Sewage overflow prediction method for municipal drainage system

Abstract

The invention discloses a sewage overflow prediction method for a municipal drainage system, and belongs to the technical field of municipal drainage, the drainage system comprises a plurality of drain outlets, and the prediction method comprises the following steps: obtaining historical rainfall information and drainage system information; dividing meteorological grids according to the positions of the meteorological stations; according to the rainfall information, obtaining a plurality of rainfall characteristics when a rainfall event occurs in each meteorological grid; determining an optimal rainfall prediction factor when an overflow event occurs at each drain outlet; acquiring a sewage overflow rainfall threshold value corresponding to the optimal rainfall prediction factor when an overflow event occurs at each sewage draining exit; on the basis of the sewage overflow rainfall threshold value of each sewage draining exit and the rainfall forecast data of the meteorological grid where the sewage draining exit is located, predicting whether each sewage draining exit overflows or not; the prediction method is simple, convenient and effective, data are easy to obtain, and the prediction method has high practicability and applicability.

Description

Technical Field

[0001] The invention belongs to the technical field of municipal drainage, and in particular relates to a sewage overflow prediction method for a municipal drainage system. Background Art

[0002] During rainfall, untreated overflow sewage from drainage systems may be discharged into natural water bodies, exacerbating water pollution problems. At present, whether and when sewage overflow will occur is mostly determined by experience, on-site observation, or flow and water level monitoring. The simple on-site monitoring method consumes a lot of manpower and material resources, and cannot predict the occurrence of sewage overflow.

[0003] Drainage network modeling is currently being used to predict the impact of climate change on drainage systems, but numerical simulations are based on a large amount of data and require long-term debugging and operation, which will affect the progress of sewage overflow prevention and treatment. Summary of the invention

[0004] The purpose of the present invention is to overcome the deficiencies in the prior art and to provide a method for predicting sewage overflow in a municipal drainage system, which is simple, effective and highly applicable.

[0005] The present invention provides the following technical solutions:

[0006] A method for predicting sewage overflow in a municipal drainage system, wherein the drainage system comprises a plurality of sewage outlets, and the prediction method comprises:

[0007] Acquire historical rainfall information and drainage system information; the drainage system information includes the location of each sewage outlet and overflow data when an overflow event occurs at each sewage outlet;

[0008] Divide the meteorological grid according to the location of the meteorological stations;

[0009] According to the rainfall information, for each meteorological grid, multiple rainfall characteristics when a rainfall event occurs are obtained;

[0010] Based on the overflow data of each sewage outlet when the overflow event occurs and multiple rainfall characteristics when the rainfall event occurs in the meteorological grid where the sewage outlet is located, the optimal rainfall prediction factor when the overflow event occurs at each sewage outlet is determined;

[0011] Obtain the sewage overflow rainfall threshold corresponding to the best rainfall prediction factor when an overflow event occurs at each sewage outlet;

[0012] Based on the sewage overflow rainfall threshold of each sewage outlet and the rainfall forecast data of the meteorological grid where the sewage outlet is located, it is predicted whether overflow will occur at each sewage outlet.

[0013] Optionally, the overflow data when an overflow event occurs at each sewage outlet includes the start time, end time and overflow flow rate of each sewage outlet when the overflow occurs;

[0014] The rainfall information includes hourly rainfall at each weather station.

[0015] Optionally, in dividing the meteorological grids according to the locations of the meteorological stations, the meteorological grids are determined using the Thiessen polygon method, and each meteorological grid includes a unique meteorological station.

[0016] Optionally, the step of obtaining, for each meteorological grid according to the rainfall information, a plurality of rainfall characteristics when a rainfall event occurs therein includes:

[0017] According to the rainfall information, all rainfall events of each meteorological grid are identified; the conditions for identifying a rainfall event are: a rainfall period with a rainfall intensity of less than 0.2 mm / hour for 12 consecutive hours or a rainfall of 0 for 2 consecutive hours;

[0018] Based on the identified rainfall event, a plurality of rainfall features of the rainfall event are obtained.

