Method and system for fluid characterization and non-transitory computer readable medium
By installing electrodes in the container and using charge transfer curves, combined with neural network models, non-contact fluid characteristics measurement is realized, solving the problem of electrical contact limitation in the prior art, and providing high-precision fluid level and characteristic measurement solutions plan.
Patent Information
- Application Number
- CN202410688132.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Priority Date
- 2023-06-06
- Filing Date
- 2024-05-30
- Publication Date
- 2024-12-06
AI Technical Summary
The prior art is difficult to effectively measure the liquid level and characteristics of a fluid without contacting the fluid, especially in applications in automobiles, the Internet of Things and consumer fields. Traditional methods have limitations on electrical contact and cannot meet the needs of contactless sensing. .
By installing the first and second electrodes in the container, an excitation signal is generated using a signal generator and measuring charge transfer, fluid parameters are determined based on the charge transfer curve, and fluid characterization is performed using a neural network model to realize contactless fluid characteristics measurement.
It realizes high-precision non-contact measurement of fluid level and characteristics, and can determine parameters such as water hardness and ethanol concentration. It is suitable for a variety of application scenarios and improves the flexibility and accuracy of the equipment.
Smart Images

Figure CN119085739A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to methods and systems and non-transitory computer-readable media for fluid characterization. Background Art
[0002] Various sensing technologies can be used to sense the level or properties of a fluid in a container. There is a growing market for combined fluid level and fluid properties in the automotive, Internet of Things (IoT), and consumer sectors. For example, some applications of fluid level and fluid property sensing can include systems for windshield washer fluid, fuel, water hardness levels in coffee machines, smart sensing in refrigerators, etc. Many of these applications require contactless sensing with no electrical contact between the sensor and the fluid. Summary of the invention
[0003] This Summary is provided to introduce a selection of concepts in a simplified form that are further described below in the Detailed Description. This Summary is not intended to identify key factors or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.
[0004] In an embodiment of the technology presented herein, a method includes: measuring a first charge generated by a first excitation signal and transferred to a first electrode mounted to a container containing a test fluid during a first time interval; measuring a second charge generated by a second excitation signal and transferred to the first electrode during a second time interval; and determining a parameter of the test fluid based on a first charge transfer curve, the first charge transfer curve being generated based on the first charge and the second charge.
[0005] In an embodiment of the technology presented herein, a system includes: a device for measuring a first charge generated by a first excitation signal and transferred to a first electrode mounted to a container containing a test fluid during a first time interval; a device for measuring a second charge generated by a second excitation signal and transferred to the first electrode during a second time interval; and a device for determining a parameter of the test fluid based on a first charge transfer curve, the first charge transfer curve being generated based on the first charge and the second charge.
[0006] In an embodiment of the technology presented herein, a system includes: a container; a first electrode mounted to the container; a signal generator configured to apply a first excitation signal to the first electrode during a first time interval and to apply a second excitation signal to the first electrode during a second time interval; a first device configured to measure a first charge generated by the first excitation signal and transferred to the first electrode during the first time interval, and to measure a second charge generated by the second excitation signal and transferred to the first electrode during the second time interval; and a processor configured to determine a parameter of a test fluid in the container based on a first charge transfer curve, the first charge transfer curve being generated based on the first charge and the second charge.
[0007] In an embodiment of the technology presented herein, a non-transitory computer-readable medium stores instructions that, when executed, facilitate the performance of operations, the operations comprising: receiving a first charge generated by a first excitation signal and transferred to a first electrode mounted to a container containing a test fluid during a first time interval; receiving a second charge generated by a second excitation signal and transferred to the first electrode during a second time interval; and determining a parameter of the test fluid based on a charge transfer curve, the charge transfer curve being generated based on the first charge and the second charge.
[0008] In order to achieve the aforementioned and related purposes, the following description and the accompanying drawings set forth some illustrative aspects and implementations. These illustrative aspects and implementations merely indicate some of the various ways in which one or more aspects may be employed. Other aspects, advantages, and novel features of the present disclosure will become apparent from the following detailed description when considered in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0009] Figure 1 is a diagram illustrating an example system for fluid characterization according to some implementations.
[0010] Figure 2 is a diagram of an equivalent circuit of a container sensing device according to some embodiments.
[0011] Figure 3 is a graph of charge transfer curves according to some embodiments.
[0012] Figure 4 is a diagram of a neural network for fluid characterization according to some embodiments.
[0013] Figure 5 is a diagram of a processing unit according to some implementations.
[0014] Figure 6 is a diagram illustrating a method for characterizing a fluid according to some embodiments.
