Fluid sensing device and control system

Abstract

A system for determining characteristics of milk or other fluid flowing through an in-line sensor system is disclosed, the system comprising: a laser engine that emits laser radiation through the milk as it flows through the sensing system; a laser detector that receives the laser light after the laser light has passed through the milk and generates a corresponding laser reading; one or more processors; and a computer memory storing computer readable instructions. The instructions cause the processor to: receive laser readings from the laser detector from the laser detector; identifying, from the laser readings, spectral data reflecting a physical property of the fluid as it flows through the sensing system; and determining one or more fluid measurements for the corresponding one or more components of the fluid using the spectral data and reference data defining one or more reference spectra for each possible component of the fluid.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application claims the benefit of U.S. Provisional Application No. 63 / 414,065, filed on October 7, 2022, the disclosure of which is incorporated herein in its entirety. Technical Field

[0002] This document describes automated control and sensing using lasers. Background Art

[0003] A tunable laser is a laser with an operating wavelength that can be changed in a controlled manner. Most or all laser gain media allow small shifts in the output wavelength, and some such laser gain media also allow continuous tuning over a more significant wavelength range. There are gas lasers, liquid lasers, and solid-state lasers. Some examples include excimer lasers, gas lasers, dye lasers, solid-state lasers, semiconductor crystal and diode lasers, and free electron lasers.

[0004] Industrial control systems (ICS) include electronic control systems and associated instrumentation that can be used for industrial process control. Control systems can range in size from a few modular panel mounted controllers to large interconnected and interactive distributed control systems. Some control systems are implemented through supervisory control and data acquisition (SCADA) and / or programmable logic controllers (PLC).

[0005] Dairy farms involve lactating mammals such as cows, goats, sheep, etc. for milk production, which in turn is used for a range of other dairy products such as fluid milk, anhydrous milk fat, whole milk powder, lactose, cheese, butter, yogurt, cream, kefir, etc. Milk and dairy products are an integral and important part of the global food industry, and dairy farms are responsible for raw material production. Production efficiency, sustainability and ultimately profitability depend on many factors, but those of key importance are efficient herd health and herd selection management. Summary of the invention

[0006] In-line electro-optical sensors for real-time composition analysis can be implemented in different industrial, agricultural and biomedical environments where there are liquid, solid or gas phase substances flowing through. Specifically, methods are proposed for in-line real-time monitoring of milk composition in milking lines for individual animals, combined with the use of measured composition data to aggregate and construct both short-term and long-term data trends and build an overall process optimization model, thereby enhancing farm efficiency in terms of output, minimum animal downtime, and controlled herd selection. Some embodiments of the present invention use combined electro-optical in-line sensors within the milking line to monitor and aggregate real-time or near real-time milk composition data for each individual milking process for each animal in the herd. The data aggregated over time can be used by the control system to proactively provide early warning indications of animal health, in this way providing the opportunity for timely treatment, possibly at a very low cost in terms of both medication and animal downtime. Post-treatment animal output and milk composition monitoring for data trending can provide information on the efficacy of treatment, which in turn can help farmers establish the most efficient way to treat one or another animal health problem and compare different available medication options. Additionally, individual animal monitoring within a herd provides direct data for herd selection based on specific desired traits (such as high protein and / or high fat content, disease resistance, etc.), resulting in a controlled process and improved business efficiency and commercial profitability.

[0007] A system of one or more computers may be configured to perform specific operations or actions by means of installing software, firmware, hardware, or a combination thereof on the system, which in operation causes the system to perform the actions. One or more computer programs may be configured to perform specific operations or actions by means of including instructions, which when executed by a data processing device causes the device to perform the actions. An overall aspect includes a sensing system for sensing a physical property of a fluid. The system includes a laser engine configured to emit spectrally tunable laser radiation that passes through the fluid as the fluid flows through the sensing system. The sensing system also includes a laser detector configured to receive the laser radiation after the laser radiation has passed through the fluid and generate a corresponding laser reading. The system also includes one or more processors. The system also includes a computer memory storing computer-readable instructions that, when executed by the one or more processors, cause the one or more processors to perform operations that may include: receiving laser readings from a laser detector; identifying spectral data reflecting physical properties of the fluid as the fluid flows through the sensing system from the laser readings; and determining one or more fluid measurements for one or more components of the fluid using the spectral data and reference data defining one or more reference spectra for each possible component of the fluid. Other embodiments of this aspect include corresponding computer systems, apparatus, and computer programs recorded on one or more computer storage devices, each of which is configured to perform the actions of the method. Implementations may include one or more of the following features. The system wherein the system may further include a housing housing the laser engine, the laser detector, and one or more processors, and computer memory. The system may further include a network interface, and wherein the operation may further include transmitting the one or more fluid measurements through the network interface. The system may further include: a housing housing the laser engine and the laser detector; and one or more computing devices may include the one or more processors and computer memory. The system may further include a fluid channel through which a fluid flows between the laser engine and the laser detector, and wherein the laser engine and the laser detector are at least partially fixedly held in the fluid channel so that a portion of the fluid flows between the laser engine and the laser detector. The laser engine and the laser detector are fixedly held apart by a distance of less than 10 mm. The laser engine is coupled to a photon-permeable sheath configured to prevent contact of the laser engine by the fluid. The system may further include: a contact sensor at least partially fixedly held in the fluid channel; an optical emitter at least partially fixedly held in the fluid channel; and a color sensor at least partially fixedly held in the fluid channel. The system may further include a contact sensor configured to: contact the fluid as the fluid flows through the sensing system; sense one or more contact phenomena of the fluid to create corresponding contact readings; and wherein determining one or more fluid measurements may further include using the contact readings. The system may further include: an optical emitter configured to emit incoherent light; and a color sensor configured to receive the incoherent light after the incoherent light has passed through the fluid and generate corresponding incoherent readings; and wherein determining one or more fluid measurements may further include using the incoherent readings. The system may further include an automatic valve configured to selectively direct the flow of the fluid to a plurality of output channels; and wherein the operation may include actuating the automatic valve based on at least one of the fluid measurements. Actuating the automatic valve may include: engaging the automatic valve in response to determining that the fluid measurement for the contaminant is greater than a threshold value to direct the fluid to a waste bin. Actuating the automatic valve based on at least one of the fluid measurements may include: actuating the automatic valve to direct the fluid to a waste bin before the contaminated fluid reaches the automatic valve. The fluid is raw milk collected from livestock. The laser engine may include a III-V semiconductor-based laser. The III-V semiconductor-based laser is configured to emit light through an optical interface, and wherein the laser detector is positioned opposite the optical interface. The III-V semiconductor-based laser is a tunable laser.The III-V semiconductor-based laser is configured to emit a certain wavelength spectrum of light through the optical interface. The laser engine may include a III-V / IV semiconductor-based laser. The III-V / IV semiconductor-based laser is configured to emit light through the optical interface, and wherein the laser detector is positioned opposite the optical interface. The III-V / IV semiconductor-based laser is a tunable laser. The III-V / IV semiconductor-based laser is configured to emit a certain wavelength spectrum of light through the optical interface. The optical interface is positioned in a flow path of a fluid flowing through the sensing system. The optical interface may include a tube extending from the laser engine into a channel through which the fluid flows through the sensing system, the tube extending toward the laser detector, wherein the distance from the distal end of the glass tube to the surface of the laser detector is between 0.5 mm and 10 mm, and the tube may include an optically transparent portion. The fluid measurement value is an individual measurement value of a component at a specific time, and the operation may further include: aggregating the fluid measurement values ​​of a single milking period into an aggregate value, the aggregate value reflecting the change in the fluid measurement value through the milking period. The operations may further include storing fluid measurements for a single milking session, the fluid measurements being indexed for an individual animal by a unique identifier for the single milking session. The operations may further include storing the fluid measurements for a single milking session together with other fluid measurements for other milking sessions to generate historical data for a particular animal. The operations may further include using the historical data for each animal in the herd to generate herd-level indicators for a plurality of animals. The operations may further include matching the herd-level indicators with third-party data to at least one of the group that may include: 1) herd health data; 2) herd selection data; and 3) herd management data. The generation of individual or herd-level indicators includes using third-party data and historical data for each animal in the herd. Physical properties of the fluid include fluid composition, electrical properties, temperature, flow, color, quantitative component concentration levels, presence or absence of one or more components. Implementations of the described techniques may include hardware, methods or processes, or computer software on a computer-accessible medium.

[0008] Other features, aspects and potential advantages will be apparent from the accompanying description and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1A and Figure 1B An example system for collecting milk from livestock using an electro-optical in-line sensor including a tunable laser spectrum sensor is shown.

[0010] FIG. 2A to FIG. 2B An example apparatus for sensing a phenomenon of a fluid is shown.

[0011] Figure 3A and Figure 3B An example apparatus for sensing a phenomenon of a fluid is shown.

[0012] Figure 4 Example fluid channels are shown.

[0013] Figure 5 Shows a hardware architecture that can be used.

[0014] Figure 6 A process to generate a unique animal milk composition record is shown.

[0015] Figure 7 The model is shown.

