A system and method for designing an analyte sensing system

Abstract

Disclosed herewith is a method for designing a polymer sensor array for detecting an analyte. The method uses an iterative process of selecting polymers from a group of polymers, each polymer belonging to a different family of polymers, printing the polymers to form a sensor array and exposing the array to a known analyte to generate a multi dimensional response from the sensor. The multi dimensional response is processed by a pretrained AI based processor that checks for separation between the manifolds, formed by the multi dimensional response, in association with a polymer and replaces or retains the polymer when a separation between the manifolds for plurality of analytes of different concentrations is observed.

Description

A system and method for designing an analyte sensing systemFIELD OF THE INVENTION

[0001] This disclosure relates to a method for designing an analyte sensing system wherein the sensing elements are made from a plurality of polymers. .BACKGROUND

[0002] Selecting a polymer for sensing application is a cumbersome and time consuming process, given the number of polymeric families that are available. Further, polymers have similar behaviour to certain classes of analytes and hence it becomes difficult to select the right polymer for the sensing system when the response can be similar for multiple analytes. The current disclosure relates to a method that uses advanced Al based processes to select the polymer for the sensor array.SUMMARY

[0003] Disclosed herewith is a method for making a sensor array to detect volatile organic compounds (VOCs) or analytes. It involves selecting and printing polymers onto electrodes based on their chemical families and how well they can be printed. Then, the array is exposed to different analytes, and the sensor responses are analyzed by an Al engine to identify any saturated or unresponsive sensors.BRIEF DESCRIPTION OF DRAWINGS

[0004] FIG. 1 illustrates the process of selecting a polymer for the analyte sensing system.DETAILED DESCRIPTION

[0005] The application discloses a system and method that may be used for designing an analyte sensing system. The analyte sensing system comprises a plurality of sensors that may measure at least one of the changes in physical and chemical properties of the pluralityof sensors when the sensor is exposed to an analyte. The sensing system designing method includes the steps of identifying a set of polymers that may undergo at least one of physical and chemical change when exposed to an analyte, operating in a given environmental condition, and may be produced by a large-scale manufacturing process. The method comprises the steps of classifying a plurality of polymers into a plurality of polymer families, identifying a representative polymer from the plurality of polymer families, capturing the distribution of response over the plurality of manufacturing process of the sensor, capturing the distribution of response over the plurality of conditions which the plurality of sensors of the sensing system are exposed to, identifying the difference between distributions for a plurality of conditions, clustering of response to a condition and identifying a sensor candidate for which the cluster of response for a plurality of conditions is distinguishable and separable.

[0006] Disclosed herewith is a system and method that is used to design an analyte sensing system wherein the analyte sensing system may be used to detect the presence of a plurality of components in the analyte. The sensing system comprises a plurality of sensors that detect the presence of the components in the analyte. Each of the sensors of the plurality of sensors of the sensing system reacts with at least one of the plurality of components of the analyte and undergoes at least one of physical and chemical change. At least one of physical and chemical change of the plurality of sensors is used to identify the components and the concentration of components in the analyte.

[0007] In some embodiments of the invention, the plurality of the sensors of the sensing system is present on a single substrate, wherein the sensor may be present in the form of a rectangular array. In some embodiments, the plurality of sensors may be present in multiple substrates, wherein each substrate may have a group of the plurality of sensors. The plurality of sensors of the sensor array is sufficiently spaced apart from each other, thereby minimizing the effect of change in at least one of physical and chemical change in one sensor to affect at least one of physical and chemical change of another sensor of the plurality of sensor of the sensor array.

[0008] In some embodiments of the invention, the plurality of sensors of the sensor array is positioned such that the position of the sensor array does not bias at least one of physicaland chemical change of the sensors when the plurality of sensors react with the components of the analyte.

[0009] The sensing system may be used for sensing analytes that are in fluidic form, specifically gaseous form. The sensors of the sensing system may be exposed to the analyte in an operational environment of the sensing system, wherein the components of the analyte react with the plurality of sensors of the sensing system.

[0010] In some embodiments of the invention, the sensing system is designed such that the level of exposure of each of the sensors to the analyte is the same. Further, each of the plurality of sensors of the sensing element may undergo at least one physical and chemical change during exposure.

[0011] In yet another embodiment, the sensors of the sensing system are constantly exposed to the analytes of the operational environment. In some embodiments, the exposure of the plurality of sensors to the analyte may be intermittent, after an interval, wherein the interval may depend on the sensing system's processing and sensor cleaning capacity.

