WO2019103626A1

WO2019103626A1 - A device and method for associating sensor information with a milking position

Info

Publication number: WO2019103626A1
Application number: PCT/NZ2018/050163
Authority: WO
Inventors: John-Gerard Robert VAN BEEK
Original assignee: Lic Automation Limited
Priority date: 2017-11-22
Filing date: 2018-11-20
Publication date: 2019-05-31
Also published as: EP3713396A1

Abstract

Systems, devices, and methods for use in a milking facility having a plurality of milking clusters, each configured to be connected to a milking animal to extract milk therefrom, are described herein. The system includes at least one orientation detection device positioned on one of the milking clusters, the orientation detection device including at least one orientation sensor configured to output orientation data. The orientation detection device includes at least one processor configured to receive the orientation data, determine a current orientation of the milking cluster using the orientation data, and output a signal indicative of the current orientation. The system includes at least one processor configured to receive the signal from the orientation detection device indicative of the current orientation of the milking cluster, and determine a milking position associated with the milking cluster based on the current orientation.

Description

A DEVICE AND METHOD FOR ASSOCIATING SENSOR INFORMATION WITH A MILKING POSITION

STATEMENT OF CORRESPONDING APPLICATIONS

This application is based on the provisional specification filed in relation to New Zealand Patent Application No. 737594, the entire contents of which are incorporated herein by reference.

TECHNICAL FIELD

The present disclosure relates to a device and method for associating sensor information with a milking position in a milking shed - more particularly by determining the orientation of a component of a milking cluster and determining the milking position at which cups of the milking cluster have been applied to an animal.

BACKGROUND ART

In known milking facility configurations, a plurality of milking clusters are provided for the collection of milk from milking animals. The use of sensors to obtain information relating to milk collected from one or more of the individual milking clusters, and associating that information with individual animals from which the milk was collected, is well known. Such information is used in decision making regarding such matters as culling, breeding, medical treatment, animal specific feed rations as well as measurement of milk production efficiency. It should be appreciated that while reference will herein be made to a milking animal being a dairy cow this is not intended to be limiting, and the various embodiments of the present disclosure may be used in the milking of other animals, for example: sheep, goats, donkeys, dromedaries, yaks, fillies, buffalo, horses and similar.

Numerous systems are known for the identification ("ID") of individual animals and association of that ID with a milking position in order to attribute collected sensor data to that animal. However, in some milking facility configurations a milking cluster may be applied to a range of milking positions - i.e. there is not a one to one relationship between the milking cluster and a milking position within the facility. For example, a milking cluster may be intended to be swung between opposing rows. Further, the milking cluster may be capable of reaching forwards or backwards along the length of a row to be applied to more than one milking position along that row. Without determination of the milking position to which a milking cluster is applied, and therefore the animal at that milking position, errors may be introduced to an individual animal's data records by mistakenly attributing sensor data from another animal.

It is an object of the present invention to address the foregoing problems or at least to provide the public with a useful choice.

All references, including any patents or patent applications cited in this specification are hereby incorporated by reference. No admission is made that any reference constitutes prior art. The discussion of the references states what their authors assert, and the applicants reserve the right to challenge the accuracy and pertinency of the cited documents. It will be clearly understood that, although a number of prior art publications are referred to herein, this reference does not constitute an admission that any of these documents form part of the common general knowledge in the art, in New Zealand or in any other country.

Unless the context clearly requires otherwise, throughout the description and the claims, the words "comprise", "comprising", and the like, are to be construed in an inclusive sense as opposed to an exclusive or exhaustive sense, that is to say, in the sense of "including, but not limited to".

Further aspects and advantages of the present invention will become apparent from the ensuing description which is given by way of example only.

SUMMARY

According to one aspect of the disclosure there is provided a system for use in a milking facility having a plurality of milking clusters, each configured to be connected to a milking animal to extract milk therefrom, the system including: at least one performance sensor associated with one of the milking clusters, and configured to output data relating to a characteristic of milk extracted by the milking cluster; at least one orientation detection device positioned on the milking cluster with which the performance sensor is associated, the orientation detection device including: an accelerometer device configured to output acceleration data; a magnetometer device configured to output magnetic field data; at least one processor configured to: receive the acceleration data and the magnetic field data; determine, using the acceleration data and the magnetic field data, a current orientation of the milking cluster; and output a signal indicative of the current orientation; at least one processor configured to: receive the data from the performance sensor; receive the signal from the orientation detection device indicative of the current orientation of the milking cluster; determine a milking position associated with the milking cluster based on the current orientation; and associate the data from the performance sensor with an identifier of an animal associated with the milking position at the time of collecting the data relating to the characteristic of milk.

According to one aspect of the disclosure there is provided a method for associating an animal identifier with data relating to the characteristic of milk output from a performance sensor associated with one of a plurality of milking clusters in a milking facility, the method including: receiving acceleration data from an accelerometer device, and magnetic field data from a magnetometer device positioned on the milking cluster with which the performance sensor is associated; determining, using the acceleration data and the magnetic field data, a current orientation of the milking cluster; and determining a milking position associated with the milking cluster based on the current orientation; and associating the data from the performance sensor with an identifier of an animal associated with the milking position at the time of collecting the data relating to the characteristic of milk. According to an aspect of the present disclosure there is provided an orientation detection device configured to be positioned on a milking cluster of a milking facility, the orientation detection device including: an accelerometer device configured to output acceleration data; a magnetometer device configured to output magnetic field data; at least one processor configured to: receive the acceleration data and the magnetic field data; determine, using the acceleration data and the magnetic field data, a current orientation of the milking cluster; and output a signal indicative of the current orientation.

According to an aspect of the present disclosure there is provided a method for determining an orientation of one of a plurality of milking clusters of a milking facility, the method including: positioning an accelerometer device and magnetometer device on the milking cluster; receiving acceleration data from the accelerometer device, and magnetic field data from the magnetometer device; determining, using the acceleration data and the magnetic field data, a current orientation of the milking cluster.

According to one aspect of the disclosure there is provided a system for use in a milking facility having a plurality of milking clusters, each configured to be connected to a milking animal to extract milk therefrom, the system including: at least one orientation detection device positioned on one of the milking clusters, the orientation detection device including: at least one orientation sensor configured to output orientation data; at least one processor configured to: receive the orientation data; determine, using the orientation data, a current orientation of the milking cluster; and output a signal indicative of the current orientation; at least one processor configured to: receive the data from the performance sensor; receive the signal from the orientation detection device indicative of the current orientation of the milking cluster; determine a milking position associated with the milking cluster based on the current orientation.

