GB2595712A

GB2595712A - System for predicting if operation can be performed

Info

Publication number: GB2595712A
Application number: GB2008429.9A
Authority: GB
Inventors: Wilkinson Kevin
Original assignee: Advance Technical Systems Ltd
Current assignee: Advance Technical Systems Ltd
Priority date: 2020-06-04
Filing date: 2020-06-04
Publication date: 2021-12-08
Anticipated expiration: 2040-06-04
Also published as: GB202008429D0; GB2595712B

Abstract

A data processing system 102 on which is implemented a computer implemented prediction function configured to: receive operation parameter data associated with an operation to be performed by an apparatus 101 and apparatus capability data associated with an ability of the apparatus 101 to perform the operation; process the operation parameter data and the apparatus capability data to generate and output completion prediction data 103, said completion prediction data indicative of an estimate of whether the operation can be completed. The apparatus 101 may be a battery powered electrofusion welding system and the apparatus capability data may be indicative of the amount of charge left in the battery.

Description

SYSTEM FOR PREDICTING IF OPERATION CAN BE PERFORMED

Technical Field

The present invention relates to a system for predicting if an operation can be performed to completion.

Background

There are many examples of apparatus that perform operations where it is desirable, or very important, that operations that the apparatus performs, are performed, without interruption, to completion. That is, it is desirable, or very important, that once the apparatus has commenced the operation, the operation must be performed to completion.

One such example is electrofusion welding. Electrofusion welding is a well-known 15 welding technique for joining sections of pipes. Two pipe ends are brought together by being inserted in either end of an electrofusion weld fitting.

Embedded in the weld fitting is a wire heating coil. Via a voltage applied across special welding cables, a current is passed through the wire heating coil which melts adjacent regions of the weld fitting and pipe sections. Once the voltage ceases to be applied, the melted regions of the weld fitting and pipe section cool, and as they do so, they fuse together forming a fluid tight joint. For reliable joints to be formed, the correct amount of heating must be applied to the welding fitting. That is, the wire heating coil must be heated to a predetermined temperature for a predetermined period of time.

It is very important that the voltage applied is not interrupted during the welding operation. If the voltage supply is interrupted, the melted regions may start to cool, and even if subsequently the welding operation re-starts, there is a risk the joint will not be properly formed. If there is a risk that a joint has not properly been formed, the welding operation must be repeated, typically with a new welding fitting and potentially new sections of pipes. This is costly and time consuming.

In systems where a welding power supply is unlikely to run out of power, the likelihood of a welding operation being interrupted is typically low. However, in settings where a welding system may run out of power (for example, if the welding system is powered by a battery or a power supply with a limited amount of fuel), there is a risk that a welding operation will be started, but that the welding system will run out of power before the welding operation is completed.

In such situations, it is desirable to estimate whether or not a welding operation or a sequence of welding operations can be completed, before the welding operations commence.

However, this may be difficult because the parameters associated with different welding operations can vary greatly. There are a wide variety of weld types (varying in size, material, manufacturer etc), each which require different amounts of energy making it difficult to predict the amount of energy required to perform one or more welding operations (for example, that might be expected to be performed by an operator during the day). Further because the amount of energy required to perform an electrofusion weld may vary based on environmental conditions such as ambient temperature.

It would be desirable to provide a technique which enabled reliable predictions to be 20 made as to whether or not apparatus, such as electrofusion welding systems, are able to undertake operations to completion, before the operation commences.

Summary of the Invention

In accordance with a first aspect of the invention, there is provided a data processing system on which is implemented a computer implemented prediction function. The computer implemented prediction function is configured to receive operation 5 parameter data associated with an operation to be performed by an apparatus and apparatus capability data associated with an ability of the apparatus to perform the operation. The computer implemented prediction function is configured to process the operation parameter data and the apparatus capability data to generate completion prediction data, said completion prediction data indicative of an estimate of whether 10 the operation can be completed, and said data processing system is configured to output the completion prediction data.

Optionally, the prediction function is configured to generate the completion prediction data by: identifying, using the operation parameter data, a data record from a plurality of operation statistic data records, said data record indicative of operation requirements required for the apparatus to perform the operation with a combination of operation parameters specified in the operation parameter data; comparing the operation requirements with the apparatus capability data, and generating completion prediction data indicative of an estimate that the operation can be performed to completion if the apparatus capability data matches the operation requirements, and generating completion prediction data indicative of an estimate that the operation cannot be performed to completion if the apparatus capability data does not match the operation requirements.

Optionally, the prediction function comprises an update function configured to receive updated operation statistic data and to update the operation statistic data records in accordance with the updated operation statistic data.

Optionally, the updated operation statistic data comprises completed operation parameter data and completed operation apparatus capability data associated with operation parameters and apparatus capability of one or more successfully completed operations.

Optionally, the prediction function comprises a neural network configured to receive at an input layer the operation parameter data and the apparatus capability data, and generate at an output layer the prediction data.

Optionally, the neural network is trained using previously generated operation statistic data comprising training data records, each training data record indicative of operation parameter data and associated apparatus capability data for an operation and an indication of the operation was performed to completion.

Optionally, the operation parameter data is associated with an amount of energy required to perform the operation.

Optionally, the apparatus capability data is associated with an amount of energy available to the apparatus to perform the operation.

Optionally, the apparatus is an electrofusion welding system, said operation parameter data indicative of a welding operation type.

Optionally, the apparatus capability data is data indicative of an amount of energy available to the electrofusion welding system to perform the welding operation type.

Optionally, the prediction data is indicative of whether or not the weld operation of the welding type can be performed to completion.

Optionally, the electrofusion welding system is a battery powered electrofusion welding system and the apparatus capability data is data indicative of an amount of charge in the battery of the battery powered electrofusion welding system.

Optionally, the data processing system is provided by a computing device remote from the apparatus.

Optionally, the computing device is a user computing device provided by one of a smartphone, tablet or personal computer.

Optionally, the data processing system is an embedded system integrated into the apparatus.

In accordance with a second aspect of the invention, there is provided method of predicting if an operation can be performed to completion. The method comprises: receiving operation parameter data associated with an operation to be performed by an apparatus and apparatus capability data associated with an ability of the apparatus to perform the operation; processing the operation parameter data and the apparatus capability data to generate completion prediction data, said completion prediction data indicative of an estimate of whether the operation can be completed, and outputting the completion prediction data on a data processing device.

Optionally, the completion prediction data is generated by: identifying, using the operation parameter data, a data record from a plurality of operation statistic data records, said data record indicative of operation requirements required for the apparatus to perform the operation with a combination of operation parameters specified in the operation parameter data; comparing the operation requirements with the apparatus capability data, and generating completion prediction data indicative of an estimate that the operation can be performed to completion if the apparatus capability data matches the operation requirements, and generating completion prediction data indicative of an estimate that the operation cannot be performed to completion if the apparatus capability data does not match the operation requirements.

Optionally, the method further comprises receiving updated operation statistic data, and updating the operation statistic data records in accordance with the updated operation statistic data.

