White beech mushroom growth environment parameter monitoring method and system

Abstract

The invention relates to the technical field of environment monitoring, in particular to a white beech mushroom growth environment parameter monitoring method and system. Comprising the following steps: acquiring temperature data points collected by each sensor at each moment in a white beech mushroom growth environment, and forming temperature time sequence data of each sensor; determining the abnormal degree of each temperature data point according to the temperature time sequence data; marking the temperature data points of which the abnormal degrees are greater than a first threshold value as abnormal data points; and if the duration time of the abnormal data point is greater than a second threshold value, performing early warning on the white beech mushroom growth environment. By monitoring the parameters in the growth environment of the white beech mushrooms, the normal growth environment of the white beech mushrooms is ensured, so that the yield and quality of the white beech mushrooms are improved.

Description

Technical Field

[0001] The invention relates to the technical field of environmental monitoring, and in particular to a method and system for monitoring parameters of the growing environment of Pleurotus eryngii. Background Art

[0002] White jade mushroom is a common edible fungus. The cultivation method of white jade mushroom is usually in a special culture medium in a sterile environment; too high or too low temperature in the growth environment may inhibit the growth of mushrooms; insufficient humidity will cause the mushrooms to shrink, and too high humidity may cause mold or bacteria to grow; inappropriate light may affect the development of mushrooms; poor ventilation may lead to carbon dioxide accumulation and affect the quality of mushrooms; unsuitable pH value may affect the growth of mycelium and the health of mushrooms; therefore, in order to improve the yield and quality of white jade mushrooms, it is necessary to monitor the growth environment parameters of white jade mushrooms to ensure that the mushrooms grow under optimal conditions.

[0003] In order to ensure that Agaricus bisporus grows under the best conditions, the temperature data of its growth environment is monitored and abnormal temperature is identified. However, since there is a regulation system in the Agaricus bisporus greenhouse that controls conditions such as temperature and humidity, the regulation system will produce large temperature fluctuations when adjusting the temperature of the greenhouse, which will affect the temperature data monitored by the surrounding sensors, thereby affecting the reliability of monitoring the temperature data. Summary of the invention

[0004] In order to solve the technical problem that the temperature fluctuations generated during temperature adjustment affect the temperature data monitored by sensors at different positions, and thus affect the reliability of temperature monitoring of the white jade mushroom growth environment, the purpose of the present invention is to provide a method and system for monitoring parameters of the white jade mushroom growth environment. The technical solutions adopted are as follows:

[0005] In a first aspect, the present invention provides a method for monitoring parameters of a white jade mushroom growth environment, the monitoring method comprising: obtaining temperature data points collected by each sensor in the white jade mushroom growth environment at each time to form temperature time series data of each sensor; determining the degree of abnormality of each temperature data point based on the temperature time series data; marking the temperature data point whose degree of abnormality is greater than a first threshold as an abnormal data point; and if the duration of the abnormal data point is greater than a second threshold, issuing an early warning for the white jade mushroom growth environment.

[0006] The present invention collects temperature data points of all temperature sensors in time series, and each temperature data point is the value of a temperature point. All temperature data points of each sensor in time series form a temperature time series data. There are as many temperature time series data as there are sensors. The temperature data points in each temperature time series data and the relationship between the temperature data points are analyzed to determine all abnormal data points. When the number of abnormal data points that continue to appear is greater than a certain threshold, it indicates that an abnormal situation has occurred in the growth environment of the white jade mushroom, and an early warning needs to be sent to the management terminal, and the sensor and the temperature control system of the greenhouse need to be manually checked to eliminate the abnormal situation and ensure the normal operation of the temperature control system.

[0007] Further, according to the temperature time series data, the abnormality of each temperature data point is determined; specifically including: determining the danger possibility of each temperature data point according to the deviation of the temperature data point in the temperature time series data; averaging the average danger possibility of all temperature data points in the temperature time series data of the nth sensor to obtain the average danger possibility of the temperature data point of the nth sensor; determining the temperature breakthrough rate of the nth sensor according to the average danger possibility of the temperature data point of the nth sensor and the fluctuation of the temperature time series of the nth sensor; determining the abnormality of each temperature data point in the nth sensor according to the temperature breakthrough rate of the nth sensor, the temperature breakthrough allowable degree of the temperature time series of the nth sensor and the danger possibility of each temperature data point in the nth sensor; traversing the temperature time series data of each sensor to obtain the abnormality of all temperature data points; wherein n is a positive integer.

