Intelligent fishpond oxygenation system based on cloud-fog-side collaborative optimization and application

Abstract

The invention discloses an intelligent fishpond oxygenation system based on cloud-fog-side collaborative optimization and application. A cloud-fog-side communication architecture is adopted; the cloud is responsible for system-level data analysis and optimization control decision making; the fog end is responsible for data analysis and uploading of the edge device and executing a control command issued by the cloud end; the edge equipment is arranged at the edge end and comprises a sensor detection device, aerator equipment and an aerator controller. According to the invention, a fishpond monitoring node control algorithm based on fuzzy logic is used, even if input data has noise or is incomplete, the system can still quickly respond to environment change, and meanwhile, the optimization rule can be continuously adjusted, so that different environment and management requirements can be met.

Description

Technical Field

[0001] The present invention belongs to the field of fish pond aquaculture, and particularly relates to an intelligent fish pond oxygenation system and application based on cloud-fog-edge collaborative optimization. Background Art

[0002] The oxygen content in a fish pond is a key condition affecting the growth and survival of fish. When the oxygen content in the water decreases, people usually use relevant oxygenation devices to oxygenate the water. For example, Patent 201910533972.X discloses an intelligent fish pond oxygen supply system capable of automatically adjusting the oxygen supply amount, including an oxygen content monitoring device, a mobile terminal, an oxygenation device, and a power supply module, to realize the real-time monitoring of the oxygen content in the fish pond and automatically adjust the oxygen content in the fish pond according to different requirements. However, there are problems of non-linearity, large inertia, and time delay in the control process of oxygen supply in this system, resulting in difficulty in adapting to different environmental and management requirements. Summary of the Invention

[0003] The purpose of the present invention is to overcome the disadvantages existing in the prior art, and provide an intelligent fish pond oxygenation system and application based on cloud-fog-edge collaborative optimization, using a fish pond monitoring node control algorithm based on fuzzy logic. Even when the input data is noisy or incomplete, the system can still quickly respond to environmental changes, and at the same time, it can continuously adjust and optimize the rules to adapt to different environmental and management requirements.

[0004] The purpose of the present invention is achieved by the following technical solutions:

[0005] An intelligent fish pond oxygenation system based on cloud-fog-edge collaborative optimization adopts a cloud-fog-edge communication architecture; the cloud side is responsible for system-level data analysis and optimization control decision-making; the fog side is responsible for data analysis and uploading of edge devices, and executes the control commands issued by the cloud side; the edge side is edge devices, including a sensor detection device, an aerator device, and an aerator controller.

[0006] The sensor detection device is used to obtain water quality parameter data such as the water quality PH value and dissolved oxygen in the fish pond, and transmit the data to the fog side.

[0007] The fog side includes a microprocessor, which is used for data analysis of water quality parameters, and uploads the data analysis results to the cloud side; at the same time, it executes the control commands issued by the cloud side and transmits them to the edge devices.

[0008] The cloud side is responsible for system-level data analysis, adopts a fish pond monitoring node control algorithm based on fuzzy logic; and makes optimization control decisions, sets and issues commands for the control threshold and working mode of the fish pond aerator.

[0009] The control algorithm of the fishpond monitoring node based on fuzzy logic takes the error e between the given value and the actual output value of dissolved oxygen and the error change rate ec as inputs, and u as the output quantity; the theoretical change value of dissolved oxygen is 0 - 20 mg / L, and the optimal dissolved oxygen is set to 5 mg / L, so the error range is [-20, 20] mg / L, and the range of the output quantity u is 0 - 50 Hz; the actual range [-20, 20] of the error e and the error change rate ec is transformed into the universe of discourse [-6, 6], and the scale factors K e and K ec are determined by the following formula. The scale factor K e = 0.3, K ec = 0.3, where n represents the entire universe of discourse range; the actual range of the output quantity u is [0, 50], and the universe of discourse is [-6, 6], and the transformation is:

[0010] (x is [-6, 6], u is [0, 50])

[0011] K e = n / x e , K ec = n / x ec

[0012] In the formula: u is the output quantity of the fuzzy controller; x is the universe of discourse range of the output quantity u; n is the range of the entire universe of discourse; x e is the actual interval of the error e; x ec is the actual interval of the error change rate ec; K e and K ec are the scale factors of the error and the error change rate.

