CN113887530A - Hydraulic station monitoring and management system - Google Patents

Abstract

The invention provides a hydraulic station monitoring and management system, which comprises: the monitoring module is used for monitoring each detection point in the hydraulic station in real time and acquiring a monitoring image of each monitoring point in real time; the image recognition module is used for carrying out image processing on the monitored image, then carrying out similarity recognition on the processed image and the stored standard image, and generating a recognition result corresponding to the detection point when the similarity is lower than a preset value; and the checking module is used for acquiring the field actual detection information of the detection point corresponding to the identification result, and when the identification result of the image identification module is different from the field actual detection information, the identification accuracy of the image identification module is corrected according to the field actual detection information. This scheme can realize the effective control of the condition in the hydraulic pressure station.

Description

Hydraulic station monitoring and management system

Technical Field

The invention belongs to the field of industrial monitoring management, and particularly relates to a hydraulic station monitoring management system.

Background

A large number of hydraulic stations are distributed on a ferrous metallurgy production line, the hydraulic stations are distributed on each production line, the related area is large, and the time spent by inspection personnel in one inspection is long. Because the oil leakage of equipment in the hydraulic station cannot be found in time, a large amount of oil is accumulated in the hydraulic station, and the ground cleaning is damaged. At present, a production business mainly depends on a point inspection worker to inspect a hydraulic station, and a place where oil leakage is found informs a maintenance worker to clean in a form of a work order. As the number of the patrol stations is large and the time spent is long, the workload of workers is heavy, and the problems of poor ground cleaning of the hydraulic station and the like occur.

Disclosure of Invention

In view of the above-mentioned drawbacks of the prior art, it is an object of the present invention to provide a hydraulic station monitoring management system for achieving effective monitoring of conditions within a hydraulic station.

To achieve the above and other related objects, the present invention provides a hydraulic station monitoring and management system, including:

the monitoring module is used for monitoring each detection point in the hydraulic station in real time and acquiring a monitoring image of each monitoring point in real time;

the image recognition module is used for carrying out image processing on the monitored image, then carrying out similarity recognition on the processed image and the stored standard image, and generating a recognition result corresponding to the detection point when the similarity is lower than a preset value;

and the checking module is used for acquiring the field actual detection information of the detection point corresponding to the identification result, and when the identification result of the image identification module is different from the field actual detection information, the identification accuracy of the image identification module is corrected according to the field actual detection information.

Optionally, the monitoring module includes:

the pipeline monitoring submodule is used for monitoring whether the pipeline in the hydraulic station leaks oil or not;

the ground pollution condition monitoring submodule is used for monitoring the pollution condition of the ground in the hydraulic station;

and the equipment monitoring submodule is used for monitoring the oil leakage condition of the equipment in the hydraulic station.

Optionally, the pipeline monitoring submodule includes a plurality of pipeline monitoring units, and the plurality of pipeline monitoring units are respectively used for monitoring pipelines at different detection points; the ground pollution condition monitoring submodule comprises a plurality of ground pollution monitoring units, and the plurality of ground pollution monitoring units are used for monitoring the ground with different detection points respectively; the equipment monitoring submodule comprises a valve station monitoring unit and a pump group monitoring unit.

Optionally, the image recognition module comprises:

the storage submodule is used for storing the standard image, the monitoring image and the image processing model corresponding to each detection point;

the image processing submodule is used for acquiring an image processing model corresponding to the detection point according to the identification result, identifying and cutting a corresponding key detection area in the monitored image according to the image processing model and generating a key detection area image;

and the recognition and judgment submodule is used for carrying out similarity comparison on the key detection area image and the standard image and generating a recognition result corresponding to the detection point when the similarity is smaller than a preset value.

Optionally, the hydraulic station monitoring and management system further includes a training module, configured to train different image processing models according to different application conditions of the detection points.

Optionally, the application conditions include illumination intensity, view angle offset angle, and detection for the object.

Optionally, the verification module includes:

the field information acquisition submodule is used for acquiring field actual detection information of the corresponding detection point according to the detection result;

the verification judgment submodule is used for judging whether the identification result is different from the actual field detection information or not, and if the identification result is different from the actual field detection information, a judgment result is generated;

and the verification execution submodule is used for retraining the corresponding image processing model according to the judgment result.

