Multi-environment proofreading system and method based on intelligent fuel gas inspection unmanned aerial vehicle

Abstract

The invention relates to the technical field of fuel gas inspection unmanned aerial vehicle proofreading, and discloses a multi-environment proofreading system and method based on an intelligent fuel gas inspection unmanned aerial vehicle, and the system comprises an acquisition module which is used for extracting historical detection data of the unmanned aerial vehicle; the model generation module is responsible for cleaning the data and establishing an environment detection model. The first central control module obtains environment information and gas leakage detection quantity in historical data and substitutes the environment information and the gas leakage detection quantity into the environment detection model, and the preset gas leakage quantity is compared with the actual detection quantity to determine whether the model is corrected or not. The acquisition module is used for acquiring environment information of a gas leakage area in real time; and the second central control module obtains the actual gas leakage rate of the region, and determines whether the detection quantity needs to be corrected based on the real-time environment information. Through cooperative work of the modules, the detection result of the fuel gas inspection unmanned aerial vehicle is checked, and the accuracy of leakage detection of the fuel gas inspection unmanned aerial vehicle is ensured.

Description

Technical Field

[0001] The present invention relates to the field of gas inspection drone calibration technology, and in particular to a multi-environment calibration system and method based on an intelligent gas inspection drone. Background Art

[0002] In the field of gas supply, it is particularly important to ensure the safe operation of gas facilities. In order to ensure public safety and the stability of people's lives, the reliability and safety of gas facilities must be given full attention. At present, the traditional gas inspection method mainly relies on manual inspection, which is not only inefficient and costly, but also limited by manpower and environmental factors, making it difficult to achieve comprehensive and timely inspection.

[0003] With the continuous advancement and innovation of science and technology, more and more advanced technologies are being applied to various fields. Especially in gas inspection, some advanced drone equipment has begun to emerge. These drones are equipped with high-precision sensors and cameras, which can efficiently complete the inspection tasks of gas pipelines. These drones can not only quickly cover a large area of ​​gas pipelines, but also go deep into some areas that are difficult for humans to reach for detailed inspections. Through real-time transmission of data and images, staff can promptly detect gas leaks, pipeline damage and other problems, and quickly take corresponding maintenance measures. This not only improves the efficiency and safety of inspections, but also greatly reduces manpower and time costs.

[0004] However, the current gas inspection drones have significant limitations in adapting to a variety of environments. On the one hand, the accuracy of the test results of the current gas inspection equipment will be significantly affected when encountering different environmental conditions such as temperature, humidity and air pressure, which in turn leads to misjudgment or missed judgment in complex environments. At the same time, when environmental factors change, it is difficult for the current technology to quickly and effectively proofread and correct the test results. This makes it impossible to accurately judge the amount of gas leakage, which poses a great safety hazard to gas maintenance personnel.

[0005] Therefore, there is an urgent need to invent a calibration technology for gas inspection drones during inspections, so as to solve the problem in the prior art that gas inspection drones may misjudge the detection structure due to the complex and changeable environment, thereby posing a great hidden danger to the safety of gas maintenance personnel. Summary of the invention

[0006] In view of this, the present invention proposes a multi-environment calibration system and method based on an intelligent gas inspection drone, aiming to solve the problem in current technology that gas inspection drones may misjudge the detection structure due to the complex and changeable environment, thereby posing a great hidden danger to the safety of gas maintenance personnel.

[0007] The present invention proposes a multi-environment calibration system based on an intelligent gas inspection drone, comprising:

[0008] An acquisition module, electrically connected to the database, and used to acquire various historical detection data of the drone;

[0009] A model generation module, electrically connected to the acquisition module, the model generation module is used to clean up each of the historical detection data, and the model generation module is also used to establish an environmental detection model of the inspection drone according to each of the historical detection data after data cleaning;

[0010] The first central control module is electrically connected to the model generation module, and is used to obtain the environmental information and the gas leakage detection amount in any of the historical detection data. The first central control module is also used to substitute the environmental information and the gas leakage detection amount into the environmental detection model, compare the preset gas leakage amount output by the environmental detection model with the gas leakage detection amount, and determine whether to modify the environmental detection model according to the comparison result, wherein:

[0011] When the preset gas leakage amount is inconsistent with the gas leakage detection amount, the first central control module determines to iteratively correct the environmental detection model;

[0012] A collection module, connected to the drone, for collecting real-time environmental information of the gas leakage area;

[0013] The second central control module is electrically connected to the first central control module and the acquisition module respectively. The second central control module is used to obtain the gas leakage amount detected by the drone in the gas leakage area, and determine whether to calibrate the gas leakage amount based on the real-time environmental information of the gas leakage area.

[0014] Furthermore, when the model generation module is used to clean up the historical detection data, it includes:

[0015] The model generation module is used to obtain duplicate data in each of the historical detection data and clear the duplicate data;

[0016] The model generation module is also used to obtain abnormal data in each of the historical detection data after removing duplicate data, and eliminate the abnormal data.