[0013] The control rules of the fuzzy controller all adopt 7 fuzzy linguistic variables: NB, NM, NS, ZE, PS, PM, PB, which represent positive large, positive medium, positive small, zero, negative small, negative medium, and negative large respectively, and their membership functions are triangular membership functions; the membership functions of the error e, the error change rate ec, and the output quantity u are the same.

[0014] Referring to the experience of engineers and technicians, 49 rules are summarized. According to the summarized rules, the result fuzzy set is obtained by using the min-max fuzzy inference method, and then defuzzified into the actual value by the centroid method and plotted in the following table:

[0015] Fuzzy rule table

[0016]

[0017] The present invention has the following advantages and effects compared with the prior art:

[0018] (1) The present invention adopts a fuzzy logic algorithm, which can calculate an appropriate adjustment amount according to fuzzy logic rules to quickly adapt to environmental changes in the fish pond, such as water temperature, pH value, etc., and is suitable for dynamic and complex water ecosystems. Fuzzy logic can imitate the human decision-making process, provide reasoning based on a fuzzy rule table, allow reasonable control decisions to be made in the absence of precise information, and do not require an accurate mathematical model.

[0019] (2) The fuzzy control method based on a fuzzy rule table of the present invention makes the monitoring and control process easy to understand and optimize, can provide a better decision-making basis, and has decision transparency.

[0020] (3) The present invention makes full use of the advantages of cloud computing, fog computing, and edge computing, realizes hierarchical optimization of data processing and decision-making, and improves the intelligence and response speed of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 is the overall design block diagram of the intelligent fish pond aeration system of the present invention.

[0022] Figure 2 is the flowchart of the PH automatic control program.

[0023] Figure 3 is the flowchart of the dissolved oxygen automatic control program.

[0024] Figure 4 is the schematic diagram of the composition of the intelligent fish pond aeration system.

[0025] Figure 5 is the topology structure of the cloud-fog-edge collaborative optimization control system. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0026] To facilitate the understanding of the present invention, the present invention will be described in detail below in conjunction with specific embodiments. The following embodiments will help those skilled in the art to further understand the present invention. However, the present invention is not limited in any form. It should be noted that for those skilled in the art, without departing from the concept of the present invention, the present invention can also make several deformations and improvements, and these all belong to the protection scope of the present invention.

[0027] Embodiment

[0028] The intelligent fish pond aeration system based on cloud-fog-edge collaborative optimization of the present invention adopts a cloud-fog-edge communication architecture; the cloud end is responsible for system-level data analysis and optimization control decisions; the fog end is responsible for data analysis and uploading of edge devices and executing control commands issued by the cloud end; the edge end is edge devices, including a sensor detection device, an aerator device, and an aerator controller, and the specific technical route is as Figure 1 shown.

[0029] In the edge device, a single-chip microcomputer is used as the main control chip, and it also includes a sensor detection device, an aerator device, an aerator controller, a relay, and a power supply module, etc. Among them, the sensor detection device includes a PH sensor (using an electrode-type sensor to measure the acidity and alkalinity by measuring the potential of the electrode) and a dissolved oxygen sensor (using a primary battery-type sensor to detect the dissolved oxygen in the water body), etc., which are used to obtain water quality parameter data such as the PH value and dissolved oxygen of the fish pond, and transmit the data to the fog end. By collecting data through the sensor detection device, a fuzzy logic model is established, fuzzy reasoning is carried out, and according to the control signal obtained by defuzzification, the output of the aerator is controlled, and finally the automatic regulation of the dissolved oxygen in the fish pond water quality is realized.

[0030] The fog end includes a microprocessor, which is used to transfer and collect the data of the edge perception sensor module and select the operation mode of the aerator based on the predicted dissolved oxygen content, and transmit the control scheme corresponding to the corresponding operation mode to the device control module.

[0031] The cloud end uses a fuzzy controller to optimize data analysis, and uses a fish pond monitoring node control algorithm of fuzzy logic. The water quality parameters such as PH and dissolved oxygen obtained from continuous monitoring are input into the fuzzy inference system, so as to obtain more comprehensive water quality control parameters.

[0032] For the cloud-fog-edge communication architecture, the encrypted MQTT broadcast protocol is used to realize data uploading to the cloud through a wireless DTU gateway; and an edge node is designed, which will process most of the redundant data locally. The edge node of this platform refers to a business platform built on the network edge side close to the fish pond, providing resources such as storage, computing, and network, and sinking some key business applications to the access network edge to reduce the bandwidth and delay losses caused by network transmission and multi-level forwarding, and realize data processing on the network edge side. Data transmission uses the wireless communication transmission device DTU to transmit the collected data to the cloud through 4G mobile communication technology using the MQTT protocol, and the communication mode is as Figure 5 shown.

