Intelligent sensor for aquaculture water quality index determination through automated sampling device

Abstract

The present invention discloses an intelligent sensor for water quality index determination along with a method of determining the water quality index for an aquaculture pond. The present invention provides an intelligent sensor wherein the sampling is implemented by an automated sampling device. The present invention provides for timely alerting to enable corrective action for aquafarming management and wastewater treatment process management. The output value of the water quality index is notified to an end user by blockchain encryption for taking remediate actions.

Description

[0001] DESCRIPTION

[0002] TITLE OF THE INVENTION INTELLIGENT SENSOR FOR AQUACULTURE WATER

[0003] QUALITY INDEX DETERMINATION THROUGH AUTOMATED SAMPLING DEVICE

[0004] FIELD OF THE INVENTION

[0005] The present invention is related to an intelligent sensor for precise and secure water quality index determination. Also disclosed are the method and system for water quality index determination for an aquaculture pond implemented by an automated sampling device as per international standards such as GAP (Global aquaculture practice) principles or Pollution control boards guidelines where sensing reactor chamber is a stand-alone system placed outside the pond and sampler is deployed in the pond with designated location.

[0006] BACKGROUND OF THE INVENTION

[0007] Determining accurate water quality conditions is essential for various applications ranging from industrial uses, wastewater management, drinking water supply, to aquaculture operations.

[0008] Aquaculture operations are very specifically sensitive to water quality. During the aquaculture operations, various water quality parameters including minerals play a vital role during the growth of the freshwater and brackish water cultured organisms such as carp, shrimp, sea bass etc. Furthermore, these parameters are interrelated and vary in a pattern which is difficult for farmers to understand and find the reasoning and outcome. Also, the available sensing technology has issues with the accuracy of predicting water quality parameters, human handling, biofouling, instrument, and spatial-temporal variation, along with sampling as per defined environmental sampling protocols.

[0009] The present invention addresses these gaps, resulting in timely determination and notification of the water quality index which is the interpretation of the water quality as per user need. It provides a method, for sensing parameters to output a precise water quality index.

[0010] BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The other objects, features and advantages will occur to those skilled in the art from the following description of the preferred embodiment and the accompanying drawings in which:

[0012] FIG. 1 illustrates the Data Capturing Architecture

[0013] FIG. 2 illustrates the schematic view of sampling module

[0014] FIG. 3 illustrates data prediction procedure through neuro-fuzzy inference system FIG. 4. illustrates a schematic of the intelligent sensor system for determining water quality index of a water body wherein the sensor comprises

[0015] 101-sensor unit (reactor module), 102-pump 3, 103-reservoir 2, 104-pump2 ,105-reservoir 1, 106- pump 1, 107-pulleys,108-pumping pipe, 109-sampler module, 110-water inlet, I l l-motor, valves 112,113 and 114.

[0016] Although the specific features of the present invention are shown in some drawings and not in others. This is done for convenience only as each feature may be combined with any or all of the other features in accordance with the present invention.

[0017] DETAILED DESCRIPTION OF THE INVENTION

[0018] In the following detailed description, a reference is made to the accompanying drawings that form a part hereof, and in which the specific embodiments that may be practiced are shown by way of illustration. These embodiments are described in sufficient detail to enable those skilled in the art to practice the embodiments and it is to be understood that other changes may be made without departing from the scope of the embodiments. The following detailed description is therefore not to be taken in a limiting sense.

[0019] The various embodiments of the present invention provides an intelligent system to predict water quality by capturing various water quality parameters a method for interpretation of the variation of water quality as aquaculture index, and a sensing system for determining water quality index.

[0020] The present invention overcomes the gaps in the existing solutions by providing a process, technology and design of sensing parameters with a data sampling device in line with environmental sampling protocols and best aquaculture practice in line with international standards such as GAP (Global Aquaculture Practice) or VietBAP.

[0021] The parameters identified are (i) the weather parameters such as wind speed and direction, humidity, rainfall, and temperature over the air (ii) water column parameters such as dissolved oxygen, water temperature, pH, turbidity, dissolved phosphate, nitrate, total carbon, (iii) toxic metabolites such as ammonia, nitrite, sulphide.