[0017] Furthermore, the model generation module is also used to establish an environmental detection model of the inspection drone according to the historical detection data after data cleaning, including:

[0018] The model generation module is also used to obtain environmental information and gas leakage detection amount in each historical detection data after removing the abnormal data, wherein the environmental information includes: actual gas leakage amount, environmental temperature and humidity, environmental pressure and environmental ventilation amount;

[0019] The model generation module is also used to establish a linear axis of the gas leakage detection amount according to the relationship between the actual gas leakage amount, ambient temperature and humidity, ambient air pressure, ambient ventilation amount and the gas leakage detection amount;

[0020] The model generation module is also used to establish the environmental detection model according to the linear axis of the gas leakage detection quantity.

[0021] Furthermore, the model generation module is also used to obtain abnormal data in each of the historical detection data after removing duplicate data, including:

[0022] The model generation module is also used to obtain the actual gas leakage amount and the gas leakage detection amount in each of the historical detection data after removing duplicate data, and determine whether the historical detection data is abnormal data according to the relationship between the actual gas leakage amount and the gas leakage detection amount:

[0023] When the actual gas leakage amount is consistent with the gas leakage detection amount, the model generation module determines that the historical detection data is not the abnormal data;

[0024] When the actual gas leakage amount is inconsistent with the gas leakage detection amount, the model generation module determines that the historical detection data is the abnormal data.

[0025] Furthermore, when the preset gas leakage amount is inconsistent with the gas leakage detection amount, the first central control module determines to iteratively correct the environment detection model, including:

[0026] The first central control module is further used to obtain a detection amount difference between the preset gas leakage amount and the gas leakage detection amount, and determine a correction coefficient for the iterative correction according to a relationship between the detection amount difference and a first preset detection amount difference and a second preset detection amount difference configured by the first central control module:

[0027] When the detection quantity difference is lower than or equal to the first preset detection quantity difference, the first central control module determines that the correction coefficient is M3;

[0028] When the detection quantity difference is higher than the first preset detection quantity difference, and the detection quantity difference is lower than or equal to the second preset detection quantity difference, the first central control module determines that the correction coefficient is M2;

[0029] When the detection value difference is higher than the second preset detection value difference, the first central control module determines that the correction coefficient is M1;

[0030] The first preset detection quantity difference is smaller than the second preset detection quantity difference, and M1<M2<M3<1.

[0031] Further, when the first central control module determines that the correction coefficient of the iterative correction is M i, i=1, 2, 3, it includes:

[0032] The first central control module is also used to obtain the iteratively corrected environment detection model;

[0033] The first central control module is further used to obtain environmental information and gas leakage detection quantity in any of the historical detection data, and substitute the environmental information and gas leakage detection quantity into the environmental detection model;

[0034] The first central control module is further used to compare the second preset gas leakage amount output by the iteratively corrected environmental detection model with the gas leakage detection amount, and determine whether to perform a second correction on the iteratively corrected environmental detection model according to the comparison result, wherein:

[0035] When the second preset gas leakage amount is inconsistent with the gas leakage detection amount, the first central control module determines to perform a second iterative correction on the iteratively corrected environmental detection model.

[0036] Furthermore, the acquisition module includes:

[0037] A gas collection unit, electrically connected to the gas detection system of the drone, and used to obtain the real-time concentration of the gas detected by the drone;

[0038] A temperature and humidity detection unit connected to the drone, the temperature and humidity detection unit is used to obtain the real-time environmental temperature and humidity of the gas leakage area;

[0039] An air pressure detection unit connected to the drone, the air pressure detection unit is used to obtain the real-time ambient air pressure of the gas leakage area;

[0040] A flow detection unit is connected to the drone, and the flow detection unit is used to obtain the real-time environmental ventilation volume and real-time environmental wind direction of the gas leakage area.

[0041] Furthermore, the second central control module is used to determine whether to calibrate the gas leakage amount according to the real-time environmental information of the gas leakage area, including:

[0042] The second central control module is further used to substitute the real-time environmental information into the environmental detection model and obtain a preset detection leakage amount input by the environmental detection model;

[0043] The second central control module is further used to determine whether the gas leakage amount needs to be calibrated according to the relationship between the preset detection leakage amount and the gas leakage amount, wherein:

[0044] If the preset detected leakage amount is consistent with the gas leakage amount, the second central control module determines that the gas leakage amount does not need to be calibrated;

[0045] If the preset detection leakage amount is inconsistent with the gas leakage amount, the second central control module determines a calibration coefficient according to the difference between the preset detection leakage amount and the gas leakage amount, and calibrates the gas leakage amount according to the calibration coefficient.

[0046] Furthermore, when the second central control module determines the calibration coefficient according to the difference between the preset detected leakage amount and the gas leakage amount, it includes:

[0047] The second central control module is further used to determine the calibration coefficient according to the difference and the relationship between the first preset difference and the second preset difference configured by the second central control module;

[0048] When the difference is less than or equal to the first preset difference, the second central control module determines that the calibration coefficient is N3;

[0049] When the difference is greater than the first preset difference and the difference is less than or equal to the second preset difference, the second central control module determines that the calibration coefficient is N2;

[0050] When the difference is greater than the second preset difference, the second central control module determines that the calibration coefficient is N1;

[0051] Among them, the first preset difference is smaller than the second preset difference, N1<N2<N3<1.