[0016] FIG. 8A to FIG. 8D The generation of data from raw sensor data is shown.

[0017] Fig. 9 is a swim lane diagram of an example process for sensing a fluid.

[0018] Fig.10 Data showing the absorption spectra of the emulsion for various transmission path distances measured between the optical interface and the laser detector are shown.

[0019] Fig.11 Example data that may be used to sense fluids and control automated devices is shown.

[0020] Fig.12 A swim diagram showing an example process for sensing fluid that may be used in a milk collection system.

[0021] Fig.13 A flow chart of an example process for diverting contaminated fluid away from a holding tank and into a waste tank is shown.

[0022] Fig.14 is a schematic diagram illustrating examples of computing devices and mobile computing devices.

[0023] Like reference numbers in the various drawings indicate like elements. DETAILED DESCRIPTION

[0024] The online sensor can use one or more sensors to detect one or more properties of the fluid when the fluid passes through the online sensor. For example, the electro-optical sensor of the online sensor can be used to sense the properties of raw milk when raw milk is being collected from cows or other livestock. Based on the sensing performed by the online sensor, one or more automatic devices can be actuated by computer control. For example, if contaminants (e.g., blood, high somatic cell counts, etc.) are identified in the milk, an automatic valve in the fluid line can direct the flow of raw milk to a waste tank. Information from the online sensor can also be used to perform composition analysis to determine other properties of the milk. The determined properties can be used to make decisions about ongoing milk collection (e.g., directing high-fat content milk to a specific box, identifying milking equipment that is not correctly positioned, etc.), and can be aggregated with other historical and third-party information to identify trends related to the output of animals within the herd and a specific farm. In addition, the aggregated data can provide information about the health and production of the herd, which can be used to make decisions about herd health, selection, management and care.

[0025] like Figure 1A As shown in , the number of animals in a typical dairy farm can range from a few dozen to a few thousand, which results in a large number of animals being milked simultaneously several times a day (typically 2-3 times). A milking station designed to milk N cows simultaneously is equipped with N, 2N or 4N sensors (depending on the configuration of the milking system, which can collect milk from all 4 parts of the udder simultaneously, or 22 individually, or all 4 individually). Figure 5, data from each electro-optical sensor 2 (including milk composition, conductivity, temperature, color, flow, etc.) is streamed to a local network device - router 5, which collects the data and sends it to a local data server 6, which is hardware installed locally in each farm (or software as a virtual machine, etc.). Server 6 includes an operating system 61, such as but not limited to Ubuntu. The operating system contains a solution environment 62, which is a virtualized software environment with a module runtime function 620. The module runtime is a platform for running different modules, which are custom code applications designed to perform specific tasks such as spectrum capture 621, which connects to sensors, captures data streams, performs data pre-processing such as jitter correction, filtering, averaging, valid data selection, and data conversion to calibrated units such as time to frequency / wavelength, etc. Other specific tasks are local data storage 622, where data from sensors is stored, such as file reports, logs, processed data, partially processed data, and data from 3rd party sources 8; data processing 623, where live measurements from sensors (electrical, optical, spectral) are provided to the data model and aggregated with farm data such as unique animal ID, milking time, historical data, etc., and a unique animal milk composition record is generated. Additional modules are sensor management 624, responsible for connectivity with each sensor, monitoring sensor status, performance and configuration; another module - telemetry 625, responsible for sending data to and receiving data from the cloud infrastructure of the sensor system 7. The cloud infrastructure of the embodiment acts as a centralized infrastructure, providing resources, components and solutions, such as a data ingestion 71 component responsible for receiving data from different farm servers, 3rd party data sources, and successfully saving it to a cloud data warehouse 72 as a database and / or file storage 74, typically for large binary files, such as spectra, images, external data inputs, etc. Data processing and computing 76 provides cloud-based computing resources for different stages of data processing, where the stages depend on the configuration of the local farm servers 6 and the level of local data processed at the farm. The processed data is then stored again in the data warehouse 72 and / or file storage 74, and a subset of the data is then provided to the user application 73, which in turn provides the data to the end user 11 in the form of a web application, a local mobile application, a desktop application, etc.The data provided to the end user is adapted to the user according to the information content, which can be viewed as different selectable views or as interface layers, such as: a farmer interface that focuses more deeply on herd productivity, farm profitability, etc.; a veterinary interface that focuses more on individual animal health status, treatment efficacy, historical data, etc.; and an animal husbandry interface that focuses on herd selection, allowing farmers to determine favorable traits and select appropriate individual animals for herd selection to enhance desired traits, such as high fat and / or protein content, or disease resistance or milk volume, etc. These interfaces are interconnected and allow in-depth monitoring from individual animals to herds to multiple farms, and applying best practices in treatment, selection, nutrition, etc. based on actual data. Configuration and Management 75 serves as an administrator console for monitoring and configuring remote farm servers, sensors and the entire (Internet of Things) IoT infrastructure.

[0026] Real-time on-line milk monitoring in dairy farms provides a rather challenging environment, since the milk flowing through the milking line is discontinuous, often turbulent, contains air bubbles, and the composition of the milk changes dynamically during the milking cycle, so the sensor needs to track the dynamics. For spectral milk composition measurements, spectrally tunable laser radiation of known intensity and wavelength distribution is transmitted through the milk flow in the sensor flow compartment via an optical interface and is collected by a detector via a corresponding optical interface. The detector (which is a photodetector and thus converts the optical signal into an electrical signal) records a time domain signal (photovoltage or photocurrent) that needs to be processed into a usable absorption spectrum that can be used by further data processing to convert the spectral data into component concentration levels or in other words - composition. The process of pre-processing the raw data is called spectral capture and is described in detail in the literature. Figure 5 However, in some configurations, this module can also be located in the CPU module of each sensor (e.g. Figure 2A 212) shown in FIG. 1 , or in another scenario, the module may also be executed locally at the processor 212 shown in FIG. 1 . Figure 5 The data processing unit 76 of the cloud environment runs.

[0027] Figure 6The spectrum capture module 621 is shown in more detail. Here, the electrical signal from the detector 204 is first amplified by the amplifier 6211, and the current signal is converted to a voltage. The amplified signal is then sent to the analog-to-digital converter (ADC) 6212 and digitized. The signal from the detector, amplifier and ADC is a time signal - that is, an intensity function according to time. This signal is then sent to the processing device 6214, which can be a central processing unit (CPU), a microcontroller unit (MCU), a field programmable gate array (FPGA), a complex programmable logic device (CPLD) or a combination thereof, which performs further signal processing such as jitter correction, filtering, selection of valid spectra based on predefined rules, averaging, and finally time to wavelength / frequency conversion, and this signal is then sent to the data processing module 622 via the data link 6215, which is essentially an Ethernet cable. Time to wavelength conversion requires knowing the absolute wavelength emitted by the laser passing through the milk at all times, and then using this information for conversion. Frequency tunable laser architectures with absolute wavelength tracking and determination are described in US1177630 and US11202453.

[0028] Figure 1B An example system 100 for collecting milk from livestock using an electro-optical online sensor including a tunable laser spectrum sensor is shown. In the system 100, cows 102a-d are being milked to collect milk. The milk is conveyed through an online sensor 104 of a pipe 106. Depending on the properties of the milk detected by the online sensor 104, a corresponding valve 108 conveys the milk to a collection bin 110 or a waste bin 112, for example, depending on the presence or absence of contamination such as blood in the milk.

[0029] Cows 102a-d represent milking lines through which milk from one or more farm animals flows during the milking process. The number of animals in a typical dairy farm can range from tens to thousands, which results in a large number of animals being milked several times (typically 2-3 times) per day. A milking station designed to milk N cows simultaneously is equipped with N, 2N, or 4N sensors (depending on the configuration of the milking system, which can collect milk from all 4 parts of the udder at the same time, or 22 individually, or 4 all individually). The milking line can be connected to the animal manually or by a milking robot. The online sensor 104 can be integrated into the milking line or subsequently added to the milking line between the cows 102a-d and the collection box 110 and the waste box 112. The online sensor 104 can include one or more adapters that facilitate the mechanical interface between the milking line and the online sensor 104.

[0030] Data from the online sensor 104 is collected by one or more computing devices 114 (such as a cloud service or server process executed on a physical or virtual server) over one or more data networks. The device 114 may send data or graphical elements over a network (such as the Internet 116) for display on a user device 118, may store the data for long-term storage, or may use the data for other automated processes that utilize computer-readable instructions to engage computer-controlled hardware based on the data. The online sensor 104 provides electro-optical emulsion composition sensing in conjunction with additional physical parameters. As the milk flows through the online sensor 104, the online sensor 104 performs analysis (e.g., composition, color, electrical parameters) through spectral sensing, color sensing, conductivity and temperature monitoring, and milk volume, milk flow rate measurement. Although a single device 114 is depicted, it will be understood that the system 100 may operate using multiple devices as the device 114. For example, one or more local servers may be operated at the collection location, one or more remote servers may be operated in data centers located in different geographical locations, and the like. In some implementations, a local server receives and preprocesses data received from online sensors and transmits the preprocessed data to an external server (e.g., a cloud-based server). The data is further processed at the external server and used to provide feedback to a specific farm based on the data and to aggregate the data with additional historical or third-party data to build a herd data model, as will be further described below. The herd data model is used to understand herd health and to provide information to make decisions about herd selection, veterinary care, and economic management of the herd. In addition, the data processing in the external server can determine recommendations for farmers based on the herd data model output (e.g., recommendations about nutrition, treatment efficacy, disease or health warnings, and selection).

