Determining whether a gutter is blocked

Abstract

The invention relates to a method for determining a blockage state of a gutter (1), comprising the following method steps: in a training phase while ensuring a completely unblocked gutter (1): sequential recording of a fill level value and storing the respectively recorded fill level value, so that a fill level value reference time series is obtained, and sequential recording of a precipitation value and storing the respectively recorded precipitation value, so that a precipitation value reference time series is obtained, and in a monitoring phase following the training phase without ensuring a completely unblocked gutter (1): sequential recording of the fill level value and storing the respectively recorded fill level value, so that an actual fill level value time series is obtained,sequentially recording the precipitation value and storing each recorded precipitation value to produce an actual precipitation value time series; comparing the actual fill level value time series and the actual precipitation value time series with the fill level value reference time series and the precipitation value reference time series; and determining the clogging status of the gutter (1). This provides a reliable and efficient method for determining the clogging status of a gutter.

Description

[0001] The invention relates to a method for determining a blockage condition of a gutter.

[0002] Gutters are usually located along the edge of a building's roof and serve to collect and direct rainwater. A gutter is usually made of weather-resistant materials such as metal or plastic. Their main function is to collect rainwater that runs on the roof and channel it safely to downpipes or storm drains. This allows for controlled drainage of the water and helps prevent water damage to the building's structure, foundations, and masonry. In addition, gutters minimize the risk of soil erosion because the water is diverted in a targeted and controlled manner. For optimal function, regular maintenance is important to ensure that the gutter is free of debris such as leaves and branches, so that the drainage of rainwater is not impeded by blockages in the gutter.

[0003] CN 111640284 A describes a wireless roof drainage monitoring system and an early warning method therefor. The monitoring system includes a roof precipitation sensor, a gutter water level sensor, a downpipe water flow sensor, a wireless communication module, and a server. The roof precipitation sensor is located on an external roof, the gutter water level sensor is located in a roof drainage channel, and the downpipe water flow sensor is located on the surface or outlet of a gutter downpipe. The roof precipitation sensor, the gutter water level sensor, and the downpipe water flow sensor are all connected to the wireless communication module, and the wireless communication module is connected to the server via a wireless network. Data on precipitation, water level, and runoff velocity can be obtained in real time.For example, a gutter blockage during a rain event is reported in real time. However, it is often not possible to detect an actual gutter blockage immediately during a rain event. Immediate real-time reporting of a gutter blockage therefore frequently leads to false alarms.

[0004] Based on this, the object of the present invention is to provide a reliable and efficient method for determining a blockage condition of a gutter.

[0005] This problem is solved by the subject matter of patent claim 1. Preferred developments can be found in the subclaims.

[0006] According to the invention, a method for determining the blockage state of a gutter is thus provided, comprising the following method steps: (1) in a training phase, ensuring that the gutter is completely unblocked: sequentially recording a fill level value describing the fill level of the gutter and storing the respectively recorded fill level value, so that a fill level value reference time series is obtained, and sequentially recording a precipitation value indicating the amount of precipitation per time and area at the location of the gutter and storing the respectively recorded precipitation value, so that a precipitation value reference time series is obtained, and (2) in a monitoring phase following the training phase without ensuring that the gutter is completely unblocked: sequentially recording the fill level value and storing the respectively recorded fill level value,so that an actual time series of fill level values is obtained, sequential recording of the precipitation value and storing each recorded precipitation value so that an actual time series of precipitation values is obtained, and comparing the actual time series of fill level values and the actual time series of precipitation values with the reference time series of fill level values and the reference time series of precipitation values and determining the clogging status of the gutter on the basis of this comparison.

[0007] The invention provides that a certain number of precipitation events must have occurred in the training phase before transitioning to the monitoring phase. As a result, the fill level value reference time series contains a certain number of possible fill level values of the completely unblocked gutter, which can then be assigned to the precipitation values of the completely unblocked gutter in the precipitation value reference time series. The precipitation values are contained in the form of the amount of precipitation per time and area at the location of the gutter. The time series thus generally show the fill levels of the gutter or precipitation values in a specific chronological sequence. The time periods of the training phases for the fill level value reference time series and the precipitation value reference time series are preferably identical, so that the values can be directly correlated with one another.In this context, it is preferred that the time series values are recorded successively at intervals of 5 minutes during a precipitation event and thereafter at intervals of 15 minutes.

