Integrated water and fertilizer irrigation control method for sand-cultured celery

Abstract

This application relates to the field of irrigation control technology, specifically to a water and fertilizer integrated irrigation control method for sand-cultured celery. The method includes: acquiring humidity and flow sequences at various times; when the humidity data at the current time exceeds a preset prediction threshold, initiating humidity data prediction, the prediction process of which involves: obtaining the time-lag confidence of each mutation point based on the difference in dispersion of humidity data before and after each mutation point, and the difference between each mutation point and its subsequent mutation point, thereby obtaining the lag duration; acquiring the rising sequence at the current time; and obtaining the smoothing coefficient at the current time based on the oscillation characteristics of the rising sequence, the difference in the number and distance of mutation points between the humidity sequence and the rising sequence, and the dispersion of the flow sequence, thereby predicting the humidity data at the lag duration after the current time, and determining whether irrigation needs to be stopped. This application improves the effectiveness of irrigation control by more accurately predicting future soil moisture.

Description

Technical Field

[0001] This application relates to the field of irrigation control technology, specifically to an integrated water and fertilizer irrigation control method for sand-cultured celery. Background Technology

[0002] Celery, a typical plant used for both food and medicine, possesses significant nutritional and health benefits. As a shallow-rooted crop that thrives in fertile soil, celery is extremely sensitive to water and fertilizer management. If the amount of water and fertilizer during alternating irrigation does not meet the celery's requirements, it will affect its growth rate and lead to reduced yield. Conversely, if the amount of water and fertilizer is far higher than the celery's needs, it will result in water and fertilizer waste, decreased resistance to pests and diseases, soil salinization, and reduced celery quality. Therefore, it is necessary to develop an integrated water and fertilizer irrigation method based on the irrigation characteristics of celery to ensure that the irrigation flow rate meets the requirements of sand-cultivated celery, thus ensuring celery quality and growth rate while conserving water and fertilizer.

[0003] While existing technologies for controlling water and fertilizer irrigation in sand-cultivated celery have taken into account the nonlinear interference issues inherent in existing irrigation systems and employ control algorithms such as PID control for precise control, they have not fully considered the characteristics of soil, such as high inertia and hysteresis. When the sensor detects that the soil water and fertilizer content has reached a set threshold, even after the irrigation valve is closed, the remaining water and fertilizer in the pipes will still be used for irrigation. This accumulation can lead to excessive water and fertilizer content in the celery, affecting its quality. Conversely, if the valve is closed before the soil water and fertilizer content reaches the threshold, insufficient water and fertilizer content may occur, thus affecting the yield of celery and resulting in poor irrigation control. Summary of the Invention

[0004] To address the aforementioned technical problems, this application provides a water and fertilizer integrated irrigation control method for sand-cultivated celery cultivation, thereby resolving the existing issues.

[0005] The water and fertilizer integrated irrigation control method for sand-cultured celery cultivation proposed in this application adopts the following technical solution:

[0006] One embodiment of this application provides a water and fertilizer integrated irrigation control method for sand-cultured celery, the method comprising the following steps:

[0007] Real-time acquisition of humidity and flow data at various times in the drip irrigation area, thereby obtaining the humidity sequence and flow sequence at the current moment;

[0008] When the current humidity data exceeds the preset prediction threshold, humidity data prediction begins, and the prediction process is as follows:

[0009] S1: Obtain all abrupt changes in the humidity sequence at the current moment. Based on the difference between the dispersion of all humidity data before each abrupt change and the dispersion of all humidity data after each abrupt change, as well as the difference between each abrupt change and the next abrupt change, obtain the time-delay confidence of each abrupt change. Obtain the lag duration based on the maximum value among the time-delay confidences of all abrupt changes.

[0010] S2: Obtain the rising sequence at the current moment based on the abrupt change point with the highest time-delay confidence in the humidity sequence at the current moment, and divide the rising sequence into multiple subsequences based on the abrupt change point in the rising sequence; obtain the rising oscillation coefficient at the current moment based on the dispersion of the shortest distance between all data in the rising sequence at the current moment and its fitted line, the dispersion of the slope of the fitted line corresponding to all subsequences in the rising sequence, and the difference in the number of abrupt change points between the humidity sequence at the current moment and the rising sequence.