[0015] Figure 7 Exemplary implementations of computer readable media in accordance with some implementations are shown. DETAILED DESCRIPTION
[0016] The claimed subject matter is now described with reference to the accompanying drawings, wherein the same reference numerals are used to refer to the same elements throughout the text. In the following description, for the purpose of illustration, a large number of specific details are set forth in order to provide a thorough understanding of the claimed subject matter. However, it is apparent that the claimed subject matter can be practiced without these specific details. In other cases, well-known structures and devices are shown in block diagram form to facilitate description of the claimed subject matter.
[0017] It should be understood that the following description of the embodiments should not be understood as limiting. The scope of the present disclosure is not intended to be limited by the embodiments or drawings described below, which are considered to be illustrative only. The drawings are considered to be schematic representations, and the elements shown in the drawings are not necessarily shown to scale. On the contrary, the various elements are represented so that their functions and general purposes become apparent to those skilled in the art.
[0018] All numerical values in the detailed description and claims herein are indicated values modified by "about" or "approximately", and take into account experimental errors and variations that would be expected by a person of ordinary skill in the art.
[0019] Fluid characterization has applications in the automotive, consumer, and industrial sectors. In vehicle applications, containers or reservoirs may be provided for windshield washer fluid, fuel, or diesel exhaust fluid (AdBlue). In consumer applications, containers may be provided for appliances such as refrigerators or coffee machines. In industrial applications, containers may include fermentation containers, milk storage containers, technical fluid containers (e.g., oil or hydraulic fluids), process fluid containers, etc. Some applications employ level sensing, some employ fluid characterization, and some employ both level detection and fluid characterization. In some applications, the container is not used for fluid storage, but rather as a chamber for fluid characterization of a fluid provided to an appliance or tool. Example fluid characterization parameters include water hardness, ethanol concentration in wine, beer, or spirits, fat content in milk, or fluid contamination levels of oil or hydraulic fluids. Knowledge of fluid composition is useful for preventing waste of consumables, extending the life of machines, controls in industrial processes, preventing solid carbonates from clogging heating elements, determining dirt levels and detergent concentrations to control detergent and water consumption, controlling fermentation processes, determining the quality of technical fluids to ensure optimal fluid replacement intervals, etc.
[0020] In some embodiments, the fluid characterization system measures the charge transfer for multiple sensing intervals to generate a charge transfer curve. For a given test fluid, the charge transfer curve is unique to a given fluid property, such as conductivity and dielectric constant. Therefore, the charge transfer curve can be used for fluid characterization, such as determining the hardness of water, determining ethanol concentration, determining contamination levels, etc. In some embodiments, a neural network classifier is used to characterize the test fluid, which receives the conductivity curve as input and generates fluid characterization parameters as output.
[0021] Figure 1 1 is a block diagram of a fluid characterization system 100 for non-contact fluid sensing to characterize a test fluid 102 in a container 104 according to some embodiments. The electrical properties of the test fluid 102 are represented by a distributed network of impedances. In some embodiments, the system 100 includes an analog processing block 106 and a digital processing block 108. The analog processing block 106 is coupled to a first electrode 110 and a second electrode 112, wherein the first electrode 110 is mounted at a first point on an outer surface of a container 104 containing the test fluid 102, and the second electrode 104 is mounted at a second point on the outer surface of the container 104, such as opposite to the first point. In some embodiments, the first electrode 110 and the second electrode 112 are arranged in pairs at different heights on the container 104 to facilitate liquid level detection. In some embodiments, the first electrode 110 and the second electrode 112 are arranged on the same side of the container 104 to simplify sensor installation. The container 104 has an ambient ground 114 representing an ambient ground to surrounding objects and wall impedances 116 , 118 representing electrical characteristics of the container 104 , each represented by a characteristic resistance and capacitance.
[0022] The analog processing block 106 defines a single-port network configured to couple the signal generator 120 and the current integrator 122 or one or more of the first electrodes 110 to determine a set of charge transfer measurements (e.g., the charge transfer curve 300) associated with the container 104 and the test fluid 102. The signal generator 120 generates an excitation signal, such as a rectangular signal, and the current integrator 122 integrates the current provided to one or more of the first electrodes 110 to determine the charge transferred over a selected time interval.
