Method and system for detecting fire hydrant

Abstract

The application relates to the technical field of fire-fighting pipeline detection, and discloses a detection method and system for a fire-fighting pipeline, which comprises the following steps: collecting pipeline inner wall reflection data through a mobile detection device, extracting corrosion feature vectors and wall thickness change feature vectors and fusing the feature vectors to generate comprehensive feature vectors; when an abnormal index in the comprehensive feature vectors is greater than a preset index threshold, marking a corresponding pipe section as a defective pipe section; determining a defect type of the defective pipe section according to the comprehensive feature vectors and a defect type historical probability distribution model; acquiring coordinate data of the defective pipe section, combining the defect type to calculate a health index of the defective pipe section; acquiring a historical health index change rule of the defective pipe section, and combining the health index to generate a state evaluation report of the defective pipe section. The problems that pipeline detection relies on manual work, is low in efficiency and is difficult to quantitatively evaluate the health state of the pipeline are solved, and accurate identification of defects of the fire-fighting pipeline and quantitative evaluation of the health state of the fire-fighting pipeline are realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of fire-fighting pipeline detection, and in particular to a detection method and system for a fire-fighting pipeline. BACKGROUND

[0002] As a core infrastructure for building life safety guarantee, the operation state of a fire-fighting pipeline system is directly related to the effectiveness of fire emergency response and the safety of personnel life and property. With the acceleration of urbanization and the continuous improvement of building complexity, the scale of the fire-fighting pipeline network is increasingly large, and accurate monitoring of its health state has become a key link in fire safety management.

[0003] When detecting a fire-fighting pipeline, manual inspection or the use of fixed sensors is usually used for detection. However, the internal space of a fire-fighting pipeline is narrow, and manual detection cannot penetrate into narrow or hidden pipeline areas. In addition, when using fixed sensors, the detection coverage is limited, and the comprehensive health status of the pipeline cannot be accurately judged. In particular, when the pipeline has multiple potential problems such as corrosion, blockage, and wall thickness change, single-dimensional sensor information often leads to misjudgment or missed detection.

[0004] Therefore, how to comprehensively detect narrow and complex fire-fighting pipelines and fuse multi-dimensional detection data for analysis to generate an accurate and reliable pipeline health assessment report is a problem that needs to be solved in fire-fighting pipeline detection. SUMMARY

[0005] The embodiments of the present application provide a detection method and system for a fire-fighting pipeline, which solves the problem of relying on manual detection, low efficiency, and difficulty in quantitatively evaluating the health status of the pipeline during pipeline detection, and realizes accurate identification of defects and quantitative evaluation of the health status of the fire-fighting pipeline.

[0006] The embodiments of the present application provide a detection method for a fire-fighting pipeline, which comprises:

[0007] The mobile detection device collects the pipeline inner wall reflection data and extracts the corrosion feature vector and the wall thickness change feature vector of the pipeline inner wall reflection data;

[0008] The corrosion feature vector and the wall thickness change feature vector are fused to generate a comprehensive feature vector;

[0009] If an abnormal index of the comprehensive feature vector is detected, and the abnormal index is greater than a preset index threshold, a pipe section corresponding to the abnormal index is determined as a defective pipe section;

[0010] The initial probability distribution data of the defect type of the defective pipe section is calculated according to the comprehensive feature vector, and the defect type of the defective pipe section is determined in combination with a historical probability distribution model of the defect type.

[0011] obtaining coordinate data of the defective pipe section, and calculating a health index of the defective pipe section according to the coordinate data and the defect type;

[0012] obtaining a historical health index change rule of the defective pipe section, and generating a state evaluation report of the defective pipe section in combination with the health index.

[0013] Optionally, the step of collecting the pipeline inner wall reflection data by the mobile detection device, and extracting the corrosion feature vector and the wall thickness change feature vector of the pipeline inner wall reflection data comprises:

[0014] collecting spectrum reflection data and wall thickness sound wave reflection data of the pipeline inner wall by the mobile detection device;

[0015] if the infrared wave band intensity in the spectrum reflection data is greater than a preset infrared wave threshold value, and the ultrasonic echo time difference of the wall thickness sound wave reflection data is greater than a preset standard time difference, marking the pipeline inner wall as a defective pipeline;

[0016] extracting the corrosion feature vector and the wall thickness change feature vector of the defective pipeline.

[0017] Optionally, the step of fusing the corrosion feature vector and the wall thickness change feature vector to generate a comprehensive feature vector comprises:

[0018] obtaining an accuracy level value of a sensor in the mobile detection device, and adjusting a weight value of the sensor according to the accuracy level value to generate a weight parameter;

[0019] fusing the corrosion feature vector and the wall thickness change feature vector in combination with the weight parameter to generate a comprehensive feature vector corresponding to a pipeline risk area.

[0020] Optionally, the step of calculating initial probability distribution data of a defect type of the defective pipe section according to the comprehensive feature vector, and determining the defect type of the defective pipe section in combination with a defect type historical probability distribution model comprises:

[0021] generating a probability distribution model of a corrosion defect, a crack defect and a blockage defect of a pipeline based on the comprehensive feature vector, and obtaining initial probability distribution data;

[0022] obtaining the defect type historical probability distribution model, and calculating posterior probability values of the corrosion defect, the crack defect and the blockage defect in combination with the initial probability distribution data;

[0023] comparing the posterior probability values with a defect type preset threshold value, and determining the defect type according to a comparison result.

[0024] Optionally, the step of acquiring the coordinate data of the defective pipe section, and calculating the health index of the defective pipe section according to the coordinate data and the defect type comprises:

[0025] acquiring the coordinate data, and fusing the coordinate data with the defect type to generate a defect type data set containing defect type identification and the coordinate data;

[0026] calculating the defect weight and defect severity of the defective pipe section according to the defect type data set, to obtain the health index.

[0027] Optionally, the step of acquiring the historical health index change rule of the defective pipe section, and generating a state evaluation report of the defective pipe section in combination with the health index comprises:

[0028] acquiring the historical health index change rule, and generating a health index data set containing health index time series and the coordinate data in combination with the coordinate data;

[0029] generating a health index prediction value of the defective pipe section according to the health index data set and the health index, to obtain a prediction trend data set;

[0030] generating the state evaluation report according to the prediction trend data set, the coordinate data, the health index and the defect type.