[0011] S3: Based on the dispersion of the flow sequence at the current moment and the distance between the flow sequence and the rising sequence, obtain the irrigation stability coefficient at the current moment, and combine it with the rising oscillation coefficient at the current moment to obtain the smoothing coefficient at the current moment. Then, predict the humidity data after the lag time after the current moment and determine whether irrigation needs to be stopped.

[0012] Preferably, the current humidity sequence and flow rate sequence refer to the sequence composed of humidity data and flow rate data from the start of irrigation to the current time, respectively, arranged in chronological order.

[0013] Preferably, the formula for calculating the time-delay confidence level of each mutation point is: A u =B u ×exp(C u In the formula, A u B represents the time-delay confidence level of the u-th mutation point; u C is the first difference at the u-th mutation point; u Let be the difference between the (u+1)th mutation point and the uth mutation point; exp() is an exponential function with the natural constant e as the base; wherein, the process of obtaining the first difference of each mutation point is as follows: calculate the dispersion of all humidity data before each mutation point in the humidity sequence and the dispersion of all humidity data after each mutation point; record the absolute difference between the two dispersions as the first difference of each mutation point.

[0014] Preferably, the lag time is the time between the time corresponding to the maximum value of the lag confidence of all abrupt change points in the humidity sequence at the current time and the time when irrigation begins.

[0015] Preferably, the rising sequence at the current moment refers to the sequence of all data following the abrupt change point with the highest time-delay confidence in the humidity sequence at the current moment.

[0016] Preferably, the formula for calculating the rising oscillation coefficient at the current moment is: In the formula, D is the rising oscillation coefficient at the current moment, F is the first degree of dispersion at the current moment, G is the second degree of dispersion at the current moment, and H is the difference between the number of abrupt change points in the humidity sequence at the current moment and the number of abrupt change points in the rising sequence; wherein, the first degree of dispersion at the current moment refers to the variance of the shortest distance between all data in the rising sequence at the current moment and its fitted straight line; the second degree of dispersion at the current moment refers to the variance of the slope of the fitted straight line corresponding to all subsequences in the rising sequence at the current moment.

[0017] Preferably, the formula for calculating the irrigation stability coefficient at the current moment is: In the formula, K is the irrigation stability coefficient at the current time; L is the variance of all data in the flow sequence at the current time; W is the DTW distance between the flow sequence at the current time and the rising sequence; and τ is a preset constant.

[0018] Preferably, the formula for calculating the smoothing coefficient at the current moment is: In the formula, α is the smoothing coefficient at the current time, D is the rising oscillation coefficient at the current time, K is the irrigation stability coefficient at the current time, and exp() is an exponential function with the natural constant e as the base.

[0019] Preferably, the specific process of predicting the humidity data after a lag time following the current moment is as follows: the rising sequence and smoothing coefficient of the current moment are used as inputs to the triple exponential smoothing algorithm, and the humidity prediction value after the lag time following the current moment is output.

[0020] Preferably, the specific process for determining whether irrigation needs to be stopped is as follows: the lag time is recorded as t seconds. When the humidity prediction value at the t-th second after the current time is greater than or equal to the preset humidity threshold, irrigation needs to be stopped; otherwise, irrigation does not need to be stopped.

[0021] This application has at least the following beneficial effects:

[0022] This application addresses the problem that existing technologies do not adequately consider the effects of soil lag and residual water and fertilizer in pipelines, leading to over- or under-irrigation. It constructs a time-lag confidence coefficient to reflect the reliability of soil moisture changes relative to irrigation flow, providing a time benchmark for subsequent predictions. By constructing an upward oscillation coefficient, it reflects the irregularity of the amplitude and direction of soil moisture fluctuations during the rising process, analyzing the dependence of the prediction model on historical data. By constructing an irrigation stability coefficient, it reflects the stability of irrigation flow and its correlation with soil moisture changes, thus adjusting the weights of the smoothing coefficient. Through the construction of the smoothing coefficient, it accurately predicts soil moisture data, enabling precise prediction of irrigation stop times, avoiding excessive or insufficient soil moisture, improving irrigation control effectiveness, saving water and fertilizer, and improving celery growth. Attached Figure Description

[0023] To more clearly illustrate the technical solutions and advantages in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 A flowchart illustrating the steps of the integrated water and fertilizer irrigation control method for sand-cultured celery provided in this application;

[0025] Figure 2 This application provides a flowchart for predicting humidity data after the current moment. Detailed Implementation

[0026] To further illustrate the technical means and effects adopted by this application to achieve the intended purpose of the invention, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of the water and fertilizer integrated irrigation control method for sand-cultured celery proposed in this application. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0027] Unless otherwise defined, 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 pertains.

