AU2020226203A1

AU2020226203A1 - Power monitoring

Info

Publication number: AU2020226203A1
Application number: AU2020226203A
Authority: AU
Inventors: John Alfred Gardner; John Wright SCOTT
Original assignee: Movus Tech Pty Ltd
Current assignee: Movus Technologies Pty Ltd
Priority date: 2019-02-19
Filing date: 2020-02-18
Publication date: 2022-10-06
Also published as: WO2020168379A1

Abstract

A monitoring system including a power monitoring device including a housing having an opening configured to receive a power cable, a plurality of current sensors spaced around the opening to measure an electrical current within the power cable, a power monitoring device processor that acquires current sensor signals from the current sensors and generates sensor data in accordance with the current sensor signals, and a power monitoring device transmitter that transmits the sensor data. Processing systems can be provided that receive and analyze the sensor data to determine a power supplied to the machine.

Description

POWER MONITORING

Background of the Invention

[0001] The present invention relates to a method and system for power monitoring, and in one example to a method and system using a power monitoring device that monitors electrical power supplied to a machine or other electrical equipment.

Description of the Prior Art

[0002] The reference in this specification to any prior publication (or information derived from it), or to any matter which is known, is not, and should not be taken as an acknowledgment or admission or any form of suggestion that the prior publication (or information derived from it) or known matter forms part of the common general knowledge in the field of endeavour to which this specification relates.

[0003] Monitoring of machines, such as pumps is often performed in order to monitor operation, and in particular to ensure the machine is operating correctly and has not failed. Such monitoring is typically performed on an ad-hoc basis through a process of visual inspections and routine maintanence. However, this is not always a practical solution. For example, the water industry within the Australian context suffers from the ‘tyranny of distance’, in which a machine is generally spread across broad geographic expanses. As a result, Sydney Water undertakes over 10,000 manual machine inspections for machine condition monitoring. Manual inspections are therefore costly, time consuming and irregular.

[0004] Assets are generally classified into a tiered system, where low value/low impact machines are considered uneconomical to conduct condition monitoring. The next class of assets are regularly inspected (typically monthly), and finally high value/high impact machinery where‘online’ monitoring or real time monitoring is installed (this is typically the top 5% of machinery). In such situations, custom sensor suites are developed and installed for each machine, with alerts being sent once a day. Such systems typically cost several thousand dollars per machine, with the largest costs being the installation and setup which has to be conducted by a trained engineer. These systems require permits, paperwork and cabling. [0005] WO2018/119489 describes a monitoring system for monitoring a machine, the monitoring system including at least one monitoring device and one or more processing systems. The monitoring device includes a housing, a coupling that physically attaches the housing to the machine, a plurality of sensors, the plurality of sensors including a vibration sensor that senses vibration transmitted from the machine to the vibration sensor at least in part via the coupling, a monitoring device processor that acquires sensors signals from the plurality of sensors and generates sensor data at least partially in accordance with signals from the sensors, and a transmitter that transmits the sensor data. The one or more processing systems receive the sensor data, analyse the sensor data to determine a machine status and either store an indication of the machine status as part of machine status data associated with respective machine or cause a status indication indicative of the machine status to be displayed.

Summary of the Present Invention

[0006] In one broad form, an aspect of the present invention seeks to provide a monitoring system for monitoring a machine, the monitoring system including: at least one power monitoring device including: a housing having an opening configured to receive a power cable; a plurality of current sensors spaced around the opening to measure an electrical current within the power cable; a power monitoring device processor that: acquires current sensor signals from the current sensors; and, generates sensor data at least partially in accordance with the current sensor signals; a power monitoring device transmitter that transmits the sensor data; and, one or more processing systems configured to: receive the sensor data; analyse the sensor data to determine a power supplied to the machine; and, at least one of: store an indication of the power supplied as part of machine status data associated with the respective machine; determine a machine status at least in part using the power supplied to the machine; and, cause an indication to be displayed of at least one of: the power supplied to the machine; and, the machine status.

[0007] In one embodiment the housing includes first and second housing sections pivotally coupled to allow the housing sections to be moved between an open position in which the power cable can be positioned in the opening and a closed position in which the power cable is enclosed within the opening.

[0008] In one embodiment current sensors are provided in each of the first and second housing sections.

[0009] In one embodiment the monitoring system includes first and second circuit boards, each contained in a respective housing portion, and each including at least one current sensor.

[0010] In one embodiment the power monitoring device includes at least one of: a respective power monitoring device processor and power monitoring device transmitter for each circuit board; and, a single power monitoring device processor and power monitoring device transmitter that receive signals from current sensors on each circuit board via wired or wireless connections.

[0011] In one embodiment the housing includes a number of resilient members provided around the opening to locate the power cable within the opening.

[0012] In one embodiment the sensors include at least one of: Hall effect sensors; current sensing coils; micro electro mechanical current sensors; and, magnetic field detector integrated circuits.

[0013] In one embodiment the current sensors are circumferentially spaced around the opening.

[0014] In one embodiment the power cable is a multi-core cable including a plurality of conductors and wherein the sensors are configured to measure an electrical current in multiple ones of the plurality of conductors.

[0015] In one embodiment one or more processing systems are configured to analyse the sensor data to determine a respective electrical current in each of the conductors.

[0016] In one embodiment the power supply is a multi-phase power supply, and wherein the one or more processing systems are configured to analyse the sensor data to determine a current supplied by each phase. [0017] In one embodiment the one or more processing systems are configured to analyse the sensor data to determine at least one of: a current frequency; a cycle time; a power factor; a power draw; a phase difference between different phases; a power utilization; and, a power efficiency.

[0018] In one embodiment the power monitoring device includes at least one monitoring device power supply.

[0019] In one embodiment the monitoring device power supply includes at least one of: a battery; and, a coil that generates power using electrical current within the power cable.

[0020] In one embodiment the power monitoring device is configured to measure current signals from the current sensors.

[0021] In one embodiment the power monitoring device processor is configured to control a measurement frequency or extent in accordance with the current sensor signals.

[0022] In one embodiment the power monitoring device processor is configured to detect activation of the machine in accordance with the current sensor signals.

[0023] In one embodiment in response to activation of the machine, the power monitoring device processor is configured to: adjust a measurement frequency or extent in response to activation of the machine; and, generate a machine activation indication.

[0024] In one embodiment the monitoring system includes a vibration monitoring device that includes a vibration sensor that senses vibration transmitted from the machine and wherein the one or more processing systems are configured to analyse sensor data from the vibration sensor to determine a machine status.

[0025] In one embodiment the vibration monitoring device magnetically attaches to the machine.

[0026] In one embodiment the vibration monitoring device includes: a housing; a coupling that physically attaches the housing to the machine; a plurality of sensors, the plurality of sensors including a vibration sensor that senses vibration transmitted from the machine to the vibration sensor at least in part via the coupling; a vibration monitoring device processor that: acquires sensors signals from the plurality of sensors; and, generates sensor data at least partially in accordance with signals from the sensors; a vibration monitoring device transmitter that transmits the sensor data.

[0027] In one embodiment the vibration monitoring device is controlled at least one of: at least in part using current sensor signals from the current sensors; and, using a machine activation indication.

[0028] In one embodiment the power monitoring device transmits the sensor data to the vibration monitoring device and wherein the vibration monitoring device transmits the sensor data to the one or more processing systems.

[0029] In one embodiment the system includes at least one hub that: receives sensor data from a plurality of monitoring devices; and, transfers the sensor data to the one or more processing devices via a communications network.

[0030] In one embodiment the hub and monitoring devices communicate using a short range wireless communications protocol.

[0031] In one embodiment the sensor data includes at least one of: a monitoring device identifier; signals from the sensors; and, one or more parameters derived from signals from the sensors.

[0032] In one embodiment the power monitoring device at least partially processes the current sensor signals.

[0033] In one embodiment the power monitoring device at least partially processes the current sensor signals by at least one: filtering; amplifying; digitizing; and, parameterizing.

[0034] In one embodiment the system: uses signals from one or more sensors during a first time period to establish reference behaviour for the machine; and, uses current sensor signals and the reference behaviour to determine a machine status. [0035] In one embodiment the system: uses signals from one or more sensors to generate reference data indicative of the reference behaviour, the reference data being indicative of at least one of: current sensor signals; parameters derived from current sensor signals; patterns derived from current sensor signals; reference thresholds derived from the current sensor signals; and, reference ranges derived from the current sensor signals; and, determines a machine status at least in part based on the reference data and current sensor signals.

[0036] In one embodiment the system: determines operational data using current sensor signals, the operational data being based on at least one of: current sensor signals; parameters derived from current sensor signals; and, patterns derived from current sensor signals; and, compares the operational data to the reference data.

[0037] In one embodiment the parameters include at least one of: a current frequency; a cycle time; a power factor; a power draw; a phase difference; a power utilization; a power efficiency; a parameter change; and, a rate of parameter change.

[0038] In one embodiment the system assesses the machine status at least in part using machine learning techniques.

[0039] In one embodiment the system uses machine learning techniques to: identify at least one category of behaviour for the machine from the reference behaviour; and, determine the machine status by analysing current sensor signals to categorize a current behaviour based on the at least one category.

[0040] In one embodiment the system analyses current sensor signals with respect to reference behaviour determined during corresponding time intervals during which the machine is expected to exhibit similar behaviour.

[0041] In one embodiment the system: monitors changes in machine status over time; and, at least one of: stores an indication of changes in machine status as part of machine status data associated with respective machine; cause a status indication indicative of the change in machine status to be displayed. [0042] In one embodiment the system: uses signals from one or more sensors during a calibration time period when the monitoring device is attached to a calibration machine to establish calibration data; and, using the calibration data to interpret signals from the sensors when the monitoring device is attached to the machine.

[0043] In one embodiment the one or more processing systems are configured to: determine an identifier of the monitoring device; uses the identifier to retrieve calibration data; and, analyse the sensor data at least in part using the calibration data.

[0044] In one embodiment the system: determines a monitoring device integrity; and, selectively generates an alert depending on results of the determination.

[0045] In one embodiment the system: analyses signals from a humidity sensor to determine changes in humidity within the housing; and, using changes in humidity to determine at least one of: if the housing has been breached; and, if a housing seal has failed.

[0046] In one embodiment the housing contains a desiccant.

[0047] In one embodiment the system: analyses signals from a light sensor to determine changes in light levels within the housing; and, using changes in light levels to determine at least one of: if the housing has been breached; and, if a housing seal has failed.

[0048] In one embodiment the system determines if the monitoring device has been moved by: analysing signals from a movement sensor to determine at least one of: movement; and, a change in orientation; analysing signals from a microphone to determine a change in noise levels; and, determine a wireless network signal strength to determine a change in position of the transmitter relative to a receiver.