[0023] The digital processing block 108 includes a controller 124 and a fluid classifier 126, the controller 124 controls the signal generator 120 to generate an excitation signal and receives the current integration measurement result from the current integrator 122, and the fluid classifier 126 characterizes the test fluid 102 based on the charge transfer curve. In some embodiments, the fluid classifier 126 uses a fluid classification model 128, which receives the charge transfer curve as an input and generates one or more fluid characterization parameters as an output. In some embodiments, the fluid classification model 128 includes a neural network model trained using a reference charge transfer curve of a fluid with known characteristics. The controller 124 iterates the excitation and current measurement results over a set of time intervals of different lengths to generate a charge transfer curve. In some embodiments, only the bottom first electrode 110 is used for charge transfer measurement for fluid characterization, and all electrodes in the first electrode 110 and the second electrode 112 pair are used for fluid level detection. In some embodiments, the charge transfer measurement is also used for level detection. In another embodiment, the first electrode 110 and the second electrode 112 pair covered by the test fluid 102 (ie, the upper surface of the test fluid 102 is higher than the first electrode 110 and the second electrode 112 pair) are connected in parallel by the routing circuit system 124 to increase the effective surface area available for sensing.
[0024] The current integrator 122 uses the principle of self-capacitance measurement to determine the charge transferred to one or more first electrodes 110. In some embodiments, a second current integrator 123 is provided in series with the second electrode to use mutual capacitance to determine the charge transferred from the first electrode 110 to the second electrode 112. A first charge transfer curve can be generated based on data from the first integrator 122, and a second charge transfer curve can be generated based on data from the second integrator 123. The self-capacitance and mutual capacitance charge transfer curves can be used to characterize the test fluid 102. The first charge transfer curve and the second charge transfer curve can be provided as input to the fluid classifier 126 and the fluid classification model 128.
[0025] In some embodiments, the fluid characterization system 100 includes one or more sensors 130 that measure fluid properties (such as density) or environmental properties (such as temperature). The fluid classifier 126 can use information from the one or more sensors 130 for fluid characterization.
[0026] Figure 2is a diagram of an equivalent circuit 200 of a container 104 and a test fluid 102 according to some embodiments. The effective resistance and capacitance of the test fluid 102 are represented by resistor 202 (Rw) and capacitor 204 (Cw). The wall capacitance is represented by capacitor 206 (Cp) and the switch resistance is represented by resistor 208 (Rsw). The signal generator 120 generates a rectangular excitation signal. The properties of the test fluid 102 affect the values of resistor 202 and capacitor 204, which changes the response of the circuit 200 to the excitation signal.
[0027] Figure 3 3 is a graph of a set of charge transfer curves 300 for fluids 102 having different properties according to some embodiments. The charge transfer curves 300 are differentiated by fluid parameters, such as conductivity and / or dielectric constant, which affect the values of Rw and Cw for a given wall capacitance Cp and switch resistance Rsw. Note that the curves are distinguishable for different fluid parameters. Each data point of the charge transfer curve 300 represents the charge transferred through the electrodes 110, 112 during a given time interval as measured by the current integrator 122 (and optionally the current integrator 123). In some embodiments, the time interval is at a minimum time interval value t int_min With the maximum time interval value t int_max The maximum charge Q max Depends on the wall capacitance Cp.
[0028] In some embodiments, the fluid classifier 126 receives charge transfer data points at multiple time intervals from the controller 124 and accumulates the charge transfer data points to generate a charge transfer curve 300 for the test fluid 102 having unknown characteristics. The fluid classifier 126 employs the fluid classification model 128 to generate an output indicative of a fluid parameter, such as conductivity, dielectric constant, ethanol concentration, diesel exhaust fluid concentration, water hardness, a combination of output parameters, such as conductivity and dielectric constant, or some other parameter or combination of parameters.
[0029] In some embodiments, the fluid classification model 128 is a neural network model trained using reference charge transfer curves from reference fluids with known parameter values (such as known conductivity and / or dielectric constant parameters). The fluid classification model 128 can also be trained using different grounding states of the reference fluid or container 104. For example, for each grounding state in a set of grounding states, such as ungrounded, weakly grounded, strongly grounded, fluid grounded, etc., a reference charge transfer curve can be generated for a reference fluid with a known conductivity value or dielectric constant value. The grounding state affects the shape of the charge transfer curve. Training the fluid classification model 128 with different grounding states enables the fluid classification model 128 to determine fluid parameters regardless of the grounding state. The training charge transfer curves for known fluids can be generated using theoretical calculations or by using the fluid characterization system 100 to generate reference charge transfer curves for fluids with known parameters. The training set can vary depending on the desired output. For example, if the desired output has only one parameter, the training set includes reference charge transfer curves with known values for the output parameter. If the desired output is more than one parameter, the training set includes reference charge transfer curves having known values for all of the output parameters or multiple sets of reference charge transfer curves, each set having a known value for one of the output parameters.
