CN116933186B - Sewage pipe network blocking real-time monitoring method based on data driving - Google Patents
Sewage pipe network blocking real-time monitoring method based on data driving Download PDFInfo
- Publication number
- CN116933186B CN116933186B CN202311182448.5A CN202311182448A CN116933186B CN 116933186 B CN116933186 B CN 116933186B CN 202311182448 A CN202311182448 A CN 202311182448A CN 116933186 B CN116933186 B CN 116933186B
- Authority
- CN
- China
- Prior art keywords
- monitoring
- blockage
- monitoring point
- acquiring
- index
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 203
- 239000010865 sewage Substances 0.000 title claims abstract description 77
- 230000000903 blocking effect Effects 0.000 title claims abstract description 57
- 238000000034 method Methods 0.000 title claims abstract description 50
- 239000007788 liquid Substances 0.000 claims abstract description 42
- 230000002159 abnormal effect Effects 0.000 claims abstract description 40
- 230000005856 abnormality Effects 0.000 claims description 21
- 230000008859 change Effects 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 11
- 239000012530 fluid Substances 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 7
- 230000036962 time dependent Effects 0.000 claims description 2
- 238000001514 detection method Methods 0.000 abstract description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 5
- 238000009434 installation Methods 0.000 description 3
- 238000009825 accumulation Methods 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008021 deposition Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000004519 grease Substances 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000001556 precipitation Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- VEMKTZHHVJILDY-UHFFFAOYSA-N resmethrin Chemical compound CC1(C)C(C=C(C)C)C1C(=O)OCC1=COC(CC=2C=CC=CC=2)=C1 VEMKTZHHVJILDY-UHFFFAOYSA-N 0.000 description 1
- 239000010802 sludge Substances 0.000 description 1
- 235000019640 taste Nutrition 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F17—STORING OR DISTRIBUTING GASES OR LIQUIDS
- F17D—PIPE-LINE SYSTEMS; PIPE-LINES
- F17D5/00—Protection or supervision of installations
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01F—MEASURING VOLUME, VOLUME FLOW, MASS FLOW OR LIQUID LEVEL; METERING BY VOLUME
- G01F1/00—Measuring the volume flow or mass flow of fluid or fluent solid material wherein the fluid passes through a meter in a continuous flow
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01F—MEASURING VOLUME, VOLUME FLOW, MASS FLOW OR LIQUID LEVEL; METERING BY VOLUME
- G01F23/00—Indicating or measuring liquid level or level of fluent solid material, e.g. indicating in terms of volume or indicating by means of an alarm
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01L—MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER, MECHANICAL EFFICIENCY, OR FLUID PRESSURE
- G01L13/00—Devices or apparatus for measuring differences of two or more fluid pressure values
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01P—MEASURING LINEAR OR ANGULAR SPEED, ACCELERATION, DECELERATION, OR SHOCK; INDICATING PRESENCE, ABSENCE, OR DIRECTION, OF MOVEMENT
- G01P5/00—Measuring speed of fluids, e.g. of air stream; Measuring speed of bodies relative to fluids, e.g. of ship, of aircraft
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2123/00—Data types
- G06F2123/02—Data types in the time domain, e.g. time-series data
Abstract
The application relates to the technical field of data processing, and provides a sewage pipe network blocking real-time monitoring method based on data driving, which comprises the following steps: acquiring an original data sequence of each monitoring point; acquiring sewage flow of each monitoring point; calculating the flow loss between two adjacent monitoring points; acquiring an energy loss index of each monitoring point; acquiring the total liquid energy of each monitoring point; taking the energy loss and abnormal blocking value between two adjacent monitoring points; acquiring a blockage degree index of a monitoring point; obtaining an improved path length of an isolated forest; calculating an anomaly score; and (5) real-time monitoring of the blockage condition of the pipeline is completed. Thereby realizing the real-time monitoring of the blockage of the sewage pipe network and effectively solving the problem of missing detection and false detection of abnormal data in the real-time monitoring of the blockage of the sewage pipe network.
Description
Technical Field
The application relates to the technical field of data processing, in particular to a sewage pipe network blocking real-time monitoring method based on data driving.
