchmark index set according to actual needs. For example, the obtained operation comprehensive measurement index is 7, and the preset operation parameter index is 10, then 7 / 10=0.7 is the relative value of the operation index. The relative value of the operation index is then compared with the preset equipment calibration operation evaluation threshold to obtain the final evaluation status of the coarse grid equipment. In this embodiment, the preset equipment calibration operation evaluation threshold is set to (0, 0.8], (0.8, 1], corresponding to abnormal state and normal state, respectively. For example, if the obtained relative value of the operation index is 0.7, which is less than the preset equipment calibration operation evaluation threshold, the final evaluation status is determined to be an abnormal state, and an early warning response is output. If the obtained relative value of the operation index is 0.85, which is greater than the preset equipment calibration operation evaluation threshold, the final evaluation status is determined to be a normal state, indicating that the suspected abnormality in the initial evaluation is a false alarm.

[0120] It is worth mentioning that according to the embodiment of the present invention, it also includes:

[0121] Obtain the pollution interception effectiveness data and water flow capacity monitoring data of the coarse screen equipment;

[0122] The pollution interception effectiveness data include interception efficiency and screen residue moisture content;

[0123] The water flow capacity monitoring data includes the measured value of water flow and head loss;

[0124] Comparing the measured water flow rate with the preset water flow rate design value to obtain the water flow rate, and comparing the head loss amount with the preset head reference amount to obtain the head loss rate;

[0125] The interception efficiency and the moisture content of the screen residue are processed in combination with the water flow rate and the head loss rate to obtain a performance evaluation index of the coarse screen equipment.

[0126] It should be noted that in addition to evaluating the operation of the coarse screen equipment through monitoring images, attention should also be paid to the actual operation effectiveness of the coarse screen equipment. The interception efficiency refers to the ratio of the amount of solid pollutants intercepted by the coarse screen to the total amount of pollutants entering the screen per unit time. The water flow rate refers to the ratio of the difference between the preset water flow design value and the measured water flow value to the preset water flow design value. The head loss rate refers to the ratio of the difference between the preset head reference value and the head loss value to the preset head reference value.

[0127] The performance evaluation index calculation formula of coarse screen equipment is:

[0128]

[0129] Among them, p e is the performance evaluation index, n e 、m c 、w p 、w s are interception efficiency, screen residue moisture content, water flow rate and head loss rate respectively; κ1, κ2, λ1 and λ2 are preset characteristic coefficients (the characteristic coefficients are obtained by querying the preset sewage treatment operation detection platform).

[0130] It is worth mentioning that according to the embodiment of the present invention, it also includes:

[0131] Obtain the running speed of the rake bucket and compare it with the preset design parameter speed to obtain the running speed change rate;

[0132] Obtain the tension data of the coarse grid equipment chain and compare it with the preset design parameter tension to obtain the tension change rate;

[0133] The running speed change rate and the tension change rate are input into a preset coarse grid equipment operation evaluation model for processing to obtain the running stability efficiency index of the coarse grid equipment.

[0134] It should be noted that when the bucket jams, jumps teeth or deviates during operation, the operating speed will be significantly different from the design value. Chain tension that is too loose or too tight will affect the operation of the equipment. The operating speed change rate refers to the ratio of the absolute value of the difference between the operating speed and the preset design parameter speed to the preset design parameter speed. The tension change rate refers to the ratio of the absolute value of the difference between the tension data and the preset design parameter tension to the preset design parameter tension. Those skilled in the art can evaluate the tension by measuring the sag of the chain or checking the engagement of the chain with the sprocket; the obtained operating speed change rate and tension change rate are input into the preset coarse screen equipment operation evaluation model for processing to obtain the operation stability index of the coarse screen equipment, wherein the preset coarse screen equipment operation evaluation model is obtained by obtaining the operating speed change rate and tension change rate of a large number of historical samples and the corresponding operation stability index training.

[0135] It is worth mentioning that according to the embodiment of the present invention, it also includes:

[0136] Processing is performed based on the performance evaluation index and the operation stability efficiency index to obtain an abnormality identification correction coefficient of the coarse grid equipment;

[0137] The operation comprehensive measurement index is corrected according to the abnormality identification correction coefficient to obtain an operation comprehensive measurement correction index.