[0030] Figure 44 is a diagram of a neural network classifier 400 according to some embodiments. At 402, the neural network classifier 400 receives an input 402, such as a charge transfer curve. The neural network classifier 400 includes an input layer 404, a convolutional layer 406, a rectified linear unit (ReLU) layer 408, a flattening layer 410, a dense layer 412, and a softmax layer 414 that generates an output 416 from the input 402. In some embodiments, the input layer 404 receives data points of the charge transfer curve of the test fluid 102 as an input vector. In some embodiments, the convolutional layer 406 applies a kernel and a bias to extract features of the charge transfer curve. In some embodiments, the convolutional layer 406 implements a Conv2D function with a kernel of 6x2x1x4 and a bias of 4, although other configurations may also be used. In some embodiments, the ReLU layer 408 replaces negative numbers in the filtered data with zeros. In some embodiments, the flattening layer 410 is used to convert all resulting two-dimensional arrays from the convolutional layer 406 into continuous linear vectors. In some embodiments, dense layer 412 is a neuron layer where each neuron receives input from all neurons in the previous layer and is used to classify the charge transfer curves based on the output from convolutional layer 406. In some embodiments, softmax layer 414 is used as an activation function in the output layer for predicting a multinomial probability distribution. Output 416 represents one or more characterizing parameters of test fluid 102, such as conductivity, dielectric constant, ethanol concentration, diesel exhaust fluid concentration, water hardness, a combination of output parameters, such as conductivity and dielectric constant, or some other parameter or combination of parameters.
[0031] In some embodiments, the fluid classification model 128 is trained for a specific application, such as determining ethanol concentration. It is known that the conductivity and dielectric constant of an ethanol-water mixture depend on the weight percentage of ethanol. After the fluid classification model 128 is trained using charge transfer curves from fluids with different ethanol concentrations and ground states, the fluid characterization system 100 can be used to sense the ethanol concentration of the test fluid 102 and output the percentage of ethanol. The ethanol percentage can be used to automatically control a fermentation system or automatically generate a message when an ethanol percentage threshold is met.
[0032] Similarly, the fluid classification model 128 can be trained to detect the hardness of water for use with an appliance, such as a coffee maker, a washing machine, a dishwasher, a wet vacuum cleaner, a water softener, or some other appliance. The appliance can have an internal water softener, or a setting that depends on the water hardness can be used. The fluid characterization system 100 can be integrated into the appliance so that the appliance can enable or disable the internal water softener, or select a setting based on the water hardness measured by the fluid characterization system 100. For example, if the fluid characterization system 100 detects that the incoming water is soft enough (a built-in water softener that provides soft water to the appliance is in place), the appliance can disable the internal water softener. If the appliance uses a water softener, recharge can be initiated in response to the fluid characterization system 100 detecting a water hardness that exceeds a threshold. Initiating recharge based on the measured water hardness reduces the waste of unnecessary recharging.
[0033] In another embodiment, the fluid classification model 128 can be trained to identify unknown fluids. In addition to the charge transfer curve, additional fluid properties such as density can be provided as inputs to the fluid classification model 128. After the fluid classification model 128 is trained using charge transfer curves from fluids with different densities, the fluid characterization system 100 can be used to identify unknown fluids using the measured charge transfer curves and density information from the sensor.
[0034] Figure 5 5 is a diagram of a device 500 for implementing the fluid characterization system 100 according to some embodiments. In some embodiments, the device 500 includes a bus 502, a processor 504, a memory 506 storing software instructions or operations, an input device 508, an output device 510, a communication interface 512, and a power source 514, such as a battery. The processor 504 receives data from the current integrator 122 (and optionally the current integrator 123) and implements a software application (implementing the controller 124 and the fluid classifier 126). The device 500 may include a processor 504, a memory 506 storing software instructions or operations, an input device 508, an output device 510, a communication interface 512, and a power source 514, such as a battery. The processor 504 receives data from the current integrator 122 (and optionally the current integrator 123) and implements a software application (implementing the controller 124 and the fluid classifier 126). Figure 5 Fewer components, more components, different components and / or different arrangements of components may be shown in the drawings.
[0035] According to some embodiments, bus 502 includes a path that enables communication between components of device 500. For example, bus 502 may include a system bus, an address bus, a data bus, and / or a control bus. Bus 502 may also include a bus driver, a bus arbiter, a bus interface, a clock, etc. Processor 504 includes one or more processors, microprocessors, data processors, coprocessors, application specific integrated circuits (ASICs), controllers, programmable logic devices, chipsets, field programmable gate arrays (FPGAs), application specific instruction set processors (ASIPs), systems on chip (SoCs), central processing units (CPUs) (e.g., one or more cores), microcontrollers, and / or some other types of components that interpret and / or execute instructions and / or data. Processor 504 may be implemented as hardware (e.g., microprocessors, etc.), a combination of hardware and software (e.g., SoCs, ASICs, etc.), and may include one or more memories (e.g., caches, etc.), etc.