[0031] The system 100 may allow for automated data collection and control of hardware involved in the milk collection process. For example, the online sensor 104 may sense milk (or another related fluid) as it travels through a pipe. As will be appreciated, it takes some time (e.g., seconds) for the milk to travel between the online sensor 104 and the valve 108. In a time that is shorter than the time it takes for the milk to travel that distance, the online sensor 104 (perhaps working in conjunction with the computing device 114) may analyze the composition of the milk. Light from the sensor (i.e., tunable laser radiation from a spectral sensor, RGB light from a color sensor) continuously illuminates the flowing milk as the milk flows through the sensor. The spectral sensor responsible for the spectral milk composition analysis records a real-time milk absorption spectrum that is later reconstructed into real-time concentration data. Since milk composition is not constant over a milking cycle, for most situations, such as farm economic (yield) management, the real-time concentration levels are averaged over a single milking event to provide an average concentration level value for the milk collected from the cow. At the same time, high-resolution temporal data on concentration levels and other physical parameters (such as temperature, conductivity, contamination, etc.) can indicate valuable information, such as improper attachment of the milking system to the breast, sudden leakage of blood or other contaminants, etc. Both the high-resolution temporal data and the averaged data are collected and stored for further processing and aggregation. In the event of a contaminant being detected, the system 100 can promptly engage the corresponding valve 108 to divert the contaminated milk to the waste bin 112 rather than allowing the contamination to reach the collection bin 110 and contaminate the already collected milk, and / or simply display a warning to the operator and suggest the action that needs to be taken. This is particularly beneficial in situations where the contamination is difficult or impossible to detect by manual inspection and the valve needs to be controlled at a faster speed than a human reaction is possible. In some examples, the milk travels in the pipe 106 for less than two seconds—which is enough for automatic analysis and actuation, but shorter than the time it takes for a person to notice that the blood contaminated milk, not to mention the additional time required to reach and switch the valve to divert the contaminated milk.

[0032] The ability to detect contaminants in flowing milk in real time can allow automated systems to react quickly to contaminated milk and can provide timely warnings in non-automated systems. If not detected, a blood leak into the milking line caused by one animal could contaminate the entire collection box and thus result in loss of milk and, therefore, loss of income for the farm. Timely detection allows the milk of a bleeding animal to be automatically shut off or diverted from the box to waste without affecting milk collected from other farm animals. In manually operated farms, the sensor can provide an immediate audio or light signal to the operator so that milk from a bleeding animal does not reach the milk collection box.

[0033] Similarly, the use of online sensors that can sense properties and contaminants in flowing milk, as opposed to sensors that require extraction and separation of a test sample from a regular stream, can be used to identify contamination at the onset of contamination. For example, consider a system that extracts a test sample from a pipeline every five seconds. In this five-second window, a new contaminant may appear in the milk stream and have four seconds to reach the valve—longer than the two seconds required. In this way, the online sensor 104 can provide continuous sensing and faster automation than periodic sensing, thereby retaining milk that has been collected in the collection box 110 in the event that periodic sampling would result in contamination of the collection box (which would contaminate all collected milk and require the destruction of contaminated milk in the collection box, and therefore result in overall lower efficiency due to avoidable waste of materials). In addition, in contrast to online non-invasive optical sensing, periodic sampling is labor intensive and wastes milk because it is an offline measurement.

[0034] Figure 2A and Figure 2B An example device for sensing a phenomenon of a fluid is shown. Figure 2B , a schematic diagram of an online sensor 104 is shown. As shown, the online sensor 104 includes a fluid channel 106, which can be coupled to the pipe 106 to allow the fluid to pass through the online sensor 104. The channel 106 may include a coupler 200 (e.g., a threaded or tapped connector) for connecting in line with other pipe segments of the pipe 106. The fluid (e.g., milk) flows through the online sensor 104. As will be appreciated, there may be a certain amount of turbulence in the flow.

[0035] The in-line sensor 104 includes a plurality of sensing elements for sensing physical phenomena of the fluid, such as transmission spectrum, reflection spectrum, temperature, electrical properties, flow rate, etc.

[0036] The laser engine 202 emits laser radiation that passes through the fluid as the fluid flows through the sensing system. The laser engine 202 may include a spectrally tunable semiconductor laser or laser array, an external cavity spectrally tunable laser based on a semiconductor laser, and / or an on-chip laser or laser spectrometer based on a hybrid III-V / IV semiconductor. The laser engine 202 is coupled to a probe or sheath forming an optical interface (hereinafter referred to as FIG. 3 and FIG. 4 ). Figure 4). The optical interface directs the light emitted by the laser to illuminate the milk flow passing through the sheath or probe. The optical interface can be an optical fiber, an optical lens, a system of lenses and optical reflectors, an optical window, a hollow tube with an optical window, a glass tube, or a combination thereof. The laser engine 202 provides a laser beam that passes through the optical interface. Depending on the system optical design, the laser beam can be collimated, focused, or divergent. An example of a laser engine can be an external cavity tunable laser based on a III-V semiconductor (such as, for example, a gallium antimonide gain chip) that emits in the 1900nm-2400nm band, which covers the molecular absorption spectra of lactose, milk fat, and milk protein. Another example of a laser engine can be an on-chip laser spectrometer based on a hybrid gallium antimonide and a group IV semiconductor photonic integrated circuit, which includes one or more widely tunable hybrid III-V / IV lasers or laser arrays. For liquid substances other than milk, other tunable lasers or laser arrays based on group III-V semiconductors can be considered, depending on the location of the absorption characteristics of the target analyte within the electromagnetic spectrum. For example, GaAs may be the preferred material platform for wavelengths between 800nm ​​and 1100nm, InP may be the preferred material platform for wavelengths between 1300nm and 1700nm, and GaSb may be the preferred material platform for wavelengths above 1700nm.

[0037] In some implementations, the laser engine 202 is a solid-state laser-based device having a solid-state gain medium based on a widely tunable laser for emitting light. In some implementations, the laser engine also includes a wavelength shift tracking device for tracking the wavelength shift of the emitted light. In some implementations, the laser engine also includes an internal absolute wavelength reference (e.g., an absolute wavelength etalon) that contains a known calibration spectrum. In some implementations, the laser engine 202 performs a wavelength scan and uses the wavelength shift tracking device in combination with the absolute wavelength reference to provide an absolute wavelength determination of the emitted spectrum during the scan and provide calibration of the emitted spectrum. This wavelength calibration may also include additional components of the laser engine 202, including optical elements such as retroreflectors, mirrors, prisms, etc., which implement tunable laser radiation, output beam pointing, and spatial stability as required by the application. In some implementations, the laser engine 202 provides internal calibration of the wavelength for spectral measurement. Additional details of laser engine components, manufacturing of laser engines, and wavelength calibration hardware that can be used in the sensor systems described herein can be found in U.S. Patent Application No. 16 / 609,355 filed on May 21, 2018 and U.S. Patent Application No. 16 / 965,867 filed on January 31, 2019 and now issued as U.S. Patent No. 11,177,630, the contents of which are incorporated herein by reference. The laser engine provides tunable laser radiation that is always known by internal wavelength calibration during each spectral scan across the laser output bandwidth. This information is read by the electronics and used to convert the time spectrum to frequency—i.e., time to frequency conversion. After preprocessing such as jitter correction, filtering, averaging, and time to frequency conversion, such spectra can be used for spectral composition analysis by data algorithms.

[0038] Light emitted from the laser engine 202 and transmitted through the optical interface illuminates the milk flowing through the probe or sheath and is collected by a laser detector 204 positioned at the channel opposite the optical interface. The laser detector 204 receives the laser radiation after it has passed through the fluid and generates a corresponding laser reading. The laser detector 204 may include a photodiode or photodetector or a photodiode or photodetector array with an appropriate optical interface, which may be an optical window, lens, or fiber, etc. The photodetector or photodiode is typically a semiconductor-based component selected to be spectrally sensitive to the appropriate spectrum of the laser radiation emitted by the laser engine. In some implementations, the detector is a PIN or pBp or nBn based on AlGaInAsSb / GaSb or a superlattice based detector. Especially for wavelengths >1700nm. The detector may also be an extended GaInAs / InP photodetector. For shorter wavelengths, Si, GaInAs / InP, Ge may also be used.