[0031] Optionally, after the step of acquiring the historical health index change rule of the defective pipe section, and generating a state evaluation report of the defective pipe section in combination with the health index, the method further comprises:

[0032] acquiring the defect type and the health index of the pipe section in the state evaluation report, determining the risk level of the pipe section, to obtain risk classification data;

[0033] if the risk level of a to-be-maintained defect point in the risk classification data exceeds a preset risk threshold, generating a maintenance suggestion of the to-be-maintained defect point in combination with the prediction trend data set, to obtain maintenance planning information;

[0034] updating the maintenance planning information to the state evaluation report.

[0035] In addition, to achieve the above-mentioned purpose, the embodiment of the present application further provides a detection system for a fire-fighting pipeline, the system comprising:

[0036] a data acquisition module, configured to acquire pipeline inner wall reflection data and coordinate data of a pipe section;

[0037] a defect detection module, configured to determine whether the pipe section has defects according to the pipeline inner wall reflection data;

[0038] a defect type identification module configured to determine a defect type of the pipe section according to the comprehensive feature vector and a historical defect probability model;

[0039] a health index calculation and prediction module configured to output a health index of the pipe section according to the defect type and the coordinate data, and generate a prediction trend dataset in combination with a historical health index change rule;

[0040] a state evaluation module configured to generate the state evaluation report according to the prediction trend dataset, the coordinate data, the health index and the defect type.

[0041] In addition, to achieve the above object, the embodiment of the present application further provides a terminal device, comprising a memory, a processor and a detection program for a fire-fighting pipeline stored in the memory and executable on the processor, and the processor executes the detection program for the fire-fighting pipeline to realize the method as described above.

[0042] In addition, to achieve the above object, the embodiment of the present application further provides a computer readable storage medium, wherein the computer readable storage medium stores a detection program for a fire-fighting pipeline, and the detection program for the fire-fighting pipeline is executed by a processor to realize the method as described above.

[0043] The one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0044] (1) The present application scans the fire-fighting pipeline by the mobile detection device, captures the corrosion and wall thickness change characteristics in the pipeline, and provides a comprehensive data basis for subsequent analysis.

[0045] (2) The present application fuses the spectral reflectance data and the wall thickness acoustic wave reflection data collected by the multiple sensors, eliminates the error of a single sensor, generates a feature vector that can comprehensively reflect the health state of the pipeline, and improves the reliability of abnormal detection.

[0046] (3) The present application realizes automatic determination of the defective pipe section based on a quantitative threshold value, matches with historical data, determines the defect type of the defective pipe section, avoids subjectivity of manual judgment, and improves detection efficiency.

[0047] (4) The present application generates a quantifiable health index through a coordinate correlation and defect weighting algorithm, and realizes intuitive and visual presentation of the pipeline risk.

[0048] (5) The present application fuses the current pipeline health index with the historical trend, predicts the state change trend of the pipeline and generates a state evaluation report, which can help the management personnel to maintain the risk pipeline in advance, and ensure the safety and stability of the pipeline operation. BRIEF DESCRIPTION OF DRAWINGS

[0049] Figure 1 This is a flow chart of Example 1 of the detection method for fire protection pipes of the present application;

[0050] Figure 2 This is a flow chart of Example 2 of the detection method for fire protection pipes of the present application;

[0051] Figure 3 This is a schematic diagram of the terminal structure of the hardware operating environment involved in an embodiment of the present application. DETAILED DESCRIPTION

[0052] To address the difficulty in quantifying and assessing the health status of fire protection pipelines, this application uses a mobile detection device to collect spectral and ultrasonic data from the pipeline's inner wall. Feature extraction and fusion generate a comprehensive feature vector, which, combined with a Bayesian probability model, enables intelligent defect identification and classification. Furthermore, through health index calculation and trend analysis, the pipeline's future health status is predicted and a status assessment report is generated. This approach enables intelligent detection, assessment, and early warning of pipeline inner wall defects, providing a scientific basis for pipeline maintenance and effectively improving the safety and reliability of pipeline operations.

[0053] To better understand the above technical solutions, exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments described herein. Instead, these embodiments are provided to enable a more thorough understanding of the present application and to fully convey the scope of the present application to those skilled in the art.

[0054] In order to better understand the above technical solution, the above technical solution will be described in detail below with reference to the accompanying drawings and specific implementation methods.

[0055] Example 1

[0056] In this embodiment, a detection method for fire protection pipelines is provided.

[0057] Reference Figure 1 The fire protection pipeline detection method of this embodiment includes the following steps:

[0058] Step S100: collecting pipeline inner wall reflection data by a mobile detection device, and extracting the corrosion feature vector and the wall thickness change feature vector of the pipeline inner wall reflection data;

[0059] In the embodiment, the movement detection device is composed of a multispectral imaging sensor and an ultrasonic sensor, and full-segment scanning is performed in the pipeline space to obtain spectral reflection data and wall thickness acoustic reflection data of the inner wall of the pipeline. The corrosion feature vector includes a corrosion area proportion, a corrosion depth distribution, a corrosion morphology feature, a corrosion product spectral feature, and a surface roughness. The wall thickness change feature vector includes a residual wall thickness value, a wall thickness thinning rate, an unevenness index, a defect area, and an axial distribution feature.

[0060] As an optional implementation, full-segment scanning is performed on the inner wall of the pipeline by the multispectral imaging sensor to obtain spectral reflection data of the inner wall of the pipeline, infrared band intensity information is extracted, and the information is stored in a pre-established database to obtain preliminary spectral abnormal region distribution information. Full-segment scanning is performed on the inner wall of the pipeline by the ultrasonic sensor to obtain wall thickness data, and an ultrasonic echo time difference is recorded. If the echo time difference is greater than a preset echo time standard value percentage, the area is marked as a potential defect area, and preliminary wall thickness abnormal region information is determined. According to the spectral abnormal region distribution information and the wall thickness abnormal region information, data fusion processing is performed, and the overlapping area is marked as a defective pipeline. The way of determining the defective pipeline according to the spectral abnormal region and the wall thickness abnormal region can improve the accuracy of defect determination and reduce the risk of misjudgment.

