Intelligent pipeline monitoring device and monitoring system

Abstract

The embodiment of the application discloses a kind of intelligent pipeline monitoring device and system, it includes: pipeline position positioning unit, for positioning identification and generating the positioning identification data of each pipeline unique;Pipeline environment monitoring unit, for fixed-point monitoring and generating pipeline environment monitoring data to key monitoring position;Flow detection unit, for determining whether there is abnormal flow signal;Cloud server, for determining abnormal pipeline position information based on monitoring analysis strategy and issuing to specified supervision personnel communication end;The monitoring analysis strategy includes based on abnormal flow signal, calling the pipeline environment monitoring data packet of each key monitoring position to carry out pipeline anomaly analysis and form potential anomaly analysis result to determine that there is abnormal pipeline, and positioning identification data is issued to specified supervision personnel communication end.The application can effectively reduce the labor intensity of field staff, high efficiency, strong target nature;And can effectively improve its identification accuracy to pipeline anomaly.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of clara pipe, and particularly relates to an intelligent pipe monitoring device capable of intelligently monitoring clara pipe and a monitoring system. BACKGROUND

[0002] Clara pipe is a high-density polyethylene (HDPE) winding structure wall pipe formed by hot winding. The wall pipe is made of high-density polyethylene resin as the main raw material, and is made of polypropylene (PP) single-wall corrugated pipe as the supporting structure to form a special structure wall pipe with high external pressure resistance by using a hot winding process.

[0003] Clara pipe has excellent performance. For example, HDPE can be recycled and used, and the main raw material of the winding structure wall pipe, high-density polyethylene, has no toxicity and does not produce any dye during the production process, and the waste pipe can be 100% recycled and reused. For another example, since the product is lighter than other pipe materials under the same application conditions, it is convenient for transportation, construction is convenient and fast, and construction cost can be reduced. In the application range, the pipe can be directly laid after the concrete cushion and concrete pipe foundation trench are qualified, basically achieving the purpose of excavating, laying pipe and backfilling at the same time, simplifying the construction procedure and shortening the construction period. For another example, the high-density polyethylene winding structure wall pipe has flexibility in macroscopic view, and the local pipe section has strong rigidity and overall external pressure resistance. When used under the super heavy load pavement, the traffic safety can be ensured. Due to the flexibility of the pipe, the damage and loss of the pipe can be minimized in the case of geological activities such as earthquakes and uneven settlement, thereby improving the ability of public facilities to resist earthquakes and reduce disasters.

[0004] Generally, clara pipe products can be divided into multiple series, and the most commonly used is the PR series. The inner surface of the products in this series is smooth, the outer part is a special reinforcing structure, the standard length of the pipe is 6 meters, the inner diameter of the pipe ranges from DN300 to DN4000, and the pipe can be mainly used as buried pipeline.

[0005] In the current technical research on how to improve the performance (service life) of clara pipe products, especially the PR series products, it is mainly divided into two directions. One is to improve the sealing effect of the pipe by setting the pipe structure, especially the pipe joint structure or connecting piece. The other is to improve the overall pipe performance by improving the production process, such as controlling the inner and outer ring cooling process to cool the formed pipe quality. For another example, the quality of the pipe is detected. At present, the quality detection method commonly used is to directly detect the quality of the pipe in the production link to prevent the problem of interrupting the pipe production as much as possible.

[0006] Based on the above technical direction, the current research on the clara tube product is more concerned about the design layout of the involved links in the front-end production process, but the quality inspection and monitoring process of the clara tube product in the subsequent application process is also important. As a buried pipeline (such as liquid conveying pipeline for drainage, sewage, etc.), it is damaged over time and with the change of surrounding geological environment and other factors, thereby causing leakage or harm to the surrounding environment and other problems. Therefore, how to establish effective monitoring of its service life is particularly important. At the same time, due to the use characteristics of the PR series clara tube product, it is also easy to cause waste of manpower and material resources by regularly digging the actual pipeline state of the buried pipeline. SUMMARY

[0007] Based on this, in order to solve the defect that the use state of the clara tube product cannot be effectively monitored and predicted in the subsequent application process, an intelligent pipeline monitoring device and a monitoring system are proposed.

