Drainage control method and device, computer equipment and storage medium

Abstract

The invention relates to a drainage control method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring historical rainfall data of a first time period; predicting a rainwater turbidity change trend according to the historical rainfall data of the first time period through a pre-trained time sequence neural network model; the moment when the rainwater turbidity in the drainage system reaches a preset threshold value is determined according to the rainwater turbidity change trend, and starting and stopping control is conducted on the drainage system according to the moment when the rainwater turbidity reaches the preset threshold value. By adopting the method, the rainwater turbidity change can be accurately predicted, and the drainage system can be accurately and efficiently controlled according to the rainwater turbidity change.

Description

Technical Field

[0001] The present application relates to the field of drainage technology, and in particular to a drainage control method, device, computer equipment and storage medium. Background Art

[0002] The drainage system is a very important part of urban infrastructure. It can drain rainwater to sewage treatment plants and ensure the sanitation and safety of the urban environment. With the acceleration of urbanization, the efficient management of the drainage system has become an important issue in environmental protection and urban operation.

[0003] Traditional drainage system control solutions usually rely on scheduling methods based on flow or rainfall to control the drainage system. However, scheduling methods based on flow or rainfall cannot accurately consider the turbidity changes in the early stage of rainwater, resulting in the drainage system being unable to effectively deal with environmental problems caused by increased rainwater turbidity in the early stage of rainfall. Therefore, how to accurately predict the changes in rainwater turbidity and accurately and efficiently control the drainage system based on the changes in rainwater turbidity has become a technical problem that needs to be solved at present. Summary of the invention

[0004] Based on this, it is necessary to provide a drainage control method, device, computer equipment and storage medium that can accurately predict the change of rainwater turbidity and accurately and efficiently control the drainage system according to the change of rainwater turbidity to address the above technical problems.

[0005] In a first aspect, the present application provides a drainage control method, comprising:

[0006] Get historical rainfall data for the first time period;

[0007] The pre-trained time series neural network model is used to predict the rainwater turbidity change trend based on the historical rainfall data in the first time period;

[0008] The time when the rainwater turbidity in the drainage system reaches a preset threshold is determined according to the changing trend of the rainwater turbidity, and the drainage system is started and stopped according to the time when the rainwater turbidity reaches the preset threshold.

[0009] In one embodiment, the rainwater turbidity change trend is predicted based on historical rainfall data in a first time period by using a pre-trained time series neural network model, including:

[0010] Through the pre-trained time series neural network model, the historical rainfall data of the first time period is predicted and calculated to obtain the correlation parameters between rainwater turbidity and rainfall time;

[0011] The changing trend of rainwater turbidity is determined based on the correlation parameters and the log-normal distribution relationship between rainwater turbidity and rainfall time.

[0012] In one of the embodiments, the rainwater turbidity change trend is a rainwater turbidity change curve; the associated parameters include a scaling factor, a standard deviation, and a mean; wherein the scaling factor is used to determine the peak height of the rainwater turbidity change curve, the standard deviation is used to control the width of the rainwater turbidity change curve, and the mean is used to determine the peak position of the rainwater turbidity change curve.

[0013] In one embodiment, before obtaining the historical rainfall data for the first time period, the method further includes:

[0014] Obtaining historical rainfall data for a second time period; the second time period corresponds to multiple seasons and multiple climate conditions;

[0015] The time series neural model to be trained is trained by using the historical rainfall data of the second time period and the log-normal distribution relationship between rainwater turbidity and rainfall time to obtain the correlation parameters between rainwater turbidity and rainfall time;

[0016] When the correlation parameter between rainwater turbidity and rainfall time enables the log-normal distribution relationship between rainwater turbidity and rainfall time to fit the historical rainfall data of the second time period, the training is stopped to obtain a pre-trained time series neural network model.

