Garden engineering data acquisition management system and method
Through real-time data analysis and sensor clustering, the performance and data deviation of sensors in garden irrigation systems are evaluated, and the problems of waste of water resources and uneven irrigation in traditional irrigation technologies are solved, and the accuracy and efficiency of garden irrigation systems are improved.
Patent Information
- Application Number
- CN202411667529.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-21
- Publication Date
- 2024-12-20
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Traditional garden irrigation technology has problems of waste of water resources and uneven irrigation, and it is difficult to accurately control the actual water demand of plants and environmental conditions. The automated irrigation system relies on data to accurately collect but is difficult to process a large amount of sensor data, resulting in low collection accuracy.
By obtaining soil moisture and surface air temperature data in real time, analyzing the differences in weather changes, screening similar dates, evaluating the degree of sensor performance defects, and clustering the humidity sensor to judge data deviations, so as to achieve accurate evaluation and maintenance of sensor data accuracy.
It improves the accuracy of garden engineering data collection, promptly detects sensor abnormalities, ensures the accuracy and efficiency of the irrigation system, and reduces waste of water resources.
Smart Images
Figure CN119167119A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of sensor data processing, and in particular to a garden engineering data collection management system and method. Background Art
[0002] With the development of Internet of Things technology, modern management of garden projects tends to be refined, digitalized and intelligent. In the trend of intelligent modern garden management, with the increasing tension of global water resources and people's pursuit of environmentally friendly gardens, garden irrigation methods are beginning to tend towards efficient, precise and energy-saving irrigation needs.
[0003] Traditional garden irrigation often uses automated timed sprinkler irrigation or drip irrigation, but these methods generally have problems such as water waste and uneven irrigation, resulting in low irrigation efficiency.
[0004] Moreover, it is difficult to accurately control the actual water demand of plants and environmental conditions, such as soil moisture, weather conditions, etc. In recent years, with the rapid development of artificial intelligence technology, gardens have begun to introduce automated irrigation systems. However, automated garden irrigation technology is highly dependent on accurate data collection, and it is difficult to accurately screen a large number of sensor data, resulting in data collected by sensors with abnormal functions affecting the accuracy of the final garden project data collection. Summary of the invention
[0005] In order to solve the above technical problems, the purpose of this application is to provide a garden engineering data collection management system and method, and the technical solutions adopted are as follows: In a first aspect, an embodiment of the present application provides a garden engineering data collection and management method, the method comprising the following steps: S1, obtains soil moisture, elevation and surface air temperature at each soil moisture sensor in the garden in real time every day; S2, based on the difference in surface air temperature between any two dates at all the same times, obtain the difference in weather changes between the two dates; perform threshold analysis on the difference in weather changes between each date and all other dates, and screen out weather-similar dates for each date; based on the difference in weather changes and time interval between each date and all weather-similar dates, screen out environmentally similar dates for each date; S3, according to the soil moisture difference at all times on each date at the humidity sensor and all similar environmental dates, the performance defect degree of the humidity sensor on each date is obtained; according to the position and elevation difference of any two humidity sensors, the local environmental similarity of the two humidity sensors is obtained; S4, clustering the humidity sensors according to the local environment similarity of all humidity sensors to obtain clusters; obtaining the data deviation degree of each humidity sensor on each date according to the performance defect degree difference and distance between each humidity sensor and all other humidity sensors in the same cluster; S5, judging the working status of each humidity sensor according to the data deviation degree of each humidity sensor on the current date.
[0006] Furthermore, the method for obtaining the difference in weather changes between the two dates includes: For any two dates, the sum of the differences in surface air temperature at all times between the two dates is calculated as the difference in weather change between the two dates.
[0007] Furthermore, the method for screening weather-similar dates for each date includes: Any date is recorded as the target date, and the threshold analysis is performed on the weather change difference between the target date and all other dates to obtain the segmentation threshold; the date whose weather change difference between all other dates and the target date is less than the segmentation threshold is taken as the date with weather similarity to the target date.
[0008] Furthermore, the method for screening dates with similar environments for each date includes: Calculate the product of the number of days between any date and its weather-similar dates and the difference in weather changes, and use the exponential function value with the natural constant as the base and the opposite number of the product as the exponent as the environmental similarity between any date and its weather-similar dates; Among the environmental similarities between the any date and all its weather-similar dates, the weather-similar date whose environmental similarity is greater than a preset similarity threshold is used as the environmental similarity date for the any date.