[0039] The distance between the end of the optical interface and the laser detector 204 defines the optical path and is selected to provide the best signal-to-noise ratio, which depends on the optical configuration, i.e., the spectral range of the laser, the laser output power, the measured fluid properties (e.g., absorption coefficient), and the detector sensitivity, etc. As described below in FIG. Figure 4 As described in , the optical path is defined in such a way that when the emulsion is flowing through the pipe, the laser optical interface 300 and the detector optical interface define a gap of known size, which is the thickness of the flowing liquid (especially emulsion) that the light passes through before being detected by the detector. The interface is designed so that its mechanical implementation does not hinder the flow of emulsion, or the obstruction is minimal. For example, the interface can be implemented as a glass tube, a hollow tube with a window, or a lens, among other variants.

[0040] The use of a laser engine 202 and an optical interface placed within the flow path of the milk through the channel may require periodic cleaning of the optical interface to ensure transmission of light through the optical interface. Fatty residue from the milk may be deposited on the optical interface (and on the sensor described below). In some cases, the accumulation of fatty residue can be monitored by the sensor and removed or offset within the collected data. The sensor system is airtight and withstands milking system cleaning cycles that include high temperature cycles with water, low pH detergents, and high pH detergents. In addition, the system may include an alarm when the residue deposited on the optical interface reaches a threshold level that threatens measurement accuracy. In some implementations, one or more sensor systems may be included online, including redundant laser engines, laser detectors, and other sensors to ensure accurate readings and measurements.

[0041] The contact sensor group 206 contacts the fluid as it flows through the online sensor 104 and senses one or more contact phenomena of the fluid to create corresponding contact readings. The contact sensor group 206 may include a temperature sensor for measuring the temperature of the milk and / or an electrode pair or electrode array for measuring the conductivity of the milk. The conductivity value and dynamics are associated with the concentration of somatic cells present in the milk flowing through the sensor. In addition, conductivity, temperature, or a combination of both may also be used to assess the flow of milk through the sensor, which may help to quantitatively assess the milk component concentration level with the laser engine 202. In some implementations, the contact sensor group 206 includes a plurality of discrete sensors positioned away from each other in or adjacent to the fluid channel. The contact sensor group 206 may include a conductivity sensor and a temperature sensor. In other implementations, the contact sensor group 206 includes a single sensor capable of detecting multiple contact phenomena, or alternatively includes a plurality of sensors positioned adjacent to each other.

[0042] The optical emitter within the color sensor 208 emits incoherent light into the fluid, and the light reflected from the fluid is collected by the RGB detector forming the color sensor. The color sensor 208 can receive the incoherent light after it has passed through the fluid and generate a corresponding incoherent reading. The optical emitter of 208 can emit a broad spectrum of light into the milk flowing through the emitter. The light is reflected from the milk flow and is collected by the color sensor 208. The color sensor 208 may include an optical window, a wavelength filter, an optical lens, an optical prism, a diffraction grating, or a combination thereof. The presence of blood in the milk will affect the color of the milk, which in turn will change the reflectance spectrum of the light and be detected by the color sensor 208. In some implementations, the milk fat content can also be distinguished by changes in the reflectance spectrum (essentially color) as collected by the color sensor 208, and can be used in combination with the spectrum engine data or independently for milk fat level assessment.

[0043] The online sensor 104 may include computing hardware, such as one or more processors 212, memory 214, and other electrical components 216. Examples of processors, memory, and other electrical components are described below, for example, with respect to Fig. 9 Describe in more detail.

[0044] Figure 2B Another example online sensor 218 is shown. In the online sensor, some or all of the computations performed by the processor and memory are performed by 220 a computing device 220, which may include one or more servers, desktop computers, or the like.

[0045] Figure 3A and Figure 3BAn example inline sensor 104 for sensing a phenomenon of a fluid is shown. Shown here are an isometric view and a cross-sectional view of the inline sensor 104. The housing 302 is shown as housing components ( Figure 2B ), the components include a laser engine 202, a laser detector 204, a contact sensor group 206, an optical emitter and color sensor 208, and electronic components (such as a processor 212, a memory 214 and other electronic components 216).

[0046] In the cross-sectional view, the contact sensor group 206, the laser engine 202, the laser detector 204, and the optical emitter and color sensor 208 are shown. As shown, the laser engine 202 includes a sheath 300 that encapsulates the optical interface of the laser 212 to prevent fluid from reaching the laser engine 202 and making contact with the laser engine. For example, the sheath 300 can be constructed of glass, plastic, stainless steel, or another suitable material that allows the laser radiation of the laser engine 202 to pass through the optical interface within the sheath 300 to reach the laser detector 204. Depending on the material (e.g., for non-transparent materials), the sheath 300 can include one or more optical windows of transparent material. Sealing structures (e.g., adhesive layers, sliding fittings, gaskets) can be used to provide a fluid-proof / waterproof seal from external humidity. The contact sensor group 206, the laser engine 202, the laser detector 204, and the optical emitter and color sensor 208 210 sense multiple parameters of the flowing fluid, including the temperature of the fluid, the conductivity of the fluid for composition determination, and the color of the fluid based on reflection mode detection. The laser engine as shown in FIG3(A) is an external cavity laser with a III-V semiconductor gain chip embedded in a Metcalf-Littman external cavity configuration with a rotating mirror for wavelength tuning. Other variations of the cavity configuration may include Littrow, or micromechanical membrane mirrors (MEMS) may be used instead of rotating mirrors. FIG3(B) illustrates another possibility, where the laser engine 202 is implemented as an on-chip hybrid III-V / IV laser spectrometer, where wavelength discrimination is achieved electronically without moving parts, for example by means of vernier type filtering techniques.

[0047] Figure 4An example fluid channel 106 is shown in a side view. As shown therein, a sheath 300 is shown positioned inside the fluid channel 106. The cross-section of the fluid channel 106 is circular, but other geometries may also be possible. The circular cross-section of the fluid channel 106 promotes laminar flow of fluid through the channel. In some implementations, the diameter of the fluid channel 106 is 20 mm, 30 mm, 40 mm, 50 mm, 60 mm, or 80 mm, or any other suitable diameter. As described above, the optical interface sheath 300 is formed as a needle that does not obstruct the flow of fluid through the fluid channel 106. In some implementations, the optical interface sheath includes a material window that allows spectrally tunable laser radiation with a known intensity and wavelength distribution to pass through the window and through the emulsion in the channel 106 to the laser detector. In some implementations, the optical interface sheath is formed as a needle that enters the fluid channel, using a material that is opaque to the body of the sheath and a laser radiation transparent window. In some implementations, the optical interface sheath has other configurations, including as a tube / needle extending farther or closer into the channel, as a rod spanning the channel, or as a window in a sidewall of the channel, or any other suitable configuration.

[0048] The laser engine 202 and the laser detector 204 are at least partially fixedly held in the fluid channel 106 so that a portion of the fluid flows between the laser engine 202 and the laser detector 204. Specifically, a portion of the fluid flows between the optical interface in the sheath 300 and the laser detector 204. In this example, the laser engine 202 (i.e., the optical interface within the sheath 300) and the biconvex lens 400 are held at a distance of 0.6 mm from each other, thereby allowing the flow of the fluid therebetween for sensing. The lens 400 can be used, for example, to remove coherence from the laser emission before the laser emission reaches the laser detector 204. The end of the sheath 300 can have a width determined by the type of fluid to be sensed, with a larger width being used for some more transparent fluids. As will be understood, the distance can depend on the fluid type (and its absorption properties) and the laser output power. A longer distance can allow more interactions with the target analyte molecules, and therefore a smaller concentration / higher accuracy can be obtained. In some implementations, the end of the sheath 300 used to sense milk can be 0.25 mm, 0.5 mm, 1 mm, 1.5 mm, 2 mm, 2.5 mm, 3 mm, 3.75 mm, 8 mm, 10 mm, 12 mm, 15 mm, or any other suitable distance from the laser detector 204. Other distances are possible, including larger or shorter distances. Because milk consists primarily of water, the measurement of fat, protein, and lactose requires knowing the precise transmission distance between the optical interface of the laser 300 and the optical interface of the laser detector 204, which is essentially the thickness of the milk flowing through the laser optical path. If the gap between the components is too large, the signal from the amount of water in the milk will dominate the sensed spectrum, and the modulation of the laser spectrum by the valuable target components (lactose, fat, and protein) will be buried in the noise. On the other hand, if the gap between the components is too small, the absorbing components such as lactose and protein will also be small and difficult to measure because the laser intensity modulation of the milk components is proportional to the molar absorptivity of the target molecules, which in turn modulates the laser spectrum. Too small a gap will result in a small emulsion between the laser and the detector, and therefore the signal modulation is too small to be detected by the detector. The optimal gap depends on the laser output power level, the properties of the fluid flowing through, and the detector sensitivity, and is therefore selected for the best signal-to-noise ratio based on the performance of the components that make up the system. This step is completed during assembly and factory calibration.

[0049] The distance between the end of the sheath 300 and the laser detector 204 is oriented toward the bottom of the fluid channel 106 so that the portion of the fluid channel 106 between the end of the sheath 300 and the laser detector is always filled with fluid due to gravity. Any fluid turbulence that causes air bubbles or other artifacts can be detected from the photodetection data at the laser detector 204 and removed from the data during signal processing using appropriate algorithms.