[0052] Compared with the prior art, the beneficial effect of the present invention is that the acquisition module obtains the historical detection data of the drone from the database, which provides a rich data basis for the operation of the system. By collecting these historical data, the detection results under different environmental conditions can be covered, providing a comprehensive source of information for subsequent analysis and model building. The model generation module performs data cleaning on each historical detection data, removes invalid and erroneous data, and ensures the quality and reliability of the data. The environmental detection model of the inspection drone established on this basis can make full use of historical experience and more accurately reflect the impact of different environmental factors on gas leak detection. Secondly, the first central control module substitutes the environmental information and gas leak detection amount in the historical detection data into the environmental detection model for comparison, and this process realizes real-time monitoring of the accuracy of the model. When the preset gas leakage amount is inconsistent with the actual gas leakage detection amount, the first central control module determines to iteratively correct the environmental detection model. This self-correction mechanism enables the model to continuously adapt to new situations and changes, and the accuracy and reliability of the model will continue to improve over time. For example, in different seasons and under different weather conditions, environmental factors will change, and through this iterative correction, the model can be adjusted in time to adapt to these changes, ensuring that the prediction of gas leaks always remains accurate. Finally, by connecting the acquisition module to the drone, the environmental information of the gas leakage area can be collected in real time. At the same time, the second central control module is electrically connected to the first central control module and the acquisition module respectively, so that the gas leakage amount in the gas leakage area detected by the drone can be obtained on the one hand, and on the other hand, it can be determined whether to calibrate the gas leakage amount based on the real-time environmental information. This real-time calibration capability greatly improves the accuracy and reliability of the detection results. Even in the event of sudden environmental changes, such as sudden temperature rise, sudden change in air pressure, etc., the second central control module can respond quickly and adjust the detection results according to the new environmental information to ensure that there will be no misjudgment or missed judgment, providing a solid guarantee for gas safety.

[0053] On the other hand, the present application also provides a multi-environment calibration method based on an intelligent gas inspection drone, comprising:

[0054] Acquire historical detection data of the drone, and clean up the historical detection data;

[0055] Establish an environmental detection model for the inspection drone according to each of the historical detection data after data cleaning; obtain environmental information and gas leakage detection quantity in any of the historical detection data, substitute the environmental information and gas leakage detection quantity into the environmental detection model, compare the preset gas leakage quantity output by the environmental detection model with the gas leakage detection quantity, and determine whether to modify the environmental detection model according to the comparison result, wherein:

[0056] When the preset gas leakage amount is inconsistent with the gas leakage detection amount, determining to iteratively correct the environment detection model;

[0057] Obtaining the amount of gas leakage detected by the drone in the gas leakage area;

[0058] The real-time environmental information of the gas leakage area is collected, and according to the real-time environmental information of the gas leakage area, it is determined whether to calibrate the gas leakage amount.

[0059] It can be understood that the multi-environment calibration system and method based on the intelligent gas inspection drone in the above-mentioned embodiments of the present invention have the same beneficial effects and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0061] Figure 1 A functional block diagram of a multi-environment calibration system based on an intelligent gas inspection drone provided in an embodiment of the present invention;

[0062] Figure 2 A flowchart of a multi-environment calibration method based on an intelligent gas inspection drone is provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0063] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art. It should be noted that, in the absence of conflict, the embodiments of the present invention and the features described in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0064] In the field of gas supply, it is particularly important to ensure the safe operation of gas facilities. In order to ensure public safety and the stability of people's lives, the reliability and safety of gas facilities must be given full attention. At present, the traditional gas inspection method mainly relies on manual inspection, which is not only inefficient and costly, but also limited by manpower and environmental factors, making it difficult to achieve comprehensive and timely inspection.

[0065] With the continuous advancement and innovation of science and technology, more and more advanced technologies are being applied to various fields. Especially in gas inspection, some advanced drone equipment has begun to emerge. These drones are equipped with high-precision sensors and cameras, which can efficiently complete the inspection tasks of gas pipelines. These drones can not only quickly cover a large area of ​​gas pipelines, but also go deep into some areas that are difficult for humans to reach for detailed inspections. Through real-time transmission of data and images, staff can promptly detect gas leaks, pipeline damage and other problems, and quickly take corresponding maintenance measures. This not only improves the efficiency and safety of inspections, but also greatly reduces manpower and time costs.

[0066] However, the current gas inspection drones have significant limitations in adapting to a variety of environments. On the one hand, the accuracy of the test results of the current gas inspection equipment will be significantly affected when encountering different environmental conditions such as temperature, humidity and air pressure, which in turn leads to misjudgment or missed judgment in complex environments. At the same time, when environmental factors change, it is difficult for the current technology to quickly and effectively proofread and correct the test results. This makes it impossible to accurately judge the amount of gas leakage, which poses a great safety hazard to gas maintenance personnel.