[0028] The following description, in conjunction with the accompanying drawings, details the specific scheme of the integrated water and fertilizer irrigation control method for sand-cultured celery provided in this application.

[0029] This application provides an embodiment of a water and fertilizer integrated irrigation control method for sand-cultured celery. Specifically, the method is described below. Please refer to [link to relevant documentation]. Figure 1 The method includes the following steps:

[0030] Step 1: Obtain humidity and flow data in the drip irrigation area at any time in real time, and then obtain the humidity sequence and flow sequence at the current time.

[0031] The integrated water and fertilizer machine utilizes water-soluble fertilizer technology to dissolve fertilizer in water and apply it via drip irrigation. Due to the large planting area, the growth effect and water and fertilizer requirements of celery in different planting areas may vary. Therefore, this application uses an alternating irrigation method to adjust the water and fertilizer concentration ratio and perform alternating irrigation in different areas. Since the required water and fertilizer concentration ratio has been prepared for each drip irrigation area before drip irrigation, this application uses soil temperature and humidity sensors to collect soil moisture content to reflect the irrigation effect of the integrated water and fertilizer machine.

[0032] This application analyzes the drip irrigation area currently being irrigated in a sand-cultivated celery planting area during alternating irrigation. An electromagnetic flowmeter is used to collect the overall irrigation flow rate of the integrated water and fertilizer machine during irrigation. Since the drip irrigation pipes are arranged in neat rows, N soil temperature and humidity sensors (ranging from 5 to 10, with 5 in this embodiment) are buried at equal intervals in the soil below each row of drip irrigation pipes to collect soil moisture content. The burial depth is close to the root system of the sand-cultivated celery; in this embodiment, the burial depth is 10cm. Implementers can set appropriate values ​​according to actual conditions.

[0033] The average of the moisture content data collected at the same time by all soil temperature and humidity sensors in the drip irrigation area currently being irrigated is recorded as the humidity data at that time; the irrigation flow rate collected at each time in the drip irrigation area currently being irrigated is recorded as the flow rate data at that time.

[0034] All data is collected synchronously and in real time, with a data collection interval of 1 second, starting from the moment the integrated water and fertilizer machine begins drip irrigation. The humidity and flow rate data from the start of irrigation to the current moment are respectively arranged in chronological order and denoted as the humidity sequence and flow rate sequence at the current moment.

[0035] To eliminate the influence of different dimensions between data, humidity data and flow data are normalized separately. Normalization methods include Z-score, maximum value normalization, maximum and minimum value normalization, etc. This embodiment uses maximum value normalization.

[0036] Since it is necessary to compare the predicted humidity with the preset humidity threshold in the future, this application uses the preset maximum humidity value (taken from the range of 293-305mm, and 300mm in this embodiment) as the maximum value for normalization when normalizing the humidity sequence.

[0037] Step 2: When the humidity data at the current moment is greater than the preset prediction threshold, start humidity data prediction and obtain the predicted humidity value after the current moment.

[0038] Currently, growers typically monitor soil temperature and humidity data for each group when irrigating sand-cultured celery in alternating cycles. They then compare this data with preset thresholds and stop irrigation for that group via a solenoid valve when the threshold is reached. However, due to the high inertia, nonlinearity, and time lag characteristics of soil, relying solely on soil temperature and humidity data combined with preset thresholds for irrigation control introduces timing errors, thus affecting the growth of sand-cultured celery. To achieve better irrigation control, predictions can be made based on changes in soil moisture. By analyzing the lag between changes in soil moisture and the irrigation time, future soil moisture can be predicted. When the predicted moisture reaches a preset threshold, irrigation for that group can be stopped, thus achieving precise alternating irrigation control and ensuring the growth rate and quality of sand-cultured celery.