[0009] Further, the method for obtaining the performance defect degree of the humidity sensor on each date includes: recording the performance defect degree of the humidity sensor on date Z as , ; Among them, sigmoid[] is the sigmoid normalization function; is the soil moisture at the xth moment on date Z at the humidity sensor; is the soil moisture at the xth moment of the Sth environmentally similar date on date Z at the humidity sensor; is the number of times collected each day; N is the number of days with similar environment to date Z.
[0010] Furthermore, the local environment similarity of the two humidity sensors is obtained based on the position and elevation difference of any two humidity sensors, including: for any two humidity sensors, respectively calculating the elevation difference and the Euclidean distance between the two humidity sensors; obtaining the product of the elevation difference and the Euclidean distance, recorded as the first product; and reverse normalizing the first product to obtain the local environment similarity between the two humidity sensors.
[0011] Further, the first product is reverse normalized to obtain the local environment similarity between the two humidity sensors, including: An exponential function value with a natural constant as base and the opposite number of the first product as exponent is used as the local environment similarity between the two humidity sensors.
[0012] Furthermore, the method for obtaining the data deviation degree of each humidity sensor on each date specifically includes: in, Indicates the degree of data deviation of humidity sensor i on date Z; , They represent the performance defect levels of humidity sensor i and humidity sensor k on date Z respectively; represents the Euclidean distance between humidity sensor i and humidity sensor k; sigmoid[] is the sigmoid normalization function; R is the number of humidity sensors in the cluster where humidity sensor i is located, and humidity sensor i and humidity sensor k belong to the same cluster.
[0013] Further, judging the working state of each humidity sensor according to the data deviation degree of each humidity sensor on the current date includes: The data deviation degree of humidity sensor h on the current date t is recorded as ; The preset judgment threshold is recorded as ;like ; then the humidity sensor h fails; otherwise, the humidity sensor h works normally.
[0014] In the second aspect, an embodiment of the present application also provides a garden engineering data collection and management system, including a memory, a processor, and a computer program stored in the memory and running on the processor, and when the processor executes the computer program, it implements the steps of any one of the above-mentioned garden engineering data collection and management methods.
[0015] This application has at least the following beneficial effects: The present application analyzes that the accuracy of garden engineering data collection under automated garden irrigation technology is affected by the accuracy of data collection of many sensors. In order to accurately judge the accuracy of data collected by each sensor, the periodic changes in soil moisture are first analyzed, and environmentally similar dates of each date are screened according to the similarity of temperature and humidity changes on different dates, and the similarity of data collected by the sensor under historical environmentally similar dates is further judged; the degree of performance defects is obtained based on the cumulative difference between the soil moisture changes of the same humidity sensor and the historical soil moisture changes, and the accuracy of the data of each humidity sensor is evaluated; the influence of geographical location on soil moisture data collection is further analyzed, and the differences in geographical location and performance defect levels between different humidity sensors are combined to obtain the degree of data deviation of each humidity sensor on each date. By extracting the change characteristics of the sensor data, the accuracy of the data collected by each sensor is accurately judged, the abnormal situation of the sensor is obtained, and the sensor is maintained and inspected in time according to the abnormal situation of the sensor, so as to improve the collection accuracy of garden engineering data. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the prior art 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 creative work.
[0017] Figure 1 A flowchart of a method for collecting and managing garden engineering data provided by one embodiment of the present application; Figure 2 A block diagram for obtaining local environment similarity provided in one embodiment of the present application. DETAILED DESCRIPTION
[0018] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. In the absence of conflict, the embodiments of the present application and the technical features in the embodiments can be combined with each other. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0019] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
[0020] The specific scheme of a garden engineering data collection management system and method provided by the present application is described in detail below with reference to the accompanying drawings.
[0021] See also Figure 1 , which shows a flow chart of a method for collecting and managing garden engineering data provided by an embodiment of the present application, the method comprising the following steps: S1, obtains the soil moisture, elevation and surface air temperature at each soil moisture sensor in the garden in real time every day.
[0022] A specific implementation scenario of this application is the collection and processing scenario of garden engineering data. First, humidity sensors are evenly arranged near the plant root system of the garden to avoid direct sunlight, and the plane coordinates and elevation information of the humidity sensors are recorded. The surface air temperature is collected by the temperature sensor on the soil surface. The soil moisture collected in real time by humidity sensors at various locations in the garden is obtained; the collection time interval is 10 minutes, with a day as the cycle.
[0023] S2, based on the difference in surface air temperature between any two dates at all the same times, obtain the difference in weather changes between the two dates; perform threshold analysis on the difference in weather changes between each date and all other dates, and filter out weather-similar dates for each date; based on the difference in weather changes and time intervals between each date and all weather-similar dates, filter out environmentally similar dates for each date.