[0067] In view of this, the present invention proposes a multi-environment calibration system and method based on an intelligent gas inspection drone, aiming to solve the problem in current technology that gas inspection drones may misjudge the detection structure due to the complex and changeable environment, thereby posing a great hidden danger to the safety of gas maintenance personnel.

[0068] like Figure 1 As shown, in some embodiments of the present application, this embodiment provides a multi-environment calibration system based on an intelligent gas inspection drone, including: an acquisition module, a model generation module, a first central control module, a collection module, and a second central control module;

[0069] Specifically, the acquisition module is electrically connected to the database, and the acquisition module is used to acquire various historical detection data of the drone; the model generation module is electrically connected to the acquisition module, and the model generation module is used to clean up various historical detection data, and the model generation module is also used to establish an environmental detection model for the inspection drone according to various historical detection data after data cleaning; the first central control module is electrically connected to the model generation module, and the first central control module is used to acquire environmental information and gas leakage detection quantity in any historical detection data, and the first central control module is also used to substitute the environmental information and gas leakage detection quantity into the environmental detection model, and output the preset gas leakage detection quantity according to the environmental detection model. The gas leakage amount is compared with the gas leakage detection amount, and according to the comparison result, it is determined whether to correct the environmental detection model, wherein: when the preset gas leakage amount is inconsistent with the gas leakage detection amount, the first central control module determines to iteratively correct the environmental detection model; the acquisition module is connected to the drone, and the acquisition module is used to collect real-time environmental information of the gas leakage area; the second central control module is electrically connected to the first central control module and the acquisition module respectively, and the second central control module is used to obtain the gas leakage amount of the gas leakage area detected by the drone, and according to the real-time environmental information of the gas leakage area, it is determined whether to calibrate the gas leakage amount.

[0070] It can be seen that the multi-environment calibration system based on the intelligent gas inspection drone in the present invention is mainly composed of an acquisition module, a model generation module, a first central control module, a collection module and a second central control module. The acquisition module is first electrically connected to the database to extract the historical detection data recorded in the previous inspection process of the drone, which covers the environmental information and gas leakage of the gas leak. Secondly, after receiving the historical detection data, the model generation module performs data cleaning to eliminate redundant data or errors, and generates an environmental detection model based on the cleaned data to provide an accurate basis for subsequent detection. After the model is generated, the first central control module takes over the analysis task. It is not only responsible for substituting the environmental information and gas leakage detection amount in the historical detection data into the environmental detection model, but also compares the preset gas leakage amount generated by the model with the actual detected gas leakage amount. If there is a difference between the two, the first central control module will automatically trigger the iterative correction mechanism to dynamically optimize the model. Through this iteration, the first central control module can continuously adjust the model as the detection data increases, so that the gas leakage detection in different environments is more accurate. At the same time, the acquisition module collects the environmental information of the current gas leakage area in real time and transmits it to the second central control module. The second central control module will compare the real-time environmental information with the gas leakage detection result of the first central control module to determine whether the detection result needs to be corrected. If the real-time environmental information indicates that the detection conditions have changed, the second central control module will make necessary corrections to the gas leakage to ensure the accuracy of the detection result.

[0071] In some embodiments of the present application, when the model generation module is used to clean up each historical detection data, it includes: the model generation module is used to obtain duplicate data in each historical detection data and remove the duplicate data. The model generation module is also used to obtain abnormal data in each historical detection data after removing the duplicate data, and remove the abnormal data.

[0072] Specifically, the model generation module is also used to establish the environmental detection model of the inspection drone based on the historical detection data after data cleaning, including: the model generation module is also used to obtain the environmental information and gas leakage detection amount in each historical detection data after eliminating abnormal data, wherein the environmental information includes: actual gas leakage amount, ambient temperature and humidity, ambient air pressure and ambient ventilation amount. The model generation module is also used to establish the linear axis of the gas leakage detection amount based on the relationship between the actual gas leakage amount, ambient temperature and humidity, ambient air pressure, ambient ventilation amount and the gas leakage detection amount. The model generation module is also used to establish the environmental detection model based on the linear axis of the gas leakage detection amount.

[0073] Specifically, when the model generation module is also used to obtain abnormal data in each historical detection data after removing duplicate data, it includes: the model generation module is also used to obtain the actual gas leakage amount and the gas leakage detection amount in each historical detection data after removing duplicate data, and determine whether the historical detection data is abnormal data based on the relationship between the actual gas leakage amount and the gas leakage detection amount: when the actual gas leakage amount is consistent with the gas leakage detection amount, the model generation module determines that the historical detection data is not abnormal data. When the actual gas leakage amount is inconsistent with the gas leakage detection amount, the model generation module determines that the historical detection data is abnormal data.

