Inferring motor energy consumption based on digital twin

Abstract

A method is disclosed, comprising: obtaining a process dataset associated with an industrial process, wherein the process dataset comprises measurement values associated with the industrial process during a time period; estimating, based at least in part on the process dataset and a plurality of digital twins associated with a plurality of motors, an energy consumption of each motor of the plurality of motors during the time period, wherein the plurality of digital twins comprises at least a first digital twin of a first motor and a second digital twin of a second motor different from the first motor; inferring, at least, an energy consumption of each motor of the plurality of motors during an expected total useful life of each motor; and indicating, at least, the inferred energy consumption of each motor of the plurality of motors.

Description

Technical Field

[0001] The following exemplary implementations relate to industrial automation and industrial communication networks. Background Technology

[0002] Proper motor size and selection are crucial for ensuring performance and reliability. Incorrectly sized motors can lead to reduced energy efficiency, accelerated component aging, and increased maintenance requirements due to excessive physical stress from operating in suboptimal environments. Summary of the Invention

[0003] The scope of protection sought by the various exemplary embodiments is defined by the independent claims. Exemplary embodiments and features (if any) described in this specification that do not fall within the scope of the independent claims are to be interpreted as examples useful for understanding the various exemplary embodiments.

[0004] According to one aspect, an apparatus is provided, the apparatus comprising at least one processor and at least one memory, the at least one memory including computer program code, wherein the at least one memory and the computer program code are configured, together with the at least one processor, to enable the apparatus to: obtain a process dataset associated with an industrial process, wherein the process dataset includes measurements associated with the industrial process over a time period; at least partially based on the process dataset and a plurality of digital twins associated with a plurality of motors, at least estimating the energy consumption of each of the plurality of motors over the time period, wherein the plurality of digital twins at least includes a first digital twin of a first motor and a second digital twin of a second motor different from the first motor; at least inferring the energy consumption of each of the plurality of motors over the expected total service life of each motor; and at least indicating the inferred energy consumption of each of the plurality of motors.

[0005] According to another aspect, an apparatus is provided, the apparatus comprising means for: obtaining a process dataset associated with an industrial process, wherein the process dataset includes measurements associated with the industrial process during a time period; at least partially based on the process dataset and a plurality of digital twins associated with a plurality of motors, at least estimating the energy consumption of each of the plurality of motors during the time period, wherein the plurality of digital twins at least include a first digital twin of a first motor and a second digital twin of a second motor different from the first motor; at least inferring the energy consumption of each of the plurality of motors during the expected total service life of each motor; and at least indicating the inferred energy consumption of each of the plurality of motors.

[0006] According to another aspect, a method is provided, comprising: obtaining a process dataset associated with an industrial process, wherein the process dataset includes measurements associated with the industrial process during a time period; at least partially based on the process dataset and a plurality of digital twins associated with a plurality of motors, at least estimating the energy consumption of each of the plurality of motors during the time period, wherein the plurality of digital twins at least include a first digital twin of a first motor and a second digital twin of a second motor different from the first motor; at least inferring the energy consumption of each of the plurality of motors during the expected total service life of each motor; and at least indicating the inferred energy consumption of each of the plurality of motors.

[0007] According to another aspect, a computer-implemented method is provided, comprising: obtaining a process dataset associated with an industrial process, wherein the process dataset includes measurements associated with the industrial process during a time period; at least partially based on the process dataset and a plurality of digital twins associated with a plurality of motors, at least estimating the energy consumption of each of the plurality of motors during the time period, wherein the plurality of digital twins at least include a first digital twin of a first motor and a second digital twin of a second motor different from the first motor; at least inferring the energy consumption of each of the plurality of motors during the expected total service life of each motor; and at least indicating the inferred energy consumption of each of the plurality of motors.

[0008] According to another aspect, a computer program product including program instructions is provided, which, when executed on a computing device, cause the computing device to perform at least the following operations: obtain a process dataset associated with an industrial process, wherein the process dataset includes measurements associated with the industrial process during a time period; at least partially estimate the energy consumption of each of the plurality of motors during the time period based on the process dataset and a plurality of digital twins associated with a plurality of motors, wherein the plurality of digital twins at least include a first digital twin of a first motor and a second digital twin of a second motor different from the first motor; at least infer the energy consumption of each of the plurality of motors during the expected total service life of each motor; and at least indicate the inferred energy consumption of each of the plurality of motors.

[0009] According to another aspect, a computer program is provided, comprising instructions for causing a device to at least perform the following operations: obtaining a process dataset associated with an industrial process, wherein the process dataset includes measurements associated with the industrial process during a time period; at least partially based on the process dataset and a plurality of digital twins associated with a plurality of motors, at least estimating the energy consumption of each of the plurality of motors during the time period, wherein the plurality of digital twins at least include a first digital twin of a first motor and a second digital twin of a second motor different from the first motor; at least inferring the energy consumption of each of the plurality of motors during the expected total service life of each motor; and at least indicating the inferred energy consumption of each of the plurality of motors.

[0010] According to another aspect, a computer-readable medium is provided, comprising program instructions for causing a device to perform at least the following operations: obtaining a process dataset associated with an industrial process, wherein the process dataset includes measurements associated with the industrial process during a time period; at least partially estimating the energy consumption of each of the plurality of motors during the time period based on the process dataset and a plurality of digital twins associated with a plurality of motors, wherein the plurality of digital twins at least include a first digital twin of a first motor and a second digital twin of a second motor different from the first motor; at least inferring the energy consumption of each of the plurality of motors during the expected total service life of each motor; and at least indicating the inferred energy consumption of each of the plurality of motors.