[0008] An intelligent pipeline monitoring device, characterized in that it comprises:

[0009] A pipeline position positioning unit for positioning and identifying the position information of each section of clara tube buried pipeline and generating unique positioning identification data of each pipeline;

[0010] A pipeline environment monitoring unit for monitoring the use environment of the pipeline corresponding to the key monitoring position and generating pipeline environment monitoring data uploaded to the cloud server;

[0011] A flow detection unit arranged at the network side of the clara tube buried pipeline to be monitored, for real-time flow normalization detection of the liquid flowing in the clara tube buried pipeline network to determine whether there is an abnormal flow signal; the clara tube buried pipeline network is composed of several sections of clara tube buried pipeline;

[0012] A cloud server for determining abnormal pipeline position information based on a given monitoring analysis strategy and issuing it to a designated supervisor communication terminal when the flow detection unit determines that there is an abnormal flow signal; the monitoring analysis strategy includes calling the pipeline environment monitoring data packet of each key monitoring position based on the abnormal flow signal to analyze the pipeline anomaly and form a potential abnormal analysis result to determine the pipeline with abnormality, and issuing the positioning identification data corresponding to the pipeline to the designated supervisor communication terminal; the cloud server is also used to store the positioning identification data as data classification storage information to form the pipeline environment monitoring data packet corresponding to each pipeline.

[0013] Optionally, in one embodiment, the pipeline environment monitoring unit comprises a geological environment prediction module and a regular inspection information monitoring module; the geological environment prediction module is used for periodically sampling the laying geological environment data around the pipeline during laying construction and sending the sampling data to the cloud server, so that the cloud server can perform prediction analysis and form pipeline life prediction data; the regular inspection information monitoring module can facilitate the classification and arrangement of the data information uploaded by the monitoring personnel during the regular pipe removal process, and form regular inspection data.

[0014] Optionally, in one embodiment, the process of forming pipeline life prediction data by the cloud server comprises: obtaining geological sampling feature information corresponding to the current sampling data, and determining a geological feature type matched with the geological sampling feature information with a preset geological sampling feature database, and calling a geological feature model corresponding to the geological sampling feature information to perform pipeline life prediction analysis and form pipeline life prediction data.

[0015] Optionally, in one embodiment, the cloud server comprises an expiration supervision and early warning module, which can perform expiration supervision and early warning on the pipeline life prediction data, that is, generate expiration early warning information automatically after the life prediction data predicts that the life period is expired.

[0016] Optionally, in one embodiment, the cloud server comprises an environment construction information monitoring module, which can monitor and collect other municipal construction information within a certain range centered on the position information of each section of buried pipeline, and notify the regular inspection information monitoring module to form regular inspection data after actual construction.

[0017] Optionally, in one embodiment, the cloud server can perform data cleaning operation on the sampling data

[0018] Based on the same invention essence, the application also proposes an intelligent pipeline monitoring system, which comprises a plurality of intelligent pipeline monitoring devices that communicate with each other independently.

[0019] The implementation of the embodiments of the present application will have the following beneficial effects:

[0020] The present application can effectively reduce the labor intensity of field workers, has high efficiency and strong target, and can effectively improve the identification accuracy of pipeline abnormalities and ensure the real-time of detection to a certain extent. BRIEF DESCRIPTION OF DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative labor.

[0022] In which:

[0023] Fig. 1 For an embodiment, the structure schematic diagram of the device is implemented;

[0024] Fig. 2 For an embodiment, the structure schematic diagram of the cloud server is implemented;

[0025] Fig. 3 For an embodiment, the structure schematic diagram of the intelligent pipeline monitoring system is implemented. DETAILED DESCRIPTION

[0026] In order to make the objects, technical solutions and advantages of the present application clearer, the following will further describe the present application in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, and are not intended to limit the present application.

[0027] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in the description of the application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. It is to be understood that the use of "first", "second", etc. herein does not denote any order, quantity, combination of elements, but rather is used to distinguish one element from another. For example, in the absence of further recitation, a first element could be termed a second element, and similarly, a second element could be termed a first element without departing from the scope of the present application. Both the first element and the second element are elements, but they are not the same element.

[0028] The Krah pipe product used as a buried pipeline (such as a liquid conveying pipeline for drainage, sewage, etc.) has excellent pipeline performance, so that it can be relatively stable in use for a certain period of time after installation, but with the passage of time and changes in the surrounding geological environment and other factors, the pipeline will be damaged, thereby causing leakage or harm to the surrounding environment and other problems. Since it is generally located underground and the pipe network covers a wide area, there is a certain lag in monitoring the service life of the pipeline, especially the damage to the pipeline. When obvious leakage problems are found, some damage or pollution has already been caused. Therefore, it is particularly important to establish an effective monitoring logic by simply surveying or periodically excavating the buried pipeline to survey the actual pipeline state.