[0074] It can be seen that the model generation module performs comprehensive data cleaning on the historical detection data accumulated during the drone inspection process. The first step of data cleaning is to remove duplicate data to ensure that the data on which the model is based is independent and non-redundant. By effectively eliminating duplicate data, the model generation module can avoid the interference of redundant data on model calculation and ensure the accuracy and reliability of model generation. Secondly, after removing duplicate data, the model generation module will further identify and eliminate abnormal data. Abnormal data may come from sensor failure, environmental fluctuations or other unforeseen error sources. Eliminating these abnormal data is an important step to ensure the stability of the model. By effectively identifying and excluding abnormal data, the model generation module ensures the authenticity and validity of the input data, thus laying the foundation for the accurate generation of the model. After completing data cleaning, the model generation module begins to extract key variables from the processed historical data, including information such as actual gas leakage, ambient temperature and humidity, ambient air pressure, and ambient ventilation. These variables directly affect the accuracy of gas leak detection, so the relationship between them constitutes the core of the model. After extracting these variables, the model generation module establishes a linear axis of the gas leak detection amount based on the relationship between them and the gas leak detection amount. This linear axis provides a simplified mathematical expression that links complex environmental factors and gas leak data to form a quantifiable prediction framework. Finally, the model generation module further generates an environmental detection model based on the linear axis. This model is the core tool for patrol drones to detect gas leaks. It can predict and monitor gas leaks based on preset mathematical relationships under different environmental conditions. In this way, the system can adapt to different environmental changes and ensure the accuracy of gas leak detection.

[0075] In some embodiments of the present application, when the preset gas leakage amount is inconsistent with the gas leakage detection amount, the first central control module determines to iteratively correct the environmental detection model, including: the first central control module is also used to obtain the detection amount difference between the preset gas leakage amount and the gas leakage detection amount, and determine the correction coefficient for iterative correction according to the relationship between the detection amount difference and the first preset detection amount difference and the second preset detection amount difference configured by the first central control module: when the detection amount difference is lower than or equal to the first preset detection amount difference, the first central control module determines the correction coefficient to be M3. When the detection amount difference is higher than the first preset detection amount difference, and the detection amount difference is lower than or equal to the second preset detection amount difference, the first central control module determines the correction coefficient to be M2. When the detection amount difference is higher than the second preset detection amount difference, the first central control module determines the correction coefficient to be M1. Among them, the first preset detection amount difference is less than the second preset detection amount difference, and M1<M2<M3<1.

[0076] Specifically, when the first central control module determines that the correction coefficient of the iterative correction is Mi, i = 1, 2, 3, it includes: the first central control module is also used to obtain the iteratively corrected environmental detection model. The first central control module is also used to obtain environmental information and gas leakage detection quantity in any historical detection data, and substitute the environmental information and gas leakage detection quantity into the environmental detection model. The first central control module is also used to compare the second preset gas leakage quantity output by the iteratively corrected environmental detection model with the gas leakage detection quantity, and determine whether to perform a secondary correction on the iteratively corrected environmental detection model based on the comparison result, wherein: when the second preset gas leakage quantity is inconsistent with the gas leakage detection quantity, the first central control module determines to perform a secondary iterative correction on the iteratively corrected environmental detection model.

[0077] It can be seen that the first central control module determines the size of the correction coefficient according to the relationship between the difference in the detected amount and the preset difference. When the difference in the detected amount is small, the first central control module selects the coefficient M3 with a smaller correction amplitude to ensure that the fine-tuning of the model is accurate and does not introduce additional errors; if the difference in the detected amount is in the medium range, the first central control module uses the intermediate correction coefficient M2 for moderate adjustment; and when the difference in the detected amount exceeds the higher preset threshold, the first central control module will use the maximum correction coefficient M1 for a larger correction. This design ensures that the first central control module can take corresponding adjustment measures when facing different degrees of deviation to ensure the smoothness and effectiveness of the correction process. After completing the first correction, the first central control module will substitute the environmental information in the historical data and the gas leakage detection amount into the model again based on the corrected environmental detection model for prediction, and compare the corrected model output results. If there is still a deviation in the comparison result, the first central control module will trigger the second iterative correction and continue to adjust the model according to the new difference in the detected amount until the preset gas leakage amount and the actual gas leakage detection amount are consistent. Through this mechanism of multiple iterative corrections, the model can gradually approach the real environmental conditions, thereby improving its accuracy and robustness in practical applications. The advantage of this solution lies in its high adaptability. The first central control module does not rely on only one correction to complete the adjustment of the model, but flexibly selects the correction coefficient according to the specific deviation situation and makes gradual adjustments. This hierarchical and gradually optimized correction mechanism enables the model to adapt to different environmental conditions and complex detection situations. At the same time, by setting the correction coefficient to less than 1, the stability of the correction process is ensured, the instability caused by excessive adjustment of the model is avoided, and the reliability of the model in different scenarios is maintained. Finally, this model optimization strategy based on iterative correction and flexible adjustment greatly enhances the accuracy of gas leak detection, enables the inspection drone to conduct efficient inspections in complex environments, and corrects the gas leak detection model in real time to ensure that the monitoring results of gas leaks match the actual situation. Through this continuous iteration and adjustment, the first central control module can achieve long-term self-optimization and adapt to complex and changeable actual inspection tasks.

