Valve intelligent control method and system based on Internet of Things

Abstract

The present invention relates to the field of data processing, and more specifically, the present invention relates to a valve intelligent control method and system based on the Internet of Things. The method comprises: obtaining historical water level data, performing anomaly detection to obtain multiple abnormal data segments, and marking abnormal water level intervals. The positions of the current water level and the standard water level in the historical data are obtained. If the standard water level is not within the abnormal interval, the solenoid valve works normally; if it is within the abnormal interval, the water supply influence coefficient is calculated, the future water level is predicted based on normal data, and the timestamp corresponding to the standard water level is found as the target stamp. The closing time of the solenoid valve is determined according to the water supply influence coefficient, the maximum predicted value and the target stamp. By calculating the water supply influence coefficient and performing abnormal water level interval prediction, the present invention realizes intelligent control of the solenoid valve and improves the accuracy and efficiency of water level control.

Description

Technical Field

[0001] The present invention generally relates to the field of data processing, and more specifically, to a valve intelligent control method and system based on the Internet of Things. Background Art

[0002] As user needs change, electric water heaters on the market can automatically open or close the solenoid valve by receiving instructions through the network to control the flow of water. This intelligent control method not only improves the user experience, but also enhances the functionality of the water heater.

[0003] Due to long-term use of the water heater, scale may be generated inside, and the accumulation of scale will affect the measurement accuracy of the water level sensor. Specifically, scale may cover the surface of the sensor or change the conductivity of water, thereby affecting the sensor's perception of water level changes. When the water level measurement data becomes inaccurate due to scale, the control system cannot accurately reach the standard water level when controlling the solenoid valve to fill water according to these data, which causes the water level inside the water heater to be too high or too low, thereby adversely affecting the service life and performance of the water heater. Therefore, processing the water level data inside the water heater to ensure that the control system can control the operation of the solenoid valve based on accurate data, thereby achieving precise water filling control, is a problem to be solved by the present invention. Summary of the invention

[0004] In order to solve the technical problem that the above-mentioned solenoid valve cannot be accurately controlled, the present invention provides solutions in the following aspects.

[0005] In a first aspect, a valve intelligent control method based on the Internet of Things includes:

[0006] Acquire a time series set of historical water level data, perform anomaly detection on the time series set to obtain multiple abnormal data segments, mark the minimum water level value and the maximum water level value in the abnormal data segments, and determine the abnormal water level interval corresponding to each abnormal data segment;

[0007] Get the water level value at the current moment, determine the position of the water level value at the current moment in the time series set of historical water level data, and the position of the standard water level in the time series set of historical water level data;

[0008] If the standard water level is not within the abnormal water level interval, the solenoid valve works normally; if the standard water level is within the abnormal water level interval, the water supply influence coefficient is calculated, and the water level is predicted based on the normal data segment to obtain the preset future abnormal water level prediction interval, and the timestamp corresponding to the standard water level value is found in the abnormal water level prediction interval, and the timestamp is marked as the target stamp;

[0009] Acquire the closing time of the solenoid valve according to the water influencing coefficient, the maximum predicted value of the abnormal water level prediction interval and the target stamp;

[0010] The water impact coefficient satisfies the relationship:

[0011] ; In the formula, is the water impact coefficient, is the maximum water level value of all abnormal water level intervals, As parameters, is the standard water level, is the time interval between the minimum water level value of the target interval and the standard water level, It is the time interval from the timestamp under the preset conditions to the timestamp corresponding to the minimum water level value of the target interval. is the activation function, and the target interval is the abnormal water level interval corresponding to the maximum water level value among all abnormal water level intervals.

[0012] The present invention first performs anomaly detection on the collected historical water level data, identifies the time period that does not conform to the normal water level change law, and preliminarily evaluates the water level change trend. Then, according to whether the standard water level set by the water heater is within any abnormal water level interval, a solenoid valve control decision is made, which includes calculating the water supply influence coefficient and predicting the water level based on the normal water level data, so that the system predicts the future abnormal water level prediction interval and finds the timestamp (target stamp) corresponding to the standard water level value. Then, the closing time of the solenoid valve is determined according to the water supply influence coefficient, the maximum predicted value and the target stamp, thereby realizing intelligent control of the solenoid valve and effectively avoiding potential risks caused by abnormal water levels.