[0019] Optionally, the method of determining the best rainfall prediction factor when an overflow event occurs at each sewage outlet based on the overflow data when the overflow event occurs at each sewage outlet and the multiple rainfall characteristics when a rainfall event occurs at the meteorological grid where the sewage outlet is located, comprises:

[0020] Match the overflow events of the sewage outlets with the rainfall events of the meteorological grid where the sewage outlets are located, and construct a data set of the sewage outlets; the data set of the sewage outlets includes the overflow data of each overflow event of all sewage outlets, and the rainfall characteristic data corresponding to each rainfall event of the meteorological grid where the sewage outlets are located;

[0021] Based on the data set of sewage outlets, for each sewage outlet, the overflow event rate is respectively analyzed with multiple rainfall characteristics, and the odds ratio corresponding to each rainfall characteristic is determined respectively; the multiple rainfall characteristics include rainfall depth, maximum rainfall intensity, average rainfall intensity and rainfall duration;

[0022] The odds ratios corresponding to all rainfall characteristics are compared, and the rainfall characteristic corresponding to the maximum odds ratio is determined as the best rainfall prediction factor for the current sewage outlet.

[0023] Optionally, the overflow event of the sewage outlet is matched with the rainfall event of the meteorological grid where the sewage outlet is located, and a data set of the sewage outlet is constructed.

[0024] The overflow event of the sewage outlet is related to all rainfall events within 48 hours before the overflow occurs. If the overflow event of the sewage outlet is only related to one rainfall event, the related rainfall event is matched with the overflow event. If the overflow event of the sewage outlet is related to multiple rainfall events, one rainfall event is selected according to the set rules to match the overflow event;

[0025] If the overflow event of the sewage outlet is related to multiple rainfall events, a rainfall event is selected according to a set rule to match the overflow event, including the following steps:

[0026] E1: Compare the rainfall depths P of all relevant rainfall events. If there is only one rainfall event corresponding to the maximum rainfall depth P, stop selecting rainfall events, and match the rainfall event corresponding to the maximum rainfall depth P with the overflow event of the sewage outlet. If there is more than one rainfall event corresponding to the maximum rainfall depth P, proceed to step E2;

[0027] E2: Compare the average rainfall intensity of all relevant rainfall events I ave , if the average rainfall intensity I ave If there is only one rainfall event corresponding to the maximum value, stop selecting rainfall events and set the average rainfall intensity I ave The rainfall event corresponding to the maximum value is matched with the overflow event of the sewage outlet. If the average rainfall intensity I ave If there is more than one rainfall event corresponding to the maximum value, then go to step E3;

[0028] E3: Compare the maximum rainfall intensity of all relevant rainfall events I max , if the maximum rainfall intensity I max If there is only one rainfall event corresponding to the maximum value, stop selecting rainfall events and set the maximum rainfall intensity I max The rainfall event corresponding to the maximum value is matched with the overflow event of the sewage outlet. If the maximum rainfall intensity I max If there is more than one rainfall event corresponding to the maximum value, then go to step E4;

[0029] E4: Compare the rainfall duration D of all relevant rainfall events. If there is only one rainfall event corresponding to the maximum rainfall duration D, stop selecting rainfall events and match the rainfall event corresponding to the maximum rainfall duration D with the overflow event of the sewage outlet. If there is more than one rainfall event corresponding to the maximum rainfall duration D, arbitrarily select one of the rainfall events corresponding to the maximum rainfall duration D to match the overflow event of the sewage outlet.

[0030] Optionally, the odds ratio OR is the ratio of the probability of a sewage overflow event to the probability of no sewage overflow event; the formula of the odds ratio OR is:

[0031]

[0032] Among them, p1 is the probability of sewage overflow incident at the sewage outlet, and p2 is the probability of no sewage overflow incident at the sewage outlet.

[0033] Optionally, in the step of obtaining the sewage overflow rainfall threshold corresponding to the best rainfall prediction factor when an overflow event occurs at each sewage outlet,

[0034] Obtain the Logistic curve corresponding to the best prediction factor of the sewage outlet;

[0035] The value of the rainfall characteristic corresponding to the sewage overflow event rate of 1 is the sewage overflow rainfall threshold.