[0011] According to another aspect, a non-transitory computer-readable medium is provided, comprising program instructions for causing a device to perform at least the following operations: obtaining a process dataset associated with an industrial process, wherein the process dataset includes measurements associated with the industrial process during a time period; at least partially estimating the energy consumption of each of the plurality of motors during the time period based on the process dataset and a plurality of digital twins associated with a plurality of motors, wherein the plurality of digital twins at least include a first digital twin of a first motor and a second digital twin of a second motor different from the first motor; at least inferring the energy consumption of each of the plurality of motors during the expected total service life of each motor; and at least indicating the inferred energy consumption of each of the plurality of motors.

[0012] According to another aspect, a system is provided that includes at least a cloud server and a user device. The cloud server includes means for: acquiring a process dataset associated with an industrial process, wherein the process dataset includes measurements associated with the industrial process during a time period; estimating at least, in part, the energy consumption of each of the plurality of motors during the time period based on the process dataset and a plurality of digital twins associated with a plurality of motors, wherein the plurality of digital twins at least include a first digital twin of a first motor and a second digital twin of a second motor different from the first motor; inferring at least the energy consumption of each of the plurality of motors during the expected total service life of each motor; and indicating at least the inferred energy consumption of each of the plurality of motors to the user device. The user device includes means for: displaying at least the inferred energy consumption of each of the plurality of motors to a user.

[0013] According to another aspect, a system is provided that includes at least a cloud server and a user device. The cloud server is configured to: acquire a process dataset associated with an industrial process, wherein the process dataset includes measurements associated with the industrial process during a time period; estimate at least, in part, the energy consumption of each of the plurality of motors during the time period based on the process dataset and a plurality of digital twins associated with a plurality of motors, wherein the plurality of digital twins at least include a first digital twin of a first motor and a second digital twin of a second motor different from the first motor; infer at least the energy consumption of each of the plurality of motors during the expected total service life of each motor; and indicate at least the inferred energy consumption of each of the plurality of motors to the user device. The user device is configured to: display at least the inferred energy consumption of each of the plurality of motors to a user. Attached Figure Description

[0014] In the following description, various exemplary embodiments will be described in more detail with reference to the accompanying drawings, in which:

[0015] Figure 1 A communication system to which some exemplary implementations can be applied is shown;

[0016] Figure 2 A signaling diagram according to an exemplary embodiment is shown;

[0017] Figures 3 to 4 A flowchart according to some exemplary embodiments is shown;

[0018] Figure 5 A device according to an exemplary embodiment is shown. Detailed Implementation

[0019] The following embodiments are exemplary. Although the specification may refer to "a," "an," or "some" embodiments in several places in the text, this does not necessarily mean that each reference refers to the same embodiment(s) or that a particular feature applies only to a single embodiment. Individual features of different embodiments may also be combined to provide other embodiments.

[0020] The following embodiments are exemplary. Although the specification may refer to "a," "an," or "some" embodiments in several places in the text, this does not necessarily mean that each such reference refers to the same embodiment(s), or that a particular feature applies only to a single embodiment. Individual features of different embodiments may also be combined to provide other embodiments.

[0021] Various exemplary implementations can be applied to at least partially automated processes in industrial plants, including processing systems and / or industrial manufacturing-related processes and / or systems for technical processes, thereby providing different measured / sensed values ​​for multiple variables regarding one or more devices (equipment) and / or one or more processes. A non-limiting list of examples includes power plants, pulp and paper mills, manufacturing plants, chemical processing plants, power transmission systems, mining and mineral processing plants, oil and gas systems, data centers, and ship and transport fleet systems.

[0022] The following uses single units, models, apparatuses, and storage to describe different implementations and examples, without limiting the implementations / examples to such solutions. Concepts referred to as cloud computing and / or virtualization can be used. Virtualization can allow a single physical computing device to host one or more instances of virtual machines, which appear and operate as independent computing devices, enabling the single physical computing device to dynamically create, maintain, delete, or otherwise manage the virtual machines. Device operation can also be distributed across multiple servers, nodes, devices, or hosts. In cloud computing network devices, computing devices and / or storage devices provide shared resources. Other technological advancements, such as Software-Defined Networking (SDN), can migrate one or more of the functions described below to any corresponding abstract concept or device or apparatus. Therefore, all words and expressions should be interpreted broadly, and they are intended to illustrate rather than limit the exemplary implementations.

[0023] When commissioning a new motor, its size can be determined based on the anticipated requirements of the industrial process to select a motor suitable for that process. However, the requirements of the process may change over time and become different from what was expected during motor commissioning. For example, the initial motor size may be based on an overestimation of the actual production volume of the process, which could result in an oversized motor. Therefore, the initially commissioned motor may not be optimally suited for the process given the changing requirements. Correct motor size and selection are crucial to ensuring performance and reliability. An incorrectly sized motor may still meet the process requirements, but the excessive physical stress from operating in a suboptimal environment will lead to reduced energy efficiency, accelerated component aging, and increased maintenance requirements over the motor's expected total service life (e.g., 20 years).

[0024] Some exemplary implementations can achieve retrospective motor optimization by considering the motor's expected total lifespan and process requirements. Retrospective motor optimization means replacing the initially commissioned motor with another motor that is more optimally suited to the process requirements. For example, some exemplary implementations can help select a more optimized motor, thereby reducing total energy consumption and / or maintenance requirements over the motor's expected total lifespan. This can be done by creating a simulation (virtual representation) of the industrial process using a digital twin of the motor based on collected real process data, such as speed and torque varying over time, environmental conditions, etc. A digital twin is a virtual representation (or virtual model) that serves as a digital counterpart to a physical object, system, or process. Once process data has been collected during a monitoring period, the performance (e.g., energy consumption) of an existing motor during the monitoring period can be estimated and inferred based on this simulation over the motor's entire expected total lifespan. This estimation and inference can then be applied to digital twins of different motors to find the motor that provides optimal performance (e.g., the lowest energy consumption over the motor's expected total lifespan).