[0013] In one embodiment, determining the abnormal water level interval corresponding to each abnormal data segment further includes clustering the abnormal water level interval, and the clustering process is:

[0014] The abnormal water level interval of each abnormal data segment is taken as a vector, which contains two elements: the minimum water level value and the maximum water level value of the abnormal water level interval;

[0015] All vectors are clustered using the mean shift method, and multiple categories of abnormal water level intervals are output;

[0016] For each category, the minimum water level mean and the maximum water level mean of all abnormal water level intervals in the category are calculated to obtain the representative abnormal water level interval of each category.

[0017] Introducing cluster analysis (especially using the mean shift method) in the process of determining the abnormal water level interval corresponding to each abnormal data segment can improve the representativeness of the abnormal water level interval, simplify the processing process, and enhance the robustness of anomaly detection.

[0018] In one embodiment, the process of obtaining the time interval from the timestamp under the preset condition to the timestamp corresponding to the minimum water level value of the target interval includes:

[0019] Traverse all abnormal water level intervals. If there is an abnormal water level interval with the smallest difference between the maximum water level value and the target interval, mark the abnormal water level interval as a neighboring interval, and then calculate the time interval between the timestamp corresponding to the maximum water level value of the neighboring interval and the timestamp corresponding to the minimum water level value of the target interval;

[0020] If the adjacent interval does not exist, the time interval between the lowest value of the water level and the timestamp corresponding to the minimum water level value of the target interval is calculated.

[0021] By accurately estimating the time interval from the timestamp under the preset conditions to the timestamp corresponding to the minimum water level value in the target interval, the water supply influence coefficient can be calculated more accurately, and then the closing time of the solenoid valve can be determined to ensure that the water level fluctuates within a safe range.

[0022] In one embodiment, the process of obtaining the abnormal water level prediction interval includes:

[0023] Align the timestamps of the historical water level data time series set;

[0024] Extract the normal water level interval adjacent to the target interval; average all water level values ​​at each time stamp in the normal water level interval to obtain the normal water level mean curve;

[0025] The normal water level mean curve is fitted, and based on the target interval, the abnormal water level prediction interval of the target interval is obtained.

[0026] Extracting the normal water level interval adjacent to the target interval and calculating its water level mean curve can reflect the trend and law of normal water level changes and provide a reliable reference benchmark for abnormal water level prediction.

[0027] In one embodiment, the process of obtaining the closing time of the solenoid valve includes:

[0028] Get the maximum value of the water level difference between the water level value of the abnormal water level prediction interval and the water level value between the timestamp under the preset conditions and the timestamp corresponding to the minimum water level value of the target interval at the same timestamp;

[0029] Calculate the average water level change rate within the normal water level interval; take the ratio of the maximum value of the water level difference to the average water level change rate as the error compensation length; take the product of the water impact coefficient and the error compensation length as the advance response time;

[0030] The closing time of the solenoid valve is obtained by subtracting the advance response time from the target time.

[0031] In one embodiment, the water impact coefficient also satisfies the relationship:

[0032] ; In the formula, is the water impact coefficient, is the maximum water level value of all abnormal water level intervals, As parameters, is the standard water level, is the time interval between the minimum water level value of the target interval and the standard water level, It is the time interval from the timestamp under the preset conditions to the timestamp corresponding to the minimum water level value of the target interval. is the activation function, the target interval is the abnormal water level interval corresponding to the maximum water level value among all abnormal water level intervals, , are all weight factors.

[0033] In one embodiment, the water impact coefficient also satisfies the relationship:

[0034] ; In the formula, is the water impact coefficient, is the maximum water level value of all abnormal water level intervals, As parameters, is the standard water level, is the time interval between the minimum water level value of the target interval and the standard water level, It is the time interval from the timestamp under the preset conditions to the timestamp corresponding to the minimum water level value of the target interval. is the activation function, and the target interval is the abnormal water level interval corresponding to the maximum water level value among all abnormal water level intervals.