[0036] Optionally, the predicting whether overflow occurs at each sewage outlet based on the sewage overflow rainfall threshold of each sewage outlet and the rainfall forecast data of the meteorological grid where the sewage outlet is located includes:

[0037] If the sewage overflow rainfall threshold of the sewage outlet is greater than or equal to the rainfall forecast data of the meteorological grid where the sewage outlet is located, no sewage overflow event will occur at the sewage outlet;

[0038] If the sewage overflow rainfall threshold of the sewage outlet is less than the rainfall forecast data of the meteorological grid where the sewage outlet is located, a sewage overflow event will occur at the sewage outlet;

[0039] The rainfall forecast data includes forecast values ​​of multiple rainfall characteristics.

[0040] Compared with the prior art, the present invention has the following beneficial effects:

[0041] The present invention determines the optimal rainfall prediction factor when overflow occurs at each sewage outlet based on the meteorological grid where the sewage outlet is located and the rainfall characteristics of rainfall events in the meteorological grid, and predicts sewage overflow according to the sewage overflow rainfall threshold corresponding to the optimal rainfall prediction factor. The present invention has different optimal rainfall prediction factors for each sewage outlet, and the corresponding sewage overflow rainfall threshold is also different. Therefore, sewage overflow prediction can be carried out for each sewage outlet in a targeted manner. The present invention is simple and effective, and the data is easy to obtain. It can be applicable to sewage overflow control of all drainage systems, thereby providing strong support for formulating more scientific drainage plans, and has strong practicality and applicability. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 It is a schematic flow chart of the steps of the method for predicting sewage overflow of a municipal drainage system of the present invention;

[0043] Figure 2 It is a specific example of the Logistic curve corresponding to the rainfall depth P given by the present invention;

[0044] Figure 3 It is an operation flow chart of the sewage overflow prediction method of the municipal drainage system according to the second embodiment of the present invention. DETAILED DESCRIPTION

[0045] The present invention will be further described below in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and cannot be used to limit the protection scope of the present invention.

[0046] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0047] Embodiment 1

[0048] like Figure 1 As shown, a sewage overflow prediction method for a municipal drainage system, the drainage system includes a plurality of sewage outlets, and the prediction method includes the following steps:

[0049] S1: Acquire historical rainfall information and drainage system information; the drainage system information includes the location of each sewage outlet and the overflow data when an overflow event occurs at each sewage outlet.

[0050] The rainfall information includes the hourly rainfall at each weather station; the overflow data when an overflow event occurs at each sewage outlet includes the start time, end time and overflow flow rate of each sewage outlet when the overflow occurs.

[0051] When obtaining the location of each sewage outlet, the number of sewage outlets is also counted.

[0052] S2: Divide the meteorological grid according to the location of the meteorological stations.

[0053] The Thiessen polygon method is used to determine the meteorological grid. Each meteorological grid includes a unique meteorological station. The rainfall information of the meteorological station is the rainfall information of the meteorological grid. That is, assuming that there are M meteorological stations in total, M meteorological grids are determined.

[0054] S3: According to the rainfall information, for each meteorological grid, multiple rainfall characteristics when a rainfall event occurs are obtained.

[0055] Specifically, S31: identifying all rainfall events of each meteorological grid according to rainfall information; wherein the conditions for identifying a rainfall event are: a rainfall period in which the rainfall intensity is less than 0.2 mm / hour for 12 consecutive hours or the rainfall is 0 for 2 consecutive hours.

[0056] Assume that the i-th meteorological grid (i=1,2,…,M) determines N i rainfall events;

[0057] M meteorological grids, a total of A rainfall event.

[0058] S32: Based on the identified rainfall event, a plurality of rainfall features of the rainfall event are obtained.

[0059] Multiple rainfall characteristics include rainfall depth, maximum rainfall intensity, average rainfall intensity, and rainfall duration.

[0060] Get data on rainfall characteristics for each rainfall event for all meteorological grids.

[0061] The rainfall feature dataset corresponding to the rainfall event of the i-th meteorological grid contains at least data.