[0024] The soil moisture sensor uses a resistive humidity sensor. The conductivity of the soil changes with humidity, affecting the size of the resistance, and then expressed as soil humidity changes through signal conversion. The electrodes are easily corroded in a humid, acidic, alkaline, and strongly oxidizing soil environment, which affects the conductivity of the humidity sensor, and then affects the accuracy of humidity monitoring by the humidity sensor. When the electrode humidity sensor is corroded, the resistance between its electrodes will increase, which reduces the sensitivity of the humidity sensor when measuring soil humidity. After the garden is irrigated, the soil humidity of the garden changes, because the soil texture, plant species, and terrain of the garden are different in different locations, and the sensitivity of the soil humidity sensor decreases slowly. Therefore, this embodiment evaluates the accuracy of the data of each humidity sensor by analyzing the cumulative difference between the soil humidity changes of the same humidity sensor and the historical soil humidity changes and the differences between humidity sensors with the same changes.
[0025] Specifically, when the soil moisture sensor is placed in the soil, the water molecules, electrolytes, acid-base substances, etc. in the soil begin to corrode the electrodes continuously. The higher the humidity in the air, the greater the degree of oxidation corrosion of the humidity sensor over time. In the morning of a day, the air is humid. After a night of cooling, the humidity decreases, the surface soil becomes moist, the soil humidity increases, and the corrosion effect on the electrode increases. As the temperature rises at sunrise, the water in the soil evaporates, the soil humidity decreases, and the corrosion effect on the electrode decreases, and the cycle repeats.
[0026] Therefore, this embodiment uses the change of surface air temperature to evaluate the weather change situation, and selects dates with similar weather change situations. First, the difference in weather change between date a and date b is calculated, and the calculation formula is: in, is the difference in weather changes between date a and date b; , are the surface air temperatures at the hth moment on date a and date b respectively; is the number of moments collected each day.
[0027] The smaller the difference in surface air temperature at the same time on different dates, the smaller the difference in weather change between the two dates; therefore, a threshold analysis is performed on the difference in weather change between date a and all other dates to obtain a segmentation threshold; the date whose difference in weather change between all other dates and date a is less than the segmentation threshold is taken as a weather-similar date to date a. In this embodiment, the Otsu threshold method is used for threshold analysis, and the specific implementation process is a well-known technology and will not be repeated here.
[0028] Furthermore, in order to eliminate the interference of seasonal factors, the intervals of weather-similar dates are comprehensively considered. Taking date a as an example, the environmental similarity between date a and its mth weather-similar date is recorded as , ; In the formula, exp() is an exponential function with the natural constant e as the base; is the difference in weather change between date a and its mth weather-similar date; The number of days between date a and its mth date with similar weather.
[0029] When the weather temperature is more similar, it is closer to the target date. The purpose of choosing a date close to the target date is to eliminate the interference of factors such as seasonal weather changes, that is, The larger the value, the more similar the weather and environment changes on that day are to the current target date. Set the similarity threshold. ,choose The weather similar date of date a is used as the environmental similar date of date a.
[0030] S3, according to the soil moisture difference at all times on each date at the humidity sensor and all similar environmental dates, the performance defect degree of the humidity sensor on each date is obtained; according to the position and elevation difference of any two humidity sensors, the local environmental similarity of the two humidity sensors is obtained.
[0031] The continuous change of the same weather has a similar impact on soil moisture. When the humidity sensor is abnormal, the change of soil moisture monitored by the humidity sensor will have a large offset under similar weather changes. In a day with similar weather changes, because the weather changes are similar, the water evaporates during the day, the temperature drops at night, and the dew forms and the soil moisture increases. There are periodic changes. Although there may be small differences in the initial soil moisture every day, the difference in the change of soil moisture every day is small.
[0032] To further analyze the differences in the magnitude of soil moisture changes at different locations, first, the performance defect degree of the humidity sensor on each date is obtained based on the soil moisture differences at all times on each date at the humidity sensor and all dates with similar environments.
[0033] Specifically, the performance defect degree of the humidity sensor on date Z is recorded as , the calculation formula is: Among them, sigmoid[] is the sigmoid normalization function; is the soil moisture at the xth moment on date Z at the humidity sensor; is the soil moisture at the xth moment of the Sth environmentally similar date on date Z at the humidity sensor; is the number of times collected each day; N is the number of days with similar environment to date Z.
[0034] Formula logic: When the external environment changes are similar, the difference in soil moisture at the same time on different days is small. However, when the sensitivity of the soil moisture sensor decreases, aging and rust occur, the soil moisture at the same time will produce a larger deviation. The greater the performance defect of the humidity sensor, the lower the sensitivity of the soil moisture sensor at the same time and the lower the accuracy over time.