[0008] It is further preferred that the fill level values of the fill level reference time series be determined taking into account the dimensions of the gutter, such as the gutter width, length, height, and / or inclination. The fill level values can be recorded using a fill level sensor, which, for example, has a water level sensor in a riser pipe. Alternatively, sensors that use capacitive pads to measure the fill level can also be used. Taking the dimensions of the gutter into account enables a more accurate assessment of the fill level of the gutter. The current precipitation values can be obtained accordingly using a precipitation sensor and / or on-site weather data via GPS localization.

[0009] The key to the invention is that the fill level reference time series recorded in the training phase and the precipitation reference time series are compared with the fill level actual time series and the precipitation actual time series in the monitoring phase. The reference time series provide precise information about the behavior of the gutter during and shortly after a precipitation event, allowing a gutter blockage status to be determined based on the comparison of the reference time series with the actual time series.If the comparison of the fill level values from the actual time series with the fill level values from the reference time series during a comparable precipitation event shows that the fill level values from the actual time series during and after the precipitation event are generally higher or above a predetermined limit than those from the reference time series during and after the comparable precipitation event, the gutter is blocked. The comparable precipitation event is determined by comparing the reference time series with the actual time series. Therefore, it is only possible to determine a blockage status for the specific gutter using the reference time series determined in the training phase. The accuracy of the blockage status determination can advantageously be increased, as needed, through appropriately detailed training phases.

[0010] In general, the blockage state can be indicated in various ways. However, according to a preferred embodiment of the invention, the blockage state is one of a finite number of states that indicate a measure of the blockage of the gutter with regard to the drainage of rainwater. For example, the blockage of a gutter can be measured using four different states: "not blocked," "slightly blocked," "heavily blocked," and "completely blocked." This allows a uniform and reliable determination as soon as the state becomes known whether and when action is required or the gutter should be cleaned. In this context, according to a further preferred embodiment of the invention, the blockage state can also indicate the extent to which the drainage of rainwater from the gutter is impeded. This information can then, for example,The percentage can range from 0% = no blockage to 100% = no more flow. The percentage allows for more precise adjustment of maintenance or cleaning intervals and gives the user a more detailed insight into the development of blockages.

[0011] According to a preferred development of the invention, the method for determining the clogging state of the gutter comprises the following further step: in the training phase, wherein the gutter is brought into various clogging states: sequentially recording and storing the fill level values in the fill level value reference time series and the precipitation values in the precipitation value reference time series for the respective clogging state of the gutter. It is provided that the individual clogging states in the gutter are intentionally induced in order to obtain corresponding fill level values and precipitation values. Because these clogging states are already included in the fill level value reference time series and in the precipitation value reference time series, the corresponding clogging states can be detected with greater accuracy when comparing the actual time series with the reference time series.

[0012] According to a further preferred development of the invention, the method for determining the blockage state of the gutter comprises the following further steps: in the training phase, while ensuring that the gutter is completely unblocked: sequential recording of at least one meteorological value, wherein the at least one meteorological value is a humidity and / or a temperature and / or a wind direction and / or a wind force, and storing the respectively recorded meteorological value so that a meteorological value reference time series is obtained, and in the monitoring phase without ensuring that the gutter is completely unblocked: sequential recording of the meteorological value and storing the respectively recorded meteorological value so that a meteorological value actual time series is obtained, and comparing the fill level value actual time series,The actual precipitation values and the actual meteorological values are compared with the fill level values, the precipitation values reference time series, and the meteorological values reference time series, and the gutter blockage status is determined based on this comparison. By incorporating the meteorological values, which are compared with the fill level values, the accuracy in determining blockage status can be further increased. At the same time, false alarms such as blockages caused by snow or similar can be detected. Furthermore, additional meteorological values, such as wind speed, or general meteorological data available from a weather service can be included. This allows the precipitation event to be better described. These values can be obtained from an external service, the unit itself, or from another technical system, such as a SmartHome weather station.originate.,

[0013] In principle, the blockage condition can be reported at regular intervals. However, according to a preferred embodiment of the invention, a report is automatically generated during the monitoring phase when a predetermined blockage condition is exceeded. This report can then be received by a maintenance service, e.g., a roofing company, and / or the user, e.g., a homeowner, who can then remove the blockage according to the report. Because the report is only generated when a predefined blockage condition is exceeded, unnecessary maintenance work on the gutter is avoided. The gutter is maintained efficiently.