[0033] The aerator controller includes a GSM module, a 30A relay, an antenna, a transformer, a power supply interface, etc. The GSM module receives remote instructions to drive the 30A high-power relay to complete the on-off of the power input. There are two groups of power supply interfaces for the entire controller. The input interface is connected to the 220V household power supply, and the output interface controls the load it connects. The power supply connected to the input interface is regulated by the transformer to provide a 5V power supply voltage for the entire controller.

[0034] The aerator device is a water spray type aerator, which uses a water pump to send water into the nozzles installed in the middle and on the shore of the fish pond, so that the water is sprayed out and falls like rain, thereby contacting the air to increase the dissolved oxygen concentration in the water.

[0035] The working mode of an intelligent fishpond aeration system based on cloud-fog-edge collaborative optimization is as follows:

[0036] (1) The PH sensor and the dissolved oxygen sensor collect data using analog signals. The collected data is processed by a signal conditioning circuit and a conversion circuit, and then sent to the 12-bit ADC built into the STM32 single-chip microcomputer for analog-to-digital conversion. The digital quantity information is output, and the corresponding values are calculated using relevant formulas to obtain the original collected data;

[0037] (2) The wireless communication transmission device DTU uploads the cached data to the cloud according to specific conditions (such as data change thresholds) using the MQTT protocol for the original data collected;

[0038] (3) When the cloud receives the water quality data information, as Figure 4 shown, through the fuzzy logic-based fishpond monitoring node control algorithm, the water quality parameters such as PH and dissolved oxygen obtained from continuous monitoring are input into the fuzzy inference rule table to obtain more comprehensive water quality control parameters, complete system-level data analysis, optimize control decisions, data collection, and overall management, and set and issue commands for the relevant control thresholds and working modes of the fishpond;

[0039] (4) Using the PH value prediction data and real-time monitoring data in the database, compare them with the pre-set thresholds, and perform intelligent control on the inlet pump and the drain pump according to the quantitative relationship. As Figure 2 shown, when either the predicted value or the monitored value of the PH is less than the pre-set lower threshold G1 or greater than the upper threshold G2, the inlet pump and the drain pump are simultaneously turned on for one hour to adjust the water body. The specific process of its automatic control is as follows:

[0040] (4-1) Set the lower threshold G1 and the upper threshold G2 of the PH in the water tank;

[0041] (4-2) Determine whether it is in the automatic mode;

[0042] (4-3) Obtain the predicted value g and the monitored value G of the water body PH;

[0043] (4-4) When it is detected that both the predicted value g and the monitored value G of the PH are between G1 and G2, this function remains in the sleep state;

[0044] (4-5) When it is detected that g < G1 or G < G1, the inlet pump and the drain pump are simultaneously turned on for one hour; when it is detected that g > G2 or G > G2, the inlet pump and the drain pump are simultaneously turned on for one hour;

[0045] (5) Decide whether to turn on the aeration pump by comparing the predicted oxygen content data x and the monitored value X with the pre-set oxygen content threshold, as Figure 3As shown, when either the predicted value x or the monitored value X is less than the preset lower limit of oxygen content X1, the aerator is turned on; to prevent the oxygen content in the pool from being too high, when both the predicted value x and the monitored value X are higher than X2, the aerator is turned off. The specific process of its automatic control is as follows:

[0046] (5-1) Set the lower limit threshold X1 and the upper limit threshold X2 of the oxygen content in the pool

[0047] (5-2) Determine whether it is in the automatic mode;

[0048] (5-3) Obtain the predicted value x and the monitored value X of the water body oxygen content;

[0049] (5-4) When it is detected that x > X1 and X > X1, this function remains in the sleep state; when x < X1 or X < X1, this function is started;

[0050] (5-5) Continuously obtain the predicted value x and the monitored value X of the oxygen content, and compare them with the set values of X1 and X2;

[0051] (5-6) When it is detected that the predicted value x < X1 or the monitored value X < X1, check the current operating state of the aerator. If the aerator is in the off state, send an on command; when x > X2 and X > X2, if the aerator is in the on state, send a off command.

[0052] It can be understood that the above specific description of the present invention is only for explaining the present invention and is not limited to the technical solutions described in the embodiments of the present invention. Those of ordinary skill in the art should understand that partial modifications or equivalent replacements can still be made to the present invention to achieve the same technical effects; as long as the usage requirements are met, they are all within the protection scope of the present invention.