[0061] For example, the multispectral imaging sensor irradiates the inner wall of the pipeline with light of different wavebands, captures the characteristics of the reflected spectrum, especially the intensity information of the infrared band, to determine material changes or surface abnormalities. Assuming that in the detection of a 0.5-meter-diameter industrial pipeline, the sensor scanning finds that the infrared band intensity value of a certain area reaches 1.2 times the preset threshold, indicating that there may be surface roughness changes or material deposition caused by corrosion, and this area is marked as a spectral abnormal region and stored in the database. The ultrasonic sensor determines wall thickness changes by emitting ultrasonic waves and measuring the echo time difference. Assuming that in the same pipeline, the echo time difference of a certain area reaches 1.3 times the preset echo time standard value, which exceeds the preset echo time standard value percentage, indicating that the wall thickness may be thinned due to corrosion, and the area is marked as a defective pipeline. This non-contact method of quickly locating potential problem areas can directly reflect the structural integrity of the pipeline and provide physical evidence for defect determination.

[0062] As another optional implementation, after the defective pipeline is determined, the corresponding coordinate data can be recorded, and the defect location data is associated with the spatial coordinates of the inner wall of the pipeline to provide accurate positioning support for subsequent maintenance.

[0063] Exemplarily, assuming that the pipeline is 100 meters long, the defect is located at the 25th meter, and the module records that the defect is accurately mapped into the spatial coordinate system and a defect distribution map with a position mark is generated and stored in the database. Assuming that 3 defect areas are found in the above detection, respectively located at the 25th, 50th and 75th meters, the distribution map directly displays the defect positions and the corresponding corrosion feature vectors and wall thickness change feature vectors, which facilitates the management personnel to quickly understand the pipeline health status.

[0064] As yet another optional implementation, after the defective pipeline is marked, the corresponding corrosion feature vector and wall thickness change feature vector can be extracted, and different types of detection data can be feature-extracted through a convolutional neural network algorithm.

[0065] Exemplarily, when extracting the corrosion feature, a natural gas pipeline with a diameter of 0.6 meters is subjected to multi-spectral scanning, and it is detected that the infrared band intensity of a local area abnormally increases by 1.5 times the preset band threshold. Through spectral analysis, it is identified that the area has oxide deposition or surface roughness change, and the peak intensity is 80% higher than that of the normal area. The image processing algorithm calculates that the area of the abnormal area is 15.6 square centimeters, accounting for about 8.2% of the total area of the pipeline inner wall. At the same time, the three-dimensional topography reconstruction shows that the maximum corrosion depth of the area is 0.75 millimeters, and the surface roughness Ra value is 12.6 micrometers. As for the extraction of the wall thickness change feature, the ultrasonic sensor measures the wall thickness every 10 centimeters along the pipeline axis, and detects that the ultrasonic echo time difference of the defective pipeline section is 69.6 microseconds, which is 20% higher than the standard value of 58 microseconds. According to the sound speed conversion formula, it is calculated that the actual wall thickness of the area is 5.0 millimeters, which is 16.7% thinner than the standard wall thickness of 6.0 millimeters. The continuous measurement value shows that the abnormal area extends about 50 centimeters along the pipeline axis, showing a distribution feature of thin in the middle and thick at both ends.

[0066] Step S200: fuse the corrosion feature vector and the wall thickness change feature vector to generate a comprehensive feature vector;

[0067] In this embodiment, after the corrosion feature vector and the wall thickness change feature vector are extracted, the initial data such as spectral reflection data and wall thickness data can be quantitatively processed. The initial data can be quantified according to dimensions such as data stability, environmental adaptability and historical consistency, and the accuracy level value of each sensor can be determined according to the quantification result. The corrosion feature vector and the wall thickness change feature vector are weighted and fused to generate a comprehensive feature vector.

[0068] As an optional implementation, the precision grade values of each sensor are obtained by performing a weighted fusion processing according to the corrosion feature vector F1 and the wall thickness change feature vector F2, and the weight values of the sensors are adjusted according to the precision grade values to generate the weight parameters W1 and W2. The corrosion feature vector and the wall thickness change feature vector are fused by a calculation formula F = W1*F1 + W2*F2 to generate a comprehensive feature vector F.

[0069] Exemplarily, for a 0.6-meter-long natural gas pipeline, the multispectral imaging sensor collects visible light and infrared band data, and evaluation of the data shows that the data fluctuation is less than 5%, so the multispectral imaging sensor is given a higher precision grade value, such as 0.9. The echo data collected by the ultrasonic sensor fluctuates greatly due to environmental noise interference, and the precision grade value may be 0.7. The precision grade value of the multispectral imaging sensor is greater than that of the ultrasonic sensor, so the weight value of the multispectral data is increased, for example, from 0.5 to 0.6, while the weight value of the ultrasonic data is correspondingly reduced to 0.4, and the comprehensive feature vector is 0.6F1 + 0.4F 2。

[0070] Step S300: If the comprehensive feature vector is detected to have an abnormal index, and the abnormal index is greater than a preset index threshold, it is determined that the pipe section corresponding to the abnormal index is a defective pipe section.

[0071] In this embodiment, the abnormal index refers to an index related to the defect type, such as the corrosion comprehensive index, the crack risk value, or the flow resistance rate. When it is detected that a certain abnormal index in the comprehensive feature vector exceeds the corresponding preset index threshold, it is determined that the pipe section corresponding to the abnormal index is a defective pipe section.

[0072] As an optional implementation, each dimension in the comprehensive feature vector corresponds to a specific physical feature, such as corrosion depth, wall thickness reduction rate, and spectral abnormal intensity. These features are converted into standardized risk indexes through a pre-calibrated mathematical model. The risk indexes are compared with the dynamically adjusted index threshold. When one or more risk indexes in the comprehensive feature vector of a certain pipe section exceed the preset index threshold, a multi-level verification mechanism is started. The spatiotemporal continuity of the abnormal features is checked, such as whether the corrosion area presents a gradient change at adjacent detection points. Cross-sensor evidence verification is performed, such as the simultaneous existence of infrared spectral abnormalities and ultrasonic wall thickness reduction.