[0029] In the present embodiment, an intelligent pipeline monitoring device is particularly provided, as shown in Figs. 1-3 The intelligent pipeline monitoring device comprises:

[0030] A pipeline position positioning unit for positioning and identifying the position information of each section of the Krah buried pipeline and generating unique positioning identification data of each pipeline;

[0031] A pipeline environment monitoring unit for monitoring the pipeline use environment corresponding to the key monitoring position and generating pipeline environment monitoring data uploaded to the cloud server;

[0032] A flow detection unit arranged at the network side of the Krah buried pipeline to be monitored, for real-time flow normalization detection of the liquid flowing in the Krah buried pipeline network, to determine whether there is an abnormal flow signal; the Krah buried pipeline network is composed of several sections of Krah buried pipelines;

[0033] A cloud server for determining abnormal pipeline position information based on a given monitoring analysis strategy and issuing it to the designated supervisor's communication terminal when the flow detection unit determines that there is an abnormal flow signal; the monitoring analysis strategy comprises calling the pipeline environment monitoring data packet of each key monitoring position based on the abnormal flow signal to analyze the pipeline anomaly and form a potential abnormal analysis result to determine the pipeline with the abnormality, and issuing the positioning identification data corresponding to the pipeline to the designated supervisor's communication terminal; the cloud server is also used to form the pipeline environment monitoring data packet corresponding to each pipeline with the positioning identification data as the data classification storage information.

[0034] Based on the above, the intelligent pipeline monitoring device can realize the arrangement of the position information of all network nodes of the buried pipeline network of the to-be-monitored Krah pipe and give a unique positioning identifier; the pipeline environment monitoring unit can distinguish whether each node has specificity (such as a pipe joint prone to leakage) in the actual use process and perform intensive monitoring and normalization monitoring, and effectively combine the flow detection unit to reduce the monitoring cost and improve the monitoring accuracy.

[0035] In some specific embodiments, the pipeline position positioning unit can obtain the geographic position coordinate information of each section of the buried pipeline of the Krah pipe and configure a corresponding and unique positioning identifier for it to generate unique positioning identifier data of each pipeline; the geographic position coordinate information can use various types of positioning technologies to obtain the current location, and is not specifically limited, and preferably uses a GIS geographic information system.

[0036] In some specific embodiments, the flow detection unit can use a flow sensor.

[0037] In some specific embodiments, in the pipeline environment monitoring unit, the monitoring cost cannot be real-time monitored for each region, so the intensive monitoring position generally refers to the pipeline position laid in a complex geological environment region, the pipeline position laid in a multi-type municipal pipeline intersection region, or a pipeline position that needs to be focused on, especially the joint position between pipelines, which is set according to actual needs; in some more specific embodiments, the pipeline environment monitoring unit includes a geological environment prediction module and a regular inspection information monitoring module; the geological environment prediction module is used to periodically sample the laying geological environment data around the pipeline during laying and construction and send the sampling data to the cloud server, so that the cloud server can perform prediction analysis and form pipeline life prediction data; the regular inspection information monitoring module can classify and arrange the data information uploaded by the monitoring personnel during the regular pipeline inspection to form regular inspection data. The geological environment data includes but is not limited to underground water environment monitoring data (such as humidity, pH value, etc. which can cause long-term aging of the pipeline material and lead to a decrease in bearing strength), rock environment monitoring data (geological change data such as ground subsidence data, which can cause pipeline deformation and cracking to a certain extent), and soil environment monitoring data (pressure and vibration of the pipeline, etc.); the data information uploaded during the regular pipeline inspection generally refers to the images of the change of the pipeline use environment at the specified position or the patrol route shot by the monitoring personnel or the unmanned aerial vehicle, and the specified position or the patrol route needs to form a patrol route map by means of the positioning identifier of the to-be-patrolled pipeline.