[0022] The detected data is compared with the parameters of growth function for the interpretation and gradation of an aquaculture index which captures the health of animal and water quality. These indexes are computed by Neurofuzzy inference system through clustering basic water parameters, nutrients, metabolites, and stocking density to provide a deeper interpretation through C / N ratio, dissolved oxygen variation, N / P ratio, Ca / Mg ratio, at various depths, mainly at the sediment-water interface. The index is predicted as output in terms of 1-5 where 1 is the worst and 5 is very good. Also, failsafe mechanisms infused detects the issues regarding biofouling, human handling, instrument, spatial- temporal variation etc during sensing. The data sampling protocols are different from the proposed technology, process and design than existing technology. The present invention provides for efficient management of harvesting by lowering operational cost and prediction of water quality parameters and its interpretation as an index for aquaculture operations to be profitable:

[0023] • This index helps in understanding the growth or hindrance in growth

[0024] • Feeding pattern which saves unnecessary feed cost

[0025] • Aeration operation

[0026] • Addition of mineral or any medicines essential for the harvest

[0027] • Moulting phase

[0028] • Time of the harvest based on size and stage.

[0029] Definitions:

[0030] "Artificial intelligence module" as used herein refers to a module that receives data from the sensors, compares it with values of pre-existing sensor readings, desired value parameters and provides input to the control modules of one or more aeration modules, aquaculture inputs dispensing module. The module can lead to corrective action, opening or closing of valves or switches, or notify / alert on parameters. The module has machine vision capability as well as GPS functionality. The module can create and utilize a plurality of data training models. It can involve various algorithms selected from an artificial neural network algorithm, a Gaussian process regression algorithm, a logistical model tree algorithm, a random forest algorithm, a fuzzy classifier algorithm, a decision tree algorithm, a hierarchical clustering algorithm, a k-means algorithm, a fuzzy clustering algorithm, a deep Boltzmann machine learning algorithm, a deep convolutional neural network algorithm, a deep recurrent neural network, or any combination thereof. The various algorithms can model the following parameters without limitation, humidity, wind speed, wind direction, air temperature, and water quality parameters such as temperature, DO, pH, ORP, at multiple coordinates of the same water body.

[0031] The training data is generated through a repetitive process of randomly choosing values for each of one or more input process control parameters and scoring adjustments to the input process control parameters as leading to either undesirable or desirable outcomes. The outcomes based respectively on the presence or absence of defects detected in a fabricated object arising from the process control parameter adjustments.

[0032] The training data set further comprises process characterization data, in-process inspection data, or post-build inspection data that is generated by an operator while manually adjusting the process control parameters.

[0033] "Ammonia" refers to unionized and ionized ammonia.

[0034] "Battery" as used herein is used interchangeably with electricity, to power the device.

[0035] “Corrective action” as used herein is done by following processes of understanding errors due to :

[0036] 1. Equipment error (it is being considered by measuring the resistance in dark conditions and in the absence of water as a benchmark)

[0037] 2. Environmental error (It is because of changes in the ambient light and temperature range)

[0038] 3. Handling error (The placement of the device and the interval of data acquisition)

[0039] 4. Error due to biofouling (Deposition of the microbial which changes the absorption of the laser)

[0040] 5. Error due to Sampling (Time of sampling and process of sampling).

[0041] These errors will be produced sequentially to the customer as well as the manager for remediate action.

[0042] “Sensor module” as defined herein is a collection of various sensors including water quality sensors. Sensors store data on the cloud and also locally. Sensor module houses an artificial intelligence module in its control module. The data is later used for directing inputs to the aeration, aquaculture inputs dispensing module or the sensor module or any other module.

[0043] "Control module" as defined herein is a unit to transmit and receive data from and to other modules. It can also be termed as a communication module, to receive data from the Al module. It comprises a microcontroller / microprocessor and a wifi component. It may contain other components based on the functions of the system or a module of which it is a part. These are computing devices with digital storage and digital processing capabilities. The module may comprise an image capturing device or navigation module.

[0044] "DO gap or Dissolved Oxygen Gap" as used herein refers to the gap between the existing level of dissolved oxygen and the demand for dissolved oxygen at the sediment-water interface of the waterbody. The demand for DO is the level of DO required for the viability of the animals.