[0014] In principle, the training phase and the monitoring phase can be of any length. However, according to a preferred embodiment of the invention, the recording of the fill level values is not terminated during the training phase and the monitoring phase until a fill level of zero has been recorded. This also allows for the detection of a blockage that only occurs immediately after a precipitation event. For example, if leaves are washed into a downpipe fluidically connected to the gutter and clog the downpipe, leaving small residual amounts of precipitation in the gutter. These are detected and can be reported accordingly.

[0015] It is possible to determine the blockage state in various ways. However, according to a preferred development, the determination of the blockage state of the gutter is carried out with the aid of an artificial neural network. The neural network is preferably a recurrent neural network. According to a particularly preferred development of the invention, it is further provided that the determination of the blockage state of the gutter is carried out with the aid of a time series prediction model. This then makes it possible to predict future blockages in the form of the blockage states with a certain probability and to issue a corresponding message before a blockage state occurs. Even more preferably, the time series prediction model is a long short-term memory model.

[0016] The Long Short-Term Memory (LSTM) is a type of recurrent neural network (RNN) designed to solve the vanishing gradient problem in traditional recurrent neural networks. LSTMs are less sensitive to the length of gaps between relevant information compared to other RNNs and sequence learning methods such as Hidden Markov Models. They are used in various applications such as handwriting recognition, speech recognition, machine translation, and healthcare. A typical LSTM consists of a cell and three gates: the input gate, the output gate, and the forget gate. These gates control the flow of information into and out of the cell. The forget gate decides which information from the previous state is discarded, while the input gate determines which new information is stored. The output gate, in turn, controls which information from the current state is output.Through these mechanisms, the LSTM network can maintain useful long-term dependencies for predictions in both current and future time steps.

[0017] The LSTM model is particularly suitable for creating time series forecasts due to its ability to capture long dependencies and store information over a longer period of time for processing time series values.

[0018] The reference time series from the training phase are provided to the LSTM model as input. The LSTM model then recognizes patterns and correlations based on the input, which, when compared with the actual time series, allow a blockage or impending blockage to be identified in the monitoring phase. If the LSTM model is additionally provided with fill level value reference time series, precipitation value reference time series, and meteorological value reference time series during the training phase, which contain fill level values, precipitation values, and meteorological values for the blockage states, the LSTM model can achieve a high degree of accuracy in predicting and determining the blockage state of the gutter.In this context, a further preferred development provides for information on obstructive objects such as photovoltaic systems, dormers, and satellite dishes to be incorporated into the long-short-term memory model. Together with the gutter dimensions, the LSTM model is thus personalized to the gutter. The gutter's blockage status can be determined periodically and / or on demand. This allows for flexible decisions, if necessary, regarding how often the blockage status should be determined, either taking into account energy savings or safety considerations.

[0019] According to the invention, there is also a non-volatile, computer-readable storage medium with instructions stored thereon which, when executed on a processor, effect the method described above.

[0020] The invention further relates to a system comprising a fill level sensor, a communication interface connected to the fill level sensor for signal transmission, and a computing unit. The communication interface is configured to transmit a fill level value measured by the fill level sensor to the computing unit, and the computing unit is configured to carry out the method for determining the blockage status of the gutter, as described above. The signal transmission can be wireless or wired. The fill level sensor is arranged in or on the gutter magnetically or by means of a snap-in device. For communication with the computing unit, the communication interface has a microcontroller with a transmitting unit. As already mentioned, the precipitation values can be measured on site using a precipitation value sensor and / or retrieved via GPS localization of the gutter.The same applies to meteorological values. The corresponding sensors are then also connected to the communication interface for signal transmission. The sensors and the communication interface can be powered by batteries, accumulators, photovoltaics, or a connection to a household power grid.