[0078] In some embodiments of the present application, the collection module includes: a gas collection unit, a temperature and humidity detection unit, an air pressure detection unit and a flow detection unit.

[0079] Specifically, the gas collection unit is electrically connected to the gas detection system of the drone, and the gas collection unit is used to obtain the real-time concentration of gas detected by the drone. The temperature and humidity detection unit is connected to the drone, and the temperature and humidity detection unit is used to obtain the real-time environmental temperature and humidity in the gas leakage area. The air pressure detection unit is connected to the drone, and the air pressure detection unit is used to obtain the real-time environmental air pressure in the gas leakage area. The flow detection unit is connected to the drone, and the flow detection unit is used to obtain the real-time environmental ventilation volume and real-time environmental wind direction in the gas leakage area.

[0080] In some embodiments of the present application, when the second central control module is used to determine whether to calibrate the gas leakage amount based on the real-time environmental information of the gas leakage area, it includes: the second central control module is also used to substitute the real-time environmental information into the environmental detection model, and obtain the preset detection leakage amount input by the environmental detection model. The second central control module is also used to determine whether the gas leakage amount needs to be calibrated based on the relationship between the preset detection leakage amount and the gas leakage amount, wherein: if the preset detection leakage amount is consistent with the gas leakage amount, the second central control module determines that the gas leakage amount does not need to be calibrated. If the preset detection leakage amount is inconsistent with the gas leakage amount, the second central control module determines the calibration coefficient based on the difference between the preset detection leakage amount and the gas leakage amount, and calibrates the gas leakage amount based on the calibration coefficient.

[0081] Specifically, when the second central control module determines the calibration coefficient according to the difference between the preset detection leakage amount and the gas leakage amount, it includes: the second central control module is also used to determine the calibration coefficient according to the difference and the relationship between the first preset difference and the second preset difference configured by the second central control module: when the difference is less than or equal to the first preset difference, the second central control module determines the calibration coefficient to be N3. When the difference is greater than the first preset difference, and the difference is less than or equal to the second preset difference, the second central control module determines the calibration coefficient to be N2. When the difference is greater than the second preset difference, the second central control module determines the calibration coefficient to be N1. Among them, the first preset difference is less than the second preset difference, and N1<N2<N3<1.

[0082] It can be seen that when the drone detects the real-time environmental information of the gas leakage area, the second central control module substitutes this information into the environmental detection model to obtain the preset detection leakage generated by the model. The preset detection leakage is the theoretical value predicted by the model according to the environmental conditions, and is compared with the actual detected gas leakage. If the preset detection leakage is consistent with the actual detected gas leakage, the second central control module will determine that the gas leakage does not need further calibration, indicating that the detection result is consistent with the model prediction and meets the expected situation under environmental conditions. However, when there is a discrepancy between the two, the second central control module will determine whether calibration is required by calculating the difference between the two, and select an appropriate calibration coefficient according to the size of the difference. When the difference is small, the second central control module uses a smaller calibration coefficient N3 for slight correction to ensure that the impact on the detection result is minimized when the data deviation is small and avoid over-adjustment; when the difference is in the medium range, the second central control module uses the intermediate calibration coefficient N2 to adjust the gas leakage with a moderate amplitude; and when the difference is large, the second central control module selects a larger calibration coefficient N1 to significantly adjust the gas leakage and correct the larger error. This design ensures that the second central control module can flexibly adjust the gas leakage detection results under different degrees of deviation, improving the accuracy and precision of the detection. Through the hierarchical proofreading mechanism, the second central control module can effectively and dynamically adjust the gas leakage detection results according to the real-time environmental information. The entire proofreading process not only relies on the reasonable configuration of the preset difference and proofreading coefficient, but also combines the influence of real-time environmental factors, thereby improving the model's adaptive ability. This enables the system to maintain a high level of monitoring accuracy when facing complex and changing environmental conditions.

[0083] In the above embodiment, the acquisition module obtains the historical detection data of the drone from the database, which provides a rich data basis for the operation of the system. By collecting these historical data, the detection results under different environmental conditions can be covered, providing a comprehensive source of information for subsequent analysis and model building. The model generation module performs data cleaning on each historical detection data, removes invalid and erroneous data, and ensures the quality and reliability of the data. The environmental detection model of the inspection drone established on this basis can make full use of historical experience and more accurately reflect the impact of different environmental factors on gas leak detection. Secondly, the first central control module substitutes the environmental information and gas leak detection amount in the historical detection data into the environmental detection model for comparison, and this process realizes real-time monitoring of the accuracy of the model. When the preset gas leakage amount is inconsistent with the actual gas leakage detection amount, the first central control module determines to iteratively correct the environmental detection model. This self-correction mechanism enables the model to continuously adapt to new situations and changes, and the accuracy and reliability of the model will continue to improve over time. For example, in different seasons and under different weather conditions, environmental factors will change, and through this iterative correction, the model can be adjusted in time to adapt to these changes, ensuring that the prediction of gas leaks always remains accurate. Finally, by connecting the acquisition module to the drone, the environmental information of the gas leakage area can be collected in real time. At the same time, the second central control module is electrically connected to the first central control module and the acquisition module respectively, so that the gas leakage amount in the gas leakage area detected by the drone can be obtained on the one hand, and on the other hand, it can be determined whether to calibrate the gas leakage amount based on the real-time environmental information. This real-time calibration capability greatly improves the accuracy and reliability of the detection results. Even in the event of sudden environmental changes, such as sudden temperature rise, sudden change in air pressure, etc., the second central control module can respond quickly and adjust the detection results according to the new environmental information to ensure that there will be no misjudgment or missed judgment, providing a solid guarantee for gas safety.