[0039] Since the data is collected in real time, when the normalized humidity data collected at the current moment is greater than the preset prediction threshold, real-time humidity data prediction begins. In this embodiment, the preset prediction threshold is 0.85, but the implementer can choose a value according to the actual situation. Figure 2 The flowchart for predicting humidity data after the current moment is as follows:

[0040] S1: Obtain all abrupt changes in the humidity sequence at the current moment. Based on the difference between the dispersion of all humidity data before each abrupt change and the dispersion of all humidity data after each abrupt change, as well as the difference between each abrupt change and the next abrupt change, obtain the time-delay confidence of each abrupt change. Obtain the lag duration based on the maximum value among all time-delay confidences of all abrupt changes.

[0041] Because soil moisture has a lag effect, the moisture content at the root zone of the sand-cultured celery does not change immediately upon the initial drip irrigation, and the soil moisture remains relatively stable at this stage. However, as the drip irrigation continues, the soil moisture gradually increases. Nevertheless, since the flow of water and fertilizer within the sandy soil layer is unpredictable, the soil moisture will exhibit a fluctuating upward trend. Therefore, a thorough analysis of the moisture sequence is necessary to determine the lag time of soil moisture relative to the drip irrigation process.

[0042] The current humidity sequence is used as input to the mutation point detection algorithm to obtain all mutation points in the humidity sequence. The mutation point detection algorithm is not limited to PELT, Pettitt, and MK algorithms; this embodiment uses the PELT algorithm.

[0043] All abrupt changes are sorted according to their position in the humidity sequence. Taking the u-th abrupt change as an example, the dispersion of all humidity data before and after the u-th abrupt change is calculated. The absolute difference between the two dispersions is recorded as the first difference for the u-th abrupt change. The first difference reflects the variation of humidity sequence elements before and after the u-th abrupt change; the larger the value, the greater the likelihood that the humidity data is no longer stable after the u-th abrupt change. Dispersion can be calculated using variance, coefficient of variation, standard deviation, etc. This embodiment uses variance calculation.

[0044] As a preferred embodiment, the time-delay confidence of each mutation point is obtained based on the first difference of each mutation point and the difference between the next mutation point and each mutation point, which is used to characterize whether a significant increase in humidity has occurred at each mutation point.

[0045] In this embodiment, the time-delay confidence level of the u-th mutation point is denoted as A. u Its specific expression is: A u =B u ×exp(C u In the formula, A u B represents the time-delay confidence level of the u-th mutation point; u C is the first difference at the u-th mutation point; u The difference between the (u+1)th mutation point and the uth mutation point is given by exp(), which is an exponential function with the natural constant e as the base. The exponential function is used because the differences between the normalized values ​​are smaller, thus increasing the parameter weights and avoiding the problem of the second difference being negative. It should be noted that if the uth mutation point is the last mutation point, then the difference between the uth mutation point and the previous mutation point is calculated as the second difference for the uth mutation point.

[0046] C u This value reflects whether the humidity data at the (u+1)th mutation point has increased significantly compared to the uth mutation point. A larger value indicates higher soil humidity at the (u+1)th mutation point compared to the uth mutation point, thus reflecting a greater likelihood of a rapid increase in soil humidity in the drip-irrigated area. uIt can reflect whether the soil moisture in the current drip irrigation area has increased significantly near the u-th mutation point. The larger the value, the greater the possibility that the soil moisture began to gradually increase from the u-th mutation point.

[0047] The time between the maximum value of the time lag confidence of all abrupt change points in the current humidity sequence and the start of irrigation is recorded as the lag time t, which characterizes the lag time of soil moisture at the root position of sand-cultured celery in the drip irrigation area compared to irrigation by the integrated water and fertilizer machine.

[0048] S2: Obtain the rising sequence at the current moment based on the abrupt change point with the highest time-delay confidence in the humidity sequence at the current moment, and divide the rising sequence into multiple subsequences based on the abrupt change point in the rising sequence; obtain the rising oscillation coefficient at the current moment based on the dispersion of the shortest distance between all data in the rising sequence at the current moment and its fitted line, the dispersion of the slope of the fitted line corresponding to all subsequences in the rising sequence, and the difference in the number of abrupt change points between the humidity sequence at the current moment and the rising sequence.

