CN115931055B - Rural water supply operation diagnosis method and system based on big data analysis - Google Patents
Rural water supply operation diagnosis method and system based on big data analysis Download PDFInfo
- Publication number
- CN115931055B CN115931055B CN202310015617.XA CN202310015617A CN115931055B CN 115931055 B CN115931055 B CN 115931055B CN 202310015617 A CN202310015617 A CN 202310015617A CN 115931055 B CN115931055 B CN 115931055B
- Authority
- CN
- China
- Prior art keywords
- flow
- value
- pressure
- time
- day
- 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
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 43
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000003745 diagnosis Methods 0.000 title claims abstract description 17
- 238000007405 data analysis Methods 0.000 title claims abstract description 13
- 238000012544 monitoring process Methods 0.000 claims abstract description 110
- 230000002159 abnormal effect Effects 0.000 claims abstract description 55
- 238000004880 explosion Methods 0.000 claims abstract description 26
- 238000004364 calculation method Methods 0.000 claims abstract description 25
- 238000001914 filtration Methods 0.000 claims abstract description 22
- 230000005856 abnormality Effects 0.000 claims description 11
- 230000001502 supplementing effect Effects 0.000 claims description 11
- 238000005259 measurement Methods 0.000 claims description 7
- 230000009172 bursting Effects 0.000 claims description 3
- 230000008030 elimination Effects 0.000 claims description 3
- 238000003379 elimination reaction Methods 0.000 claims description 3
- 241000728173 Sarima Species 0.000 claims 3
- 238000005206 flow analysis Methods 0.000 claims 1
- 239000000463 material Substances 0.000 claims 1
- 230000001932 seasonal effect Effects 0.000 description 21
- 238000004458 analytical method Methods 0.000 description 11
- 230000003203 everyday effect Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000012217 deletion Methods 0.000 description 2
- 230000037430 deletion Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000035772 mutation Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000012821 model calculation Methods 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A20/00—Water conservation; Efficient water supply; Efficient water use
Abstract
The invention relates to the field of water supply monitoring, and provides a rural water supply operation diagnosis method and system based on big data analysis, wherein the method comprises the following steps: taking the flow data and the pressure data of the previous T days of the monitoring day as an original flow pressure data set to obtain a flow pressure data set after rejection; dividing the flow pressure data set at each moment into a flow data set at each moment and a pressure data set at each moment; judging whether the pressure monitoring value at the corresponding moment is abnormal or not according to the pressure standard deviation at each moment; calculating flow estimated values of the flow data sets at all the moments through the improved and optimized Kalman filtering model, and judging whether the flow monitored values at the corresponding moments are abnormal or not through the flow estimated values at all the moments; if the pressure monitoring value and the flow monitoring value are abnormal, judging that the data of the monitoring point is abnormal. The influence of historical monitoring data on pipe explosion judgment is fully considered; the calculation result of the flow estimation value can be more accurate by improving the optimized Kalman filtering model.
Description
Technical Field
The invention relates to the field of water supply monitoring, in particular to a rural water supply operation diagnosis method and system based on big data analysis.
Background
The existing pipe explosion analysis methods are various, but are often used for analysis and judgment according to the change of the pipeline pressure or flow monitoring value in a continuous period. Because the data reported by the monitoring equipment has errors or anomalies and is difficult to avoid, most of the prior methods do not consider the processing of the anomalies, few methods are simpler in processing the anomalies, and the methods of directly deleting the anomalies, zero-filling after deletion, normal data filling after deletion and the like are generally adopted, so that the trend of the data is influenced, and the accuracy of pipe explosion judgment is further reduced.
Moreover, the fluctuation of the monitoring value in a period of continuous time is large, the normal water change is easy to identify as the pipe explosion, and the pressure or the flow is not fully analyzed independently, so that a certain error is easy to cause the judgment and the positioning of the pipe explosion.
In addition, the pipeline can be aged and the like along with the use of the pipeline, so that the judging standard of the pipe explosion can be changed along with the use of the pipeline, and the judging standard of the pipe explosion and historical monitoring data have a direct relation; however, the conventional pipe explosion analysis method often does not consider the influence of the historical monitoring data on pipe explosion judgment, so that the pipe explosion judgment accuracy is not high.