Optionally, the method is implemented by a neural network configured to receive at an input layer the operation parameter data and the apparatus capability data, and generate at an output layer the prediction data.

In accordance with a third aspect of the invention, there is provided a system comprising a data processing system on which is implemented a computer implemented prediction function and an apparatus for performing an operation. The apparatus comprises communication means configured to communicate to the data processing system operation parameter data associated with an operation to be performed by the apparatus and apparatus capability data associated with an ability of the apparatus to perform the operation, and the data processing system has communication means configured to receive the operation parameter data and apparatus capability data. The computer implemented prediction function is configured to process the operation parameter data and the apparatus capability data to generate completion prediction data, said completion prediction data indicative of an estimate of whether the operation can be completed, and said data processing system is configured to output the completion prediction data.

Optionally, the apparatus comprises means to perform an operation and communication means to communicate to a data processing system operation parameter data associated with an operation to be performed by the apparatus and apparatus capability data associated with an ability of the apparatus to perform the operation.

Optionally, the apparatus is an electrofusion welding power supply.

Optionally, the electrofusion welding power supply is a battery powered electrofusion power supply.

In accordance with a fourth aspect of the invention, there is provided a computer 30 program comprising computer readable instructions which when run on a computing device, controls the computing device to implement a method according to the second aspect of the invention.

In accordance with certain aspects of the invention, a system is provided that enables completion prediction data to be generated indicating whether or not an operation can be completed by an apparatus. Operation parameters associated with an operation to be performed and apparatus capability data associated with an ability of the apparatus to perform the operation are input to a computer implemented prediction function which is configured to process this data to generate the completion prediction data.

In certain embodiments, the completion prediction data is generated by using the operation parameters to identify an appropriate data record from a stored operation statistics which indicates what the apparatus requirements are to undertake the operation with the combination of operation parameters specified in the operation parameter data. The apparatus requirements data is then compared with the apparatus capability data to generate an estimate of whether or not the operation can be completed.

In certain embodiments, the operation statistics are generated based on data collected from previously performed operations. In such embodiments, the system can "learn" to predict whether or not an operation can be completed based on this data.

In certain embodiments, the completion prediction data is generated by inputting the operation parameter data and the apparatus capability data into a suitably trained neural network which is configured to generate an output estimate indicative of whether or not the operation can be performed.

In accordance with certain embodiments of the invention, a battery powered electrofusion welding system is provided which is configured so that an operator of the system can be informed whether or not a battery powering the system has sufficient charge to conduct an electrofusion welding operation.

Specifically, a modified electrofusion welding power supply unit is provided that can communicate battery status data to a processor, provided, for example in a remote device such as a smartphone, which is configured to use this data, along with retrieved weld information relating to a weld operation to be performed, to identify a data record, typically from weld statistic data comprising a plurality of such data records, which is indicative of an amount of charge required to perform the weld. An output is then generated which indicates to an operator whether there is sufficient charge in the battery to perform the weld operation.

In this way, an operator can begin a welding operation with a battery powered electrofusion welder power supply unit with improved certainty that the battery is capable of providing sufficient current to successfully perform the weld operation.

In certain embodiments, the modified electrofusion welding power supply unit is configured to communicate weld report data associated with welding operations that have been performed to an application server. The application server is configured to receive weld report data from other modified electrofusion welding power supply units. The application server is configured to generate and update the weld statistic data in accordance with the received weld report data and communicate this back to the processor. In this way, the information is used to determine whether or not the battery powering the system has sufficient charge to conduct an electrofusion welding operation is updated to take account of changes, for example, arising due to manufacturing differences between different batches of electrofusion weld fittings.

Various further features and aspects of the invention are defined in the claims.

Brief Description of the Drawings

Embodiments of the present invention will now be described by way of example only with reference to the accompanying drawings where like parts are provided with corresponding reference numerals and in which: Figure 1 provides a simplified schematic diagram depicting the communication of data in a system arranged in accordance with certain embodiments of the invention; Figure 2 provides a schematic diagram of a first implementation of a prediction function in accordance with certain embodiments of the invention; Figure 3 provides a schematic diagram of a second implementation of a prediction function in accordance with certain embodiments of the invention; Figure 4 provides a further simplified schematic diagram depicting the communication of data in a system arranged in accordance with certain embodiments of the invention; Figure 5 provides a schematic diagram of an implementation of an update function in accordance with certain embodiments of the invention; Figure 6 provides a schematic diagram of a system for predicting if an electrofusion welding operation can be undertaken to completion in accordance with certain embodiments of the invention; Figure 7 provides a schematic diagram depicting the communication of data between components of the system depicted in Figure 6; Figure 8 provides a schematic diagram depicting an example data record in accordance with certain embodiments of the invention; Figure 9 provides a further schematic diagram depicting the communication of data between components of the system depicted in Figure 6; Figures 10a and 10b provide schematic diagram depicting the output of completion prediction data in the form of graphical elements on a display screen in accordance with certain embodiments of the invention; Figure 11 provides a schematic diagram of a graphical element comprising text indicative of the minimum amount of charge required in a welder unit battery to perform a weld in accordance with certain embodiments of the invention, and Figure 12 provides a schematic diagram provides a schematic diagram depicting an example implementation of a power profile analysis function in accordance with certain embodiments of the invention.

Detailed Description

Figure 1 provides a simplified schematic diagram depicting components of a system for predicting if an operation can be performed to completion arranged in accordance with certain embodiments of the invention.

The system comprises apparatus 101 configured to perform an operation, a data processing device 102 and a computer implemented prediction function 103. The apparatus 101 is adapted to communicate operation parameter data associated with an operation to be performed by the apparatus 101 and apparatus capability data associated with a capability of the apparatus 101 to perform operations. In certain embodiments, the operation parameter data and the apparatus capability data may be received from other sources such as another computing device or manually input via a user interface.

The data processing device 102 is configured to communicate the operation parameter data and the apparatus capability data to the prediction function 103.

Once this processing has been performed, the prediction function 103 is configured to generate output completion prediction data indicative of a prediction of whether or not the operation intended to be performed by the apparatus 101 can be completed and return this to the data processing device 102. The data processing device 102 is configured to output the completion prediction data.

The prediction function 103 generates the completion prediction data based on predetermined operation statistic data.

In examples of the invention, the apparatus is an apparatus that is configured to perform a particular type of operation, where it is desirable, very important, or critical that the operation undertaken by the apparatus is performed, uninterrupted to the point where it is completed. That is, where it is desirable, very important, or critical that the apparatus does not cease operating during the operation.

In examples of the invention, the operation parameters are typically variables, associated with the operation, that may vary between instances of the operation being performed.

In examples of the invention, the apparatus capability data is data associated with the apparatus and specifically variables associated with the apparatus that may change over time and effect the ability of the apparatus to perform operations.

Examples of apparatus for performing operations in accordance with examples of the invention can include, in particular, apparatus where an amount of energy for performing operations, for example charge in a battery or a fuel supply is limited and where it is desirable to know before commencing an operation, whether or not the operation can be completed.

Illustrative examples include electrofusion welding systems, particularly battery-powered electrofusion welding system, where it is important to know before a welding operation commences, whether or not there is enough energy available to for the weld to be completed.