[0045] "Aquaculture inputs" as used herein refers to all the inputs like probiotics, prebiotics, minerals, vitamins or any components used for enhancing the quality of water, health and growth conditions of aquatic animals. The term " Aquaculture inputs " is used interchangeably with drugs or probiotics in embodiments describing the invention.

[0046] "Preset Values " / 'preset range" or "preset configuration" as used herein refers to values of various parameters like dissolved oxygen (DO), Oxygen Reduction Potential (ORP), nitrite, nitrate, sulphide, unionized ammonia, total ammonia nitrogen, phosphate, which can be set manually by a user, retrieved from reference values stored in the cloud, or derived from predicted values by the artificial intelligence module. These values can vary by waterbody, and / or by objective of deployment of waterbody management system of the invention.

[0047] “Neuro-fuzzy module” refers to a Neuro-fuzzy system ,a combination of artificial neural networks (ANN) and fuzzy logic. It leverages the learning capabilities of neural networks and the reasoning capabilities of fuzzy logic to create powerful models that can handle complex and uncertain information.

[0048] Neural Network handle learning from data, pattern recognition, and adaptation. Fuzzy Logic deals with reasoning under uncertainty, using fuzzy sets and rules.

[0049] Although the embodiments herein are described with various specific embodiments, it will be obvious for a person skilled in the art to practice the embodiments herein with modifications.

[0050] One embodiment of the invention is an intelligent sensor system for determining water quality index of a water body wherein the sensor comprises

[0051] A reactor module

[0052] And a sampling module.

[0053] In one embodiment, the reactor module comprises an

[0054] An inlet chamber;

[0055] A laser; plurality of sensors;

[0056] A control module coupled with artificial intelligence module

[0057] A network adaptor

[0058] A detector

[0059] Optionally a display device

[0060] A battery

[0061] In one embodiment the inlet chamber receives water from a pond / aquaculture tank. In one embodiment the inlet chamber receives water through the sampling modules. In one embodiment, the reactor module has multiple reactor chambers. In one embodiment the reactor module comprises photodiode with lasers. In one embodiment the reactor module comprises Al cameras to detect visual changes upon detection of dissolved parameters. In one embodiment the dissolved parameters include DO, TAN, NO3, NO2, PO4, minerals such as calcium (Ca), Magnesium (Mg), Sodium (Na), Potassium (K). In one embodiment the water is sourced from different depths across the water column by means of a sampling module. In one embodiment, one or more dissolved parameters is detected simultaneously in different reactor chambers.

[0062] In one embodiment, the intelligent sensor system is configured with a user interface and wherein the user interface is integrated with a data visualization dashboard.

[0063] In one embodiment the plurality of sensors comprised in the reactor module includes sensors for; Environmental parameters;

[0064] Undissolved water quality parameters such pH, TDS, Temperature, ORP, Salinity, undissolved ammonia;

[0065] Sensors for sensing dissolved water quality parameters including DO, COD, TOC, NO2, NO3, PO4, S2, dissolved ammonia, dissolved inorganic carbon (DIC) and dissolved organic carbon (DOC).

[0066] In one embodiment the environmental parameters include wind speed, wind direction, air temperature, humidity and rainfall.

[0067] In one embodiment the sensed environmental parameters are cross co-related with remote sensed data for accuracy.

[0068] In one embodiment the sampling module comprises a plurality of samplers. In one embodiment the samplers pump water to a centralized container.

[0069] In one embodiment, the centralized container sends water to the inlet chamber of the reactor module. In one embodiment, the water quality parameters of water from the centralized container are sensed via the plurality of sensors comprised in the reactor module.

[0070] In one embodiment, the samplers comprised in the sampling module is placed in multiple aquaculture ponds or RAS / Biofloc tanks.

[0071] In one embodiment the reactor module is equipped with a visual detection means to detect the change in color after mixing of reagents in reactor chamber as an indicator of completion of procedure for estimate the values of sensed parameters including DO, calcium, nitrite, pH, magnesium, alkalinity, ammonia, hardness.

[0072] In one embodiment the visual detection means is to identify the reaction is completed for spectrophotometric detection means. In one embodiment the visual detection is captured by means of an image sensor equipped in the control module. Which is placed near the reaction chamber. In one embodiment, the image sensor transmits data to the Al module,

[0073] In one embodiment the plurality of sensors comprised in the reactor module sends the values of the sensed parameters to the artificial intelligence module configured with the control module.