Background
Sewage networks are an important component of systems for urban collection, transportation and treatment. The urban water system guarantees the safety of urban water bodies, improves urban functions and improves urban tastes. But the sewage pipe network is blocked due to accumulation of foreign matters in the pipe, precipitation of sludge, and aggregation of grease and fat. The light sewage flows slowly, the heavy sewage flows backward and overflows, the problems of environment and sanitation are caused, and the living of residents is uncomfortable and puzzled.
The data of the blocked sewage pipeline and the non-blocked data are not greatly different due to the fact that the blocking of the sewage pipeline is usually slow in deposition and stacking, the isolated forest is easy to cause the phenomenon of overfitting of the isolated forest when the data of the sewage pipeline are processed, abnormal data are missed to be detected and are misplaced, and the effect of abnormal monitoring of the blocking of the sewage pipeline is not ideal.
Disclosure of Invention
In order to solve the technical problems, the application aims to provide a sewage pipe network blocking real-time monitoring method based on data driving, and the adopted technical scheme is as follows:
the embodiment of the application provides a real-time monitoring method for sewage pipe network blockage based on data driving, which comprises the following steps:
acquiring an original data sequence of each monitoring point; the original data sequence comprises a flow rate, pressure, liquid level height and density data sequence;
acquiring the sewage flow of each monitoring point according to the flow velocity data sequence of each monitoring point; calculating the flow loss between two adjacent monitoring points according to the sewage flow of each monitoring point; acquiring an energy loss index of each monitoring point according to the flow velocity and the pressure data sequence of the monitoring point and the flow loss between two adjacent monitoring points; acquiring the total liquid energy of the monitoring point according to each original data sequence of the monitoring point; acquiring energy loss between two adjacent monitoring points according to the total liquid energy and the energy loss index of each monitoring point; acquiring abnormal blocking values between two adjacent monitoring points at each moment according to the liquid level height data sequence of each monitoring point and the energy loss between the two adjacent monitoring points; acquiring a blockage degree index of each monitoring point at each moment according to the abnormal blockage value between two adjacent monitoring points at the same moment;
acquiring a blockage degree index sequence; constructing an isolated forest according to the blockage degree index sequence; acquiring the improved path length of the isolated forest according to the blocking degree index of the monitoring points at each moment; calculating an anomaly score from the improved path length of the isolated forest; and (5) completing real-time monitoring of the channel blocking condition according to the abnormal score.
Preferably, the method for calculating the flow loss between two adjacent monitoring points according to the sewage flow of each monitoring point comprises the following specific steps:
acquiring monitoring pointsAnd monitoring Point->Is a flow difference value of (1); the flow difference value is added with a monitoring point>As a flow loss; wherein (1)>Representing a monitoring point.
Preferably, the energy loss index of each monitoring point is obtained according to the flow velocity and pressure data sequence of the monitoring point and the flow loss between two adjacent monitoring points, and the specific method comprises the following steps:
calculating the pressure difference and the flow velocity square difference of two adjacent monitoring points; if the pressure difference is 0, the energy loss index of the monitoring point is 0; if the pressure difference is not 0, calculating the ratio of the pressure difference to the flow velocity square difference; the product of the flow loss and the ratio is taken as an energy loss index.
Preferably, the obtaining the total energy of the liquid at the monitoring point according to each original data sequence of the monitoring point specifically includes:
and calculating the total liquid energy of each monitoring point by adopting the Bernoulli equation of the fluid and combining the original data sequence of each monitoring point.
Preferably, the method for acquiring the energy loss between two adjacent monitoring points according to the total energy and the energy loss index of the liquid at each monitoring point comprises the following steps:
acquiring an energy error of a pipeline; recording the difference value of the total energy of the liquid of two adjacent monitoring points as a total energy change value of the liquid; calculating the absolute value of the difference between the total energy change value and the energy error of the liquid; taking the product of the absolute value and the energy loss index as the energy loss between two adjacent monitoring points.
Preferably, the abnormal blocking value between two adjacent monitoring points at each moment is obtained according to the liquid level height data sequence of each monitoring point and the energy loss between the two adjacent monitoring points, and the specific method comprises the following steps:
calculating the absolute value of the liquid level difference value of two adjacent monitoring points; and taking the product of the absolute value and the energy loss between two adjacent monitoring points as an abnormal blocking value between the two adjacent monitoring points.