[0008] Furthermore, the danger possibility of each temperature data point is determined according to the deviation of the temperature data point in the temperature time series data; specifically including: determining the danger possibility of the i-th temperature data point of the n-th sensor according to the deviation of the i-th temperature data point in the n-th sensor, the deviation of the i-1-th temperature data point of the n-th sensor and the suitable temperature for the growth of Pleurotus eryngii; traversing the temperature time series data of each sensor to obtain the danger possibility of all temperature data points; wherein i is a positive integer.

[0009] Furthermore, the difference between the ith temperature data point and the suitable temperature for the growth of Pleurotus eryngii is calculated and the absolute value is taken as the deviation of the ith temperature data point.

[0010] Furthermore, the temperature breakthrough rate of the nth sensor is determined according to the average danger possibility of the nth sensor temperature data point and the fluctuation of the nth sensor temperature time series; specifically including: taking the product of the average danger possibility of the nth sensor temperature data point and the fluctuation of the nth sensor temperature time series as the temperature breakthrough rate of the nth sensor; determining the fluctuation of the nth sensor temperature time series according to the numerical relationship between the jth maximum point and the j'th maximum point in the nth sensor temperature time series data and the span between the jth maximum point and the j'th maximum point; the j'th maximum point is the maximum point in the nth sensor temperature time series data that is closest to the jth maximum point in time series; wherein j and j' are both positive integers.

[0011] Furthermore, the temperature breakthrough tolerance of the nth sensor temperature timing data is determined based on the synchronization between the nth sensor temperature timing data and the remaining N-1 sensor temperature timing data, and the average of the Pearson coefficients between the nth sensor temperature timing data and the remaining N-1 sensor temperature timing data; wherein n∈[1,N], N is a positive integer greater than 1.

[0012] Further, according to the mean of the characteristic difference between the characteristic point in the nth sensor temperature time series data and the characteristic point in the mth sensor temperature time series data, the synchronization of the nth sensor temperature time series data and the remaining N-1 sensor temperature time series data is determined; wherein m∈[1,N-1], m is a positive integer. The maximum point whose danger possibility is greater than the third threshold value is taken as the characteristic point.

[0013] Furthermore, for the i-th temperature data point in the temperature time series data of the n-th sensor, if the value of the i-th temperature data point is greater than the value of the i-1-th temperature data point and greater than the value of the i+1-th temperature data point, then the i-th temperature data point is taken as a maximum point; where i is a positive integer; all temperature data points in the temperature time series data of the n-th sensor are traversed to obtain multiple maximum points.

[0014] In a second aspect, the present invention provides a system for monitoring parameters of the growth environment of Pleurotus eryngii, the monitoring system comprising: a temperature data acquisition module, used to obtain temperature data points collected by each sensor in the growth environment of Pleurotus eryngii at each moment, to form temperature time series data of each sensor; a temperature data analysis module, used to determine the degree of abnormality of each temperature data point according to the temperature time series data; and mark the temperature data point whose degree of abnormality is greater than a first threshold as an abnormal data point; a temperature data early warning module, used to judge that if the duration of the abnormal data point is greater than a second threshold, then issue an early warning to the growth environment of Pleurotus eryngii.

[0015] The present invention has the following beneficial effects:

[0016] The present invention screens out abnormal data points by analyzing the temperature time series data, and then determines whether to send an early warning based on the persistence of the abnormal data points in time. The mutual influence between the temperature data points in the time series is taken into account, and the early warning error caused by the abnormal judgment of a single temperature point is avoided.

[0017] In order to make the white jade mushroom grow under the best conditions, the present invention obtains a number of temperature time series data through a number of temperature sensors, obtains the danger possibility by analyzing the trend of the temperature data points, and obtains the temperature breakthrough allowable degree according to the historical status of the temperature time series data of each sensor combined with the relationship between each time series, and finally obtains the abnormal degree of the data point, providing good data support for subsequent abnormality detection.