Optionally, the verification judgment sub-module includes:

the verification processing unit is used for acquiring another image processing model under the similar application condition, cutting the corresponding monitoring image identified by the image identification module according to the image processing model and generating a key detection area inspection image;

the verification identification unit is used for comparing the similarity of the key area inspection image with the standard image and generating an inspection identification result when the similarity is smaller than a preset value;

and the judging unit is used for comparing the similarity of the inspection identification result with the actual inspection information on site, and if the similarity exceeds a preset value, generating a judgment result needing to be corrected by the image identification module.

Optionally, the check execution sub-module includes:

the training image acquisition unit is used for acquiring a plurality of groups of monitoring images in front of the monitoring images identified by the image identification module in the same detection point to generate a training image group;

the verification training unit is used for training a new image processing model according to the training image group, judging whether the recognition result generated by the image recognition module according to the new image processing model is consistent with the on-site actual detection information or not, and if so, replacing the corresponding original image processing model with the new image processing model; and if the data are inconsistent, generating maintenance information for the maintenance personnel to check.

Optionally, the hydraulic station monitoring and management system further includes an output module for outputting the identification result, and the output module includes a display sub-module and an alarm sub-module.

As described above, the hydraulic station monitoring and management system of the present invention has the following beneficial effects:

according to the scheme, the monitoring image is acquired through the monitoring module, the image recognition module is used for carrying out image processing and recognition on the monitoring image, whether the ground in the hydraulic station is polluted or not and whether oil leaks in equipment and pipelines or not are judged, and a recognition result is generated. And then the output module outputs the identification result for the detection personnel to check. And when the recognition result is inconsistent with the actual situation in the field, the verification module retrains and optimizes the image processing model called by the image recognition module so as to ensure the recognition accuracy of the image recognition module.

Drawings

Fig. 1 is a block diagram of a hydraulic station monitoring and management system according to an embodiment of the present invention.

Detailed Description

The following description of the embodiments of the present invention is provided for illustrative purposes, and other advantages and effects of the present invention will become apparent to those skilled in the art from the present disclosure.

Examples

As shown in fig. 1, the present embodiment provides a hydraulic station monitoring and management system, including:

monitoring module

The monitoring module is used for monitoring each detection point in the hydraulic station in real time and acquiring a monitoring image of each monitoring point in real time.

The monitoring module includes:

the pipeline monitoring submodule is used for monitoring whether the oil leakage condition of the pipeline in the hydraulic station exists; the pipeline monitoring submodule comprises a plurality of pipeline monitoring units, and the pipeline monitoring units are respectively used for monitoring pipelines with different detection points. The acquisition end of the pipeline monitoring unit is aligned with the corresponding detection point on the pipeline.

The ground pollution condition monitoring submodule is used for monitoring the pollution condition of the ground in the hydraulic station; the ground pollution condition monitoring submodule comprises a plurality of ground pollution monitoring units, and the plurality of ground pollution monitoring units are used for monitoring the ground with different detection points respectively. The acquisition end of the ground pollution monitoring unit is aligned with the corresponding detection point on the ground.

And the equipment monitoring submodule is used for monitoring the oil leakage condition of the equipment in the hydraulic station. The equipment monitoring submodule comprises a valve station monitoring unit, a pump group monitoring unit, an energy accumulator monitoring unit and the like. The collecting ends of the valve stand monitoring unit and the pump set monitoring unit are arranged in alignment with corresponding detecting points on the ground.

The acquisition ends of the pipeline monitoring unit, the ground pollution monitoring unit, the valve station monitoring unit, the pump group monitoring unit and the energy accumulator monitoring unit in the embodiment all comprise cameras, and video and image acquisition is carried out through the cameras, so that the monitoring of the hydraulic station is realized.

Second, training module

The training module is used for training different image processing models according to different application conditions of the detection points, and the image processing models and the detection points are correspondingly arranged. Applying conditions includes detecting target objects and environmental conditions including illumination intensity, viewing angle offset angle, etc.

Image recognition module

The image recognition module is used for circularly extracting the monitoring images corresponding to the detection points, carrying out image processing on the monitoring images, carrying out similarity judgment on the processed images and the standard images, and generating recognition results corresponding to the detection points when the similarity is lower than a preset value.