[0049] Furthermore, after obtaining the lag time, the soil moisture fluctuation at the root location of the sand-cultivated celery can be analyzed, and the soil moisture data after the lag time t seconds can be predicted by combining the data of the period of moisture increase and the fluctuation. This allows for the determination of whether irrigation needs to be stopped in the current drip irrigation area, thereby ensuring celery growth while saving water and fertilizer, and achieving precise control of alternating water and fertilizer irrigation.

[0050] Because the flow of water and fertilizer in the soil is not fixed, and water and fertilizer can penetrate to deeper layers, there will inevitably be fluctuations in soil moisture during the process of increasing soil moisture.

[0051] The sequence following the point of highest time-delay confidence in the current humidity sequence is denoted as the current rising sequence. A linear fitting algorithm is used to fit a straight line to the rising sequence, and the shortest distance between each element in the rising sequence and the fitted line is calculated. The variance of all shortest distances is then calculated and denoted as the first degree of dispersion at the current time. The first degree of dispersion reflects the degree of fluctuation in soil moisture during the rising process; a larger value indicates a greater fluctuation in the rising soil moisture.

[0052] Furthermore, although the first degree of dispersion can reflect the degree of fluctuation of soil moisture during the rising process, it does not reflect the direction of fluctuation. Therefore, there may be cases where soil moisture fluctuates frequently but the degree of dispersion between the shortest distances is small, which requires further analysis.

[0053] The rising sequence is divided into multiple subsequences by identifying all abrupt changes in the current time step. A linear fitting algorithm is then used to fit a straight line to each subsequence. The variance of the slope of the fitted lines for all subsequences is calculated and denoted as the second degree of dispersion at the current time step. The second degree of dispersion reflects the irregularity of the fluctuation direction in the rising sequence; a larger value indicates more frequent fluctuations in soil moisture during the rise, such as rapid increases followed by slow decreases or even decreases. This makes predictions less reliable based on overall data and more reliant on recent data.

[0054] As a preferred implementation, the rising oscillation coefficient at the current moment is obtained based on the dispersion of the shortest distance between all data in the rising sequence and its fitted straight line at the current moment, the dispersion of the slope of the fitted straight line corresponding to all subsequences in the rising sequence, and the difference in the number of abrupt change points between the current humidity sequence and the rising sequence. This coefficient is used to characterize the degree of oscillation of the soil moisture data during the rising process before the current moment.

[0055] In this embodiment, the rising oscillation coefficient at the current moment is denoted as D, and its specific expression is as follows: In the formula, D is the rising oscillation coefficient at the current moment, F is the first degree of dispersion at the current moment, G is the second degree of dispersion at the current moment, and H is the difference between the number of abrupt changes in the humidity sequence at the current moment and the number of abrupt changes in the rising sequence. It should be noted that the minimum value of H is 1, and it cannot be 0.

[0056] H reflects the number of abrupt changes during periods of stable soil moisture. A smaller value indicates more accurate sensor data collection, thus avoiding the risk of misjudgment due to environmental interference. The rising oscillation coefficient reflects the degree of oscillation in soil moisture data during the rising process before the current moment. A larger value indicates greater fluctuations in soil moisture during the rising process due to the uncertainty of water and fertilizer flow in the soil, resulting in poorer regularity of soil moisture rising data and making it less suitable for prediction using long-term historical data.

[0057] S3: Based on the dispersion of the flow sequence at the current moment and the distance between the flow sequence and the rising sequence, obtain the irrigation stability coefficient at the current moment, and combine it with the rising oscillation coefficient at the current moment to obtain the smoothing coefficient at the current moment. Then, predict the humidity data after the lag time after the current moment and determine whether irrigation needs to be stopped.