[0018] The present invention monitors the parameters in the growth environment of white jade mushrooms to ensure that the growth environment of white jade mushrooms is normal, thereby improving the yield and quality of white jade mushrooms. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention 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 invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0020] Figure 1 A flow chart of a method for monitoring parameters of the growth environment of Pleurotus eryngii provided by one embodiment of the present invention;

[0021] Figure 2 A structural diagram of a system for monitoring the growth environment parameters of Pleurotus eryngii provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0022] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of a method and system for monitoring the growth environment parameters of Pleurotus eryngii proposed in accordance with the present invention, its specific implementation, structure, features and effects, in conjunction with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0023] 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 invention belongs.

[0024] The following is a detailed description of a method and system for monitoring the growth environment parameters of Pleurotus eryngii provided by the present invention in conjunction with the accompanying drawings.

[0025] See also Figure 1 , which shows a flow chart of a method for monitoring parameters of the white jade mushroom growth environment provided by an embodiment of the present invention. First, the temperature data points collected by each sensor in the white jade mushroom growth environment at each time are obtained to form temperature time series data of each sensor. The sensor in the embodiment of the present invention refers to a sensor that can collect temperature data, which can be a temperature sensor or other sensor with a temperature data collection function. All temperature sensors in the embodiment of the present invention continuously collect temperatures in time series, and each temperature data point is the value of a temperature point. All temperature data points of each sensor in time series form a temperature time series data. There are as many temperature time series data as there are sensors.

[0026] Then, according to the temperature time series data of each sensor obtained above, the abnormality of each temperature data point is determined. Specifically, according to the deviation of each temperature data point, the danger possibility of each temperature data point is determined.

[0027] In the current growth environment of white jade mushroom, there are a total of N sensors and N temperature time series data. Each sensor collects I temperature data points, and each temperature time series data has I temperature data points. n represents the nth sensor among N sensors; i represents the ith temperature data point among I temperature data points. n∈[1,N], i∈[1,I], n, i, N and I are all positive integers.

[0028] The difference between the ith temperature data point and the suitable temperature for the growth of white jade mushroom is taken as the deviation of the ith temperature data point. Since the growth temperature of white jade mushroom is usually between 20℃-25℃, 22.5℃ is selected as the suitable temperature for the growth of white jade mushroom in the embodiment of the present invention. The difference between the ith temperature data point and 22.5 is taken as the deviation of the ith temperature data point.

[0029] According to the deviation of the ith temperature data point in the nth sensor, the deviation of the i-1th temperature data point in the nth sensor, and the suitable temperature for the growth of Pleurotus eryngii, the hazard possibility of the ith temperature data point in the nth sensor is determined. The temperature time series data of N sensors are traversed to obtain the hazard possibility of all temperature data points.

[0030] The average hazard probability of all temperature data points in the n-th sensor temperature time series data is averaged to obtain the average hazard probability of the n-th sensor temperature data point.

[0031] In the example of the present invention, for the i-th temperature data point in the n-th sensor temperature time series data, if the value of the i-th temperature data point is greater than the value of the i-1-th temperature data point and greater than the value of the i+1-th temperature data point, then the i-th temperature data point is taken as the maximum point. Traverse all temperature data points in the n-th sensor temperature time series data to obtain multiple maximum points. The n-th sensor temperature time series data has J maximum points, j∈[1,J]. Determine the absolute value of the time distance between the j-1-th maximum point and the j-th maximum point, determine the absolute value of the time distance between the j+1-th maximum point and the j-th maximum point, and take the maximum point of the absolute value of the time distance as the j'th maximum point.

[0032] According to the numerical relationship between the jth maximum point and the jth' maximum point in the nth sensor temperature time series data and the span between the jth maximum point and the jth' maximum point, the fluctuation of the nth sensor temperature time series is determined; the jth' maximum point is the maximum point in the nth sensor temperature time series data that is closest to the jth maximum point in time series; wherein j and j' are both positive integers. The product of the average danger probability of the nth sensor temperature data point and the fluctuation of the nth sensor temperature time series is taken as the temperature breakthrough rate of the nth sensor.