The image recognition module includes:

the storage submodule is used for storing the standard image, the monitoring image and the image processing model corresponding to each detection point;

the image processing submodule is used for acquiring an image processing model corresponding to the detection point according to the identification result, identifying and cutting a corresponding key detection area in the monitored image according to the image processing model and generating a key detection area image;

and the recognition and judgment submodule is used for carrying out similarity comparison on the key detection area image and the standard image and generating a recognition result corresponding to the detection point when the similarity is smaller than a preset value.

Four, output module

The output module is used for outputting the recognition result of the image recognition module.

The output module includes:

and the display submodule is used for displaying the identification result so as to facilitate the detection personnel to check the corresponding detection point according to the identification result.

And the alarm submodule is used for sending out an alarm so as to be known by detection personnel. The alarm module in this embodiment includes alarm indicator and buzzer.

Fifth, check module

The checking module is used for adjusting the image processing model used by the image recognition module when the recognition result of the image recognition module is not correct.

The verification module comprises:

and the field information acquisition submodule is used for acquiring field actual detection information of the corresponding detection point according to the detection result. The mode of acquiring the actual detection information may be information input by a detection person according to actual conditions on site after the detection result reaches a corresponding detection point, or may be acquired by installing other acquisition equipment (for example, installing a plurality of cameras at the same detection point, etc.), detection equipment (installing a sensor for hydraulic detection, etc. in a pipeline, etc.), and the like.

And the checking and judging submodule is used for judging whether the identification result is different from the actual field detection information or not, and generating a judgment result if the identification result is different from the actual field detection information. The check judgment submodule comprises:

and the checking processing unit is used for acquiring another image processing model under the similar application condition, and cutting the corresponding monitoring image when the recognition result of the image recognition module is inaccurate according to the image processing model to generate a key detection area inspection image. The similar application condition in this embodiment refers to a case where the detection is similar or identical for objects and the environmental conditions are similar. For example: a plurality of pipeline monitoring units are arranged in the same hydraulic station, wherein the distance between the two pipeline monitoring units is short, the environmental conditions are similar, the detection is carried out on the object by aiming at the pipeline, and the image processing models suitable for the two pipeline monitoring units are similar. The verification identification unit is used for comparing the similarity of the key area inspection image with the standard image and generating an inspection identification result when the similarity is smaller than a preset value;

and the judging unit is used for comparing the similarity of the inspection identification result with the actual inspection information on site, and if the similarity exceeds a preset value, generating a judgment result needing to be corrected by the image identification module.

And the verification execution submodule is used for retraining the image processing model originally called by the image recognition module according to the judgment result. The check execution submodule comprises:

and the training image acquisition unit is used for acquiring a plurality of groups of monitoring images before the monitoring images which are not accurately identified by the image identification module in the same detection point to generate a training image group. In this embodiment, the training image group is generated by all the monitoring images within 30 minutes before the corresponding monitoring image is acquired. For example: and the monitoring image which is not accurately identified by the image identification module is a monitoring image A, and 30 minutes before the monitoring image A is acquired by the image identification module, the monitoring images corresponding to the detection points comprise a monitoring image B, a monitoring image C, a monitoring image D and a monitoring image E, and the training image acquisition unit generates a training image group according to the monitoring image B, the monitoring image C, the monitoring image D and the monitoring image E.

The verification training unit is used for training a new image processing model according to the training image group, judging whether the recognition result generated by the image recognition module according to the new image processing model is consistent with the on-site actual detection information or not, and if so, replacing the corresponding original image processing model with the new image processing model; if the identification result is inconsistent with the actual field detection information, calling the image processing model with the identification result closest to the actual field detection information for temporary use, and generating maintenance information for maintenance personnel to maintain the image processing model.

During the use, this scheme obtains the surveillance image through the monitoring module, carries out image processing and discernment to the surveillance image through the image recognition module, judges whether ground pollutes in the hydraulic pressure station, whether equipment and pipeline oil leak, and the formation discernment result. And then the output module outputs the identification result for the detection personnel to check. And when the recognition result is inconsistent with the actual situation in the field, the verification module retrains and optimizes the image processing model called by the image recognition module so as to ensure the recognition accuracy of the image recognition module.