[0050] Real-time online milk monitoring in a dairy farm provides a rather challenging environment, as the milk flowing through the milking line is discontinuous, often turbulent, contains bubbles, and the composition of the milk changes dynamically during the milking cycle, so the sensor needs to track the dynamics. For spectral milk composition measurement, the laser engine 202 emits spectrally tunable laser radiation of known intensity and wavelength distribution, which is transmitted through the milk flow in the channel 106 via an optical interface in the sheath 300 and collected by the laser detector 204 via a corresponding optical interface. The laser detector 204, which may be a photodetector, converts the received optical signal into an electrical signal and records the time domain signal (e.g., photovoltage or photocurrent). The signal may be processed into a usable absorption spectrum and may undergo further data processing to convert the spectral data into component concentration levels or milk composition.

[0051] In the example, the electrical signal from the laser detector 204 is first amplified by an amplifier, and the current signal is converted to a voltage. The amplified signal is then sent to an analog-to-digital converter (ADC) and digitized. The signal from the detector, amplifier, and ADC is a time domain signal—that is, an intensity function of time. This signal is then sent to a processing device (e.g., a central processing unit (CPU), a microcontroller unit (MCU), a field programmable gate array (FPGA), a complex programmable logic device (CPLD), or any combination of these devices or another one or more devices, which performs further signal processing, such as jitter correction, filtering, selection of valid spectra based on predefined rules, averaging, and finally time to wavelength / frequency conversion, and this signal is then sent to a data processing module via a data link (e.g., an Ethernet cable). The time to wavelength conversion requires that the absolute wavelength emitted by the laser radiation passing through the milk is always known, and this information comes from the laser engine 202 and is then used for the conversion.

[0052] Figure 5 It shows the IT hardware and software architecture that can be used. For example, Figure 5 The hardware architecture shown in can be used in a milk collection operation using an online sensor. Figure 5 elements.

[0053] Figure 6 A process 622 is shown to generate a unique animal milk composition record. Input is received via 6215 including data from spectral capture and other electronic optical sensors and used as live measurements 6220. This input 6215 may include data 6221 including temperature, flow rate, color, conductivity, and other physical measurements. This input 6215 may include spectral data 6222.

[0054] Process 622 also uses static model inputs 6230 and real-world measurements 6220 in model 6240. Static model inputs 6230 may include model reference parameters 6222 and reference data 6231, which may include water reference spectra, molecular reference spectra (such as for fat, lactose, protein, urea, etc.), sensor reference spectra, and component density data.

[0055] The model combines data 6220 and 6230 to create model output 6250. Model output 6250 may include component concentration levels from spectrum 6251 and other related parameters 6252 such as color (eg, for blood testing), somatic cell levels, and / or other diagnostic parameters.

[0056] Aggregation 6270 may use model output 6250, live parameters 6220, and farm data 6260 to create a unique animal milk composition record 6271 to be sent to local storage 624. Farm data 6260 may include data related to farm activities (or other operational activities for other types of operations), including milking times 6261, animal identifiers 6262, and data 6263 (such as historical health data and / or treatment data).

[0057] Figure 7 An example of a model 6240 for composition analysis is shown in more detail. In this example, the model 6240 operates to generate a model output 6250.

[0058] In step 6241, the laser intensity value as detected by the photodetector is converted to absorbance. Then, the system background is subtracted in step 6242. An example may be to have a system background spectrum provided from a static model. System background All optical features of the system (i.e., lasers, photodetectors, optics, mirrors, etc.) except the spectrum of the milk or other liquid flowing through the sensor.

[0059] System background subtraction 6242 is performed and the resulting spectrum is then primarily the spectrum of the fluid flowing through the spectrum. For example, milk, which is a substance of many different molecules (water, protein, fat, lactose, metabolites, and different analytes). The following steps are baseline calibration and water residual subtraction in step 6243. Water is the main baseline dominant, and therefore subtraction is important in order to reveal the other components of the fluid.

[0060] After performing baseline calibration and water residual subtraction 6243, the target component concentration is derived in step 6244 using, for example, a Beer-Lambert absorption model in a nonlinear regression framework. For higher accuracy, a reference spectrum for the component is provided from a library within the static model. The absorption spectrum changes with changes in concentration and temperature in terms of peak width, slope, etc. And the static model input minimizes the prediction error. Additional parameters or parameter ranges for the nonlinear model can be slope, path length, offset, detector background correction, dark current correction, etc. The output of step 6244 is already the quantitative concentration level of the target component or set of components. The value is sent to the model output 6250 and included in a single milking data set together with additional parameters from other sensors and 3rd party data.

[0061] FIG. 8A to FIG. 8D The generation of data from raw sensor data is shown. Sensor data is processed 621 using the raw sensor data as previously described. This processing 621 can generate spectral capture (e.g., time to frequency format), color sensor data, temperature, flow, and other parameters. Third party data 6260 (such as animal identifiers, milking start / stop times, and veterinary records) can be combined in data processing 622 using the model, which can include spectrum to composition determination and other physical parameters determination (such as flow, temperature, contamination, etc.).

[0062] Animal and herd data aggregation and calculations are performed 624. This can include aggregating data for individual animals (e.g., cows) and / or for herds of animals. Data can be aggregated across multiple farms. This can be used to provide health indicators for individual milkings, individual cows, farms, or groups of farms. Veterinary indicators, animal husbandry indicators, and economic indicators can also be created.

[0063] exist Fig. 8A In one example shown in , operations 621-624 are performed in a cloud computing architecture. Figure 8B In one example shown in , a raw spectrum buffer is used to buffer raw sensor data, with raw spectrum temporary storage and raw spectrum transmission. Figure 8C In one example shown in , operation 621 is performed on a local server (e.g., physically located on a farm), and operations 622 and 624 are performed in a cloud architecture. Fig.8D In one example shown in , operations 621 and 622 are performed on a local server, while operation 624 is performed in the cloud.

[0064] Fig. 9is a swim lane diagram of an example process for sensing a fluid. In the process, a processing unit receives readings from sensors (such as electrical property sensors, optical color sensors, and temperature flow sensors) and determines fluid parameters. The processing unit also generates spectra, including filtering, jitter correction, and time-frequency conversion. A local server performs data processing, including obtaining concentration levels and averaging the levels over milking cycles. This can produce aggregate parameters (e.g., for all cows on a farm) and individual milking records for individual milking sessions for individual cows.

[0065] Cloud data processing can include collecting individual milking records and aggregating individual milking records with historical data. Health, veterinary, breeding and economic models can be provided for individual level and herd level analysis.

[0066] Farm equipment can enforce actions / actuate valves or alarms based on optical color sensor and / or temperature sensor data and / or electrical property sensors. Software user interfaces can be used to show individual milking data, show data trends, and / or provide health / veterinary / economic / zootyping data and advice.

[0067] Fig.10 Data showing the absorption spectra of the emulsion for various transmission path distances measured between the optical interface and the laser detector are shown. Fig.10 Six spectral absorption signals at various light wavelengths for the transmission path between the optical interface and the photodetector are shown. From bottom line to top line, the absorption spectra for transmission paths of 0.2 mm, 0.4 mm, 0.66 mm, 0.82 mm, 1.11 mm and 1.63 mm are shown. Fig.10 Spectral data are shown for various path lengths (i.e., the gap between the optical housing interface and the laser detector) at fixed laser power. The peak-to-valley ratio of the spectrum is related to the measurement specificity, and the path length (gap size) should be selected to maximize the peak-to-valley ratio. If the optical interface (or Figure 4 If the gap between the sensor (the end of the sheath 300 in the sensor) and the laser detector 204 is too small, the absolute absorption of the milk fat is also small, resulting in a weakly modulated laser signal, as can be seen for gaps of 0.2 mm and 0.4 mm for a given laser power and spectral region. The milk spectrum data shows an optimum for a gap of 0.6 mm-1 mm, where the laser signal modulation by molecular absorption is highest. This can be seen from the peak-to-valley ratio of the two fat peaks. For larger gap widths, at a given laser output power, the absorption of water becomes dominant and the signal is lost. For different applications and different implementation configurations, the gap will vary from tens of microns to several millimeters, and in some cases, to centimeters or meters, depending on the laser output power used in the sensor and the optical properties of the fluid in the pipeline.

[0068] Fig.11 Example data 1100 that can be used to sense fluids and control automated devices is shown. In this example, the data is maintained in various data storage devices 1102-614 and can be accessed via a network 1116. In some cases, the data storage devices 1102-614 can be implemented in one or more computing elements (e.g., servers, virtual machines, desktop computers, handheld devices) and in one or more data structures (e.g., relational databases, files, data messages, memory entries) implemented in the one or more computing elements. The network 1116 can include an internal data bus, an external data network, etc.

[0069] Live laser detector parameters 1102 may include incoming data and historically stored data generated by laser detector 204. For example, laser detector 204 may generate analog data that is converted to digital data, conditioned (e.g., jitter removed or reduced, filtered, averaged, converted to aggregate values ​​or a smaller data format), and transmitted for storage over network 1116. Laser parameters 1102 may include time series data (including spectral values ​​and corresponding timestamp data) or another suitable format.