[0033] Among the temperature data points, the maximum value point whose danger possibility is greater than the third threshold is taken as the characteristic point. It can be understood that the characteristic point is both a temperature data point and a maximum value point, and the danger possibility of the characteristic point is greater than the third threshold.

[0034] According to the mean of the characteristic differences between the characteristic points in the temperature time series data of the nth sensor and the characteristic points in the temperature time series data of the mth sensor, the synchronization of the temperature time series data of the nth sensor and the temperature time series data of the remaining N-1 sensors is determined. Wherein, m∈[1,N-1], m is a positive integer. The mth sensor is any sensor different from the nth sensor.

[0035] According to the synchronization between the nth sensor temperature time series data and the remaining N-1 sensor temperature time series data, and the mean of the Pearson coefficients between the nth sensor temperature time series data and the remaining N-1 sensor temperature time series data, the temperature breakthrough tolerance of the nth sensor temperature time series is determined; wherein n∈[1,N], N is a positive integer greater than 1. The mean of the Pearson coefficients between the two sensor temperature time series data is a common technical means used by those skilled in the art, and will not be described in detail here.

[0036] According to the temperature breakthrough rate of the nth sensor, the temperature breakthrough allowance of the temperature time series of the nth sensor and the danger possibility of each temperature data point in the nth sensor, the abnormality degree of each temperature data point in the nth sensor is determined.

[0037] Using the same method, traverse the temperature time series data of each sensor to obtain the degree of abnormality of all temperature data points. Finally, mark the temperature data points whose degree of abnormality is greater than the first threshold as abnormal data points; abnormal data points are data points that need to be focused on. If the duration of the abnormal data point is greater than the second threshold, an early warning is issued for the growth environment of the white jade mushroom. In an embodiment of the present invention, according to the requirements of the growth environment of the white jade mushroom, the first threshold is 0.8, the second threshold is 0.5, and the third threshold is 0.8. The method of the embodiment of the present invention can also be applied to the growth environment monitoring process of other similar mushrooms, fungi or vegetable plants, and the above-mentioned thresholds can be adaptively changed according to the needs of the actual growth environment.

[0038] Another possible embodiment of the present invention is to monitor the temperature data of the growth environment of the white jade mushroom to identify abnormal temperatures in order to ensure that the white jade mushroom grows under optimal conditions. However, since there is a regulating system in the white jade mushroom greenhouse that controls conditions such as temperature and humidity, the regulating system will produce large temperature fluctuations when regulating the temperature of the greenhouse, which will affect the temperature data monitored by the surrounding sensors, thereby affecting the reliability of monitoring the temperature data. In order to make the white jade mushroom grow under optimal conditions, the embodiment of the present invention obtains several temperature time series in the greenhouse by installing several temperature sensors, obtains the danger possibility of the temperature data point by analyzing the trend of the temperature data point, and obtains the sensor temperature breakthrough allowable degree according to the historical state of each sensor temperature time series combined with the relationship between each sensor temperature time series, and finally obtains the abnormal degree of the temperature data point, providing good data support for subsequent abnormal monitoring.

[0039] In order to ensure that the growth environment of white jade mushroom is normal, it is necessary to collect real-time parameters in the growth environment of white jade mushroom for analysis and monitoring, including the following steps:

[0040] Step S1: Collect data and perform preprocessing.

[0041] In order to adapt to a large range, commercial cultivation of white jade mushrooms is usually carried out in greenhouses. White jade mushroom greenhouses usually use steel frame structures to support the gravity of the greenhouse and greenhouse equipment; the exterior of the greenhouse is usually covered with transparent plastic film or glass to ensure that light can penetrate, and the interior is equipped with ventilation, heating and humidity control systems to provide a suitable growth environment. In order to ensure that the growth environment of white jade mushrooms is good, it is necessary to monitor the growth environment of white jade mushrooms in real time. In order to monitor the overall growth environment of the greenhouse in real time, it is necessary to install multiple temperature sensors at different locations in the greenhouse and obtain the temperature parameters in the growth environment in real time. Each sensor corresponds to a temperature time series, and each temperature data point in the time series reflects the temperature data collected by the temperature sensor at each moment.

[0042] Step S2: Analyze the temperature data in the growth environment of Pleurotus eryngii.