Disclosure of Invention
In order to solve the technical problems, the invention provides a rural water supply operation diagnosis method based on big data analysis, which comprises the following steps:
s1: taking the flow data and the pressure data of the previous T days of the monitoring day as an original flow pressure data set, removing abnormal data in the original flow pressure data set, and obtaining a removed flow pressure data set;
s2: supplementing the removed flow pressure data set through an SARIMA model to obtain a flow pressure data set to be analyzed, dividing the flow pressure data set to be analyzed into flow pressure data sets at all times according to different times, and dividing the flow pressure data sets at all times into flow data sets at all times and pressure data sets at all times;
s3: calculating the pressure standard deviation of the pressure data set at each moment, and judging whether the pressure monitoring value at the corresponding moment is abnormal or not according to the pressure standard deviation at each moment;
s4: calculating the flow estimated value of the flow data set at each moment by the improved and optimized Kalman filtering model, and judging whether the flow monitored value at the corresponding moment is abnormal or not by the flow estimated value at each moment;
s5: if the pressure monitoring value and the flow monitoring value are abnormal, judging that the data of the monitoring points are abnormal, and bursting the pipe.
Preferably, step S1 specifically includes:
s11: obtaining the pipe diameter d of a water supply pipeline, wherein the unit of d is millimeter; the maximum monitoring value of the water flow speed of the water supply pipeline in the normal state is v, wherein the unit of v is m/s, m is m, and s is seconds; the abnormal flow value determination threshold value of the water supply pipeline is
The unit of the abnormal flow value judgment threshold value is m w/s;
s12: setting a pressure value abnormality judgment threshold;
s13: and eliminating the flow data larger than the flow value abnormality judgment threshold and the pressure data larger than the pressure value abnormality judgment threshold from the original flow pressure data set to obtain an eliminated flow pressure data set.
Preferably, step S2 specifically includes:
s21: supplementing the flow pressure data set after the elimination through an SARIMA model to obtain a flow pressure data set to be analyzed;
s22: dividing one day into U moments to obtain flow pressure data sets of the total U moments, wherein the flow pressure data sets of the moments are expressed as P t The method comprises the steps of carrying out a first treatment on the surface of the t is the number of the moment, the minimum value of t is 1, the maximum value of t is U, and U is a positive integer greater than 1;
s23: the flow data of the U moments of the flow pressure data set to be analyzed are put into the flow data sets of the corresponding moments, and the flow data sets of the moments are expressed as Z t The method comprises the steps of carrying out a first treatment on the surface of the The pressure data of the flow pressure data set to be analyzed at U times each day are put into the pressure data set at the corresponding time, and the pressure data set at each time is expressed as F t 。
Preferably, the step S3 specifically includes:
s31: acquiring a pressure dataset F at time t t The standard pressure difference at the time t is calculated and obtained, and the calculation formula is as follows:
wherein ,
the standard deviation of pressure at time T is the number of days, i has an initial value of 1 and a maximum value of T, and a larger value of i indicates a closer distance from the monitoring day, f t i For the pressure data in the pressure data set at time t of day i,
an average value of pressure data in the pressure data set at time t;
s32: the normal range of the pressure data is
；
S33: acquiring a pressure monitoring value f at the time of monitoring day t t now If f t now And judging that the pressure monitoring value is normal within the normal range of the pressure data, and otherwise, judging that the pressure monitoring value is abnormal.
Preferably, step S4 specifically includes:
s41: acquiring a flow data set Z at t moment t And a flow rate monitoring value z for monitoring time of day t t now ；
S42: the flow standard deviation at the time t is obtained through calculation, and the calculation formula is as follows:
wherein ,
the standard deviation of the flow at the time T is the number of days, i has an initial value of 1 and a maximum value of T, and a larger value of i indicates a closer distance from the monitoring day, z t i Number of flows at time t of day iFrom the data of the traffic in the set,
the average value of the flow data in the flow data set at the time t;
s43: and calculating and obtaining the Kalman gain at the t moment of the ith day through the improved and optimized Kalman filtering model, wherein the calculation formula is as follows:
wherein ,
in order to optimize the parameters of the device,
is the standard deviation multiple, Q is the process noise, R is the measurement noise,
for the kalman gain at time t of day i,
covariance is estimated for the posterior at time t of day i,
for a priori estimated covariance at time t of day i,
estimating covariance for a posterior at time t of day i-1;
s44: calculating to obtain a flow estimated value at the time t of the ith day, wherein the calculation formula is as follows:
wherein ,
as an estimated flow value at time t of the i-th day,
for a priori estimates of flow at time t of day i,
the estimated flow value is the estimated flow value at the time of the i-1 th day t;
let i=i+1;
s45: repeating the steps S43-S44 for T times to obtain the estimated flow value at the T time of the T day
If (if)
Judging the flow monitoring value as abnormal, otherwise judging the flow monitoring value as normal.