[0021] The invention is described in more detail below with reference to the drawings using preferred embodiments.

[0022] In the drawing show Fig. 1 schematically shows a flow chart for a method for determining a blockage state of a gutter according to a preferred embodiment of the invention and Fig. 2 schematically shows a system for determining a blockage condition according to a preferred embodiment of the invention.

[0023] Out of Fig. 1 schematically shows a flow diagram for a method for determining a blockage state of a gutter 1 according to a preferred embodiment of the invention. In a first step S1, it is provided that in a training phase, while ensuring a completely unblocked gutter 1 in step S1a, the chronologically successive recording of a fill level value describing the fill level of the gutter 1 and the storage of the respectively recorded fill level value in a fill level value reference time series takes place. The fill level values are compared with a Fig. The level sensor 2 shown in Figure 2 is measured. The level sensor 2 has a water level sensor in a riser pipe. The level values are linearized taking into account the dimensions of the gutter 1.

[0024] In parallel, step S1b involves the sequential recording of a precipitation value, which indicates the amount of precipitation per time and area at the location of gutter 1, and the storage of each recorded precipitation value in a precipitation value reference time series. Furthermore, step S1d involves the sequential recording of meteorological values. The meteorological values are humidity, temperature, wind force, and wind direction at the location of the gutter. These meteorological values are stored in a meteorological value reference time series.

[0025] The training phase also involves introducing various clogging states into the gutter. The clogging state indicates, as a percentage, the degree to which the drainage of rainwater from gutter 1 is impeded. In step S1c, the fill level values and the precipitation values are recorded and stored for the respective clogging state of the gutter in the fill level value reference time series and the precipitation value reference time series. This ensures that several precipitation events have occurred during the training phase.

[0026] The fill level value reference time series, the precipitation value reference time series, and the meteorological value reference time series are passed as input values for training to a Long Short-Term Memory Model (LSTM model). With the trained LSTM model, in a monitoring phase following the training phase in step S2, without ensuring that gutter 1 is completely unblocked, in steps S2a to S2c, the fill level value is recorded sequentially and each recorded level value is saved, resulting in an actual fill level value time series; the precipitation value is recorded sequentially and each recorded meteorological value is saved, resulting in an actual precipitation value time series; and the meteorological value is recorded sequentially and each recorded meteorological value is saved, resulting in an actual meteorological value time series.

[0027] In a third step S3, the LSTM model is used to compare the actual fill level values, the actual precipitation values, and the actual meteorological values with the fill level value reference time series, the precipitation value reference time series, and the meteorological value reference time series. Based on this comparison, the LSTM model then determines the clogging status of the gutter. At the same time, the LSTM model can predict future clogging in the form of a future clogging status of the gutter based on the prediction of the time series values. The clogging status of gutter 1, or the prediction of a future clogging of gutter 1, is performed at regular intervals. These intervals can be specified by a user.

[0028] Fig.Finally, Figure 2 schematically shows a system for determining a blockage condition according to a preferred embodiment of the invention. A fill level sensor 2 is magnetically attached to the gutter 1. The fill level sensor 2 is connected to a communication interface 3 for transmitting the fill level value. A precipitation sensor 7 for detecting a precipitation value, as well as a thermometer 8 for detecting a temperature, a hygrometer 9 for detecting a relative humidity, and an anemometer 10 for detecting wind direction and wind speed are also connected to the communication interface 3 for transmitting the respective values. These values are transmitted to a receiving unit 6 of a computing unit 4 by a transmitting unit 5 connected to the communication interface. Within the computing unit, the LSTM model can then be used to determine the blockage condition of the gutter based on the transmitted values.The processing unit can be located locally or on an external server. As soon as a blockage level of 50% or more is detected, a notification is sent to a maintenance service to initiate gutter cleaning.