[0043] For the temperature time series of each temperature sensor obtained by the above operation, the temperature data collected by different sensors will be different due to the different installation locations of the sensors. Therefore, the subsequent analysis of temperature anomalies needs to be combined with the individual conditions of each sensor. The process of processing the temperature time series of the growing environment of Pleurotus eryngii and obtaining the degree of abnormality of the temperature data point is as follows:

[0044] a. Analyze the hazardous potential of each sensor temperature.

[0045] Since the growth temperature of white jade mushroom is usually between 20℃-25℃, it is necessary to analyze whether the growth temperature of white jade mushroom at the current moment is outside the suitable temperature range or whether there is a trend of breaking through the suitable temperature. Therefore, it is necessary to analyze each temperature data point and its trend in the temperature time series on each sensor to obtain the temperature danger possibility of each sensor; if the temperature data changes outside the suitable temperature range, it means that the danger possibility of the temperature data point is high.

[0046] In order to analyze the difference between the collected temperature data and normal growth conditions, each temperature data point on the temperature time series of each sensor is subtracted from 22.5 and the absolute value is taken as the deviation, thereby obtaining the danger possibility of each temperature data point.

[0047] WK n,i =th[(p n,i -22.5)×(p n,i -p n,i-1 )]

[0048] Where n is the serial number of the sensor, i is the serial number of the temperature data point in the temperature time series data of the nth sensor, and WK n,i is the hazard probability of the ith temperature data point in the nth sensor temperature time series data, p n,i is the deviation of the ith temperature data point in the nth sensor temperature time series data, p n,i-1 The deviation of the i-1th temperature data point in the nth sensor temperature time series data, where th() is the hyperbolic tangent function.

[0049] The difference between the deviation of each temperature data point in the sensor temperature time series data and 22.5 (p n,i -22.5), the larger the value, the greater the deviation of the temperature data point, and therefore the closer the temperature data point is to the normal temperature range; and for the deviation difference (p n,i -p n,i-1), the larger the value is, the more likely the temperature data point is to move away from the normal temperature range. Therefore, the risk potential is high. This allows us to obtain the risk potential of the temperature data point in the sensor temperature time series data.

[0050] b. Analyze historical data to calculate the temperature limit of each sensor.

[0051] Regarding the danger possibility of the temperature data points of each sensor obtained by the above operation, due to the different locations of different sensors, the temperatures of sensors in different parts are different. There may be a sensor located around the temperature control device, which may cause the temperature of the sensor to be affected by the temperature control device, so that the temperature data obtained will exceed the normal growth temperature range of the white jade mushroom. Therefore, for the temperature sensor, it is necessary to analyze the temperature conditions of different sensor temperature time series at the same time, and then analyze and obtain the temperature breakthrough allowance of different sensors;

[0052] 1. Calculate the temperature breakthrough rate of each sensor based on the historical data in the temperature time series data.

[0053] For the temperature time series data of each sensor and the possibility of danger of the temperature data points obtained by the above operations, since different sensors are located in different parts of the greenhouse, and the temperature changes in different parts of the greenhouse will be different due to the uneven air flow and light factors in the greenhouse, it is necessary to analyze the fluctuation of the data in the temperature time series of different sensors and the possibility of danger of the data points in the temperature time series, so as to obtain the temperature breakthrough rate of the temperature time series data of different sensors.

[0054] For each temperature data point in the sensor temperature time series data, if the value of the temperature data point is the largest among its adjacent temperature data points (compared with the temperature data point adjacent to each other, the value of the temperature data point is the largest), it is recorded as a maximum point, thereby obtaining the volatility of the sensor temperature time series data.

[0055]

[0056] Where WB n represents the fluctuation of the nth sensor temperature time series data; j is the jth maximum point in the sensor temperature time series, j' is the maximum point in the sensor temperature time series that is closest to the jth maximum point in time; w n,j is the value of the jth maximum point in the nth sensor temperature time series data, w n,j' is the value of the j'th maximum point in the nth sensor temperature time series data; is the numerical mean of the temperature data points between the jth maximum point and the j'th maximum point in the temperature time series data of the nth sensor; t n(j, j') is the time span between the jth maximum point and the j'th maximum point in the nth sensor temperature time series data (the span indicates the total number of temperature data points); th() is the hyperbolic tangent function; for The larger the value, the smaller the time span between the maximum points in the sensor temperature time series data, and therefore the greater the fluctuation of the time series; The larger the value, the larger the maximum value of the sensor temperature time series data and the smaller the value of the temperature data point between the maximum value points, which indicates that the fluctuation of the time series is greater. In order to avoid the denominator being zero, the parameter adjustment coefficient is added to the denominator, = 0.01.