A rural water supply operation diagnostic system based on big data analysis, comprising:
the removing module is used for taking the flow data and the pressure data of the previous T days of the monitoring day as an original flow pressure data set, removing abnormal data in the original flow pressure data set, and obtaining a removed flow pressure data set;
the distribution module is used for supplementing the removed flow pressure data set through the SARIMA model to obtain a flow pressure data set to be analyzed, dividing the flow pressure data set to be analyzed into flow pressure data sets at all times according to different times, and dividing the flow pressure data sets at all times into flow data sets at all times and pressure data sets at all times;
the pressure monitoring value judging module is used for calculating the pressure standard deviation of the pressure data set at each moment and judging whether the pressure monitoring value at the corresponding moment is abnormal or not according to the pressure standard deviation at each moment;
the flow monitoring value judging module is used for calculating the flow estimated value of the flow data set at each moment through the improved optimized Kalman filtering model, and judging whether the flow monitoring value at the corresponding moment is abnormal or not through the flow estimated value at each moment;
and the pipe explosion diagnosis module is used for judging that the data of the monitoring points are abnormal and pipe explosion occurs if the pressure monitoring value and the flow monitoring value are abnormal.
The invention has the following beneficial effects:
1. predicting and supplementing the abnormal data removed from the monitoring value and the missing data which is not reported on time by using an SARIMA model, maintaining the change trend of the monitoring data and effectively reducing the influence of the abnormal data on the pipe explosion analysis;
2. the pipe explosion judgment analysis is carried out through the monitoring data of the previous T days of the monitoring day, the influence of the historical monitoring data on the pipe explosion judgment is fully considered, the influence of water fluctuation on the pipe explosion judgment can be effectively eliminated, and the accuracy of the pipe explosion judgment is effectively improved;
3. and (3) carrying out improvement optimization on the Kalman filtering model according to rural water supply characteristics, and enabling the calculation result of the flow estimation value to be more accurate through improving the optimized Kalman filtering model.
Drawings
FIG. 1 is a flow chart of a method according to an embodiment of the present invention;
FIG. 2 is a system architecture diagram of an embodiment of the present invention;
the achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Referring to fig. 1, the present invention provides a rural water supply operation diagnosis method based on big data analysis, comprising:
s1: taking the flow data and the pressure data of the previous T days of the monitoring day as an original flow pressure data set, removing abnormal data in the original flow pressure data set, and obtaining a removed flow pressure data set;
specifically, T is preferably set to 30 days, and the collection of the original flow pressure dataset does not include the day of monitoring, for example, the monitoring day is No. 2 of the month, and the flow data and the pressure data 30 days before No. 2 are taken;
s2: supplementing the removed flow pressure data set through an SARIMA model to obtain a flow pressure data set to be analyzed, dividing the flow pressure data set to be analyzed into flow pressure data sets at all times according to different times, and dividing the flow pressure data sets at all times into flow data sets at all times and pressure data sets at all times;
s3: calculating the pressure standard deviation of the pressure data set at each moment, and judging whether the pressure monitoring value at the corresponding moment is abnormal or not according to the pressure standard deviation at each moment;
s4: calculating the flow estimated value of the flow data set at each moment by the improved and optimized Kalman filtering model, and judging whether the flow monitored value at the corresponding moment is abnormal or not by the flow estimated value at each moment;
s5: if the pressure monitoring value and the flow monitoring value are abnormal, judging that the data of the monitoring points are abnormal, and bursting the pipe.
In step S1 of the embodiment, the flow data and the pressure data reported by the monitoring device often have problems of abnormal fluctuation, defect number and the like, and analysis and processing of the monitoring acquired data are required; for example, for the mutation of the monitoring value, whether the data reported by the equipment is caused by normal water fluctuation or not needs to be analyzed, if the data is abnormal, the normal water fluctuation is generally increased in a reasonable range and recovered in a section, the data has certain regularity, if the data reporting abnormality is generally irregular, the data mutation amplitude is overlarge and the data is likely to recover to be normal in the next reporting period, and the upper limit of the flow value of each pipeline can be calculated according to the pipe diameter of the pipeline; if abnormal values exist in the data used for pipe network operation diagnosis analysis, adverse effects are likely to be generated on the pipe explosion analysis result, so that the abnormal values in the original data need to be removed;
the step S1 specifically comprises the following steps:
s11: obtaining the pipe diameter d of a water supply pipeline, wherein the unit of d is millimeter; the maximum monitoring value of the water flow speed of the water supply pipeline in the normal state is v, wherein the unit of v is m/s, m is m, and s is seconds; the abnormal flow value determination threshold value of the water supply pipeline is
The unit of the abnormal flow value judgment threshold value is m w/s;
s12: setting a pressure value abnormality judgment threshold;
s13: and eliminating the flow data larger than the flow value abnormality judgment threshold and the pressure data larger than the pressure value abnormality judgment threshold from the original flow pressure data set to obtain an eliminated flow pressure data set.