[0035] In a second aspect, a valve intelligent control system based on the Internet of Things includes: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned valve intelligent control method based on the Internet of Things is implemented.

[0036] The beneficial effects of the present invention are:

[0037] The present invention determines the working state of the solenoid valve according to the positional relationship between the current water level value and the standard water level in the historical water level data time series set, and whether it is in the abnormal water level interval. When the standard water level is in the abnormal water level interval, by calculating the water influencing coefficient and performing water level prediction, the closing time of the solenoid valve can be determined more accurately, thereby effectively avoiding the potential risks caused by the abnormal water level. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0039] Figure 1 It is a method flow chart of steps S1 to S4 in the valve intelligent control method based on the Internet of Things in an embodiment of the present invention.

[0040] Figure 2 It is a structural block diagram of a valve intelligent control system based on the Internet of Things according to an embodiment of the present invention. DETAILED DESCRIPTION

[0041] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0042] The embodiment of the present invention discloses a valve intelligent control method based on the Internet of Things, referring to Figure 1 , including steps S1 to S4, which are specifically as follows:

[0043] S1: Obtain a time series set of historical water level data, perform anomaly detection on the time series set to obtain multiple abnormal data segments, mark the minimum water level value and the maximum water level value in the abnormal data segments, and determine the abnormal water level interval corresponding to each abnormal data segment.

[0044] In an embodiment of the present invention, a water level sensor is installed in the water heater, and the water level sensor has a wireless function. The water level sensor is used to collect the water level value of the water heater every day in the past, for example, 10 days. The water level values ​​collected on that day are arranged in chronological order to form a data set, thereby ensuring that the water level values ​​of each day in the past have been collected and saved as a separate data set, which contains a timestamp and the corresponding water level value.

[0045] Preprocess each dataset and align the timestamps of all datasets to a unified reference time point. Merge all preprocessed datasets into a single time series set in chronological order.

[0046] During the operation of the water level sensor, if its surface is blocked by scale, it will directly affect the accuracy of water level data collection. This blockage will cause the sensor to fail to correctly reflect the actual water level at certain times, resulting in abnormal data points or abnormal data segments. These abnormal data segments are caused by the difference between the sensor reading and the actual water level, usually manifested as a sudden increase or decrease in data, or an abnormally large fluctuation in data, so according to the existing anomaly detection method (such as), the above time series set is analyzed to identify data segments that do not conform to the normal water level change pattern.

[0047] Exemplarily, a time series anomaly detection method is used to perform anomaly detection on a time series set to obtain multiple abnormal data segments, and the minimum water level value and the maximum water level value in the abnormal data segment are marked. These two values ​​represent the lowest point and the highest point of the water level in the abnormal data segment, respectively, and the abnormal water level interval corresponding to each abnormal data segment is determined, that is, the abnormal water level interval can be expressed as: , For the The minimum water level value of a data segment, For the The maximum watermark value of a data segment.

[0048] It should be noted that if an abnormal data segment is caused by accidental factors, it may not be clustered with other abnormal data segments. Therefore, multiple abnormal data segments obtained by the above anomaly detection are clustered.

[0049] Specifically, the abnormal water level interval of each abnormal data segment is taken as a vector, which contains two elements: the minimum water level value and the maximum water level value of the abnormal water level interval; all vectors are clustered using the mean shift method, and abnormal water level intervals of multiple categories are output; for each category, the minimum water level mean and the maximum water level mean of all abnormal water level intervals in the category are calculated, and then the representative abnormal water level interval of each category is obtained.

[0050] Exemplarily, each abnormal water level interval is defined as a 1×2 vector D, the vectors D corresponding to all abnormal water level intervals are classified, and approximate abnormal water level intervals are clustered into one category, resulting in a total of E categories of abnormal water level intervals. For each category of abnormal water level intervals, the minimum water level mean and maximum water level mean of the abnormal water level interval are calculated, and then the representative abnormal water level interval of each category is calculated.

[0051] S2: Obtain the water level value at the current moment, determine the position of the water level value at the current moment in the time series set of historical water level data, and the position of the standard water level in the time series set of historical water level data.