The computer implemented prediction function 103 can be implemented in various ways.

In certain examples, the prediction function operates in conjunction with data records stored in data storage. The data records comprise operation statistics. The operation statistics comprise records of apparatus capability requirements for performing operations associated with various combinations of operation parameters.

The operation statistics can be provided in different ways. In certain examples, the operation statistics are derived partially or wholly from previously undertaken operations. In some examples, the operation statistics are derived partially or wholly from other sources of data, for example simulation data associated with simulations of operations, and/or calculation data, associated with calculations of operation statistics.

An example of such an implementation of the prediction function is shown in Figure 2.

An operation requirement data look-up function 201 receives the operation parameter data from the apparatus, via the data processing device, and communicates the operation parameter data to data storage 202 in which is stored a plurality of data records. Typically, each data record associates a particular combination of operation parameters with the operation requirements required to successfully perform an operation with that particular combination of operation parameters.

The operation parameter data is used to identify a data record with a corresponding combination of operation parameters. The operation requirement data of this data record is then identified. This operation requirement data is then returned to the operation requirement data look-up function 201.

The operation requirement data look-up function 201 communicates the returned operation requirement data to a comparison function 203 which also receives as input the apparatus capability data.

The comparison function 203 then undertakes a comparison operation in which the apparatus capability data is compared with the operation requirement data to determine if the apparatus is capable of performing the operation, given the combination of operation parameters indicated in the operation parameter data. The comparison function 203 then outputs completion prediction data which is communicated to the data processing device.

The completion prediction data indicates that it is predicted that it is possible for the apparatus to successfully complete the operation if the apparatus capability data matches the operation requirement data.

The completion prediction data indicates that it is predicted that it is not possible for the apparatus to successfully complete the operation if the apparatus capability data do not match the operation requirement data.

In certain examples, the prediction function can be implemented using machine learning techniques. In one such example, a neural network can be used. Figure 3 provides an example implementation of the prediction function using a trained neural network.

A trained neural network 301 is provided which, in response to an input comprising the 5 operation parameter data and the apparatus capability data generates an output providing an estimation of whether or not the operation is possible.

During a training phase, training data associated with, for example previously performed operations is used.

For example, the training data comprises multiple training data records each training data record comprising operation parameters associated with an operation that has been performed, apparatus capability data associated with an apparatus that attempted to complete that operation with those operation parameters and completion data indicating the extent to which the operation was performed successfully.

The network is configured to receive at an input layer, inputs corresponding to an operation parameters and apparatus capability data. The network is configured to generate at an output layer completion prediction data corresponding to an estimation of whether the operation can be performed successfully.

During the training phase, a sequential training process is undertaken in which operation parameter data and apparatus capability data of a training data record is input to the input layer. The output completion prediction data output at the output layer is analysed to determine the degree to which it differs from the completion data of the training data record. Depending on the degree of divergence, changes are made to weightings of the nodes of the network. Another training data record is used, and the process repeated. The process repeats until the error between the output data generated by the network and the completion data from the training data records is minimised to an acceptable degree. Further training steps can be taken for example adding or removing layers of the network or changing the configuration of the nodes of the network.

In operation, the neural network 301 receives as input data the operation parameter data and apparatus capability data from the apparatus, via the data processing device, and passes this data through the neural network 301. The neural network 301 generates output completion prediction data corresponding to an estimation of whether the apparatus can successfully perform the operation.

In other embodiments, other machine learning techniques can be used to implement the prediction function. For example, genetic algorithms, linear regression algorithms, logistical regression algorithms, Bayesian based machine learning algorithms and so on.

In certain embodiments, the prediction function is updated over time. For example, when the apparatus conducts an operation, details of the operation parameters associated with conducting the operation are communicated to the prediction function along with apparatus capability data associated with the capability of the apparatus when the operation was performed. Similar data may be received by the prediction function from a plurality of different apparatus.

This data is used to update the prediction function so that the prediction function can be updated as more operations are conducted. In this way, the prediction function can be adapted to account for changes over time in the apparatus capability required for to perform operations with different combinations of operation parameters and, as more data is available, to improve the accuracy of the prediction function.

An example of this is shown in Figure 4.

Figure 4 depicts a system corresponding to that shown in Figure 1 except that the apparatus 101 is further configured to communicate to the data processing device 102 data associated with operations that have been performed.

Specifically, on completion of an operation, the apparatus 101 is configured to communicate completed operation parameter data to the data processing device 102 and completed operation capability data associated with the capability of the apparatus when undertaking the operation. The data processing device is configured to communicate the completed operation parameter data and the completed operation capability data to the prediction function 103 so that the prediction function can be updated in accordance with this information.

An example of how the prediction function 103 can be updated is described further with reference to Figure 5.

Figure 5 provides a schematic diagram depicting an implementation of the prediction function corresponding to that described with reference to Figure 2, except that the to implementation of the prediction function includes an update function 501. The update function 501 is configured to receive, as input, the completed parameter data and the completed operation capability data from the data processing device.

The update function 501 is configured to generate update data corresponding to modifications in the operation statistics in view of the received completed operation parameter data and corresponding completed operation capability data. The update data is then communicated from the update function 501 to the data storage 202, and the operation statistics are updated in accordance with update data.

In implementations in which the prediction function is implemented with a neural network, the neural network can be updated by periodically retraining the neural network with training data comprising more recently generated data records.

Examples of systems in accordance with embodiments of the invention can be manifested in different ways depending on the application of the system.

Returning to Figure 1, the computer implemented prediction function 103 is typically manifested as software running on a computing device configured to process the operation parameters and the apparatus capability data to determine whether or not the operation associated with the operation parameter data can be performed by the apparatus 101. Although shown separately in Figure 1, the prediction function may be integrated within the data processing device. In other examples, the prediction function may be implemented on a separate, remote computing device, such as an application server with which the data processing device is configured to communicate via a suitable data network.

The data processing device can be provided by any suitable data processing device.

Typically, the data processing device comprises a data communication interface, data processing means, such as a data processor, data output means such as a display screen and a local memory. The data processing device can be provided by any suitable computing device personal computing devices such as laptops, tablets and "smart" devices such as smartphones and smartwatches. In such examples, the data to communication interface may include a suitable data transceiver capable of establish a wired or wireless link with a corresponding data transceiver incorporated in the apparatus for performing the operation.

In some examples, the data processing device is physically integrated in the apparatus. For example, the data processing device may be incorporated as a distinct physical module within the apparatus itself, or may be integrated in data processing equipment (for example an embedded system) with which the apparatus is already equipped and which is configured to perform other functions, such as control the operation of the apparatus. In such examples, the data communication interface may include suitable internal data communication means, for example an internal data bus.

Figure 6 provides a schematic diagram of a system arranged in accordance with certain embodiments of the invention. In particular, the system depicted in Figure 6 implements an example of a system for predicting if an operation can be performed to completion of the type described with reference to Figures 1, 2 and 4 where the operation is an electrofusion weld operation.

The system is arranged to capture and store data relating to electrofusion weld operations performed on various weld fittings by battery powered electrofusion 30 welders.