[0073] Exemplarily, in a 0.6-meter-diameter natural gas pipeline, the fusion data of a certain region show that the infrared band intensity exceeds the threshold, and the wall thickness change rate reaches 25%, the abnormal index exceeds the preset index threshold, and it is determined that the pipe section corresponding to the region is a defective pipe section. This cross-verification method of verifying the pipeline state according to infrared spectral abnormalities and ultrasonic wall thickness changes can effectively eliminate most transient interference false alarms.

[0074] It should be noted that the preset index threshold is not a fixed value, but a benchmark value dynamically calculated by an aging model based on pipe material characteristics, service life and environmental factors. For example, for a carbon steel pipe used for 10 years, its corrosion risk threshold will be increased by 15%-20% compared with a new pipe to adapt to the natural attenuation of material performance.

[0075] Optionally, after determining the defective pipe section, the coordinate position of the defective pipe can be recorded, the defect distribution information is associated with the spatial coordinates of the pipe, assuming that the total length of the pipe is 80 meters, the defect distribution information shows that the 30th and 60th meters are defective pipe sections, the positions are recorded and a distribution map with position marks is generated, and stored in the database. The management personnel can quickly locate the defect position according to the distribution map.

[0076] Step S400: calculating defect type initial probability distribution data of the defective pipe section according to the comprehensive feature vector, and determining the defect type of the defective pipe section in combination with a defect type historical probability distribution model;

[0077] In this embodiment, the comprehensive feature vector can be subjected to defect type identification through a Bayesian classification algorithm, a probability distribution model of three types of defects of corrosion, crack and blockage is established, and the posterior probability of each type of defect is calculated. If the posterior probability of a certain type of defect exceeds a preset threshold of the defect type, the defect type corresponding to the pipe section is determined.

[0078] As an optional implementation, a probability distribution model of corrosion defects, crack defects and blockage defects is generated based on the comprehensive feature vector, initial probability distribution data is obtained, a historical probability distribution model of each defect type is acquired, and the posterior probability values of the corrosion defects, crack defects and blockage defects are calculated in combination with the initial probability distribution data. Comparing the posterior probability values with a preset threshold of the defect type can determine the specific defect type.

[0079] Exemplarily, for a natural gas pipeline with a diameter of 0.8 meters, the comprehensive feature data includes surface corrosion features detected by a multi-spectral imaging sensor and wall thickness anomaly information captured by an ultrasonic sensor. According to historical data, a probability distribution model is established to analyze the distribution of surface corrosion features and wall thickness anomaly information in different defect types, and initial probability distribution data is generated. For example, the initial probability distribution shows that the probability of corrosion defects is 0.6, the probability of crack defects is 0.3, and the probability of blockage defects is 0.1, reflecting that the current data is more inclined to corrosion defects. Then, the historical probability distribution model of the defect type is called again, and the prior probability distribution data of the three types of defects is corrosion 0.5, crack 0.3, and blockage 0.2. According to the initial probability distribution data and the prior probability distribution data, the posterior probability values are calculated as corrosion defect 73.2%, crack defect 22.0%, and blockage defect 4.8%. If the preset threshold values of the defect types are corrosion threshold 65%, crack threshold 45%, and blockage threshold 35%, comparing the posterior probability values with the preset threshold values can determine that the defect type is a corrosion defect.

[0080] Optionally, after determining the defect type, a corresponding defect type identifier can be generated, and the defect type identifier is associated with the spatial coordinates of the pipeline to generate a defect location record. Assuming that the total length of the pipeline is 100 meters, it is found through analysis that corrosion defects are concentrated in the 40th to 45th segments, and a record containing the specific location is generated, which shows that the infrared band intensity is abnormal and the wall thickness reduction rate reaches 20% in this area, indicating that the corrosion is serious. Combining these information with the pipeline coordinate system, a visual distribution map is generated and stored in the database. This accurate positioning enables maintenance personnel to quickly lock the problem area and optimize the maintenance plan.

[0081] Step S500: Obtain coordinate data of the defect pipe segment, and calculate a health index of the defect pipe segment according to the coordinate data and the defect type;

[0082] In this embodiment, the database stores defect information of different positions of the pipeline, such as the corrosion degree or crack distribution of a certain segment of the pipeline, covering the specific state of each segment of the pipeline. Since adjacent defects can affect each other, for example, two corrosion points within an interval of 1 meter can form a synergistic effect, making the health index decrease at a speed 30%-50% faster than that of isolated defects, and defects at special positions such as welds and elbows need to be additionally weighted. These information need to be obtained through coordinate positioning. Therefore, the coordinate data is obtained, and the coordinate data is combined with the defect type to calculate the health index.

[0083] As an optional implementation, the coordinate data is obtained, the coordinate data is fused with the defect type to generate a defect type data set containing a defect type identifier and the coordinate data, and according to the defect type data set, a defect weight and a defect severity of the defect pipe segment are calculated to obtain the health index.

[0084] Exemplarily, the long-term cumulative damage of the corrosion defect is easy to cause the pipe wall to be perforated and leaked, the crack defect can cause sudden fracture, but generally has a local impact, and the blockage defect mainly affects the flow and has a low structural risk. Therefore, the defect weight value is adjusted according to the defect type, that is, the corrosion defect basic weight is 0.8, the crack defect basic weight is 0.7, and the blockage defect basic weight is 0.4. For example, a certain defect pipe section has both corrosion defects and crack defects. According to the coordinate data, the corrosion defect is located underground in the commercial area, and the weight factor is 0.7. Therefore, the corrosion defect weight is 0.8*1.7=0.56. The crack defect is also located underground, and the weight factor is 0.9. Moreover, there is a corrosion defect within 1 meter of the crack defect, and the weight is increased by 15%. Therefore, the crack defect weight is 0.7*0.9*1.15=0.72. The defect severity is determined based on the detection data and the coordinate data. The length of the crack defect is 15 cm, corresponding to a score of 12, and the depth is 2 mm, corresponding to a score of 20. According to the coordinate data, the position is near the weld, and the crack severity is calculated to be (12+20)*2=64. The area of the corrosion defect is 8 cm2, the depth is 1.5 mm, and the position is in a straight pipe section. The corrosion severity is calculated to be (8+7.5)*1=15.5. According to the defect weight and the defect severity, the health index is calculated to be 0.56*64+0.72*15.5=47.