[0052] Through the water level sensor, the current water level value is obtained in real time, and the current water level value is compared with the historical water level data time series set to analyze its position in the time series set. In addition, the specific position of the standard water level in the time series can be found from the time series set, and the gap between the current water level and the standard water level can be evaluated.

[0053] S3: If the standard water level is not within the abnormal water level range, the solenoid valve works normally.

[0054] Specifically, the solenoid valve is a key component in the water level control system, which is usually used to control the on and off of water flow or adjust the water flow. In the water level control system, the opening and closing of the solenoid valve is often closely linked to the real-time monitoring results of the water level. When the water level sensor detects that the actual water level deviates from the standard water level range, that is, enters the abnormal water level range, the system may issue a command to make the solenoid valve take corresponding action to adjust the water level to prevent safety hazards caused by too high or too low water levels.

[0055] However, when the actual water level remains within the standard water level range, the solenoid valve does not need to make additional adjustments and can maintain its normal working state. This means that the system is in a stable state and the water flow is effectively controlled within the predetermined range, thus ensuring the safety and stability of the system.

[0056] S4: If the standard water level is within the abnormal water level interval, calculate the water inflow influence coefficient, perform water level prediction based on the normal data segment, obtain the preset future abnormal water level prediction interval, and find the timestamp corresponding to the standard water level value in the abnormal water level prediction interval, mark the timestamp as the target stamp, and obtain the closing time of the solenoid valve according to the water inflow influence coefficient, the maximum predicted value of the abnormal water level prediction interval and the target stamp.

[0057] If the standard water level is within the abnormal water level interval, then within this abnormal water level interval, there must be a maximum water level value greater than the standard water level, or it can be understood that within this abnormal water level interval, the relative relationship between the standard water level and the maximum water level value is unique, that is, the standard water level is lower than the maximum water level value. If the maximum water level value of the abnormal water level interval is much greater than the standard water level, it means that the actual water level may rise rapidly to a higher level in a short period of time. The greater the difference between the maximum water level value of the abnormal water level interval and the standard water level, the greater the potential risk.

[0058] Then, the water impact coefficient is calculated based on the inclusion relationship between the abnormal water level interval of each category and the standard water level.

[0059] Specifically, all abnormal water level intervals are traversed. If there is an abnormal water level interval with the smallest difference in maximum water level value from the target interval, the abnormal water level interval is marked as a neighboring interval, and then the time interval between the timestamp corresponding to the maximum water level value of the neighboring interval and the timestamp corresponding to the minimum water level value of the target interval is calculated; if the neighboring interval does not exist, the time interval between the lowest value of the water level and the timestamp corresponding to the minimum water level value of the target interval is calculated.

[0060] Then the water impact coefficient satisfies the relationship:

[0061]

[0062] In the formula, is the water impact coefficient, is the maximum water level value of all abnormal water level intervals, As parameters, is the standard water level, is the time interval between the minimum water level value of the target interval and the standard water level, It is the time interval from the timestamp under the preset conditions to the timestamp corresponding to the minimum water level value of the target interval. is the activation function, and the target interval is the abnormal water level interval corresponding to the maximum water level value among all abnormal water level intervals.

[0063] in, , it means that there is a neighboring interval with a maximum water level close to the standard water level, which may have an impact on it; , it means that there is a neighboring interval with a maximum water level greater than the standard water level. At this time, the risk of using the water heater increases and The bigger it is, the greater the risk; , it means that there is an adjacent interval where the maximum water level is lower than the standard water level, and the risk of using the water heater is relatively small at this time.

[0064] Furthermore, the relu activation function is used to Adjust so that when hour, is 0; otherwise Such adjustments enable the water supply impact coefficient to more accurately reflect the current water level conditions and the risks of water heater use.

[0065] It reflects the error size when predicting the standard water level. The smaller the value, the higher the accuracy of the prediction.