[0084] In another preferred embodiment based on the above embodiment, Figure 2 As shown, this embodiment provides a multi-environment calibration method based on an intelligent gas inspection drone, comprising:

[0085] Step S100: Acquire each historical detection data of the drone, and perform data cleaning on each historical detection data.

[0086] Step S200: Establish an environmental detection model for the inspection drone based on the historical detection data after data cleaning.

[0087] Step S300, obtain environmental information and gas leakage detection amount in any historical detection data, substitute the environmental information and gas leakage detection amount into the environmental detection model, compare the preset gas leakage amount output by the environmental detection model with the gas leakage detection amount, and determine whether to correct the environmental detection model according to the comparison result. Wherein: when the preset gas leakage amount is inconsistent with the gas leakage detection amount, it is determined to iteratively correct the environmental detection model.

[0088] Step S400: Obtain the amount of gas leakage in the gas leakage area detected by the drone.

[0089] Step S500: Collect real-time environmental information of the gas leakage area, and determine whether to calibrate the gas leakage amount based on the real-time environmental information of the gas leakage area.

[0090] It can be understood that the multi-environment calibration system and method based on the intelligent gas inspection drone in the above-mentioned embodiments of the present invention have the same beneficial effects and will not be repeated here.

[0091] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0092] The present application is described with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0093] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1A function specified in one or more boxes.

[0094] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0095] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A multi-environment calibration system based on intelligent gas inspection drone, characterized in that: include: An acquisition module, electrically connected to the database, and used to acquire various historical detection data of the drone; A model generation module, electrically connected to the acquisition module, the model generation module is used to clean up each of the historical detection data, and the model generation module is also used to establish an environmental detection model of the inspection drone according to each of the historical detection data after data cleaning; The first central control module is electrically connected to the model generation module, and is used to obtain the environmental information and the gas leakage detection amount in any of the historical detection data. The first central control module is also used to substitute the environmental information and the gas leakage detection amount into the environmental detection model, compare the preset gas leakage amount output by the environmental detection model with the gas leakage detection amount, and determine whether to modify the environmental detection model according to the comparison result, wherein: When the preset gas leakage amount is inconsistent with the gas leakage detection amount, the first central control module determines to iteratively correct the environmental detection model; A collection module, connected to the drone, for collecting real-time environmental information of the gas leakage area; The second central control module is electrically connected to the first central control module and the acquisition module respectively. The second central control module is used to obtain the gas leakage amount detected by the drone in the gas leakage area, and determine whether to calibrate the gas leakage amount based on the real-time environmental information of the gas leakage area.

2. The multi-environment calibration system based on the intelligent gas inspection drone as claimed in claim 1 is characterized in that: The model generation module is used to clean up the historical detection data, including: The model generation module is used to obtain duplicate data in each of the historical detection data and clear the duplicate data; The model generation module is also used to obtain abnormal data in each of the historical detection data after removing duplicate data, and eliminate the abnormal data.

3. The multi-environment calibration system based on the intelligent gas inspection drone as claimed in claim 2 is characterized in that: The model generation module is also used to establish an environmental detection model of the inspection drone according to the historical detection data after data cleaning, including: The model generation module is also used to obtain environmental information and gas leakage detection amount in each historical detection data after removing the abnormal data, wherein the environmental information includes: actual gas leakage amount, environmental temperature and humidity, environmental pressure and environmental ventilation amount; The model generation module is also used to establish a linear axis of the gas leakage detection amount according to the relationship between the actual gas leakage amount, ambient temperature and humidity, ambient air pressure, ambient ventilation amount and the gas leakage detection amount; The model generation module is also used to establish the environmental detection model according to the linear axis of the gas leakage detection quantity.

4. The multi-environment calibration system based on the intelligent gas inspection drone as claimed in claim 3 is characterized in that: The model generation module is also used to obtain abnormal data in each of the historical detection data after removing duplicate data, including: The model generation module is also used to obtain the actual gas leakage amount and the gas leakage detection amount in each of the historical detection data after removing duplicate data, and determine whether the historical detection data is abnormal data according to the relationship between the actual gas leakage amount and the gas leakage detection amount: When the actual gas leakage amount is consistent with the gas leakage detection amount, the model generation module determines that the historical detection data is not the abnormal data; When the actual gas leakage amount is inconsistent with the gas leakage detection amount, the model generation module determines that the historical detection data is the abnormal data.