[0017] In one embodiment, the preset threshold value includes a start threshold value; determining the time when the rainwater turbidity in the drainage system reaches the preset threshold value according to the rainwater turbidity change trend, and starting and stopping the drainage system according to the time when the rainwater turbidity reaches the preset threshold value, including:

[0018] Determine the moment when the rainwater turbidity in the drainage system rises to the opening threshold according to the changing trend of the rainwater turbidity;

[0019] When the rainfall time reaches the opening threshold, the drainage system is controlled to open.

[0020] In one embodiment, the preset threshold value includes a stop threshold value; determining the time when the rainwater turbidity in the drainage system reaches the preset threshold value according to the rainwater turbidity change trend, and starting and stopping the drainage system according to the time when the rainwater turbidity reaches the preset threshold value, including:

[0021] Determine the moment when the rainwater turbidity in the drainage system drops to the stop threshold according to the changing trend of the rainwater turbidity;

[0022] When the rainfall time reaches the stop threshold, the drainage system is controlled to stop.

[0023] In one embodiment, obtaining historical rainfall data for a first time period includes:

[0024] Acquiring historical rainfall data for a first time period through a rainfall sensor pre-installed in the drainage system;

[0025] Acquire historical rainwater turbidity data for the first time period through a turbidity meter pre-installed in the drainage system;

[0026] The historical rainfall data for the first time period is obtained according to the historical rainfall data for the first time period and the historical rainwater turbidity data for the first time period.

[0027] In a second aspect, the present application also provides a drainage control device, comprising:

[0028] A data acquisition module, used to acquire historical rainfall data for a first time period;

[0029] A turbidity prediction module is used to predict the change trend of rainwater turbidity based on historical rainfall data in a first time period by using a pre-trained time series neural network model;

[0030] The drainage control module is used to determine the time when the rainwater turbidity in the drainage system reaches a preset threshold according to the changing trend of the rainwater turbidity, and to start and stop the drainage system according to the time when the rainwater turbidity reaches the preset threshold.

[0031] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0032] Get historical rainfall data for the first time period;

[0033] The pre-trained time series neural network model is used to predict the rainwater turbidity change trend based on the historical rainfall data in the first time period;

[0034] The time when the rainwater turbidity in the drainage system reaches a preset threshold is determined according to the changing trend of the rainwater turbidity, and the drainage system is started and stopped according to the time when the rainwater turbidity reaches the preset threshold.

[0035] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the following steps are implemented:

[0036] Get historical rainfall data for the first time period;

[0037] The pre-trained time series neural network model is used to predict the rainwater turbidity change trend based on the historical rainfall data in the first time period;

[0038] The time when the rainwater turbidity in the drainage system reaches a preset threshold is determined according to the changing trend of the rainwater turbidity, and the drainage system is started and stopped according to the time when the rainwater turbidity reaches the preset threshold.

[0039] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0040] Get historical rainfall data for the first time period;

[0041] The pre-trained time series neural network model is used to predict the rainwater turbidity change trend based on the historical rainfall data in the first time period;

[0042] The time when the rainwater turbidity in the drainage system reaches a preset threshold is determined according to the changing trend of the rainwater turbidity, and the drainage system is started and stopped according to the time when the rainwater turbidity reaches the preset threshold.

[0043] The drainage control method, device, computer equipment, storage medium and computer program product, by introducing a pre-trained time series neural network model, predicts the change trend of rainwater turbidity according to the historical rainfall data of the first time period, and can predict the change trend of rainwater turbidity in real time and accurately, solving the problem that the traditional scheduling method based on flow or rainfall cannot accurately consider the turbidity change in the early stage of rainwater, which causes the drainage system to be unable to effectively deal with the environmental problems caused by the increase of rainwater turbidity in the early stage of rainfall. According to the real-time predicted rainwater turbidity change trend, the time when the rainwater turbidity in the drainage system reaches the preset threshold is determined, and the drainage system can be accurately and efficiently started and stopped according to the time when the rainwater turbidity reaches the preset threshold, so as to avoid premature stop or over-operation of the water pump, significantly improve the operation efficiency of the drainage system, and effectively save energy, and solve the problem that the traditional water pump control scheme based on fixed time or flow is difficult to respond to the turbidity change in real time during the rainfall process, which may cause the water pump to stop working prematurely or over-operate, which not only affects the drainage effect, but also wastes energy. At the same time, through the time series neural network model, automatic decision-making can be made, and the drainage system can be flexibly adjusted according to the actual turbidity change, ensuring efficient drainage under different rainfall conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0045] FIG1 is an application environment diagram of a drainage control method according to an embodiment;