Preferably, the blocking degree index of each monitoring point at each moment is obtained according to the abnormal blocking value between two adjacent monitoring points at the same moment, and the specific method comprises the following steps:
acquiring abnormal blocking values between two monitoring points at each time to form a sequence; obtaining the range and the minimum value of the sequence; recording the difference value of adjacent abnormal blocking values in the sequence as the time-dependent change value of the abnormal blocking value; calculating a difference between the variation value and the minimum value; taking the ratio of the difference value to the polar difference as an index of an exponential function based on a natural constant; obtaining a calculation result of the exponential function; and taking the calculation result of the index function as a blockage degree index of the monitoring point.
Preferably, the obtaining the improved path length of the isolated forest according to the blocking degree index of the monitoring point at each moment specifically includes:
in the method, in the process of the application,indicate->The blockage level index at each moment is an improved path length throughout the isolated forest,indicate->Index of degree of blockage at each moment>Representing the number of constructed orphaned trees>Indicate->The blocking degree index at each moment is +.>Path length of an isolated tree, +.>Representing the path length +.>Frequency of occurrence in isolated forests.
Preferably, the calculating the anomaly score according to the improved path length of the isolated forest includes the following specific steps:
acquiring the average path length of a BST binary tree; calculating the ratio of the improved path length of the isolated forest to the average path length of the BST binary tree; and taking the calculation result of an exponential function taking 2 as a base and the opposite number of the ratio as an index as an abnormality score.
Preferably, the real-time monitoring of the channel blockage situation is completed according to the abnormality score, which comprises the following specific steps:
setting an abnormality score threshold, and when the abnormality score is larger than the abnormality score threshold, representing that the interior of the sewage pipeline is blocked; and when the abnormality score is smaller than the abnormality score threshold, the abnormality score represents that the inside of the pipeline is not blocked.
The application has at least the following beneficial effects:
according to the application, the energy loss between two adjacent monitoring points is obtained by using the Bernoulli equation through the monitored data, the state conditions of the two monitoring points are considered in the energy loss, and the circulation condition of the pipeline can be effectively reflected. Further obtain unusual blocking value, unusual blocking value can accurately judge the jam condition in the sewer line, avoid the debris in the sewage to the influence of data. And then, processing the abnormal blocking value of the sewage pipeline to obtain a blocking degree index at a certain moment, wherein the blocking condition of the sewage pipeline at a certain moment can be obviously reflected by the abnormal blocking value. And finally, the improved algorithm of the isolated forest is used for analyzing the data among the monitoring points in real time, so that the problem of small data fluctuation caused by slow blocking process can be effectively solved, the condition of false detection and missing detection is caused, and the accuracy of the isolated forest on the blocking monitoring of the sewage pipe network is improved.
Drawings
In order to more clearly illustrate the embodiments of the application or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the application, and that other drawings can be obtained according to these drawings without inventive faculty for a person skilled in the art.
Fig. 1 is a schematic flow chart of a method for monitoring blockage of a sewage pipe network based on data driving according to an embodiment of the application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
Referring to fig. 1, a flow chart of a method for monitoring blockage of a sewage pipe network based on data driving according to an embodiment of the application is shown, and the method comprises the following steps:
step S001: and acquiring monitoring point data in a section of sewage pipe network.
The existing sewage pipe network generally adopts a net layout, including a main pipe network, a branch pipe network and the like. In view of the problem that the pipe turns may cause inaccurate data monitoring, the sensors are installed at the joints of the pipes in the present embodiment, and the sensors at these positions can change the sewage pipe into a straight pipe section.
For the pipeline section, the main sewage pipeline takes 100 meters as the maximum distance to install the sensor, and the branch pipeline takes the following steps of) Maximum distance mounting sensor (+)>Radius for main and branch pipes). When the installation is carried out, if the length of the main pipeline is divided by 100 to obtain a value, 1 is added after the value is rounded up, and the number of the installed sensors is as large as 350 meters, for example, 5 sensors are required to be installed, and the distance between every two sensors after the uniform installation is 87.5. And obtaining the sensor for installing the branch pipeline by the same method. The method for setting the installation distance of the sensor and the embodiment of setting the sensor are not limited, and an operator can select the sensor according to actual situations, and four sensors including a pressure sensor, a flow rate sensor, a liquid level sensor and a density sensor are used in the embodiment. The location of each sensor is the location of the monitoring point.