5. The multi-environment calibration system based on the intelligent gas inspection drone as claimed in claim 1 is characterized in that: When the preset gas leakage amount is inconsistent with the gas leakage detection amount, the first central control module determines to iteratively correct the environment detection model, including: The first central control module is further used to obtain a detection amount difference between the preset gas leakage amount and the gas leakage detection amount, and determine a correction coefficient for the iterative correction according to a relationship between the detection amount difference and a first preset detection amount difference and a second preset detection amount difference configured by the first central control module: When the detection quantity difference is lower than or equal to the first preset detection quantity difference, the first central control module determines that the correction coefficient is M3; When the detection quantity difference is higher than the first preset detection quantity difference, and the detection quantity difference is lower than or equal to the second preset detection quantity difference, the first central control module determines that the correction coefficient is M2; When the detection value difference is higher than the second preset detection value difference, the first central control module determines that the correction coefficient is M1; The first preset detection quantity difference is smaller than the second preset detection quantity difference, and M1<M2<M3<1.

6. The multi-environment calibration system based on the intelligent gas inspection drone as claimed in claim 5 is characterized in that: When the first central control module determines that the correction coefficient of the iterative correction is Mi, i=1, 2, 3, it includes: The first central control module is also used to obtain the iteratively corrected environment detection model; The first central control module is further used to obtain environmental information and gas leakage detection quantity in any of the historical detection data, and substitute the environmental information and gas leakage detection quantity into the environmental detection model; The first central control module is further used to compare the second preset gas leakage amount output by the iteratively corrected environmental detection model with the gas leakage detection amount, and determine whether to perform a second correction on the iteratively corrected environmental detection model according to the comparison result, wherein: When the second preset gas leakage amount is inconsistent with the gas leakage detection amount, the first central control module determines to perform a second iterative correction on the iteratively corrected environmental detection model.

7. The multi-environment calibration system based on the intelligent gas inspection drone as claimed in claim 1 is characterized in that: The acquisition module comprises: A gas collection unit, electrically connected to the gas detection system of the drone, and used to obtain the real-time concentration of the gas detected by the drone; A temperature and humidity detection unit connected to the drone, the temperature and humidity detection unit is used to obtain the real-time environmental temperature and humidity of the gas leakage area; An air pressure detection unit connected to the drone, the air pressure detection unit is used to obtain the real-time ambient air pressure of the gas leakage area; A flow detection unit is connected to the drone, and the flow detection unit is used to obtain the real-time environmental ventilation volume and real-time environmental wind direction of the gas leakage area.

8. The multi-environment calibration system based on the intelligent gas inspection drone as claimed in claim 1 is characterized in that: The second central control module is used to determine whether to calibrate the gas leakage amount according to the real-time environmental information of the gas leakage area, including: The second central control module is further used to substitute the real-time environmental information into the environmental detection model and obtain a preset detection leakage amount input by the environmental detection model; The second central control module is further used to determine whether the gas leakage amount needs to be calibrated according to the relationship between the preset detection leakage amount and the gas leakage amount, wherein: If the preset detected leakage amount is consistent with the gas leakage amount, the second central control module determines that the gas leakage amount does not need to be calibrated; If the preset detection leakage amount is inconsistent with the gas leakage amount, the second central control module determines a calibration coefficient according to the difference between the preset detection leakage amount and the gas leakage amount, and calibrates the gas leakage amount according to the calibration coefficient.

9. The multi-environment calibration system based on the intelligent gas inspection drone as claimed in claim 8, characterized in that: The second central control module determines the calibration coefficient according to the difference between the preset detected leakage amount and the gas leakage amount, including: The second central control module is further used to determine the calibration coefficient according to the difference and the relationship between the first preset difference and the second preset difference configured by the second central control module; When the difference is less than or equal to the first preset difference, the second central control module determines that the calibration coefficient is N3; When the difference is greater than the first preset difference and the difference is less than or equal to the second preset difference, the second central control module determines that the calibration coefficient is N2; When the difference is greater than the second preset difference, the second central control module determines that the calibration coefficient is N1; Among them, the first preset difference is smaller than the second preset difference, N1<N2<N3<1.

10. A multi-environment calibration method based on an intelligent gas inspection drone, applicable to a multi-environment calibration system based on an intelligent gas inspection drone as claimed in any one of claims 1 to 9, characterized in that: include: Acquire historical detection data of the drone, and clean up the historical detection data; Establishing an environmental detection model for the inspection drone based on the historical detection data after data cleaning; Obtaining environmental information and gas leakage detection amount in any of the historical detection data, substituting the environmental information and gas leakage detection amount into the environmental detection model, comparing the preset gas leakage amount output by the environmental detection model with the gas leakage detection amount, and determining whether to modify the environmental detection model according to the comparison result, wherein: When the preset gas leakage amount is inconsistent with the gas leakage detection amount, determining to iteratively correct the environment detection model; Obtaining the amount of gas leakage detected by the drone in the gas leakage area; The real-time environmental information of the gas leakage area is collected, and according to the real-time environmental information of the gas leakage area, it is determined whether to calibrate the gas leakage amount.

Images