[0046] FIG2 is a schematic flow chart of a drainage control method in one embodiment;

[0047] FIG3 is a schematic diagram of a process of predicting a rainwater turbidity change trend according to historical rainfall data in a first time period using a pre-trained time series neural network model in one embodiment;

[0048] FIG4 is a schematic diagram of a rainwater turbidity variation curve in one embodiment;

[0049] FIG5 is a structural block diagram of a drainage control device in one embodiment;

[0050] FIG. 6 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0052] The drainage control method provided in the embodiment of the present application can be applied in the application environment as shown in FIG1 . Among them, a data acquisition device 104 is pre-installed in the drainage system 102, and the drainage system 102 and the data acquisition device 104 communicate with the server 106 through the network. The data acquisition device 104 collects historical rainfall data in the first time period, and sends the historical rainfall data in the first time period to the server 106. The server 106 obtains the historical rainfall data in the first time period, and predicts the rainwater turbidity change trend according to the historical rainfall data in the first time period through the pre-trained time series neural network model. After that, the moment when the rainwater turbidity in the drainage system 102 reaches the preset threshold is determined according to the rainwater turbidity change trend, and the drainage system 102 is started and stopped according to the moment when the rainwater turbidity reaches the preset threshold. Among them, the data acquisition device 104 can be various sensors for collecting rainfall data. The server 106 can be implemented by an independent server or a server cluster composed of multiple servers.

[0053] In an exemplary embodiment, as shown in FIG2 , a drainage control method is provided, which is described by taking the method applied to the server in FIG1 as an example, and includes the following steps 202 to 206. Among them:

[0054] Step 202, obtaining historical rainfall data for a first time period.

[0055] Optionally, a data acquisition device is pre-installed in the drainage system, and the data acquisition device is used to collect historical rainfall data for a first time period. The first time period refers to the historical time period including the current moment. For example, the first time period may be 15 days including the current moment, that is, the data acquisition device collects historical rainfall data for 15 days including the current moment. The historical rainfall data for the first time period includes rainfall data and water quality data. The rainfall data includes rainfall intensity, rainfall duration, rainwater flow and other data, and the water quality data includes rainwater turbidity data. The historical rainfall data for the first time period is rainfall time series data. The server obtains the historical rainfall data for the first time period sent by the data acquisition device.

[0056] Step 204 , predicting the rainwater turbidity change trend based on the historical rainfall data in the first time period by using the pre-trained time series neural network model.

[0057] Specifically, the server calls a pre-trained time series neural network model (Gated Recurrent Unit, GRU), and uses the time series neural network model to perform prediction operations on the historical rainfall data of the first time period, thereby predicting the future trend of rainwater turbidity changes. It refers to the degree of obstruction to the passage of light caused by suspended particles in rainwater, including silt, algae, plankton, etc. Rainwater turbidity is an important indicator for measuring the clarity of rainwater, reflecting factors such as the content of suspended matter in rainwater, particle size, shape and refractive index. Rainwater turbidity change trend refers to the change pattern of rainwater turbidity with rainfall time.

[0058] Furthermore, the time series neural network model is trained by a large amount of historical rainfall time series data. Among them, the collection time span of the historical rainfall time series data can cover rainfall data of different seasons and climate conditions, which can ensure the reliability of the historical rainfall time series data, thereby improving the accuracy of the time series neural network model. The time series neural network model can predict future data based on historical data. Therefore, after being trained with a large amount of historical rainfall time series data, the time series neural network model can capture the complex relationship between rainfall data, rainfall time and rainwater turbidity changes, that is, it can accurately predict the future trend of rainwater turbidity changes.