[0085] Optionally, the health index determines the risk level of the fire-fighting pipeline. The lower the health index value, the greater the risk, and the health index threshold values for fire-fighting pipelines of different materials are different. For ordinary fire-fighting pipes, the health index threshold value can be set to 60, the health index threshold value for high-position chemical area pipelines is 30, and the health index threshold value for underground main pipe networks is 40. When the health index is less than the preset health index threshold value, it indicates that the pipe section is in a risk area and needs to be repaired.

[0086] Step S600: Obtain the historical health index change rule of the defect pipe section, and generate a state evaluation report of the defect pipe section in combination with the health index.

[0087] In this embodiment, after the health index of each pipe section is calculated, the historical change rule of the health index can be obtained, and a state evaluation report of the defect pipe section is generated in combination with the health index. The state evaluation report content includes defect position, defect type, severity and maintenance suggestion.

[0088] As an optional implementation manner, the historical health index change rule and the corresponding coordinate data of each pipe section are obtained from the database, and the two are fused to generate a health index data set. The health index data set includes a health index time sequence and corresponding coordinate data.

[0089] Exemplarily, a 300-meter-long pipeline, the database stores the health index records of each section of the pipeline in the past 12 months, such as the health index of the 100-meter section gradually decreases from 85 to 70 in the past 6 months. These data come from periodic detection equipment, combined with location information to form a preliminary data set, and these scattered historical health indexes are bound to specific locations to form a structured time series data set.

[0090] As another optional implementation, after generating the health index data set, the health index prediction value of the defective pipe section is generated in combination with the current health index to obtain the prediction trend data set.

[0091] Exemplarily, according to the time series data set, the historical decline rate of the health index is obtained, and then a time series analysis method is used to first perform data stationarity test, eliminate the trend through difference operation, and then establish a difference regression moving average model to predict the health index. To further improve the prediction accuracy, a spatial correlation factor can also be introduced. Assuming that there are two corrosion defect pipe sections within a 3-meter range around the pipe section, their health indexes are 54 and 61 respectively, and by establishing a distance-based weight matrix, the spatial influence coefficient is calculated to be 1.18, and the corrected prediction value is adjusted to be 56-60. At the same time, considering that the soil resistivity in this area is continuously decreasing, an environmental corrosion correction coefficient of 0.9 is added, and the final prediction result is updated to be that the health index will reach the risk threshold range of 50-54 after 6 months. This prediction method that integrates time and space characteristics improves the prediction accuracy.

[0092] As yet another optional implementation, the prediction results of each defective pipe section are integrated to obtain the prediction trend data set, and according to the prediction trend data set, coordinate data, health index and defect type, a state evaluation report can be generated.

[0093] Exemplarily, the predicted trend data set is associated with the coordinate data, sorted according to the health index decline amplitude, the maintenance priority list is determined, and the maintenance priority list can also be classified and stored according to the defect type, and a state evaluation report is generated. For example, a fire pipe detection shows that the detection position is located in a certain underground parking lot B area, the current health index is 65, the health index threshold is 50, and there is a problem of bottom corrosion depth of 1.8 mm. The prediction analysis shows that if no intervention measures are taken, the health index will decrease to 58 after 3 months, and may drop below the safety threshold to 45-49 after 6 months, and the leakage risk will rise to 32%. The evaluation found that there are 2 associated corrosion points within a range of 2 meters, which may accelerate the overall degradation. Based on the above analysis, the report suggests that the epoxy resin lining repair be implemented within 2 months, and the status of the adjacent 3-meter pipe section be checked synchronously. All prediction data is calibrated by confidence, with an error controlled within ±3%, and the evaluation results are automatically updated every quarter to ensure the timeliness of the maintenance scheme. This data-driven evaluation method has been proven in practice to reduce the sudden failure rate by more than 30% and optimize the efficiency of maintenance resource allocation.

[0094] Optionally, when the predicted trend data set is associated with the coordinate data, the pipe segment surrounding environment information can also be associated with the predicted trend data set according to the coordinate data, for example, whether it is close to a residential area. If it is close to a residential area, the priority of maintenance can be increased.

[0095] In this embodiment, a multispectral and ultrasonic composite detection technology is adopted, combined with a pipe feature database, to realize automatic identification of defects such as corrosion and cracks, with a detection accuracy of millimeter level. Meanwhile, by establishing a pipe health index dynamic calculation model, the risk evaluation results generated by comprehensively considering the defect type, spatial distribution and environmental factors are consistent with the actual working conditions with a coincidence degree of more than 90%, and potential failures can be warned 3-6 months in advance. The automatically generated evaluation report contains present situation analysis, trend prediction and maintenance suggestion, supporting precise scheduling of maintenance resources, which can greatly reduce operation and maintenance costs, shorten fault response time, and greatly improve the safety and reliability of the fire fighting system.

[0096] Embodiment Two

[0097] Based on Embodiment One, another embodiment of the present application is proposed, referring to Figure 2 After the step of obtaining the historical health index variation law of the defect pipe segment and generating a state evaluation report of the defect pipe segment in combination with the health index, the following steps are included:

[0098] Step S700: Obtain the defect type and the health index of the pipe segment in the state evaluation report, determine the risk level of the pipe segment, and obtain risk classification data;

[0099] Step S800: If the risk level of the defect point to be maintained in the risk classification data exceeds a preset risk threshold, a maintenance suggestion for the defect point to be maintained is generated in combination with the prediction trend data set to obtain maintenance planning information;

[0100] Step S900: updating the maintenance plan information into the status assessment report.