[0066] In another embodiment, the water impact coefficient also satisfies the relationship:

[0067]

[0068] In the formula, is the water impact coefficient, is the maximum water level value of all abnormal water level intervals, As parameters, is the standard water level, is the time interval between the minimum water level value of the target interval and the standard water level, It is the time interval from the timestamp under the preset conditions to the timestamp corresponding to the minimum water level value of the target interval. is the activation function, the target interval is the abnormal water level interval corresponding to the maximum water level value among all abnormal water level intervals, , are all weight factors.

[0069] The value of the weight factor can be adjusted based on historical data or multiple tests.

[0070] In another embodiment, the water impact coefficient also satisfies the relationship:

[0071]

[0072] In the formula, is the water impact coefficient, is the maximum water level value of all abnormal water level intervals, As parameters, is the standard water level, is the time interval between the minimum water level value of the target interval and the standard water level, It is the time interval from the timestamp under the preset conditions to the timestamp corresponding to the minimum water level value of the target interval. is the activation function, and the target interval is the abnormal water level interval corresponding to the maximum water level value among all abnormal water level intervals.

[0073] Among them, replace the relu function with Function can ensure that the water impact coefficient is smoother and more continuous during the calculation process.

[0074] Furthermore, the normal water level interval adjacent to the target interval is extracted; all water level values ​​at each time stamp in the normal water level interval are averaged to obtain a normal water level mean curve; the normal water level mean curve is fitted (such as using the least squares method), and based on the target interval, an abnormal water level prediction interval of the target interval is obtained.

[0075] In addition, a timestamp corresponding to the standard water level value is found in the abnormal water level prediction interval, and the timestamp is marked as the target stamp.

[0076] Furthermore, the greater the value of the water level influence coefficient, the greater the error risk of the abnormal water level prediction interval, and thus in the embodiment of the present invention, the closing of the solenoid valve is controlled in advance. The general steps of the control are as follows:

[0077] Get the water level value of the abnormal water level prediction interval and the timestamp under the preset conditions to the timestamp corresponding to the minimum water level value of the target interval (i.e. ) at the same timestamp;

[0078] Calculate the average water level change rate within the normal water level interval (i.e., the difference between the maximum water level value and the minimum water level value in the normal water level interval divided by the number of timestamps corresponding to the normal water level interval); take the ratio of the maximum value of the water level difference to the average water level change rate as the error compensation length; take the product of the water supply influence coefficient and the error compensation length as the advance response time;

[0079] The closing time of the solenoid valve is obtained by subtracting the advance response time from the target time.

[0080] When the water level reaches the preset abnormal water level range, the system can close the solenoid valve in time according to the calculated closing time to prevent water overflow or dry burning.

[0081] An embodiment of the present invention also discloses a valve intelligent control system based on the Internet of Things, including a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the valve intelligent control method based on the Internet of Things according to the present invention is implemented.

[0082] The system also includes other components familiar to those skilled in the art, such as a communication bus and a communication interface. The configuration and functions of these components are known in the art and will not be described in detail here.

[0083] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, apparatus or device. For example, a computer-readable storage medium may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random-Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high-bandwidth memory HBM (High-Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc., or any other medium that can be used to store the required information and can be accessed by an application, a module or both. Any such computer storage medium may be part of a device or accessible or connectable to a device.

[0084] In the description of this specification, "plurality" or "several" means at least two, such as two, three or more, etc., unless otherwise clearly and specifically defined.

[0085] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

Claims

1. The valve intelligent control method based on the Internet of Things is characterized by: include: Acquire a time series set of historical water level data, perform anomaly detection on the time series set to obtain multiple abnormal data segments, mark the minimum water level value and the maximum water level value in the abnormal data segments, and determine the abnormal water level interval corresponding to each abnormal data segment; Get the water level value at the current moment, determine the position of the water level value at the current moment in the time series set of historical water level data, and the position of the standard water level in the time series set of historical water level data; If the standard water level is not within the abnormal water level interval, the solenoid valve works normally; if the standard water level is within the abnormal water level interval, the water inflow influence coefficient is calculated, and the water level is predicted based on the normal data segment to obtain the preset future abnormal water level prediction interval, and the timestamp corresponding to the standard water level value is found in the abnormal water level prediction interval, and the timestamp is marked as the target stamp, and the closing time of the solenoid valve is obtained according to the water inflow influence coefficient, the maximum predicted value of the abnormal water level prediction interval and the target stamp; The water impact coefficient satisfies the relationship: ; In the formula, is the water impact coefficient, is the maximum water level value of all abnormal water level intervals, As parameters, is the standard water level, is the time interval between the minimum water level value of the target interval and the standard water level, It is the time interval from the timestamp under the preset conditions to the timestamp corresponding to the minimum water level value of the target interval. is the activation function, and the target interval is the abnormal water level interval corresponding to the maximum water level value among all abnormal water level intervals.