From this captured data, the system is configured to generate operation statistic data relating to welder parameters for performing particular types of welds. These parameters include, for example, minimum peak currents, maximum peak currents and minimum energy, maximum energy and average energy required.

Once collected, this statistic data is conveyed to an app running on user devices and 5 can be used when a weld is about to be undertaken to predict, based on metrics derived from the previously conducted weld operations, whether or not a battery powered electrofusion welder has sufficient charge in its battery to perform the weld.

The system comprises a modified electrofusion welder power supply unit 601 arranged to supply welding current to an electrofusion weld fitting 602. The system further comprises a portable user device 603, provided for example by smartphone or tablet device. The user device 603 has running thereon battery capacity information software. The battery capacity information software implements a data collection function and a battery capacity indication function.

The user device 603 is configured to communicate data to and from the electrofusion welding unit via a suitable data link, provided, for example, by a short-range wireless data connection such as a Bluetooth wireless data connection.

The user device 603 is further configured to communicate data to and from an application server 604. The application server is connected to a data network 605 (for example the internet) which is connected to a wireless base station 606 (which, for example, is provided by a cellular mobile telephone network 607). Data to be communicated to the application server 604 from the user device 603 is transmitted via a wireless link from the user device 603 to the base station 606 of the cellular mobile telephone network 607. This data is then communicated onwards from the cellular mobile telephone network 607 and via the data network 605 to the application server 604. Correspondingly, data to be communicated from the application server 604 to the user device 603 is communicated from the application server 604 to the data network 605 and then to the cellular mobile telephone. The base station 606 of the cellular mobile telephone network 607 then communicates the data via the wireless link to the user device 603.

The modified electrofusion welder power supply unit 601 comprises a control unit 608, typically provided by a suitably configured microprocessor. The modified electrofusion welder power supply unit 601 further comprises a battery unit 609 and a power convertor 610. The control unit 608 is connected, via suitable control lines, to the battery unit 609 which comprises a battery management system and a battery (typically a lithium ion battery, although any suitable battery can be used, for example a lithium ion polymer battery, lead acid, lithium air battery and so on). The control unit 608 is further connected to the power convertor 610 via suitable control lines. In use, under the control of the control unit 608, electrical current from the battery of the battery unit 609, converted to a suitable output by the power convertor 610, provides an electrical welding current which is delivered to the electrofusion weld fitting 602 via conducting leads 612a, 612b. The conducting leads 612a, 612b are connected to the electrofusion weld fitting 602 via terminals 613a, 613b and connected to an output of the electrofusion welder power supply unit 601 via output terminals 611a, 611b.

The modified electrofusion welder power supply unit 601 further comprises a wireless data transceiver 614, provided, for example, by a Bluetooth data transceiver. The wireless data transceiver 614 is connected to the control unit 608 and, as described above, is configured to communicate data to and from the user device 603. The modified electrofusion further comprises a barcode scanner port 615 which is configured to connect to the connection line of a barcode scanner 616 (in certain embodiments, this may be a wireless connection). The bar code scanner 616 is configured to scan a first bar code 617a and second barcode 617b which are fixed on a surface of the electrofusion weld fitting 602. The first bar code 617a typically identifies the weld fitting type, and the second barcode 617b identifies a manufacturing batch associated with weld fitting 602. Once scanned, corresponding barcode data is communicated from the barcode scanner 616 to the control unit 608 via the port 615.

The application server 604 is connected to a database 618, which under control of welding data management software running on the application server, enables electrofusion weld data to be stored, modified and retrieved. The application server 604 is connected to a control terminal 619 via which an operator can control the operation of the application server 604.

When an electrofusion weld is performed using the welder power supply unit 601, an operator scans the first and second barcodes 617a, 617b and corresponding barcode data is communicated to the control unit 608.

Typically, the control unit 608 uses this barcode data to select predetermined welding parameters which are associated with the electrofusion weld fitting 602. The predetermined welding parameters typically specify the voltage which must be applied to the electrofusion weld fitting 602 and how long this voltage must be applied for. The electrofusion weld is then performed by the control unit 608 controlling the power convertor 610 to deliver the current to the weld fitting 602 in accordance with the selected predetermined welding parameters.

The control unit 608 is configured to ensure that the weld is conducted in accordance with these predetermined parameters, for example by monitoring the voltage and resistance across the coil of the electrofusion weld fitting 602 and the current passing through it.

The barcode data (that is, data encoded in the first barcode 617a indicative of the weld fitting type and data encoded in the second barcode 617b indicative of the weld fitting batch) is stored in a memory of the control unit 608.

The control unit 608 further comprises a weld monitoring function which records welding metrics associated with the operation of the welder power supply unit 601 as it performs a welding operation. The welding metrics may include, for example, the peak current discharged into the weld fitting 602 as the weld is performed and the total amount of energy discharged into the weld fitting 602 during the weld process.

In certain embodiments, the modified electrofusion welder power supply unit 601 further comprises a temperature sensor 620 connected to the control unit 608 which is configured to measure an ambient temperature. The weld monitoring function also records the ambient temperature during the welding operation and includes corresponding temperature data in the weld metrics.

When the weld is complete, these welding metrics are communicated to the application server 604. This is described in further detail with reference to Figure 7.

Data collection phase The barcode reader 616 is configured to communicate the barcode data to the control unit 608 (S701). When the weld is completed, the control unit 608 is configured to communicate (S702) to the user device weld report data which comprises data indicative of the weld fitting type (derived from the first barcode 617a), data indicative of the weld fitting batch (derived from the second barcode 617b) and weld metrics to associated with the weld that was undertaken (e.g. peak current, total energy and ambient temperature).

In certain embodiments, for example where the modified electrofusion welder power supply unit 601 is not equipped with a temperature sensor 620, a temperature sensor 15 may be incorporated in the user device 603 for capturing temperature data and ambient temperature data is added to the weld report data at the user device 603.

The data collection function implemented by the battery capacity information software running on the user device 603 is configured to communicate (S703) this weld report data to the application server 604. The welding data management software running on the application server 604 is configured to communicate (S704) the weld report data to the database 618 which stores the weld data as a weld report data record.

The application server 604 is configured to receive weld report data from multiple electrofusion units and corresponding user devices, all of which are configured to communicate weld report data, generated as described above, to the application server 604. In this way, over time, a collection of weld report data records is stored in the database 618.

At a suitable time, for example when the collection of weld report data records contains a predetermined number of weld report data records; after a predetermined interval of time, or in response to control input to the application server from the control terminal 619, the welding data management software running on the application server 604 is configured to perform an analysis function in which statistics data relating to different types of welds are determined and a weld statistic data record produced.

Specifically, the analysis function retrieves weld report data records from the database 5 618 record and processes them to generate operation statistics in the form of weld statistic data.

Specifically, for each available combination of operation parameters, that is each available combination of weld fitting type, batch and ambient temperature, the analysis function determines statistic data associated with the energy required to perform the weld and the current to perform the weld. Specifically, for each combination of operation parameters for which data is available, the analysis function determines operation requirement data corresponding to the average energy required to perform the weld and the maximum peak current required to perform the weld. The analysis function then generates operations statistics comprising a plurality of weld statistic data records and communicates these for storage to the database 618.