[0058] Furthermore, integrated water and fertilizer systems first dissolve soluble fertilizers in water before applying the solution. However, since most fertilizers undergo a thermal reaction upon dissolution, and different fertilizers have varying dissolution rates, they may react with each other after mixing, producing sediment and affecting the stability of drip irrigation. Therefore, it is necessary to analyze the fluctuation characteristics of irrigation flow and study its impact on the fluctuations during soil moisture rise to achieve more precise alternating irrigation control.

[0059] As a preferred implementation, the irrigation stability coefficient at the current moment is obtained based on the dispersion of the flow sequence at the current moment and the distance between the flow sequence and the rising sequence, which is used to characterize the stability of the flow data in the current drip irrigation area at the current moment.

[0060] In this embodiment, the irrigation stability coefficient at the current moment is denoted as K, and its specific expression is as follows: In the formula, K is the irrigation stability coefficient at the current time; L is the variance of all data in the flow sequence at the current time; W is the DTW distance between the flow sequence at the current time and the rising sequence; τ is a preset constant. To avoid the denominator being 0, the integer range is [0.001, 0.01]. The value has little impact on the calculation and can be ignored. In this embodiment, τ is taken as 0.005. The implementer can choose the value himself.

[0061] A smaller L value indicates a more stable irrigation flow rate during the irrigation process. W reflects whether the irrigation flow rate has a significant impact on humidity changes; a larger value indicates a smaller impact of the irrigation flow rate on soil moisture changes. K reflects the stability of the flow rate data in the current drip irrigation area at the current moment; a smaller value indicates a less stable irrigation flow rate at the current moment. The irrigation stability coefficient can supplement the soil moisture rise oscillation coefficient, thereby further determining whether to make predictions based on historical or recent data.

[0062] Furthermore, although soil moisture fluctuates during irrigation, it generally shows a clear upward trend. Therefore, this application employs the classic cubic exponential smoothing algorithm to predict soil moisture data. In the cubic exponential smoothing algorithm, the selection of the smoothing coefficient is crucial. A larger smoothing coefficient results in a faster response to the data and a greater focus on recent data for prediction; a smaller smoothing coefficient results in a greater focus on predicting based on overall data. An inappropriate selection of the smoothing coefficient will directly affect the prediction accuracy.

[0063] In a preferred embodiment, the smoothing coefficient for the current moment is obtained based on the rising oscillation coefficient and the irrigation temperature coefficient. In this embodiment, the smoothing coefficient for the current moment is denoted as α, and its specific expression is: In the formula, α is the smoothing coefficient at the current time, D is the rising oscillation coefficient at the current time, K is the irrigation stability coefficient at the current time, and exp() is an exponential function with the natural constant e as the base.

[0064] The smaller the (D / K) ratio, the more stable the irrigation flow rate at the current moment, the more stable the soil moisture rise process, and the more uniform the water and fertilizer flow. In this case, the more moisture can be predicted based on the overall moisture data. Conversely, the larger the (D / K) ratio, the more unstable the irrigation flow rate data, the greater the fluctuation in the soil moisture rise process, and the more necessary it is to predict moisture based on recent data.

[0065] The rising sequence and smoothing coefficient at the current moment are used as inputs to a triple exponential smoothing algorithm, outputting the predicted humidity value for the next t seconds after the current moment. When the predicted humidity value at the t-th second after the current moment is greater than or equal to a preset humidity threshold, the irrigation of the fertigation machine is stopped, and the remaining water and fertilizer in the pipes are used to complete the final irrigation of the sand-cultured celery in the current drip irrigation area. The preset humidity threshold is the soil moisture data when the soil moisture reaches the irrigation requirements of the sand-cultured celery. Since the humidity data is normalized in this embodiment, the preset humidity threshold in this embodiment is 1.

[0066] Furthermore, for the next group that needs irrigation, the water and fertilizer ratio is reset, and then irrigation is controlled in the same way, thereby achieving precise alternating irrigation control of water and fertilizer integration for sand-cultivated celery.