According to one aspect of the disclosure there is provided a method for determining a milking position associated with one of a plurality of milking clusters in a milking facility, the method including: receiving orientation data from at least one orientation sensor positioned on the milking cluster; determining, using the orientation data, a current orientation of the milking cluster; and determining a milking position associated with the milking cluster based on the current orientation. According to an aspect of the present disclosure there is provided an orientation detection device configured to be positioned on a milking cluster of a milking facility, the orientation detection device including: at least one orientation sensor configured to output orientation data; at least one processor configured to: receive the orientation data; determine, using the orientation data, a current orientation of the milking cluster; and output a signal indicative of the current orientation.

According to an aspect of the present disclosure there is provided a method for determining an orientation of one of a plurality of milking clusters of a milking facility, the method including: positioning at least one orientation sensor on the milking cluster; receiving orientation data from the at least one orientation sensor; determining, using the orientation data, a current orientation of the milking cluster.

Milking clusters are well known in the art for use in the extraction of milk from milking animals. Each milking cluster typically includes a plurality of teatcups to be applied to the teats of the animal. The teatcups are pulsated by a varying vacuum to draw milk through a "long milk tube" for delivery to a storage tank or vat - often via a common milk line which is shared by the milking clusters.

In exemplary embodiments, the milking cluster may include a dropper, and the orientation detection device may be positioned on the dropper. Reference to a dropper should be understood to mean a rigid component between the connection to the milk line and the claw - more particularly being part of the long milk tube. It is envisaged that the rigid nature of the dropper may assist with ease of installation of the orientation detection device, and determination of the orientation. However, the inventors contemplate mounting the orientation detection device to other components of the milking cluster, more particularly any component that moves during a change in position of the teatcups. By way of example, this may include a flexible portion of the long milk tube, a swing arm, a cup remover, a vacuum line, or attachments such as information displays or warning lights.

The present disclosure has particular application to milking facility configurations in which a single milking cluster has the potential to be shared between more than one potential milking position within the facility. For example, in a swing-over herringbone configuration, two rows of standing positions are located to either side of a central pit. Milking clusters are typically suspended from an overhead position, from which the teatcups may be applied to an animal in either row - i.e. from side to side - and potentially reaching different positions along the row. It should be appreciated that reference to a swing-over herringbone configuration is not intended to be limiting to all exemplary embodiments of the present disclosure, as other configurations in which milking clusters may be shared between animals are known in the art.

Reference to a milking position should be understood to mean the position of an animal within a milking facility at which milk is extracted from that animal using a milk cluster. In some milking facility configurations, the milking positions of animals are prescribed within the facility by barriers. For example, in a rotary shed configuration, each milking position is typically delineated by physical barriers. In such cases, the milking position may be defined as a fixed position within the milking facility. Similarly, while some configurations may not include physical barriers between animals, an assumption may be made that there is a high likelihood of a one to one relationship between animals and known positions within the facility - for example a herringbone configuration having zig-zag rump rails.

However, in other configurations, the milking position may not be fixed. For example, animals may enter a row of standing positions - with the exact positioning of an animal influenced by factors such as the sizes of animals in the row, number of animals entering the row, or animal temperament. In such configurations, the milking position determined to be associated with a milking cluster may be a relative one - although it should be appreciated that a one to one relationship between animal order and milking position may be assumed in exemplary embodiments. For example, where the total number of animals in a row is known, this may be used in conjunction with the orientation of the milking cluster to infer a likely milking position in terms of the position count of an animal within the sequence. In an exemplary embodiment, the animal's relative position may be determined by an animal identification system, and used in conjunction with the orientation of the milking cluster to infer a likely milking position. Further, in exemplary embodiments the orientation of a milking cluster relative to one or more other milking clusters may be used to determine the milking position.

Reference to orientation of the milking cluster or the orientation detection device should be understood to mean the relative position within a spatial frame of reference - more particularly the milking facility. While the desired characteristic of orientation may depend on the milking facility configuration, orientation of the milking cluster will be discussed herein in terms of imaginary rotations within a frame of reference provided by the milking facility.

Reference may herein be made to tilting of the milking cluster in a direction along the length of a milking facility as the "pitch", while tilting in a lateral direction (i.e. side to side) may be referred to as the "roll". For example, in a milking shed configuration having first and second rows of milking positions, with milking clusters positioned between the rows (such as in a herringbone swing-over configuration), tilting of a milking cluster along the rows may be referred to as the pitch, while tilting towards the rows may be referred to as the roll.

In an exemplary embodiment, determination of the current orientation may include determining the roll of the orientation detection device. In an exemplary embodiment, determination of the current orientation may include determining a side of the milking facility towards which the milking cluster is inclined. In an exemplary embodiment, determination of the current orientation may include determining an extent to which the milking cluster is inclined towards the side of the milking facility.

In an exemplary embodiment, determination of the current orientation may include determining the pitch of the orientation detection device. In an exemplary embodiment, determination of the current orientation may include determining a direction along the length of the milking facility towards which the milking cluster is inclined. In an exemplary embodiment, determination of the current orientation may include determining an extent to which the milking cluster is inclined in the direction along the length of the milking facility.

It should be appreciated that in exemplary embodiments determination of milking position may only use one characteristic of the orientation of the milking cluster. For example, only roll may be used to determine which side of the milking facility the milking cluster is oriented towards, while in another exemplary embodiment only pitch may be used to determine milking position along a row. In exemplary embodiments, both pitch and roll may be used to determine the milking position.

It should be appreciated that the orientation may be defined with respect to subcomponents of the milking cluster. For example, it is envisaged that the orientation may be expressed, or determined, in terms of angle of rotation of the dropper or long milk tube of the milking cluster in one or more directions. In an exemplary embodiment, the accelerometer device and magnetometer device may be provided in a single unit. For example, the accelerometer device and magnetometer device may be provided in an inertial measurement unit (IMU). In an exemplary embodiment, the IMU may also include a gyroscope device.