[0025] Figure 1 A communication system to which some exemplary implementations can be applied is shown. (Refer to...) Figure 1 Some exemplary implementations may be based on wireless communications, such as 3G (third generation), 4G (fourth generation), LTE (Long Term Evolution), LTE-A (Advanced Long Term Evolution), 5G (fifth generation), 5G NR (New Radio), UMTS (Universal Mobile Telecommunications System), EDGE (Enhanced Data Rate GSM Evolution), WCDMA (Wideband Code Division Multiple Access), Bluetooth, WLAN (Wireless Local Area Network), Wi-Fi, Li-Fi (Light Fidelity), or any other mobile or wireless network. Communication may also occur between nodes belonging to different but compatible systems, such as LTE and 5G. Alternatively, some exemplary implementations may be at least partially based on a wired connection.

[0026] It should be noted that Figure 1 A simplified system architecture is shown, illustrating only some of the elements and functional entities, all of which are logical units whose implementations may differ from those shown. Figure 1 The connections shown are logical connections; actual physical connections may differ. Data collection may utilize a so-called master protocol, in which a master network node subscribes to data from slave devices (devices whose data the master network node wants to possess), and the slave devices / network nodes send their data to the receiver / master device based on queries or automatically based on subscriptions. It will be apparent to those skilled in the art that the system also includes other functions and structures. It should be understood that the functions, structures, elements, and protocols used in or for communication are unrelated to the exemplary implementation. Therefore, they need not be discussed in further detail here.

[0027] The system may include a variable speed drive 101. A variable speed drive may also be referred to as a variable frequency drive. The variable speed drive 101 can be used to operate machines, such as motor 102 and / or pumps, at different speeds. The variable speed drive 101 may be electrically connected to the machine. Motor 102 may also be referred to as an electric motor, induction motor, or alternating current (AC) motor. The variable speed drive 101 may include or be connected to a controller, such as a proportional-integral-derivative (PID) controller. The controller may be configured to send control signals to the variable speed drive 101. The variable speed drive 101 can control highly dynamic industrial processes in which, for example, the speed or torque applied to motor 102 must vary according to the needs of the industrial process.

[0028] The variable speed drive 101 may store information about control parameter settings, such as controller gain, ramp time, motor data, limits, magnetization settings, signal filtering settings, and / or current values ​​of motor control parameters, for example, in internal or external memory. The variable speed drive 101 may also store operational information recorded during operation, such as information about key performance indicators, such as load current histograms, torque pulsation, torque-to-speed curves and / or power-to-speed curves, temperature, voltage, current, and / or other information such as resonant frequency and / or load inertia.

[0029] The transmission drive 101 may be equipped with a short-range communication interface, such as Bluetooth, Ethernet, ZigBee, Li-Fi, Wi-Fi, wireless mesh networking, near field communication (NFC), or any other wireless or wired connection. The short-range communication interface may be included, for example, within the transmission drive 101 or in the control panel of the transmission drive 101. The transmission drive 101 may be configured to communicate with the motor 102 and / or one or more sensor devices 103 via the short-range communication interface.

[0030] Furthermore, the transmission drive 101 can connect to the Internet via a network interface such as 3G, 4G, LTE, LTE-A, 5G, 5G NR, UMTS, EDGE, WCDMA, WLAN, Wi-Fi, Li-Fi, or any other mobile, wireless, or wired network. The network interface can be included, for example, within the transmission drive 101 itself or in its control panel. The transmission drive 101 can connect to a cloud server 104 via the network interface. The transmission drive 101 can connect to the cloud server directly (e.g., via a cellular link) or via a gateway device such as an edge gateway. The transmission drive 101 can be configured to exchange information with the cloud server 104, i.e., send and / or receive data. For example, the transmission drive 101 can be configured to send alarms and fault logs, real-time operating information, and / or existing control parameter settings to the cloud server 104. Existing control parameter settings refer to the control parameters currently applied to the transmission drive 101.

[0031] Motor 102 may be equipped with a short-range communication interface, such as Bluetooth, Ethernet, ZigBee, Li-Fi, Wi-Fi, wireless mesh networking, NFC, or any other wireless or wired connection. Motor 102 may be configured to communicate with transmission drive 101 and / or one or more sensor devices 103 via the short-range communication interface.

[0032] Furthermore, motor 102 can connect to the Internet via a network interface such as 3G, 4G, LTE, LTE-A, 5G, 5G NR, UMTS, EDGE, WCDMA, WLAN, Wi-Fi, Li-Fi, or any other mobile, wireless, or wired network. Motor 102 can connect to cloud server 104 via a network interface. Motor 102 can connect to the cloud server directly (e.g., via a cellular link) or via a transmission drive 101, or via a gateway device such as an edge gateway. Motor 102 can be configured to exchange information with cloud server 104, i.e., send and / or receive data. For example, motor 102 can be configured to send real-time process data and / or historical process data to cloud server 104. Process data may include, for example, measurements of the motor's speed, torque, and / or temperature over time. Process data may also include measurements of environmental conditions, such as external temperature and / or humidity outside the motor. Process data may be associated with an industrial process in which motor 102 is part.

[0033] Process data can be measured by one or more sensor devices 103. One or more sensor devices 103 may be included in, attached to, or adjacent to the motor 102. One or more sensor devices 103 may be configured to measure, for example, the speed, torque, and / or temperature of the motor 102. For example, separate sensor devices may be present for measuring speed and temperature, respectively. At least one of the one or more sensor devices 103 may be configured to measure environmental conditions, such as temperature, in the external environment of the motor 102.