[0074] In one embodiment, the Al module predicts the dependent parameters selected from Dissolved oxygen (DO), COD, TOC, NO2, NO3, PO4, S2, unionized ammonia, dissolved inorganic carbon (DIC) and dissolved organic carbon (DOC) or a combination thereof from the input independent parameters as temperature, salinity, pH, ORP to accurately compute the water quality index.

[0075] The intelligent water quality sensor system incorporates environmental or weather parameter such as pH, salinity, temperature and absorption spectra into consideration for sensing of dependent parameters such as DO, NO3, NO2, NH4, S2-, PO3, PO4, COD based on particular concentration. These independent parameters are input for predicting the accurate parametric value.

[0076] As the Parametric value nonlinearly depends upon the variation of physical parameters temperature, pH, salinity and known concentration. The value of parameters may change if any of the independent value changes. The current invention incorporates nonlinear modeling implemented by the Al module to make the prediction of parametric value of dependent parameters in a robust cost effective and accurate manner.

[0077] In one embodiment the artificial intelligence module predicts value of water quality parameters based on the inputs of the sensed values such as pH, Temperature, Salinity, Wind speed, and voltage value from photo diode. In one embodiment, the output from the artificial intelligence module is configured with a neurofuzzy module for the prediction of water quality index. In one embodiment the artificial intelligence module is configured with a repository of referenced values from best aquaculture practices for different aquatic species to predict water quality index (WQI) from 1 to 5. The WQI value forms modules of C / N ratio, N / P ratio, Mg / Ca Ratio for understanding the status of cultured practices to value tag the harvest and impact of water pollution. (Here C is combination of both DIC and DOC: N is both DIN and DON). C / N ratio <15 suggests the aquaculture potential is adequate, N / P ratio <10 suggests the eutrophication potential is in control. Mg / Ca predicts the moulting phase. These also helps optimize feeding cycle and feeding rate based on stocking density.

[0078] In one embodiment, the artificial intelligence module outputs a value / score that determines the particular water quality parameters. The index value co-relates with market prices for creating the value chain of the harvest.

[0079] In one embodiment the score / output on the water quality index derived from the water quality variation for a specific culture with a defined stocking density is specific to an aquatic species. In one embodiment the aquatic species are selected from crustaceans and finfishes.

[0080] In one embodiment the reference values (from experiments and peer-reviewed articles and best aquaculture practices) for aquatic species include optimal growth rate, for a specific time period of lifecycle.

[0081] In one embodiment, the reactor module is equipped with a light intensity detection means to detect the change in intensity of incident light in reactor chamber for estimating dissolved or dependent parameters such as DO, calcium, nitrite, pH, magnesium, alkalinity, ammonia, hardness.

[0082] Figure 4 shows a Sampler comprising of pulley with motor controller, a water pump, water inlet, valves, reservoir 1 and reservoir 2, for sampling water from desired depth and quantity from dashboard as per user defined value.

[0083] EXAMPLE i.user inputs depth of 2 meter and 500ml of water be sampled at time of 5pm. The motor of pulley enables the sampler to take the sampling module to 2m depth and starts pumping of 500ml to the reservoir stationed near the reactor. ii.A network of samplers powered by solar or grid are deployed in all ponds in multiple units as per need of farming or water monitoring. Respective numbers of reservoirs are either stationed near reactor unit for holding the sampled water or one reservoir connected with multiple samplers deployed in ponds. iii. The reservoir gets filled in based on schedule of sampling as defined by user when there is reservoir connected with multiple sampler iv. If dedicated reservoirs are provided for each sampler and reactor the scheduling is omitted in the part of process automation.

[0084] In one embodiment, the reservoir 1 pulls direct water from the pond. In one embodiment, the reservoir 2 pulls water from reservoir 1 to 2. In one embodiment, reservoir 2 pulls predetermined water quantity for sampling or testing.

[0085] In one embodiment, reservoir 1 controls turbidity of water.