In an exemplary embodiment, the orientation sensor may be an inertial measurement unit (IMU). However, it is also envisaged that alternate sensor types may be used to obtain orientation data. For example, it is envisaged that orientation data may be provided by one or more tilt sensors (for example force balance sensors, solid state micro-electromechanical systems, fluid-filled sensors - for example electrolytic or capacitive tilt sensors). In exemplary embodiments, an electronic compass may be provided in addition to the one or more tilt sensors.

The determination of orientation, more particularly one or both of pitch and roll, of an accelerometer is well known. In an exemplary embodiment, the accelerometer device may be a three axis accelerometer, configured to output a signal indicative of the acceleration on each axis.

Milking clusters in many milking shed configurations are capable of being twisted about at least a portion of their length in use. Accordingly, pitch and roll determined from the accelerometer output only may have the potential to return a false determination of orientation - for example, a milk cluster twisted while being applied to a milking position on a right side of the milking facility may result in a determination of the milking position being on the left side.

While the present disclosure describes herein means for accommodating for such a twisting action, it is also envisaged that some milking facility configurations may be less susceptible to this. For example, configurations are known in which a rigid swing arm pivots between sides of the facility. In such a configuration, it is envisaged that the side of the facility may be reliably determined from the sensor output without compensation for the twisting action.

In an exemplary embodiment, the magnetometer device may be a three axis magnetometer, configured to output one or more signals indicative of the direction, strength, or relative change of a magnetic field - more particularly the Earth's magnetic north - in each axis. The magnetic field data may be used to determine the orientation of the magnetometer device (and therefore orientation detection device) relative to magnetic north. This may then be used to correct the frame of reference for a determination of one or both of pitch and roll from the acceleration data.

In an exemplary embodiment, the bearing of the orientation detection device may be determined, and compared with a reference bearing. In the context of a three axis system, reference to the bearing of the orientation detection device may be understood to be the yaw about the axis perpendicular to the pitch and roll axes - i.e. where the pitch and roll axes are on a substantially horizontal plane, yaw is rotation about a vertical axis.

It is envisaged that the reference bearing may be established while the milking cluster or orientation detection device is in a neutral position - i.e. not rotated from the position in which the milking cluster sits while not in use. For example, a calibration setting may be used to establish the reference bearing during installation of the orientation detection device. In an exemplary embodiment, an installer may position the orientation detection device such that the bearing in the neutral position is directed towards the exit of the milking facility.

In an exemplary embodiment, the relative angle between the determined bearing and the reference bearing may be used to transform the accelerometer data values to fit the frame of reference of the milking facility. These transformed values may then be used to determine the current pitch and roll values of the orientation detection device within the reference frame of the milking facility.

It should be appreciated that a range of techniques for statistical analysis may be applied to the pitch and/or roll values in determining the milking position. In an exemplary embodiment, determination of side of the milking facility towards which the milking cluster is inclined may include comparison of a roll value against one or more thresholds. By way of explanation, where a neutral position of the milking cluster is ascribed a zero roll value, positive and negative roll values may be used to determine an inclination of the milking cluster towards the left or right sides respectively. For example, a positive threshold may be provided - above which the milking cluster is determined to be inclined towards a first side - and a negative threshold, below which the milking cluster is determined to be inclined towards the other side.

In exemplary embodiments, the pitch of individual milking clusters may be used to distinguish between different conditions of use of the milking clusters in order to assist with determining the milking position.

In an exemplary embodiment, a "normal condition" may be considered as a scenario in which sequential milking clusters are applied to sequential milking animals. In such a condition, it is anticipated that the pitch for adjacent or nearby milking clusters will be similar, indicating that performance sensor data associated with each of the milking clusters may be attributed to the milking animals in sequential order. It should be appreciated that some variation in pitch is expected along the entirety of a row, for example due to spacing between animals not being equal to the cluster spacing. As such, it is anticipated that detection of abnormal conditions may be increased by a comparison of the pitch of adjacent or nearby milking clusters. In an exemplary embodiment, a "crossed cups" condition may occur where a first milking cluster and second milking cluster are intended to be applied to a first milking animal and a second milking animal respectively, but are instead applied to the other animal. In this condition, it is anticipated that the pitch of one of the milking clusters may be greater than expected, and the pitch of the other milking cluster may be lower than, or opposite to, that expected.

In an exemplary embodiment, an "unused cluster" condition may occur where a first milking cluster and second milking cluster are intended to be applied to a first milking animal and a second milking animal respectively, but the second milking cluster goes unused and the first milking cluster is used to milk the second milking animal. In this condition, it is anticipated that the pitch of the second milking cluster may be neutral rather than inclined in the same direction as a next third milking cluster, and the pitch of the first milking cluster is differing to that expected - i.e. opposing that of the third milking cluster.

In exemplary embodiments, the performance sensor data may be used together with the orientation data to distinguish between different conditions of use of the milking clusters in order to assist with determining the milking position

For example, in a "cluster used twice" condition a milking cluster is used to milk a first milking animal, and then a second adjacent milking animal. In this condition, it is anticipated that a change in pitch will be produced - whether direction or magnitude, depending on the circumstances. Further, the milking status (for example, start and end of milking) of one animal may be determined using performance sensor data, as known in the art, to distinguish over a situation in which an animal moves sideways along the row while being milked - i.e. a change in pitch is not as indicative of a "cluster used twice" condition.

In exemplary embodiments, the orientation of the milking cluster may be used to determine a non-use condition of the milking cluster. Depending on the milking facility or milk cluster configuration, there are several positions the milking cluster may take when not applied to an animal. For example, when not in use the claw of the cluster may be supported by a hanger to keep the teatcups above ground level, or in a washing position in which the teatcups are applied to a washing system or jetter. Further, the claw may fall from the hanger or washer to hang downwardly, potentially resting the teatcups on the ground. It is envisaged that it may be useful to distinguish between these conditions, for example to assist with ensuring that cleaning occurs, or reduce the likelihood of damage or contamination due to contact with the ground.

Numerous performance sensors are known for use in relation to milking animals. Non-limiting examples of such performance sensors may include: yield sensors that measure a volume of milk produced by an animal; composition sensors that measure properties of milk produced by an animal - e.g. fat and/or protein content; flow rate sensors to determine the rate of delivery of milk produced by an animal; temperature sensors; weight sensors to determine an animal's weight; health sensors such to measure conditions such as mastitis (for example, a SCC sensor such as the CellSense™ somatic cell count sensor sold by LIC Automation™), body condition score, metabolic disorders, lameness, fertility disorders, BVD, Johne's disease; sensors to measure the feed efficiency of an animal - e.g. milk urea; sensors to measure the environmental impact of an animal - e.g. methane production; sensors to measure the reproductive status of an animal, including but not limited to pregnancy or oestrus detection; sensors to measure properties of milk relevant to milk processing - e.g. suitability for cheese making (such as the AfiLab™ system sold by Af i Milk Limited), free fatty acid content; and/or sensors detecting movement activity of an animal.