The foregoing embodiments are merely illustrative of the principles and utilities of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or change the above-mentioned embodiments without departing from the spirit and scope of the present invention. Accordingly, it is intended that all equivalent modifications or changes which can be made by those skilled in the art without departing from the spirit and technical spirit of the present invention be covered by the claims of the present invention.

Claims (10)

1. A hydraulic station monitoring and management system, comprising:

the monitoring module is used for monitoring each detection point in the hydraulic station in real time and acquiring a monitoring image of each monitoring point in real time;

the image recognition module is used for carrying out image processing on the monitored image, then carrying out similarity recognition on the processed image and the stored standard image, and generating a recognition result corresponding to the detection point when the similarity is lower than a preset value;

and the checking module is used for acquiring the field actual detection information of the detection point corresponding to the identification result, and when the identification result of the image identification module is different from the field actual detection information, the identification accuracy of the image identification module is corrected according to the field actual detection information.

2. The hydraulic station monitoring and management system of claim 1, wherein the monitoring module comprises:

the pipeline monitoring submodule is used for monitoring whether the pipeline in the hydraulic station leaks oil or not;

the ground pollution condition monitoring submodule is used for monitoring the pollution condition of the ground in the hydraulic station;

and the equipment monitoring submodule is used for monitoring the oil leakage condition of the equipment in the hydraulic station.

3. The hydraulic station monitoring and management system according to claim 2, wherein the pipeline monitoring submodule comprises a plurality of pipeline monitoring units, and the plurality of pipeline monitoring units are respectively used for monitoring pipelines with different detection points; the ground pollution condition monitoring submodule comprises a plurality of ground pollution monitoring units, and the plurality of ground pollution monitoring units are used for monitoring the ground with different detection points respectively; the equipment monitoring submodule comprises a valve station monitoring unit and a pump group monitoring unit.

4. The hydraulic station monitoring and management system according to claim 1, wherein the image recognition module comprises:

the storage submodule is used for storing the standard image, the monitoring image and the image processing model corresponding to each detection point;

the image processing submodule is used for acquiring an image processing model corresponding to the detection point according to the identification result, identifying and cutting a corresponding key detection area in the monitored image according to the image processing model and generating a key detection area image;

and the recognition and judgment submodule is used for carrying out similarity comparison on the key detection area image and the standard image and generating a recognition result corresponding to the detection point when the similarity is smaller than a preset value.

5. The hydraulic station monitoring and management system according to claim 4, further comprising a training module for training different image processing models according to different application conditions at each detection point.

6. The hydraulic station monitoring and management system according to claim 5, wherein the application conditions include illumination intensity, view angle offset angle, and detection for an object.

7. The hydraulic station monitoring and management system of claim 5, wherein the verification module comprises:

the field information acquisition submodule is used for acquiring field actual detection information of the corresponding detection point according to the detection result;

the verification judgment submodule is used for judging whether the identification result is different from the actual field detection information or not, and if the identification result is different from the actual field detection information, a judgment result is generated;

and the verification execution submodule is used for retraining the corresponding image processing model according to the judgment result.

8. The hydraulic station monitoring and management system according to claim 7, wherein the verification judgment sub-module comprises:

the verification processing unit is used for acquiring another image processing model under the similar application condition, cutting the corresponding monitoring image identified by the image identification module according to the image processing model and generating a key detection area inspection image;

the verification identification unit is used for comparing the similarity of the key area inspection image with the standard image and generating an inspection identification result when the similarity is smaller than a preset value;

and the judging unit is used for comparing the similarity of the inspection identification result with the actual inspection information on site, and if the similarity exceeds a preset value, generating a judgment result needing to be corrected by the image identification module.

9. The hydraulic station monitoring and management system of claim 8, wherein the verification execution submodule comprises:

the training image acquisition unit is used for acquiring a plurality of groups of monitoring images in front of the monitoring images identified by the image identification module in the same detection point to generate a training image group;

the verification training unit is used for training a new image processing model according to the training image group, judging whether the recognition result generated by the image recognition module according to the new image processing model is consistent with the on-site actual detection information or not, and if so, replacing the corresponding original image processing model with the new image processing model; and if the data are inconsistent, generating maintenance information for the maintenance personnel to check.

10. The hydraulic station monitoring and management system according to any one of claims 1-9, further comprising an output module for outputting the identification result, wherein the output module comprises a display sub-module and an alarm sub-module.

Images