[0138] It should be noted that in order to further improve the accuracy of abnormality identification and judgment by combining the actual operation effect and the operation status of the power equipment, the abnormality identification correction coefficient of the coarse grid equipment is obtained according to the performance evaluation index and the operation stability index, and the operation comprehensive measurement index of the coarse grid equipment is corrected;

[0139] The calculation formula of the abnormality identification correction coefficient is:

[0140]

[0141] Among them, c f is the abnormal identification correction coefficient, p e 、s t They are performance evaluation index and operation stability index respectively. is the preset characteristic coefficient (the characteristic coefficient is obtained by querying the preset sewage treatment operation detection platform);

[0142] The calculation formula of the operation comprehensive measurement correction index is:

[0143] c mx =(1+μ×c f )×c m ;

[0144] Among them, c mx is the running comprehensive test correction index, c f 、c m are the abnormality identification correction coefficient and the operation comprehensive measurement index respectively, and μ is the preset characteristic coefficient (the characteristic coefficient is obtained by querying the preset sewage treatment operation detection platform).

[0145] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0146] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed across multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the scheme of this embodiment.

[0147] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0148] Those skilled in the art will understand that all or part of the steps of the above-mentioned method embodiments can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above-mentioned method embodiments; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROMs), random access memories (RAMs), magnetic disks or optical disks, and other media that can store program codes.

[0149] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

Claims

1. A method for identifying abnormalities in coarse grid equipment based on an AI model, characterized in that: The following steps are involved: Acquire an initial coarse grid image of the coarse grid device, and perform preprocessing to obtain an optimized coarse grid image; Obtaining an initial target detection model and performing optimization processing to obtain an optimized target detection model; Inputting the optimized coarse grid image into the optimized target detection model for processing to obtain target position data corresponding to the detection target; Segmenting the optimized coarse grid image according to the target position data to obtain a target image, and extracting the image feature data of the target image; Processing the image feature data to obtain a preliminary evaluation index of the coarse grid device operation, and performing a threshold comparison with a preset preliminary evaluation threshold of the device operation to obtain a preliminary evaluation status of the coarse grid device; If the initial evaluation status is suspected abnormal, the image feature data is input into a preset abnormality detection model for evaluation and processing to obtain a comprehensive operation index of the coarse grid equipment; Comparing the comprehensive operation index with a preset equipment calibration operation evaluation threshold, and determining the final evaluation status of the coarse grid equipment according to the comparison result; The obtaining of the initial target detection model and performing optimization processing to obtain the optimized target detection model includes: Obtain the initial target detection model; The FPN module in the initial target detection model is optimized by an adaptive weighted fusion method to obtain a weighted optimized target detection model. Using a channel attention module and a spatial attention module to optimize the network structure in the weighted optimization target detection model to obtain an optimized target detection model; The step of segmenting the optimized coarse grid image according to the target position data to obtain a target image, and extracting the target image to obtain image feature data of the target image includes: Segmenting the optimized coarse grid image according to the coarse grid device position data, the rake bucket position data, and the garbage position data to obtain a target image; The target images include a coarse grid equipment image, a rake bucket image, and a garbage image; Extracting image feature data from the coarse grid device image to obtain coarse grid device feature data, including coarse grid shape feature data, coarse grid color feature data, and coarse grid texture feature data; Image feature data of the bucket image is extracted to obtain bucket image feature data, including bucket shape feature data, bucket color feature data, bucket texture feature data and bucket inclination angle.

2. The method for identifying abnormalities of coarse grid equipment based on an AI model according to claim 1 is characterized in that: The step of inputting the optimized coarse grid image into the optimized target detection model for processing to obtain target position data corresponding to the detected target includes: Inputting the optimized coarse grid image into the optimized target detection model for processing to obtain target position data corresponding to the detection target; The target location data includes coarse screen equipment location data, rake bucket location data and garbage location data.

3. The method for identifying abnormalities of coarse grid equipment based on an AI model according to claim 2 is characterized in that: Also includes: Perform pixel counting on the garbage image to obtain the number of pixels in the garbage area; Perform pixel statistics based on the optimized coarse grid image to obtain the number of pixels in the monitoring area; The number of pixels in the garbage area is compared with the number of pixels in the monitoring area to obtain the garbage ratio.

4. The method for identifying abnormalities of coarse grid equipment based on an AI model according to claim 3 is characterized in that: The processing according to the image feature data to obtain the preliminary evaluation index of the coarse grid device operation, and performing a threshold comparison with a preset preliminary evaluation threshold of the device operation to obtain the preliminary evaluation status of the coarse grid device, includes: Comparing the bucket inclination angle with the preset bucket design inclination angle to obtain the bucket inclination angle deviation rate; Comparing the garbage percentage with a preset allowable garbage percentage to obtain a garbage excess rate; A weighted summation process is performed based on the bucket inclination deviation rate and the garbage overload rate to obtain a preliminary evaluation index of the coarse screen equipment; Comparing the operation preliminary evaluation index with a preset equipment operation preliminary evaluation threshold to obtain a preliminary evaluation status of the coarse grid equipment; If the operation preliminary evaluation index is less than or equal to the preset equipment operation preliminary evaluation threshold, the preliminary evaluation status is determined to be normal; If the operation preliminary evaluation index is greater than the preset equipment operation preliminary evaluation threshold, the preliminary evaluation status is determined to be suspected abnormality.