In exemplary embodiments, at least one performance sensor may be associated with each milking cluster. However, it should be appreciated that this is not intended to be limiting, as in exemplary embodiments one or more performance sensors may be associated with a subset of the total number of milking clusters - for example, every fourth milking cluster. In an exemplary embodiment, at least two of the milking clusters have at least one associated performance sensor.

The identification of an animal, and association of data with an identifier of an individual animal, is well known in the art. For example, the identifier may be unique to an animal within a herd, or a larger collection of animals - such as New Zealand's National Animal Identification and Tracing (NAIT) scheme. It is well known to display this identifier on the animal - for example printed on an ear tag attached to an ear of the animal, although this is not intended to be limiting to all embodiments.

Systems are also known in the art for identifying an animal's position within a milking facility. In an exemplary embodiment, the system may include an animal identification device configured to read an animal identification tag carried by an animal. For example, the animal may carry a Radio Frequency Identification (RFID) tag configured to be read by an RFID reader. The identifier may then be allocated to a position within the milking facility using any suitable means known in the art - for example, based on a one to one relationship between the reader and a milking position, or reading of the identifier on the animal's entry to the milking facility and basing position on sequential order of entry into the milking facility.

In an exemplary embodiment, on determination of the milking position associated with the milking cluster based on the current orientation, the data from the associated performance sensor may be associated with an identifier of an animal associated with the milking position at the time of collecting the data relating to the characteristic of milk.

In an exemplary embodiment, the system may record the performance data against the identifier within an individual animal historical record as known in the art. The historical record may also include, for example, one or more of: the timing of the recordal event (for example time of day and date), and one or more operator actions (for example: operator observations, designation of the animal being treated or requiring treatment).

For a firmware and/or software (also known as a computer program) implementation, the techniques of the present disclosure may be implemented as instructions (for example, procedures, functions, and so on) that perform the functions described. It should be appreciated that the present disclosure is not described with reference to any particular programming languages, and that a variety of programming languages could be used to implement the present invention. The firmware and/or software codes may be stored in a memory, or embodied in any other processor readable medium, and executed by a processor or processors. The memory may be implemented within the processor or external to the processor.

A processor may be a microprocessor, but in the alternative, the processor may be any processor, controller, microcontroller, state machine, or cloud computing device known in the art. A processor may also be implemented as a combination of computing devices, for example, a combination of a digital signal processor (DSP) and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration.

The processors may function in conjunction with servers and network connections as known in the art. By way of example, the orientation detection devices, performance sensors, and central processor may communicate with each other over a Controller Area Network (CAN) bus system. In an exemplary embodiment, animal identifiers, data from the performance sensors, and any other data may be stored in a data cloud.

The steps of a method, process, or algorithm described in connection with the present disclosure may be embodied directly in hardware, in a software module executed by one or more processors, or in a combination of the two. The various steps or acts in a method or process may be performed in the order shown, or may be performed in another order. Additionally, one or more process or method steps may be omitted or one or more process or method steps may be added to the methods and processes. An additional step, block, or action may be added in the beginning, end, or intervening existing elements of the methods and processes.

BRIEF DESCRIPTION OF DRAWINGS

Further aspects of the present invention will become apparent from the following description which is given by way of example only and with reference to the accompanying drawings in which:

FIG. 1A is a schematic diagram of an exemplary livestock management system;

FIG. IB is a schematic diagram of an exemplary sensor and orientation detection device arrangement associated for use in the exemplary livestock management system;

FIG. 1C is a isometric view of an exemplary accelerometer package for use in the exemplary orientation detection device;

FIG. ID is an isometric view of an exemplary magnetometer package for use in the exemplary orientation detection device;

FIG. 2A is a perspective view of an exemplary milking facility with which the exemplary livestock management system may be implemented;

FIG. 2B is an overhead view of the exemplary milking facility;

FIG. 3A to 3C illustrate an exemplary milking cluster for use in the exemplary milking facility;

FIG. 4 is an end view of the exemplary milking facility in use;

FIG. 5A to 5D illustrate different use cases for milking clusters in the exemplary milking facility;

FIG. 6 is a flow chart illustrating an exemplary method of determining an orientation of the exemplary orientation detection device;

FIG. 7 is a graph of roll angles of the exemplary orientation detection device in use;

FIG. 8 is a flow chart illustrating an exemplary method of determining a milking position characteristic of the milking cluster; FIG. 9 is a graph of average roll angles of the exemplary orientation detection device in use;

and

FIG. 10 is a graph of pitch and roll angles of the exemplary orientation detection device in use, against flow rate obtained from a flow rate sensor.

DETAILED DESCRIPTION

FIG. 1A illustrates a livestock management system 100, within which a local hardware platform 102 manages the collection and transmission of data relating to operation of a milking facility. The hardware platform 102 has a processor 104, memory 106, and other components typically present in such computing devices. In the exemplary embodiment illustrated the memory 106 stores information accessible by processor 104, the information including instructions 108 that may be executed by the processor 104 and data 110 that may be retrieved, manipulated or stored by the processor 104. The memory 106 may be of any suitable means known in the art, capable of storing information in a manner accessible by the processor 104, including a computer-readable medium, or other medium that stores data that may be read with the aid of an electronic device. The processor 104 may be any suitable device known to a person skilled in the art. Although the processor 104 and memory 106 are illustrated as being within a single unit, it should be appreciated that this is not intended to be limiting, and that the functionality of each as herein described may be performed by multiple processors and memories, that may or may not be remote from each other. The instructions 108 may include any set of instructions suitable for execution by the processor 104. For example, the instructions 108 may be stored as computer code on the computer-readable medium. The instructions may be stored in any suitable computer language or format. Data 110 may be retrieved, stored or modified by processor 104 in accordance with the instructions 110. The data 110 may also be formatted in any suitable computer readable format. Again, while the data is illustrated as being contained at a single location, it should be appreciated that this is not intended to be limiting - the data may be stored in multiple memories or locations. The data 110 may also include a record 112 of control routines for aspects of the system 100.