[0049] In one broad form, an aspect of the present invention seeks to provide a method for monitoring a machine, the method including, in one or more processing systems: receiving current sensor data from a power monitoring device having an opening configured to receive a power cable, the current sensor data being generated at least in part based on signals from a plurality of current sensors spaced around the opening to measure an electrical current within the power cable; analysing the current sensor data to determine a power supplied to the machine; and, at least one of: storing an indication of the power supplied as part of machine status data associated with the respective machine; determining a machine status at least in part using the power supplied to the machine; and, causing an indication to be displayed of at least one of: the power supplied to the machine; and, the machine status.

[0050] In one embodiment the method includes: using signals from one or more sensors during a first time period to establish reference behaviour for the machine; and, using current sensor signals and the reference behaviour to determine a machine status.

[0051] In one embodiment the method includes: using current sensor signals to generate reference data indicative of reference behaviour, the reference data being indicative of at least one of: current sensor signals; parameters derived from current sensor signals; patterns derived from current sensor signals; reference thresholds derived from the current sensor signals; and, reference ranges derived from the current sensor signals; and, determining a machine status at least in part based on the reference data and current sensor data.

[0052] In one embodiment the method includes: determining operational data using current sensor signals, the operational data being based on at least one of: current sensor signals; parameters derived from current sensor signals; and, patterns derived from current sensor signals; and, comparing the operational data to the reference data.

[0053] In one embodiment the parameters include at least one of: a current frequency; a cycle time; a power factor; a power draw; a phase difference between different phases; a power utilization; and, a power efficiency.

[0054] In one embodiment the method includes assessing the machine status at least in part using machine learning techniques.

[0055] In one embodiment the method includes using machine learning techniques to: identify at least one category of behaviour for the machine from the reference behaviour; and, determine the machine status by analysing current sensor signals to categorize a current behaviour based on the at least one category. [0056] In one embodiment the method includes: determining at least one metric from the sensor data; and, apply the at least one metric to at least one computational model to determine a machine status, the computational model embodying a relationship between a machine status and one or more metrics.

[0057] In one embodiment the at least one computational model is obtained by applying machine learning to reference metrics derived from sensor data measured for the machine during the first time period.

[0058] In one embodiment the method includes analysing current sensor signals with respect to reference behaviour determined during corresponding time intervals during which the machine is expected to exhibit similar behaviour.

[0059] In one embodiment the method includes: monitoring changes in machine status over time; and, at least one of: storing an indication of changes in machine status as part of machine status data associated with respective machine; causing a status indication indicative of the change in machine status to be displayed.

[0060] In one broad form, an aspect of the present invention seeks to provide a computer program product for monitoring a machine, the computer program product including computer executable code, which when executed by one or more suitably programmed processing systems, causes the one or more processing systems to: receive current sensor data from a power monitoring device having an opening configured to receive a power cable, the current sensor data being generated at least in part based on signals from a plurality of current sensors spaced around the opening to measure an electrical current within the power cable; analyse the current sensor data to determine a power supplied to the machine; and, at least one of: store an indication of the power supplied as part of machine status data associated with the respective machine; determine a machine status at least in part using the power supplied to the machine; and, cause an indication to be displayed of at least one of: the power supplied to the machine; and, the machine status.

[0061] In one broad form, an aspect of the present invention seeks to provide a power monitoring device including: a housing having an opening configured to receive a power cable; a plurality of current sensors spaced around the opening to measure an electrical current within the power cable; a power monitoring device processor that: acquires current sensor signals from the current sensors; and, generates sensor data at least partially in accordance with the current sensor signals; and, at least one of: a power monitoring device transmitter that transmits the sensor data; and, a display that displays an indicator derived from the sensor data.

[0062] In one embodiment the housing includes first and second housing sections pivotally coupled to allow the housing sections to be moved between an open position in which the power cable can be positioned in the opening and a closed position in which the power cable is enclosed within the opening.

[0063] In one embodiment current sensors are provided in each of the first and second housing sections.

[0064] In one embodiment the power monitoring device includes first and second circuit boards, each contained in a respective housing portion, and each including at least one current sensor.

[0065] In one embodiment the power monitoring device includes at least one of: a respective power monitoring device processor and power monitoring device transmitter for each circuit board; and, a single power monitoring device processor and power monitoring device transmitter that receive signals from current sensors on each circuit board via wired or wireless connections.

[0066] In one embodiment the housing includes a number of resilient members provided around the opening to locate the power cable within the opening.

[0067] In one embodiment the sensors include at least one of: Hall effect sensors; current sensing coils; micro electro mechanical current sensors; and, magnetic field detector integrated circuits.

[0068] In one embodiment the current sensors are circumferentially spaced around the opening. [0069] In one embodiment the power cable is a multi-core cable including a plurality of conductors and wherein the sensors are configured to measure an electrical current in multiple ones of the plurality of conductors.

[0070] In one embodiment the sensor data is analysed to determine a respective electrical current in each of the conductors.

[0071] In one embodiment the power supply is a multi -phase power supply, and the sensor data is analysed to determine a current supplied by each phase.

[0072] In one embodiment the sensor data is analysed to determine a parameter including at least one of: a current frequency; a cycle time; a power factor; a power draw; a phase difference between different phases; a power utilization; and, a power efficiency.

[0073] In one embodiment the transmitter transmits the sensor data to one or more processing systems configured to analyse the sensor data.

[0074] In one embodiment the power monitoring device processor is configured to analyse the sensor data.

[0075] In one embodiment the at least one parameter is compared to a defined threshold, and wherein the power monitoring device generates an indication of the result of the comparison.

[0076] It will be appreciated that the broad forms of the invention, and their respective features can be used in conjunction, interchangeably and/or independently, and reference to separate broad forms is not intended to be limiting.

Brief Description of the Drawings

[0077] Various examples and embodiments of the present invention will now be described with reference to the accompanying drawings, in which: -

[0078] Figure 1A is a schematic front view of an example of a system for monitoring a machine;

[0079] Figure IB is a schematic side view of the system of Figure 1A; [0080] Figure 2 is a flow chart of an example of a process for monitoring a machine;

[0081] Figure 3 is a schematic diagram of a second example of a system for monitoring a machine;

[0082] Figure 4 is a schematic diagram of a processing system of Figure 3;

[0083] Figure 5 is a schematic diagram of an example of a client device of Figure 3;

[0084] Figure 6A is a schematic perspective view of an example of a monitoring device housing;

[0085] Figure 6B is a schematic plan view of an example of a circuit board provided in the housing of Figure 6 A;

[0086] Figure 6C is a schematic cutaway view of the housing of Figure 6A in an open position;

[0087] Figure 6D is a schematic cutaway view of the housing of Figure 6A in a closed position;

[0088] Figures 7A and 7B are a flow chart of an example of a process for monitoring a machine;

[0089] Figure 8A is a schematic diagram of a first example of a screen shot for use in monitoring a machine;

[0090] Figure 8B is a schematic diagram of a second example of a screen shot for monitoring a machine;

[0091] Figure 9 is a flow chart of an example of a process for establishing reference data; and,

[0092] Figure 10 is a flow chart of an example of a process for analysing sensor signals. Detailed Description of the Preferred Embodiments

[0093] An example of a system for monitoring a machine will now be described with reference to Figures 1A and IB.

[0094] In this example, the apparatus 100 includes a power monitoring device 110 having a housing 120, which has an opening 121 configured to receive a power cable 101, which is used to supply power to a machine that is to be monitored. In this example, the housing 120 surrounds the power cable 101, so that the power cable is retained within the opening 121, thereby securing the housing 120 to the power cable 101. This can be achieved by sliding the housing 120 along the power cable, but more typically the housing can be opened to access the opening 121, and allow the housing to be attached to the cable in situ, and further details of such an arrangement will be described in more detail below.

[0095] The machine that is monitored can be any form of machine that requires monitoring, and which receives electrical power via a power cable, such as a multi-core power cable and example machines include, but are not limited to, pumps, compressors, motors, or the like. It should be noted that the term power cable is used to refer to any arrangement that is used to conduct electrical power to the machine, and this could include a discrete cable, conduit containing multiple cables or conductors, or the like, and the term power cable is not intended to be restrictive.

[0096] The power monitoring device 110 includes a plurality of current sensors 113, spaced around the opening to measure an electrical current within the power cable. In the current example, the current sensors 113 are provided evenly spaced around the opening, but it will be appreciated that this is not essential, and other configurations could be used. The current sensors 113 could be of any appropriate form, but in one preferred example are contactless sensors, such as current sensing coils, micro electro mechanical (MEMS) current sensors, Hall effect sensors, magnetic field detector integrated circuits, or the like, allowing the current to be sensed without requiring the cable to be breached or otherwise interfered with. It will be appreciated that other sensors, such as anti-tamper sensors, or the like, could also be provided as will be described in more detail below. [0097] The monitoring device 110 also typically includes a monitoring device processor 111 and a transmitter 112, as well as an optional power supply 114, allowing the monitoring device to monitor the sensors and provide sensor data to one or more processing systems 130, for subsequent analysis. For ease of illustration the remaining description will refer to a processing system, but it will be appreciated that multiple processing systems could be used, with processing distributed between the processing systems as needed, and that reference to the singular encompasses the plural arrangement and vice versa. Similarly, whilst reference is generally made to a single power monitoring device processor, but it will be appreciated that multiple processors could be used, with processing distributed between them as needed, and that reference to the singular encompasses the plural arrangement and vice versa.

[0098] The nature of the processing system 130 will vary depending upon preferred implementation and could include computer systems, such as personal computers, laptops, desktops, servers, mobile communication devices such as smart phones or tablets or the like. Communication with the processing system 130 could be directly, via a wired or wireless point to point connection, or could be via one or more intermediate devices, communications networks or the like, and further examples will be described in more detail below.

[0099] An example of a process for using the system of Figures 1A and IB to monitor machine will now be described with reference to Figure 2.

[0100] In this example, at step 200 current sensor signals are acquired from the current sensors 113. The current sensor signals are acquired by the power monitoring device processor 111 optionally after preliminary processing, such as filtering, or the like, has been performed.

[0101] At step 210 the power monitoring device processor 111 generates sensor data at least partially in accordance with current sensor signals acquired from the current sensors. The sensor data could be of any appropriate form and may include an indication of the current sensor signals, or information derived therefrom, such as one or more parameters obtained by analysing the current sensor signals. For example, the power monitoring device processor 111 could perform preliminary analysis, such as determining the magnitude, frequency or phase of a supplied current, which can be provided instead of raw data. The sensor data may also include other information, such as an identifier used to identify the power monitoring device 110.

[0102] At step 220, the sensor data is transmitted by the transmitter 112, allowing this to be received by the processing system 130 at step 230, for example by having the sensor data transferred via a communications network, point-to-point connection, intermediate device, or the like.