[0101] In this embodiment, after obtaining the current health index data and predicted trend data for each pipeline segment from the database and performing data fusion processing to generate a preliminary dataset containing defect location, defect type, and current health index, a condition assessment report is generated. Based on the condition assessment report, the defect location is correlated with the three-dimensional coordinate data. By analyzing the defect type and current health index, the risk level of each defect point is determined, generating risk classification data. Based on this risk classification data and the predicted trend dataset, maintenance recommendations for the defect points to be maintained are generated, resulting in maintenance planning information. This maintenance planning information is then updated in the condition assessment report, resulting in the final pipeline status profile. This continuously updated pipeline status profile continuously calibrates the assessment model, improving prediction accuracy.

[0102] As an optional implementation method, after generating risk classification data, if the risk level of a defect point in the risk classification data exceeds the preset risk threshold, maintenance recommendations for the defect point are generated in combination with the predicted trend data and processing time requirements to obtain maintenance planning information.

[0103] For example, during the inspection of a fire protection pipeline, the assessment revealed a circumferential crack defect in section 5. The health index had dropped to 45, compared to the preset high-risk threshold of 50, and the risk level was marked as "urgent." Analysis of predictive trend data predicted that the health index of this section would drop to 38 within the next two months, and the crack length could increase by 15%. Based on the on-site construction conditions (a 2.5-meter buried depth, a main road above), and the availability of maintenance resources (epoxy resin repair requires 4 hours per meter, and pipe replacement requires 8 hours per meter), maintenance recommendations were automatically generated, prioritizing carbon fiber composite reinforcement, with completion within 14 days and a work window limited to 12:00 AM to 4:00 AM to minimize traffic impact. Preventive coating maintenance was also recommended for the adjacent 3-meter section with a health index of 58. This planning information was automatically updated to the pipeline status file.

[0104] As another optional implementation, the defect location, three-dimensional coordinates, risk level, severity, maintenance recommendations, and health status data are integrated and processed through maintenance planning information to determine the final pipeline status profile.

[0105] Exemplarily, after the comprehensive detection of the fire-fighting pipeline of a factory is completed, it is found that the pipe section 102 has a serious corrosion defect. Through a series of data fusion, a complete pipeline state file is generated: the three-dimensional coordinates of the pipe section (X: 287.45, Y: 156.32, Z: -2.8), the current health index is only 38 (the preset risk threshold is 50), the risk level is marked as "critical", the corrosion area reaches 35% of the pipe wall and the maximum depth is 2.3 mm. Based on the prediction model, it is shown that if not handled, a perforation leakage may occur within 2 months, combined with the production plan of the factory, the shutdown and maintenance window next week and the corrosion characteristics, a customized maintenance scheme is generated: using a high-molecular composite material to wrap and reinforce on site, closing No. 1 operation channel for 8 hours, and simultaneously replacing the adjacent 2-meter aged pipe section. The file is associated with the three-dimensional digital twin model of the factory in real time, and the high-risk area is marked with a red flashing warning, and is automatically pushed to the maintenance supervisor's mobile terminal, and the emergency disposal plan attached contains a temporary water supply scheme for the affected fire hydrant. After implementation verification, the digital file makes the actual maintenance time 20% shorter than expected, and through the construction acceptance module integrated in the file, the comparison of detection data before and after repair is recorded, forming a traceable closed-loop management record, providing data support for subsequent pipe network reconstruction.

[0106] In the embodiment, the risk pipe section is automatically identified based on the risk classification data, and a maintenance scheme is generated. The maintenance scheme is updated to the state evaluation report, so that the management personnel allocate maintenance resources according to the state evaluation report, and the operation and maintenance cost is greatly reduced.

[0107] Embodiment three

[0108] In the embodiment of the present application, a detection device for a fire-fighting pipeline is provided.

[0109] Reference Figure 3 , Figure 3 The terminal structure diagram of the hardware running environment involved in the embodiment of the present application.

[0110] As Figure 3 shown, the control terminal can include a processor 1001, such as a CPU, a network interface 1003, a memory 1004, and a communication bus 1002. The communication bus 1002 is used to realize the connection and communication between these components. The network interface 1003 can optionally include a standard wired interface, a wireless interface (such as a WI-FI interface). The memory 1004 can be a high-speed RAM memory or a stable memory (non-volatile memory), such as a magnetic disk memory. The memory 1004 can optionally also be a storage device independent of the aforementioned processor 1001.

[0111] Those skilled in the art can understand, Figure 3The terminal structure shown in the figures does not constitute a limitation on the terminal, and can include more or fewer components than shown, or combine certain components, or arrange different components.

[0112] As shown in Figure 3 The memory 1004 as a computer storage medium can include an operating system, a network communication module, and a detection program for fire-fighting pipelines.

[0113] In Figure 3 In the hardware structure of the detection device for fire-fighting pipelines, the processor 1001 can call the detection program for fire-fighting pipelines stored in the memory 1004 and perform the following operations:

[0114] Collect the pipe inner wall reflection data by the mobile detection device, and extract the corrosion feature vector and the wall thickness change feature vector of the pipe inner wall reflection data;

[0115] Fuse the corrosion feature vector and the wall thickness change feature vector to generate a comprehensive feature vector;

[0116] If an abnormal index exists in the comprehensive feature vector, and the abnormal index is greater than a preset index threshold, determine that the pipe section corresponding to the abnormal index is a defective pipe section;

[0117] Calculate the initial probability distribution data of the defect type of the defective pipe section according to the comprehensive feature vector, and determine the defect type of the defective pipe section in combination with a historical probability distribution model of the defect type;

[0118] Obtain the coordinate data of the defective pipe section, and calculate the health index of the defective pipe section according to the coordinate data and the defect type;

[0119] Obtain the historical health index change rule of the defective pipe section, and generate a state evaluation report of the defective pipe section in combination with the health index.

[0120] Optionally, the processor 1001 can call the detection program for fire-fighting pipelines stored in the memory 1004, and further perform the following operations:

[0121] Collect the spectral reflection data and the wall thickness sound wave reflection data of the pipe inner wall by the mobile detection device;

[0122] If the infrared waveband intensity in the spectral reflection data is greater than a preset infrared fluctuation threshold, and the ultrasonic echo time difference of the wall thickness sound wave reflection data is greater than a preset standard time difference, mark the pipe inner wall as a defective pipe;

[0123] Extract the corrosion feature vector and the wall thickness change feature vector of the defective pipe.