[0038] In some specific embodiments, the cloud server forms the pipeline life prediction data by: obtaining geological sampling feature information corresponding to the current sampling data, and determining a geological feature type matched with the geological sampling feature information in a preset geological sampling feature database, and calling a geological feature model corresponding to the geological sampling feature information to perform pipeline life prediction analysis and form pipeline life prediction data. Since the service life of the pipeline is closely related to the operating temperature, pressure, water quality, and the environment in which it is located in the soil, etc., the number of sample sets of the geological sampling feature information participating in the analysis plays a relatively important role, but in fact, the change of the environment around the pipeline, especially the change of the rock environment monitoring data, is relatively stable, so certain assumptions need to be given and a suitable mathematical analysis model needs to be used to analyze the residual life prediction value of the pipeline; the material properties of the pipeline and the pipe fittings do not change gradually with the service time, and the corrosion and wear of the pipeline wall thickness have a linear relationship with time; when selecting the mathematical analysis model, the sample database sample is small or the feature content is not comprehensive, and a suitable sample sampling strategy needs to be selected, such as SMOTE or SMOTE+TomekLinks four sampling strategies for the geological sampling feature information sample set, and the machine learning model is not specifically limited, and XGBoost, AdaCost algorithm can be commonly used.

[0039] In addition, when collecting the sampling data, in order to obtain more accurate sampling data, the sampling data also needs to be cleaned to prevent sampling errors or to process invalid values and missing values of certain sampling data.

[0040] The matching degree prediction formula is:

[0041]

[0042] Wherein, r is a certain sampling data, g is any sampling data value in the standard range database, P is the matching probability, P is (0, 1], and more than 0.95 indicates that the matching degree is high, and less than 0.95 indicates that the matching degree is low. d (*) represents the matching degree predicted by the twin network feature extracted by using the contrast loss training, and the value is (0, 1], f r (*) represents the feature vector extracted by using the convolution network trained by the cross-entropy, and the dimension is 1*512, represents the inner product operation, and r', g' represents the serialized sampling data; specifically, f r(*) represents a feature vector extracted by a convolutional network trained using cross-entropy, i.e., according to an input sample data, a feature is extracted from the sample data using a convolutional network trained using cross-entropy, and during training, the input is a sample data, equivalent to a one-dimensional array, and then the one-dimensional array is sequentially fed into a convolutional layer, a pooling layer and a fully connected layer, the specific convolutional network is ResNet-100, and finally a 1*512 feature vector is output, f r (r)⊙f r (g) represents an inner product operation on two features extracted by a convolutional network trained using cross-entropy, and the value is (0, 1];l d (*) represents the matching degree extracted by a twin network trained using contrastive loss, and specifically for r or g, it is equivalent to a one-dimensional array, and for r', g', the serialized data is also a one-dimensional array, l d (*) extraction of features refers to the extraction of features by a twin network trained using contrastive loss on a one-dimensional array, and the twin network trained using contrastive loss refers to the use of possible matching degrees, and the training pairs of one-dimensional arrays, the specific convolutional network is IResNet-101, and the matching degree is trained by a twin network using a loss function of contrastive loss, and the corresponding relationship between the one-dimensional arrays, so when the input is a one-dimensional array, the extraction of features is the matching degree, and the output matching degree, the value is (0, 1], and specifically, the twin network includes two sub-networks, the input of the first sub-network is a one-dimensional array x1, and then it is sequentially fed into a convolutional layer, a pooling layer and a fully connected layer, the specific convolutional network is IResNet-101, and finally a feature vector l(x1) is output. The final vector l(x1) is the encoding of the input x1. Then, another one-dimensional array x2 is input into the second sub-network (which is exactly the same as the first sub-network), and the same processing is performed on it, and the encoding l(x2) of x(2) is obtained. The distance between l(x1) and l(x2) is solved by applying gradient descent on the triple loss function, and this distance is the output matching degree, the value is (0, 1].

[0043] In some specific embodiments, the cloud server comprises an expiration supervision warning module capable of generating expiration warning information automatically after the pipeline life prediction data predicts that the life limit has expired.

[0044] In some specific embodiments, the cloud server comprises an environmental construction information monitoring module, which can monitor and collect other municipal construction information within a certain range centered on the location information of each section of the buried pipeline, and notify the periodic inspection information monitoring module to form periodic inspection data after actual construction. The specific monitoring and collection refers to that the information grabbing based on a given keyword group can be performed on the government website information in the communication network to form monitoring data. For example, the network crawler algorithm can be used to automatically grab the interested messages on the network according to the given rules, so that the environmental construction information monitoring module comprises an information search sub-module, which is used to complete the collection of web page data through a Web protocol, and then complete the information extraction task to automatically grab the interested data in the given web page. The grabbing strategy preferably adopts a focused search strategy, or uses an IP address-based search strategy to obtain construction information based on the key monitoring requirements, so as to determine whether other construction will affect the pipeline route.