In this embodiment, step S2 specifically includes:
s21: supplementing the flow pressure data set after the elimination through an SARIMA model to obtain a flow pressure data set to be analyzed;
specifically, the abnormal data removed from the monitoring value and the data which are not reported on time are supplemented by using a seasonal differential autoregressive moving average model (SARIMA);
the data removed by abnormality and the defect number caused by non-on-time report in the monitoring value are all required to be supplemented, the supplementing principle is that the original integral change trend of the data cannot be influenced, otherwise, the accuracy of pipe network pipe explosion analysis and judgment is influenced;
seasonal differential autoregressive moving average model (SARIMA) can be used for modeling a time series with periodicity by the following steps:
firstly, eliminating periodic variation by using a seasonal difference method, setting the variation period of a seasonal time sequence as s and the seasonal unit root as
Season differenceDivide u t =y t -y t-s T is the moment, and the seasonal difference operator is
, wherein Ls For lag operator, pair
The primary season difference is expressed as
For a non-stationary seasonal time series with D seasonal unit roots, D seasonal differences are needed to convert to a stationary series:
，
a P-th auto-regressive Q-th moving average seasonal time series model may be created for the variation period s:
, wherein AP （L s ) The middle is capitalized P, A P （L s ) For seasonal autoregressive operator, B Q (L s ) For the seasonal moving average operator, s is the length of a single seasonal period, P is the order of seasonal autoregressive, D is the order calculated by seasonal differences, Q is the order of seasonal moving average, u can be calculated t Described as
I.e.
； wherein 
The middle is the lower case p and,
as a non-seasonal autoregressive operator,
for non-seasonal moving average operator, v t White noise; p is the maximum order of non-seasonal autoregressions; q is the maximum order of the moving average operator; d is u t Is the first order difference times of (a). Due to
Thus, it is
；
The above formula is represented by SARIMA (P, D, Q) × (P, D, Q) s;
modeling is carried out on flow data and pressure data of a rural water supply network with seasonal periodicity through a seasonal differential autoregressive moving average model (SARIMA), so that missing data are predicted and supplemented, the change trend of flow and pressure can be reserved, and the influence of the missing data on water supply diagnosis is avoided;
s22: dividing one day into U moments to obtain flow pressure data sets of the total U moments, wherein the flow pressure data sets of the moments are expressed as P t The method comprises the steps of carrying out a first treatment on the surface of the t is the number of the moment, the minimum value of t is 1, the maximum value of t is U, and U is a positive integer greater than 1;
specifically, because the water consumption of the user has normal variation in different time periods of each day, corresponding fluctuation is generated in the flow data and the pressure data of the rural water supply network in the corresponding time periods of each day, if the flow data and the pressure data are directly analyzed, the normal water fluctuation and the fluctuation caused by pipe explosion are obviously distinguished, and the accuracy of pipe explosion analysis is easily affected; considering that the water consumption habits of users at the same time every day are generally consistent, the monitoring values at the same time every day are taken for comparison analysis, so that the interference of normal water fluctuation can be reduced, the flow pressure data set to be analyzed is divided, and the data reported at the same time every day are taken to form a new flow data set and a new pressure data set;
preferably, a day is divided into 24 time points, and each time point is separated by one hour;
s23: the flow data of the U moments of the flow pressure data set to be analyzed are put into the flow data sets of the corresponding moments, and the flow data sets of the moments are expressed as Z t The method comprises the steps of carrying out a first treatment on the surface of the The pressure data of the flow pressure data set to be analyzed at U times each day are put into the pressure data set at the corresponding time, and the pressure data set at each time is expressed as F t 。
In this embodiment, step S3 specifically includes:
s31: acquiring a pressure dataset F at time t t The standard pressure difference at the time t is calculated and obtained, and the calculation formula is as follows:
wherein ,
the standard deviation of pressure at time T is the number of days, i has an initial value of 1 and a maximum value of T, and a larger value of i indicates a closer distance from the monitoring day, f t i For the pressure data in the pressure data set at time t of day i,
an average value of pressure data in the pressure data set at time t;
specifically, for example, if the pressure monitoring value at 8 points on the monitoring day is abnormal, the value of t is 8;
s32: the normal range of the pressure data is
；
S33: acquiring a pressure monitoring value f at the time of monitoring day t t now If f t now Judging that the pressure monitoring value is normal within the normal range of the pressure data, otherwise judging that the pressure monitoring value is normalThe value is abnormal.