[0124] Optionally, the processor 1001 can call the detection program for the fire-fighting pipeline stored in the memory 1004, and further perform the following operations:

[0125] Obtain the precision level value of the sensor in the movement detection device, and adjust the weight value of the sensor according to the precision level value to generate a weight parameter;

[0126] Combine the corrosion feature vector and the wall thickness change feature vector based on the weight parameter to generate a comprehensive feature vector corresponding to the pipeline risk area.

[0127] Optionally, the processor 1001 can call the detection program for the fire-fighting pipeline stored in the memory 1004, and further perform the following operations:

[0128] Generate a probability distribution model of the corrosion defect, the crack defect and the blockage defect of the pipeline based on the comprehensive feature vector, and obtain initial probability distribution data;

[0129] Obtain the defect type historical probability distribution model, and calculate the posterior probability value of the corrosion defect, the crack defect and the blockage defect based on the initial probability distribution data;

[0130] Compare the posterior probability value with a defect type preset threshold value, and determine the defect type according to the comparison result.

[0131] Optionally, the processor 1001 can call the detection program for the fire-fighting pipeline stored in the memory 1004, and further perform the following operations:

[0132] Obtain the coordinate data, and fuse the coordinate data with the defect type to generate a defect type data set containing defect type identification and the coordinate data;

[0133] According to the defect type data set, calculate the defect weight and the defect severity of the defect pipe segment to obtain the health index.

[0134] Optionally, the processor 1001 can call the detection program for the fire-fighting pipeline stored in the memory 1004, and further perform the following operations:

[0135] Obtain the historical health index change rule, and generate a health index data set containing a health index time sequence and the coordinate data based on the coordinate data;

[0136] Generate a health index prediction value of the defect pipe segment according to the health index data set and the health index to obtain a prediction trend data set;

[0137] generate the state evaluation report according to the prediction trend data set, the coordinate data, the health index and the defect type.

[0138] Optionally, the processor 1001 can call the detection program for the fire-fighting pipeline stored in the memory 1004, and further perform the following operations:

[0139] In the state evaluation report, the defect type and the health index of the pipe section are acquired, the risk level of the pipe section is determined, and risk classification data is obtained;

[0140] If the risk level of the defect point to be maintained in the risk classification data exceeds a preset risk threshold, a maintenance suggestion for the defect point to be maintained is generated in combination with the prediction trend data set, and maintenance planning information is obtained;

[0141] The maintenance planning information is updated into the state evaluation report.

[0142] In addition, to achieve the above-mentioned purpose, an embodiment of the present application further provides a system for detection of a fire-fighting pipeline, comprising:

[0143] A data acquisition module is configured to acquire pipe wall reflection data and coordinate data of a pipe section;

[0144] A defect detection module is configured to determine whether the pipe section has defects according to the pipe wall reflection data;

[0145] A defect type identification module is configured to determine the defect type of the pipe section according to the comprehensive feature vector and a historical defect probability model;

[0146] A health index calculation and prediction module is configured to output the health index of the pipe section according to the defect type and the coordinate data, and generate a prediction trend data set in combination with a historical health index change rule;

[0147] A state evaluation module is configured to generate the state evaluation report according to the prediction trend data set, the coordinate data, the health index and the defect type.

[0148] In addition, to achieve the above-mentioned purpose, an embodiment of the present application further provides an apparatus comprising a memory, a processor and a detection program for the fire-fighting pipeline stored in the memory and executable on the processor, wherein the processor executes the detection program for the fire-fighting pipeline to implement the detection method for the fire-fighting pipeline as described above.

[0149] In addition, to achieve the above-mentioned purpose, an embodiment of the present application further provides a computer readable storage medium having a detection program for the fire-fighting pipeline stored thereon, wherein the detection program for the fire-fighting pipeline is executed by a processor to implement the detection method for the fire-fighting pipeline as described above.

[0150] Those skilled in the art will appreciate that embodiments of the present application can be readily used as a method, a system or a computer program product. Accordingly, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application can take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage devices, etc.) embodying computer readable program code.

[0151] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flowcharts and / or blocks in the flowcharts and / or blocks can represent code, circuits, processes, procedures, modules, functions, and / or Figure 1 an apparatus configured to perform the functions specified in the flowchart block(s) or block(s).

[0152] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the flowchart block(s) or block(s). Figure 1 one or more flowcharts and / or blocks in the flowcharts and / or blocks can represent code, circuits, processes, procedures, modules, functions, and / or Figure 1 an apparatus configured to perform the functions specified in the flowchart block(s) or block(s).

[0153] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flowcharts and / or blocks in the flowcharts and / or blocks can represent code, circuits, processes, procedures, modules, functions, and / or Figure 1 an apparatus configured to perform the functions specified in the flowchart block(s) or block(s).

[0154] It is to be noticed that the singular form "a", "an", and "the" include plural references unless the context clearly dictates otherwise. As used herein, the term "comprising" or "comprises" does not exclude other steps of the method identified by this method steps as disclosed herein other steps of the method identified by this method steps as disclosed herein as well as any additional optional steps, features, compositions and / or ingredients defined herein. As used herein, the term "comprising" or "comprises" does not exclude other steps of the method identified by this method steps as disclosed herein other steps of the method identified by this method steps as disclosed herein as well as any additional optional steps, features, compositions and / or ingredients defined herein. As used herein, the term "consisting of" or "consists of" excludes any additional step, feature, composition, ingredient or ingredient of the method identified by this method steps as disclosed herein. As used herein, the term "consisting essentially of" or "consists essentially of" excludes any additional step, feature, composition, ingredient or ingredient of the method identified by this method steps as disclosed herein.

[0155] Although the preferred embodiments of the application have been described, those skilled in the art will recognize that many modifications and variations of the preferred embodiments could be made without departing from the spirit or scope of the application. Accordingly, it is intended that there be included within the scope of the application, all such modifications and variations as can be reasonably inferred from the above description.