The hardware platform 102 may communicate with various devices associated with the milking facility, for example: first performance sensors 114a to 114n associated with individual milking clusters within the milking facility, and second performance sensors 116a to 116n - again associated with individual milking clusters. It is envisaged that the first performance sensors 114 may be Somatic Cell Count (SCC) sensors such as the CellSense™ somatic cell count sensor sold by LIC Automation™. In exemplary embodiments, the second performance sensors 116 may be a different type of sensor such as the YieldSense™ volume, fat, and protein sensor sold by LIC Automation™. It should be appreciated that reference to these particular forms of performance sensing in the exemplary embodiment presented is not intended to be limiting to all embodiments of the present disclosure.

Animal identification devices 118a to 118n are provided for determining an animal identification ("animal ID") of individual animals entering, or within, the milking facility. More particularly, the animal identification devices 118a to 118n may be used to determine the sequential order of animals along a row of the milking facility, to assist with attributing sensor data to the individual animals as collected. A variety of methodologies are known for the determination of an animal ID - for example a radio frequency identification ("RFID") reader configured to read a RFID tag carried by the animal. In an alternative embodiment, or in conjunction with the animal identification devices 118a to 118n, a user may manually enter (or correct) animal IDs via a user device - examples of which are discussed below. Orientation detection devices 120a to 120n are positioned on milking clusters of the milking facility - as described in greater detail below - and communicate with the hardware platform 102 to assist with determination of the orientation of the milking clusters, and therefore the likely milking position, in order to enable association of performance sensor data with the animal ID recorded at that milking position.

The hardware platform 102 may also communicate with user devices, such as touchscreen 122 located within the milking facility for monitoring operation of the system, and a local workstation 124. The hardware platform 102 may also communicate over a network 126 with one or more server devices 128 having associated memory 130 for the storage and processing of data collected by the local hardware platform 102. It should be appreciated that the server 128 and memory 130 may take any suitable form known in the art - for example a "cloud based" distributed server architecture. The network 126 potentially comprises various configurations and protocols including the Internet, intranets, virtual private networks, wide area networks, local networks, private networks using communication protocols proprietary to one or more companies - whether wired or wireless, or a combination thereof. It should be appreciated that the network 126 illustrated may include distinct networks and/or connections: for example a local network over which the user interface may be accessed within the vicinity of the milking facility, and an internet connection via which the cloud server is accessed. Information regarding operation of the system 100 may be communicated to user devices such as a smart phone 132 or a tablet computer 134 over the network 126.

FIG. IB illustrates the first performance sensors 114a to 114n and orientation detection devices 120a to 120n connected over a Controller Area Network (CAN) bus with the hardware platform 102. It should be appreciated that while not illustrated, additional performance sensors (for example second performance sensors 116a to 116n) may also be connected to, and communicate over, the CAN bus. Each of the performance sensors 114a to 114n is associated with an individual milking cluster in the milking facility - i.e. the sensor data output by an individual sensor relates to milk from individual animals milked using the associated milking cluster.

In exemplary embodiments, performance sensors may be provided for each milking cluster in the milking facility. However, it should be appreciated that this is not intended to be limiting to every embodiment of the present disclosure. For example, it is contemplated that only a subset of milking clusters may have an associated performance sensor (e.g. 1 in 4). Further, it is envisaged that an orientation detection device 120 may be provided for each milking cluster having an associated performance sensor. However, it is also contemplated that in an exemplary embodiment an orientation detection sensor 120 may be provided for every milking cluster, regardless of whether there is an associated performance sensor. It is envisaged that this arrangement may be used to distinguish between different instances in which milking clusters are crossed over and/or unused, as will be discussed further below.

Each orientation detection device 120 includes a processor 136, an accelerometer device 138, a magnetometer device 140, and a network adapter 142 for communication over the CAN bus. By way of example, the accelerometer device 138 may be a "MMA8652FC, 3-Axis, 12-bit, Digital Accelerometer", available from Freescale Semiconductor, Inc. at the time of filing the present application. By way of example, the magnetometer device 140 may be a "Xtrinsic MAG3110 Three-Axis, Digital Magnetometer" available from Freescale Semiconductor, Inc. at the time of filing the present application.

Referring to FIG. 1C and FIG. ID, each of the accelerometer device 138 and the magnetometer device 140 are configured to sense their respective orientation characteristics along three axes: x, y, and z. In an exemplary embodiment, the accelerometer device 138 and the magnetometer device 140 are oriented within the housing of the orientation detection device 120 such that the respective z axes are parallel, and the respective planes in which the x and y axes lie are also parallel. It should be appreciated that the data associated with each axis may be converted to a common frame of reference in software.

It should further be appreciated that these examples are not intended to be limiting to every embodiment of the present disclosure. For example, it is envisaged that the accelerometer device 138 and magnetometer device 140 may be provided in a single device. In a further exemplary embodiment the accelerometer 138 and magnetometer 140 may be provided in an inertial measurement unit (IMU) device, which may also include a gyroscope device.

FIG. 2A and FIG. 2B illustrate an exemplary milking facility 200 in which exemplary embodiments of the present disclosure may be implemented. In this exemplary embodiment, the milking facility is configured as a herringbone swing-over type, having a central pit 202, a left row 204 of milking bails on a first side of the pit 202, and a right row 206 of milking bails on the opposing side of the pit 202. In the embodiment illustrated, a central overhead milk line 208 is provided along the pit 202, with a plurality of milking clusters 210a to 210i connected to, and distributed along the central overhead milk line 208. It should be appreciated that the number of milking clusters 210 will depend on the configuration of the individual milking facility. As will be expanded on below, the milking clusters 210a to 210i may be tilted towards the left row 204 or the right row 206, the value of which may be referred to herein as the roll (indicated in FIG. 2B by arrow 212, having a positive value in the right side direction, and a negative value in the left side direction. Further, the milking clusters 210a to 210i may be tilted in directions along the length of the pit 200, the value of which may be referred to herein as the pitch (indicated in FIG. 2B by arrow 214, having a positive value in the exit direction, and a negative value in the entry direction).