[0067] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, specific embodiments of this specification have been described above. Additionally, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0068] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0069] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them; modifications to the technical solutions described in the foregoing embodiments, or equivalent substitutions of some of the technical features, do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A water and fertilizer integrated irrigation control method for sand-cultivated celery planting, characterized in that, The method comprises the following steps: Real-time acquisition of humidity data and flow data at each time in the drip irrigation area, and then acquisition of a humidity sequence and a flow sequence at the current time; When the humidity data at the current time is greater than a preset prediction threshold, humidity data prediction is started, and the prediction process is as follows: S1: All mutation points in the humidity sequence at the current time are acquired, a time lag confidence of each mutation point is acquired according to the difference between the discrete degree of all humidity data before the mutation point and the discrete degree of all humidity data after the mutation point, and the difference between the next mutation point and the mutation point, and a lag time length is acquired according to the maximum value in the time lag confidence of all mutation points; S2: An ascending sequence at the current time is acquired according to all data after the mutation point with the maximum time lag confidence in the humidity sequence at the current time, and the ascending sequence is divided into multiple subsequences according to the mutation points in the ascending sequence; an ascending oscillation coefficient at the current time is acquired according to the discrete degree of the shortest distance between all data in the ascending sequence at the current time and a fitting straight line, the discrete degree of the slope of the fitting straight line corresponding to all subsequences in the ascending sequence, and the difference in the number of mutation points between the humidity sequence at the current time and the ascending sequence; S3: An irrigation stability coefficient at the current time is acquired according to the discrete degree of the flow sequence at the current time and the distance between the flow sequence and the ascending sequence, and a smoothing coefficient at the current time is acquired in combination with the ascending oscillation coefficient at the current time, the smoothing coefficient and the ascending sequence are taken as inputs of a cubic exponential smoothing algorithm, and then humidity data at a time lag of the lag time length after the current time is predicted, and it is judged whether irrigation needs to be stopped; The calculation formula of the rising oscillation coefficient at the current time is: ; in the formula, is the rising oscillation coefficient at the current time, is the first dispersion degree at the current time, is the second dispersion degree at the current time, is the difference between the number of mutation points in the humidity sequence at the current time and the number of mutation points in the rising sequence at the current time; wherein the first dispersion degree at the current time refers to the variance of the shortest distance between all data in the rising sequence at the current time and the fitting straight line thereof; the second dispersion degree at the current time refers to the variance of the slope of the fitting straight line corresponding to all sub-sequences in the rising sequence at the current time; The calculation formula of the irrigation stability coefficient at the current time is: ; in the formula, is the irrigation stability coefficient at the current time; is the variance of all data in the flow sequence at the current time; is the DTW distance between the flow sequence at the current time and the rising sequence; is a preset constant, and the value range is [0.001, 0.01]. The calculation formula of the smoothing coefficient of the current time is: ; in the formula, is the smoothing coefficient of the current time, is the rising oscillation coefficient of the current time, is the irrigation stability coefficient of the current time, is an exponential function with the natural constant e as the base number.

2. The water and fertilizer integrated irrigation control method for sand oysterplanting of claim 1, wherein, The humidity sequence and the flow sequence at the current time refer to sequences composed of humidity data and flow data respectively in chronological order from the starting irrigation time to the current time.

3. The water and fertilizer integrated irrigation control method for sand oysterplanting of claim 1, wherein, The calculation formula of the time lag confidence of each mutation point is: ; in the formula, is the time lag confidence of the u-th mutation point; is the first difference value of the u-th mutation point; is the difference value between the u+1-th mutation point and the u-th mutation point; is an exponential function with a natural constant e as a base; wherein, the first difference value of each mutation point is obtained by calculating the dispersion degree of all humidity data before each mutation point in the humidity sequence and the dispersion degree of all humidity data after each mutation point, respectively; and the absolute difference value between the two dispersion degrees is recorded as the first difference value of each mutation point.

4. The water and fertilizer integrated irrigation control method for sand oysterplanting of claim 1, wherein, The lag time length is the time length between the time corresponding to the maximum value of the time lag confidence of all mutation points in the humidity sequence at the current time and the starting irrigation time.

5. The water and fertilizer integrated irrigation control method for sand oysterplanting according to claim 1, wherein, The specific process of judging whether irrigation needs to be stopped is that the lag time length is recorded as t seconds, when the humidity prediction value at the tthsecond after the current time is greater than or equal to a preset humidity threshold, irrigation needs to be stopped; otherwise, irrigation does not need to be stopped; the humidity prediction value is the predicted humidity data.

Images