[0057] For the fluctuation of the temperature time series of each sensor, the possibility of danger of the temperature data points in the temperature time series of each sensor is combined. Since there are various control devices in the greenhouse, the temperature conditions in different parts will change differently, so the temperature breakthrough rate of each sensor can be combined. Some sensors may be located in ventilation areas, and the fluctuation of their temperature time series is large, but the overall possibility of danger is small. The sensor near the greenhouse insulation device has a higher possibility of danger, but the fluctuation of its temperature data is small. This sensor is not easy to break through the normal range, so the temperature breakthrough rate of each sensor data can be calculated.

[0058]

[0059] Where WT n is the temperature breakthrough rate of the nth sensor temperature time series; It is the average danger probability of the temperature data points in the nth sensor temperature time series data. The larger the value, the easier it is for the temperature data points in the sensor temperature time series to break through the normal growth range. Combined with the fluctuation degree WB of the sensor temperature time series data, n , where the volatility WB n Average risk probability The larger the value, the greater the fluctuation of the sensor temperature time series data and the higher the risk. It means that the sensor temperature time series fluctuates more strongly and is more likely to fluctuate out of the normal growth range. Therefore, it is positively correlated with the temperature breakthrough rate.

[0060] 2. Calculate the temperature limit based on historical sensor data.

[0061] The temperature breakthrough rate of each sensor's temperature time series data reflects the situation where the temperature time series data breaks through the growth range. However, due to the different locations of each sensor, the tolerance for the temperature breaking through the normal range in different locations is different. Since there is a temperature control device inside the greenhouse, the temperature of the greenhouse will be regulated in real time. If the sensor is located near the temperature control device, the sensor will be affected by the temperature control device, resulting in the temperature breaking through the normal range. And the temperature control device controls the temperature inside the greenhouse within the normal range. The temperature control device usually increases the temperature when the temperature inside the greenhouse drops, and increases the temperature when the temperature inside the greenhouse drops. The temperature change of the sensor near the control device is opposite to the temperature change of the rest of the normal parts. The temperature breakthrough tolerance of each sensor temperature series can be obtained by analyzing the difference between the temperatures of each sensor.

[0062] For each sensor temperature time series data, if the temperature data point on the time series is the largest or smallest among its adjacent temperature data points, it is recorded as a maximum point and a minimum point respectively. The maximum point in each sensor temperature time series data and the temperature data point whose danger possibility is greater than the preset threshold σ=0.8 are obtained and recorded as a feature point. The danger possibility of the feature point is large enough and it is an extreme point, which can reflect the change trend of the time series.

[0063] For the characteristic points in the acquired sensor temperature time series data, the acquired characteristic points are analyzed and compared with the characteristic points of other temperature sensors. For the characteristic points in any sensor temperature time series data, the closest distance between the characteristic points of other sensors and it in time series is obtained and recorded as its characteristic difference (the ordinal number of the characteristic point of one sensor in time series is a, and the minimum distance between the characteristic points on the other sensors and a is found; this characteristic difference is the gap between the characteristic points in different time series), and then the synchronization of the sensor temperature time series data and the other sensors is obtained;

[0064]

[0065] Where N is the number of sensors, m is any sensor of the nth sensor, and l n,m It is the mean of the characteristic differences between the characteristic points in the temperature time series data of the nth sensor and the characteristic points in the temperature time series data of the mth sensor. exp() is an exponential function with the natural constant e as the base. m∈[1,N-1], n∈[1,N], n, N, m, M are all positive integers, and n≠m.