5. The method for identifying abnormalities of coarse grid equipment based on an AI model according to claim 4 is characterized in that: If the initial evaluation status is suspected abnormal, the image feature data is input into a preset abnormality detection model for evaluation and processing to obtain a comprehensive operation index of the coarse grid equipment, including: If the initial evaluation status is suspected abnormality, the coarse grid shape feature data, the coarse grid color feature data, and the coarse grid texture feature data are input into a preset coarse grid abnormality detection model for evaluation and processing to obtain a coarse grid quality evaluation index; Inputting the bucket shape feature data, bucket color feature data and bucket texture feature data into a preset bucket anomaly detection model for evaluation and processing to obtain a bucket quality evaluation index; The coarse screen quality evaluation index and the bucket quality evaluation index are processed in combination with the bucket inclination deviation rate and the garbage overcapacity rate to obtain the comprehensive operation index of the coarse screen equipment.

6. The method for identifying abnormalities of coarse grid equipment based on an AI model according to claim 5 is characterized in that: The operation comprehensive measurement index is compared with a preset equipment calibration operation evaluation threshold, and the final evaluation status of the coarse grid equipment is determined according to the comparison result, including: Comparing the comprehensive operation index with a preset operation parameter index to obtain a relative value of the operation index; Comparing the relative value of the operating index with a preset equipment calibration operating evaluation threshold to obtain a final evaluation status of the coarse grid equipment; If the relative value of the operation index is less than or equal to the preset equipment calibration operation evaluation threshold, the final evaluation status is determined to be an abnormal state, and an early warning response is output; If the relative value of the operation index is greater than the preset equipment calibration operation evaluation threshold, the final evaluation status is determined to be normal.

7. Based on AI model combined with the system for identifying abnormalities of coarse grid equipment, it is characterized by: The system includes a memory and a processor, wherein the memory includes a method program for identifying abnormalities of coarse grid equipment based on an AI model. When the method program for identifying abnormalities of coarse grid equipment based on an AI model is executed by the processor, the following steps are implemented: Acquire an initial coarse grid image of the coarse grid device, and perform preprocessing to obtain an optimized coarse grid image; Obtaining an initial target detection model and performing optimization processing to obtain an optimized target detection model; Inputting the optimized coarse grid image into the optimized target detection model for processing to obtain target position data corresponding to the detection target; Segmenting the optimized coarse grid image according to the target position data to obtain a target image, and extracting the image feature data of the target image; Processing the image feature data to obtain a preliminary evaluation index of the coarse grid device operation, and performing a threshold comparison with a preset preliminary evaluation threshold of the device operation to obtain a preliminary evaluation status of the coarse grid device; If the initial evaluation status is suspected abnormal, the image feature data is input into a preset abnormality detection model for evaluation and processing to obtain a comprehensive operation index of the coarse grid equipment; Comparing the comprehensive operation index with a preset equipment calibration operation evaluation threshold, and determining the final evaluation status of the coarse grid equipment according to the comparison result; The obtaining of the initial target detection model and performing optimization processing to obtain the optimized target detection model includes: Obtain the initial target detection model; The FPN module in the initial target detection model is optimized by an adaptive weighted fusion method to obtain a weighted optimized target detection model. Using a channel attention module and a spatial attention module to optimize the network structure in the weighted optimization target detection model to obtain an optimized target detection model; The step of segmenting the optimized coarse grid image according to the target position data to obtain a target image, and extracting the target image to obtain image feature data of the target image includes: Segmenting the optimized coarse grid image according to the coarse grid device position data, the rake bucket position data, and the garbage position data to obtain a target image; The target images include a coarse grid equipment image, a rake bucket image, and a garbage image; Extracting image feature data from the coarse grid device image to obtain coarse grid device feature data, including coarse grid shape feature data, coarse grid color feature data, and coarse grid texture feature data; Image feature data of the bucket image is extracted to obtain bucket image feature data, including bucket shape feature data, bucket color feature data, bucket texture feature data and bucket inclination angle.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a method program for identifying abnormalities of coarse grid equipment based on an AI model. When the method program for identifying abnormalities of coarse grid equipment based on an AI model is executed by a processor, the steps of the method for identifying abnormalities of coarse grid equipment based on an AI model as described in any one of claims 1 to 6 are implemented.

Images