[0156] Obviously, numerous modifications and variations of the present application are possible in light of the above teachings. It is therefore to be understood that within the scope of the appended claims and their equivalents, the application can be practiced otherwise than as specifically described.

Claims

1. A method for detecting fire protection pipes, characterized in that: The method comprises: collecting pipeline inner wall reflection data by a mobile detection device, and extracting a corrosion feature vector and a wall thickness change feature vector of the pipeline inner wall reflection data; fusing the corrosion feature vector and the wall thickness change feature vector to generate a comprehensive feature vector; If it is detected that the comprehensive feature vector has an abnormal indicator, and the abnormal indicator is greater than a preset indicator threshold, the pipe section corresponding to the abnormal indicator is determined to be a defective pipe section; Calculating initial probability distribution data of the defect type of the defective pipe section based on the comprehensive feature vector, and determining the defect type of the defective pipe section in combination with a historical probability distribution model of the defect type; Acquiring coordinate data of the defective pipe section, and calculating a health index of the defective pipe section according to the coordinate data and the defect type; Obtaining the historical health index variation pattern of the defective pipe section and generating a status assessment report of the defective pipe section based on the health index, specifically including: Obtain the historical health index change pattern and corresponding coordinate data of each pipe segment from the database, and fuse the two to generate a health index dataset, which includes the health index time series and the corresponding coordinate data; The historical decline rate of the health index is obtained from the time series data set. Time series analysis is then used to first test the data for stationarity. After eliminating trends through differencing, a differential regression moving average model is established to predict the health index. A spatial correlation factor is introduced, and a distance-based weight matrix is ​​established to calculate the spatial influence coefficient, which is then adjusted to obtain a revised predicted value. Furthermore, if the soil resistivity in the pipe section continues to decrease, an environmental corrosion correction factor is added to update the final prediction of the health index. The final prediction results of each defective pipe section are integrated to obtain a prediction trend dataset. The prediction trend dataset is associated with the coordinate data and sorted by the decline in health index to determine the maintenance priority list. The maintenance priority list is also classified and stored according to the defect type to generate a condition assessment report. When associating the predicted trend dataset with the coordinate data, the surrounding environment information of the pipe section is associated with the predicted trend dataset based on the coordinate data. If the pipe section is close to a residential area, the maintenance priority is increased.

2. The detection method for fire protection pipes according to claim 1, characterized in that: The steps of collecting pipeline inner wall reflection data by a mobile detection device and extracting the corrosion feature vector and the wall thickness change feature vector of the pipeline inner wall reflection data include: The mobile detection device collects spectral reflection data and wall thickness acoustic wave reflection data of the inner wall of the pipeline; If the infrared band intensity in the spectral reflection data is greater than a preset infrared fluctuation threshold, and the ultrasonic echo time difference of the wall thickness acoustic wave reflection data is greater than a preset standard time difference, the inner wall of the pipeline is marked as a defective pipeline; The corrosion feature vector and the wall thickness variation feature vector of the defective pipe are extracted.

3. The detection method for fire protection pipes according to claim 1, characterized in that: The step of fusing the corrosion feature vector and the wall thickness change feature vector to generate a comprehensive feature vector includes: Obtaining an accuracy level value of a sensor in the motion detection device, and adjusting a weight value of the sensor according to the accuracy level value to generate a weight parameter; The corrosion feature vector and the wall thickness change feature vector are fused in combination with the weight parameter to generate a comprehensive feature vector corresponding to the pipeline risk area.

4. The detection method for fire protection pipes according to claim 1, characterized in that: The step of calculating the initial probability distribution data of the defect type of the defective pipe section based on the comprehensive feature vector and determining the defect type of the defective pipe section in combination with the defect type historical probability distribution model includes: Generate a probability distribution model of corrosion defects, crack defects and blockage defects of the pipeline based on the comprehensive feature vector, and obtain initial probability distribution data; Obtaining the defect type historical probability distribution model, and calculating the posterior probability values ​​of the corrosion defect, the crack defect, and the blockage defect in combination with the initial probability distribution data; The posterior probability value is compared with a preset threshold value of the defect type, and the defect type is determined according to the comparison result.

5. The detection method for fire protection pipes according to claim 1, characterized in that: The step of obtaining the coordinate data of the defective pipe section and calculating the health index of the defective pipe section according to the coordinate data and the defect type includes: Acquire the coordinate data, and fuse the coordinate data with the defect type to generate a defect type data set including a defect type identifier and the coordinate data; The defect weight and defect severity of the defective pipe section are calculated according to the defect type data set to obtain the health index.

6. The detection method for fire protection pipes according to claim 1, characterized in that: After the step of obtaining the historical health index variation pattern of the defective pipe section and generating a status assessment report of the defective pipe section in combination with the health index, the method includes: Obtain the defect type and health index of the pipe section in the condition assessment report, determine the risk level of the pipe section, and obtain risk classification data; If the risk level of the defect point to be maintained in the risk classification data exceeds a preset risk threshold, a maintenance suggestion for the defect point to be maintained is generated in combination with the prediction trend data set to obtain maintenance planning information; The maintenance plan information is updated in the condition assessment report.

7. A detection system for fire protection pipelines, characterized in that: For implementing the method according to any one of claims 1 to 6, the system comprises: Data acquisition module, used to collect pipeline inner wall reflection data and pipe section coordinate data; A defect detection module, configured to determine whether a pipe section has defects based on the reflection data from the inner wall of the pipe; a defect type identification module, configured to determine the defect type of the pipe section based on the comprehensive feature vector and the historical defect probability model; A health index calculation and prediction module, configured to output the health index of the pipe section according to the defect type and the coordinate data, and generate a prediction trend data set based on historical health index change patterns; A status assessment module is used to generate a status assessment report based on the predicted trend data set, the coordinate data, the health index and the defect type.

8. A terminal device, characterized in that: The invention comprises a memory, a processor and a detection program for fire protection pipes stored in the memory and executable on the processor. When the processor executes the detection program for fire protection pipes, the method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a detection program for fire protection pipes. When the detection program for fire protection pipes is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images