[0103] At step 240 the processing system 130 analyses the sensor data to determine an electrical power supplied to the machine. For example, this could include determining the current drawn by the machine across multiple phases, including information regarding the frequency of each phase, and a phase difference between the phases.

[0104] Once a power supplied has been determined, this can be stored, for example as part of machine status data forming part of a profile associated with the respective machine. Additionally and/or alternatively, the supplied power could be used to determine a machine status, such as an indication of whether or not the machine is functioning correctly. For example, variations in the power supplied to the machine can be indicative of whether the machine is functioning as expected, or if not, could be used to derive the nature of any problem.

[0105] This allows the processing system 130 to generate an indication indicative of the machine status or the power supplied, allowing this to be displayed to a user at step 250. For example, this could include displaying an indication of sensor signals or parameters derived from the sensor signals and/or a result of comparison of the sensor signals or parameters to reference ranges or thresholds. Alternatively, this could include showing a currently power usage compared to an expected power usage to determine whether the machine is currently operating normally.

[0106] Accordingly, it will be appreciated that the above described system enables monitoring of a machine to be performed. In particular, the above described system allows machine to be monitored by attaching a power monitoring device to a power cable, or other power conduit, used to provide electrical power to the machine. This allows the power monitoring device to be used to monitor power supplied to the machine, for example to monitor power fluctuations or similar.

[0107] Furthermore, the power monitoring device is configured to easily attach to existing power cables, enabling the power monitoring device to be easily retrofitted to existing machines, simply by attaching the monitoring device to the power cable used to supply electrical power to the machine. Through suitable configuration of the housing, this can be achieved without requiring the power cable to be disconnected or otherwise interfered with, enabling the power monitoring device to be deployed on machines that are in use, without interfering with machine operation. This also avoids major safety issues, for example associated with interfering with high current or voltage power supply equipment.

[0108] Sensor data indicative of the power supplied, and optionally any other measured parameters, can then be transferred to one or more remote processing systems, allowing these to be analysed to ensure the machine is functioning correctly. This reduces the level of processing required by the power monitoring device, allowing this to be implemented using relatively cheap and straightforward sensors and associated hardware, in turn allowing the sensors to be deployed widely without undue expense. Consequently, a number of different power monitoring devices can be associated with a variety of different pieces of machine (generally referred to as assets), allowing these to be monitored centrally, making it easy for an entity to monitor a wide range of distributed assets.

[0109] This arrangement also allows data to be stored and analysed centrally. This in turn generates a repository of sensor data that can be analysed on an ongoing basis, for example using machine learning techniques, which can assist with the identification of a wide range of different machine faults.

[0110] It will also be appreciated from the above and the following description that the power monitoring device could have other applications and could be used for monitoring electrical power supply more generally. For example, the power monitoring device could be used for monitoring power supplied via for switchboards, smart fuse applications, or the like, and does not necessarily need to be used as part of a machine monitoring process. [0111] In this instance, the power monitoring device can still communicate with remote processing systems, including computers, smart phones, tablets, or the like, to allow information to be displayed. This could include the sensor data, or information derived therefrom, such as a current, a power supplied, or the like. Additionally and/or alternatively, this information could be calculated on board and used to display an indicator indicative of the supplied current, power usage, or other parameters, as will be described in more detail below.

[0112] It will be appreciated from this that reference throughout the following to machine monitoring is therefore intended to be illustrative of a preferred usage of the power monitoring device, but is not intended to be limiting and that the power monitoring device could be used more generally for other power monitoring applications.

[0113] A number of further features will now be described.

[0114] In one example, the housing includes first and second housing sections pivotally coupled to allow the housing sections to be moved between an open position, in which the power cable can be positioned in the opening and a closed position in which the power cable is enclosed within the opening. This provides a mechanism to simply attach the power monitoring device to the power cable without requiring the power cable to be disconnected from the machine, or otherwise interfered with.

[0115] In one example, current sensors are provided in each of the first and second housing sections, so that the current sensors can be provided around substantially the perimeter of the opening, which can in turn help the current sensors more accurately sense current in the power cable. To achieve this arrangement, and depending on the nature of the current sensors, the power monitoring device can include first and second circuit boards, each contained in a respective housing portion, with each circuit board having at least one current sensor mounted thereon.

[0116] In circumstances in which two circuit boards are provided, a respective power monitoring device processor and power monitoring device transmitter could be provided for each circuit board, so that each circuit board effectively operates independently, with information from the sensors being integrated by the processing system 130 as needed. Alternatively, a single power monitoring device processor and power monitoring device transmitter could be provided, which receive signals from current sensors on each circuit board, via wired or wireless connections.

[0117] In one example, the housing includes a number of resilient members, such as plastic or rubber fingers, which are provided around the opening to locate the power cable within the opening. In particular, this can be used to centralise the power cable within the opening, so that the power cable is approximately equally spaced from each of the current sensors, thereby helping ensure each of the sensors senses a relatively equal magnitude of signal. Additionally, this can help reduce movement of the housing relative to the cable, which could in turn interfere with readings performed, particularly if readings are compared to historical readings collected for the same machine and power cable. Despite this, the use of resilient members, allows the housing to be used with different sized power cables, allowing a single design of power monitoring device to be deployed in a wide range of different situations.

[0118] As previously mentioned, in one example, the sensors are MEMS current sensors or digital magnetic field detector integrated circuits, which can be mounted directly on the circuit boards. Alternatively, the current sensors could include current sensing coils, such as Hall effect sensors, which may be wound on a core supported by the circuit board and/or housing, depending on the preferred implementation. It will be appreciated that other suitable current sensor arrangements could also be used, and these examples are not intended to be limiting.

[0119] In one example, the power cable is a multi-core cable including a plurality of conductors, with the sensors being configured to measure an electrical current in multiple ones of the plurality of conductors. In particular, providing a plurality of current sensors circumferentially spaced around the opening, allows the current sensor signals from each of the current sensors to be analysed in order to determine a respective electrical current in each of the different conductors. This allows multi-core cable supplying multi-phase power to be monitored, without requiring that the housing is attached to the multi-core cable in any particular orientation, and also allowing for a variety of different configuration multi-core cables to be monitored.

[0120] The processing system can be configured to analyse the sensor data to determine at least one of a current frequency, a cycle time, a power factor, a power draw, a phase difference between different phases, a power utilization, a power efficiency, a DC current, a DC voltage, an AC current or an AC voltage, or the like. For example, examining the current and phase differences on a multi-phase power connection can allow a power efficiency or power factor to be calculated, which can in turn be used to optimise power supplied to machines. For example, examining this collectively within a facility can be used to identify phase shifts between different phases, which can result in inefficient power usage, which can in turn be corrected using capacitor bank installations, or similar, as will be appreciated by persons skilled in the art. This is particularly beneficial, as the ability to analyse power factor across multiple machines is normally difficult and generally requires an in depth analysis that involves disconnecting machines from the power supply, which in turn is highly disruptive.

[0121] In a similar manner, this can also be used in order to monitor power usage across one or more machines, for example to understand power consumption within a facility. This can in turn be analysed and used in order to optimise power usage, for example to selectively control machines in order to control peak loads, reduce power consumption, or the like.

[0122] Additionally and/or alternatively, monitoring the current supply to a machine can be used to derive parameters regarding machine operation. For example, examining power fluctuations, such as fluctuations in phase, or DC voltage or current magnitude, as a result of power drawn by a motor, can be used to derive information regarding the operation of the motor, including, but not limited to calculating a motor speed and/or torque. It will therefore be appreciated that the system can be used to monitor machines in order to determine details regarding operation of the machine, to identify faults in the machine and/or power supply,

[0123] The power monitoring device can include a power supply, which could be in the form of a battery or the like. In one example, first and second power supplies can be provided, with one operating to power to the sensors/processing device/transmitter in normal use and another acting to provide ancillary power, for example to power volatile memory in the event of failure of the first power supply. However, this is not essential and any suitable arrangement could be used.

[0124] In a further example, the power supply can be adapted to generate power based on available ambient sources. For example, the power supply could include solar panels adapted to generate electricity from ambient solar radiation, or could be adapted to scavenge power from the power cable, for example, using a coil to generate power using electrical current within the power cable, using this to power the monitoring device and/or charge the battery is needed.

[0125] In one example, the power monitoring device is configured to periodically perform measurements. Thus, rather than monitoring the current continuously, this could be performed at periodic intervals, for example to monitor the power for ten seconds every one or two minutes. Using a measurement strategy of this form typically allows sufficient sensor data to be collected to identify any issues, whilst significantly reducing power usage of the monitoring device, which can in turn reduce power supply requirements.

[0126] In a further example, the power monitoring device processor can be configured to control a measurement frequency or extent in accordance with the current sensor signals. This allows the amount of measurements performed to be controlled based on power usage by the machine. For example, if the machine is switched off, or in a standby mode, little power would be used and power monitoring is of little value. In this instance, the power monitoring device can enter a sleep or other low power mode, in which a reduced number of measurements are performed, so that power monitoring is performed for a shorter time period and/or less frequently, to thereby reduce power usage. Conversely, when the machine commences operation, the power monitoring device processor can be configured to increase the frequency and/or duration of readings performed, allowing more accurate information to be collected.

[0127] As part of this process, the power monitoring device processor can be configured to detect activation of the machine in accordance with the current sensor signals, for example by detecting when current sensor signals reflect the power usage increasing to more than a threshold amount. In this instance, this can be used to control a measurement frequency or extent. Additionally and/or alternatively, this can be used to generate a machine activation indication, which can in turn be used to control other actions or equipment.

[0128] In this regard, in one example, the monitoring system includes a vibration monitoring device that includes a vibration sensor that senses vibration transmitted from the machine and wherein the one or more processing systems analyse sensor data from the vibration sensor to determine a machine status. In one example, the vibration monitoring device magnetically attaches to the machine, which allows the vibration monitoring device to be easily and rapidly installed, without unduly effecting machine operation.

[0129] In one example, the vibration monitoring device includes a housing, a coupling that physically attaches the housing to the machine, a plurality of sensors, the plurality of sensors including a vibration sensor that senses vibration transmitted from the machine to the vibration sensor at least in part via the coupling, and a vibration monitoring device processor that acquires sensors signals from the plurality of sensors and generates sensor data at least partially in accordance with signals from the sensors. A vibration monitoring device transmitter is provided that transmits the sensor data, for example to the processing system 130.

[0130] The monitoring device can include a plurality of sensors, including any one or more of a noise sensor, an acoustic sensor, a temperature sensor, a pressure sensor, a humidity sensor, a movement sensor and an optical sensor. It will be appreciated from this that a range of different parameters regarding machine operation can be monitored depending on the preferred implementation. The sensors can also be adapted to ensure integrity of the monitoring device, as will be described in more detail below.

[0131] Examples of such vibration monitoring devices are described in co-pending application WO2018/119489, the contents of which are incorporated herein by cross reference.