The time interval for collecting data is set for the data of each monitoring point, so that the time sequence of pressure, flow rate and liquid level can be obtained. It should be noted that, the time interval enforcer for collecting data can choose according to the actual situation, and the time interval chosen in this embodiment is 1 second.
Step S002: and acquiring the blockage degree index of each moment between two adjacent monitoring points.
The blockage of the sewage pipeline is divided into two cases, namely complete blockage and incomplete blockage, wherein the complete blockage is achieved by only monitoring whether one monitoring point has water and the other monitoring point has no water; and when the blockage is not complete, various factors are combined for analysis. According to the embodiment, the blocking condition of the pipeline is monitored in real time, and early warning is carried out on the blocked pipeline, so that relevant staff can clean or replace the interior of the pipeline in time, and the condition that the interior of the pipeline is blocked completely is avoided.
When the drainage pipeline is blocked, the blocking reduces the flow area in the pipeline, increases the speed of fluid passing through the area, and causes the first stepThe sewage speed of the monitoring points is higher than the +.>The sewage speed of each monitoring point is higher. And the liquid level of the sewage in the pipeline is correspondingly reduced. The more severe the blockage, the greater the difference in velocity between two adjacent monitoring points, and the greater the difference in height.
After the blockage occurs, the blockage can obstruct the normal flow of the sewage through the pipeline, so that the flow rate at the monitoring point is reduced, and the first step is calculated by the flow rate of the sewage and the cross-sectional area of the sewageSewage flow of each monitoring point->Wherein->Indicate->Sewage flow of each monitoring point->Indicate->The flow rate of the sewage at each monitoring point, < > and->Indicate->The cross-sectional area of sewage at each monitoring point needs to be described, and the cross-sectional area of sewage can be obtained by the liquid level through the properties of circles and right triangles, and is not described herein.
The sewage flow in the drainage pipeline can obviously reflect the change of the sewage in the pipeline when encountering the blockage. The sewage flow of the two monitoring points can reflect the sewage flow loss of the two monitoring points. The slave is calculated by the following formulaTo->The flow loss at two sewage monitoring positions is calculated as follows:
in the method, in the process of the application,indicate->Person to->Flow loss between monitoring points, +.>、/>Respectively represent +.>Person, th->The sewage flow of each monitoring point. When the flow loss of the two monitoring points is larger, the possibility of blocking the two monitoring points is provedThe greater the sex.
It should be noted that, whenWhen the flow rate of the position monitoring point is 0, namely +.>At this time, the explanation is at +.>No sewage flows through the pipeline at each monitoring point, and thus at +.>No sewage can flow through the pipeline at each monitoring point, and the flow loss is +.>Is 0.
When no blockage occurs, the variation of the total energy of the sewage in each part of the pipeline is tiny, and the relation between the pressure difference of two monitoring points and the flow rate of the fluid can reflect the energy loss index of the fluid. The energy loss index between the two monitoring points is calculated as follows:
in the method, in the process of the application,to be from->Person and->Energy loss index between monitoring points, < >>Represent the firstPerson and->Pressure difference of each monitoring point ∈>Indicate->Person and->The flow loss between the monitoring points,、/>respectively indicate the fluid is at->Person, th->Flow rate at each monitoring point.
It should be noted that when the sewage pipeline is blocked, the pressure difference between the two monitoring points is increased, and according to the Bernoulli equation, under the ideal condition of neglecting pipeline friction and other energy losses, the speeds of the two monitoring points are also increased under the action of pressure, wherein the ratio of the pressure difference to the square difference of the speeds is expressed as a constant; however, in practical situations, if a blockage situation occurs between two monitoring points, the sewage flow rate may be reduced to a certain extent due to the influence of the blockage, the sewage liquid level rises due to the existence of the blockage, the pressure difference also rises along with the rise, at this time, the variation degree of the pressure difference is greater than the variation degree of the velocity square difference, and when the pressure difference is greater, the energy loss index is greater.