[0012] The plurality of sensors of the sensing system may be made from a polymeric material, wherein the polymeric material may comprise conducting particles. The polymers may be configured in the form of polymeric thin films wherein the thin films may be deposited by processes such as drop casting, direct write, etc.

[0013] In some embodiments of the invention, each of the plurality of sensors of the sensing system may be made from a different polymeric material. In yet some embodiments, some of the sensors of the sensing system may be formed from the same polymeric material, but with different concentrations of fillers. The polymers of the sensors may be made from at least one of the block polymers, such as polymers belonging to one polystyrene, poly siloxane, poly acetate, saccharides, and poly ether families. In an embodiment of the invention, the polymer of at least one of the sensors of the sensing system may be made from one of Polystyrene-co-methyl styrene, Poly (dimethyl siloxane- co-diphenyl siloxane), Poly (vinyl acetate), Polystyrene-co-Acrylonitrile, Hydroxypropyl cellulose and Poly (methyl vinyl ether-co maleic acid).

[0014] The conductive particles embedded in the polymer of the sensor may be one of carbon black and carbon nanotubes, wherein the weight ratio of conductive particles to polymer in the sensor maybe 10% to 30 %.

[0015] The sensing system may comprise an apparatus that includes a plurality of sensors that may be mounted on a single substrate. Further, the sensing system may comprise a plurality of electrodes, environmental sensors, heater module, clock or timer, processor, power supply, pump, and communication module. Further, the system may include internal flow paths and pump-induced biased flow paths, that may allow control of the level of exposure of each of the plurality of sensors of the sensing system.

[0016] One end of the electrodes of the sensing system is embedded in the polymer of the sensor of the sensing system. Another end may be connected with the power supply and processor of the sensing system, directly or indirectly. The electrodes of the sensing system may be used to transfer electrical energy from the power source to the sensor. The power may be transferred continuously or intermittently. Further, the electrodes may be used to communicate at least one of physical and chemical change, that the polymer of the sensor and thus the sensor underwent, to the processor when the sensor is exposed to the analyte of the operational environment.

[0017] In some embodiments, the sensing system may further comprise environmental sensors, such as temperature sensors, pressure sensors, humidity sensors, wind speed sensors, etc. The data from at least one of the sensors of the environmental sensors may be provided to the processor of the sensing system.

[0018] In some embodiments, the clock or timer of the sensing system is used to record the time at which at least one of physical and chemical change is observed in the sensor element. Further, the clock or timer may be used to record the time of recording data from the plurality of environmental sensors of the sensing system. The processor of the sensing system may combine the time data with the sensing data of a plurality of sensors of the sensing system and the environmental sensors of the sensing system, thus making the data time-stamped data. In an embodiment of the invention, a separate processor may be provided that combines the data of the plurality of sensors of the sensing system and the environmental sensors, before sending it to the processor of the sensing system.

[0019] In some embodiments of the invention, a heater may be provided for each of the sensors of the sensing system, wherein the heater may heat the substrate of the sensing system and evaporate the analyte from the polymer of the sensors, thereby cleaning the sensor.

[0020] The sensing system may be provided with a power supply that provides electrical power to the plurality of sensors of the sensing system. The power supply may be an AC power supply that may provide sinusoidal power to the plurality of sensors. In an embodiment, a DC power source is used to power the plurality of sensors of the sensor array, thereby providing constant power to the plurality of sensors of the sensing system.

[0021] The processor of the sensing system may be an artificial intelligence-based processor, that comprises a plurality of trained models to infer the composition of the analyte from the time-stamped data from the plurality of sensors of the sensing system and the environmental sensors.

[0022] According to an embodiment of the invention, the artificial intelligence-based processor may use deep learning methods, such as artificial neural networks, deep neural networks, convolutional neural networks, and recurrent neural networks may be used by the processor of the sensing system to process the stream of the multi-dimensional response of the plurality of sensors of the sensing system.

[0023] In yet another embodiment of the invention, at least one of long short-term memory, gated recurrent unit, time series forecasting, transformers, autoregressive integrated moving average, and seasonal autoregressive integrated moving average may be used by the processor of the sensing system to process the stream of the time-stamped data of the plurality of sensors of the sensing system

[0024] The communication module of the sensing system may be a wireless communication module, that comprises a transmitter and receiver working on WiFi, Bluetooth, 2G, 3F, LTE, 5G, or other similar protocols. The wireless module is used to communicate with a remote server, wherein the remote server may be provided with an artificial intelligence-based processor, to infer the composition of the analyte from the time-stamped data from the plurality of sensors of the sensing systems and the environmental sensors. In some embodiments, a wireline network comprising fiber or electrically conducting cables may be used to connect the sensing system with one of thenodes of one of the access networks, aggregate network, and core network, to connect the sensing system with the remote server.