[0132] In one example, vibration and current monitoring devices can be used in conjunction to monitor a single machine. In this example, the current and vibration monitoring devices can be provided in master/slave or other similar arrangements, allowing these to controlled collectively. For example, the vibration monitoring device could be controlled based on current sensor signals from the current sensors and/or using a machine activation indication, allowing the vibration monitoring device to be woken from a sleep or other low powered state by the power monitoring device, when the machine is activated. It will be appreciated that the opposite approach could alternatively be used, for example to wake the power monitoring device when machine vibrations are detected by the vibration monitoring device.

[0133] In another example, the power monitoring device transmits the sensor data to the vibration monitoring device, allowing the vibration monitoring device to transmit the sensor data to the processing system. This allows the sensor data to be transmitted collectively from the vibration monitoring device, reducing transmission requirements for the power monitoring device. Again, it will be appreciated that a converse arrangement, in which sensor data is transmitted from the vibration monitoring to the power monitoring device could be used, although in general as the vibration monitoring device collects data from a broader range of sensors, this is generally not preferred.

[0134] Whilst the vibration and/or power monitoring devices can communicate directly with the processing system, for example via mobile phone networks, or the like, this is not essential and indirect communication could be used. In one example, the system includes at least one hub that receives sensor data from a plurality of monitoring devices, optionally including both power and vibration monitoring devices, and then transfers the sensor data to the one or more processing devices 130 via a communications network. This allows a number of monitoring devices to be provided in a given location, such as a respective building, with these communicating with a single central hub via short range communications protocols such as Bluetooth, Wi-Fi, or the like, or other longer range wireless communications protocols. The hub can then provide onward connectivity to a communications network, for example via a GPRS or other cellular communications protocol. This allows a number of devices to be provided in a location remote from the processing systems, but without requiring the ability to communication directly with the processing systems themselves, which may require more energy intensive communications, which in turn can reduce battery life. [0135] The sensor data transmitted by the monitoring device can include signals from sensors, or one or more parameters derived from signals from the sensors, such as signal magnitudes, frequencies or the like. In this regard, the monitoring device can be adapted to partially process the sensor signals, for example by filtering, digitising or parameterising the sensor signals. Thus, the power monitoring device can at least partially process current sensor signals, whilst the vibration monitoring device can partially process vibration or other sensor data.

[0136] The sensor data also typically includes a monitoring device identifier, allowing the processing system(s) to identify the monitoring device from which sensor data has been received. By associating each monitoring device with a respective piece of machine, this in turn allowing the processing system(s) to determine the machine to which the sensor data relates.

[0137] Analysis of the sensor data will now be discussed in more detail. For the purpose of ease of illustration, the following section of the document will make reference to a monitoring device, which could include a power monitoring device and/or a vibration monitoring device. It will therefore be appreciated that the term monitoring device could include either a power monitoring device or a vibration monitoring device, with the corresponding sensor data being derived from the respective on-board sensors, such as the current and/or vibration sensors.

[0138] Analysis of the sensor signals is typically achieved by comparing the sensor signals to reference behaviour of the machine, which is usually at least partially indicative of normal operation of the machine. In this regard, as each piece of machine typically behaves in a unique way, depending on the configuration of the machine and the manner in which it is used, the system typically uses signals from sensors during a first time period to establish reference behaviour, then using signals from the sensors outside this first time period, together with the reference behaviour, to determine a machine status. Thus, current drawn by the machine is compared to reference current drawn, allowing differences or similarities to be used to determine a machine status. [0139] Thus, this approach allows normal behaviour for the machine to be monitored, allowing this to be used in establishing reference behaviour. The system can then analyse current operation of the machine by comparing signals from the one or more sensors to signals collected while the machine is operating normally in order to assess the current operational status of the machine. Deviation of the sensor signals from those collected during the first time period can be indicative of abnormal behaviour, which is in turn indicative of a potential problem. For example, if the measured current does not exceed certain threshold values during the first time period, but does exceed these threshold values during monitored operation, this could be indicative of a problem that requires maintenance or additional investigation.

[0140] This approach of analysing machine during a reference time period and using this to establish reference behaviour allows monitoring of machines to be performed with no prior knowledge of the particular machine which is being monitored. In particular, this avoids the need to perform a complex analysis of machine operation to understand machine behaviour, instead establishing sensor readings associated with reference behaviour and then analysing current sensor readings to identify deviations from the reference behaviour.

[0141] In one example, this analysis is performed by generating reference data indicative of the reference behaviour, and then determining a machine status at least in part based on the reference data and signals from the one or more sensors, for example by generating operational data using signals from the one or more sensors and then comparing this to the reference data.

[0142] Whilst reference and operational data in the form of sensor signals can be compared directly, more typically signals from one or more sensors are used to determine parameters indicative of machine operation with the parameters being used to determine the machine status. The parameters can include any one or more of a current frequency, a cycle time, a power factor, a power draw, a phase difference between different phases, a power utilization or a power efficiency. This can also be combined with parameters derived from the vibration monitoring device, which could include any one or more of noise level, noise frequency, a temperature, a temperature change, a rate of temperature change, a vibration frequency, a vibration magnitude, a vibration pattern, a vibration change and a rate of vibration change.

[0143] It will be appreciated that other parameters could be determined depending upon the nature of the machine and the preferred implementation. It will also be appreciated that collecting additional parameters allows a multi-parametric analysis to be performed, which increasing the ability to detect abnormal conditions.

[0144] Additionally and/or alternatively, the reference and/or operational data could be based on patterns derived from signals from the one or more sensors, for example examining particular sequences of signal or parameter values. For example a particular sequence of power fluctuations might occur during pump start-up, so presence of that pattern in signals being analysed indicates that the pump is starting up. It should be noted in this regard that the system does not need to understand that this pattern of signals means the pump is starting up, but merely needs to identify that this is normal behaviour, and hence that the pump is operating correctly when the pattern is detected.

[0145] Additionally, the reference data could include thresholds or reference ranges derived from the signals from the one or more sensors, for example based on average and standard deviation ranges of signals measured during the reference time period. This can be used to define absolute values of sensor readings that are expected in normal use, so that readings exceeding these values are indicative of abnormal behaviour.

[0146] In a preferred example, the system assesses the machine status at least in part using machine learning techniques. This is particularly beneficial as this allows the system to learn different operational behaviours of the machine over time, which in turn allows the monitoring system to be used with a wide range of different types of machine, without undergoing a separate analysis of the machine to assess possible failure modes.

[0147] Whilst any form of machine learning techniques could be used, in one example, the system uses machine learning techniques to identify at least one category of behaviour for the machine from the reference behaviour and then determines the machine status by analysing signals from the one or more sensors to categorize a current behaviour based on the at least one category. For example, the machine learning technique could identify signal ranges or patterns corresponding to normal behaviour. If the measured signals then deviate from these ranges or patterns, this allows operation to be classified as abnormal. In one example, a degree of deviation of the signals could be used to define a degree of any issues. For example, if sensor readings fall within a single standard deviation of normal values, this could indicate minor problems, whereas signals beyond a single standard deviation could indicate more serious problems. Similarly, by defining multiple categories, this in turn allows multiple different classifications to be established, such as a range extending from "healthy" to "moderate" and then to "serious".

[0148] It will be appreciated that the machine learning process can be aided by feedback from users. For example, if an event is classified as a serious problem, and it is later confirmed that this was in fact normal operation, this information can be fed back into the machine learning process, allowing the system to reclassify behaviours and more accurately identify issues moving forward.

[0149] In one example, the system can be adapted to compare reference and operational data determined during corresponding time intervals during which the machine is expected to exhibit similar behaviour. For example, a pump in a pumping facility may be adapted to operate at different pumping levels during different times of the day, for example starting up at 7am, operating at an intermediate capacity until midday and then operating at maximum capacity until 5pm. Accordingly, the machine learning approach can identify these patterns and then analyse reference and operational data at similar times of the day to ensure that operational data is compared to reference data collected when the pump is exhibiting similar behaviours.

[0150] Thus, machine learning techniques can be used to establish models that are unique to each machine, and which may additionally be unique to particular operating conditions or time periods, so that different models can be selected based on current operation of the machine.

[0151] In one example, sensor data can be used to derive metrics, such as different power usage parameters, or the like, which are then applied to the relevant model, which embodies a relationship between a machine status and one or more metric, allowing the machine status to determined. In this example, the computational model is obtained by applying machine learning to reference metrics derived from sensor data measured for the machine during the first time period.

[0152] In addition to monitoring a current operational status, the system can also be adapted to perform longitudinal monitoring, in which changes in machine status over time are examined to determine a rate of change of operational state. An indication of this can then be stored as part of machine status data associated with respective machine and/or displayed to a user. This allows a user to assess not only a current status, but how the status is changing over time, for example to assess if changes are rapid or slow, in turn allowing the user to determine a likely point of failure and how urgent is the need for maintenance.

[0153] In addition to comparing data collected during a first time period with operational data collected during second time period, the sensor can also undergo a calibration process. In this example, calibration data can be established while the monitoring device is attached to calibration equipment. The calibration data can then be used to interpret signals from the sensor when the monitoring device is attached to the machine. In this example, when sensor data is to be analysed it is typical to determine an identifier of the monitoring device, use the identifier to retrieve calibration data and then analyse the sensor data at least in part using the calibration data. Whilst it will be appreciated that calibration is not strictly required if the same monitoring device is used on the same machine at all times, the use of calibration data can assist in allowing reference data established using one monitoring device to be utilised in analysing signals from a second different monitoring device for example if the first fails. This can also assist in counting for variations such as to account for sensor drift or the like.

[0154] In addition to, or as an alternative to calibrating the monitoring device during a calibration process, ongoing calibration can be performed, for example by comparing the output of similar sensors. In this regard, outputs from the multiple current sensors could be compared, with this being used to correct for sensor drift.

[0155] In addition to monitoring the machine, the system can also be adapted to monitor the monitoring device and in particular determine a monitoring device integrity. In this regard, the integrity could include a physical integrity of the monitoring device, for example to determine if the monitoring device housing has been breached, or examining if the monitoring device has been moved, which could in turn impact on the parameters sensed by the monitoring device. In this instance, the system can be adapted to selectively generate an alert if the integrity of the monitoring device has been affected, alerting users to the fact that the monitoring device requires checking and that in the intervening time, sensor data from the monitoring device may not be accurate.

[0156] A variety of different mechanisms can be used to verify the monitoring device integrity. Analysing signals from a humidity sensor can be used to determine changes in humidity within the housing, which can indicate if the housing has been breached or if the seal has failed. For example, a rapid change in humidity is likely to indicate the housing has been opened, whilst a slow change could indicate the seal has failed. To assist with this determination, the housing can contain a desiccant to ensure humidity in the housing is minimised and hence constant when the housing is sealed.