[0035] S4, clustering the humidity sensors according to the local environment similarity of all humidity sensors to obtain each cluster; according to the performance defect degree difference and distance between each humidity sensor and all other humidity sensors in the same cluster, obtaining the data deviation degree of each humidity sensor on each date.
[0036] Due to the rich changes in gardens, diverse vegetation, mountains, forests, lakes, and different terrains, the rust degree of humidity sensors at different locations is also different. For example, the humidity sensor is located closer to the lake, where the terrain is lower, and the soil moisture and inorganic salts are more, so the rust degree of the humidity sensor is naturally higher. When the humidity sensor is placed on the top of a mountain with higher terrain, the soil moisture is less, so the rust degree of the humidity sensor is lower. Because the sensitivity of soil humidity changes needs to be judged based on the changes in soil moisture content, it is necessary to cluster humidity sensors at the same location as the target humidity sensor, and select humidity sensors with similar soil humidity changes accordingly.
[0037] The soil moisture change at the location of the soil moisture sensor is mainly affected by the moisture content of the soil and the elevation and position of the soil moisture sensor. The moisture in the soil is affected by the temperature change, so that evaporation decreases, which in turn affects the soil moisture change. When the location of a humidity sensor is close to the location of the target humidity sensor and the elevation is similar, the temperature change in the area where the humidity sensor is located is similar, which means that the soil moisture change in the area where the soil moisture sensor is located is highly similar to the soil moisture change in the area where the target soil moisture sensor is located. Based on this, the local environment similarity of any two humidity sensors is calculated: In the formula, represents the local environment similarity between humidity sensor c and humidity sensor v; represents the Euclidean distance between humidity sensor c and humidity sensor v; , They represent the elevations at humidity sensor c and humidity sensor v respectively. It is an exponential function with the natural constant e as its base.
[0038] It should be noted that is a method for reverse normalization of A. In this embodiment, A is the first product. ; Finally, the first product A and the local environment similarity e show an inverse relationship, where the larger A is, the smaller e is, and the value range of e is between [0,1].
[0039] When the distance between humidity sensor v and humidity sensor c is smaller, that is, The smaller the value, the closer the vegetation environment between the two humidity sensors is. The smaller it is, the greater the similarity of the environmental changes between humidity sensors v and c, and the greater the local environmental similarity.
[0040] The humidity sensors are clustered according to the local environment similarity of all humidity sensors to obtain clusters. In this embodiment, k-means clustering is used.
[0041] The environmental changes at the locations of the humidity sensors in the cluster are similar. The greater the difference between the humidity sensor and the other humidity sensors in the cluster, the greater the severity of the corrosion of the target humidity sensor. The degree of data deviation is further calculated: in, Indicates the degree of data deviation of humidity sensor i on date Z; , They represent the performance defect levels of humidity sensor i and humidity sensor k on date Z respectively; represents the Euclidean distance between humidity sensor i and humidity sensor k; sigmoid[] is the sigmoid normalization function; R is the number of humidity sensors in the cluster where humidity sensor i is located, and humidity sensor i and humidity sensor k belong to the same cluster.
[0042] The greater the difference in the degree of performance defects, the greater the difference between the two humidity sensors on the same date. At the same time, the greater the distance between the two humidity sensors, the greater the difference in the environment between the two humidity sensors, the greater the deviation in measuring soil moisture, and the greater the degree of rust on the inductive resistor of the humidity sensor.
[0043] The block diagram for obtaining local environment similarity is as follows: Figure 2 shown.
[0044] S4, judging the working status of each humidity sensor according to the data deviation degree of each humidity sensor on the current date.
[0045] When the soil moisture sensor is seriously corroded, the data collected by the soil moisture sensor at that moment exceeds the error range required for data collection accuracy required for garden irrigation. This may cause the system to make an incorrect judgment on the drought condition of the garden plant soil, and then the garden irrigation system makes an incorrect judgment and issues an incorrect instruction. Therefore, this embodiment sets the judgment threshold , if the data deviation of humidity sensor h on the current date t is When the humidity sensor h fails, it is considered that at this time, according to the actual engineering and plant maintenance needs of garden irrigation, the system will promptly issue an early warning prompt and promptly repair or replace the corresponding soil moisture sensor. On the contrary, when When , it is considered that the target sensor has good working performance and normal working condition, the corrosion of the soil moisture sensor is within a controllable range, and the stability of the soil moisture sensor is good.