FIG. 3A to 3C illustrate an exemplary embodiment of the milking cluster 210. In this embodiment, four teatcups 300 are connected to a claw 302 by short milk tubes 304 for collection of milk from the teatcups, and short pulse tubes 306 for pulsating the teatcups to encourage milk extraction. A long milk tube is provided by a central portion 308 as part of a rigid dropper 310, with a lower flexible portion 312 connecting the central portion 308 to the claw 302, and an upper flexible portion 314 connecting to the overhead milk line 208 (see FIG. 4, for example). A hanger 316 is provided on the dropper 310 for supporting the claw 302 when the cluster 210 is not in use.

In this exemplary embodiment, the orientation detection device 120 is installed on the dropper 310, more particularly such that the z axes of the accelerometer 138 and magnetometer 140 are approximately aligned with the longitudinal axis of the dropper 310. Calibration of the device 120 will be discussed further below. It should be appreciated that exemplary embodiments of the present disclosure are not intended to be limited to installation of the orientation detection device 120 on the dropper 310, nor exclusive to milking clusters using a rigid dropper as illustrated herein.

Referring to FIG. 4, a milking animal (first cow 400a) is positioned in the left side row 204, and the teatcups 300 of the have been applied to the teats of the first cow 400a. It may be seen that the roll value of the dropper 310 (and therefore orientation detection device 120) in the negative direction has increased from a neutral or zero position. Conversely, application of the teatcups 300 to an animal in the right side row 206 would increase the roll value in the positive direction. In determining the roll of the dropper 310, performance sensor data associated with the milking cluster may be attributed to the cow in the milking position on the determined side.

FIG. 5A to FIG. 5D illustrate exemplary scenarios in which variation in pitch value may be introduced FIG. 5A illustrates a scenario in which sequential milking clusters 210a to 210d are applied to sequential milking animals (first cow 400a to fourth cow 400d) with similar animal and cluster spacing - i.e. a "normal" condition. In this scenario the pitch value for each milking cluster 210 will be similar, indicating that performance sensor data associated with each of the milking clusters 210a to 210d may be attributed to the cows 400a to 400d in sequential order.

In FIG. 5B, the first milking cluster 210a is applied to the second cow 400b, and the second milking cluster 210b is applied to the first cow 400a - i.e. a "crossed cups" condition. In this condition, the pitch of the second milking cluster 210b is greater than expected, and the pitch direction of the first milking cluster 210a is opposite to that expected - i.e. opposing that of the third milking cluster 210c. Without determination that a crossed cup condition exists, using the relative pitch values, performance sensor data associated with the first milking cluster 210a may be attributed to the first cow 400a, and performance sensor data associated with the second milking cluster 210b attributed to the second cow 400b. This scenario may arise, for example, if a milking cluster 210 is out of order, or if farm personnel want to apply a particular cluster to a particular animal (for example where only a subset of clusters have an associated performance sensor).

In FIG. 5C, the second milking cluster 210b is unused, and the first milking cluster 210a is used to milk the second cow 400b - i.e. an "unused cluster" condition. In this condition, the pitch of the second milking cluster 210b is neutral rather than inclined in the same direction as the third milking cluster 210c (and potentially confirmed using the roll value), and the pitch direction of the first milking cluster 210a is opposite to that expected - i.e. opposing that of the third milking cluster 210c. Without determination that an unused cluster condition exists, using the relative pitch values (and potentially roll values), performance sensor data associated with the first milking cluster 210a may be attributed to the first cow 400a, rather than the second cow 400b. This scenario may arise, for example, if a milking cluster 210 is out of order or if the animal spacing is such that there are more milking clusters 210 than animals in the row.

In FIG. 5D, the first milking cluster 210a is used to milk the second cow 400b, and then the first cow 400a - i.e. a "cluster used twice" condition. In this condition, the pitch of the first milking cluster 210a changes significantly mid milking. The start and end of milking of one animal may be determined using performance sensor data, as known in the art, with the change in pitch angle used to determine subsequent application to the first animal 400a. Without determination that a cluster used twice condition exists, performance sensor data associated with the first milking cluster 210a may be attributed to the first cow 400a only, rather than separate sets of data attributed to the second cow 400b and then the first cow respectively. This scenario may arise, for example, if a milking cluster 210 is out of order or if the animal spacing is such that there are less milking clusters 210 than animals in the row.

FIG. 6 illustrates a method 600 of determining an orientation of the orientation detection device 120, in which the term "yaw" will be used to describe the rotation of the orientation detection device 120 about a longitudinal axis of the dropper 310. The data obtained from the accelerometer device 138 may be used to determine the magnitude of the tilt angle of the orientation detection device 120. Flowever, the long milk tube (and more particularly the dropper 310) of the milking cluster 210 has the potential to be twisted about in use, such that the direction of the tilt angle (i.e. whether the roll or pitch is positive or negative) cannot be determined from the accelerometer values alone. The data obtained from the magnetometer device 140 may be used to determine the yaw of the orientation detection device 120, to correct for this. In step 602 of the method 600, the processor 136 receives data from the accelerometer device 138 representing the magnitude of acceleration along each of the x, y, and z axes, and data from the magnetometer device 140 representing the magnitude of the earth's magnetic field along each of the x, y, and z axes. In step 604, the acceleration data is filtered, and used together with the magnetometer data to determine the current yaw value, or bearing, of the orientation detection device 120.

For example, a tilt compensated yaw angle may be determined using the equation:

where: y is the tilt-compensated yaw angle; y is the roll angle; ϋ is the pitch angle; and (B_px, B_py, B_pz) represent the components of the magnetometer data.

During installation of the orientation detection device 120 on the dropper 310, the installer aligns the axes of the orientation detection device 120 with those of the milking facility - i.e. such that the pitch direction is aligned with the longitudinal axis of the pit, and the roll direction is aligned with an axis transverse to the longitudinal axis. A calibration signal may then be sent to the orientation detection device 120 to establish a yaw value, or bearing, of the milking facility, such that a current bearing of the orientation detection device 120 may later be compared with the milking facility bearing to determine relative orientation.

In step 606, the current bearing of the orientation detection device 120 is subtracted from the reference milking facility bearing to determine a relative bearing angle a. In step 608, the relative bearing angle a is used to transform the accelerometer data values for the x and y axes to fit the frame of reference of the milking facility, such that: x' = xcosa + ysina; y' = -xsina + ycosa; and z' = z. In step 610, the transformed x and y acceleration values are used to determine the current pitch and roll values of the orientation detection device 120 within the frame reference of the milking facility, where roll angle f may be derived using the equation: tan(<(>) = (y' / z'); and the pitch angle Q may be derived using the equation: tan(G) = (-x'/(y'sin f +z'cos f)).