Figure 8 provides a schematic diagram depicting an example of these operation statistic data records.

As can be seen, the weld statistic data records correspond to a table specifying the average energy and maximum peak current required to perform a weld for each combination of operation parameters (each combination of weld connector type (Weld Ds), batch (Batch No) ambient temperatures (Ambient Temp). These operation parameters can be generated in any suitable data format as is well known in the art for example as a text file.

Prediction if operation is possible phase Once the operation parameters provided by the weld statistic data records have been generated as described above, the application server 604 is configured to communicate them to a plurality of user devices on which the battery capacity information software is running, typically including the user devices from which the weld report data was received.

At each user device, the battery capacity information software is configured to store the weld statistic data records and subsequently use them to implement a prediction function in which completion prediction data is generated for an operator of the welder unit to indicate whether or not there is sufficient charge in the battery of the welder unit to perform a particular weld operation.

An example of this is described in more detail with reference to Figure 9 which shows a flow of data associated with the determination at a user device whether or not a particular weld associated with a weld fitting can be performed.

As described above, weld report data is retrieved (S901) from the application server 604 and used to generate (S902) operation statistics in the form of weld statistic data records. These weld statistic data records are then communicated (S903) to the various user devices on which is the running the battery capacity information software.

When a weld is to be performed, an operator scans the first barcode 617a and the second barcode 617b with the bar code scanner 616 and barcode data is communicated (S904) to the control unit 608 of the modified electrofusion welder power supply unit 601.

Before commencing the weld procedure, the control unit 608 controls the wireless data transceiver 614 to communicate (S905) operation parameters in the form of this barcode data and ambient temperature data generated by the temperature sensor 620 to the user device 603 along with apparatus capability data in the form of welder status data.

Typically, the welder status data is indicative of the total amount of energy that the welder power supply unit 601 can, at that time, discharge and the maximum and minimum current levels that the welder power supply unit can, at that time discharge.

The welder status data may include other information, such as the total amount of energy and/or charge available in the battery when fully charged.

The control unit 608 can determine the total amount of energy that can be discharged at that time based on the detected levels of charge present in the battery of the battery unit 609. This information is typically provided by a suitable output signal from the battery management system. The control unit 608 can determine a peak current that can be discharged by the welder power supply unit based on predetermined values stored in the control unit 608 and associated with parameters of the power convertor 610 and the battery of the battery unit 609.

Responsive to receipt of the bar code data and welder status data, the battery capacity information software is configured to perform a prediction function in the form of a battery capacity indication function.

The battery capacity indication function performs an operation requirement data lookup function in which a combination of operation parameters (the bar code data (typically comprising barcode data derived from the first code 617a relating to the type of the weld fitting 617a and the second barcode 617b relating to the batch number of the weld fitting 602) and the temperature data) are matched with a corresponding record from the weld statistic data records received from the application server 604 and stored on the user device 601.

Once such a record has been identified, the operation requirement data (in this example the average energy required and the maximum peak current required) is identified by the operation requirement data look-up function and input to a comparison function. The comparison function is configured to compare the apparatus capability data provided in the welder status data (the total amount of energy that the welder power supply unit 601 can, at that time, discharge and the maximum and minimum current levels that the welder power supply unit can, at that time discharge) with the operation requirement data to determine (S906) if the operation can be performed.

Specifically, this comparison is undertaken by comparing the average energy required to undertake the weld indicated in the weld statistic data record with the available energy in the battery indicated in the weld status data, and by comparing the maximum peak current with the available peak current indicated in the welder power supply unit status data.

If the available energy in the battery is greater by a predetermined margin than the average energy required to undertake the weld indicated in the weld statistic data record and if the available peak current is at least greater than the maximum peak current in the weld statistic data record, then the battery capacity indication function determines that the weld can be performed by the welder power supply unit 601 and generates completion prediction data in the form of a "weld is possible" message.

On the other hand, if the available energy in the battery is less than the energy required to undertake the weld indicated in the weld statistic data record and/or if the available peak current is less than the maximum peak current in the weld statistic data record, then the battery capacity indication function determines that the weld cannot be performed by the welder power supply unit 601 and generates completion prediction data in the form of a "weld is not possible" message.

For example, with reference to Figure 8, the barcode data may indicate that the operation parameters are: a weld fitting of type A from batch number 1 with the ambient temperature data of 15 °C. The data comparison operation therefore identifies the data record identified in Figure 8 which specifies operation requirement data of an average energy of 490 kJ and a maximum peak current of 2.3A.

The welder status data (i.e. the apparatus capability data) may indicate that the total amount of charge in the battery is sufficient to deliver a total of 800kJ at a maximum current of 3A. Accordingly, the battery capacity indication function determines that the battery does contain sufficient charge to undertake the weld and generates the corresponding completion prediction data, i.e. a weld possible message.

Typically, the battery capacity information software running on the user device 603 controls the user device to display the relevant message (i.e. "weld is possible" or "weld is not possible") on a user interface of the user device informing the operator of the welder power supply unit that the weld can be performed based on the current charge levels of the battery.

Figure 10a provides a schematic diagram depicting the generation of a "weld not possible" message on a user device. Figure 10a shows a user device 1001 comprising a display screen 1002 and on which the battery capacity information software has, responsive to the battery capacity indication function determining that the weld cannot be performed, controlled the user device 1001 to generate and display a graphical element 1003 comprising text stating "weld not possible!".

Correspondingly, Figure 10b provides a schematic diagram depicting the generation of a "weld possible" message on a user device. Figure 10b shows a user device corresponding to that shown in Figure 10b and on which the battery capacity information software has, responsive to the battery capacity indication function determining that the weld can be performed, controlled the user device 1001 to generate and display a graphical element 1004 comprising text stating "weld possible!".

Update phase Once a weld statistic data record has been generated by the application server 604 it can be periodically updated based on further weld report data received from user devices on which the battery capacity information software is running. For example, over a predetermined period of time, further weld report data is received and stored in the application server 604. At the end of this predetermined period of time, an update function running on the application server 604 generates new (updated) weld statistic data records which are generated using the previously collected weld report data and the newly collected weld report data. These are then communicated to the user devices as described above, and the operation statistics stored on the user devices are updated accordingly.

In certain examples, this also enables new fittings introduced to the market to be reported by an electrofusion welding power supply unit to the database, allowing other users to understand their power requirements even if they have never welded with them before.

In certain examples, the weld statistic data record can be updated based on information provided from external sources, for example from third party suppliers, for example manufacturers of weld fittings. This information may include identification data relating to new batch numbers or new weld fitting types. Such further information can be received by the application server 604 via the data network 605 or can be manually entered into application server 604 via suitable means, for example, the control terminal 619.

In certain embodiments, the battery capacity information software running on the user device is configured to perform a minimum requirement prediction function. The minimum requirement prediction function generates prediction data which is indicative of a minimum level of battery charge required to perform one or more welds and generates a corresponding output to inform a user of this.