[0034] Furthermore, the variable speed drive 101 can be configured to measure additional process data, such as the switching frequency, slip, and flux associated with the motor 102. The switching frequency can refer to the rate at which the DC bus voltage is switched on and off during a pulse-width modulation process. The slip can refer to the difference between the synchronous speed (the rotational speed of the motor's magnetic field) and the rotor speed (the speed of the rotating part of the motor). The slip can be expressed as the ratio of the rotor speed to the synchronous speed. The flux can refer to the magnetic flux of the motor's magnetic field.

[0035] One or more sensor devices 103 may be equipped with a short-range communication interface, such as Bluetooth, Ethernet, ZigBee, Li-Fi, Wi-Fi, wireless mesh networking, NFC, or any other wireless or wired connection. One or more sensor devices may be configured to communicate with the motor 102 and / or the transmission drive 101 via the short-range communication interface. For example, one or more sensor devices 103 may be configured to transmit measured process data to the motor 102 and / or the transmission drive 101 via the short-range communication interface.

[0036] Furthermore, one or more sensor devices 103 can connect to the Internet via a network interface such as 3G, 4G, LTE, LTE-A, 5G, 5G NR, UMTS, EDGE, WCDMA, WLAN, Wi-Fi, Li-Fi, or any other mobile, wireless, or wired network. One or more sensor devices 103 can connect to a cloud server 104 via a network interface. One or more sensor devices 103 can connect to the cloud server directly (e.g., via a cellular link) or via a gateway device such as an edge gateway. One or more sensor devices 103 can be configured to exchange information with the cloud server 104, i.e., send and / or receive data. For example, one or more sensor devices 103 can be configured to send measured process data to the cloud server 104.

[0037] The cloud server 104 can be configured to exchange information with the transmission drive 101, the motor 102, one or more sensor devices 103 and / or with the user device 105, i.e., to send and / or receive data. The cloud server 104 can also be configured to store the received information, such as received process data, in at least one memory 104-1.

[0038] Cloud server 104 can be configured to simulate industrial processes using a digital twin of motor 102 and received process data. Cloud server 104 can also be configured to simulate industrial processes based on process data and digital twins of one or more other motors different from motor 102. Cloud server 104 includes a digital twin database 104-2, which includes digital twins of motor 102 and one or more other motors. The digital twins can be predefined models provided by motor manufacturers. Alternatively, the digital twins can be user-defined models. Digital twin database 104-1 can also include digital twins of other devices and / or systems, such as a digital twin of variable speed drive 101.

[0039] The cloud server 104 can be configured to estimate the energy consumption and / or maintenance requirements of motor 102 and one or more other motors based on simulation.

[0040] The cloud server 104 can be configured to infer or predict the energy consumption and / or maintenance requirements of motor 102 and one or more other motors during the expected total service life of a given motor based on this estimate.

[0041] The cloud server 104 can also be connected to the user device 105. For example, the cloud server 104 can be configured to indicate to the user device 105 the inferred energy consumption of each motor, the inferred maintenance requirements of each motor, and / or recommended motors. The user device 105 can be configured to display or visualize, for example, the inferred energy consumption of each motor, the inferred maintenance requirements of each motor, and / or recommended motors to the user of the user device 105 in a graphical user interface.

[0042] User device 105 may include user equipment such as a smartphone, mobile phone, tablet, laptop, desktop computer, or any other computing device. User device 105 may be a remote device located at a different location from motor 102. Alternatively, user device 105 may be a local device located very close to motor 102 in the field.

[0043] User equipment 105 can connect to the Internet via a network interface such as 3G, 4G, LTE, LTE-A, 5G, 5GNR, UMTS, EDGE, WCDMA, WLAN, Wi-Fi, Li-Fi, Ethernet, or any other mobile, wireless, or wired network. User equipment 105 can be configured to exchange information with cloud server 104 via the network interface, i.e., send and / or receive data.

[0044] User device 105 may be equipped with a short-range communication interface to provide local connectivity to transmission drive 101, motor 102, and / or one or more sensor devices 103. The short-range communication interface may be, for example, Bluetooth, Ethernet, ZigBee, Wi-Fi, Li-Fi, wireless mesh networking, NFC, or any other wireless or wired connection. User device 105 may be configured to exchange information with transmission drive 101 and / or motor 102, i.e., to send and / or receive data. For example, user device 105 may be configured to send control parameters and / or other configuration changes to transmission drive 101 and / or motor 102. As another example, user device 105 may be configured to forward process data from transmission drive 101, motor 102, and / or one or more sensor devices 103 to cloud server 105 (i.e., user device 105 may act as a gateway).

[0045] Figure 2 A signaling diagram according to an exemplary implementation is shown. In this exemplary implementation, real-world process data associated with an initially commissioned motor is collected and used for backtracking motor optimization. After the process data has been collected, the motor's operating environment is simulated in the cloud. This process can be simulated using digital twins of several different motors, thereby tracking efficiency and energy consumption and estimating physical stress and maintenance requirements based on motor and component life models. This data can then be extrapolated over the expected total service life of a given motor to estimate total energy consumption and / or maintenance requirements over the expected total service life of the motor.

[0046] Reference Figure 2 The initially commissioned motor sends a process dataset associated with the industrial process to the cloud server, whereby the process data includes measurements of the industrial process during a certain monitoring period. Alternatively, the process dataset can be sent to the cloud server via a variable speed drive and / or one or more sensor devices connected to the motor. The process data may include, for example, speed, torque, and / or temperature values ​​of the initially commissioned motor during the monitoring period. The process data may also include measurements of environmental conditions associated with the industrial process during the monitoring period, such as temperature and / or humidity. In other words, the process data is obtained using an initially commissioned motor (a real physical motor) with a (real) industrial process.

[0047] If the motor is connected to a variable speed drive, the variable speed drive can also send additional process data to the cloud server. This additional process data may include, for example, measurements of the motor's associated switching frequency, slip, and / or flux.

[0048] The cloud server can retrospectively collect process data for the monitoring period after the motor has been debugged. Alternatively, data collection can begin immediately (or almost immediately) when the motor is first installed and started.

[0049] The monitoring period for data collection should be long enough to determine what operations the industrial process requires (i.e., to determine the requirements of the industrial process). The monitoring period depends on the type of process and can range from a few days to more than a year. For processes with minor variations, such as constant-rate pump applications under optimal environmental conditions, a shorter monitoring period may be sufficient. Longer periods can be used to track seasonal variations in process and environmental conditions.

[0050] Once the process data has been collected, the cloud server simulates the monitored industrial process in parallel using each of the multiple digital twins (motor models) associated with multiple different motors (motor types). Different motors can refer to motors with different performance or capacity, such as operating at different speeds, electrical power, and / or torque compared to each other.

[0051] Because simulation models may contain some errors compared to the real process, a digital twin of the initially commissioned motor can also be used to simulate the process to provide comparable results relative to other (simulated) motors. Alternatively, the performance (e.g., energy consumption) of the initially commissioned motor can be estimated using an actual physical motor with a real industrial process, rather than simulating the industrial process using a digital twin of the initially commissioned motor. The actual performance of the initially commissioned motor can then be compared to the simulated performance of other motors.

[0052] While the simulation is running, the cloud server can track parameters that may need to be optimized. For example, based on a simulation performed for a specific motor, the cloud server can estimate the energy consumption of at least 204 motors during the monitoring period.

[0053] The cloud server can also estimate the maintenance needs of each of the 205 motors during the monitoring period. Using precise digital twins (motor models) and information about the motor's operating environment, motor heating and cooling can be monitored, and how they affect the motor's maintenance needs can be estimated. In other words, the maintenance needs of a given motor can be estimated, at least in part, based on the temperature values ​​indicated by the digital twin corresponding to that particular motor during the simulation.

[0054] The cloud server infers the energy consumption and / or maintenance requirements of each motor during its expected total lifespan. Inference can also be referred to as prediction. Therefore, the cloud server can estimate the total energy efficiency and total wasted energy of a given motor during its expected total lifespan.

[0055] This inference can indicate how energy consumption and maintenance requirements will evolve over the expected total lifespan of each motor. For example, the following equation can be used to estimate the total cost of a given motor, where the total cost represents the total energy consumption and maintenance requirements of the given motor over its expected total lifespan:

[0056]

[0057] Where TUL is the expected total lifespan of the motor, T o T1 is the start of the monitoring period, and P is the end of the monitoring period. E is the motor power (e.g., in kilowatts) monitored at a given time t, and x is an estimate of the energy cost per kilowatt-hour (kWh).

[0058] To compare the performance of different motors, the total cost per unit of time can be used. Therefore, the motor with the lowest total cost per unit of time can be determined as the optimal motor for the process. For example, the total cost per unit of time can be defined as:

[0059]

[0060] Total Expected Life (TUL) is equal to the Expected Remaining Life (RUL) of a brand-new motor. The TUL of a given motor can include the time window from the start of motor installation or commissioning to the expected end of motor operation. The TUL can also include a monitoring period during which process data is collected using the initially commissioned motor.

[0061] The expected total service life can vary between different motors. Furthermore, the expected total service life of a given motor may not be constant, as it can vary depending on the motor's operating conditions and / or environmental conditions. For example, the bearing life of a motor may depend on the estimated bearing temperature and the motor's operating speed.

[0062] Operating and / or environmental conditions can be indicated by process data collected during the monitoring period using an initially commissioned motor (i.e., the actual physical motor). The operating and / or environmental conditions during the expected total service life of a given motor can be assumed to correspond to the operating and / or environmental conditions observed during the monitoring period.

[0063] The expected total service life of a given motor can be determined using a manufacturer's life model based on collected process and / or environmental data, using that specific motor. The life model defines the expected total service life of one or more components (e.g., bearings) of the motor under given operating and / or environmental conditions. Based on the operating conditions (e.g., stress) and / or environmental conditions monitored during the monitoring period, the expected total service life of each motor can be determined under these specific conditions. Therefore, the expected total service life of a motor undergoing initial commissioning is comparable to the expected total service life of other motors.

[0064] Maintenance costs are used as an indicator of motor maintenance needs. If this amount does not vary between different motors and is assumed to be constant, maintenance costs can be ignored. Furthermore, the total cost may include some initial costs of purchasing and installing the motor to assess whether replacing the initially commissioned motor with the new one is worthwhile.

[0065] This motor can be used in repetitive industrial applications or more dynamic industrial applications. In more dynamic applications, additional simulations can be run compared to repetitive applications to see what would happen to the estimated energy consumption and maintenance requirements if process requirements change.

[0066] The cloud server instructs the user device on 207 inference results, which include the inferred energy consumption and / or maintenance requirements for each motor over its expected total lifespan. Therefore, the results indicate how energy-efficient the existing motor (i.e., the initially commissioned motor) compares to other (simulated) motors. In other words, the results indicate whether it would be beneficial to replace the initially commissioned motor with some other motor that is more energy-efficient and / or has lower maintenance requirements than the existing motor over its expected total lifespan. For example, for an industrial process, the motor associated with the lowest inferred total cost could be the most energy-efficient and / or the motor with the lowest maintenance requirements. Furthermore, the cloud server can explicitly instruct (or recommend) the user device the optimal motor among multiple motors that has the lowest inferred energy consumption and / or the lowest combined inferred energy consumption and inferred maintenance requirements.

[0067] The user device can, for example, display 208 or visualize recommended motors and / or inferences about different motors to the user of the user device via a graphical user interface. The user can then decide, for example, to replace the initially debugged motor with the recommended motor to retrospectively optimize the motor.

[0068] Figure 3 A flowchart according to an exemplary implementation is shown. Figure 3 The functions shown can be performed by a device such as a cloud server or any other computing device, or by a device included in a cloud server or any other computing device.

[0069] Reference Figure 3 This process dataset, associated with the industrial process, is obtained. The process dataset includes measurements associated with the industrial process during a specific time period. The time period refers to the monitoring period.

[0070] The process dataset can be obtained using a motor undergoing initial commissioning in an industrial process (i.e., a real motor). At least a subset of the process dataset can be obtained by receiving it from the initially commissioned motor, and / or from a variable speed drive connected to the initially commissioned motor, and / or from one or more sensor devices. The initially commissioned motor may also be referred to herein as a third motor.

[0071] Based at least in part on a process dataset and multiple digital twins associated with multiple motors, the energy consumption of each of at least 302 motors during a given time period is estimated, wherein the multiple digital twins include at least a first digital twin of a first motor and a second digital twin of a second motor different from the first motor. In other words, the energy consumption of each motor during the given time period is estimated, but the estimation itself is not necessarily performed during the given time period.

[0072] The energy consumption and / or maintenance requirements of the third motor (the motor initially commissioned) during the time period can be estimated based on the third digital twin of the third motor. Alternatively, the energy consumption and / or maintenance requirements of the third motor during the time period can be estimated by using or operating a third motor with a real industrial process (i.e., a real physical motor) instead of using the digital twin of the third motor.

[0073] Energy consumption for each of at least 303 motors (i.e., per motor) during the expected total service life of each motor is inferred. In other words, the energy consumption of a given motor can be inferred over a time window from the start of the motor's installation / commissioning to the end of its expected shutdown operation, where this time window includes the period during which measurements in process data are collected. For example, the energy consumption of a first motor can be inferred over the expected total service life of the first motor, and the energy consumption of a second motor can be inferred over the expected total service life of the second motor. The expected total service life of the second motor may differ from that of the first motor. In other words, the inferred energy consumption of a given motor during its specific expected total service life can be determined based on the estimated energy consumption of that specific motor during that time period.

[0074] The estimated energy consumption of each of the more than 304 motors (i.e., per motor) is indicated to, for example, a user device. The estimated energy consumption may differ for different motors. For example, the estimated energy consumption of the first motor may differ from the estimated energy consumption of the second motor.

[0075] It should be noted that the terms "first motor," "second motor," and "third motor" are used herein to distinguish different motors, and they do not necessarily imply a specific order of the motors. Similarly, the terms "first digital twin," "second digital twin," and "third digital twin" are used herein to distinguish different digital twins, and they do not necessarily imply a specific order of the digital twins.

[0076] Figure 4 A flowchart according to another exemplary implementation is shown. Figure 4 The functions shown can be performed by a device such as a cloud server or any other computing device, or by a device included in a cloud server or any other computing device.

[0077] Reference Figure 4 The expected total service life of each of the 401+ motors is estimated, at least in part, based on process data and a life model for each of the multiple motors. For example, the expected total service life of the first motor can be estimated, at least in part, based on process data and a life model for the first motor. The expected total service life of the second motor can be estimated, at least in part, based on process data and a life model for the second motor. The expected total service life of the third motor can be estimated, at least in part, based on process data and a life model for the third motor.

[0078] The above uses Figures 2 to 4 The described functions and / or blocks do not have an absolute temporal order, and some of them may execute concurrently or in a different order than described. Other functions and / or blocks may also execute between or within them. For example, Figure 4 Box 401 can be Figure 3 Execute between boxes 302 and 303, or in Figure 3 Execute between boxes 301 and 302.

[0079] The technical advantages provided by some exemplary embodiments are that they can reduce motor energy consumption and / or physical wear by improving motor size, making it possible to select an optimal (or near-optimal) motor for a given process. For example, some exemplary embodiments can help select a better motor when process requirements have changed and the initially commissioned motor does not operate optimally. Thus, some exemplary embodiments can help avoid using an incorrectly sized motor, which would lead to excessive energy consumption and / or premature motor wear due to insufficient or excessive capacity.

[0080] Figure 5Device 500 is shown, which may be a device such as a cloud server, user device, motor, or any other computing device, or a device included in a cloud server, user device, motor, or any other computing device. Device 500 includes a processor 510. Processor 510 interprets computer program instructions and processes data. Processor 510 may include one or more programmable processors. Processor 510 may include programmable hardware with embedded firmware and may alternatively or additionally include one or more application-specific integrated circuits (ASICs).

[0081] Processor 510 is coupled to memory 520. The processor is configured to read data from memory 520 and write data to memory 520. Memory 520 may include one or more memory cells. Memory cells may be volatile or non-volatile. Note that in some exemplary embodiments, one or more cells of non-volatile memory and one or more cells of volatile memory may be present; or alternatively, one or more cells of non-volatile memory may be present; or alternatively, one or more cells of volatile memory may be present. Volatile memory may be, for example, random access memory (RAM), dynamic random access memory (DRAM), or synchronous dynamic random access memory (SDRAM). Non-volatile memory may be, for example, read-only memory (ROM), programmable read-only memory (PROM), electrically erasable programmable read-only memory (EEPROM), flash memory, optical memory, or magnetic memory. Generally, memory may be referred to as a non-transitory computer-readable medium. Memory 520 stores computer-readable instructions that are executed by processor 510. For example, non-volatile memory stores computer-readable instructions, and processor 510 uses volatile memory for temporary storage of data and / or instructions to execute instructions.

[0082] The computer-readable instructions may have been pre-stored in memory 520, or alternatively or otherwise, the computer-readable instructions may be received by the device via an electromagnetic carrier signal and / or copied from a physical entity such as a computer program product. Execution of the computer-readable instructions causes the device 500 to perform one or more of the functions described above.

[0083] In the context of this document, "memory" or "computer-readable medium" or "computer-readable device" can be any non-transitory medium or device that can contain, store, transmit, propagate or transfer instructions for use by or in conjunction with an instruction execution system, device or apparatus such as a computer.

[0084] Device 500 may also include or be connected to input unit 530. Input unit 530 may include one or more interfaces for receiving input. One or more interfaces may include, for example, one or more temperature sensors, motion sensors and / or orientation sensors, one or more camera devices, one or more accelerometers, one or more microphones, one or more buttons and / or one or more touch detection units. Furthermore, input unit 530 may include interfaces to which external devices can be connected.

[0085] The device 500 may also include an output unit 540. The output unit may include or be connected to one or more displays capable of displaying visual content, such as light-emitting diode (LED) displays, liquid crystal displays (LCDs), and / or liquid crystal on silicon (LCoS) displays. The output unit 540 may also include one or more audio outputs. The one or more audio outputs may be, for example, speakers.

[0086] Device 500 also includes a connection unit 550. Connection unit 550 enables wired and / or wireless connections to one or more external devices. Connection unit 550 may include at least one transmitter and at least one receiver, which may be integrated into device 500 or connected to it. At least one transmitter includes at least one transmitting antenna, and at least one receiver includes at least one receiving antenna. Connection unit 550 may include an integrated circuit or set of integrated circuits providing communication capabilities to device 500. Alternatively, the connection may be a hardwired application-specific integrated circuit (ASIC). Connection unit 550 may include one or more components, such as a power amplifier, digital front-end (DFE), analog-to-digital converter (ADC), digital-to-analog converter (DAC), frequency converter, modulator (demodulator), and / or encoder / decoder circuitry, controlled by corresponding control units.

[0087] Note that device 500 may also include Figure 5 Various components not shown. These components may be hardware components and / or software components.

[0088] As used in this application, the term "circuit system" may refer to one or more or all of the following: a) a purely hardware circuit implementation (e.g., an implementation in an analog and / or digital circuit system only); and b) a combination of hardware circuitry and software, such as (if applicable): i) a combination of analog and / or digital hardware circuitry with software / firmware, and ii) any part of a hardware processor having software (including digital signal processors, software, and memory that work together to enable a device, such as a smartphone, to perform various functions); and c) hardware circuitry and / or processors that require software (e.g., firmware) for operation, such as a microprocessor or a portion thereof, but where the software may be absent when operation does not require it.

[0089] This definition of "circuit system" applies to all uses of the term in this application, including its use in any claim. As another example, as used herein, the term "circuit system" also covers implementations of hardware circuitry or processors (or processors) alone, or of hardware circuitry or processors and their accompanying software and / or firmware. For example, and where applicable to specific claim elements, the term "circuit system" also covers baseband integrated circuits or processor integrated circuits used in similar integrated circuits in mobile devices or servers, cellular network devices, or other computing or networking devices.

[0090] The techniques and methods described herein can be implemented in various ways. For example, these techniques can be implemented in hardware (one or more devices), firmware (one or more devices), software (one or more modules), or a combination thereof. For hardware implementation, devices of exemplary embodiments can be implemented in one or more of the following: application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), image processing units (GPUs), processors, controllers, microcontrollers, microprocessors, or other electronic units designed to perform the functions described herein. For firmware or software, the implementation can be performed by modules (e.g., processes, functions, etc.) of at least one chipset that perform the functions described herein. Software code can be stored in memory cells and executed by a processor. Memory cells can be implemented within or outside the processor. In the latter case, as is known in the art, memory cells can be communicatively coupled to the processor in various ways. Furthermore, the components of the systems described herein can be rearranged and / or supplemented by other components to facilitate the implementation of various aspects described herein, and these components are not limited to the precise configurations illustrated in the given figures, as will be understood by those skilled in the art.

[0091] It will be apparent to those skilled in the art that the inventive concept can be implemented in various ways as technology advances. The embodiments are not limited to the exemplary embodiments described above, but may vary within the scope of the claims. Therefore, all words and expressions should be interpreted broadly, and they are intended to be illustrative rather than limiting of the exemplary embodiments.

Claims

1. A device for inferring motor energy consumption, the device comprising at least one processor and at least one memory, the at least one memory comprising computer program code, wherein, The at least one processor is configured to, when executing the computer program code: A process dataset associated with the industrial process is obtained by using an initially commissioned motor with the industrial process, wherein the process dataset includes measurements associated with the industrial process over a time period; Receive multiple digital twins for multiple motors from a digital twin database, the multiple motors being selectable to replace the motors used in the initial commissioning of the industrial process; The industrial process is simulated by at least partially based on the process dataset and the plurality of digital twins associated with the plurality of motors, and the energy consumption of each of the plurality of motors is estimated during the time period, wherein the plurality of digital twins includes at least a first digital twin of a first motor and a second digital twin of a second motor that is different from the first motor; At least the energy consumption of each of the plurality of motors during the expected total service life of each of the plurality of motors is inferred, wherein the inference is made at least in part based on the expected total service life of each of the plurality of motors, the power of each of the plurality of motors, and the time period during which the measurement is obtained; At least the estimated energy consumption of each of the plurality of motors is indicated; Based on the inferred energy consumption, a motor is selected from the plurality of motors; and The selected motor is controlled using the selected motor's control parameters.

2. The device according to claim 1, wherein, The processor is also configured to: Based at least in part on the process dataset and the plurality of digital twins, the maintenance requirements of each of the plurality of motors during the time period are estimated; Estimate the maintenance requirements of each of the plurality of motors during the expected total service life of each of the plurality of motors; as well as Indicates the inferred maintenance requirements for each of the plurality of motors.

3. The device according to claim 1 or 2, wherein, The maintenance requirements of each of the plurality of motors are estimated, at least in part, based on the temperature of each of the plurality of motors as indicated by the respective digital twins in the plurality of digital twins.

4. The device according to claim 1 or 2, wherein, The processor is also configured to: Indicates the motor among the plurality of motors that has the lowest inferred energy consumption.

5. The device according to claim 1, wherein, The motor being initially tested is included among the plurality of motors, and the energy consumption of the motor being initially tested is estimated at least in part based on the process dataset and a third digital twin of the motor being initially tested.

6. The device according to claim 1, wherein, The processor is also configured to: The energy consumption of the initially commissioned motor during the time period is estimated by using the industrial process with the initially commissioned motor during the time period. Estimate the energy consumption of the initially commissioned motor during its expected total service life. as well as Indicates the inferred energy consumption of the motor during the initial commissioning.

7. The device according to claim 1 or 2, wherein, The energy consumption of each of the plurality of motors is estimated by simulation of the industrial process running in parallel for each of the plurality of digital twins.

8. The device according to claim 1, wherein, The process data includes measurements of at least one of speed, torque, temperature, switching frequency, slip, and / or flux during the said time period.

9. The device according to claim 8, wherein, The process data also includes measurements of environmental conditions associated with the industrial process during the time period.

10. The device according to claim 1 or 2, wherein, The processor is also configured to: The expected total service life of each of the plurality of motors is estimated, at least in part, based on the process data and the life model of each of the plurality of motors.

11. A method for inferring motor energy consumption, the method comprising: A process dataset associated with the industrial process is obtained by using an initially commissioned motor with the industrial process, wherein the process dataset includes measurements associated with the industrial process over a time period; Receive multiple digital twins for multiple motors from a digital twin database, the multiple motors being selectable to replace the motors used in the initial commissioning of the industrial process; The industrial process is simulated by at least partially based on the process dataset and the plurality of digital twins associated with the plurality of motors, and the energy consumption of each of the plurality of motors is estimated during the time period, wherein the plurality of digital twins includes at least a first digital twin of a first motor and a second digital twin of a second motor that is different from the first motor; At least the energy consumption of each of the plurality of motors during the expected total service life of each of the plurality of motors is inferred, wherein the inference is made at least in part based on the expected total service life of each of the plurality of motors, the power of each of the plurality of motors, and the time period during which the measurement is obtained; At least the estimated energy consumption of each of the plurality of motors is indicated; Based on the inferred energy consumption, a motor is selected from the plurality of motors; and The selected motor is controlled using the selected motor's control parameters.

12. A computer-readable medium comprising program instructions that, when executed by at least one processor of a device, cause the device to perform at least the following operations: A process dataset associated with the industrial process is obtained by using the initially debugged motor in conjunction with the industrial process, wherein, The process dataset includes measurements associated with the industrial process over a period of time; Receive multiple digital twins for multiple motors from a digital twin database, the multiple motors being selectable to replace the motors used in the initial commissioning of the industrial process; The industrial process is simulated by at least partially based on the process dataset and the plurality of digital twins associated with the plurality of motors, and the energy consumption of each of the plurality of motors is estimated during the time period, wherein the plurality of digital twins includes at least a first digital twin of a first motor and a second digital twin of a second motor that is different from the first motor; At least the energy consumption of each of the plurality of motors during the expected total service life of each of the plurality of motors is inferred, wherein the inference is made at least in part based on the expected total service life of each of the plurality of motors, the power of each of the plurality of motors, and the time period during which the measurement is obtained; At least the estimated energy consumption of each of the plurality of motors is indicated; Based on the inferred energy consumption, a motor is selected from the plurality of motors; and The selected motor is controlled using the selected motor's control parameters.

13. A system for inferring motor energy consumption, the system comprising at least a cloud server and a user device. in, The cloud server is configured as follows: A process dataset associated with the industrial process is obtained by using an initially commissioned motor with the industrial process, wherein the process dataset includes measurements associated with the industrial process over a time period; Receive multiple digital twins for multiple motors from a digital twin database, the multiple motors being selectable to replace the motors used in the initial commissioning of the industrial process; The industrial process is simulated by at least partially based on the process dataset and the plurality of digital twins associated with the plurality of motors, and the energy consumption of each of the plurality of motors is estimated during the time period, wherein the plurality of digital twins includes at least a first digital twin of a first motor and a second digital twin of a second motor that is different from the first motor; At least the energy consumption of each of the plurality of motors during the expected total service life of each of the plurality of motors is inferred, wherein the inference is made at least in part based on the expected total service life of each of the plurality of motors, the power of each of the plurality of motors, and the time period for which the measurements are obtained; and The user device is informed at least of the estimated energy consumption of each of the plurality of motors; The user equipment is configured to: The estimated energy consumption of at least each of the plurality of motors shall be displayed to the user. The cloud server is also configured as follows: Based on the inferred energy consumption, a motor is selected from the plurality of motors; and The selected motor is controlled using the selected motor's control parameters.

Images