[0070] Live optical detector parameters 1104 may include incoming data and historically stored data generated by color sensor 208. For example, color sensor 208 may generate analog data that is converted to digital data, conditioned (e.g., jitter removed or reduced, filtered, averaged, converted to aggregate values ​​or smaller data formats), and transmitted for storage over network 1116. Optical parameters 1104 may include time series data (including light intensity values, color values, or other values ​​and corresponding timestamp data) or another suitable format.

[0071] Live contact sensor parameters 1106 may include incoming data and historically stored data generated by contact sensor set 206. For example, contact sensor set 206 may generate analog data that is converted to digital data, conditioned (e.g., jitter removed or reduced, filtered, averaged, converted to aggregate values ​​or smaller data formats), and transmitted for storage over network 1116. Contact parameters 1106 may include time series data (including temperature, conductivity values, flow rate, or other values ​​and corresponding time stamp data) or another suitable format.

[0072] Reference parameters 1108 for a fluid may include a library of reference values ​​for a particular fluid (e.g., milk) or for various fluids. For example, for a fluid with different components (e.g., milk), reference parameters 1108 may be stored for each component or possible contaminant (e.g., water, milk protein, lactose, urea, blood). For example, these reference parameters may be used when generating quantitative outputs (such as milk component concentration levels obtained from spectral measurements) that may be stored as fluid measurements 1110 and other related parameters (such as temperature, milk volume, milk conductivity, somatic cell count, blood content, etc.).

[0073] Fluid measurements 1110 may include individual measurements and aggregate measurements. For example, individual measurements may include measurements of the fluid at a specific point in time or within a small time window (e.g., less than half a second). Individual measurements may provide a "snapshot" of the fluid at a given moment. On the other hand, aggregate measurements may be created to capture the properties of the fluid over a longer period of time. For example, a single set of aggregate measurements 1110 may be present for a given animal's milking session. Aggregate measurements may be created by aggregating individual measurements. For example, hundreds or thousands of fluid measurements recording fat content in milk may be aggregated into an average fat content for a milking session. As will be appreciated, such aggregation may include all individual measurements within a certain time period, or may include a sub-sampling of all individual measurements. Using both individual measurements and aggregate measurements may provide many advantages. For example, the fat content of milk may be expected to change over the span of a milking session. The fat content at any particular point may have limited value, and therefore taking the average of individual fat content measurements when aggregating milking values ​​across a longer period of time (i.e., weeks, months) may provide more useful measurements for the operation of a dairy farm. This composition trend reveals valuable insights into individual animal health, lactation, nutrition, recovery (treatment efficacy), and allows early action on disease onset, nutritional changes, etc. In some examples, hundreds or thousands of individual measurements are created per second, and aggregating them into fewer aggregate measurements can allow for reasonable understandability. On the other hand, many automated systems can operate at hundreds or thousands of cycles per second, and having individual measurements in addition to aggregated measurements can allow for accurate and responsive control systems. In some cases, keeping hundreds or thousands of individual measurements per second can allow for precise pointing to the time when fluid changes are first noticed, which can help troubleshoot faulty systems (e.g., milking cups on cows are missing). Similarly, time series data of fluid measurements can be used to identify environmental conditions that affect fluid production. For example, light, sound, temperature, or other environmental sensors around cows being milked can be used to record changes in light, sound, temperature, or other environmental factors. These environmental factors can be compared with individual and / or aggregated to determine improved environmental conditions for milk production (e.g., modifying light to emulate daylight intensity, reducing sudden sounds, increasing heat with heaters).

[0074] Fluid system data 1112 may include information collected or generated for the operation of a fluid system (e.g., system 100). Data 1112 may include computer-readable instructions for various components of the fluid system, which may be compiled or used to drive an automated device (e.g., valve 108). Additionally, a record of historical operations (e.g., information regarding milk collection, including the amount, the timeline of collection, the operation of valve 108, and the amount currently in collection tank 110) may be stored in data 1112.

[0075] Animal data 1114 can record information about animals (e.g., cows 102) used in the fluid system. This animal data 1114 can record individual animal information (e.g., indexed by a unique identifier associated with each animal) as well as aggregated information about animal herds (such as historical health data, lactation data, treatment data, etc.). Animal data 1114 can also be used to provide herd management professionals with timely alerts about health problems that exist in individual animals before possible health problems spread within the herd. In the case where the onset of the disease is diagnosed early enough to be able to be treated with lower cost and lower downtime alternatives, timely health management ensures minimal downtime for the animal and minimal use of "powerful" agents (such as antibiotics), thereby maximizing the output of individual animals and herds. In addition, animal data 1114 will provide insight into the efficacy of treatments, and when treating specific health problems, it can be used as a reference for establishing a "standard operating procedure" by selecting the agent and / or procedure that provides the highest efficacy based on historical herd and / or farm data.

[0076] Animal data 1114 recording information related to milk production, content and properties of individual animals can be used in other aspects of herd management and breeding. Knowing the milk composition data of each herd animal is a very valuable asset for controlled herd breeding, where only herd members that aggregate desirable traits in the milking data will be used for herd breeding. For example, an animal that provides a lower annual milk volume but has a higher amount of fat and protein in its milk may be more valuable than another herd member in the herd that provides a higher amount of milk per year, because in some countries there is an overpayment for excess fat and protein.

[0077] Animal data 1114 can be reported and displayed in various interfaces and on various client devices, as described herein. Information can be formatted or filtered in each interface in the program for storing and visualizing information for specific purposes, such as: a farmer interface that focuses more deeply on herd productivity, farm profitability, etc.; a veterinary interface that focuses more on individual animal health status, treatment efficacy, historical data, etc.; and an animal husbandry interface that focuses on herd selection, allowing farmers to determine favorable traits and select appropriate individual animals for herd selection to enhance desired traits, such as high fat and / or protein content, or disease resistance or milk volume, etc. These interfaces can be interconnected and allow in-depth monitoring from individual animals to herds to multiple farms, and apply best practices in treatment, selection, nutrition, etc. based on actual data. Configuration and management serves as an administrator console for monitoring and configuring remote farm servers, sensors, and the entire Internet of Things ("IoT") infrastructure on the farm.

[0078] Fig.12 A swim-lane diagram of an example process 1200 for sensing fluid that may be used in a milk collection system is shown. Process 1200 may be performed by, for example, system 100, and thus will be described with reference to elements of system 100. However, process 1200 or another similar process may be performed using another system or systems.

[0079] The laser detector 204 generates a laser reading 1202. For example, the laser detector 204 receives the laser radiation after it has passed through the fluid and generates a corresponding laser reading. As such, as the laser radiation passes through the fluid, various properties of the fluid will affect the laser radiation, which will therefore be recorded by the laser reading in the computer readable data. Specifically, the laser signal will be modulated by absorption by specific molecules of the milk components as it passes through the flow. The modulation is later recovered and converted to quantitative component concentration levels through signal processing and data models.

[0080] The contact sensor set 206 senses contact phenomena, which may include electrical phenomena and temperature phenomena 704. For example, the contact sensor set 206 may sense one or more contact phenomena of the fluid to create corresponding contact readings, such that the determination 1212 of one or more fluid measurements may further include using the contact readings. As such, various properties of the fluid will affect the sensing elements of the contact sensors (e.g., a semiconductor thermistor will strongly change resistance depending on temperature), which will therefore be recorded by the contact readings in the computer-readable data.

[0081] The color sensor 208 generates an incoherent reading 1206. For example, the color sensor 208 can generate corresponding incoherent readings such that determining one or more fluid measurements further includes using the incoherent readings. As such, various properties of the fluid will affect the sensing element of the color sensor (e.g., based on color, intensity, or other optical properties), which will therefore be recorded in the incoherent readings in the computer-readable data, an example of a color sensor being, for example, a standard commercial RGB color sensor such as, but not limited to, the S9706 from Hamamatsu or the AS73211 from AMS AG, etc.

[0082] The processor 212 receives the readings 1208. For example, the processor 212 may access the laser readings, the contact readings, and / or the incoherent readings. The processor 212 identifies the spectral data 1210. For example, the spectral data may be identified as reflecting physical properties of the fluid as it flows through the sensing system.