The sewage has total energy of liquid at each monitoring point, the firstTotal energy of liquid at each monitoring point->The pressure, the flow rate, the density and the liquid level height of each monitoring point can be calculated by using the Bernoulli equation of the fluid, and it should be noted that the Bernoulli equation of the fluid is a known technology, and will not be described in detail in this embodiment.
The total energy of the fluid at a certain position is obtained through the Bernoulli equation, and the energy loss to two adjacent monitoring points can be calculated by calculating the difference value of the total energy. The calculation formula is as follows:
in the method, in the process of the application,indicate->Person and->The total energy lost between the monitoring points due to the blockage,to be from->Person and->Energy loss index between monitoring points, < >>Indicate->First, secondTotal energy of liquid at each monitoring point, +.>Representing an energy error.
The absolute value is taken to prevent the energy change from being negative. When the drain pipe is not blocked, the total energy of each monitoring point in the pipeline and the energy of the last monitoring point have an error due to factors such as friction of the pipe wall. This error is determined by the material, distance and friction of the pipe wall of the drain pipe, and can be obtained by darcy-Wei Siba hz, which is not described in detail in this embodiment.
When no blockage occurs, the pressure, flow rate and energy between the two monitoring points are not changed basically. After occlusion, changes in pressure, flow rate, and energy are caused. Some energy loss occurs when the blockage collides with the blockage due to blockage. Therefore, when the energy difference between the two monitoring points and the energy loss index of the two monitoring points are larger, the energy loss between the two monitoring points is larger.
When the sewage pipeline is blocked, the liquid level between the two monitoring points can obviously change, and the more serious the blocking is, the larger the liquid level difference between the two monitoring points is caused. Thus, an abnormal blocking value between two adjacent monitoring points can be constructed.
Wherein:
in the method, in the process of the application,indicate->Person and->Each monitoring pointAbnormal blocking value between->Indicate->Person and->Total energy loss between monitoring points due to blockage, < >>Indicate->And the first and secondThe liquid level change value of each monitoring point, < + >>、/>Indicate->Person, th->The liquid level of each monitoring point.
The greater the difference in fluid level at the two monitoring points, the more severe the degree of blockage in the conduit. Because the flowing water has certain fluctuation, the absolute value is used as the difference between the liquid levels of the two monitoring points. If the liquid level at the two monitoring points is the same, the liquid level change value is 0, which indicates that the liquid level is not changed when sewage flows in the pipeline, and further indicates that no blockage in the pipeline blocks the sewage flow, so that the abnormal blockage value is 0.
Abnormal blocking values can be obtained between two adjacent monitoring points, the abnormal blocking values change along with time, a characteristic sequence can be formed, and the fluctuation of the abnormal blocking values between the two monitoring points along with time is described. In general, when an abnormal blockage value increases, the energy loss representing two monitoring points increases, and the possibility of blockage increases, or vice versa. After the blockage, the degree of the blockage is not increased any more, the energy loss of the two monitoring points can fluctuate within a certain range, and the abnormal blockage value can also fluctuate within a certain range.
The greater the difference between adjacent abnormal clogging values, the greater the likelihood that it will clog during this time period, and the greater the resulting clogging degree index. For any one of the feature sequences, the following is calculated:
in the method, in the process of the application,representing the%>Index of degree of blockage at individual sites>Represents the maximum value in the sequence,/->Representing the minimum in the sequence,/->Is the difference between adjacent abnormal blocking values in the sequence, i.eWherein->、/>Respectively the>、/>Abnormal blocking value of individual location, +.>Is a natural constant.
Step S003: and the blocking condition of the sewage pipeline is monitored in real time by using the isolated forest.
According to the condition, any two adjacent monitoring points can generate a blockage degree index sequence within a certain time range, and as blockage is usually carried out slowly, numerical fluctuation between normal data and blockage data in the sequence is not large, the numerical value is relatively close, and the accuracy of abnormal monitoring of an isolated forest is weakened by the data. The probability coefficient is introduced to improve the isolated forest algorithm. The algorithm process is as follows:
1) And constructing an isolated forest through a data sequence of the blockage level index.
2) The average path length of the data in the sequence in the isolated forest is influenced by the probability coefficient.