[0086] In one embodiment, the sampling module comprises reservoir 1 and 2 for pulling water from a tank. In one embodiment, the sampling module comprises reservoir 1 for pulling water from a pond. One embodiment of the invention is a method of determining the water quality index of an aquaculture pond, the method comprising the steps of a. selecting an aquatic species b. auto generation of referenced parameters for the species selected in step a. c. parametric selection of sensor relevant to selected aquatic specie based on environmental condition, nutrient requirement and metabolic requirement d. detection of dissolved water quality parameters by a plurality of sensors equipped in the reactor module wherein the water is sourced from the sampling module e. index computation by the Al module configured with the control module.

[0087] In one embodiment, index computation in step e. comprised of generating a rule table for good, moderate and worst conditions.

[0088] In one embodiment, Al module uses neuro fuzzy inference system.

[0089] In one embodiment, the computed index in step e. enables alerting and decision making.

[0090] In one embodiment, the intelligent sensor system outputs a water quality at an index scale of 1-10.

[0091] In one embodiment, the intelligent sensor system outputs a water quality index at a scale of 1-7. In one embodiment, intelligent sensor system outputs a water quality index at a scale of 1-5.

[0092] In one embodiment, the score / value of the water quality index for a culture waterbody enables corrective action.

[0093] In one embodiment, the corrective action is done when the index value reaches 5 or as red flag alerts based on a combination of a period of harvest, water quality parameter and growth function for management issues.

[0094] Equipment error (it is being considered by measuring the resistance in dark conditions and in the absence of water as a benchmark)

[0095] Environmental error (It is because of changes in the ambient light and temperature range)

[0096] Handling error (The placement of the device and the interval of data acquisition)

[0097] Error due to biofouling (Deposition of the microbial which changes the absorption of the laser) Error due to Sampling (Time of sampling and process of sampling).

[0098] This error will be produced sequentially to the customer as well as the manager for immediate action. These parameters will be compared with the developed rule based on best aquaculture practices and growth function which is dependent on temperature, salinity, pH and an index will be projected. The detection of point value.

[0099] In one embodiment the end user includes, without limitation, a consumer, aquaculture operations manager, a private or government organization, a transport company.

[0100] In in-land aquaculture operations with multiple ponds or indoor aquaculture operations with multiple RAS / Biofloc tanks, the samplers will be placed in ponds or tanks. The samplers sample the water by pumping it to plurality of sensors in the reactor module. The sensed values are sent to the cloud server or local server. Each of the ponds and tanks does not require the sensing unit which is a centralized system. It saves the cost and energy.

[0101] In one embodiment of the invention, the intelligent sensor for water quality index determination is configured as a hand-held device for routine checks for the harvesters for applications such as soil quality, inlet water quality, and outflow water quality.

[0102] One embodiment of the invention is a web based app configured with the intelligent sensor system encompassed by the invention.

[0103] In one embodiment, the web based application is configured to implement defined protocols for sampling the water as per environmental protocols for aquaculture and environmental protocols.

[0104] In one embodiment, the sampling module is deployed in each pond or indoor tank within a network of pond or indoor tank for sampling the water and transferring to a centralized reactor unit for sensing the water quality.

[0105] In one embodiment, the sensed parameters from individual pond or indoor tank are stored locally in the local database. In one embodiment, the sensed parameters are sent to a global server as per usability.

[0106] The sampling devices are deployed based on timings as directed by the control module.

[0107] In one embodiment, the indoor sampler is a pulley based design which takes the water sample to sample water.

[0108] Aquaculture feeding, aeration, probiotic dispensation and mineral composition changes depend on this index. This index will be of two types, one for water quality management and another for shrimp health management.

[0109] Rule Tables DATA PREDICTION PROCEDURE THROUGH NEURO-FUZZY inference system

[0110] Species : Brackishwater Shrimp

[0111] 1. INDEPENDENT PARAMETERS

[0112] Table 1.1 Scale : 5-point grading

[0113] Table 1.2 Scale: 3-point grading

[0114] 2. DISSOLVED (Dependant) PARAMETERS Table 2.1 Scale : 5-point grading

[0115] Table 2.2 : Scale: 3-point grading

[0116] The foregoing description of the specific embodiments will so fully reveal the general nature of the embodiments herein that others can, by applying current knowledge, readily modify and / or adapt for various applications such as specific embodiments without departing from the generic concept, and, therefore, such adaptations and modifications should and are intended to be comprehended within the meaning and range of equivalents of the disclosed embodiments. It is to be understood that the phraseology or terminology employed herein is for the purpose of description and not of limitation. Therefore, while the embodiments herein have been described in terms of preferred embodiments, those skilled in the art will recognize that the embodiments herein can be practiced with modifications. However, all such modifications are deemed to be within the scope of the claims.