[0046] Based on the same inventive concept as the above method, an embodiment of the present application also provides a garden engineering data collection and management system, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of any one of the above-mentioned garden engineering data collection and management methods are implemented.
[0047] Through the above description of the implementation method in combination with the accompanying drawings, technical personnel in the relevant field can understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.
[0048] The above contents are only specific implementation methods of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be covered by the protection scope of the present application.
Claims
1. A garden engineering data collection and management method, characterized in that: The method comprises the following steps: S1, obtains soil moisture, elevation and surface air temperature at each soil moisture sensor in the garden in real time every day; S2, based on the difference in surface air temperature between any two dates at all the same times, obtain the difference in weather changes between the two dates; perform threshold analysis on the difference in weather changes between each date and all other dates, and screen out weather-similar dates for each date; based on the difference in weather changes and time interval between each date and all weather-similar dates, screen out environmentally similar dates for each date; S3, according to the soil moisture difference at all times on each date at the humidity sensor and all similar environmental dates, the performance defect degree of the humidity sensor on each date is obtained; according to the position and elevation difference of any two humidity sensors, the local environmental similarity of the two humidity sensors is obtained; S4, clustering the humidity sensors according to the local environment similarity of all humidity sensors to obtain clusters; obtaining the data deviation degree of each humidity sensor on each date according to the performance defect degree difference and distance between each humidity sensor and all other humidity sensors in the same cluster; S5, judging the working status of each humidity sensor according to the data deviation degree of each humidity sensor on the current date; The method for obtaining the performance defect degree of the humidity sensor on each date includes: recording the performance defect degree of the humidity sensor on date Z as , ; Among them, sigmoid[] is the sigmoid normalization function; is the soil moisture at the xth moment on date Z at the humidity sensor; is the soil moisture at the xth moment of the Sth environmentally similar date on date Z at the humidity sensor; is the number of collected moments each day; N is the number of days with similar environment to date Z; The method of obtaining the local environment similarity of the two humidity sensors according to the position and elevation difference of any two humidity sensors includes: for any two humidity sensors, respectively calculating the elevation difference and the Euclidean distance between the two humidity sensors; obtaining the product of the elevation difference and the Euclidean distance, recorded as the first product; and performing reverse normalization on the first product to obtain the local environment similarity between the two humidity sensors; The method for obtaining the data deviation degree of each humidity sensor on each date specifically includes: in, Indicates the degree of data deviation of humidity sensor i on date Z; , They represent the performance defect levels of humidity sensor i and humidity sensor k on date Z respectively; represents the Euclidean distance between humidity sensor i and humidity sensor k; sigmoid[] is the sigmoid normalization function; R is the number of humidity sensors in the cluster where humidity sensor i is located, and humidity sensor i and humidity sensor k belong to the same cluster.
2. A garden engineering data collection and management method as claimed in claim 1, characterized in that: The method for obtaining the weather change difference between the two dates comprises: For any two dates, the sum of the differences in surface air temperature at all times between the two dates is calculated as the difference in weather change between the two dates.
3. A garden engineering data collection and management method as claimed in claim 1, characterized in that: The method for screening weather-similar dates for each date includes: Any date is recorded as the target date, and the threshold analysis is performed on the weather change difference between the target date and all other dates to obtain the segmentation threshold; the date whose weather change difference between all other dates and the target date is less than the segmentation threshold is taken as the date with weather similarity to the target date.
4. A garden engineering data collection and management method as claimed in claim 1, characterized in that: The method for screening dates with similar environments for each date comprises: Calculate the product of the number of days between any date and its weather-similar dates and the difference in weather changes, and use the exponential function value with the natural constant as the base and the opposite number of the product as the exponent as the environmental similarity between any date and its weather-similar dates; Among the environmental similarities between the any date and all its weather-similar dates, the weather-similar date whose environmental similarity is greater than a preset similarity threshold is used as the environmental similarity date for the any date.
5. A garden engineering data collection and management method as claimed in claim 1, characterized in that: The reverse normalization of the first product to obtain the local environment similarity between the two humidity sensors includes: An exponential function value with a natural constant as base and the opposite number of the first product as exponent is used as the local environment similarity between the two humidity sensors.
6. A garden engineering data collection and management method as claimed in claim 1, characterized in that: The step of judging the working state of each humidity sensor according to the data deviation degree of each humidity sensor on the current date includes: The data deviation degree of humidity sensor h on the current date t is recorded as ; The preset judgment threshold is recorded as ;like ; then the humidity sensor h fails; otherwise, the humidity sensor h works normally.
7. A garden engineering data collection and management system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the garden engineering data collection and management method as described in any one of claims 1-6 are implemented.