The path lengths may be equal or unequal for the same data in the isolated trees created by different isolated forests. Since the more frequently the same path length occurs, the greater should be the impact on the computed data path.
In the method, in the process of the application,representation data->Improved path length in the whole isolated forest, < >>Indicate->Index of degree of blockage at each moment>Representing the number of constructed orphaned trees>The representation value is +.>In->Path length of an isolated tree, +.>Indicating that the path length is +.>Frequency of occurrence in isolated forests.
3) Calculating an anomaly score:
where n represents the amount of data in the sequence,representing the average path length of constructing a BST binary tree from the sequence, < >>Representation data->Improved path length in the whole isolated forest, < >>Is->Is a score of abnormality of (a). BST IIThe obtaining of the average path length of the tree is a known technique, and is not described in detail in this embodiment.
Setting an abnormality score thresholdWhen abnormality score->When the data is abnormal data, the sewage pipeline is internally blocked; abnormality score->When the data is normal, the pipeline is not blocked; wherein, the abnormal score threshold value implementer can set according to the actual situation, and takes the experience value +.>。
4) And monitoring the acquired sewage pipeline in real time according to the obtained scores of the sequence data. When the improved isolated forest algorithm is used, the situation that the data for acquiring the blockage degree indexes between the monitoring points are abnormal is found, the situation that the pipeline is blocked at the position can be considered, the monitoring points at the two ends of the blocked pipeline position send an alarm to staff, and the staff can clear the blockage in the pipeline according to the positions of the monitoring points in time.
In summary, according to the embodiment of the application, the energy loss between two adjacent monitoring points is obtained by using the Bernoulli equation according to the monitored data, the state conditions of the two monitoring points are considered in the energy loss, and the circulation condition of the pipeline can be effectively reflected. Further obtain unusual blocking value, unusual blocking value can accurately judge the jam condition in the sewer line, avoid the debris in the sewage to the influence of data. And then, processing the abnormal blocking value of the sewage pipeline to obtain a blocking degree index at a certain moment, wherein the blocking condition of the sewage pipeline at a certain moment can be obviously reflected by the abnormal blocking value. And finally, the improved algorithm of the isolated forest is used for analyzing the data among the monitoring points in real time, so that the problem of incorrect monitoring caused by small data fluctuation due to gradual blockage can be effectively solved, and the accuracy of the isolated forest on the sewage pipe network blockage monitoring is improved.
It should be noted that: the sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. And the foregoing description has been directed to specific embodiments of this specification. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and the same or similar parts of each embodiment are referred to each other, and each embodiment mainly describes differences from other embodiments.
The above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; the foregoing embodiments are merely preferred embodiments of the present application, and any modifications, equivalents, improvements and etc. made within the spirit and principles of the present application should not be construed as limiting the scope of the present application.
Claims (7)
1. The real-time monitoring method for the blockage of the sewage pipe network based on data driving is characterized by comprising the following steps of:
acquiring an original data sequence of each monitoring point; the original data sequence comprises a flow rate, pressure, liquid level height and density data sequence;
acquiring the sewage flow of each monitoring point according to the flow velocity data sequence of each monitoring point; calculating the flow loss between two adjacent monitoring points according to the sewage flow of each monitoring point; acquiring an energy loss index of each monitoring point according to the flow velocity and the pressure data sequence of the monitoring point and the flow loss between two adjacent monitoring points; acquiring the total liquid energy of the monitoring point according to each original data sequence of the monitoring point; acquiring energy loss between two adjacent monitoring points according to the total liquid energy and the energy loss index of each monitoring point; acquiring abnormal blocking values between two adjacent monitoring points at each moment according to the liquid level height data sequence of each monitoring point and the energy loss between the two adjacent monitoring points; acquiring a blockage degree index of each monitoring point at each moment according to the abnormal blockage value between two adjacent monitoring points at the same moment;