[0083] The processor 212 determines the fluid measurement 1212. For example, using the spectral data and the reference data defining one or more reference spectra for each possible component of the fluid, the processor 212 can determine the individual values ​​of the fluid measurement. For example, the processor 212 can access a spectral library, such as, for example, a temperature-dependent reference spectrum of water and components, which can be stored as part of the firmware of the sensor. The library can also contain a system background spectrum, a set of fitting parameters, a parameter fitting range, etc. In some implementations, the parameter set contained in the library includes one or more of the path length, offset, slope, and dark current correction associated with the online sensor set in the milking system for interpreting the collected data. During field operation, when the milking is being flushed with water for cleaning, the static model can be updated and corrected for the system background spectrum and the water reference spectrum. This allows timely correction of any drift from the original library data and provides higher measurement accuracy. This data is used by the model to process the real-time measurement data. Here, the collected spectral data undergoes preprocessing, and data in the form of intensity as a function of wavelength or frequency is provided for further processing until the output can provide an estimated concentration level value. In the example processing operation, the collected spectral data intensity is first converted into absorbance, and then the system background is deducted. Here, the system background spectrum is fed from the static model. This allows the nonlinearity and spectrum artifacts related to the system to be decoupled from milk (or in a broader sense, with the research object). Once the system background is deducted, the next operation is baseline calibration and the main baseline dominant residual deduction. In the case of milk, the main baseline is dominated by water. The water reference spectrum is fed from the static model, and the residual is fitted and deducted for the best fit. Finally, in some embodiments, the Beer-Lambert model processing spectrum under the nonlinear regression framework is used. In some implementations, other regression models are used in data processing. Here, the static model provides a reference spectrum of the investigation component (such as milk fat, lactose, protein, water, etc.), combined with a set of model configuration parameters (such as the range of offset, slope, path length, etc.), and the parameters are used together with the reference spectrum data to provide the best fit and restore the estimated concentration level of the component, and then the estimated concentration level is sent to the model output.

[0084] The controllable device 108 actuates 1214. For example, the controllable device 108 may include an automated valve configured to selectively direct fluid flow to a plurality of output channels. The automated valve may be actuated using computer readable instructions based on at least one of the fluid measurements.

[0085] In some cases, the automatic valve is engaged in response to determining that the fluid measurement for contamination is greater than a threshold value to direct the fluid to a waste bin. For example, the threshold value can be set so that very low values ​​of contamination (which are more likely to be the result of noise in the sensing system than actual contamination) will not result in actuation. In some cases, actuating the automatic valve based on at least one of the fluid measurements includes actuating the automatic valve to direct the fluid to a waste bin before the contaminated fluid reaches the automatic valve.

[0086] Additionally or alternatively, the automatic valve may be used to sort milk by desired composition (rather than or in addition to contamination). Monitoring milk composition allows milk to be sorted by desired composition, e.g. high fat, high protein content, since in most countries excess in milk fat, protein and / or lactose is subject to a premium, thus allowing the farm to maximise commercial profits.

[0087] Fig.13 A flow chart of an example process 1300 for diverting contaminated fluid away from a holding tank and into a waste tank is shown. The process 1300 can be used to actuate 714 a controllable device 108, for example.

[0088] Milk properties are sensed 1302. For example, contamination levels may be determined, fat content may be determined, or other suitable parameters may be determined as previously described.

[0089] If the properties are within specification, the switch 1304 is engaged to direct the milk to a holding tank. For example, the valve 108 may be placed in a first position to direct the milk to a collection tank 110.

[0090] If the property does not meet the specification (e.g., too much contamination, too little milk protein, inappropriate temperature), the same switch 1306 is engaged to direct the milk to a waste bin. For example, the valve 108 can be placed in a second position to direct the milk to a waste bin 112.

[0091] When the milk does not meet specifications, an alarm may be generated 1308. The alarm may include a physical event, such as a computer-controlled light turning on, an audible alarm playing, etc. The alarm may include a data message sent over a network or stored in a memory, such as a push notification on an application, an email sent, etc.

[0092] Fig.14An example of a computing device 1400 and an example of a mobile computing device that can be used to implement the techniques described herein are shown. Computing device 1400 is intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Mobile computing devices are intended to represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, and other similar computing devices. The components shown here, their connections and relationships, and their functions are intended to be exemplary only and are not meant to limit the implementation of the inventions described and / or claimed in this document.

[0093] The computing device 1400 includes a processor 1402, a memory 1404, a storage device 1406, a high-speed interface 1408 connected to the memory 1404 and a plurality of high-speed expansion ports 1410, and a low-speed interface 1412 connected to a low-speed expansion port 1414 and the storage device 1406. Each of the processor 1402, the memory 1404, the storage device 1406, the high-speed interface 1408, the high-speed expansion port 1410, and the low-speed interface 1412 is interconnected using various buses and can be mounted on a common motherboard or otherwise installed where appropriate. The processor 1402 can process instructions for execution within the computing device 1400, including instructions stored in the memory 1404 or on the storage device 1406, to display graphical information for a graphical user interface (GUI) on an external input / output device (such as a display 1416 coupled to the high-speed interface 1408). In other implementations, multiple processors and / or multiple buses can be used with multiple memories and multiple types of memories where appropriate. Furthermore, multiple computing devices may be connected, with each device providing portions of the necessary operations (eg, as a server bank, a group of blade servers, or a multi-processor system).

[0094] The memory 1404 stores information within the computing device 1400. In some implementations, the memory 1404 is one or more volatile memory units. In some implementations, the memory 1404 is one or more non-volatile memory units. The memory 1404 may also be another form of computer-readable medium, such as a magnetic disk or optical disk.

[0095] Storage device 1406 can provide mass storage for computing device 1400. In some implementations, storage device 1406 can be or include a computer-readable medium, such as a floppy disk device, a hard disk device, an optical disk device, or a magnetic tape device, a flash memory or other similar solid-state memory device, or an array of devices (including devices in a storage area network or other configuration). A computer program product can be tangibly embodied in an information carrier. A computer program product can also include instructions that, when executed, perform one or more methods, such as those described above. A computer program product can also be tangibly embodied in a computer-readable medium or machine-readable medium, such as memory 1404, storage device 1406, or memory on processor 1402.

[0096] The high-speed interface 1408 manages bandwidth-intensive operations for the computing device 1400, while the low-speed interface 1412 manages less bandwidth-intensive operations. This allocation of functions is exemplary only. In some implementations, the high-speed interface 1408 is coupled to the memory 1404, the display 1416 (e.g., through a graphics processor or accelerator), and to a high-speed expansion port 1410 that can accept various expansion cards (not shown). In an implementation, the low-speed interface 1412 is coupled to the storage device 1406 and the low-speed expansion port 1414. The low-speed expansion port 1414, which can include various communication ports (e.g., USB, Bluetooth, Ethernet, wireless Ethernet), can be coupled to one or more input / output devices, such as a keyboard, a pointing device, a scanner, or, for example, through a network adapter to a networking device such as a switch or a router.

[0097] As shown in the figures, computing device 1400 can be implemented in a variety of different forms. For example, the computing device can be implemented as a standard server 1420, or multiple times in a group of such servers. In addition, the computing device can be implemented in a personal computer such as a laptop computer 1422. The computing device can also be implemented as part of a rack server system 1424. Alternatively, components from computing device 1400 can be combined with other components in a mobile device (not shown), such as mobile computing device 1450. Each of such devices can contain one or more of computing device 1400 and mobile computing device 1450, and the entire system can be composed of multiple computing devices that communicate with each other.

[0098] The mobile computing device 1450 includes a processor 1452, a memory 1464, and other components such as an input / output device such as a display 1454, a communication interface 1466, and a transceiver 1468. The mobile computing device 1450 may also be provided with a storage device such as a micro drive or other device to provide additional storage. Each of the processor 1452, the memory 1464, the display 1454, the communication interface 1466, and the transceiver 1468 are interconnected using various buses, and several components may be mounted on a common motherboard or otherwise installed where appropriate.

[0099] The processor 1452 may execute instructions within the mobile computing device 1450, including instructions stored in the memory 1464. The processor 1452 may be implemented as a chipset including separate multiple analog processors and digital processors. The processor 1452 may provide, for example, coordination for other components of the mobile computing device 1450, such as control of a user interface, applications executed by the mobile computing device 1450, and wireless communications performed by the mobile computing device 1450.

[0100] The processor 1452 can communicate with the user through the control interface 1458 and the display interface 1456 coupled to the display 1454. The display 1454 can be, for example, a TFT (thin film transistor liquid crystal display) display or an OLED (organic light emitting diode) display, or other appropriate display technology. The display interface 1456 may include appropriate circuit systems for driving the display 1454 to present graphical information and other information to the user. The control interface 1458 can receive commands from the user and convert them to submit to the processor 1452. In addition, the external interface 1462 can provide communication with the processor 1452 so that the mobile computing device 1450 can communicate with other devices in a near area. The external interface 1462 can be provided for wired communication in some implementations, or for wireless communication in other implementations, and multiple interfaces can also be used.

[0101] The memory 1464 stores information within the mobile computing device 1450. The memory 1464 may be implemented as one or more of one or more computer-readable media, one or more volatile memory units, or one or more non-volatile memory units. An expansion memory 1474 may also be provided and connected to the mobile computing device 1450 via an expansion interface 1472, which may include, for example, a SIMM (single in-line memory module) card interface. The expansion memory 1474 may provide additional storage space for the mobile computing device 1450, or may also store applications or other information for the mobile computing device 1450. Specifically, the expansion memory 1474 may include instructions to perform or supplement the above-mentioned processes, and may also include security information. Thus, for example, the expansion memory 1474 may be provided as a security module for the mobile computing device 1450, and may be programmed with instructions that permit secure use of the mobile computing device 1450. In addition, a security application may be provided via a SIMM card along with additional information, such as placing identification information on the SIMM card in an unbreakable manner.