[0029] The invention underlying this patent application was created in a project funded by the BMBF under the funding reference 02K20D050 ff (“loT4H”). List of reference symbols 1 gutter 2 level sensor 3 Communication interface 4 Computing unit 5 Transmitter unit 6 Receiving unit 7 Rainfall sensor 8 thermometers 9 Hygrometer 10 anemometers QUOTES CONTAINED IN THE DESCRIPTION

[0000] This list of documents submitted by the applicant was generated automatically and is included solely for the convenience of the reader. This list is not part of the German patent or utility model application. The DPMA assumes no liability for any errors or omissions. Cited patent literature

[0000] CN 111640284 A

[0003]

Claims

[1] Method for determining a blockage condition of a gutter (1), comprising the following method steps: S1) in a training phase ensuring a completely unblocked gutter (1): S1a) temporally successive recording of a level value describing the level of the gutter (1) and storing the recorded level value in each case, so that a level value reference time series is obtained, and S1b) temporally successive recording of a precipitation value which indicates the amount of precipitation per time and area at the location of the gutter (1), and storing the respectively recorded precipitation value so that a precipitation value reference time series is obtained, and S2) in a monitoring phase following the training phase without ensuring that the gutter is completely unblocked (1): S2a) sequential recording of the fill level value and saving the recorded fill level value so that a fill level value time series is obtained, S2b) recording the precipitation value in successive time periods and storing the precipitation value recorded in each case, so that a precipitation value actual time series is obtained, and S3) comparing the actual time series of fill level values and the actual time series of precipitation values with the reference time series of fill level values and the reference time series of precipitation values and determining the clogging status of the gutter (1) on the basis of this comparison. [2] Method according to claim 1, wherein the blockage state is one of a finite number of states which indicate a measure of the blockage of the gutter (1) with regard to the drainage of rainwater. [3] Method according to claim 1, wherein the blockage state indicates the extent to which the outflow of rainwater from the gutter (1) is inhibited. [4] A method according to any one of claims 2 or 3, comprising the following further step: S1c) in the training phase, where the gutter (1) is brought into different clogging states: temporally consecutive recording and storage of the fill level values in the fill level value reference time series and the precipitation values in the precipitation value reference time series for the respective blockage state of the gutter (1). [5] Method according to one of the preceding claims, comprising the following further steps: During the training phase, ensuring that the gutter is completely unblocked (1): S1d) temporally successive recording of at least one meteorological value, wherein the at least one meteorological value is an air humidity and / or a temperature and / or a wind direction and / or a wind force, and storing the respectively recorded meteorological value so that a meteorological value reference time series is obtained, and During the monitoring phase without ensuring that the gutter is completely unblocked (1): S2c) recording the meteorological value in successive time periods and storing each recorded meteorological value so that a meteorological value actual time series is obtained, and S3) comparing the actual time series of filling levels, the actual time series of precipitation values and the actual time series of meteorological values with the reference time series of filling levels, the reference time series of precipitation values and the reference time series of meteorological values and determining the clogging status of the gutter (1) on the basis of this comparison. [6] Method according to one of the preceding claims, wherein in the monitoring phase a message is automatically issued when a predetermined blockage condition is exceeded. [7] Method according to one of the preceding claims, wherein in the training phase and in the monitoring phase the recording of the fill level values is not terminated before a fill level of zero has been recorded. [8] Method according to one of the preceding claims, wherein the determination of the blockage state of the gutter (1) is carried out with the aid of an artificial neural network. [9] Method according to one of the preceding claims, wherein the determination of the clogging state of the gutter (1) is carried out with the aid of a time series prediction model. [10] The method of claim 9, wherein the time series prediction model is a long short-term memory model. [11] Method according to one of the preceding claims, wherein the determination of the blockage state of the gutter (1) is carried out periodically and / or on demand. [12] A non-volatile, computer-readable storage medium having instructions stored thereon which, when executed on a processor, effect a method according to any one of the preceding claims. [13] System with a level sensor (2), a communication interface (3) connected to the level sensor (2) for signal transmission and a computing unit (4), wherein the communication interface (3) is designed to transmit a fill level value measured by the fill level sensor (2) to the computing unit (4), and the computing unit (4) is designed to carry out the method for determining the blockage state of the gutter (1) according to one of claims 1 to 11.

Images