acquiring a blockage degree index sequence; constructing an isolated forest according to the blockage degree index sequence; acquiring the improved path length of the isolated forest according to the blocking degree index of the monitoring points at each moment; calculating an anomaly score from the improved path length of the isolated forest; real-time monitoring of the channel blocking condition is completed according to the abnormal score;
the improved path length of the isolated forest is obtained according to the blocking degree index of the monitoring points at each moment, specifically:
in the method, in the process of the application,indicate->Improved path length of the blockage level index over the entire isolated forest at individual moments +.>Indicate->Index of degree of blockage at each moment>Representing the number of constructed orphaned trees>Indicate->The blocking degree index at each moment is +.>Path length of an isolated tree, +.>Representing the path length +.>Frequency of occurrence in isolated forests;
the method for acquiring the energy loss index of each monitoring point according to the flow velocity and pressure data sequence of the monitoring point and the flow loss between two adjacent monitoring points comprises the following steps:
calculating the pressure difference and the flow velocity square difference of two adjacent monitoring points; if the pressure difference is 0, the energy loss index of the monitoring point is 0; if the pressure difference is not 0, calculating the ratio of the pressure difference to the flow velocity square difference; taking the product of the flow loss and the ratio as an energy loss index;
the blocking degree index of each monitoring point at each moment is obtained according to the abnormal blocking value between two adjacent monitoring points at the same moment, and the specific method comprises the following steps:
acquiring abnormal blocking values between two monitoring points at each time to form a sequence; obtaining the range and the minimum value of the sequence; recording the difference value of adjacent abnormal blocking values in the sequence as the time-dependent change value of the abnormal blocking value; calculating a difference between the variation value and the minimum value; taking the ratio of the difference value to the polar difference as an index of an exponential function based on a natural constant; obtaining a calculation result of the exponential function; and taking the calculation result of the index function as a blockage degree index of the monitoring point.
2. The method for monitoring the blockage of the sewage pipe network in real time based on data driving according to claim 1, wherein the method for calculating the flow loss between two adjacent monitoring points according to the sewage flow rate of each monitoring point comprises the following specific steps:
acquiring monitoring pointsAnd monitoring Point->Is a flow difference value of (1); the flow difference value is added with a monitoring point>As a flow loss; wherein (1)>Representing a monitoring point.
3. The method for monitoring the blockage of the sewage pipe network in real time based on data driving according to claim 1, wherein the method for acquiring the total liquid energy of the monitoring point according to each original data sequence of the monitoring point is specifically as follows:
and calculating the total liquid energy of each monitoring point by adopting the Bernoulli equation of the fluid and combining the original data sequence of each monitoring point.
4. The method for monitoring the blockage of the sewage pipe network in real time based on data driving according to claim 1, wherein the method for acquiring the energy loss between two adjacent monitoring points according to the total liquid energy and the energy loss index of each monitoring point is as follows:
acquiring an energy error of a pipeline; recording the difference value of the total energy of the liquid of two adjacent monitoring points as a total energy change value of the liquid; calculating the absolute value of the difference between the total energy change value and the energy error of the liquid; taking the product of the absolute value and the energy loss index as the energy loss between two adjacent monitoring points.
5. The method for monitoring the blockage of the sewage pipe network in real time based on data driving according to claim 1, wherein the method is characterized in that the abnormal blockage value between two adjacent monitoring points at each moment is obtained according to the liquid level height data sequence of each monitoring point and the energy loss between the two adjacent monitoring points, and comprises the following steps:
calculating the absolute value of the liquid level difference value of two adjacent monitoring points; and taking the product of the absolute value and the energy loss between two adjacent monitoring points as an abnormal blocking value between the two adjacent monitoring points.
6. The method for monitoring the blockage of the sewage pipe network in real time based on data driving according to claim 1, wherein the method for calculating the abnormality score according to the improved path length of the isolated forest comprises the following specific steps:
acquiring the average path length of a BST binary tree; calculating the ratio of the improved path length of the isolated forest to the average path length of the BST binary tree; and taking the calculation result of an exponential function taking 2 as a base and the opposite number of the ratio as an index as an abnormality score.