[0062] S4: Based on the overflow data of each sewage outlet when an overflow event occurs and multiple rainfall characteristics when a rainfall event occurs in the meteorological grid where the sewage outlet is located, determine the optimal rainfall prediction factor when an overflow event occurs at each sewage outlet.

[0063] Specifically, S41: matching the overflow event of the sewage outlet with the rainfall event of the meteorological grid where the sewage outlet is located, and constructing a data set of the sewage outlet.

[0064] Overflow events at the outfall are correlated with all rainfall events within 48 hours before the overflow.

[0065] If the overflow event of the sewage outlet is only related to one rainfall event, the related rainfall event is matched with the overflow event. If the overflow event of the sewage outlet is related to multiple rainfall events, a rainfall event is selected according to the set rules to match the overflow event.

[0066] If the overflow event of the sewage outlet is related to multiple rainfall events, a rainfall event is selected according to a set rule to match the overflow event, including the following steps:

[0067] E1: Compare the rainfall depths P of all relevant rainfall events. If there is only one rainfall event corresponding to the maximum rainfall depth P, stop selecting rainfall events, and match the rainfall event corresponding to the maximum rainfall depth P with the overflow event of the sewage outlet. If there is more than one rainfall event corresponding to the maximum rainfall depth P, proceed to step E2;

[0068] E2: Compare the average rainfall intensity of all relevant rainfall events I ave , if the average rainfall intensity I ave If there is only one rainfall event corresponding to the maximum value, stop selecting rainfall events and set the average rainfall intensity I ave The rainfall event corresponding to the maximum value is matched with the overflow event of the sewage outlet. If the average rainfall intensity I ave If there is more than one rainfall event corresponding to the maximum value, then go to step E3;

[0069] E3: Compare the maximum rainfall intensity of all relevant rainfall events I max , if the maximum rainfall intensity I max If there is only one rainfall event corresponding to the maximum value, stop selecting rainfall events and set the maximum rainfall intensity I max The rainfall event corresponding to the maximum value is matched with the overflow event of the sewage outlet. If the maximum rainfall intensity I max If there is more than one rainfall event corresponding to the maximum value, then go to step E4;

[0070] E4: Compare the rainfall duration D of all relevant rainfall events. If there is only one rainfall event corresponding to the maximum rainfall duration D, stop selecting rainfall events and match the rainfall event corresponding to the maximum rainfall duration D with the overflow event of the sewage outlet. If there is more than one rainfall event corresponding to the maximum rainfall duration D, arbitrarily select one of the rainfall events corresponding to the maximum rainfall duration D to match the overflow event of the sewage outlet.

[0071] It is worth noting that if the selection of rainfall events stops in step E1, the operations of steps E2 to E4 will not be performed. Similarly, if the selection of rainfall events stops in step E2, the operations of steps E3 to E4 will not be performed. If the selection of rainfall events stops in step E3, the operation of step E4 will not be performed.

[0072] That is to say, for the overflow event of the sewage outlet, all relevant rainfall events are calculated according to the rainfall depth P, the average rainfall intensity I ave , Maximum rainfall intensity I max The rainfall events and overflow events are matched according to the priority order of rainfall duration D.

[0073] The dataset of sewage outlets includes the overflow data of each overflow event of all sewage outlets, and the rainfall characteristic data corresponding to each rainfall event in the meteorological grid where the sewage outlets are located.

[0074] Assume that the i-th meteorological grid (i=1,2,…,M) has K i There are sewage outlets, and each sewage outlet has G ij Sewage overflow event (i=1,2,…,M;j=1,2,…,W;W≤N i );

[0075] M meteorological grids, a total of sewage outlets, a total of A sewage overflow incident.

[0076] S42: Based on the data set of sewage outlets, for each sewage outlet, the overflow event rate of the sewage outlet is respectively analyzed with multiple rainfall characteristics, and the odds ratio corresponding to each rainfall characteristic is determined respectively.

[0077] For a single sewage outlet, if a sewage overflow event occurs in a single rainfall event, the sewage overflow event rate is recorded as 1; if no sewage overflow event occurs, the sewage overflow event rate is recorded as 0.