[0157] Similarly, the system can be adapted to analyse signals from a light sensor to determine changes in light levels within the housing, using changes in light levels to determine if the housing has been opened. It will be appreciated that these indications can be analysed in conjunction, for example, if the humidity increases but the light levels remain the same it is likely that the seal has failed but the housing itself has not been opened.

[0158] The system can also determine if the monitoring device has been moved by analysing signals from a movement sensor to identify a movement of or a change in orientation of the monitoring device. Similarly, analysing signals from a microphone could be used to determine a change in noise levels, in turn signify the monitoring device has been moved, whilst a wireless network signal strength could be used to determine a change in position of the transmitter relative to a receiver.

[0159] A more specific example will now be described with reference to Figures 3 to 6.

[0160] In this example, as shown in Figure 3, the system 300 includes one or more power monitoring devices 310.1, 310.2, each of which is broadly similar to the power monitoring device 110 described above, and includes a power monitoring device processor 311, power monitoring device transmitter 312, current sensors 313 and a power monitoring device power supply 314. In this example, the system 300 includes one or more vibration monitoring devices 350, each of which includes a vibration monitoring device processor 351, vibration monitoring device transmitter 352, vibration and/or other sensors 353 and a vibration monitoring device power supply 354, and which is broadly similar to the vibration monitoring devices described in WO2018/119489.

[0161] The system includes a hub 340, which is adapted to route sensor data from one or more of the monitoring devices 310 to a communications network 370. In this example, the power monitoring device 310.1 is connected directly to the hub, whereas the power monitoring device 310.2 is connected via the vibration monitoring device 350, which acts to forward current sensor data to the hub 340.

[0162] The hub can be of any appropriate form, but in one example includes a hub processor 341 and first and second interfaces 342, 343. The hub may also include additional components, such as memory, power supplies or the like, as will be appreciated by persons skilled in the art.

[0163] In this example, the first interface 342 is typically adapted to provide short range communications, allowing communication with one or more of the monitoring devices 310, and may include one or more Bluetooth transmitter/receiver chips, or the like. The second interface 343 is a network interface, for providing onward connectivity to one or more communications networks 370 and in one example can include a cellular communications interface, such as an integrated cellular dongle with an installed SIM card.

[0164] In use, the hub processor 341 executes instructions in the form of applications software stored in memory to allow the required processes, and in particular routing of sensor data, to be performed. Whilst the hub processor 341 can be a standard microprocessor, such as an Intel Architecture based microprocessor, this is not essential and any suitable arrangement, such as microchip processor, logic gate configuration, firmware optionally associated with implementing logic such as an FPGA (Field Programmable Gate Array), or any other electronic device, system or arrangement, could be used. [0165] Additionally, a number of processing systems 330 are provided coupled to one or more client devices 360, via the one or more communications networks 370, such as the Internet, and/or a number of local area networks (LANs), or the like.

[0166] Any number of monitoring devices 310, hubs 340, processing systems 330 and client devices 360 could be provided, and the current representation is for the purpose of illustration only. The configuration of the networks 370 is also for the purpose of example only, and in practice the hub 340, processing systems 330 and client devices 360 can communicate via any appropriate mechanism, such as via wired or wireless connections, including, but not limited to mobile networks, private networks, such as an 802.11 networks, the Internet, LANs, WANs, or the like, as well as via direct or point-to-point connections, such as Bluetooth, or the like.

[0167] In this example, the processing systems 330 are adapted to analyse sensor data from the monitoring devices 310, and determine a machine status, providing access to the machine status and/or sensor data, allowing this to be displayed via the client devices 360. Whilst the processing systems 330 are shown as single entities, it will be appreciated they could include a number of processing systems distributed over a number of geographically separate locations, for example as part of a cloud based environment. Thus, the above described arrangements are not essential and other suitable configurations could be used.

[0168] An example of a suitable processing system 330 is shown in Figure 4. In this example, the processing system 330 includes at least one microprocessor 400, a memory 401, an optional input/output device 402, such as a keyboard and/or display, and an external interface 403, interconnected via a bus 404 as shown. In this example the external interface 403 can be utilised for connecting the processing system 330 to peripheral devices, such as the communications networks 370, databases 411, other storage devices, or the like. Although a single external interface 403 is shown, this is for the purpose of example only, and in practice multiple interfaces using various methods (e.g. Ethernet, serial, USB, wireless or the like) may be provided.

[0169] In use, the microprocessor 400 executes instructions in the form of applications software stored in the memory 401 to allow the required processes to be performed. The applications software may include one or more software modules, and may be executed in a suitable execution environment, such as an operating system environment, or the like.

[0170] Accordingly, it will be appreciated that the processing system 330 may be formed from any suitable processing system, such as a suitably programmed PC, web server, network server, or the like. In one particular example, the processing system 330 is a standard processing system such as an Intel Architecture based processing system, which executes software applications stored on non-volatile (e.g., hard disk) storage, although this is not essential. However, it will also be understood that the processing system could be any electronic processing device such as a microprocessor, microchip processor, logic gate configuration, firmware optionally associated with implementing logic such as an FPGA (Field Programmable Gate Array), or any other electronic device, system or arrangement.

[0171] As shown in Figure 5, in one example, the client device 360 includes at least one microprocessor 500, a memory 501, an input/output device 502, such as a keyboard and/or display, an external interface 503, and typically a card reader 504, interconnected via a bus 505 as shown. In this example the external interface 503 can be utilised for connecting the client device 360 to peripheral devices, such as the communications networks 370, databases, other storage devices, or the like. Although a single external interface 503 is shown, this is for the purpose of example only, and in practice multiple interfaces using various methods (e.g. Ethernet, serial, USB, wireless or the like) may be provided.

[0172] In use, the microprocessor 500 executes instructions in the form of applications software stored in the memory 501, and to allow communication with one of the processing systems 330.

[0173] Accordingly, it will be appreciated that the client device 360 be formed from any suitably programmed processing system and could include suitably programmed PCs, Internet terminal, laptop, or hand-held PC, a tablet, a smart phone, or the like. However, it will also be understood that the client device 360 can be any electronic processing device such as a microprocessor, microchip processor, logic gate configuration, firmware optionally associated with implementing logic such as an FPGA (Field Programmable Gate Array), or any other electronic device, system or arrangement. [0174] A specific example of a power monitoring device 310 will now be described with reference to Figures 6 A to 6D.

[0175] In this example, the housing 620 includes first and second housings 620.1, 620.2, connected via a pivoting connector 620.5, at one corner, allowing the housings to move between open and closed positions, shown in Figures 6C and 6D, respectively. On an inner face of the housings, 620.1, 620.2 proximate an opposing end to the pivoting connector 620.5, semi-circular openings are provided, which align to form a generally circular opening 621 when the housings 620.1, 620.2 are in the closed position. The housings include tabs 620.3, 620.4, which can be used with a locking member, such as a catch, lock, or the like, to secure the housings 620.1, 620.2 in the closed position.

[0176] A number of resilient deformable fingers 622 extend axially outwardly, and radially inwardly, from a perimeter of the opening 621, so that the fingers engage the power cable 601, and thereby retain the power cable centrally within the opening 621.

[0177] Each housing 620.1, 620.2 contains a circuit board, and an example for the housing 620.2 is shown in Figure 6B. The circuit board is shaped to conform with the shape of the housing 620.2, and includes a number of sensors 613 spaced around a semi-circular cut-out, so that the sensors 613 are circumferentially spaced around the opening 621 in use, as shown in Figure 6D. The circuit board also incorporates a processor 611 and transceiver 612, such as a Bluetooth SoC (System on a Chip), as well as optional connectors 615, 616, which can be used to provide external power and/or data connections as needed.

[0178] Example processes performed by the monitoring a machine will now be described in further detail.

[0179] For the purpose of these examples it is assumed that one or more respective processing systems 330 are servers. In one example, the servers 330 host machine monitoring services that are accessed by the client devices 360 allowing machine to be monitored remotely. The servers 330 typically execute software, allowing relevant actions to be performed, with actions performed by the server 330 being performed by the processor 400 in accordance with instructions stored as applications software in the memory 401 and/or input commands received from a user via the I/O device 402. It will also be assumed that actions performed by the client devices 360, are performed by the processor 500 in accordance with instructions stored as applications software in the memory 501 and/or input commands received from a user via the I/O device 502.

[0180] For the purpose of ease of illustration, reference will generally be made to sensor data, and it will be appreciated that this will include current sensor data collected from current sensors in the power monitoring device 310, and may optionally also include vibration or other sensor data collected using a vibration monitoring device 350.

[0181] However, it will be appreciated that the above described configuration assumed for the purpose of the following examples is not essential, and numerous other configurations may be used. It will also be appreciated that the partitioning of functionality between the different processing systems may vary, depending on the particular implementation.

[0182] An example of a process for monitoring a machine will now be described with reference to Figures 7A and 7B.

[0183] In this example, signals are acquired from the sensors, including at least the current sensors, and optionally other sensors, such as vibrations sensors at step 700, with these optionally undergoing preliminary processing on board the monitoring device at step 705. The preliminary processing may be of any appropriate form, depending on the nature of the signals generated by the sensors. For example, this could include digitisation of analogue sensor signals achieved using a dedicated analogue to digital convertor, and optionally filtering, amplification, or the like. This can also include performing a frequency transformation, such as a fast Fourier transform, to convert time series information into the frequency domain, which can reduce the volume of data, whilst retaining the necessary meaningful data for analysis. These can be achieved utilising known techniques and will not be described in further detail.

[0184] At step 710 the power monitoring device processor 311 generates current sensor data, with the vibration monitoring device processor 311 optionally generating other sensor data, as needed. The sensor data can be of any appropriate form and typically includes an indication of a monitoring device identifier and information derived from the current sensor signals. In one example, the sensor data is in the form of data packets including a data packet header containing the identifier, and a payload indicative of the sensor signals, or parameters derived therefrom. The payload data can include raw digitised sensor signals or values derived therefrom, such as parameters, frequency domain information, or the like. Typically only limited processing is performed on board the monitoring device in order to reduce processing and power requirements, but it will be appreciated that this may not always be the case and indeed additional analysis may be performed in order to reduce the amount of sensor data that needs to be transmitted to the server 330. The data packets may also include other relevant information, such as a time or date of capture of the data.

[0185] At step 715 sensor data is transmitted to the hub 340, which routes the sensor data from multiple power monitoring devices 310 and optionally vibration monitoring devices 350, to the server 330 at step 720. It will be appreciated that these steps are performed periodically, and optionally substantially continuously, depending on monitoring requirements, data transmission bandwidths, or the like.

[0186] At step 725, for each data packet, the server 330 determines the device identifier associated with the received sensor data. This allows the server 330 to identify the machine to which the sensor data relates, as each machine is associated with a respective monitoring device 310 during an initial set-up phase. In this regard, when the power monitoring device 310 is initially attached to a power cable extending to a machine, an installer can record an indication of the power monitoring device and the machine, with this being used to establish a machine profile.