[0036] In some embodiments, the processor 504 controls the entire operation or part of the operation performed by the controller 124 and the fluid classifier 126. The processor 504 performs one or more operations based on an operating system and / or various applications or computer programs (e.g., software). The processor 504 accesses instructions from the memory 506, other components of the device 500, and / or a source external to the device 500 (e.g., a network, another device, etc.). The processor 504 can perform operations and / or processes based on various techniques including, for example, multithreading, parallel processing, pipelining, interleaving, etc.
[0037] In some embodiments, the memory 506 includes one or more memories and / or one or more other types of storage media. For example, the memory 506 may include one or more types of memory, such as random access memory (RAM), dynamic random access memory (DRAM), cache, read-only memory (ROM), programmable read-only memory (PROM), static random access memory (SRAM), single in-line memory module (SIMM), dual in-line memory module (DIMM), flash memory and / or some other suitable types of memory. The memory 506 may include a hard disk, a disk, an optical disk, a magneto-optical disk, a solid-state disk, a storage medium based on a micro-electromechanical system (MEMS), a storage medium based on nanotechnology and / or some other suitable disks. The memory 506 may include a drive for reading and writing storage media from a storage medium. The memory 506 may be external to the device 500 and / or removable from the device 500, such as, for example, a universal serial bus (USB) memory stick, a dongle, a hard disk, a mass storage device, an offline storage device or some other types of storage media (e.g., a compact disk (CD), a digital versatile disk (DVD), a blue disc (BD), etc.). The memory 506 may store data, software, and / or instructions related to the operation of the activity classifier 100 .
[0038] The communication interface 512 allows the device 500 to communicate with other devices, networks, systems, sensors, etc. on the network. The communication interface 512 may include one or more wireless interfaces and / or wired interfaces. For example, the communication interface 512 may include one or more transmitters and receivers or transceivers. The communication interface 512 may operate according to a protocol stack and a communication standard. In some embodiments, the communication interface 512 includes an antenna. The communication interface 512 may include various processing logic or circuits (e.g., multiplexing / demultiplexing, filtering, amplification, conversion, error correction, etc.). In some embodiments, the communication interface 512 uses a long-range wireless protocol such as a cellular protocol or a WiFi protocol, such as a BLUETOOTH protocol, or a wireless communication protocol such as a cellular protocol or a WiFi protocol. TM The IEEE 802.11 protocol can be used to operate over short distances or over wired protocols such as Ethernet.
[0039] In some embodiments, input device 508 allows input to device 500. For example, input device 508 may include a keyboard, mouse, display, touch screen, non-touch screen, button, switch, input port, voice recognition logic and / or some other type of suitable visual, auditory or tactile input components. Output device 510 allows output from device 500. For example, output device 510 may include a speaker, display, touch screen, non-touch screen, projection display, lamp, output port and / or some other type of suitable visual, auditory or tactile output components. In some embodiments, output device 510 may be remote and may communicate with processor 504 using communication interface 512.
[0040] In some embodiments, the fluid characterization parameters generated by the fluid characterization system 100 are used to change an operating parameter of the remote device 516, such as based on the communication over the communication interface 512. For example, if the remote device 516 is an appliance, the operating parameter can be a mode of the remote device 516, such as a water softener enabled mode or a water softener disabled mode, or some other mode. In some embodiments, the remote device 516 can take an action based on the fluid characterization parameters, such as initiating a charging cycle of a water softener. In some embodiments, the remote device 516 can display an alarm or notification based on the fluid characterization parameters, such as an alarm to terminate fermentation, an alarm that a fluid parameter is outside of an acceptable limit, or some other alarm.
[0041] Figure 6 6 is a flow chart illustrating an example method 600 for fluid characterization. At 602, a first charge generated by a first excitation signal and transferred during a first time interval to a first electrode 110 mounted to a container 104 containing a test fluid 102 is measured. At 604, a second charge generated by a second excitation signal and transferred during a second time interval to the first electrode 110 is measured. At 606, a parameter of the test fluid is determined based on a charge transfer curve generated based on the first charge and the second charge.