Claims

1. An intelligent fish pond oxygenation system based on cloud-fog-edge collaborative optimization, characterized by: It adopts a cloud-fog-edge communication architecture; the cloud is responsible for system-level data analysis and optimized control decisions; the fog end is responsible for data analysis and uploading of edge devices, and executing control commands issued by the cloud; the edge end is the edge device, including sensor detection devices, aerator equipment and aerator controller.

2. The intelligent fish pond oxygenation system according to claim 1, characterized in that: The sensor detection device is used to obtain water quality parameter data such as pH value and dissolved oxygen in the fish pond, and transmit the data to the fog end.

3. The intelligent fish pond oxygenation system according to claim 1, characterized in that: The fog terminal includes a microprocessor for data analysis of water quality parameters and uploading the data analysis results to the cloud; at the same time, it executes the control commands issued by the cloud and transmits them to the edge device.

4. The intelligent fish pond oxygenation system according to claim 1, characterized in that: The cloud is responsible for system-level data analysis, adopts a fish pond monitoring node control algorithm based on fuzzy logic, and makes optimized control decisions, sets and issues commands for the control threshold and working mode of the fish pond aerator.

5. The intelligent fish pond oxygenation system according to claim 4 is characterized in that: The fish pond monitoring node control algorithm based on fuzzy logic takes the error e between the given value of dissolved oxygen and the actual output value and the error change rate ec as input, and takes u as output; the theoretical change value of dissolved oxygen is 0-20 mg / L, and the optimal dissolved oxygen is set to 5 mg / L, so the error range is [-20, 20] mg / L, and the range of output u is 0-50 Hz; the actual range [-20, 20] of the error e and the error change rate ec is transformed into the domain [-6, 6], and the proportional factor K e and K ec The proportional factor K is determined by the following formula: e =0.3, K ec =0.3, where n represents the entire domain range; the actual range of the output u is [0,50], the domain is [-6,6], and the transformation is: (x is [-6,6], u is [0,50]) K e =n / x e ,K ec =n / x ec Where: u is the output of the fuzzy controller; x is the domain range of the output u; n is the range of the entire domain; x e is the actual interval of error e; x ec is the actual interval of error change rate ec; K e and K ec is the proportional factor between the error and the error change rate.

6. The intelligent fish pond oxygenation system according to claim 5, characterized in that: The control rate of the fuzzy controller adopts 7 fuzzy linguistic variables: NB, NM, NS, ZE, PS, PM, and PB, which respectively represent positive large, positive middle, positive small, zero, negative small, negative middle, and negative large. Its membership function is a triangular membership function; the membership functions of the error e, the error change rate ec, and the output u are the same.

7. An application of the intelligent fish pond oxygenation system based on cloud-fog-edge collaborative optimization according to any one of claims 1 to 6, characterized in that The steps include: (1) The pH sensor and dissolved oxygen sensor use analog signals for data acquisition. The collected data is processed by the signal conditioning circuit and the conversion circuit, and sent to the single-chip microcomputer for analog-to-digital conversion, which outputs digital information to obtain the collected raw data; (2) The wireless communication transmission device uses the MQTT protocol to upload the collected raw data to the cloud; (3) The cloud receives water quality data information, and through the fuzzy logic fish pond monitoring node control algorithm, the water quality parameters such as pH and dissolved oxygen obtained by continuous monitoring are input into the fuzzy reasoning rule table to obtain more comprehensive water quality control parameters, complete system-level data analysis, optimize control decisions, data collection and overall management, and set and issue commands for the relevant control thresholds and working modes of the fish pond; (4) Using the pH value prediction data and real-time monitoring data in the database, and comparing them with the pre-set thresholds, the water inlet pump and the drainage pump are intelligently controlled according to the quantitative relationship; when the pH value prediction value or the monitoring value is less than the preset lower threshold G1 or greater than the upper threshold G2, the water inlet pump and the drainage pump are turned on for one hour to regulate the water body; (5) Whether to turn on the oxygen pump is determined by comparing the predicted oxygen content data x and the monitored value X with the preset oxygen content threshold. When either the predicted value x or the monitored value X is less than the preset oxygen content lower limit X1, the oxygen pump is turned on. To prevent the oxygen content in the pool from being too high, when both the predicted value x and the monitored value X are higher than X2, the oxygen pump is turned off.

Images