In one example implementation of this, the user of the system uses the barcode scanner to scan the barcodes on the weld fitting as described above, and this weld identity data is communicated to the user device along with welder status data. The minimum requirement prediction function of the battery capacity information software then identifies corresponding data from the weld statistic data record and in particular, data relating to the total amount of energy required to perform the weld and compares this with the total capacity of the battery installed in the welder power supply unit (data provided in the welder status data). The minimum requirement prediction function then calculates what minimum charge level would be required from the battery of the welder unit to successfully undertake the weld. An example of this is shown in Figure 11.

Figure 11 provides a schematic diagram of a user device corresponding to that shown in Figures 10a and 10b except that battery capacity information software has controlled the user device to generate and display a graphical element 1101 comprising text indicative of the minimum amount of charge required in a welder unit battery to perform a weld.

In certain examples, the minimum requirement prediction function can be configured to receive weld identity data from multiple weld fittings and determine the amount of energy required to perform all of the corresponding weld operations and generate an output indicative of whether there is sufficient charge in the battery to perform all of the welds.

In certain examples, the minimum requirement prediction function can be configured to receive weld identity data from multiple weld fittings determine the amount of energy required to perform all of the corresponding weld operations and generate an output indicative of the number of times the battery of the electrofusion system will have to be recharged to perform all the corresponding welding operations.

In certain examples, the battery capacity information software is configured to generate an output reminding a user of the system to charge the battery. This may be responsive to receiving welder status data indicative that the charge in the battery is running low.

In certain embodiments, the welder status data is received from the electrofusion welder unit itself. However, in other embodiments it can be received from other sources, for example communicated from an external data source with which the data apparatus can communicate e.g. a remote application server or from a memory device (e.g. "memory stick") which can be interfaced with the user device. In certain examples, the user device comprises user interface means (for example a keyboard) via which the electrofusion welder capability data can be entered manually by a user.

Typically, the welder status data is indicative of available energy information, that is, the total amount of available energy that the electrofusion welder unit 601 is capable of delivering for welding operations. The total amount of available energy can be based on amount of fuel left in a fuel tank of, for example, a diesel-powered electrofusion welder unit or the amount of charge left in a battery of a battery powered electrofusion welder unit. In certain embodiments, the welder status data can include information indicative of the average welding current that an electrofusion welder unit can consistently deliver and the peak current the welding electrofusion welder can deliver.

In certain embodiments, welder status data can include information indicative of compatibility of the electrofusion welder unit 601 which can be used to determine if the electrofusion welder unit 601 is compatible with welding components such as weld fittings.

As described above, in certain examples, the weld identity data is provided via a barcode scanner connected to the electrofusion welder unit 601.

In other examples, the weld identity data is entered manually by a user via a user interface. In other example, the weld identity data is provided via a "QR" code reader (e.g. a digital camera) or an RFID tag reader interfaced with the electrofusion welder unit 601. In examples in which the user device 603 is provided by a device such as a smartphone or tablet, the welding identity data can be provide by a camera of the device capturing an image of an optical code (e.g. barcode or QR code) associated with the weld fitting.

In certain examples, the operating parameters include data relating to further welding 10 variables such as the humidity when the weld operation was performed and/or location data specifying information about the location (e.g. geographical location and/or elevation) where the weld operation was performed.

In certain examples, the software running on the user device 603 is configured to provide further information to a user of the system relating to ancillary information associated with the welding components of the system.

For example, the weld identity data can include data identifying a weld fitting and corresponding components (e.g. pipes) that the user intends connect by performing a welding operation using the weld fitting. In some examples the user device is provided with functionality (for example software running on the data processing means) that identifies if the weld fitting and corresponding components are compatible, and if not, generates a suitable alert to the user, for example via a text message displayed on a display screen of the user device. Similarly, the further functionally can be configured to determine if the weld fitting or corresponding components have been recalled by comparing the weld identity data with recall data received from an external data source. If the recall data indicates the weld fitting or corresponding components are subject to a recall, the further functionality is configured to generate a suitable alert to the user, for example via a text message displayed on a display screen of the user device. Similarly, the further functionally can be configured to identify from the weld identity data environmental information ("green credentials") associated with a welding operation and output data indicative of this environment information on a display screen of the user device.

In certain examples, the user device 603 can have stored thereon instruction data providing instructions for undertaking welding operations. Responsive to receiving the weld identity data, the data processing apparatus can be configured to identify instruction data associated with the welding operation associated with the weld identity data and display this to a user, for example in the form of images and/or text and/or video via a display.

If a weld has not been performed correctly, this is likely to be reflected in an abnormal profile of the power output of the power supply during the period of the time the weld operation was performed. In certain examples the software running on the user device 603 is further configured to implement a power profile analysis function. The power profile analysis function is configured to identify if a weld operation has been performed correctly or not by analysing data associated with the power output of the power supply as the welding operation is performed, that is, power by time during the welding operation.

The power profile analysis function is configured to compare power profile data collected during the performance of a welding operation with a corresponding power profile data record.

The corresponding power profile data record is associated with an expected power profile for a welding operation with operation parameters corresponding to the operation parameters of the welding operation that has been performed.

The power profile data typically comprises an indication of power consumption over time, for example a series of data values corresponding to instantaneous welding current values at fixed time points during the welding operations, for example every 2 seconds.

Figure 12 provides a schematic diagram depicting an example implementation of a power profile analysis function in accordance with certain embodiments of the invention with reference to the system described in Figure 6.

The control unit 608 controls the modified electrofusion power supply to perform a welding operation as described above.

At a first step S1201, the weld monitoring function of the control unit 608 monitors and records the welding current to generate power profile data.

At a second step S1202, the control unit 608 controls the wireless data transceiver 614 to communicate the power profile data and the operation parameters (typically including the barcode data and ambient temperature data as described above) to the user device 603.

At a third step S1203, the power profile analysis function running on the user device 603 is configured to identify from a plurality of power profile data records a corresponding power profile data record.

Similar to the weld statistic data records, the power profile data records typically comprise a plurality of data records where each data record corresponds to the power profile for a welding operation that is known to have been performed correctly for a particular combination of operation parameters (for example, weld fitting type, batch and ambient temperature). The corresponding power profile data record is a power profile data record that has operation parameters that match the operation parameters received from the modified electrofusion welding power supply 601.

At a fourth step S1204, the power profile analysis function running on the user device 603 is configured to compare the power profile data from the identified corresponding power profile data record with the power profile data received from the modified electrofusion welding power supply 601. This comparison typically involves calculating a deviation between the power profile data from the identified corresponding power profile data record and the power profile data received from the modified electrofusion welding power supply 601. The deviation can be calculated in any suitable way that would indicate an abnormal power profile during the welding operation suggesting that it has not been performed correctly.

For example, calculating the deviation may involve comparing instantaneous current values from the power profile data record with corresponding instantaneous current values from the power profile data received from the modified electrofusion welding power supply 601 to determine an average deviation value.