[0059] Step 206 , determining the time when the rainwater turbidity in the drainage system reaches a preset threshold value according to the change trend of the rainwater turbidity, and starting and stopping the drainage system according to the time when the rainwater turbidity reaches the preset threshold value.

[0060] Specifically, after predicting the rainwater turbidity change trend, the time when the rainwater turbidity in the drainage system reaches the preset threshold is calculated according to the rainwater turbidity change trend. The preset threshold refers to the turbidity threshold at which the water pump of the drainage system needs to be started and stopped. When the rainfall time reaches the preset threshold, the server starts and stops the water pump of the drainage system to achieve control of the drainage operation of the water pump.

[0061] In one of the embodiments, the above-mentioned drainage control method is not only applicable to the interception well water pump control of the urban drainage system, but can also be further applied to other scenarios requiring rainwater management and pollution control, such as rainwater discharge management in industrial parks, intelligent scheduling of agricultural irrigation systems, etc.

[0062] In the above drainage control method, by introducing a pre-trained time series neural network model, the rainwater turbidity change trend is predicted according to the historical rainfall data of the first time period, and the rainwater turbidity change trend can be predicted in real time and accurately, solving the problem that the traditional scheduling method based on flow or rainfall cannot accurately consider the turbidity change in the early stage of rainwater, which leads to the drainage system being unable to effectively deal with the environmental problems caused by the increase in rainwater turbidity in the early stage of rainfall. According to the real-time predicted rainwater turbidity change trend, the time when the rainwater turbidity in the drainage system reaches the preset threshold is determined, and the drainage system can be accurately and efficiently started and stopped according to the time when the rainwater turbidity reaches the preset threshold, so as to avoid premature stop or over-operation of the water pump, significantly improve the operation efficiency of the drainage system, and effectively save energy, and solve the problem that the traditional water pump control scheme based on fixed time or flow is difficult to respond to the turbidity change in real time during the rainfall process, which may cause the water pump to stop working prematurely or over-operate, which not only affects the drainage effect, but also wastes energy. At the same time, through the time series neural network model, automatic decision-making can be made, and the drainage system can be flexibly adjusted according to the actual turbidity change, ensuring efficient drainage under different rainfall conditions.

[0063] In an exemplary embodiment, as shown in FIG3 , the rainwater turbidity change trend is predicted based on the historical rainfall data in the first time period by using a pre-trained time series neural network model, including:

[0064] Step 302, using a pre-trained time series neural network model, a prediction operation is performed on the historical rainfall data of the first time period to obtain a correlation parameter between rainwater turbidity and rainfall time.

[0065] Step 304: determining the change trend of rainwater turbidity according to the correlation parameter and the log-normal distribution relationship between rainwater turbidity and rainfall time.

[0066] Optionally, in this embodiment, the change of rainwater turbidity with rainfall time, that is, the change trend of rainwater turbidity conforms to the log-normal distribution relationship, and the log-normal distribution relationship is displayed as a log-normal distribution curve. Therefore, the change trend of rainwater turbidity is displayed as a log-normal distribution curve, which can be called a rainwater turbidity change curve. The log-normal distribution relationship includes the correlation parameter between rainwater turbidity and rainfall time. The correlation parameter is used to determine the size and position of the rainwater turbidity change curve.

[0067] Through the pre-trained time series neural network model, the historical rainfall data of the first time period is predicted and calculated, and the correlation parameters between rainwater turbidity and rainfall time are output. After that, the correlation parameters between rainwater turbidity and rainfall time are brought into the logarithmic normal distribution relationship between rainwater turbidity and rainfall time to obtain the rainwater turbidity change curve.

[0068] Furthermore, the rainwater turbidity change trend is a rainwater turbidity change curve; the associated parameters include a scaling factor, a standard deviation, and a mean; wherein the scaling factor is used to determine the peak height of the rainwater turbidity change curve, the standard deviation is used to control the width of the rainwater turbidity change curve, and the mean is used to determine the peak position of the rainwater turbidity change curve.