Kalman filtering (Kalman filtering) is a recursive predictive filtering algorithm, and calculates the optimal estimation at the current moment according to the current monitoring value, the model calculation result at the previous moment and noise, and simultaneously calculates the model result at the next moment, essentially, the result calculated by the model and the monitoring value reported by the equipment are weighted and averaged, and the optimal estimation is realized by continuous iteration; the Kalman filtering can be used in a dynamic system containing uncertain factors, so that the trend of the next step of the system is predicted according to the trend, and the Kalman filtering is commonly used in the fields of communication, navigation, guidance, control and the like, and has good effects in algorithms such as target tracking and the like;
if the original Kalman filtering method is directly used for pipe explosion diagnosis of the rural water supply network, the problems that parameters are difficult to set and the false alarm rate is high are caused mainly because the rural water supply has water fluctuation, and meanwhile, the measurement accuracy of the monitoring equipment per se can also have fluctuation; therefore, the invention improves and optimizes the Kalman filtering according to rural water supply characteristics, improves the weight updating equation when calculating the Kalman gain, and newly increases the optimization parameters
；
In this embodiment, step S4 specifically includes:
s41: acquiring a flow data set Z at t moment t And a flow rate monitoring value z for monitoring time of day t t now ；
S42: the flow standard deviation at the time t is obtained through calculation, and the calculation formula is as follows:
wherein ,
the standard deviation of the flow at the time T is the number of days, i has an initial value of 1 and a maximum value of T, and a larger value of i indicates a closer distance from the monitoring day, z t i For the traffic data in the traffic data set at time t of the i-th day,
the average value of the flow data in the flow data set at the time t;
s43: and calculating and obtaining the Kalman gain at the t moment of the ith day through the improved and optimized Kalman filtering model, wherein the calculation formula is as follows:
wherein ,
in order to optimize the parameters of the device,
is the multiple of the standard deviation,
taking an integer greater than 3, Q is process noise, R is measurement noise,
for the kalman gain at time t of day i,
covariance is estimated for the posterior at time t of day i,
for a priori estimated covariance at time t of day i,
estimating covariance for a posterior at time t of day i-1;
s44: calculating to obtain a flow estimated value at the time t of the ith day, wherein the calculation formula is as follows:
wherein ,
as an estimated flow value at time t of the i-th day,
for a priori estimates of flow at time t of day i,
the estimated flow value is the estimated flow value at the time of the i-1 th day t;
let i=i+1;
s45: repeating the steps S43-S44 for T times to obtain the estimated flow value at the T time of the T day
If (if)
Judging the flow monitoring value as abnormal, otherwise judging the flow monitoring value as normal.
Specifically, in performing the loop calculation of steps S43-S44, the initial parameters may be defined as follows,
=1，
=0, and the subsequent iteration according to kalman filtering can converge to the optimal value faster; for the setting of the process noise Q and the measurement noise R, the optimized parameters are newly increased due to the improved and optimized Kalman gain formula
Each calculation can jointly optimize the calculation result of the Kalman gain based on the monitoring value and the historical monitoring value, so that positive influence is generated on Kalman optimal estimation, the values of the process noise Q and the measurement noise R can be taken as empirical values Q=0.1, R=0.05, and the parameters of Q and R can be adjusted according to the calculation result.
Referring to fig. 2, the present invention provides a rural water supply operation diagnosis system based on big data analysis, comprising:
the removing module is used for taking the flow data and the pressure data of the previous T days of the monitoring day as an original flow pressure data set, removing abnormal data in the original flow pressure data set, and obtaining a removed flow pressure data set;
the distribution module is used for supplementing the removed flow pressure data set through the SARIMA model to obtain a flow pressure data set to be analyzed, dividing the flow pressure data set to be analyzed into flow pressure data sets at all times according to different times, and dividing the flow pressure data sets at all times into flow data sets at all times and pressure data sets at all times;
the pressure monitoring value judging module is used for calculating the pressure standard deviation of the pressure data set at each moment and judging whether the pressure monitoring value at the corresponding moment is abnormal or not according to the pressure standard deviation at each moment;
the flow monitoring value judging module is used for calculating the flow estimated value of the flow data set at each moment through the improved optimized Kalman filtering model, and judging whether the flow monitoring value at the corresponding moment is abnormal or not through the flow estimated value at each moment;
and the pipe explosion diagnosis module is used for judging that the data of the monitoring points are abnormal and pipe explosion occurs if the pressure monitoring value and the flow monitoring value are abnormal.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the terms first, second, third, etc. do not denote any order, but rather the terms first, second, third, etc. are used to interpret the terms as labels.
The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.