[0025] In some embodiments of the invention, the polymer of the plurality of sensors of the sensing system may undergo at least one of physical change or chemical change when it is exposed to components of the analyte. In an embodiment of the invention, the polymeric thin films may expand and the resistivity of the polymeric thin film may be increased due to exposure to a reactive component. The electrodes embedded in the polymer are used to detect the change in at least one of the physical or chemical properties across the polymer and communicate with the processor, to provide at least one of the changes in physical and chemical properties to the processor.

[0026] In an embodiment of the invention, the electrodes detect and communicate at least one of change in electrical resistance or impedance between the electrodes (hereinafter referred to as electrical response), change in capacitance between the electrodes, heat generated across the polymer, and luminescence of the polymer, to the processor.

[0027] From the response of the plurality of sensors of the sensing system and the plurality of environmental sensors, which may be time-stamped, a multi-dimensional response is created by the processor, in the numeric space. The processor may use a plurality of models to process the temporal data from the plurality of sensors of the sensing system and create a response corresponding to the components of the exposed analytes.

[0028] The method of selecting the plurality of polymers for the sensors of the sensing system includes the step of identifying a set of polymers that may undergo at least one of physical and chemical change, when the polymers are exposed to the analyte. Further, the step includes shortlisting a subset of polymers from the set comprising polymers that may undergo at least one of physical and chemical change, wherein the subset includes the polymers that may undergo at least one of physical and chemical change, in the operational environment of the sensing system. In some embodiments of the invention, the operational environment includes temperatures ranging from -40 to + 60 C. Further, the humidity range may range up to 100% and the pressure may be up to 1.083 bar.

[0029] In some embodiments, a subset of polymers is generated from the subset of polymers that may undergo at least one of physical and chemical change in the operational environment of the sensing system, wherein the subset includes a set of polymers that maybe deposited on the substrate of the sensing system using scalable manufacturing methods, such as drop casting, direct write printing process, etc.

[0030] The step of identifying the subset of polymers may be followed by the step of classifying the plurality of polymers into a plurality of polymer families. In some embodiments, the families may be defined by at least one of the manufacturing process, physical structure, bond types, physical appearance, chemical structure, interlinking, crosslinking, weight, functional group, solubility, electrical characteristic, magnetic characteristic, pH values, state, etc. to name a few.

[0031] The step of classifying the plurality of polymers in the plurality of polymer families may be followed by a step of identifying a representative polymer from the plurality of polymer families. In some embodiments of the invention, the representative polymer may exhibit at least some of the physical and chemical characteristics of the polymer family, to which the polymer belongs. In some embodiments, the representative polymer may exhibit all of the physical and chemical characteristics of the polymer family.

[0032] The step of identifying the representative polymer from the plurality of polymer families may be followed by a step of forming a plurality of sensing systems wherein at least some of the representative polymers of the polymer families may be used to form at least some of the sensor’s polymer thin film of the sensing system.

[0033] The step of forming the plurality of sensing systems may then be followed by the step of exposing the sensing system to a plurality of conditions and recording the response of the sensors of the sensing system, during exposure. Herein, the plurality of conditions refers to exposing the sensing system to an analyte or a combination of analytes, such as ammonia, ethanol, benzene, etc.

[0034] In some embodiments, a plurality of sensing systems may be formed with one representative polymer of one of the polymer families. Further, the sensing system may be exposed to one of the plurality of conditions several times and the response of each of the sensors of the sensing system may be recorded. This allows capturing the distribution of sensor response over a plurality of configurations / operation conditions of the manufacturing process and capturing the distribution of sensor response over a plurality of conditions.

[0035] In another set of embodiments, the plurality of the sensing systems formed with one representative polymer of one of the polymer families may be exposed to another of the plurality of conditions, several times. After the exposure, the response of each of the plurality of sensing systems may be recorded, to capture the distribution of sensor response for another condition.