[0069] The expression of the log-normal distribution relationship between rainwater turbidity and rainfall time is:

[0070]

[0071] in, It indicates the change of rainwater turbidity with rainfall time. Scaling factor representing the lognormal distribution relationship, represents the standard deviation of the lognormal distribution relationship, Represents the mean of the lognormal distribution relationship.

[0072] For example, as shown in FIG4 , it is a schematic diagram of the rainwater turbidity change curve, which conforms to the logarithmic normal distribution relationship. Among them, the horizontal axis represents the rainfall time, the unit is minutes, the vertical axis represents the rainwater turbidity, the unit is NTU (Nephelometric Turbidity Units), and the dotted line represents the stop threshold in the preset threshold, which is 200 MTU. The stop threshold is the turbidity threshold that needs to control the drainage system water pump to stop working. According to the rainwater turbidity change curve, it is determined that the stop threshold is reached in about 12 minutes, and the water pump in the drainage system will be controlled to stop working after 12 minutes.

[0073] In this embodiment, by using a pre-trained time series neural network model to perform prediction operations on the historical rainfall data of the first time period, the correlation parameters between rainwater turbidity and rainfall time can be accurately predicted. The rainwater turbidity change trend can be predicted according to the log-normal distribution relationship based on the correlation parameters, which can simplify the prediction process of the rainwater turbidity change trend.

[0074] In an optional manner of the above embodiment, before obtaining the historical rainfall data of the first time period, the above method also includes: a training step of the time series neural network model, which step includes: obtaining the historical rainfall data of the second time period; the second time period corresponds to multiple seasons and multiple climatic conditions; training the time series neural model to be trained through the historical rainfall data of the second time period and the log-normal distribution relationship between rain turbidity and rainfall time to obtain the correlation parameters between rain turbidity and rainfall time; when the correlation parameters between rain turbidity and rainfall time enable the log-normal distribution relationship between rain turbidity and rainfall time to fit the historical rainfall data of the second time period, stop the training to obtain the pre-trained time series neural network model.

[0075] Before drainage control is performed, the variation pattern of rainwater turbidity with rainfall time, that is, the log-normal distribution relationship between rainwater turbidity and rainfall time, can be determined based on historical rainfall data. The historical rainfall data of the second time period is collected by a data acquisition device. The second time period is any time period before the current moment. For example, the historical rainfall data of the second time period can be rainfall data within two years of history. The second time period corresponds to multiple seasons and multiple climate conditions. The historical rainfall data of the second time period includes rainfall data and water quality data. The rainfall data includes rainfall intensity, rainfall duration, rainwater flow and other data. The water quality data includes rainwater turbidity data. The historical rainfall data of the second time period is rainfall time series data. The server obtains the historical rainfall data of the second time period sent by the data acquisition device.

[0076] The historical rainfall data of the second time period is used as the historical rainfall time series data to train the time series neural network model to be trained. Specifically, the historical rainfall data of the second time period and the log-normal distribution relationship between rainwater turbidity and rainfall time are input into the time series neural model to be trained to obtain the correlation parameters between rainwater turbidity and rainfall time. The correlation parameters between rainwater turbidity and rainfall time are the correlation parameters in the log-normal distribution relationship between rainwater turbidity and rainfall time. Afterwards, the time series neural model is trained with the correlation parameters between rainwater turbidity and rainfall time. When the correlation parameters between rainwater turbidity and rainfall time output by the model enable the log-normal distribution relationship between rainwater turbidity and rainfall time to fit the historical rainfall data of the second time period, the training is stopped, and the time series neural network model at this time is used as the pre-trained time series neural network model.

[0077] In this embodiment, by acquiring historical rainfall data of multiple seasons and multiple climate conditions and training the time series neural network model, the reliability of the historical rainfall data can be improved, thereby improving the accuracy of the time series neural network model.

[0078] In an exemplary embodiment, obtaining historical rainfall data for a first time period includes: obtaining historical rainfall data for the first time period through a rain sensor pre-installed in the drainage system; obtaining historical rainwater turbidity data for the first time period through a turbidity meter pre-installed in the drainage system; and obtaining historical rainfall data for the first time period based on the historical rainfall data for the first time period and the historical rainwater turbidity data for the first time period.

