Maintenance system and procedures for analyzing and / or generating health information for a hardware system

Abstract

A maintenance system (10) for maintaining a hardware system (12) is described. The maintenance system (10) comprises a data acquisition module (28) and an analysis module (20). The data acquisition module (28) is configured to acquire several operating parameters of the hardware system (12), which are relevant to the health status of the hardware system (12). The data acquisition module (28) is configured to forward the several operating parameters to the analysis module (20). The analysis module (20) is configured to determine, based on the several operating parameters, a device status point value for the hardware system (12), a remaining service life of the hardware system (12), and / or a user recommendation for operating the hardware system (12). Furthermore, a method for analyzing and / or generating health information for a hardware system (12) is described.

Description

[0001] The present invention generally relates to a maintenance system for maintaining a hardware system. The present invention further relates to a method for analyzing and / or generating health information for a hardware system.

[0002] In general, it is desirable to avoid unexpected failures of measuring instruments used to test a device under test.

[0003] Typically, such unexpected failures of measuring instruments are avoided by regularly scheduled preventive maintenance of the measuring instruments carried out by the manufacturer.

[0004] There are several different factors that determine the frequency of maintenance required to prevent unexpected failures of the measuring equipment.

[0005] Furthermore, the measuring equipment may already be operating outside of its ideal operating parameters, even if the measuring equipment has not yet failed.

[0006] Therefore, the object of the present invention is to provide a maintenance system for maintaining a hardware system and a method for analyzing and / or creating health information for a hardware system, which enables optimized maintenance of the hardware system.

[0007] According to the present invention, this object is achieved by a maintenance system for maintaining a hardware system. The maintenance system comprises a recording module and an analysis module. The recording module is configured to record a plurality of operating parameters of the hardware system, wherein the plurality of operating parameters are relevant to a health status of the hardware system. The recording module is configured to forward the plurality of operating parameters to the analysis module. The analysis module is configured to determine, based on the plurality of operating parameters, a device health score for the hardware system, a remaining service life of the hardware system, and / or a user recommendation for operating the hardware system.

[0008] The term "operating" parameters refers to parameters that relate to internal settings of the hardware system, to properties of signals processed in the hardware system, to currents flowing in the hardware system, and / or to voltages within the hardware system. Furthermore, the term "operating parameters" can refer to properties of the hardware system itself and / or to properties of the hardware system's environment.

[0009] The maintenance system according to the present invention is configured to assist a user in maintaining the hardware system in one or more ways. In general, the maintenance system according to the present invention enables monitoring of the hardware system and performing appropriate maintenance on the hardware system as needed.

[0010] The maintenance system or analysis module can determine the device health score (DHS) based on the multiple operating parameters.

[0011] In general, the DHS is an indicator of the health status of the hardware system, in particular the health status of the hardware system as a whole or of individual subsystems of the hardware system.

[0012] The DHS can be a number within a predetermined range, e.g., a number between 0 and 100. A lower number may indicate a worse health of the hardware system than a higher number.

[0013] Thus, the DHS corresponds to a continuous scale indicating the health status of the hardware system. This provides the user with more information about the health status than just "test passed" or "test failed." This allows deviations from optimal operating conditions to be detected early, i.e., before the hardware system actually reaches a critical health status.

[0014] As another example, the DHS can be a quantity that corresponds to two or more different categories. For example, the DHS can be a color or a text message that corresponds to these categories.

[0015] In a particular example, the DHS may be a first color, e.g., green, corresponding to the category of "good health," a second color, e.g., yellow, corresponding to the category of "suboptimal health," and a third color, e.g., red, corresponding to the category of "poor health - maintenance required."

[0016] As another example, the DHS can be a text message, e.g. “Return your device to service” or “Measurements may be outside specified limits”.

[0017] Accordingly, the maintenance system according to the present invention provides an easily understandable measure of the health status of the hardware system.

[0018] In other words, instead of having to analyze potentially complex interrelationships and / or interdependencies of the hardware system's operating parameters and their impact on the health status, the user can easily assess the health status of the hardware system based on a single metric, namely the DHS.

[0019] Alternatively or additionally, the maintenance system or the analysis module can determine the remaining useful life (RUL) based on the several operating parameters.

[0020] The RUL can be an indicator of the remaining time during which the hardware system can be used without a failure occurring. Alternatively or additionally, the RUL can be an indication of the remaining time during which the hardware system can be used within optimal operating parameters.

[0021] Accordingly, the RUL indicates the time period until the next maintenance must be performed on the hardware system. Instead of having to perform maintenance according to a fixed, predetermined schedule, the maintenance system according to the present invention thus allows maintenance to be performed only when it is actually necessary, thereby reducing both the likelihood of unforeseen hardware system failures and unnecessary hardware system downtime. Accordingly, the availability of the hardware system can be more predictably planned.

[0022] The RUL is an easy-to-understand measure of the time until the next maintenance is due.

[0023] In other words, instead of having to analyze potentially complex interrelationships and / or interdependencies of the hardware system's operating parameters and their impact on the need for maintenance, the user can easily estimate the time until the next maintenance based on a single metric, namely the RUL.

[0024] Hardware system failures are predicted before they actually occur, so that unexpected hardware system downtimes are reliably avoided.

[0025] Alternatively or additionally, the maintenance system or the analysis module can determine the user recommendation for operating the hardware system.

[0026] In general, the user recommendation may refer to operating parameters of the hardware system that should be adjusted to improve the DHS and / or extend the RUL. Accordingly, the user recommendation draws the user's attention to areas of use that reduce the RUL of the hardware system.

[0027] For example, if a user operates the hardware system outside of recommended operating ranges, e.g., with respect to temperatures or loads on the hardware system, the user recommendation may include information about the recommended operating ranges and / or steps necessary to adjust the operating parameters to the recommended operating ranges.