[0066] Calculate the mean difference between the feature point of the nth sensor and the feature points of the remaining N-1 sensors The smaller the value, the smaller the difference between the characteristic point of the sensor and the characteristic points of other sensors, so the synchronization of the sensor with other sensors is better. Since the characteristic points on the time series of the sensor reflect the fluctuation of the sensor temperature time series data, the smaller the characteristic difference, the stronger the synchronization.

[0067] For the temperature data points of the characteristic points in the temperature time series data of each sensor, compare them with the temperature data points at the same time in the temperature time series data of other sensors to obtain their Pearson coefficients. The Pearson coefficient can reflect the correlation between data sets, and the average Pearson coefficient between the sensor and other sensors can be obtained, thereby obtaining the temperature breakthrough tolerance of each sensor.

[0068]

[0069] In the formula, is the mean value of the Pearson coefficient between the temperature time series of the nth sensor and the temperature time series of the other sensors, WY n is the temperature breakthrough tolerance of the nth sensor temperature time series, and th() is the hyperbolic tangent function.

[0070] According to the synchronization of the sensor temperature time series and the average value of the Pearson coefficient between the sensor temperature time series data, The larger the value, the higher the TB n The larger the value, the The smaller it is, the stronger the synchronization and the smaller the Pearson coefficient. Since the small Pearson coefficient indicates negative correlation in data integration, the temperature time series data of this sensor has strong synchronization with other sensors but is negatively correlated, indicating that the sensor is located in the temperature control part, so its temperature breakthrough tolerance is high.

[0071] c. Obtain the degree of abnormality of the temperature data point.

[0072]

[0073] In the formula, YC n,0 is the abnormal degree of the nth sensor temperature data point. Since the higher the temperature breakthrough rate and temperature breakthrough tolerance of the nth sensor temperature time series, the better the tolerance of danger, it is negatively correlated with the abnormal degree of the temperature data point. In order to avoid the denominator being zero, the adjustment coefficient is added to the denominator, = 0.01.

[0074] Finally, the abnormal degree of each sensor at the current moment is obtained and compared with the preset threshold ε = 0.8. If it is greater than the threshold, it is marked as an abnormal point and recorded in the database. Since the greenhouse will automatically control the temperature inside, when the time t of the abnormal point is greater than 0.5, it indicates that the abnormal situation is serious and an early warning needs to be sent to the management terminal. The sensors and the greenhouse temperature control system need to be manually checked to eliminate abnormal situations and ensure the normal operation of the temperature control system.

[0075] Based on the same inventive concept as the above method embodiment, the present invention also provides a system for monitoring the growth environment parameters of Pleurotus eryngii. Figure 2 , which shows a structural diagram of a Pleurotus eryngii growth environment parameter monitoring system provided by an embodiment of the present invention, including:

[0076] The temperature data acquisition module is used to obtain the temperature data points collected by each sensor in the growth environment of Pleurotus eryngii at various times to form the temperature time series data of each sensor.

[0077] The temperature data analysis module is used to determine the abnormality of each temperature data point according to the temperature time series data; and mark the temperature data point whose abnormality is greater than a first threshold as an abnormal data point.

[0078] The temperature data early warning module is used to determine that if the duration of the abnormal data point is greater than the second threshold, then issue an early warning for the growth environment of Pleurotus eryngii.

[0079] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0080] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A method for monitoring the growth environment parameters of Pleurotus eryngii, characterized in that: The monitoring method comprises: Obtain the temperature data points collected by each sensor in the growth environment of Pleurotus eryngii at each time, and form the temperature time series data of each sensor; Determining the degree of abnormality of each temperature data point according to the temperature time series data; Marking the temperature data point whose abnormality degree is greater than a first threshold as an abnormal data point; If the duration of the abnormal data point is greater than the second threshold, an early warning is issued for the growth environment of Pleurotus eryngii.

2. The method for monitoring the growth environment parameters of Pleurotus eryngii according to claim 1, characterized in that: Determine the abnormality of each temperature data point according to the temperature time series data; specifically include: Determining the danger possibility of each temperature data point according to the deviation of the temperature data point in the temperature time series data; The average hazard probability of all temperature data points in the temperature time series data of the nth sensor is averaged to obtain the average hazard probability of the temperature data point of the nth sensor; Determine the temperature breakthrough rate of the nth sensor according to the average danger probability of the nth sensor temperature data points and the fluctuation degree of the nth sensor temperature time series; Determine the abnormality of each temperature data point in the nth sensor according to the temperature breakthrough rate of the nth sensor, the temperature breakthrough allowance of the temperature time series of the nth sensor, and the danger possibility of each temperature data point in the nth sensor; Traverse the temperature time series data of each sensor to obtain the abnormality degree of all temperature data points; Wherein, n is a positive integer.