[0042] Figure 7An exemplary embodiment 700 of a computer-readable medium 702 according to some embodiments is shown. One or more embodiments relate to a computer-readable medium including processor-executable instructions configured to implement one or more of the techniques presented herein. Embodiment 700 includes a non-transitory computer-readable medium 702 (e.g., a CD-R, DVD-R, flash drive, disk of a hard drive, etc.) having computer-readable data 704 encoded thereon. The computer-readable data 704 in turn includes a set of processor-executable computer instructions 706, which are configured to facilitate operations according to one or more principles set forth herein when executed by a computing device 708 including a reader 710 for reading the processor-executable computer instructions 706 and a processor 712 for executing the processor-executable computer instructions 706. In some embodiments, the processor-executable computer instructions 706 are configured to facilitate execution of a method 714 when executed, such as at least some of the aforementioned methods. In some implementations, the processor executable computer instructions 706, when executed, are configured to facilitate implementation of a system, such as at least some of one or more of the aforementioned systems.One of ordinary skill in the art may design many such computer readable media that are configured to operate according to the techniques presented herein.
[0043] In an embodiment of the technology presented herein, a method includes: measuring a first charge generated by a first excitation signal and transferred to a first electrode mounted to a container containing a test fluid during a first time interval; measuring a second charge generated by a second excitation signal and transferred to the first electrode during a second time interval; and determining a parameter of the test fluid based on a first charge transfer curve generated based on the first charge and the second charge.
[0044] In an embodiment of the technology presented herein, determining a parameter of the test fluid includes determining the parameter based on the first charge transfer curve using a fluid classification model.
[0045] In an embodiment of the technology presented in this article, the fluid classification model includes a neural network model, and the method includes: training the neural network model using a first reference charge transfer curve of a reference fluid having a first ground state and a second reference charge transfer curve of a reference fluid having a second ground state different from the first ground state.
[0046] In an embodiment of the technology presented herein, the fluid classification model includes a neural network model, and the method includes: training the neural network model using a first reference charge transfer curve associated with a first reference fluid having a first known characteristic and a second reference charge transfer curve associated with a second reference fluid having a second known characteristic different from the first known characteristic.
[0047] In an embodiment of the technology presented in this article, the method includes: placing a first reference fluid in a container, generating a first reference charge transfer curve by measuring a third charge generated by a third excitation signal and transferred to the first electrode during a third time interval, measuring a fourth charge generated by a fourth excitation signal and transferred to the first electrode during a fourth time interval, and generating a first reference charge transfer curve based on the third charge and the fourth charge.
[0048] In an embodiment of the technology presented herein, measuring the first charge includes integrating a current provided to the first electrode during a first time interval.
[0049] In an embodiment of the technology presented herein, the method includes measuring a third charge generated by a first excitation signal and transferred to a second electrode mounted to a container during a first time interval, measuring a fourth charge generated by a second excitation signal and transferred to the second electrode during a second time interval, and generating a second charge transfer curve based on the third charge and the fourth charge, wherein determining a parameter of the test fluid based on the first charge transfer curve includes determining the parameter of the test fluid based on the first charge transfer curve and the second charge transfer curve.
[0050] In embodiments of the technology presented herein, determining a parameter of the test fluid includes determining at least one of conductivity, dielectric constant, ethanol concentration, diesel exhaust fluid concentration, or water hardness.
[0051] In an embodiment of the technology presented herein, a method includes controlling a device based on a parameter of a test fluid.
[0052] In an embodiment of the technology presented herein, a method includes determining that an upper surface of a test fluid in a container is at a higher height than a second electrode mounted to the container, and connecting the first electrode in series with the second electrode.
[0053] In an embodiment of the technology presented herein, a system includes: a container; a first electrode mounted to the container; a signal generator configured to apply a first excitation signal to the first electrode during a first time interval and to apply a second excitation signal to the first electrode during a second time interval; a first device configured to measure a first charge generated by the first excitation signal and transferred to the first electrode during the first time interval, and to measure a second charge generated by the second excitation signal and transferred to the first electrode during the second time interval; and a processor configured to determine a parameter of a test fluid in the container based on a first charge transfer curve generated based on the first charge and the second charge.
[0054] In an embodiment of the technology presented herein, the processor is configured to determine the parameter based on the first charge transfer curve using a fluid classification model.
[0055] In an embodiment of the technology presented herein, the fluid classification model includes a neural network model.
[0056] In an embodiment of the technology presented herein, the first device includes a current integrator.