Alternatively, the deviation could be calculated by determining from the power profile data received from the modified electrofusion welding power supply 601 a total amount of energy used to perform the weld; determining a corresponding total energy value from the power profile data record and then generating a deviation value based on the difference between these values.

Alternatively, the deviation could be calculated by determining from the power profile data received from the modified electrofusion welding power supply 601 a maximum peak current used to perform the weld; determining a corresponding maximum peak current from the power profile data record and then generating a deviation value based on the difference between these values.

At a fifth step S1205, the result of the comparison step S1204, for example a deviation value, is used to generate weld analysis data indicative of whether or not the power profile data implies the weld has not been performed correctly.

For example, if a deviation value calculated in the fourth step S1204 indicates an abnormal power profile during the welding operation (for example, because a calculated deviation value is greater than a predetermined threshold value indicating that the difference between the power profile data record and the received power profile data is greater than a predetermined threshold), weld analysis data would be generated indicating that the weld operation has not been correctly performed.

On the other hand, if the deviation value indicates a normal power profile during the welding operation (for example, because the deviation value is less than a predetermined threshold value indicating that the difference between the power profile data record and the received power profile data is less than a predetermined threshold), weld analysis data would be generated indicating that the weld operation has been correctly performed.

Once generated, the weld analysis data can be output in keeping with the completion prediction data described above with reference to Figures 10a and 10b, e.g. in the form of a message on the display screen of the user device 603 comprising suitable text. For example, if the weld analysis data indicates that the weld has not been performed correctly, text saying "Warning! Abnormal weld". Additionally, for example, if the weld analysis data indicates that the weld has been performed correctly, text saying "Weld performed correctly".

Examples of the invention can be implemented in other contexts.

For example, the invention can be applied to other battery-powered fusion welding techniques, such as butt-fusion welding techniques whereby a plate is heated to melt pipe ends and then the pipe ends are pushed together to form a joint. Like electrofusion welding, different types and sizes of pipes require different energies to successfully perform a welding operation, and the performance of the welding operation may also be affected by ambient temperature. Historic data from previous welding operations can be used to generate the operation statistics or to train a neural network as described above so that a prediction function can determine if sufficient charge is present in a battery to perform a welding operation.

Similarly, the invention can be applied to other battery-powered welding techniques, such as steel welding operations for welding pipes together. In such examples, the operation parameters may be associated with a diameter of the pipe to be welded and also, the identity of a welding operative. Different welding operatives may have different welding styles that take more time or less time than others. Thus, the welding operations that otherwise have the same operation parameters (diameter of pipe) would require more energy for certain welding operatives and less energy for other welding operatives. Data from previous welding operations can be used to generate operation statistics including operation parameters specifying different welding operators so that the prediction function can predict if a battery has sufficient energy to enable a particular welding operative to conduct a welding operation, given the time normally taken for that welding operative to conduct welding operations compared to other welding operatives.

In one example, a battery-powered stairlift system is provided. In such examples, the apparatus is provided by a battery-powered stair lift; the operation performed by the apparatus is transporting people of different weights up a flight of stairs; the operation parameters are the weight of the person to be transported and the length of the stairs and the apparatus capability data is the charge in the battery.

During an initial phase, a prediction function, running on a computing device connected to the battery-powered stairlift is configured to receive data from the battery-powered stairlift (generated either automatically by suitable sensors integrated in the stairlift or entered manually) corresponding to the amount of battery energy consumed moving people of different weights up the stairs and to populate an associated memory device with corresponding operations statistics. Once a sufficient number of operation statistics have been generated, the prediction function can be used to generate completion prediction data as described above by receiving operation parameters comprising the weight of a person and apparatus capability data comprising the amount of charge in the battery powering the battery-powered stairlift. The completion prediction data can be output from a suitable data processing device (for example a device with a display screen integrated into the stairlift), indicating whether or not, given the person's weight and current charge-level in the battery, the person can be taken to the top of the stairs without the battery running out of energy.

In a similar example, embodiments of the invention could be manifested in a battery-powered crane system, where the crane, used for moving loads from one place to another, is powered by a battery. During an initial phase, operation statistic data can be gathered associated with one or more lifting operations and then, subsequently, a prediction function used to predict whether or not enough energy is present in a battery powering the system to perform a subsequent operation.

In another example, a battery-powered scooter or bicycle system is provided.

In such examples, the apparatus is provided by a battery-powered bicycle; the operation performed by the apparatus is transporting a person to their intended destination along a predefined route by the battery-powered bicycle; the operation parameters are the weight of the person to be transported, the length and elevation of the predefined route, the amount of energy contributed by the person by pedalling, the speed of the battery-powered bicycle during the journey, and the apparatus capability data is the charge in the battery.

A prediction function running, for example, on a smartphone of a user, or on a computer attached to the battery-powered bicycle can be configured to receive operation parameter input from a user indicating their weight, how hard they intend to pedal, details of their intended route (from which length and elevation can be derived) and the speed at which they wish to travel and also to receive apparatus capability data corresponding to a current charge level in the battery of the battery-powered bicycle. The prediction function can then generate completion prediction data indicative of whether or not the battery will last for the intended journey based on predetermined operation statistics as described above.

All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and/or all of the steps of any method or process so disclosed, may be combined in any combination, except combinations where at least some of such features and/or steps are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise. Thus, unless expressly stated otherwise, each feature disclosed is one example only of a generic series of equivalent or similar features. The invention is not restricted to the details of the foregoing embodiment(s).

The invention extends to any novel one, or any novel combination, of the features disclosed in this specification (including any accompanying claims, abstract and drawings), or to any novel one, or any novel combination, of the steps of any method or process so disclosed.

With respect to the use of substantially any plural and/or singular terms herein, those having skill in the art can translate from the plural to the singular and/or from the singular to the plural as is appropriate to the context and/or application. The various singular/plural permutations may be expressly set forth herein for sake of clarity. It will be understood by those within the art that, in general, terms used herein, and especially in the appended claims are generally intended as "open" terms (e.g., the term "including" should be interpreted as "including but not limited to," the term "having" should be interpreted as "having at least," the term "includes" should be interpreted as "includes but is not limited to," etc.). It will be further understood by those within the art that if a specific number of an introduced claim recitation is intended, such an intent will be explicitly recited in the claim, and in the absence of such recitation no such intent is present. For example, as an aid to understanding, the following appended claims may contain usage of the introductory phrases "at least one" and "one or more" to introduce claim recitations. However, the use of such phrases should not be construed to imply that the introduction of a claim recitation by the indefinite articles "a" or "an" limits any particular claim containing such introduced claim recitation to embodiments containing only one such recitation, even when the same claim includes the introductory phrases "one or more" or "at least one" and indefinite articles such as "a" or "an" (e.g., "a" and/or "an" should be interpreted to mean "at least one" or "one or more"); the same holds true for the use of definite articles used to introduce claim recitations. In addition, even if a specific number of an introduced claim recitation is explicitly recited, those skilled in the art will recognize that such recitation should be interpreted to mean at least the recited number (e.g., the bare recitation of "two recitations," without other modifiers, means at least two recitations, or two or more recitations).