[0187] The machine profile can include basic information regarding the machine, such as an indication of a machine type, identification information such as a name, serial number, or the like, a location and an indication of one or more entities responsible for the machine, such as a machine owner or operator, maintenance personnel, or the like. The machine profile also typically includes reference data associated with the machine, as monitored by the respective power monitoring device 310 and optionally vibration monitoring device 350. The reference data can include sensor data collected during a reference time period, or information derived therefrom, such as defined ranges or thresholds of different sensor readings that correspond to normal and/or abnormal operation of the machines, as will be described in more detail below. The reference data can include different sets of reference data established during different time periods, for example to account different operation of the machine at different times of the day or week.

[0188] At step 730 the server 330 retrieves the relevant reference data, optionally taking into account the time of capture of the sensor data, using this to analyse the sensor data at step 735 to determine a machine status at step 740. The nature of the analysis will vary depending on the preferred implementation and the nature of the reference data, but could include comparison to either the reference data or reference ranges derived therefrom. In another example, the reference behaviour is in the form of a computational model derived using metrics derived from sensor data collected during the first reference time period. In this instance, metrics derived from the sensor data are applied to the computational model to determine the machine status.

[0189] As part of this process, a check can be performed to determine whether the monitoring device has moved or its integrity has been in any way affected. Specific examples of the analysis will be described in more detail below, sufficed to say that upon completion of the analysis an indication of an operational status of the machine and optionally the monitoring device 310 is determined.

[0190] If a machine status is abnormal or if the power monitoring device has moved or been damaged, the server 330 might determine an alert is required at step 750. In this case, at step 755, the server 330 generates a notification which can be transferred to a client device 360 at step 760. This could include, for example, sending a text message, email or other suitable notification to a client device in accordance with contact information provided in the respective machine profile.

[0191] Otherwise sensor data and the results of the associated analysis can be stored at step 765, allowing this to be subsequently retrieved by a user using a client device 360. For example, in this instance a user may use the client device 360 to access the server 330 and request information relating to one or more assets, in which case a representation is typically generated at step 770 and displayed to the user using the client device at step 775. In this regard, it will be appreciated that the representation could be generated by the server 330 and displayed on the client device 360, for example as part of a web page or the like, or alternatively data could be transferred to the client device 360, allowing the representation to be generated locally.

[0192] In either case, the representation can be used to provide information regarding one or more assets to the user, with the user then interacting with the representation to allow further information to be displayed in an interactive manner.

[0193] Example representations are shown in Figures 8A and 8B respectively.

[0194] In the example of Figure 8A a user interface 800 is presented including a map 810, having a number of icons 811 showing the location of respective assets. The icons can be encoded to show a current asset status, for example using colours such green, amber and red to signify if the machine operation is normal, marginal, or failed or failing. The user can then interact with the representation, for example selecting a respective asset, allowing them to view further information regarding the respective asset.

[0195] In the example of Figure 8B the status of a particular asset is shown. In this example, the user interface includes a condition indication 821 and a rate of change indication 822. The condition indication indicates whether the machine is healthy or not on a graduated scale, from "healthy" to "serious". The rate of change indicates a rate of change of the condition, for example to show how quickly the condition is progressing from "healthy" to "serious". This can be used by operators to determine not only the current machine condition but also how quickly this is changing allowing operators to assess a likely time of failure, or how quickly maintenance might be required.

[0196] Additionally, the user interface 800 displays windows 831, 832, which include graphs 833, 834 showing different parameters derived from the sensor data. Each of these graphs typically includes zones 833.1, 833.2, 833.3, 834.1, 834.2, 834.3, indicating whether the respective readings exceed particular defined thresholds derived from the reference data, which are in turn indicative of whether the temperature or vibration readings are indicative of a "healthy", "moderate" or "serious" condition. Historical readings can also be selected and viewed using a respective slider 835, 836.

[0197] It will be appreciated from this that the client device 360 and server 330 cooperate to display a user interface, allowing the user to be presented with a graphical representation of status information relating to one or more assets. The user interface provides a dashboard allowing users to obtain an overview of multiple assets, and then select individual assets to review further detail, including in depth status information and representations of sensor signals.

[0198] An example of the process for generating reference data will now be described with reference to Figure 9.

[0199] In particular, current sensor data (and optionally other data) is received at step 900 with this being combined with historical reference sensor data that has already been collected at step 905. The historical and current data is then analysed to determine one or more periodic patterns at step 910, for example to identify time periods when the machine is operating in a particular manner. This is used to account for the fact that the power usage will be inherently different if the machine is operating at half power as opposed to full power, for example. This is then used to segment the data into time periods where the machine is operating in a consistent manner at step 915.

[0200] At step 920, the reference sensor data within different time periods is analysed to determine metrics, such as particular parameters, including maximum, minimum or average sensor readings, rates of change of sensor readings, or the like. The particular parameters that are determined will vary depending on the nature of the sensor data and the preferred implementation. These values can then be used to define reference ranges at step 925, with the reference ranges corresponding to ranges of sensor readings where the machine is operating in a "healthy", "moderate" or "serious" condition. In this regard, information regarding the health state of the machine might need to be confirmed, with this being used as part of an analysis process in order to define boundaries of respective machine health states. [0201] It will be appreciated that the above described processes can be performed using machine learning techniques, so that by monitoring ongoing operation of the machine, the server 330 can learn to recognise patterns of sensor readings that correspond to respective health states, allowing these states to be subsequently identified. In the event that feedback is provided regarding a health state, the server 330 can then modify the reference boundaries as required in order to ensure a determined status is correct in future. In this regard, it will be appreciated that a wide range of different machine learning techniques could be used.

[0202] Reference data embodying these reference ranges can then be stored as part of the profile associated with the respective machine at step 925.

[0203] Alternatively, as previously mentioned, the metrics can be used in a machine learning process. In this example, a combination of reference metrics obtained from sensor data collected during the first time period is used together with one or more generic computational models to perform model training. The nature of the model and the training performed can be of any appropriate form and could include any one or more of decision tree learning, random forest, logistic regression, association rule learning, artificial neural networks, deep learning, inductive logic programming, support vector machines, clustering, Bayesian networks, reinforcement learning, representation learning, similarity and metric learning, genetic algorithms, rule-based machine learning, learning classifier systems, or the like. As such schemes are known, these will not be described in any further detail.

[0204] Whilst a single model might be derived, it will be appreciated that alternatively different models are established for the different time periods, so that the model is reflective of the machine operation during that time period. In any event, once training is completed, the one or more models are stored for further use.

[0205] When analysing signals the process shown in Figure 10 is used. In particular, in this example sensor data is received at step 1000 by the server 330, with this being analysed to determine metrics, such as signal parameters at step 1005. Again the parameters can include maximum or minimum values of sensor readings, rates of change or the like. The current time period, such as the particular time of day is determined at step 1010, allowing equivalent reference ranges and/or models, to be selected at step 1015. At step 1020, the current parameters are then compared to the parameter ranges with this being used to determine a status indication at step 1025. Alternatively, the metrics can be applied to the respective computational model to determine a machine status.

[0206] Whilst the process of generating reference data and analysing signals are shown as discrete processes, it will be appreciated that analysed signals can be used to generate further reference data, allowing ongoing training and hence refinement of the reference ranges to be performed.

[0207] It will be appreciated that this approach allows a wide range of different forms of analysis to be performed. At one level, this can include examining power usage and using this to assess operation of the machine. However, additionally, this can also involve examining humidity and/or light levels within the sensing device housing to establish if the housing has been opened, breached or the seal has otherwise failed. This can also be used to examine movement and/or changes in noise levels, in order to assess whether the monitoring device has been moved.

[0208] Accordingly, the above described system provides a sensor solution for monitoring a machine. The system combines multiple sensing capabilities into a simple, easy-to-install sensing device that can be manufactured at a highly affordable price point. The system can use machine learning and artificial intelligence algorithms to learn about the machine that it is monitoring and in turn predict impending failures.

[0209] By virtue of the fact that the above system uses generic power monitoring devices that can be easily attached to any power supply cable, and that the system uses machine learning to assess when power usage readings, are out of normal operating ranges, this allows the system to be set up and configured with minimal user intervention required. This in turn allows the system to be rapidly and cheaply deployed, allowing this to be offered as a monthly subscription service.

[0210] The system can avoid the need for maintenance staff to manually inspect machines on a regular (typically monthly) basis, which is costly and ineffective, as it often involves staff inspecting machines that may be working perfectly. In Australia this can involve driving large distances to remote and inaccessible locations. This can also result in staff having to access machines in dangerous and unsafe environments. Instead the current system can continously monitor machine and provide alerts before machines need maintenance. Maintenance and operations teams are able to schedule maintenance proactively rather than operating reactively. This improves workplace safety, reduces cost, drives productivity and improves asset availability.

[0211] Thus, current maintenance practices, which involve either running machine to failure or periodic inspections (typically once a month or yearly) can be avoided. Instead providing continuous low cost monitoring avoids the need for inspections, massively reducing maintanence costs. In one example, the system achieves this by monitoring vibration and/or temperature to detect when a machine is degrading towards failure and alert maintenance staff to action. Therefore maintenance activities are targeted towards machinery that requires action, not machines that are working perfectly.

[0212] In one example, access to information regarding multiple assets can be provided via a single user interface acting as a dashboard to provide an overview of operation of individual assets. Information on specific assets can then be reviewed in more depth, allowing decisions regarding maintanence to be made in a predictive rather than reactive fashion.

[0213] The system typically involves a number of components briefly discussed in more detail below.

[0214] The sensing device uses current sensors to generate signals indicative of measured currents in a power cable, which can be passed to a processor for processing. In this regard, the processor can contain an analog to digital convertor, firmware that performs a Fast Fourier Transform (FFT) process on the data, timers that set the data sampling and transmission rate, and a wireless communication device (modem) that allows the data so collected to be uploaded to a local hub via Bluetooth or WiFi protocols. The sensing device can also include custom firmware that optimises battery life by shutting down parts of the sensor hardware except when needed. [0215] The above features enable power monitoring devices to be installed in seconds avoiding the need for disruption to power supply cabling, permits or drilling. The sensing devices can operate on batteries with a 2 year life-span, which can be further extended using energy harvesting arrangements, thereby further reducing the need for sensor maintanence and replacement.

[0216] A hub (which could also be a gateway) is typically used to scan for, and communicate with, multiple sensing devices at a site via Bluetooth or WiFi, or another short range communication protocol. This can be used to store and periodically transmits sensor data securely via a cellular communications network to one or more servers for subsequent analysis.