2. The valve intelligent control method based on the Internet of Things according to claim 1 is characterized in that: Determining the abnormal water level interval corresponding to each abnormal data segment also includes clustering the abnormal water level interval, and the clustering process is: The abnormal water level interval of each abnormal data segment is taken as a vector, and the vector contains two elements: the minimum water level value and the maximum water level value of the abnormal water level interval; All vectors are clustered using the mean shift method, and multiple categories of abnormal water level intervals are output; For each category, the minimum water level mean and the maximum water level mean of all abnormal water level intervals in the category are calculated to obtain the representative abnormal water level interval of each category.

3. The valve intelligent control method based on the Internet of Things according to claim 2 is characterized in that: The process of obtaining the time interval from the timestamp under the preset conditions to the timestamp corresponding to the minimum water level value of the target interval includes: Traverse all abnormal water level intervals. If there is an abnormal water level interval with the smallest difference between the maximum water level value and the target interval, mark the abnormal water level interval as a neighboring interval, and then calculate the time interval between the timestamp corresponding to the maximum water level value of the neighboring interval and the timestamp corresponding to the minimum water level value of the target interval; If the adjacent interval does not exist, the time interval between the lowest water level value and the timestamp corresponding to the minimum water level value of the target interval is calculated.

4. The valve intelligent control method based on the Internet of Things according to claim 3 is characterized in that: The process of obtaining the abnormal water level prediction interval includes: Align the timestamps of the historical water level data time series set; Extract the normal water level interval adjacent to the target interval; average all water level values ​​at each time stamp in the normal water level interval to obtain the normal water level mean curve; The normal water level mean curve is fitted, and based on the target interval, the abnormal water level prediction interval of the target interval is obtained.

5. The valve intelligent control method based on Internet of Things according to claim 4 is characterized in that: The process of obtaining the closing time of the solenoid valve includes: Get the maximum value of the water level difference between the water level value of the abnormal water level prediction interval and the water level value between the timestamp under the preset conditions and the timestamp corresponding to the minimum water level value of the target interval at the same timestamp; Calculate the average water level change rate within the normal water level interval; take the ratio of the maximum value of the water level difference to the average water level change rate as the error compensation length; take the product of the water impact coefficient and the error compensation length as the advance response time; The closing time of the solenoid valve is obtained by subtracting the advance response time from the target time.

6. The valve intelligent control method based on the Internet of Things according to claim 1 is characterized in that: The water impact coefficient also satisfies the relationship: ; In the formula, is the water impact coefficient, is the maximum water level value of all abnormal water level intervals, As parameters, is the standard water level, is the time interval between the minimum water level value of the target interval and the standard water level, It is the time interval from the timestamp under the preset conditions to the timestamp corresponding to the minimum water level value of the target interval. is the activation function, the target interval is the abnormal water level interval corresponding to the maximum water level value among all abnormal water level intervals, , are all weight factors.

7. The valve intelligent control method based on the Internet of Things according to claim 1 is characterized in that: The water impact coefficient also satisfies the relationship: ; In the formula, is the water impact coefficient, is the maximum water level value of all abnormal water level intervals, As parameters, is the standard water level, is the time interval between the minimum water level value of the target interval and the standard water level, It is the time interval from the timestamp under the preset conditions to the timestamp corresponding to the minimum water level value of the target interval. is the activation function, and the target interval is the abnormal water level interval corresponding to the maximum water level value among all abnormal water level intervals.

8. The valve intelligent control system based on the Internet of Things is characterized by: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the valve intelligent control method based on the Internet of Things according to any one of claims 1-7 is implemented.

Images