[0057] In an embodiment of the technology presented herein, a system includes: a second electrode mounted to a container, wherein a first device is configured to measure a third charge generated by a first excitation signal and transferred to the second electrode mounted to the container during a first time interval, measure a fourth charge generated by a second excitation signal and transferred to the second electrode during a second time interval, and generate a second charge transfer curve based on the third charge and the fourth charge, and a processor is configured to determine a parameter of a test fluid in the container based on the first charge transfer curve and the second charge transfer curve.
[0058] In an embodiment of the technology presented herein, the parameter of the test fluid includes at least one of conductivity, dielectric constant, ethanol concentration, diesel exhaust fluid concentration, or water hardness.
[0059] In an embodiment of the technology presented herein, the processor is configured to control the second device based on a parameter of the test fluid.
[0060] In an embodiment of the technology presented herein, a non-transitory computer-readable medium stores instructions that, when executed, facilitate the performance of operations including: receiving a first charge generated by a first excitation signal and transferred to a first electrode mounted to a container containing a test fluid during a first time interval; receiving a second charge generated by a second excitation signal and transferred to the first electrode during a second time interval; and determining a parameter of the test fluid based on a charge transfer curve generated based on the first charge and the second charge.
[0061] In an embodiment of the technology presented herein, operations include determining parameters of a test fluid based on a charge transfer curve using a fluid classification model.
[0062] In embodiments of the technology presented herein, determining a parameter of the test fluid includes determining at least one of conductivity, dielectric constant, ethanol concentration, diesel exhaust fluid concentration, or water hardness.
[0063] The term "computer-readable medium" may include communication media. Communication media typically embodies computer-readable instructions or other data in a "modulated data signal" such as a carrier wafer or other transport mechanism, and includes any information delivery media. The term "modulated data signal" may include a signal that has one or more of its characteristics set or changed in such a manner as to encode information in the signal.
[0064] Any aspect or design described herein as an "example" or the like is not necessarily to be construed as being superior to other aspects or designs. Rather, the use of the word "example" is intended to present one possible aspect and / or implementation that may be related to the techniques presented herein. Such an example is not necessary for or intended to be limiting of such techniques. Various implementations of such techniques may include such examples alone or in combination with other features, and / or the examples shown may be altered and / or omitted.
[0065] Various operations of the embodiments are provided herein. In one embodiment, one or more of the operations described may constitute computer-readable instructions stored on one or more computer-readable media, and if performed by a computing device, these computer-readable instructions will cause the computing device to perform the described operations. The order of some or all of the operations described in the operation should not be interpreted as implying that these operations must rely on the order. Without departing from the scope of the present disclosure, alternative sequencing can be achieved. In addition, it should be understood that not all operations must be present in each embodiment provided herein. In addition, it should be understood that in some embodiments, not all operations are necessary.
[0066] Although the subject matter has been described in language specific to structural features and / or methodological acts, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing at least some of the claims.
[0067] As used in this application, the term "or" is intended to mean an inclusive "or" rather than an exclusive "or". That is, unless otherwise specified or clear from the context, "X adopts A or B" is intended to mean any natural inclusive arrangement. That is, if X adopts A, X adopts B, or X adopts both A and B, then "X adopts A or B" is satisfied in any of the aforementioned cases. In addition, unless otherwise specified or clearly directed to a singular form from the context, the articles "one" and "an" used in this application and the appended claims can generally be interpreted as referring to "one or more". In addition, unless otherwise specified, "first", "second", etc. are not intended to imply time, space, order, etc. On the contrary, such terms are only used as identifiers, names, etc. of features, elements, items, etc. For example, the first element and the second element generally correspond to element A and element B or two different or two identical elements or the same element.
[0068] In addition, although the present disclosure has been shown and described with respect to one or more implementations, those skilled in the art will think of equivalent changes and modifications based on the reading and understanding of this specification and the drawings. The present disclosure includes all such modifications and changes and is limited only by the scope of the appended claims. In particular, with respect to the various functions performed by the components (e.g., elements, resources, etc.) described above, unless otherwise indicated, the terms used to describe such components are intended to correspond to any component that performs the specified functions of the described components (e.g., functionally equivalent), even if the disclosed structure is not structurally equivalent to the functions in the example implementations shown herein that perform the present disclosure. In addition, although specific features of the present disclosure may be disclosed only for one implementation in several implementations, such features may be combined with one or more other features of other implementations as may be desired and advantageous for any given or specific application. In addition, with respect to the terms "includes", "having", "has", "with" or variations thereof used in the detailed description and claims, such terms are intended to be inclusive in a manner similar to the term "comprising".
Claims
1. A method for fluid characterization, comprising: measuring a first charge generated by a first excitation signal and transferred during a first time interval to a first electrode mounted to a container containing a test fluid; measuring a second charge generated by a second excitation signal and transferred to the first electrode during a second time interval; as well as A parameter of the test fluid is determined based on a first charge transfer curve generated based on the first charge and the second charge.
2. The method according to claim 1, wherein: Determining a parameter of the test fluid includes determining the parameter based on the first charge transfer curve using a fluid classification model.
3. The method according to claim 2, wherein: The fluid classification model includes a neural network model, and The method includes training the neural network model using a first reference charge transfer curve of a reference fluid having a first ground state and a second reference charge transfer curve of the reference fluid having a second ground state different from the first ground state.
4. The method according to claim 2, wherein: The fluid classification model includes a neural network model, and The method includes training the neural network model using a first reference charge transfer curve associated with a first reference fluid having a first known characteristic and a second reference charge transfer curve associated with a second reference fluid having a second known characteristic different from the first known characteristic.
5. The method according to claim 4, comprising: placing the first reference fluid in the container; The first reference charge transfer curve is generated by: measuring a third charge generated by a third excitation signal and transferred to the first electrode during a third time interval; measuring a fourth charge generated by a fourth excitation signal and transferred to the first electrode during a fourth time interval; as well as The first reference charge transfer curve is generated based on the third charge and the fourth charge.
6. The method according to claim 1, wherein: Measuring the first charge includes integrating a current provided to the first electrode during the first time interval.
7. The method according to claim 1, comprising: measuring a third charge generated by the first excitation signal and transferred to a second electrode mounted to the container during the first time interval; measuring a fourth charge generated by the second excitation signal and transferred to the second electrode during the second time interval, and A second charge transfer curve is generated based on the third charge and the fourth charge, wherein: Determining a parameter of the test fluid based on the first charge transfer curve includes determining a parameter of the test fluid based on the first charge transfer curve and the second charge transfer curve.
8. The method of claim 1, wherein: Determining a parameter of the test fluid includes determining at least one of conductivity, dielectric constant, ethanol concentration, diesel exhaust fluid concentration, or water hardness.
9. The method according to claim 1, comprising: A device is controlled based on a parameter of the test fluid.
10. The method according to claim 1, comprising: determining that an upper surface of the test fluid in the container is at a height higher than a second electrode mounted to the container; as well as The first electrode and the second electrode are connected in series.
11. A system for fluid characterization, comprising: container; a first electrode mounted to the container; a signal generator configured to apply a first excitation signal to the first electrode during a first time interval and to apply a second excitation signal to the first electrode during a second time interval; a first device configured to: measure a first charge generated by the first excitation signal and transferred to the first electrode during the first time interval, and to measure a second charge generated by the second excitation signal and transferred to the first electrode during the second time interval; as well as A processor is configured to determine a parameter of a test fluid in the container based on a first charge transfer curve generated based on the first charge and the second charge.
12. The system of claim 11, wherein: The processor is configured to determine the parameter based on the first charge transfer curve using a fluid classification model.
13. The system of claim 12, wherein: The fluid classification model includes a neural network model.
14. The system of claim 11, wherein: The first device includes a current integrator.
15. The system according to claim 11, comprising: a second electrode mounted to the container, wherein: The first device is configured to measure a third charge generated by the first excitation signal and transferred to a second electrode mounted to the container during the first time interval, measure a fourth charge generated by the second excitation signal and transferred to the second electrode during the second time interval, and generate a second charge transfer curve based on the third charge and the fourth charge, and The processor is configured to determine a parameter of the test fluid in the container based on the first charge transfer curve and the second charge transfer curve.
16. The system of claim 11, wherein: The parameter of the test fluid includes at least one of conductivity, dielectric constant, ethanol concentration, diesel exhaust fluid concentration, or water hardness.
17. The system of claim 11, wherein: The processor is configured to control a second device based on a parameter of the test fluid.
18. A non-transitory computer readable medium storing instructions that, when executed, facilitate performance of operations comprising: receiving a first charge generated by a first excitation signal and transferred during a first time interval to a first electrode mounted to a container containing a test fluid; receiving a second charge generated by a second excitation signal and transferred to the first electrode during a second time interval; as well as A parameter of the test fluid is determined based on a charge transfer curve generated based on the first charge and the second charge.
19. The non-transitory computer readable medium of claim 18, wherein: The operations include: Parameters of the test fluid are determined based on the charge transfer curve using a fluid classification model.
20. The non-transitory computer readable medium of claim 18, wherein: Determining the parameters of the test fluid includes: At least one of conductivity, dielectric constant, ethanol concentration, diesel exhaust fluid concentration, or water hardness is determined.