7. The real-time monitoring method for the blockage of the sewage pipe network based on the data driving of claim 1, wherein the real-time monitoring of the blockage situation of the pipeline is completed according to the abnormality score, comprises the following specific steps:
setting an abnormality score threshold, and when the abnormality score is larger than the abnormality score threshold, representing that the interior of the sewage pipeline is blocked; and when the abnormality score is smaller than the abnormality score threshold, the abnormality score represents that the inside of the pipeline is not blocked.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311182448.5A CN116933186B (en) | 2023-09-14 | 2023-09-14 | Sewage pipe network blocking real-time monitoring method based on data driving |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311182448.5A CN116933186B (en) | 2023-09-14 | 2023-09-14 | Sewage pipe network blocking real-time monitoring method based on data driving |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116933186A CN116933186A (en) | 2023-10-24 |
| CN116933186B true CN116933186B (en) | 2023-11-24 |
Family
ID=88386386
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311182448.5A Active CN116933186B (en) | 2023-09-14 | 2023-09-14 | Sewage pipe network blocking real-time monitoring method based on data driving |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116933186B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117312617B (en) * | 2023-11-29 | 2024-04-12 | 山东优控智能技术有限公司 | Real-time sewage treatment method and system based on sewage data monitoring |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108921440A (en) * | 2018-07-11 | 2018-11-30 | 平安科技（深圳）有限公司 | Pollutant method for monitoring abnormality, system, computer equipment and storage medium |
| CN109442221A (en) * | 2018-11-21 | 2019-03-08 | 同济大学 | A kind of water supply network booster method for detecting extracted based on pressure disturbance |
| CN113435547A (en) * | 2021-08-27 | 2021-09-24 | 中国环境监测总站 | Water quality index fusion data anomaly detection method and system |
-
2023
- 2023-09-14 CN CN202311182448.5A patent/CN116933186B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108921440A (en) * | 2018-07-11 | 2018-11-30 | 平安科技（深圳）有限公司 | Pollutant method for monitoring abnormality, system, computer equipment and storage medium |
| CN109442221A (en) * | 2018-11-21 | 2019-03-08 | 同济大学 | A kind of water supply network booster method for detecting extracted based on pressure disturbance |
| CN113435547A (en) * | 2021-08-27 | 2021-09-24 | 中国环境监测总站 | Water quality index fusion data anomaly detection method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116933186A (en) | 2023-10-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116933186B (en) | Sewage pipe network blocking real-time monitoring method based on data driving | |
| US10285345B2 (en) | Irrigation device and system, and method for using the same | |
| CN110648480B (en) | Single variable alarm system and method based on change rate | |
| CN113935439B (en) | Fault detection method, equipment, server and storage medium for drainage pipe network | |
| CN103994333B (en) | A kind of oil gas pipe network leakage detection method merged based on two-dimensional signal | |
| CN105717887B (en) | Oil vapor treatment station intelligent early-warning system based on Internet of Things sensing data | |
| CN104063588A (en) | Multi-source data fusion-based system and method for predicting pipeline corrosion defect size | |
| CN109187900B (en) | Water quality safety monitoring and management system | |
| CN106088267A (en) | Domestic sewer pipe anti-blocking alarm device | |
| CN116202590A (en) | Urban river channel big data monitoring liquid level alarm system and method | |
| CN117071706B (en) | Drainage pipe network control system for municipal road | |
| CN111798529B (en) | Pipe network free outflow flow on-line monitoring method based on image recognition | |
| CN112113148A (en) | Pipe network side leakage detection method based on pressure and flow for rail transit | |
| CN116541678A (en) | Pressure monitoring method and device for gas station safety pipeline | |
| CN116658831A (en) | Intelligent drainage pipeline real-time monitoring and early warning system based on deep learning | |
| CN110503254A (en) | One kind leaking method for early warning based on markovian nonmetal pipeline | |
| CN115655422A (en) | Early warning analysis method and device for collapse of drainage pipe network, electronic equipment and medium | |
| CN111365618B (en) | Pipeline monitoring method and device, storage medium and electronic equipment | |
| CN114352946A (en) | Drainage engineering pipeline blocks up early warning system | |
| CN114840571A (en) | Drainage pipeline blockage identification and positioning method and system | |
| CN105709467B (en) | Sludge drainage system and use its method | |
| CN107228743B (en) | Online leak hunting device of trap based on density | |
| CN117909787A (en) | Intelligent diagnosis method for transportation bottleneck of drainage pipe network and overflow of inspection well | |
| CN114529106B (en) | Scale prediction algorithm for oil field heating furnace coil pipe | |
| CN111680424B (en) | River attack automatic distinguishing method based on χ pattern state characteristics |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |