Breeding environment detection system based on internet of things

Abstract

The present application relates to the technical field of environmental detection, and more particularly to a breeding environment detection system based on the Internet of Things, which specifically comprises a temperature sensor module, a data caching module, a data processing module and a control and display module, the temperature sensor module is used for collecting temperature data in the breeding environment, the data caching module is used for storing the temperature data, the data processing module is used for executing an adaptive data filtering method, and the control and display module is used for displaying the processed breeding environment parameter data. The adaptive data filtering method adopted by the present application combines a dynamic threshold setting algorithm and a spectrum analysis technology, dynamically adjusts the threshold according to multiple factors such as different seasons, breeding stages and fish population density and real-time water temperature data changes, the filtering is more in line with the actual situation, and the noise is accurately removed; and through real-time collection of water temperature data for short-time spectrum analysis, the main frequency component and amplitude are determined, the data characteristics are more accurately grasped, and effective data are screened out.

Description

Technical Field

[0001] This invention relates to the field of environmental monitoring technology, and more specifically to an Internet of Things-based aquaculture environment monitoring system. Background Technology

[0002] With the development of large-scale and intensive aquaculture, precise monitoring and control of the fishpond environment are crucial for improving yields and ensuring the healthy growth of fish. Water temperature, as one of the key parameters in the fishpond environment, directly affects fish metabolism, growth rate, immune function, and reproductive capacity. A suitable water temperature range can promote fish appetite and digestion, improving feed utilization; while abnormal fluctuations in water temperature, whether too high or too low, can lead to stress responses, decreased immunity, and increased susceptibility to disease or even death in fish. Furthermore, changes in water temperature are also interconnected with other environmental factors such as dissolved oxygen levels and microbial activity, collectively affecting the balance of the fishpond ecosystem.

[0003] However, in the actual monitoring of fishpond aquaculture environments, accurately obtaining reliable water temperature data faces many challenges. On the one hand, the surrounding environment of fishponds is complex, with various potential sources of interference. For example, the electromechanical equipment used for aeration, water exchange, and feeding in fishponds generates electromagnetic interference during operation, the frequency and intensity of which vary depending on the type of equipment and its operating status. At the same time, factors such as water flow, fish movement, and surface fluctuations caused by natural wind can lead to fluctuations and noise in the data collected by water temperature sensors. These noise signals are intertwined with the actual water temperature change signals, making them difficult to distinguish directly.

[0004] Traditional data filtering methods have significant limitations when processing fishpond water temperature data. Common simple moving average filtering methods merely average data within a certain time window, failing to effectively distinguish between noise and the characteristic differences in actual water temperature changes. When dealing with noises of different frequency characteristics, such as high-frequency electromagnetic interference and low-frequency water flow noise, the fixed weighting coefficients used in averaging often over-smooth the actual water temperature trend, leading to data distortion and an inability to accurately reflect the actual dynamic changes in water temperature.

[0005] Some filtering methods based on fixed thresholds often rely on experience or analysis of limited data, making it difficult to adapt to the dynamic changes in the fishpond aquaculture environment. For example, the normal range and rate of water temperature variation differ under different seasons, different aquaculture stages, and different fish densities. Fixed thresholds cannot be adjusted in real time according to these changes, easily leading to misjudgments. They may filter out normal water temperature changes as noise, or retain noise as normal data, thus affecting the accurate assessment of the fishpond aquaculture environment and the formulation of subsequent control decisions.

[0006] In summary, due to the special and complex nature of the fishpond aquaculture environment, traditional data filtering methods are difficult to effectively meet the requirements for accurate and reliable collection of water temperature data. Therefore, there is an urgent need for a new data filtering algorithm that can adapt to changes in the fishpond aquaculture environment and accurately identify and filter noise in order to improve the performance and data quality of the fishpond aquaculture environment monitoring system. Summary of the Invention

[0007] In view of the above-mentioned shortcomings of the existing technology, the present invention provides an Internet of Things-based aquaculture environment monitoring system, which can effectively solve the problems mentioned in the existing technology.

[0008] To achieve the above objectives, the present invention provides the following technical solution:

[0009] This invention provides an Internet of Things-based aquaculture environment monitoring system, including a temperature sensor module, a data cache module, a data processing module, and a control and display module;

[0010] The temperature sensor module is installed at different locations and depths in the fishpond to collect temperature data in the aquaculture environment.

[0011] The data caching module is connected to the temperature sensor module and is used to store the collected temperature data;

[0012] The data processing module is connected to the data caching unit and the data transmission unit respectively, and is used to execute an adaptive data filtering method to process the temperature data and transmit the processed data to the control and display module.

[0013] The control and display module is used to display the processed aquaculture environment parameter data, and according to the preset aquaculture environment standard parameter range, it issues control commands to start the corresponding control equipment to regulate the fishpond aquaculture environment when the parameters are abnormal.

[0014] Furthermore, the adaptive data filtering method employs a dynamic threshold setting algorithm combined with spectrum analysis technology to dynamically adjust the filtering threshold based on different seasons, aquaculture stages, fish density information, and the characteristics of real-time collected water temperature data changes.

[0015] Furthermore, the specific settings for the adaptive data filtering method include:

[0016] Step 1: Establish a historical water temperature database for different seasons, aquaculture stages, and fish densities;

[0017] Step 2: Perform short-time spectrum analysis on the real-time collected water temperature data to determine the main frequency components and amplitudes in the data;

[0018] Step 3: Calculate the dynamic threshold range of the current water temperature data by combining the data characteristics in the historical database;

[0019] Step 4: Filter the water temperature data according to the dynamic threshold range to remove noisy data.

[0020] Furthermore, the historical water temperature database is categorized and stored according to season, aquaculture stage, and fish density;

[0021] The seasons include spring, summer, autumn and winter; the breeding stages include the fry stage, the rearing stage and the maturity stage; and the fish density includes low density, medium density and high density.

[0022] set up This represents a set of historical water temperature data under different seasons (s), aquaculture stages (m), and fish densities (d).

[0023] Furthermore, short-time spectrum analysis was performed on the real-time collected water temperature data to determine the main frequency components and amplitudes in the data, specifically including:

[0024] First, analyze the real-time collected water temperature data sequence. Frame segmentation is performed, where n is the sampling point number, and a Hamming window function is used. If the frame length is L, then the data of the kth frame... The calculation formula is:

[0025]

[0026] Next, a Fast Fourier Transform is performed on each frame of data to obtain the spectrum. The calculation formula is:

[0027]

[0028] Finally, calculate the spectral amplitude. The calculation formula is:

[0029]

[0030] By analyzing the amplitude spectrum, the main frequency components and their corresponding amplitude values ​​are determined; an amplitude threshold is then set. ,frequency , Where is the sampling frequency, if Then it is believed It is one of the main frequency components, and its amplitude value is recorded.

[0031] Furthermore, the specific method for calculating the dynamic threshold range of the current water temperature data in step 3 includes:

[0032] Calculate the average water temperature under different seasons, aquaculture stages, and fish densities based on historical data. and standard deviation For the historical water temperature data set under season s, aquaculture stage m, and fish density d The formula for calculating its mean is:

[0033]

[0034] in, Let be the number of historical data points under the conditions of season s, farming stage m, and fish density d; the formula for calculating the standard deviation is:

[0035]

[0036] Based on the short-time spectrum analysis results of the real-time acquired data, the influence of the main frequency components on the threshold is determined. Let the amplitude weighting coefficients corresponding to the main frequency components be... The upper limit of the dynamic threshold and lower limit The calculation formula is:

[0037]

[0038]

[0039] in, and This is a set constant, with a value range of 1-3.

[0040] Furthermore, the specific conditions for removing noise data in step 4 are as follows:

[0041] For each data point in the real-time collected water temperature data sequence If satisfied If the data point is valid, it is considered valid and retained; otherwise, it is considered noise data and removed.

[0042] Furthermore, the temperature sensor module includes multiple water temperature sensors, and a low-pass filter is connected in series on the signal acquisition line of the water temperature sensors, with the cutoff frequency set to 100kHz.

[0043] Furthermore, the control and display module displays the processed aquaculture environment parameter data, including water temperature data collected by various water temperature sensors, which includes raw data and filtered data.

[0044] At the same time, a safe water temperature range is set. When the filtered water temperature data exceeds this range or the frequency of abnormal fluctuations exceeds 5 times per minute, an early warning is activated, and a notification is sent to the aquaculture personnel.

[0045] The technical solution provided by this invention has the following advantages compared with the known prior art:

[0046] (1) The adaptive data filtering method adopted by the data processing module of the present invention combines dynamic threshold setting algorithm and spectrum analysis technology. It dynamically adjusts the threshold according to multiple factors such as different seasons, breeding stages and fish density, as well as real-time water temperature data changes. The filtering is more in line with the actual situation and accurately removes noise.

[0047] (2) This invention performs short-time spectrum analysis on real-time collected water temperature data to determine the main frequency components and amplitudes. Based on this, the filtering operation is further improved to more accurately grasp the data characteristics. Unlike conventional simple filtering methods, it can better screen effective data. Attached Figure Description

[0048] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without any creative effort.

[0049] Figure 1 This is a system module structure diagram of the present invention;

[0050] Figure 2 This is a flowchart of the adaptive data filtering method of the present invention. Detailed Implementation

[0051] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0052] The present invention will be further described below with reference to embodiments.

[0053] Example:

[0054] Reference Figures 1 to 2 The IoT-based aquaculture environment monitoring system includes a temperature sensor module, a data cache module, a data processing module, and a control and display module.

[0055] Temperature sensor modules are installed at different locations and depths in the fishpond to collect temperature data in the aquaculture environment. Specifically, multiple water temperature sensors are installed at different locations and depths in the fishpond. Considering the complexity of the aquaculture environment, the water temperature distribution in the fishpond is not uniform, and the water temperature at different locations and depths may vary. The multi-point distributed measurement method can comprehensively and accurately obtain the water temperature information of the entire fishpond, providing a detailed data foundation for subsequent precise aquaculture decisions, ensuring that the entire aquaculture environment will not be out of control due to local water temperature anomalies, and improving the reliability and representativeness of the measurement.

[0056] The data caching module is connected to the temperature sensor module and is used to store the collected temperature data;

[0057] The data processing module is connected to the data caching unit and the data transmission unit respectively. It is used to execute the adaptive data filtering method, process the temperature data, and transmit the processed data to the control and display module.

[0058] The control and display module is used to display the processed aquaculture environment parameter data, and according to the preset aquaculture environment standard parameter range, it issues control commands to start the corresponding control equipment to regulate the fishpond aquaculture environment when the parameters are abnormal.

[0059] This system integrates a temperature sensor module, a data caching module, a data processing module, and a control and display module into a complete aquaculture environment monitoring system. It achieves comprehensive acquisition, storage, processing, and feedback control of aquaculture environment temperature data. Through close collaboration between these modules, the entire system operates efficiently, aiming to improve its functionality and stability, reduce information transmission losses and errors between different stages, and thus provide strong support for precision aquaculture.

[0060] Furthermore, the adaptive data filtering method uses a dynamic threshold setting algorithm combined with spectrum analysis technology. Based on different seasons, aquaculture stages, fish density information, and the characteristics of real-time water temperature data changes, the filtering threshold is dynamically adjusted to filter the collected water temperature data, effectively distinguishing noise from real water temperature change signals and accurately extracting real water temperature data.

[0061] Furthermore, the specific settings for the adaptive data filtering method include:

[0062] Step 1: Establish a historical water temperature database for different seasons, aquaculture stages, and fish densities;

[0063] Step 2: Perform short-time spectrum analysis on the real-time collected water temperature data to determine the main frequency components and amplitudes in the data;

[0064] Step 3: Calculate the dynamic threshold range of the current water temperature data by combining the data characteristics in the historical database;

[0065] Step 4: Filter the water temperature data according to the dynamic threshold range to remove noisy data.

[0066] Furthermore, the historical water temperature database is categorized and stored according to season, aquaculture stage, and fish density;

[0067] The seasons include spring, summer, autumn and winter; the breeding stages include the fry stage, the growing stage and the maturity stage; and the fish density includes low density, medium density and high density.

[0068] set up This represents a set of historical water temperature data under different seasons (s), aquaculture stages (m), and fish densities (d).

[0069] Furthermore, short-time spectrum analysis was performed on the real-time collected water temperature data to determine the main frequency components and amplitudes in the data, specifically including:

[0070] First, analyze the real-time collected water temperature data sequence. Frame segmentation is performed, where n is the sampling point number, and a Hamming window function is used. If the frame length is L, then the data of the kth frame... The calculation formula is:

[0071]

[0072] Next, a Fast Fourier Transform is performed on each frame of data to obtain the spectrum. The calculation formula is:

[0073]

[0074] Finally, calculate the spectral amplitude. The calculation formula is:

[0075]

[0076] By analyzing the amplitude spectrum, the main frequency components and their corresponding amplitude values ​​are determined; an amplitude threshold is then set. ,frequency , Where is the sampling frequency, if Then it is believed It is one of the main frequency components, and its amplitude value is recorded.

[0077] Specifically, changes in fishpond water temperature are influenced by a variety of factors. These factors, when acting on the water, produce fluctuation signals of different frequencies. For example, electromagnetic interference caused by the operation of mechanical and electrical equipment typically manifests as high-frequency noise, with relatively high and stable frequency components. Water temperature changes caused by natural water flow, fish movement, and wind-induced surface fluctuations often have lower frequencies and a relatively wide frequency range, with amplitudes varying with time and environmental conditions. Short-time spectral analysis can convert the time-domain water temperature data sequence to the frequency domain, decomposing the complex water temperature signal into sinusoidal components of different frequencies, thus clearly revealing the distribution and corresponding amplitude of each frequency component in the signal.

[0078] Furthermore, the specific method for calculating the dynamic threshold range of the current water temperature data in step 3 includes:

[0079] Calculate the average water temperature under different seasons, aquaculture stages, and fish densities based on historical data. and standard deviation For the historical water temperature data set under season s, aquaculture stage m, and fish density d The formula for calculating its mean is:

[0080]

[0081] in, Let be the number of historical data points under the conditions of season s, farming stage m, and fish density d; the formula for calculating the standard deviation is:

[0082]

[0083] Based on the short-time spectrum analysis results of the real-time acquired data, the influence of the main frequency components on the threshold is determined. Let the amplitude weighting coefficients corresponding to the main frequency components be... The upper limit of the dynamic threshold and lower limit The calculation formula is:

[0084]

[0085]

[0086] in, and This is a set constant, with a value range of 1-3.

[0087] Specifically, the mean and standard deviation of water temperature calculated based on historical data reflect the statistical characteristics of the average level and fluctuation of water temperature under specific seasons, aquaculture stages, and fish density conditions. The mean represents the central trend of water temperature under those conditions, while the standard deviation measures the dispersion of water temperature data relative to the mean, i.e., the range of water temperature fluctuation under normal circumstances. By introducing these two statistics, a reasonable range for the current water temperature data can be preliminarily determined, roughly within the range of the mean plus or minus a certain number of standard deviations.

[0088] Meanwhile, considering the impact of the main frequency components and their amplitudes obtained from short-time spectral analysis on water temperature data, the threshold range was further adjusted. The amplitude weighting coefficients corresponding to the main frequency components reflect the degree of contribution of the factors represented by these frequency components, such as water flow fluctuations and electromagnetic interference, to the deviation of water temperature data from the normal range. For example, if the amplitude of a certain low-frequency water flow fluctuation is large, it indicates that its impact on water temperature is also significant, which may cause the water temperature to deviate to some extent from the threshold range calculated solely based on historical data statistical characteristics. Therefore, it is necessary to correct the threshold accordingly using amplitude weighting coefficients to more accurately adapt to changes in actual water temperature data.

[0089] Furthermore, the specific conditions for removing noise data in step 4 are as follows:

[0090] For each data point in the real-time collected water temperature data sequence If satisfied If the data point is valid, it is considered valid and retained; otherwise, it is considered noise data and removed.

[0091] Furthermore, the temperature sensor module includes multiple water temperature sensors, and a low-pass filter is connected in series on the signal acquisition line of the water temperature sensors, with the cutoff frequency set to 100kHz.

[0092] Specifically, in real-world environments, sensors are susceptible to various high-frequency interference signals, such as electromagnetic interference generated by equipment like aerators and water pumps. Low-pass filters can effectively block high-frequency noise signals above 100kHz, allowing only low-frequency water temperature signals to pass through. This improves the accuracy and stability of the sensor's data acquisition, adheres to the basic principles of removing noise interference and extracting useful signals in signal processing, and ensures the reliability of subsequent data processing and analysis.

[0093] Furthermore, the control and display module displays the processed aquaculture environment parameter data, including water temperature data collected by various water temperature sensors, which includes raw data and filtered data.

[0094] At the same time, a safe water temperature range is set. When the filtered water temperature data exceeds this range or the frequency of abnormal fluctuations exceeds 5 times per minute, an early warning is activated, and a notification is sent to the aquaculture personnel.

[0095] In one embodiment, the data processing module first establishes a historical water temperature database. Water temperature data from the fishpond over the past three years is collected and organized, categorized and stored according to season (spring: March-May; summer: June-August; autumn: September-November; winter: December-February of the following year), rearing stage (fry stage: 0-3 months; growing stage: 4-8 months; maturity stage: 9 months-harvest), and fish density (low density: less than 5 fish per cubic meter; medium density: 5-10 fish per cubic meter; high density: more than 10 fish per cubic meter). Under medium-density rearing conditions during the summer, 1000 historical water temperature data points were collected, with a mean of 28.5℃ and a standard deviation of 2.0℃.

[0096] Perform short-time spectral analysis on the real-time collected water temperature data. Set the frame length. sampling frequency This involves collecting one water temperature data point per second, dividing the data into frames using a Hamming window function, and then performing an FFT transform. When analyzing the spectral amplitude, an amplitude threshold is set. Analysis revealed that the main frequency components were around 0.01Hz and 0.05Hz, with corresponding amplitudes of... and Determine the amplitude weighting coefficients of the main frequency components. , ;

[0097] Calculate the dynamic threshold range. Set. , Then the upper limit of the dynamic threshold is:

[0098]

[0099]

[0100] Water temperature data is filtered based on a dynamic threshold range. If the real-time collected water temperature data sequence is [25.0℃, 26.5℃, 33.0℃, 24.5℃, 27.0℃], and 33.0℃ exceeds the upper limit of the dynamic threshold, it is determined to be noise data and removed; the remaining data is considered valid data.

[0101] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions will not cause the essence of the corresponding technical solutions to deviate from the protection scope of the technical solutions of the embodiments of the present invention.

Claims

1. An IoT-based aquaculture environment monitoring system, characterized in that, It includes a temperature sensor module, a data cache module, a data processing module, and a control and display module; The temperature sensor module is installed at different locations and depths in the fishpond to collect temperature data in the aquaculture environment. The data caching module is connected to the temperature sensor module and is used to store the collected temperature data; The data processing module is connected to the data caching unit and the data transmission unit respectively, and is used to execute an adaptive data filtering method to process the temperature data and transmit the processed data to the control and display module. The control and display module is used to display the processed aquaculture environment parameter data, and according to the preset aquaculture environment standard parameter range, it issues control commands to start the corresponding control equipment to regulate the fishpond aquaculture environment when the parameters are abnormal.