[0078] The overflow event rate of the sewage outlet q is respectively related to the rainfall depth P, the maximum rainfall intensity I max , average rainfall intensity I ave and rainfall duration D, and logistic regression analysis was performed to obtain the logistic curve corresponding to rainfall depth P, the maximum rainfall intensity I max Corresponding Logistic curve, average rainfall intensity I ave The corresponding Logistic curve and the Logistic curve corresponding to the rainfall duration D are obtained, and the odds ratios OR1, OR2, OR3, and OR4 corresponding to each rainfall feature are determined respectively.

[0079] It is worth noting that the horizontal axis x of the Logistic curve is the rainfall characteristics, and the vertical axis y is the incidence rate of sewage outlet overflow events.

[0080] S43: Compare the odds ratios corresponding to all rainfall features, and determine the rainfall feature corresponding to the maximum odds ratio as the optimal rainfall prediction factor for the current sewage outlet q.

[0081] For each sewage outlet, the odds ratios corresponding to all rainfall characteristics determined in step S42 are compared, and the rainfall characteristic corresponding to the largest odds ratio is determined as the optimal rainfall prediction factor for the sewage outlet. That is, if the odds ratio OR1 corresponding to the rainfall depth P is greater than the odds ratios OR2, OR3, and OR4 corresponding to the other three rainfall characteristics, then the rainfall depth P is the optimal rainfall prediction factor for the current sewage outlet q.

[0082] The best rainfall predictors are different for each outfall.

[0083] Specifically, the odds ratio OR is the ratio of the probability of a sewage overflow event to the probability of no sewage overflow event; the formula of the odds ratio OR is:

[0084]

[0085] Among them, p1 is the probability of sewage overflow incident at the sewage outlet, and p2 is the probability of no sewage overflow incident at the sewage outlet.

[0086] If OR>1, it means that the rainfall event is positively correlated with the sewage overflow event; if OR=1, it means that the rainfall event is unrelated to the sewage overflow event; if OR<1, it means that the rainfall event is negatively correlated with the sewage overflow event.

[0087] S5: Obtain the sewage overflow rainfall threshold corresponding to the best rainfall prediction factor when an overflow event occurs at each sewage outlet.

[0088] S51: Obtain the Logistic curve corresponding to the best prediction factor of the sewage outlet.

[0089] If the best prediction factor is the rainfall depth P, the Logistic curve of the overflow event rate and rainfall depth P of the sewage outlet q is obtained.

[0090] S52: The value of the rainfall characteristic corresponding to the sewage overflow event rate of 1 is the sewage overflow rainfall threshold.

[0091] like Figure 2 As shown, in the Logistic curve of the overflow event rate of the sewage outlet q and the rainfall depth P, the horizontal axis x is the rainfall depth P, and the vertical axis y is the overflow event rate of the sewage outlet. The horizontal axis value corresponding to the intersection of the Logistic curve of the overflow event rate of the sewage outlet q and the rainfall depth P with y=1 is the sewage overflow rainfall threshold.

[0092] S6: Based on the sewage overflow rainfall threshold of each sewage outlet and the rainfall forecast data of the meteorological grid where the sewage outlet is located, predict whether overflow will occur at each sewage outlet.

[0093] If the sewage overflow rainfall threshold of sewage outlet q is greater than or equal to the rainfall forecast data of the meteorological grid where sewage outlet q is located, then sewage overflow event will not occur at sewage outlet q;

[0094] If the sewage overflow rainfall threshold of sewage outlet q is less than the rainfall forecast data of the meteorological grid where sewage outlet q is located, a sewage overflow event will occur at sewage outlet q;

[0095] The rainfall forecast data includes forecast values ​​of multiple rainfall characteristics.

[0096] As a specific example, the rainfall threshold for sewage overflow at sewage outlet q is a rainfall depth of 71.2 mm. If the rainfall forecast data of the meteorological grid where sewage outlet q is located shows a rainfall depth of 90 mm, overflow will occur at sewage outlet q.