[0117] The scope of the embodiments will be ascertained by the claims to be submitted at the time of filing a complete specification.

Claims

Claims1.An intelligent sensor system for determining water quality index of an aquaculture pond wherein the system comprises; a reactor module comprising ; an inlet chamber; a laser; plurality of sensors; a control module coupled with artificial intelligence module; a network adaptor; a detector; optionally a display device a battery; and a sampling module comprising a plurality of samplers and wherein the samplers source water from different depths of a water column.

2. The intelligent sensor system as claimed in claim 1, wherein the sampling time and coordinates are as directed by the control module.

3. The intelligent sensor system as claimed in claim 1, wherein the inlet chamber receives water through the sampling modules.4.The intelligent sensor system as claimed in claim 1, wherein the plurality of sensors comprised in the reactor module includes sensors forEnvironmental parameters;Undissolved water quality parameters such pH, TDS, Temperature, ORP, Salinity, undissolved ammonia;5.The intelligent sensor system as claimed in claim 1, wherein the water quality index is at a scale of 1-10.6.The intelligent sensor system as claimed in claim 1 wherein the reactor module comprises Al cameras to detect visual changes upon detection of dissolved parameters DO, TAN, NO3, NO2, PO4, minerals such as calcium (Ca), Magnesium (Mg), Sodium (Na), Potassium (K).7.The intelligent sensor system as claimed in claim 1, wherein the samplers comprised in the sampling module pump water to a centralized container.8.The intelligent sensor system as claimed in claim 1, wherein the samplers comprised in the sampling module is placed in multiple aquaculture ponds or tanks.9.The intelligent sensor system as claimed in claim 1, wherein the reactor module is equipped with a visual detection means to detect the change in intensity of incident light in reactor chamber as an indicator of completion of procedure for estimating by comparing with precalibrated values of sensed parameters including DO, calcium, nitrite, pH, magnesium, alkalinity, ammonia, hardness.10.The intelligent sensor system as claimed in claim 1, wherein the reactor module stores the values of the sensed parameters and values derived from the sensed parameters locally as well as the reactor module is configured to send the values to a server.1 l.The intelligent sensor system as claimed in claim 1, wherein the plurality of sensors comprised in the reactor module sends the values of the sensed parameters to the artificial intelligence module configured with the control module.

12. The intelligent sensor system as claimed in claim 1, wherein the system is configured with a user interface and wherein the user interface is integrated with a data visualization dashboard.

13. The intelligent sensor system as claimed in claim 1, wherein the artificial intelligence module predicts the dissolved parameters selected from Dissolved oxygen (DO), COD, TOC, NO2, NO3, PO4, S2, unionized ammonia, dissolved inorganic carbon (DIC) and dissolved organic carbon (DOC) or a combination thereof from the input of undissolved parameters selected from temperature, salinity, pH, ORP to accurately compute the water quality index.14.A method of determining the water quality index of an aquaculture pond by using the intelligent sensor system as claimed in claim 1, the method comprising the steps of ; a. selecting an aquatic species b. auto generation of referenced parameters for the species selected in step a. c. parametric selection of sensor relevant to selected aquatic specie based on environmental condition, nutrient requirement and metabolic requirementd. detection of dissolved water quality parameters by a plurality of sensors equipped in the reactor module wherein the water is sourced from the sampling module e. index computation by the Al module configured with the control module. f. enabling a corrective action based on the water quality index computed in step e.

15. The method as claimed in claim 14, wherein the index computation in step e. comprises generating a rule table for good, moderate and worst conditions.

16. The method as claimed in claim 14, wherein corrective action is done by understanding errors due to equipment error, environmental error, handling error, error due to biofouling, error due to Sampling.

17. The method as claimed in claim 14, wherein the sampling module deploys a plurality of samplers in step d. to source water from a plurality of aquaculture ponds simultaneously within a defined network of the said aquaculture ponds.

Images