It will be appreciated that various embodiments of the present disclosure have been described herein for purposes of illustration, and that various modifications may be made without departing from the scope of the present disclosure. Accordingly, the various embodiments disclosed herein are not intended to be limiting, with the true scope being indicated by the following claims.

Claims

CLAIMS1. Data processing system on which is implemented a computer implemented prediction function, wherein said computer implemented prediction function is configured to receive 5 operation parameter data associated with an operation to be performed by an apparatus and apparatus capability data associated with an ability of the apparatus to perform the operation, wherein the computer implemented prediction function is configured to process the operation parameter data and the apparatus capability data to generate completion prediction data, said completion prediction data indicative of an estimate of whether the operation can be completed, and said data processing system is configured to output the completion prediction data.
2. Data processing system according to claim 1, wherein the prediction function is configured to generate the completion prediction data by: identifying, using the operation parameter data, a data record from a plurality of operation statistic data records, said data record indicative of operation requirements required for the apparatus to perform the operation with a combination of operation parameters specified in the operation parameter data, comparing the operation requirements with the apparatus capability data, and generating completion prediction data indicative of an estimate that the operation can be performed to completion if the apparatus capability data matches the operation requirements, and generating completion prediction data indicative of an estimate that the operation cannot be performed to completion if the apparatus capability data does not match the operation requirements.
3. Data processing system according to claim 2, wherein the prediction function comprises an update function configured to receive updated operation statistic data and to update the operation statistic data records in accordance with the updated operation statistic data.
4. Data processing system according to claim 3, wherein the updated operation statistic data comprises completed operation parameter data and completed operation apparatus capability data associated with operation parameters and apparatus capability of one or more successfully completed operations.
5. Data processing system according to claim 1, wherein the prediction function comprises a neural network configured to receive at an input layer the operation parameter data and the apparatus capability data, and generate at an output layer the prediction data.
6. Data processing system according to claim 5, wherein said neural network is trained using previously generated operation statistic data comprising training data records, each training data record indicative of operation parameter data and associated apparatus capability data for an operation and an indication of the operation was performed to completion.
7. Data processing system according any previous claim, wherein the operation parameter data is associated with an amount of energy required to perform the operation.
8. Data processing system according to claim 7, wherein the apparatus capability data is associated with an amount of energy available to the apparatus to perform the operation.
9. Data processing system according to claim 8, wherein the apparatus is an electrofusion welding system, said operation parameter data indicative of a welding operation type.
10. Data processing system according to claim 9, wherein the apparatus capability data is data indicative of an amount of energy available to the electrofusion welding system to perform the welding operation type.
11. Data processing system according to claim 10, wherein the prediction data is indicative of whether or not the weld operation of the welding type can be performed to completion.
12. Data processing system according to claim 10 or 11, wherein the electrofusion welding system is a battery powered electrofusion welding system and the apparatus capability data is data indicative of an amount of charge in the battery of the battery powered electrofusion welding system.
13. Data processing system according to any previous claim, wherein the data processing system is provided by a computing device remote from the apparatus.
14. Data processing system according to claim 13, wherein the computing device is a user computing device provided by one of a smartphone, tablet or personal computer.
15. Data processing apparatus according to any of claims 1 to 12 wherein the data processing system is an embedded system integrated into the apparatus.
16. A method of predicting if an operation can be performed to completion, said method comprising: receiving operation parameter data associated with an operation to be performed by an apparatus and apparatus capability data associated with an ability of the apparatus to perform the operation; processing the operation parameter data and the apparatus capability data to generate completion prediction data, said completion prediction data indicative of an estimate of whether the operation can be completed, and outputting the completion prediction data on a data processing device.
17. A method according to claim 16, wherein the completion prediction data is generated by: identifying, using the operation parameter data, a data record from a plurality of operation statistic data records, said data record indicative of operation requirements required for the apparatus to perform the operation with a combination of operation parameters specified in the operation parameter data, comparing the operation requirements with the apparatus capability data, and generating completion prediction data indicative of an estimate that the operation can be performed to completion if the apparatus capability data matches the operation requirements, and generating completion prediction data indicative of an estimate that the operation cannot be performed to completion if the apparatus capability data does not match the operation requirements.
18. A method according to claim 17, further comprising: receiving updated operation statistic data, and updating the operation statistic data records in accordance with the updated operation statistic data.
19. A method according to claim 18, wherein the updated operation statistic data comprises completed operation parameter data and completed operation apparatus capability data associated with operation parameters and apparatus capability of one or more successfully completed operations.
20. A method according to claim 16, wherein the method is implemented by a neural network configured to receive at an input layer the operation parameter data and the apparatus capability data, and generate at an output layer the prediction data.
21. A method according to claim 20, wherein said neural network is trained using previously generated operation statistic data comprising training data records, each training data record indicative of operation parameter data and associated apparatus capability data for an operation and an indication of the operation was performed to completion.
22. A method according any of claims 16 to 21, wherein the operation parameter data is associated with an amount of energy required to perform the operation.
23. A method according to claim 22, wherein the apparatus capability data is associated with an amount of energy available to the apparatus to perform the operation.
24. A method according to claim 23, wherein the apparatus is an electrofusion welding system, said operation parameter data indicative of a welding operation type.
25. A method according to claim 24, wherein the apparatus capability data is data indicative of an amount of energy available to the electrofusion welding system to perform the welding operation type.
26. A method according to claim 25, wherein the prediction data is indicative of whether or not the weld operation of the welding type can be performed to completion.
27. A method according to claim 25 or 26, wherein the electrofusion welding system is a battery powered electrofusion welding system and the apparatus capability data is data indicative of an amount of charge in the battery of the battery powered electrofusion welding system.
28. A method according to any previous claim, wherein the data processing system is provided by a computing device remote from the apparatus.
29. A method according to claim 28, wherein the computing device is a user computing device provided by one of a smartphone, tablet or personal computer.
30. A method according to any of claims 16 to 27 wherein the data processing system is an embedded system integrated into the apparatus.
31. A system comprising a data processing system on which is implemented a computer implemented prediction function and an apparatus for performing an operation, wherein said apparatus comprises communication means configured to communicate to the data processing system operation parameter data associated with an operation 30 to be performed by the apparatus and apparatus capability data associated with an ability of the apparatus to perform the operation, and the data processing system has communication means configured to receive the operation parameter data and apparatus capability data, wherein the computer implemented prediction function is configured to process the operation parameter data and the apparatus capability data to generate completion prediction data, said completion prediction data indicative of an estimate of whether the operation can be completed, and said data processing system is configured to output the completion prediction data.
32 Apparatus for performing an operation for use in a system according to claim 31, wherein said apparatus comprises means to perform an operation and communication means to communicate to a data processing system operation parameter data associated with an operation to be performed by the apparatus and apparatus capability data associated with an ability of the apparatus to perform the operation.
33. Apparatus according to claim 32, wherein the apparatus is an electrofusion welding power supply.
34. Apparatus according to claim 33, wherein the electrofusion welding power supply is a battery powered electrofusion power supply.
35. A computer program comprising computer readable instructions which when run on a computing device, controls the computing device to implement a method according to any of claims 16 to 30.