[0097] Embodiment 2

[0098] like Figure 3 As shown in the figure, taking a drainage system in a certain area as an example, the steps to predict whether overflow occurs at the sewage outlet are as follows:

[0099] (1) Data collection

[0100] Data collection includes rainfall data and drainage system data; rainfall data includes hourly rainfall at the weather station; drainage system data includes the location of sewage outlets, the number of sewage outlets, the overflow flow of sewage outlets, the start time of sewage outlet overflow, and the end time of sewage outlet overflow;

[0101] (2) Determination of rainfall characteristics

[0102] The Thiessen polygon method is used to determine the meteorological grid. The rainfall of a unique meteorological station contained in the meteorological grid is the rainfall in the meteorological grid. There are 5 meteorological stations in the region, and 5 meteorological grids are determined.

[0103] Rainfall periods with a continuous rainfall intensity of less than 0.2 mm / h for 12 consecutive hours or a continuous rainfall of 0 for 2 hours were identified as rainfall events; 78, 89, 76, 69, and 74 rainfall events were identified in the 1st, 2nd, 3rd, 4th, and 5th meteorological grids, respectively; a total of 386 rainfall events were identified in the 5 meteorological grids.

[0104] Determine the rainfall characteristics of each rainfall event in each meteorological grid; rainfall characteristics include rainfall depth P, maximum rainfall intensity I max , average rainfall intensity I ave , rainfall duration D, forming a rainfall characteristic data set; the rainfall characteristic data set contains 1544 data;

[0105] (3) Determination of rainfall threshold for sewage overflow

[0106] Sewage overflow events are related to rainfall events that occur within 48 hours; if there are multiple rainfall events that can match sewage overflow events within 48 hours, the larger rainfall depth P, the larger average rainfall intensity I ave , select a rainfall event to match the sewage overflow event according to the priority order;

[0107] The first meteorological grid has 6 sewage outlets, and 62, 56, 32, 46, 38, and 52 sewage overflow events occurred respectively; the second meteorological grid has 4 sewage outlets, and 70, 48, 51, and 66 sewage overflow events occurred respectively; the third meteorological grid has 5 sewage outlets, and 41, 63, 45, 52, and 55 sewage overflow events occurred respectively; the fourth meteorological grid has 4 sewage outlets, and 43, 32, 56, and 40 sewage overflow events occurred respectively; the fifth meteorological grid has 7 sewage outlets, and 53, 61, 46, 50, 48, 39, and 52 sewage overflow events occurred respectively; a total of 26 sewage outlets and 1,297 sewage overflow events were identified in the 5 meteorological grids; based on the matching of rainfall events and sewage overflow events, as well as the rainfall feature dataset, a sewage overflow-rainfall feature dataset was formed;

[0108] For a single sewage outlet, assuming that a sewage overflow event occurs at the sewage outlet under a single rainfall event, the sewage overflow event rate is recorded as 1; if no sewage overflow event occurs, the sewage overflow event rate is recorded as 0; based on the sewage overflow-rainfall feature dataset, taking the first sewage outlet of the first meteorological grid as an example, the sewage overflow event rate is correlated with the rainfall depth P, the maximum rainfall intensity I max , average rainfall intensity I ave Logistic regression analysis was performed on the rainfall duration D, and the Logistic curves were obtained, and the odds ratios OR1=1.660, OR2=1.204, OR3=1.300, and OR4=1.286 were determined respectively; the odds ratios were all greater than 1, indicating that the rainfall depth P and the maximum rainfall intensity I max , average rainfall intensity I ave , rainfall duration D is positively correlated with sewage overflow events.

[0109] The rainfall characteristic corresponding to the largest odds ratio is rainfall depth, and the rainfall depth is determined as the best rainfall prediction factor for sewage overflow at the first sewage outlet of the first meteorological grid;

[0110] Taking the first sewage outlet of the first meteorological grid as an example, the Logistic curve, the horizontal axis x is the rainfall depth, and the vertical axis y is the sewage overflow event rate; the intersection of the Logistic curve with y = 1, the corresponding horizontal axis value x = 71.2mm, that is, the rainfall depth is 71.2mm, which is confirmed as the sewage overflow rainfall threshold of the first sewage outlet of the first meteorological grid;

[0111] (4) Sewage overflow prediction

[0112] Taking the first sewage outlet of the first meteorological grid as an example, based on the determined sewage overflow rainfall threshold and combined with the rainfall forecast value, it is predicted whether sewage overflow will occur at the sewage outlet;

[0113] When the rainfall forecast value is greater than or equal to the sewage overflow rainfall threshold, a sewage overflow event occurs;

[0114] When the rainfall forecast value is less than the sewage overflow rainfall threshold, no sewage overflow event occurs.