Claims (5)
1. A rural water supply operation diagnosis method based on big data analysis, comprising:
s1: taking the flow data and the pressure data of the previous T days of the monitoring day as an original flow pressure data set, removing abnormal data in the original flow pressure data set, and obtaining a removed flow pressure data set;
s2: supplementing the removed flow pressure data set through an SARIMA model to obtain a flow pressure data set to be analyzed, dividing the flow pressure data set to be analyzed into flow pressure data sets at all times according to different times, and dividing the flow pressure data sets at all times into flow data sets at all times and pressure data sets at all times;
s3: calculating the pressure standard deviation of the pressure data set at each moment, and judging whether the pressure monitoring value at the corresponding moment is abnormal or not according to the pressure standard deviation at each moment;
s4: calculating the flow estimated value of the flow data set at each moment by the improved and optimized Kalman filtering model, and judging whether the flow monitored value at the corresponding moment is abnormal or not by the flow estimated value at each moment;
s5: if the pressure monitoring value and the flow monitoring value are abnormal, judging that the data of the monitoring point is abnormal, and bursting the pipe;
the step S4 specifically comprises the following steps:
s41: acquiring a flow data set Z at t moment t And a flow rate monitoring value z for monitoring time of day t t now ；
S42: the flow standard deviation at the time t is obtained through calculation, and the calculation formula is as follows:
wherein ,
the standard deviation of the flow at the time T is the number of days, i has an initial value of 1 and a maximum value of T, and a larger value of i indicates a closer distance from the monitoring day, z t i For the flow data in the flow data set at time t of day i,/>
The average value of the flow data in the flow data set at the time t;
s43: and calculating and obtaining the Kalman gain at the t moment of the ith day through the improved and optimized Kalman filtering model, wherein the calculation formula is as follows:
wherein ,
to optimize the parameters +.>
Q is process noise, R is measurement noise, < >>
Kalman gain at time t of day i, < >>
Estimating covariance for a posterior at time t of day i,>
for a priori estimated covariance at time t of day i,/->
Estimating covariance for a posterior at time t of day i-1;
s44: calculating to obtain a flow estimated value at the time t of the ith day, wherein the calculation formula is as follows:
wherein ,
for the estimated flow value at time t of day i, < >>
For a priori estimates of flow at time t of day i,
the estimated flow value is the estimated flow value at the time of the i-1 th day t;
let i=i+1;
s45: repeating the steps S43-S44 for T times to obtain the estimated flow value at the T time of the T day
If (if)
Judging the flow monitoring value as abnormal, otherwise judging the flow monitoring value as normal.
2. The rural water supply operation diagnosis method based on big data analysis according to claim 1, wherein step S1 specifically comprises:
s11: obtaining the pipe diameter d of a water supply pipeline, wherein the unit of d is millimeter; the maximum monitoring value of the water flow speed of the water supply pipeline in the normal state is v, wherein the unit of v is m/s, m is m, and s is seconds; the abnormal flow value determination threshold value of the water supply pipeline is
The unit of the abnormal flow value judgment threshold value is m w/s;
s12: setting a pressure value abnormality judgment threshold;
s13: and eliminating the flow data larger than the flow value abnormality judgment threshold and the pressure data larger than the pressure value abnormality judgment threshold from the original flow pressure data set to obtain an eliminated flow pressure data set.
3. The rural water supply operation diagnosis method based on big data analysis according to claim 1, wherein step S2 is specifically:
s21: supplementing the flow pressure data set after the elimination through an SARIMA model to obtain a flow pressure data set to be analyzed;
s22: dividing one day into U moments to obtain flow pressure data sets of the total U moments, wherein the flow pressure data sets of the moments are expressed as P t The method comprises the steps of carrying out a first treatment on the surface of the t is the number of the moment, the minimum value of t is 1, the maximum value of t is U, and U is a positive integer greater than 1;
s23: the flow data of the U moments of the flow pressure data set to be analyzed are put into the flow data sets of the corresponding moments, and the flow data sets of the moments are expressed as Z t The method comprises the steps of carrying out a first treatment on the surface of the Dividing the materials to be separatedThe pressure data of U times each day in the flow analysis pressure data set are put into the pressure data set of the corresponding time, and the pressure data set of each time is expressed as F t 。
4. The rural water supply operation diagnosis method based on big data analysis according to claim 1, wherein step S3 is specifically:
s31: acquiring a pressure dataset F at time t t The standard pressure difference at the time t is calculated and obtained, and the calculation formula is as follows:
wherein ,
the standard deviation of pressure at time T is the number of days, i has an initial value of 1 and a maximum value of T, and a larger value of i indicates a closer distance from the monitoring day, f t i For the pressure data in the pressure data set at time t of day i,/v>
An average value of pressure data in the pressure data set at time t;
s32: the normal range of the pressure data is
；
S33: acquiring a pressure monitoring value f at the time of monitoring day t t now If f t now And judging that the pressure monitoring value is normal within the normal range of the pressure data, and otherwise, judging that the pressure monitoring value is abnormal.