[0217] The central server system is responsible for the storage, processing, analysis, reporting and display of all of sensor data and resulting status information. Typically the server system performs these functions for a number of different customers, allowing each customer to access information regarding their assets on a custom-built display dashboard. In one example, customers can log into this dashboard and monitor, in near real-time, the temperature and vibration status, and any trend in the value of these parameters, for all their machines. The dashboard will also show the location of the sensors at each site for each customer as a map view, and the status of each machine, and a single page overview of the status of all monitored machines for each customer. Users can‘click through’ the machine shown on the map view or the single page view to see images of each site, each machine and other useful information, such as the machine manufacturer’s nameplate.

[0218] The central server system can also contain machine learning algorithms that are initially set to Team’ the normal operating parameters of each machine via the received sensor data, and then switch to‘operate’ mode where any changes in the normal operation are detected and can trigger alarms. The alarm levels can be set for each parameter of each machine, and will display and email an alarm message to a nominated person for each machine if a parameter on that machine exceeds its alarm level. It will be appreciated however that the use of a central server is only one option, and alternatively other processing arrangements could be used. Whilst there can be discrete learning and operating modes, this is not essential, and in practice, the system will typically undergo a training period and then gradually tranisition to an ongoing monitoring phase. As this occurs, and optionally on an ongoing basis, feedback can be provided, with this being used for ongoing training of the machine learning algorithms. For example, if the algorithm identifies an issue with operation of a machine, manual inspection of the machine can be performed, with this being used to verify whether or not an issue exists, allowing further machine learning to be performed.

[0219] In any event, the ability to use machine learning analytic algorithms to analyse signals from the sensing devices enables the system to‘auto-learn’ the behaviour of the machine being monitored, thereby reducing the need for human experts to calibrate or customise. This simplifies the process for a much broader scale adoption over existing competitors products which require calibration, expert installation and complete software configuration.

[0220] The centralised process also allows the data to be hosted and presented via an intuitive visual interface, meaning users can use the system with little or no training. This also allows maintenance teams to be productive immediately, without the need for hours or days of training.

[0221] Additionally, in one example, the client device could be adapted to assist users during an installation process, for example by displaying information guiding the customers to self install the sensors and gateways via a guided process, that also configures the central system with information about the customer, site and machines being monitored that will appear on the dashboard when the customer’s users log in.

[0222] Nevertheless, as previously mentioned, it will be appreciated that the power monitoring device could be used for applications other than machine monitoring. In this case, the power monitoring device 110 would typically include the housing 120, having the opening 121 configured to receive a power cable 101, as previously described. The power monitoring device 110 includes current sensors 113, such as Hall effect, MEMS or magnetic field detector integrated circuit sensors spaced around the opening to measure an electrical current within the power cable. [0223] The monitoring device 110 also typically includes a monitoring device processor 111, as well as an optional power supply 114, allowing the monitoring device to monitor the sensors and generate the sensor data. The system can include a transmitter 112 to allow the sensor data to be transferred to a processing system 130 for subsequent analysis.

[0224] Additionally and/or alternatively, the monitoring device processor 111 can perform analysis on board, allowing one or more parameters to be calculated, and therefore allowing monitoring to be performed without requiring a processing system 130. In one example, this could involve calculating a parameter, such as a current frequency, a cycle time, a power factor, a power draw, a phase difference between different phases, a power utilization, a power efficiency, or the like. The power monitoring device can then include a display, allowing this information to be displayed, although this could alternatively be transmitted to a processing system 130 if required.

[0225] In a further example, the monitoring device processor 111 can perform additional analysis, such as comparing the parameter to a define threshold, such as a desired operating range stored in a memory, allowing a notification to provided, for example if the parameter falls outside the desired operating range. Such a notification could be provided via an output on board the power monitoring device, for example to provide a visual or audible indication via a respective visual or audible output, such as an LED and/or speaker. Alternatively, results of the analysis could be transmitted to a remote processing system allowing a user to be alerted.

[0226] It will therefore be appreciated that the power monitoring device can be used independently of a machine monitoring system to otherwise monitor supplied power.

[0227] As in the previous example, the power monitoring device can include a housing having first and second housing sections pivotally coupled to allow the housing sections to be moved between an open position in which the power cable can be positioned in the opening and a closed position in which the power cable is enclosed within the opening. In this case, current sensors and circuit boards are typically provided in each of the first and second housing sections. Resilient members can be provided around the opening to locate the power cable within the opening. [0228] The current sensors can be circumferentially spaced around the opening, which in turn can be used to allow effective monitoring of current in multi-core cables including a plurality of conductors, for example, to analyse the sensor data to determine a respective electrical current in each of the conductors. This can be used to allow a multi-phase power supply to be monitored.

[0229] The above described system can be used in wide range of different applications. Such applications include, but are not limited to monitoring operation of machines, power supply equipment, or the like. The system can be used for tracking faults, for example to identify when a machine and/or power supply is functioning incorrectly, monitoring operational parameters of machines, for example to determine a motor or pump speed, analyzing power usage within a facility, for example to monitor power consumption, power factors, efficiency, peak loads, or the like. This allows the system to be used both in monitoring to identify machine faults or potential degradation, as well as allowing the system to be used in order to optimize power usage.

[0230] Throughout this specification and claims which follow, unless the context requires otherwise, the word“comprise”, and variations such as“comprises” or“comprising”, will be understood to imply the inclusion of a stated integer or group of integers or steps but not the exclusion of any other integer or group of integers.

[0231] Persons skilled in the art will appreciate that numerous variations and modifications will become apparent. All such variations and modifications which become apparent to persons skilled in the art, should be considered to fall within the spirit and scope that the invention broadly appearing before described.

Claims

THE CLAIMS DEFINING THE INVENTION ARE AS FOLLOWS: 1) A monitoring system for monitoring a machine, the monitoring system including: a) at least one power monitoring device including: i) a housing having an opening configured to receive a power cable; ii) a plurality of current sensors spaced around the opening to measure an electrical current within the power cable; iii) a power monitoring device processor that: (1) acquires current sensor signals from the current sensors; and, (2) generates sensor data at least partially in accordance with the current sensor signals; iv) a power monitoring device transmitter that transmits the sensor data; and, b) one or more processing systems configured to: i) receive the sensor data; ii) analyse the sensor data to determine a power supplied to the machine; and, iii) at least one of:

(1) store an indication of the power supplied as part of machine status data associated with the respective machine;
(2) determine a machine status at least in part using the power supplied to the machine; and,
(3) cause an indication to be displayed of at least one of:

(a) the power supplied to the machine; and,

(b) the machine status.

2) A monitoring system according to claim 1, wherein the housing includes first and second housing sections pivotally coupled to allow the housing sections to be moved between an open position in which the power cable can be positioned in the opening and a closed position in which the power cable is enclosed within the opening.

3) A monitoring system according to claim 2, wherein current sensors are provided in each of the first and second housing sections.

4) A monitoring system according to claim 2 or claim 3, wherein the monitoring system includes first and second circuit boards, each contained in a respective housing portion, and each including at least one current sensor. 5) A monitoring system according to claim 3, wherein the power monitoring device includes at least one of:

a) a respective power monitoring device processor and power monitoring device transmitter for each circuit board; and,

b) a single power monitoring device processor and power monitoring device transmitter that receive signals from current sensors on each circuit board via wired or wireless connections.

6) A monitoring system according to any one of the claims 1 to 5, wherein the housing includes a number of resilient members provided around the opening to locate the power cable within the opening.

7) A monitoring system according to any one of the claims 1 to 6, wherein the sensors include at least one of:

a) Hall effect sensors;

b) current sensing coils;

c) micro electro mechanical current sensors; and,

d) magnetic field detector integrated circuits.

8) A monitoring system according to any one of the claims 1 to 7, wherein the current sensors are circumferentially spaced around the opening.

9) A monitoring system according to any one of the claims 1 to 8, wherein the power cable is a multi-core cable including a plurality of conductors and wherein the sensors are configured to measure an electrical current in multiple ones of the plurality of conductors.

10) A monitoring system according to claim 9 wherein the one or more processing systems are configured to analyse the sensor data to determine a respective electrical current in each of the conductors.

11) A monitoring system according to any one of the claims 1 to 10, wherein the power supply is a multi-phase power supply, and wherein the one or more processing systems are configured to analyse the sensor data to determine a current supplied by each phase.

12) A monitoring system according to any one of the claims 1 to 11, wherein the one or more processing systems are configured to analyse the sensor data to determine at least one of: a) a current frequency;

b) a cycle time; c) a power factor;

d) a power draw;

e) a phase difference between different phases;

f) a power utilization; and,

g) a power efficiency.

13)A monitoring system according to any one of the claims 1 to 12, wherein the power monitoring device includes at least one monitoring device power supply.

14) A monitoring system according to claim 13, wherein the monitoring device power supply includes at least one of:

a) a battery; and,

b) a coil that generates power using electrical current within the power cable.

15)A monitoring system according to any one of the claims 1 to 14, wherein the power monitoring device is configured to measure current signals from the current sensors.

16) A monitoring system according to claim 15, wherein the power monitoring device processor is configured to control a measurement frequency or extent in accordance with the current sensor signals.

17)A monitoring system according to any one of the claims 1 to 16, wherein the power monitoring device processor is configured to detect activation of the machine in accordance with the current sensor signals.

18) A monitoring system according to claim 17, wherein in response to activation of the machine, the power monitoring device processor is configured to:

a) adjust a measurement frequency or extent in response to activation of the machine; and,

b) generate a machine activation indication.

19) A monitoring system according to any one of the claims 1 to 18, wherein the monitoring system includes a vibration monitoring device that includes a vibration sensor that senses vibration transmitted from the machine and wherein the one or more processing systems are configured to analyse sensor data from the vibration sensor to determine a machine status.

20) A monitoring system according to claim 19, wherein the vibration monitoring device magnetically attaches to the machine. 21) A monitoring system according to claim 19 or claim 20, wherein the vibration monitoring device includes:

a) a housing;

b) a coupling that physically attaches the housing to the machine;

c) a plurality of sensors, the plurality of sensors including a vibration sensor that senses vibration transmitted from the machine to the vibration sensor at least in part via the coupling;

d) a vibration monitoring device processor that:

i) acquires sensors signals from the plurality of sensors; and,

ii) generates sensor data at least partially in accordance with signals from the sensors;

e) a vibration monitoring device transmitter that transmits the sensor data.

22) A monitoring system according to any one of the claims 19 to 21, wherein the vibration monitoring device is controlled at least one of:

a) at least in part using current sensor signals from the current sensors; and,

b) using a machine activation indication.

23) A monitoring system according to any one of the claims 19 to 22, wherein the power monitoring device transmits the sensor data to the vibration monitoring device and wherein the vibration monitoring device transmits the sensor data to the one or more processing systems.

24) A monitoring system according to any one of the claims 1 to 23, wherein the system includes at least one hub that:

a) receives sensor data from a plurality of monitoring devices; and,

b) transfers the sensor data to the one or more processing devices via a communications network.