[0115] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0116] Those skilled in the art can clearly understand that the technology in the embodiments of the present invention can be implemented by means of software plus a necessary general hardware platform. Based on this understanding, the technical solution in the embodiments of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which can be stored in a storage medium such as ROM / RAM, a disk, an optical disk, etc., and includes a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention or some parts of the embodiments.

[0117] The above are only preferred embodiments of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technicians in this technical field, some improvements and modifications without departing from the principle of the present invention should be regarded as the protection scope of the present invention.

Claims

1. A method for predicting sewage overflow in a municipal drainage system, wherein the drainage system comprises a plurality of sewage outlets, characterized in that: include: Acquire historical rainfall information and drainage system information; the drainage system information includes the location of each sewage outlet and overflow data when an overflow event occurs at each sewage outlet; Divide the meteorological grid according to the location of the meteorological stations; According to the rainfall information, for each meteorological grid, multiple rainfall characteristics when a rainfall event occurs are obtained; Based on the overflow data of each sewage outlet when the overflow event occurs and multiple rainfall characteristics when the rainfall event occurs in the meteorological grid where the sewage outlet is located, the optimal rainfall prediction factor when the overflow event occurs at each sewage outlet is determined; Obtain the sewage overflow rainfall threshold corresponding to the best rainfall prediction factor when an overflow event occurs at each sewage outlet; Based on the sewage overflow rainfall threshold of each sewage outlet and the rainfall forecast data of the meteorological grid where the sewage outlet is located, it is predicted whether overflow will occur at each sewage outlet.

2. The method for predicting sewage overflow in a municipal drainage system according to claim 1, characterized in that: The overflow data when an overflow event occurs at each sewage outlet includes the start time, end time and overflow flow rate of each sewage outlet; The rainfall information includes hourly rainfall at each weather station.

3. The method for predicting sewage overflow in a municipal drainage system according to claim 1, characterized in that: In the meteorological grid divided according to the location of the meteorological station, The Thiessen polygon method is used to determine the meteorological grid, and each meteorological grid includes a unique meteorological station.

4. The method for predicting sewage overflow in a municipal drainage system according to claim 1, characterized in that: According to the rainfall information, for each meteorological grid, multiple rainfall characteristics when a rainfall event occurs are obtained, including: According to the rainfall information, all rainfall events of each meteorological grid are identified; the conditions for identifying a rainfall event are: a rainfall period with a rainfall intensity of less than 0.2 mm / hour for 12 consecutive hours or a rainfall of 0 for 2 consecutive hours; Based on the identified rainfall event, a plurality of rainfall features of the rainfall event are obtained.

5. The method for predicting sewage overflow in a municipal drainage system according to claim 1, characterized in that: The method of determining the optimal rainfall prediction factor when an overflow event occurs at each sewage outlet based on the overflow data when the overflow event occurs at each sewage outlet and the multiple rainfall characteristics when a rainfall event occurs at the meteorological grid where the sewage outlet is located, includes: Match the overflow events of the sewage outlets with the rainfall events of the meteorological grid where the sewage outlets are located, and construct a data set of the sewage outlets; the data set of the sewage outlets includes the overflow data of each overflow event of all sewage outlets, and the rainfall characteristic data corresponding to each rainfall event of the meteorological grid where the sewage outlets are located; Based on the data set of sewage outlets, for each sewage outlet, the overflow event rate is respectively analyzed with multiple rainfall characteristics, and the odds ratio corresponding to each rainfall characteristic is determined respectively; the multiple rainfall characteristics include rainfall depth, maximum rainfall intensity, average rainfall intensity and rainfall duration; The odds ratios corresponding to all rainfall characteristics are compared, and the rainfall characteristic corresponding to the maximum odds ratio is determined as the best rainfall prediction factor for the current sewage outlet.