[0102] The memory may include, for example, flash memory and / or NVRAM memory (non-volatile random access memory), as discussed below. In some implementations, a computer program product is tangibly embodied in an information carrier. The computer program product contains instructions that, when executed, perform one or more methods, such as those described above. The computer program product may be a computer-readable medium or a machine-readable medium, such as the memory 1464, the expansion memory 1474, or a memory on the processor 1452. In some implementations, the computer program product may be received in a propagated signal, for example, by the transceiver 1468 or the external interface 1462.

[0103] The mobile computing device 1450 can communicate wirelessly through the communication interface 1466, which may include a digital signal processing circuit system if necessary. The communication interface 1466 can provide for communication under various modes or protocols, such as GSM (Global System for Mobile Communications) voice calls, SMS (Short Message Service), EMS (Enhanced Message Service) or MMS (Multimedia Message Service) message transmission, CDMA (Code Division Multiple Access), TDMA (Time Division Multiple Access), PDC (Personal Digital Cellular), WCDMA (Wideband Code Division Multiple Access), CDMA2000, or GPRS (General Packet Radio Service), etc. Such communication can occur, for example, using radio frequencies through the transceiver 1468. In addition, short-range communication can be performed such as using Bluetooth, WiFi or other such transceivers (not shown). In addition, the GPS (Global Positioning System) receiver module 1470 can provide additional navigation-related and location-related wireless data to the mobile computing device 1450, which can be used by applications running on the mobile computing device 1450 where appropriate.

[0104] The mobile computing device 1450 may also communicate audibly using an audio codec 1460, which may receive verbal information from a user and convert it into usable digital information. The audio codec 1460 may also generate audible sounds for the user, such as through a speaker (e.g., in an earpiece of the mobile computing device 1450). Such sounds may include sounds from voice phone calls, may include recorded sounds (e.g., voice messages, music files, etc.), and may also include sounds generated by applications operating on the mobile computing device 1450.

[0105] As shown in the figures, the mobile computing device 1450 can be implemented in a variety of different forms. For example, the mobile computing device can be implemented as a cellular phone 1480. The mobile computing device can also be implemented as part of a smart phone 1482, a personal digital assistant, or other similar mobile devices.

[0106] Various implementations of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, specially designed ASICs (application specific integrated circuits), computer hardware, firmware, software, and / or combinations thereof. These different implementations may include implementations in one or more computer programs executable and / or interpretable on a programmable system, the programmable system including at least one programmable processor, which may be special purpose or general purpose, coupled to receive data and instructions from and transmit data and instructions to a storage system, at least one input device, and at least one output device.

[0107] These computer programs (also referred to as programs, software, software applications, or code) include machine instructions for a programmable processor and may be implemented in a high-level procedural programming language and / or an object-oriented programming language, and / or in assembly / machine language. As used herein, the terms machine-readable medium and computer-readable medium refer to any computer program product, device, and / or apparatus (e.g., a disk, an optical disk, a memory, a programmable logic device (PLD)) for providing machine instructions and / or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term machine-readable signal refers to any signal for providing machine instructions and / or data to a programmable processor.

[0108] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user, and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, audible feedback, or tactile feedback); and input from the user can be received in any form, including acoustic input, voice input, or tactile input.

[0109] The systems and techniques described herein can be implemented in a computing system that includes a back-end component (e.g., as a data server) or includes a middleware component (e.g., an application server) or includes a front-end component (e.g., a client computer with a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described herein), or any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any digital data communication form or medium (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0110] A computing system may include clients and servers. Clients and servers are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.

Claims

1. A sensing system for sensing a physical property of a fluid, the system comprising: a laser engine configured to emit spectrally tunable laser radiation through the fluid as the fluid flows through the sensing system; a laser detector configured to receive the laser radiation after the laser radiation has passed through the fluid and generate a corresponding laser reading; one or more processors; a computer memory storing computer readable instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising: receiving a laser reading from said laser detector from said laser detector; identifying, from the laser readings, spectral data reflective of a physical property of the fluid as it flows through the sensing system; and One or more fluid measurements for corresponding one or more components of the fluid are determined using the spectral data and reference data defining one or more reference spectra for each possible component of the fluid.

2. The system according to claim 1, wherein: The system further includes a housing that houses the laser engine, the laser detector, and one or more processors, and the computer memory.

3. The system according to claim 2, wherein: The system further includes a network interface, and wherein the operations further include transmitting the one or more fluid measurements via the network interface.

4. The system according to claim 1, wherein: The system further comprises: a housing that houses the laser engine and the laser detector; and One or more computing devices, the one or more computing devices comprising the one or more processors and the computer memory.

5. The system according to claim 1, wherein: The system further includes a fluid channel through which the fluid flows between the laser engine and the laser detector, and wherein the laser engine and the laser detector are at least partially fixedly held in the fluid channel such that a portion of the fluid flows between the laser engine and the laser detector.

6. The system according to claim 5, wherein: The system further comprises: a contact sensor at least partially fixedly retained in the fluid passage; an optical emitter at least partially fixedly retained in the fluid passage; and A color sensor is at least partially fixedly held in the fluid channel.

7. The system according to claim 5, wherein: The laser engine and the laser detector are fixedly maintained apart by a distance less than 10 mm.

8. The system according to claim 5, wherein: The laser engine is coupled to a photon-permeable sheath configured to prevent contact with the laser engine by the fluid.

9. The system according to claim 1, wherein: The system further includes a contact sensor configured to: contacting the fluid as the fluid flows through the sensing system; sensing one or more contact phenomena of the fluid to create corresponding contact readings; and Wherein determining one or more fluid measurements further comprises using the contact readings.

10. The system according to claim 1, wherein: The system further comprises: an optical transmitter configured to emit incoherent light; and a color sensor configured to receive the incoherent light after the incoherent light has passed through the fluid and generate a corresponding incoherent reading; and Wherein determining one or more fluid measurements further comprises using the incoherent readings.

11. The system according to claim 1, wherein: The system further includes an automatic valve configured to selectively direct the flow of the fluid to a plurality of output channels; And wherein the operation includes actuating the automatic valve based on at least one of the fluid measurements.

12. The system according to claim 11, wherein: Actuating the automatic valve includes engaging the automatic valve to direct the fluid to a waste bin in response to determining that the fluid measurement for contaminants is greater than a threshold value.

13. The system according to claim 12, wherein: Actuating the automatic valve based on at least one of the fluid measurements includes actuating the automatic valve to direct contaminated fluid to the waste bin before the fluid reaches the automatic valve.

14. The system of claim 1, wherein: The fluid is raw milk collected from livestock.

15. The system of claim 1, wherein: The laser engine includes a III-V semiconductor based laser.

16. The system of claim 15, wherein: The III-V semiconductor based laser is configured to emit light through an optical interface, and wherein the laser detector is positioned opposite the optical interface.

17. The system of claim 15, wherein: The III-V semiconductor based laser is a tunable laser.

18. The system of claim 15, wherein: The III-V semiconductor based laser is configured to emit a spectrum of wavelengths of light through an optical interface.

19. The system of claim 18, wherein: The laser engine includes a III-V / IV semiconductor based laser.

20. The system of claim 19, wherein: The III-V / IV semiconductor based laser is configured to emit through an optical interface, and wherein the laser detector is positioned opposite the optical interface.

21. The system of claim 20, wherein: The III-V / IV semiconductor based laser is a tunable laser.

22. The system of claim 21, wherein: The III-V / IV semiconductor based laser is configured to emit a spectrum of wavelengths of light through the optical interface.

23. The system of claim 21, wherein: The optical interface is positioned in a flow path of the fluid flowing through the sensing system.

24. The system of claim 19, wherein: The optical interface comprises a tube extending from the laser engine into a channel through which the fluid flows through the sensing system, the tube extending toward the laser detector, wherein the distance from the distal end of the glass tube to the surface of the laser detector is between 0.5 mm and 10 mm, and the tube comprises an optically transparent portion.

25. The system of claim 1, wherein: The fluid measurements are individual measurements of components at a specific time, and the operations further include: The fluid measurements for a single milking session are aggregated into an aggregate value that reflects the variation in the fluid measurements through the milking session.

26. The system of claim 1, wherein: The operations further include: Fluid measurements for a single milking session are stored, indexed for an individual animal by a unique identifier for the single milking session.

27. The system of claim 26, wherein: The operations further include: Fluid measurements for a single milking session are stored together with other fluid measurements from other milking sessions to generate historical data for a particular animal.

28. The system of claim 27, wherein: The operations further include: Historical data for each animal in the herd is used to generate herd level metrics for multiple animals.

29. The system of claim 28, wherein: The operations further include: The herd level indicator is matched to third party data to at least one of the group consisting of: 1) herd health data; 2) herd selection data; and 3) herd management data.

30. The system of claim 29, wherein: The generation of individual or herd level indicators involves the use of third party data and historical data for each animal in the herd.

31. The system of claim 1, wherein: The physical properties of the fluid include fluid composition, electrical properties, temperature, flow rate, color, quantitative component concentration levels, presence or absence of one or more components.

Images