[0045] Based on the same inventive concept, the application further provides an intelligent pipeline monitoring system comprising a plurality of intelligent pipeline monitoring devices that communicate with each other independently.

[0046] The embodiments of the present application have the following beneficial effects:

[0047] The present application can effectively reduce the labor intensity of field workers, has high efficiency, high target, can effectively improve the identification accuracy of pipeline abnormalities, and to a certain extent, can guarantee the real-time detection, has high dynamic informationization, and provides a basis for intelligent operation of the pipeline.

[0048] The above-described embodiments only express several embodiments of the present application, and the description is more specific and detailed, but it should not be understood as limiting the scope of the patent of the present application. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the appended claims.

Claims

1. An intelligent pipeline monitoring device, characterized by, The application relates to a pipeline environment monitoring system, which comprises the following parts: a pipeline position positioning unit for positioning and identifying position information of each section of a buried pipeline of a Krah pipe and generating unique positioning identification data of the pipeline; a pipeline environment monitoring unit for monitoring the pipeline use environment corresponding to a key monitoring position and uploading pipeline environment monitoring data to a cloud server; a flow detection unit arranged at a network side of a buried pipeline network of a Krah pipe to be monitored, which is used for normalizing detection of liquid flowing in the buried pipeline network of the Krah pipe to determine whether an abnormal flow signal exists; the buried pipeline network of the Krah pipe is composed of several sections of buried pipelines of Krah pipes; a cloud server used for determining abnormal pipeline position information based on a given monitoring analysis strategy and delivering the abnormal pipeline position information to a designated supervisor communication terminal when the flow detection unit determines that an abnormal flow signal exists; the monitoring analysis strategy comprises calling pipeline environment monitoring data packets of each key monitoring position to analyze pipeline abnormalities based on the abnormal flow signal to form potential abnormal analysis results to determine the pipeline with the abnormality, and delivering the positioning identification data corresponding to the pipeline to the designated supervisor communication terminal; the cloud server is also used for storing the positioning identification data as data classification storage information to form pipeline environment monitoring data packets corresponding to the pipelines; the pipeline environment monitoring unit comprises a geological environment prediction module and a regular investigation information monitoring module; the geological environment prediction module is used for periodically sampling the laying geological environment data around the pipeline during laying construction and feeding back the sampling data to the cloud server, so that the cloud server can perform prediction analysis and form pipeline life prediction data; the regular investigation information monitoring module can classify and arrange data information uploaded by monitoring personnel during regular pipeline replacement to form regular investigation data; the data information uploaded during the regular pipeline replacement refers to images of changes of the pipeline use environment at specified positions or patrol routes shot by monitoring personnel or unmanned aerial vehicles; the specified positions or patrol routes need to form a patrol route map by means of the positioning identification of the pipeline to be patrolled; the cloud server forms pipeline life prediction data by the following process: acquiring geological sampling feature information corresponding to current sampling data, comparing the geological sampling feature information with a preset geological sampling feature database, determining a geological feature type matched with the geological sampling feature information, calling a geological feature model corresponding to the geological sampling feature information to perform pipeline life prediction analysis and form pipeline life prediction data. The cloud server comprises an environmental construction information monitoring module, which can monitor and collect other municipal construction information within a certain range centered on the position information of each section of the buried pipeline of the clark tube, and form periodic inspection data after actual construction is notified by the periodic inspection information monitoring module; the monitoring and collection refers to that information grabbing of government website information in the communication network based on a given keyword group can be performed to form monitoring data; and the environmental construction information monitoring module further comprises an information search submodule, which is used for collecting web page data through a Web protocol, and then performing an information extraction task to automatically grab data of interest in a given web page, and a focusing search strategy is preferably used as a grabbing strategy, or an IP address-based search strategy is used to obtain construction information based on key monitoring requirements to determine whether other construction will affect the pipeline route.

2. The intelligent pipeline monitoring device of claim 1, wherein, The cloud server can perform data cleaning operation on the sampling data.

3. The intelligent pipeline monitoring device of claim 1, wherein, The cloud server comprises an expiration supervision early warning module, which can perform expiration supervision early warning on the pipeline life prediction data, that is, expiration early warning information is automatically generated after the predicted life period in the pipeline life prediction data expires. 4.An intelligent pipeline monitoring system comprising a plurality of intelligent pipeline monitoring devices according to any one of claims 1-3, wherein each intelligent pipeline monitoring device can independently communicate with each other.

Images