6. The method for predicting sewage overflow in a municipal drainage system according to claim 5, characterized in that: The overflow events of the sewage outlet are matched with the rainfall events of the meteorological grid where the sewage outlet is located, and a data set of the sewage outlet is constructed. The overflow event of the sewage outlet is related to all rainfall events within 48 hours before the overflow occurs. If the overflow event of the sewage outlet is only related to one rainfall event, the related rainfall event is matched with the overflow event. If the overflow event of the sewage outlet is related to multiple rainfall events, one rainfall event is selected according to the set rules to match the overflow event; If the overflow event of the sewage outlet is related to multiple rainfall events, a rainfall event is selected according to a set rule to match the overflow event, including the following steps: E1: Compare the rainfall depths P of all relevant rainfall events. If there is only one rainfall event corresponding to the maximum rainfall depth P, stop selecting rainfall events, and match the rainfall event corresponding to the maximum rainfall depth P with the overflow event of the sewage outlet. If there is more than one rainfall event corresponding to the maximum rainfall depth P, proceed to step E2; E2: Compare the average rainfall intensity of all relevant rainfall events I ave , if the average rainfall intensity I ave If there is only one rainfall event corresponding to the maximum value, stop selecting rainfall events and set the average rainfall intensity I ave The rainfall event corresponding to the maximum value is matched with the overflow event of the sewage outlet. If the average rainfall intensity I ave If there is more than one rainfall event corresponding to the maximum value, then go to step E3; E3: Compare the maximum rainfall intensity of all relevant rainfall events I max , if the maximum rainfall intensity I max If there is only one rainfall event corresponding to the maximum value, stop selecting rainfall events and set the maximum rainfall intensity I max The rainfall event corresponding to the maximum value is matched with the overflow event of the sewage outlet. If the maximum rainfall intensity I max If there is more than one rainfall event corresponding to the maximum value, then go to step E4; E4: Compare the rainfall duration D of all relevant rainfall events. If there is only one rainfall event corresponding to the maximum rainfall duration D, stop selecting rainfall events and match the rainfall event corresponding to the maximum rainfall duration D with the overflow event of the sewage outlet. If there is more than one rainfall event corresponding to the maximum rainfall duration D, arbitrarily select one of the rainfall events corresponding to the maximum rainfall duration D to match the overflow event of the sewage outlet.

7. The method for predicting sewage overflow in a municipal drainage system according to claim 5, characterized in that: The odds ratio OR is the ratio of the probability of a sewage overflow event to the probability of no sewage overflow event. The formula of the odds ratio OR is: Among them, p1 is the probability of sewage overflow incident at the sewage outlet, and p2 is the probability of no sewage overflow incident at the sewage outlet.

8. The method for predicting sewage overflow in a municipal drainage system according to claim 5, characterized in that: In the sewage overflow rainfall threshold corresponding to the best rainfall prediction factor when an overflow event occurs at each sewage outlet, Obtain the Logistic curve corresponding to the best prediction factor of the sewage outlet; The value of the rainfall characteristic corresponding to the sewage overflow event rate of 1 is the sewage overflow rainfall threshold.

9. The method for predicting sewage overflow in a municipal drainage system according to claim 1, characterized in that: The method of predicting whether overflow occurs at each sewage outlet based on the sewage overflow rainfall threshold of each sewage outlet and the rainfall forecast data of the meteorological grid where the sewage outlet is located includes: If the sewage overflow rainfall threshold of the sewage outlet is greater than or equal to the rainfall forecast data of the meteorological grid where the sewage outlet is located, no sewage overflow event will occur at the sewage outlet; If the sewage overflow rainfall threshold of the sewage outlet is less than the rainfall forecast data of the meteorological grid where the sewage outlet is located, a sewage overflow event will occur at the sewage outlet; The rainfall forecast data includes forecast values ​​of multiple rainfall characteristics.

Images