[0079] Specifically, at least one rain sensor and at least one turbidity meter are pre-installed in the key nodes of the drainage system. The historical rainfall data of the first time period is obtained through the rain sensor, and the historical rainwater turbidity data of the first time period is obtained through the turbidity meter. The rain sensor and the turbidity meter respectively send the collected historical rainfall data of the first time period and the historical rainwater turbidity data of the first time period to the server, and the server uses the historical rainfall data of the first time period and the historical rainwater turbidity data of the first time period as the historical rainfall data of the first time period.

[0080] Furthermore, when acquiring the historical rainfall data for the second time period, the historical rainfall data for the second time period may be acquired through a rain sensor, and the historical rainwater turbidity data for the second time period may be acquired through a turbidity meter. The rain sensor and the turbidity meter respectively send the collected historical rainfall data for the second time period and the historical rainwater turbidity data for the second time period to the server, and the server uses the historical rainfall data for the second time period and the historical rainwater turbidity data for the second time period as the historical rainfall data for the second time period.

[0081] In traditional technology, some drainage systems rely on water quality sensors to monitor water turbidity in real time to adjust the opening and closing of water pumps. However, water quality sensors are expensive, and the cost involved in laying them in large-scale urban drainage networks cannot be ignored. In addition, water quality sensors have high long-term maintenance requirements, especially in harsh urban drainage environments, and are easily affected by dirt blockage and corrosion, which increases the difficulty and cost of system maintenance.

[0082] In this embodiment, there is no need to widely deploy expensive water quality sensors. The trend of rainwater turbidity change is mainly predicted based on the historical rainfall data of the first time period through the time series neural network model, which greatly reduces the dependence on water quality sensors. Only a limited number of rainfall sensors and turbidity meters need to be deployed at some key nodes in the drainage system, which greatly reduces the installation and maintenance costs of the system. In addition, this method can be applied to urban drainage systems of various sizes, especially in areas where conditions for large-scale deployment of data acquisition devices are not available. By reducing hardware dependence, the expanded application of drainage systems in large and medium-sized cities is more economical and feasible.

[0083] In an exemplary embodiment, the preset threshold value includes an on threshold value and a stop threshold value, wherein the on threshold value refers to the turbidity threshold value at which the water pump of the drainage system needs to be turned on. The stop threshold value refers to the turbidity threshold value at which the water pump of the drainage system needs to be stopped. The on threshold value and the stop threshold value may be the same or different, and may be set according to actual needs. Optionally, the on threshold value may be greater than the stop threshold value.

[0084] Furthermore, the moment when the turbidity of rainwater in the drainage system reaches a preset threshold is determined according to the changing trend of the turbidity of rainwater, and the start and stop control of the drainage system is performed according to the moment when the turbidity of rainwater reaches the preset threshold, including: determining the moment when the turbidity of rainwater in the drainage system rises to the start threshold according to the changing trend of the turbidity of rainwater; when the rainfall time reaches the start threshold, controlling the drainage system to start.

[0085] In the process of rainwater turbidity rising, when the rainwater turbidity rises to the opening threshold, the water pump in the drainage system is controlled to start and drain. Therefore, the server can determine the time when the rainwater turbidity in the drainage system rises to the opening threshold according to the change trend of rainwater turbidity. When the rainfall time reaches the opening threshold, the water pump of the drainage system is automatically controlled to start.

[0086] Furthermore, the moment when the turbidity of rainwater in the drainage system reaches a preset threshold is determined according to the changing trend of the turbidity of rainwater, and the start and stop control of the drainage system is performed according to the moment when the turbidity of rainwater reaches the preset threshold, including: determining the moment when the turbidity of rainwater in the drainage system drops to the stop threshold according to the changing trend of the turbidity of rainwater; when the rainfall time reaches the stop threshold, controlling the drainage system to stop.