5. A rural water supply operation diagnostic system based on big data analysis, comprising:
the removing module is used for taking the flow data and the pressure data of the previous T days of the monitoring day as an original flow pressure data set, removing abnormal data in the original flow pressure data set, and obtaining a removed flow pressure data set;
the distribution module is used for supplementing the removed flow pressure data set through the SARIMA model to obtain a flow pressure data set to be analyzed, dividing the flow pressure data set to be analyzed into flow pressure data sets at all times according to different times, and dividing the flow pressure data sets at all times into flow data sets at all times and pressure data sets at all times;
the pressure monitoring value judging module is used for calculating the pressure standard deviation of the pressure data set at each moment and judging whether the pressure monitoring value at the corresponding moment is abnormal or not according to the pressure standard deviation at each moment;
the flow monitoring value judging module is used for calculating the flow estimated value of the flow data set at each moment through the improved optimized Kalman filtering model, and judging whether the flow monitoring value at the corresponding moment is abnormal or not through the flow estimated value at each moment;
the pipe explosion diagnosis module judges that the data of the monitoring points are abnormal and pipe explosion occurs if the pressure monitoring value and the flow monitoring value are abnormal;
the workflow of the flow monitoring value judging module is specifically as follows:
s41: acquiring a flow data set Z at t moment t And a flow rate monitoring value z for monitoring time of day t t now ；
S42: the flow standard deviation at the time t is obtained through calculation, and the calculation formula is as follows:
wherein ,
the standard deviation of the flow at the time T is the number of days, i has an initial value of 1 and a maximum value of T, and a larger value of i indicates a closer distance from the monitoring day, z t i For the flow in the flow data set at time t of the ith dayData,/->
The average value of the flow data in the flow data set at the time t;
s43: and calculating and obtaining the Kalman gain at the t moment of the ith day through the improved and optimized Kalman filtering model, wherein the calculation formula is as follows:
wherein ,
to optimize the parameters +.>
Q is process noise, R is measurement noise, < >>
Kalman gain at time t of day i, < >>
Estimating covariance for a posterior at time t of day i,>
for a priori estimated covariance at time t of day i,/->
Estimating covariance for a posterior at time t of day i-1;
s44: calculating to obtain a flow estimated value at the time t of the ith day, wherein the calculation formula is as follows:
wherein ,
for the estimated flow value at time t of day i, < >>
For a priori estimates of flow at time t of day i,
the estimated flow value is the estimated flow value at the time of the i-1 th day t;
let i=i+1;
s45: repeating the steps S43-S44 for T times to obtain the estimated flow value at the T time of the T day
If (if)
Judging the flow monitoring value as abnormal, otherwise judging the flow monitoring value as normal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310015617.XA CN115931055B (en) | 2023-01-06 | 2023-01-06 | Rural water supply operation diagnosis method and system based on big data analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310015617.XA CN115931055B (en) | 2023-01-06 | 2023-01-06 | Rural water supply operation diagnosis method and system based on big data analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115931055A CN115931055A (en) | 2023-04-07 |
| CN115931055B true CN115931055B (en) | 2023-06-16 |
Family
ID=86649240
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310015617.XA Active CN115931055B (en) | 2023-01-06 | 2023-01-06 | Rural water supply operation diagnosis method and system based on big data analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115931055B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116541678B (en) * | 2023-06-30 | 2023-10-31 | 深圳市秒加能源科技有限公司 | Pressure monitoring method and device for gas station safety pipeline |
| CN116593065B (en) * | 2023-07-14 | 2023-09-15 | 青岛义龙包装机械有限公司 | Data analysis method of bag type packaging machine detection platform |
| CN116804412B (en) * | 2023-08-22 | 2023-12-01 | 济宁鲁威液压科技股份有限公司 | Monitoring data processing method of hydraulic system |
| CN117272216B (en) * | 2023-11-22 | 2024-02-09 | 中国建材检验认证集团湖南有限公司 | Data analysis method for automatic flow monitoring station and manual water gauge observation station |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112187528A (en) * | 2020-09-15 | 2021-01-05 | 浙江大学 | Industrial control system communication flow online monitoring method based on SARIMA |
| CN113065721A (en) * | 2021-05-06 | 2021-07-02 | 清华大学 | Method, device, equipment and medium for graded early warning of leakage events of community water supply network |