Referring to FIG. 7, an exemplary plot 700 of roll values over time is illustrated. A left threshold value 702 is shown, below which the associated milking cluster 210 may be inferred to be inclined towards the left side row 204 - as illustrated by first plot portion 704. A right threshold value 706 is also shown, above which the associated milking cluster 210 may be inferred to be inclined towards the right side row 206 - as illustrated by second plot portion 708. Third plot portion 710 shows the roll value when the milking cluster 210 is inferred to be in a neutral or centre position - for example with the claw 302 supported by the hanger 316.

In exemplary embodiments, noise in the roll and pitch values due to discrete local actions (for example an animal kicking, or milking personnel contacting the milking cluster while passing by) may be compensated for using incremental counters, for example using the method 800 illustrated in FIG. 8. In step 802, counters are initialized or reset for each of the left position, right position, and centre position. In step 804, the current roll values are retrieved, and in step 806 the current position is determined by way of comparison with the roll thresholds.

In step 808, the counter for the determined position is incremented, and the counter for the other positions decremented. In step 810, a determination is made as to whether any position counter is above an associated count threshold - for example a threshold of 100 for a cycle time of 50 milliseconds. If not, the process returns to step 804.

If the count threshold is met, in step 812 a determination is made as to whether that position counter is different to the currently set position. If not, the process returns to step 802. If a position change has occurred, in step 814 the current position setting is updated, and reported to the hardware platform 802. The current position may also be transmitted to the hardware platform 802 periodically, regardless of whether a position change has occurred.

In an alternative embodiment, the left and right thresholds (702, 706) may be set to be equal (e.g. at 0 degrees roll). The center counter is not incremented in this embodiment, and only left or right positions are detected. The threshold may be set at 0 degrees roll or may be adjusted for each particular milking facility.

It should be appreciated that alternate techniques for determining orientation of the orientation detection device 120 may be implemented in exemplary embodiments of the disclosure. For example, FIG. 9 illustrates a plot 900 implementing a technique for detection in changes from side to side. From the roll values, an exponential fast moving average 902, and an exponential slow moving average 904 are produced. The weighting of the fast moving average 902 is selected to be relatively responsive to a change in orientation while filtering temporary changes in orientation - functioning in a similar manner to a low pass filter. The weighting of the slow average is selected to substantially converge over the time period of a typical milking - for example 5 minutes.

The slow moving average 904 is subtracted from the fast moving average 902 to produce differential 906. A change in side may be determined by the value of the differential 906 exceeding a threshold - for example +/- 5 degrees. The points at which the differential exceeds the threshold in FIG. 9 are marked as change in side points 908a to 908d. It is envisaged that a determination of movement of a milking cluster from a neutral position (e.g. the milking cluster on the hanger) to a first side may be used to determine a starting side, with determination of a change in side based on the subsequent differential values used to set the current side of the milking cluster.

Referring to FIG. 10, the use of flow rate of milk obtained using a performance sensor to inform a determination of the milking position (and therefore animal) to which a milking cluster is applied is demonstrated. FIG. 10 provides flow rate 1000 from a flow rate sensor associated with the milking cluster, in addition to pitch values 1002 and roll values 1004 from an orientation detection device, through a milking session including three sequential portions 1006a to 1006c.

Through the first portion 1006a and the third portion 1006c, the detection of flow rate is interrupted - however the pitch and roll values indicate that the orientation of the associated milking cluster is unchanged. This allows for an inference that the data relates to a single animal with a temporary drop in flow rate - for example due to the milk flow being below a detection threshold of the flow rate sensor, while the teat cups remain connected.

In comparison, through the second portion 1006b of the milking session a change in the pitch and roll values may be seen between the interruption in flow rate. The roll value indicates that the milking cluster remains inclined towards the same side, however the pitch value indicates a change in position along the row. Coupled with the interruption in flow rate, this may be indicative of a "cup used twice" condition, in which the milking cluster is applied to an adjacent animal in the same row on completion of milking of a first animal. Depending on the direction derived from the pitch value, the data associated with the second instance of flow rate may be assigned to the animal ID of the animal in that position.

The entire disclosures of all applications, patents and publications cited above and below, if any, are herein incorporated by reference.

Reference to any prior art in this specification is not, and should not be taken as, an acknowledgement or any form of suggestion that that prior art forms part of the common general knowledge in the field of endeavour in any country in the world. The invention may also be said broadly to consist in the parts, elements and features referred to or indicated in the specification of the application, individually or collectively, in any or all combinations of two or more of said parts, elements or features.

Where in the foregoing description reference has been made to integers or components having known equivalents thereof, those integers are herein incorporated as if individually set forth.

It should be noted that various changes and modifications to the presently preferred embodiments described herein will be apparent to those skilled in the art. Such changes and modifications may be made without departing from the spirit and scope of the invention and without diminishing its attendant advantages. It is therefore intended that such changes and modifications be included within the present invention.

Aspects of the present invention have been described by way of example only and it should be appreciated that modifications and additions may be made thereto without departing from the scope thereof.

Claims

1. A system for use in a milking facility having a plurality of milking clusters, each configured to be connected to a milking animal to extract milk therefrom, the system including:

at least one orientation detection device positioned on one of the milking clusters, the orientation detection device including:

at least one orientation sensor configured to output orientation data;

at least one processor configured to:

receive the orientation data;

determine, using the orientation data, a current orientation of the milking cluster; and

output a signal indicative of the current orientation;

at least one processor configured to:

receive the signal from the orientation detection device indicative of the current orientation of the milking cluster;

determine a milking position associated with the milking cluster based on the current orientation.

2. The system of claim 1, wherein the at least one orientation sensor includes an accelerometer device configured to output acceleration data, and a magnetometer device configured to output magnetic field data.

3. The system of claim 2, wherein the accelerometer device and the magnetometer device are provided in a single unit.

4. The system of any one of claims 1 to 3, wherein determination of the current orientation includes determining the roll of the orientation detection device, wherein the roll of the orientation detection device is indicative of inclination towards a side of the milking facility.

5. The system of any one of claims 1 to 4, wherein determination of the current orientation includes determining the pitch of the orientation detection device, wherein the pitch of the orientation detection device is indicative of inclination towards an end of the milking facility.