[0087] In the process of rainwater turbidity decreasing, when the rainwater turbidity decreases to the stop threshold, the water pump in the drainage system is controlled to stop working. Therefore, the server can determine the moment when the rainwater turbidity in the drainage system decreases to the stop threshold according to the change trend of rainwater turbidity. When the rainfall time reaches the stop threshold, the water pump in the drainage system is automatically controlled to stop working, thereby avoiding energy waste.

[0088] In this embodiment, the start and stop of the water pump in the drainage system can be flexibly adjusted according to the actual turbidity change, ensuring that the drainage system can achieve efficient drainage under different rainfall conditions.

[0089] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0090] Based on the same inventive concept, the embodiment of the present application also provides a drainage control device for implementing the drainage control method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more drainage control device embodiments provided below can refer to the limitations of the drainage control method above, and will not be repeated here.

[0091] In an exemplary embodiment, as shown in FIG5 , a drainage control device is provided, comprising: a data acquisition module 502 , a turbidity prediction module 504 and a drainage control module 506 , wherein:

[0092] The data acquisition module 502 is used to acquire historical rainfall data in a first time period.

[0093] The turbidity prediction module 504 is used to predict the change trend of rainwater turbidity according to the historical rainfall data in the first time period through a pre-trained time series neural network model.

[0094] The drainage control module 506 is used to determine the time when the rainwater turbidity in the drainage system reaches a preset threshold according to the change trend of the rainwater turbidity, and to start and stop the drainage system according to the time when the rainwater turbidity reaches the preset threshold.

[0095] In an exemplary embodiment, the turbidity prediction module 504 is used to perform prediction operations on historical rainfall data in a first time period through a pre-trained time series neural network model to obtain correlation parameters between rainwater turbidity and rainfall time; and determine the rainwater turbidity change trend based on the correlation parameters and the log-normal distribution relationship between rainwater turbidity and rainfall time.

[0096] In an exemplary embodiment, the trend of rainwater turbidity change is a rainwater turbidity change curve; the associated parameters include a scaling factor, a standard deviation and a mean; the turbidity prediction module 504 is used to perform a prediction operation on the historical rainfall data of the first time period through a pre-trained time series neural network model to obtain the scaling factor, standard deviation and mean between the rainwater turbidity and the rainfall time; wherein the scaling factor is used to determine the peak height of the rainwater turbidity change curve, the standard deviation is used to control the width of the rainwater turbidity change curve, and the mean is used to determine the peak position of the rainwater turbidity change curve.

[0097] In an exemplary embodiment, the above device further includes:

[0098] The model training module is used to obtain the historical rainfall data of the second time period; the time series neural model to be trained is trained through the historical rainfall data of the second time period and the log-normal distribution relationship between rain turbidity and rainfall time to obtain the correlation parameters between rain turbidity and rainfall time; when the correlation parameters between rain turbidity and rainfall time enable the log-normal distribution relationship between rain turbidity and rainfall time to fit the historical rainfall data of the second time period, the training is stopped to obtain the pre-trained time series neural network model.

[0099] In an exemplary embodiment, the preset threshold includes an opening threshold; the drainage control module 506 is used to determine the moment when the rainwater turbidity in the drainage system rises to the opening threshold according to the rainwater turbidity change trend; when the rainfall time reaches the opening threshold, the drainage system is controlled to open.

[0100] In an exemplary embodiment, the preset thresholds include a stop threshold; the drainage control module 506 is used to determine the moment when the rainwater turbidity in the drainage system drops to the stop threshold according to the rainwater turbidity change trend; when the rainfall time reaches the stop threshold, the drainage system is controlled to stop.

[0101] In an exemplary embodiment, the data acquisition module 502 is used to obtain historical rainfall data for a first time period through a rain sensor pre-installed in the drainage system; obtain historical rainwater turbidity data for the first time period through a turbidity meter pre-installed in the drainage system; and obtain historical rainfall data for the first time period based on the historical rainfall data for the first time period and the historical rainwater turbidity data for the first time period.

[0102] Each module in the drainage control device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0103] In an exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be shown in FIG6. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface is connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data such as historical rainfall data and a time series neural network model. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a drainage control method is implemented.