2. The IoT-based aquaculture environment monitoring system according to claim 1, characterized in that, The adaptive data filtering method uses a dynamic threshold setting algorithm combined with spectrum analysis technology to dynamically adjust the filtering threshold based on different seasons, aquaculture stages, fish density information, and the characteristics of real-time collected water temperature data changes.

3. The IoT-based aquaculture environment monitoring system according to claim 2, characterized in that, The specific settings of the adaptive data filtering method include: Step 1: Establish a historical water temperature database for different seasons, aquaculture stages, and fish densities; Step 2: Perform short-time spectrum analysis on the real-time collected water temperature data to determine the main frequency components and amplitudes in the data; Step 3: Calculate the dynamic threshold range of the current water temperature data by combining the data characteristics in the historical database; Step 4: Filter the water temperature data according to the dynamic threshold range to remove noisy data.

4. The IoT-based aquaculture environment monitoring system according to claim 3, characterized in that, The historical water temperature database is stored in categories according to season, aquaculture stage, and fish density. The seasons include spring, summer, autumn and winter; the breeding stages include the fry stage, the rearing stage and the maturity stage; and the fish density includes low density, medium density and high density. set up This represents a set of historical water temperature data under different seasons (s), aquaculture stages (m), and fish densities (d).

5. The IoT-based aquaculture environment monitoring system according to claim 3, characterized in that, The step of performing short-time spectrum analysis on the real-time collected water temperature data to determine the main frequency components and amplitudes in the data specifically includes: First, analyze the real-time collected water temperature data sequence. Frame segmentation is performed, where n is the sampling point number, and a Hamming window function is used. If the frame length is L, then the data of the kth frame... The calculation formula is: Next, a Fast Fourier Transform is performed on each frame of data to obtain the spectrum. The calculation formula is: Finally, the spectral amplitude is calculated. The calculation formula is: By analyzing the amplitude spectrum, the main frequency components and their corresponding amplitude values ​​are determined; an amplitude threshold is then set. ,frequency , Where is the sampling frequency, if Then it is believed It is one of the main frequency components, and its amplitude value is recorded.

6. The IoT-based aquaculture environment monitoring system according to claim 3, characterized in that, The method for calculating the dynamic threshold range of the current water temperature data in step 3 specifically includes: Calculate the average water temperature under different seasons, aquaculture stages, and fish densities based on historical data. and standard deviation For the historical water temperature data set under season s, aquaculture stage m, and fish density d The formula for calculating its mean is: in, Let be the number of historical data points under the conditions of season s, farming stage m, and fish density d; the formula for calculating the standard deviation is: Based on the short-time spectrum analysis results of the real-time acquired data, the influence of the main frequency components on the threshold is determined. Let the amplitude weighting coefficients corresponding to the main frequency components be... The upper limit of the dynamic threshold and lower limit The calculation formula is: in, and This is a set constant, with a value range of 1-3.

7. The IoT-based aquaculture environment monitoring system according to claim 3, characterized in that, The specific conditions for removing noise data in step 4 are as follows: For each data point in the real-time collected water temperature data sequence If satisfied If the data point is valid, it is considered valid and retained; otherwise, it is considered noise data and removed.

8. The IoT-based aquaculture environment monitoring system according to claim 1, characterized in that, The temperature sensor module includes multiple water temperature sensors, and a low-pass filter is connected in series on the signal acquisition line of the water temperature sensors, with the cutoff frequency set to 100kHz.

9. The IoT-based aquaculture environment monitoring system according to claim 1, characterized in that, The control and display module displays processed aquaculture environment parameter data, including water temperature data collected by various water temperature sensors. The water temperature data includes raw data and filtered data. At the same time, a safe water temperature range is set. When the filtered water temperature data exceeds this range or the frequency of abnormal fluctuations exceeds 5 times per minute, an early warning is activated, and a notification is sent to the aquaculture personnel.

Images