25) A monitoring system according to claim 24, wherein the hub and monitoring devices communicate using a short range wireless communications protocol.

26) A monitoring system according to any one of the claims 1 to 25, wherein the sensor data includes at least one of:

a) a monitoring device identifier;

b) signals from the sensors; and, c) one or more parameters derived from signals from the sensors.

27) A monitoring system according to any one of the claims 1 to 26, wherein the power monitoring device at least partially processes the current sensor signals.

28) A monitoring system according to claim 27, wherein the power monitoring device at least partially processes the current sensor signals by at least one:

a) filtering;

b) amplifying;

c) digitizing; and,

d) parameterizing.

29) A monitoring system according to any one of the claims 1 to 28, wherein the system: a) uses signals from one or more sensors during a first time period to establish reference behavior for the machine; and,

b) uses current sensor signals and the reference behavior to determine a machine status.

30) A monitoring system according to claim 29, wherein the system:

a) uses signals from one or more sensors to generate reference data indicative of the reference behavior, the reference data being indicative of at least one of:

i) current sensor signals;

ii) parameters derived from current sensor signals;

iii) patterns derived from current sensor signals;

iv) reference thresholds derived from the current sensor signals; and,

v) reference ranges derived from the current sensor signals; and,

b) determines a machine status at least in part based on the reference data and current sensor signals.

31) A monitoring system according to claim 30, wherein the system:

a) determines operational data using current sensor signals, the operational data being based on at least one of:

i) current sensor signals;

ii) parameters derived from current sensor signals; and,

iii) patterns derived from current sensor signals; and,

b) compares the operational data to the reference data. 32) A monitoring system according to claim 30 or claim 31, wherein the parameters include at least one of:

a) a current frequency;

b) a cycle time;

c) a power factor;

d) a power draw;

e) a phase difference;

f) a power utilization;

g) a power efficiency;

h) a parameter change; and,

i) a rate of parameter change.

33) A monitoring system according to any one of the claims 29 to 32, wherein the system assesses the machine status at least in part using machine learning techniques.

34) A monitoring system according to claim 33, wherein the system uses machine learning techniques to:

a) identify at least one category of behavior for the machine from the reference behaviour; and,

b) determine the machine status by analyzing current sensor signals to categorize a current behavior based on the at least one category.

35) A monitoring system according to any one of the claims 29 to 34, wherein the system analyses current sensor signals with respect to reference behavior determined during corresponding time intervals during which the machine is expected to exhibit similar behavior.

36) A monitoring system according to any one of the claims 29 to 35, wherein the system: a) monitors changes in machine status over time; and,

b) at least one of:

i) stores an indication of changes in machine status as part of machine status data associated with respective machine;

ii) cause a status indication indicative of the change in machine status to be displayed.

37) A monitoring system according to any one of the claims 1 to 36, wherein the system: a) uses signals from one or more sensors during a calibration time period when the monitoring device is attached to a calibration machine to establish calibration data; and,

b) using the calibration data to interpret signals from the sensors when the monitoring device is attached to the machine.

38)A monitoring system according to claim 37, wherein the one or more processing systems are configured to:

a) determine an identifier of the monitoring device;

b) uses the identifier to retrieve calibration data; and,

c) analyse the sensor data at least in part using the calibration data.

39) A monitoring system according to any one of the claims 1 to 38, wherein the system: a) determines a monitoring device integrity; and,

b) selectively generates an alert depending on results of the determination.

40) A monitoring system according to any one of the claims 1 to 38, wherein the system: a) analyses signals from a humidity sensor to determine changes in humidity within the housing; and,

b) using changes in humidity to determine at least one of:

i) if the housing has been breached; and,

ii) if a housing seal has failed.

41) A monitoring system according to claim 40, wherein the housing contains a desiccant.

42) A monitoring system according to any one of the claims 1 to 41, wherein the system: a) analyses signals from a light sensor to determine changes in light levels within the housing; and,

b) using changes in light levels to determine at least one of:

i) if the housing has been breached; and,

ii) if a housing seal has failed.

43) A monitoring system according to any one of the claims 1 to 42, wherein the system determines if the monitoring device has been moved by:

a) analysing signals from a movement sensor to determine at least one of:

i) movement; and,

ii) a change in orientation; b) analysing signals from a microphone to determine a change in noise levels; and, c) determine a wireless network signal strength to determine a change in position of the transmitter relative to a receiver.

44) A method for monitoring a machine, the method including, in one or more processing systems are configured to:

a) receiving current sensor data from a power monitoring device having an opening configured to receive a power cable, the current sensor data being generated at least in part based on signals from a plurality of current sensors spaced around the opening to measure an electrical current within the power cable;

b) analysing the current sensor data to determine a power supplied to the machine; and, c) at least one of:

i) storing an indication of the power supplied as part of machine status data associated with the respective machine;

ii) determining a machine status at least in part using the power supplied to the machine; and,

iii) causing an indication to be displayed of at least one of:

(1) the power supplied to the machine; and,

(2) the machine status.

45) A method according to claim 44, wherein the method includes:

a) using signals from one or more sensors during a first time period to establish reference behavior for the machine; and,

b) using current sensor signals and the reference behavior to determine a machine status.

46) A method according to claim 45, wherein the method includes:

a) using current sensor signals to generate reference data indicative of reference behavior, the reference data being indicative of at least one of:

i) current sensor signals;

ii) parameters derived from current sensor signals;

iii) patterns derived from current sensor signals;

iv) reference thresholds derived from the current sensor signals; and,

v) reference ranges derived from the current sensor signals; and, b) determining a machine status at least in part based on the reference data and current sensor data.

47) A method according to claim 46, wherein the method includes:

a) determining operational data using current sensor signals, the operational data being based on at least one of:

i) current sensor signals;

ii) parameters derived from current sensor signals; and,

iii) patterns derived from current sensor signals; and,

b) comparing the operational data to the reference data.

48) A method according to claim 46 or claim 47, wherein the parameters include at least one of:

a) a current frequency;

b) a cycle time;

c) a power factor;

d) a power draw;

e) a phase difference between different phases;

f) a power utilization; and,

g) a power efficiency.

49) A method according to any one of the claims 45 to 48, wherein the method includes assessing the machine status at least in part using machine learning techniques.

50) A method according to claim 49, wherein the method includes using machine learning techniques to:

a) identify at least one category of behavior for the machine from the reference behavior; and,

b) determine the machine status by analyzing current sensor signals to categorize a current behavior based on the at least one category.

51) A method according to any one of the claims 45 to 49, wherein the method includes: a) determining at least one metric from the sensor data; and,

b) apply the at least one metric to at least one computational model to determine a machine status, the computational model embodying a relationship between a machine status and one or more metrics. 52) A method according to claim 51, wherein the at least one computational model is obtained by applying machine learning to reference metrics derived from sensor data measured for the machine during the first time period.

53) A method according to any one of the claims 45 to 52, wherein the method includes analysing current sensor signals with respect to reference behavior determined during corresponding time intervals during which the machine is expected to exhibit similar behavior.

54)A method according to any one of the claims 45 to 53, wherein the method includes: a) monitoring changes in machine status over time; and,

b) at least one of:

(1) storing an indication of changes in machine status as part of machine status data associated with respective machine;

(2) causing a status indication indicative of the change in machine status to be displayed.

55) A computer program product for monitoring a machine, the computer program product including computer executable code, which when executed by one or more suitably programmed processing systems, causes the one or more processing systems to:

a) receive current sensor data from a power monitoring device having an opening configured to receive a power cable, the current sensor data being generated at least in part based on signals from a plurality of current sensors spaced around the opening to measure an electrical current within the power cable;

b) analyse the current sensor data to determine a power supplied to the machine; and, c) at least one of:

i) store an indication of the power supplied as part of machine status data associated with the respective machine;

ii) determine a machine status at least in part using the power supplied to the machine; and,

iii) cause an indication to be displayed of at least one of:

(1) the power supplied to the machine; and,

(2) the machine status.

56) A power monitoring device including: a) a housing having an opening configured to receive a power cable;

b) a plurality of current sensors spaced around the opening to measure an electrical current within the power cable;

c) a power monitoring device processor that:

i) acquires current sensor signals from the current sensors; and,

ii) generates sensor data at least partially in accordance with the current sensor signals; and,

d) at least one of:

i) a power monitoring device transmitter that transmits the sensor data; and, ii) a display that displays an indicator derived from the sensor data.

57) A power monitoring device according to claim 56, wherein the housing includes first and second housing sections pivotally coupled to allow the housing sections to be moved between an open position in which the power cable can be positioned in the opening and a closed position in which the power cable is enclosed within the opening.

58)A power monitoring device according to claim 56 or claim 57, wherein current sensors are provided in each of the first and second housing sections.

59)A power monitoring device according to claim 57 or claim 58, wherein the power monitoring device includes first and second circuit boards, each contained in a respective housing portion, and each including at least one current sensor.

60) A power monitoring device according to claim 59, wherein the power monitoring device includes at least one of:

a) a respective power monitoring device processor and power monitoring device transmitter for each circuit board; and,

b) a single power monitoring device processor and power monitoring device transmitter that receive signals from current sensors on each circuit board via wired or wireless connections.

61) A power monitoring device according to any one of the claims 56 to 60, wherein the housing includes a number of resilient members provided around the opening to locate the power cable within the opening.

62) A power monitoring device according to any one of the claims 56 to 61, wherein the sensors include at least one of: a) Hall effect sensors;

b) current sensing coils;

c) micro electro mechanical current sensors; and,

d) magnetic field detector integrated circuits.

63) A power monitoring device according to any one of the claims 56 to 62, wherein the current sensors are circumferentially spaced around the opening.

64) A power monitoring device according to any one of the claims 56 to 63, wherein the power cable is a multi-core cable including a plurality of conductors and wherein the sensors are configured to measure an electrical current in multiple ones of the plurality of conductors.

65) A power monitoring device according to claim 64, wherein the sensor data is analysed to determine a respective electrical current in each of the conductors.

66) A power monitoring device according to any one of the claims 56 to 65, wherein the power supply is a multi-phase power supply, and the sensor data is analysed to determine a current supplied by each phase.

67) A power monitoring device according to any one of the claims 56 to 66, wherein the sensor data is analysed to determine a parameter including at least one of:

a) a current frequency;

b) a cycle time;

c) a power factor;

d) a power draw;

e) a phase difference between different phases;

f) a power utilization; and,

g) a power efficiency.

68) A power monitoring device according to claim 67, wherein the transmitter transmits the sensor data to one or more processing systems configured to analyse the sensor data.

69) A power monitoring device according to claim 67, wherein the power monitoring device processor is configured to analyse the sensor data.

70) A power monitoring device according to any one of the claims 67 to 69, wherein the at least one parameter is compared to a defined threshold, and wherein the power monitoring device generates an indication of the result of the comparison.