[0036] The step of exposing the sensing system to a plurality of conditions and obtaining the distribution of sensor response for a plurality of different conditions may be followed by the step of null hypothesis validation, wherein the plurality of statistical tests, such as the student’s T-test, may be performed on the distribution of responses for the plurality of conditions. Based on the outcome of the validation, the mean difference in the plurality of intervals of the distribution is calculated, for the plurality of distributions. This process allows the identification of sensors and thus polymers that show the maximum difference when exposed to different conditions.

[0037] The validation step is followed by the identification of the formation of clusters of sensor response, wherein each of the clusters of the sensor response may correspond to a condition.

[0038] The step of identification of clusters includes the use of a plurality of manifold learning algorithms, such as unsupervised machine learning, to identify and distinguish between clusters from a manifold representing the distribution of response for a condition. The step may further include the use of plurality of discriminant analysis, such as linear discriminant analysis, principal component analysis, and normal discriminant analysis to identify and distinguish the plurality of clusters (and the separability of the clusters) from the manifold representing the distribution of response for a condition. Some embodiments may include the creation of a matrix that comprises the distance between the plurality of clusters. Also, for the conditions in which a plurality of conditions represent the plurality of concentration of an analyte or a component of an analyte, the curvature of the clusters may represent different concentrations and hence the matrix comprising the angle of vectors represents the curvatures corresponding to concentration may be generated.

[0039] The separability, difference, and distance between the plurality of clusters may be used to identify the polymers that may work as a potential candidates for the plurality of sensors of the sensing system, in subsequent polymer identification steps.

[0040] In some embodiments of the invention, genetic algorithms may be used to identify all the polymers that may work as potential candidates, as identified using the preceding steps, by forming an initial set of sensors and replacing the sensors according to the output of cluster identification step and polymer identification step.

[0041] Further, in some embodiments, the redundancy in sensor response may be identified through the step of identification of clusters, and based on the redundancy, a potential candidate for the sensor may be rejected. Further, a redundancy identification substep may be involved in the cluster identification step, which may be used for the identification of overlap between the clusters in a plurality of conditions or using another sensor in the sensing system.

[0042] In some embodiments of the invention, the training set and the test set for the unsupervised learning system are independent of each other and the test set may never change the training constraints.

[0043] Some embodiments of the invention mention controlling the environmental condition of the plurality of sensors of the sensor array, such that an extrinsic bias is not created for the sensor selection method.

[0044] In some embodiments, the position of the sensors on the substrate may be randomly changed before exposing the sensor to a plurality of conditions, to remove the positional bias of any of the sensors of the sensing system, at the time of polymer and hence the sensor selection.

Claims

CLAIMS1. A method for designing a polymer sensor array for detecting an analyte, the method comprising; identifying a plurality of polymer families and selecting a representative polymer for each polymer family, wherein the representative polymer exhibit properties of other polymers typical of other polymers within the family; printing the set of polymers on to a plurality of electrodes to form a sensor array; exposing the sensor array to a plurality of analytes to generate an electrical response; and processing the combined electrical response of the sensor array through a processor that is trained to detect difference between manifolds of electrical response corresponding to plurality of concentration of a plurality of analytes accepting a polymer for the sensor array after a difference in manifolds of electrical response corresponding to plurality of concentrations of a plurality of analytes is observed.

2. A method of claim 1, wherein exposing the sensor array to a plurality of analyte comprises exposing the sensor array to at least one mixture of analyte, single analyte, and plurality of concentrations of a single analyte.

3. The method of claim 1, wherein processing the response using the Al engine comprises receiving a multi-dimensional response from the sensor array; setting a saturation level for each polymer, wherein the saturation level is a predetermined threshold value for the response of a polymer; processing the multi-dimensional response using the Al engine to identify the saturated sensor, the unresponsive sensor, or the combination thereof; processing the multi-dimensional response at different concentrations of the analytes; processing a manifold associated with the sensor array; deducing the saturated sensor, the unresponsive sensor, or the combination thereof, based on the processed multi-dimensional response; changing at least one polymer in the set of polymers based on the deduced saturated sensor, the unresponsive sensor, or the combination thereof; and repeating theprinting, exposing, detecting, sending, and processing steps to obtain a final configuration of the sensor array.

4. The method of claim 3, wherein identifying the saturated sensor comprises comparing the response of the sensor to a predetermined saturation threshold.

5. The method of claim 3, wherein identifying the unresponsive sensor comprises comparing the response of the sensor to a predetermined sensitivity threshold.

6. The method of claim 3, wherein changing the polymer comprises selecting a polymer with a different sensitivity to the analyte from the same family of polymers.

Images