[0104] Those skilled in the art will understand that the structure shown in FIG. 6 is merely a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0105] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0106] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0107] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0108] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0109] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0110] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0111] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A drainage control method, characterized in that: The method comprises: Get historical rainfall data for the first time period; Predicting the rainwater turbidity change trend based on the historical rainfall data in the first time period by using a pre-trained time series neural network model; The time when the rainwater turbidity in the drainage system reaches a preset threshold is determined according to the rainwater turbidity change trend, and the drainage system is started and stopped according to the time when the rainwater turbidity reaches the preset threshold.

2. The method according to claim 1, characterized in that The method of predicting the rainwater turbidity change trend according to the historical rainfall data in the first time period by using the pre-trained time series neural network model includes: Through the pre-trained time series neural network model, the historical rainfall data of the first time period is predicted and calculated to obtain the correlation parameters between rainwater turbidity and rainfall time; The changing trend of rainwater turbidity is determined according to the correlation parameter and the log-normal distribution relationship between rainwater turbidity and rainfall time.

3. The method according to claim 2, characterized in that The rainwater turbidity change trend is a rainwater turbidity change curve; the associated parameters include a scaling factor, a standard deviation and a mean; wherein the scaling factor is used to determine the peak height of the rainwater turbidity change curve, the standard deviation is used to control the width of the rainwater turbidity change curve, and the mean is used to determine the peak position of the rainwater turbidity change curve.

4. The method according to claim 2, characterized in that: Before obtaining the historical rainfall data for the first time period, the method further includes: Obtaining historical rainfall data for a second time period; the second time period corresponds to multiple seasons and multiple climate conditions; The time series neural model to be trained is trained by using the historical rainfall data of the second time period and the log-normal distribution relationship between rainwater turbidity and rainfall time to obtain the correlation parameter between rainwater turbidity and rainfall time; When the correlation parameter between rainwater turbidity and rainfall time enables the log-normal distribution relationship between rainwater turbidity and rainfall time to fit the historical rainfall data of the second time period, the training is stopped to obtain the pre-trained time series neural network model.

5. The method according to claim 1, characterized in that The preset threshold value includes a start threshold value; the moment when the rainwater turbidity in the drainage system reaches the preset threshold value is determined according to the rainwater turbidity change trend, and the start and stop control of the drainage system is performed according to the moment when the rainwater turbidity reaches the preset threshold value, including: Determine the time when the rainwater turbidity in the drainage system rises to the opening threshold according to the rainwater turbidity change trend; When the rainfall time reaches the opening threshold, the drainage system is controlled to open.

6. The method according to claim 1, characterized in that The preset threshold value includes a stop threshold value; the moment when the rainwater turbidity in the drainage system reaches the preset threshold value is determined according to the rainwater turbidity change trend, and the start and stop control of the drainage system is performed according to the moment when the rainwater turbidity reaches the preset threshold value, including: Determine the time when the rainwater turbidity in the drainage system drops to the stop threshold according to the rainwater turbidity change trend; When the rainfall time reaches the stop threshold, the drainage system is controlled to stop.

7. The method according to claim 1, characterized in that The obtaining of historical rainfall data for the first time period includes: Acquiring historical rainfall data for a first time period through a rainfall sensor pre-installed in the drainage system; Acquire historical rainwater turbidity data for the first time period through a turbidity meter pre-installed in the drainage system; The historical rainfall data for the first time period is obtained according to the historical rainfall data for the first time period and the historical rainwater turbidity data for the first time period.

8. A drainage control device, characterized in that: The device comprises: A data acquisition module, used to acquire historical rainfall data for a first time period; A turbidity prediction module, used to predict the turbidity change trend of rainwater according to the historical rainfall data in the first time period by using a pre-trained time series neural network model; The drainage control module is used to determine the time when the rainwater turbidity in the drainage system reaches a preset threshold according to the rainwater turbidity change trend, and to start and stop the drainage system according to the time when the rainwater turbidity reaches the preset threshold.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images