6. The system of claim 5, wherein the pitch of individual milking clusters is used to distinguish between different conditions of use of the milking clusters in order to assist with determining the milking position.

7. The system of claim 6, wherein a normal condition of use is determined based on a determination that the pitch for adjacent or nearby milking clusters is similar.

8. The system of claim 6 or claim 7, wherein a crossed cups condition of use is determined based on the pitch of one of the milking clusters may be greater than expected, and the pitch of another one of the milking clusters being lower than, or opposite to, that expected.

9. The system of any one of claims 6 to 8, wherein an unused cluster condition of use may be determined based on the pitch of a first one of the milking clusters differing to that expected, and the pitch of a second one of the milking clusters being neutral rather than inclined in the direction of a third one of the milking clusters.

10. The system of any one of claims 1 to 9, wherein determining the orientation of the orientation device includes determining a bearing of the orientation detection device, and comparing the bearing with a reference bearing.

11. The system of claim 10, wherein the reference bearing is established while the milking cluster or orientation detection device is in a neutral position.

12. The system of claim 11, wherein a calibration setting may be used to establish the reference bearing during installation of the orientation detection device.

13. The system of claim 11 or claim 12, wherein the orientation detection device is installed such that the bearing in the neutral position is directed towards an exit of the milking facility.

14. The system of any one of claims 10 to 13, wherein the relative angle between the bearing and the reference bearing is used to transform the orientation data to fit a frame of reference of the milking facility, and the current orientation is determined using the transformed orientation data.

15. The system of any one of claims 1 to 14, including at least one performance sensor associated with one of the milking clusters, the performance sensor configured to output data relating to a characteristic of milk extracted by the milking cluster, wherein the at least one processor of the system is configured to associate the data from the performance sensor with an identifier of an animal associated with the milking position at the time of collecting the data relating to the characteristic of milk.

16. The system of claim 15, wherein at least one of the performance sensors is associated with each milking cluster.

17. The system of claim 15, wherein one or more of the performance sensors are associated with a subset of the total number of milking clusters.

18. The system of any one of claims 15 to 17, wherein the performance sensor data is used together with the orientation data to distinguish between different conditions of use of the milking clusters in order to assist with determining the milking position.

19. The system of claim 18, wherein a cluster-used-twice condition of use of a milking cluster is determined based on detection of a change in pitch in combination with milking status determined using performance sensor data.

20. The system of any one of claims 1 to 19, wherein each of the milking clusters are suspended from an overhead position.

21. The system of claim 20, wherein the at least one orientation detection device is positioned on a dropper of the associated milking cluster.

22. The system of any one of claims 1 to 21, wherein the milking facility has a swing-over herringbone configuration, in which two rows of standing positions are located to either side of a central pit.

23. A method for determining a milking position associated with one of a plurality of milking clusters in a milking facility, the method including:

receiving orientation data from at least one orientation sensor positioned on the milking cluster;

determining, using the orientation data, a current orientation of the milking cluster; and determining a milking position associated with the milking cluster based on the current orientation.

24. The method of claim 23, wherein the orientation data includes acceleration data from an accelerometer device configured to output, and magnetic field data from a magnetometer device.

25. The method of claim 23 or claim 24, determination of the current orientation includes determining the roll of the at least one orientation sensor, wherein the roll of the at least one orientation sensor is indicative of inclination towards a side of the milking facility.

26. The method of any one of claims 23 to 25, wherein determination of the current orientation includes determining the pitch of the at least one orientation sensor, wherein the pitch of the at least one orientation sensor is indicative of inclination towards an end of the milking facility.

27. The method of claim 26, wherein the pitch of individual milking clusters is used to distinguish between different conditions of use of the milking clusters in order to assist with determining the milking position.

28. The method of claim 27, wherein a normal condition of use is determined based on a determination that the pitch for adjacent or nearby milking clusters is similar.

29. The method of claim 27 or claim 28, wherein a crossed cups condition of use is determined based on the pitch of one of the milking clusters may be greater than expected, and the pitch of another one of the milking clusters being lower than, or opposite to, that expected.

30. The method of any one of claims 27 to 29, wherein an unused cluster condition of use may be determined based on the pitch of a first one of the milking clusters differing to that expected, and the pitch of a second one of the milking clusters being neutral rather than inclined in the direction of a third one of the milking clusters.

31. The method of any one of claims 23 to 30, wherein determining the orientation of the at least one orientation sensor includes determining a bearing of the at least one orientation sensor, and comparing the bearing with a reference bearing.

32. The method of claim 31, wherein the reference bearing is established while the milking cluster or the at least one orientation sensor is in a neutral position.

33. The method of claim 32, wherein a calibration setting may be used to establish the reference bearing during installation of the at least one orientation sensor.

34. The method of claim 32 or claim 33, wherein the at least one orientation sensor is installed such that the bearing in the neutral position is directed towards an exit of the milking facility.

35. The method of any one of claims 31 to 34, wherein the relative angle between the bearing and the reference bearing is used to transform the orientation data to fit a frame of reference of the milking facility, and the current orientation is determined using the transformed orientation data.

36. The method of any one of claims 23 to 35, including receiving data relating to a characteristic of milk extracted by one of the milking clusters from at least one performance sensor associated with the milking cluster; and

associating the data from the performance sensor with an identifier of an animal associated with the milking position at the time of collecting the data relating to the characteristic of milk.

37. The method of claim 36, including distinguishing between different conditions of use of the milking clusters using the performance sensor data together with the orientation data, in order to assist with determining the milking position.

38. The method of claim 37, including determining a cluster-used-twice condition of use of a milking cluster based on detection of a change in pitch in combination with milking status determined using performance sensor data.

39. The method of claim 23 to 38, including positioning the at least one orientation sensor on a dropper of the associated milking cluster.

40. The method of any one of claims 23 to 39, wherein each of the milking clusters are suspended from an overhead position.

41. The method of any one of claims 23 to 40, wherein the milking facility has a swing-over herringbone configuration, in which two rows of standing positions are located to either side of a central pit.

42. An orientation detection device configured to be positioned on a milking cluster of a milking facility, the orientation detection device including:

at least one orientation sensor configured to output orientation data;

at least one processor configured to:

receive the orientation data;

determine, using the orientation data, a current orientation of the milking cluster; and output a signal indicative of the current orientation.