3. A method for monitoring the growth environment parameters of Pleurotus eryngii according to claim 2, characterized in that: Determine the danger possibility of each temperature data point according to the deviation of the temperature data point in the temperature time series data; specifically including: According to the deviation of the ith temperature data point in the nth sensor, the deviation of the i-1th temperature data point in the nth sensor, and the suitable temperature for the growth of Pleurotus eryngii, the danger possibility of the ith temperature data point in the nth sensor is determined; Traverse the temperature time series data of each sensor to obtain the danger probability of all temperature data points; Wherein, i is a positive integer.

4. The method for monitoring the growth environment parameters of Pleurotus eryngii according to claim 3, characterized in that: The difference between the ith temperature data point and the suitable temperature for the growth of Pleurotus eryngii is taken and the absolute value is taken as the deviation of the ith temperature data point.

5. The method for monitoring the growth environment parameters of Pleurotus eryngii according to claim 2, characterized in that: Determine the temperature breakthrough rate of the nth sensor based on the average danger probability of the nth sensor temperature data point and the fluctuation of the nth sensor temperature time series; specifically including: The product of the average danger probability of the nth sensor temperature data point and the fluctuation degree of the nth sensor temperature time series is taken as the temperature breakthrough rate of the nth sensor; Determine the fluctuation degree of the temperature time series of the nth sensor according to the numerical relationship between the jth maximum value point and the j'th maximum value point and the span between the jth maximum value point and the j'th maximum value point in the temperature time series data of the nth sensor; The j'th maximum value point is the maximum value point in the nth sensor temperature time series data that is closest to the jth maximum value point in time series; wherein j and j' are both positive integers.

6. The method for monitoring the growth environment parameters of Pleurotus eryngii according to claim 2, characterized in that: The temperature breakthrough tolerance of the nth sensor temperature time series is determined according to the synchronization between the nth sensor temperature time series data and the remaining N-1 sensor temperature time series data and the average of the Pearson coefficients between the nth sensor temperature time series data and the remaining N-1 sensor temperature time series data; wherein n∈[1,N], N is a positive integer greater than 1.

7. The method for monitoring the growth environment parameters of Pleurotus eryngii according to claim 6, characterized in that: Determine the synchronization of the nth sensor temperature time series data with the remaining N-1 sensor temperature time series data according to the average of the characteristic differences between the characteristic points in the nth sensor temperature time series data and the characteristic points in the mth sensor temperature time series data; Among them, m∈[1,N-1], m is a positive integer.

8. The method for monitoring the growth environment parameters of Pleurotus eryngii according to claim 7, characterized in that: The maximum point where the danger possibility is greater than the third threshold is used as the feature point.

9. A method for monitoring the growth environment parameters of Pleurotus eryngii according to claim 5 or 8, characterized in that: For the i-th temperature data point in the n-th sensor temperature time series data, if the value of the i-th temperature data point is greater than the value of the i-1-th temperature data point and greater than the value of the i+1-th temperature data point, then the i-th temperature data point is taken as the maximum value point; where i is a positive integer; Traverse all temperature data points in the temperature time series data of the nth sensor to obtain multiple maximum points.

10. A system for monitoring the growth environment parameters of Pleurotus eryngii, characterized in that: The monitoring system comprises: The temperature data acquisition module is used to obtain the temperature data points collected by each sensor in the growth environment of Pleurotus eryngii at various times to form the temperature time series data of each sensor; A temperature data analysis module, configured to determine the abnormality of each temperature data point according to the temperature time series data; and mark the temperature data point whose abnormality is greater than a first threshold as an abnormal data point; The temperature data early warning module is used to determine that the duration of the abnormal data point is greater than the second threshold value, and then issue an early warning to the growth environment of Pleurotus eryngii.

Images