| CN113868926A (en) * | 2021-10-15 | 2021-12-31 | 常州大学 | Method for constructing spatial distribution model of water quality parameters of culture pond |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040102937A1 (en) * | 2002-11-21 | 2004-05-27 | Honeywell International Inc. | Energy forecasting using model parameter estimation |
| KR101549543B1 (en) * | 2014-04-29 | 2015-09-07 | 충북대학교 산학협력단 | A power state diagnosis method using kalman estimation process and measuring the relative probability by the metric defined by functional mapping |
| CN106017582A (en) * | 2016-05-06 | 2016-10-12 | 中南大学 | A pitot tube flow measuring method based on the tube diameter dichotomy principle |
| CN111373336B (en) * | 2017-11-25 | 2022-03-29 | 华为技术有限公司 | State awareness method and related equipment |
| CN108226887B (en) * | 2018-01-23 | 2021-06-01 | 哈尔滨工程大学 | Water surface target rescue state estimation method under condition of transient observation loss |
| CN108360608B (en) * | 2018-03-21 | 2020-05-08 | 浙江大学 | Pipe burst identification and positioning method for water delivery pipe of water supply system |
| CN110672328B (en) * | 2019-11-05 | 2020-08-14 | 大连理工大学 | Turbofan engine health parameter estimation method based on random configuration network |
| CN114021836B (en) * | 2021-11-16 | 2023-05-16 | 电子科技大学 | Multi-variable reservoir water inflow prediction system based on different angle fusion, training method and application |
| CN114444290A (en) * | 2022-01-20 | 2022-05-06 | 天津智云水务科技有限公司 | Method and system for automatically generating pressure and flow monitoring threshold of water supply system |
-
2023
- 2023-01-06 CN CN202310015617.XA patent/CN115931055B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112187528A (en) * | 2020-09-15 | 2021-01-05 | 浙江大学 | Industrial control system communication flow online monitoring method based on SARIMA |
| CN113065721A (en) * | 2021-05-06 | 2021-07-02 | 清华大学 | Method, device, equipment and medium for graded early warning of leakage events of community water supply network |
| CN113868926A (en) * | 2021-10-15 | 2021-12-31 | 常州大学 | Method for constructing spatial distribution model of water quality parameters of culture pond |
Non-Patent Citations (2)
| Title |
|---|
| 水利智能物联感知平台的设计与实现;张恒飞等;水利水电快报;第43卷(第8期);118-121 * |
| 考虑预报偏差的迭代式集合卡尔曼滤波在地下水水流数据同化中的应用;杨运等;水文地质工程地质;第49卷(第6期);13-23 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115931055A (en) | 2023-04-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115931055B (en) | Rural water supply operation diagnosis method and system based on big data analysis | |
| CN108805202B (en) | Machine learning method for electrolytic bath fault early warning and application thereof | |
| CN107610464A (en) | A kind of trajectory predictions method based on Gaussian Mixture time series models | |
| WO2019080367A1 (en) | Method for evaluating health status of mechanical device | |
| AU2015293548B9 (en) | Method for detecting anomalies in a distribution network, in particular for drinking water | |
| CN113435725B (en) | Power grid host dynamic threshold setting method based on FARIMA-LSTM prediction | |
| CN111695290B (en) | Short-term runoff intelligent forecasting mixed model method suitable for changing environment | |
| EP1468361A1 (en) | Method and system for analyzing and predicting the behavior of systems | |
| CN105208040A (en) | Network attack detection method and device | |
| CN114446033A (en) | Dynamic alarm threshold value determination method | |
| WO2016039805A1 (en) | Apparatus and method for ensembles of kernel regression models | |
| CN115412455A (en) | Server multi-performance index abnormity detection method and device based on time sequence | |
| CN116976857B (en) | Predictive maintenance method and system for railway power equipment based on deep learning | |
| CN112504357B (en) | Method and system for dynamically analyzing river channel overflowing capacity | |
| Alferes et al. | Efficient automated quality assessment: Dealing with faulty on-line water quality sensors | |
| CN113743531A (en) | Equipment working condition early warning method and related device | |
| CN113158448A (en) | Self-adaptive calculation method for equipment threshold of ship system | |
| Masngut et al. | Comparison of daily rainfall forecasting using multilayer perceptron neural network model | |
| CN115794805A (en) | Medium-low voltage distribution network measurement data supplementing method | |
| CN113626978A (en) | On-line prediction method and system for detonation velocity of civil explosive emulsion explosive | |
| CN117439827B (en) | Network flow big data analysis method | |
| JP2020149259A (en) | Abnormality diagnostic device | |
| Yang et al. | Root Cause Location Based on Prophet and Kernel Density Estimation | |
| EP4276627A1 (en) | Iterative method for monitoring a computing device | |
| CN117725843B (en) | House structure deformation prediction method based on deep learning |
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 |