[0028] Another example is when a user operates the hardware system outside of recommended wear metrics, for example, in terms of instrument uptime, number of relay cycle changes, etc., the user recommendation may include information about the recommended wear metrics and / or steps required to comply with the recommended wear metrics.

[0029] According to one aspect of the present invention, the analysis module is configured to analyze the operating parameters, thereby obtaining rules for determining the device health score, the remaining service life, and / or the user recommendation. The analysis module is configured to extrapolate the obtained rules to unknown data sets of operating parameters. Thus, the DHS, the RUL, and / or the user recommendation for any set of operating parameters can be reliably determined based on the obtained rules.

[0030] In one embodiment of the present invention, the operating parameters used to derive the rules correspond to at least one known hardware system having a known health status. In this way, the rules can be obtained with high accuracy because the operating parameters are linked to a known health status.

[0031] The operating parameters used to derive the rules may correspond to several tens, several hundreds or even several thousand hardware systems, each with a known health status.

[0032] For example, the at least one known hardware system may have a perfect state of health, a degraded state of health, or a known error.

[0033] As another example, the hardware system can perform a self-test and / or internal adjustment to determine the health status. The derived rules can link the operating parameters to the passing or failing of the self-test.

[0034] The operating parameters used to obtain the rules can correspond to several (known) hardware systems, each with a known health status.

[0035] According to another aspect of the present invention, the analysis module comprises a machine learning module, wherein the machine learning module comprises a machine learning model that is pre-trained and / or trainable to determine the device health score, the remaining useful life, and / or the user recommendation based on the operating parameters. Accordingly, the operating parameters are input parameters of the machine learning model. The DHS, the RUL, and / or the user recommendation are an output of the machine learning model.

[0036] The machine learning module may employ any suitable machine learning technique. For example, the machine learning model may be (pre-)trained based on training data that includes operating parameters of at least one hardware system, in particular multiple hardware systems, and / or a known health condition.

[0037] In particular, the machine learning model may be implemented as an artificial neural network that is pre-trained and / or trainable to determine the device health score, the remaining useful life and / or the user recommendation based on the operating parameters.

[0038] As another example, the machine learning model may be implemented as a gradient-boosted decision tree algorithm that is pre-trained and / or trainable to determine the device health score, remaining useful life, and / or user recommendation based on the operating parameters.

[0039] In another aspect of the present invention, the maintenance system further comprises a visualization module and a display connected to the visualization module, wherein the visualization module is configured to generate visualization data, wherein the visualization data includes information about the device health score, the remaining service life, and / or the user recommendation, and wherein the display is configured to display the visualization data. Thus, the DHS, the RUL, and / or the user recommendation are visualized such that the user can easily assess the health status of the hardware system, the time until maintenance is required, and / or necessary steps to extend the service life of the hardware system.

[0040] Accordingly, the user is warned when the hardware system reaches a concerning or critical health state.

[0041] Indeed, the respective DHS, RUL, and / or user recommendation for multiple hardware systems (also referred to as a "fleet" of hardware systems) can be visualized simultaneously. This allows a user to easily monitor the health status of the multiple hardware systems.

[0042] In fact, the respective DHS, the respective RUL and / or the respective user recommendation relating to a plurality of hardware systems (also called a “fleet” of hardware systems) may be visualized simultaneously. Thus, a user can easily monitor the health state of the plurality of hardware systems.

[0043] In particular, the plurality of operating parameters include a usage time, a usage counter, operating voltages, a time spent in a particular operating mode, an internal correction parameter, an equalization parameter, a filter parameter, a frequency response of one or more components, a boot counter indicating how often a component boots up, an operating time, a pre-distortion parameter, time series information, a minimum data rate, a maximum data rate, and / or voltage thresholds.

[0044] As further examples, the plurality of operating parameters may include environmental parameters associated with an environment of the hardware system, such as temperature, humidity, and / or altitude above sea level.

[0045] Alternatively or additionally, the plurality of operating parameters may include dimensional and / or physical parameters, such as physical dimensions of the hardware system, a weight, etc.

[0046] Alternatively or additionally, the multiple operating parameters may include regulatory standards that the hardware system must comply with, such as laws or industry standards.

[0047] Alternatively or additionally, the plurality of operating parameters may include time-related parameters, such as a period of time since the last failure of the hardware system, a period of time since the last maintenance was performed on the hardware system, etc.

[0048] However, it is understood that the plurality of operating parameters may include any other suitable parameters.

[0049] According to one aspect of the present invention, the hardware system is configured to determine at least a subset of the plurality of operating parameters by means of a self-test and / or by means of an internal adaptation.

[0050] The term “self-test” is used here and below to refer to measurements performed by the hardware system itself to assess whether certain operating parameters are within acceptable ranges.

[0051] For example, measured operating parameters can be compared with specified threshold values ​​to assess whether the operating parameters (and thus the hardware system) pass the test or fail.

[0052] The term "internal adjustment" refers to the hardware system determining correction parameters that are applied by the hardware system to obtain accurate measurement results. These correction parameters can, for example, relate to the correction of temperature-related drift, age-related drift, and / or other inaccuracies.

[0053] It is also conceivable that the hardware system may be configured to determine the subset of the multiple operating parameters using dedicated time series tracking.

[0054] In one embodiment of the present invention, the maintenance system is configured to perform measurements on the hardware system, thereby obtaining at least a subset of the plurality of operating parameters. In other words, measurements can be performed on the hardware system using external measuring equipment, i.e., using measuring equipment provided separately from the hardware system, to obtain the subset of the plurality of operating parameters. In this way, operating parameters of the hardware system can be determined that may not be available via a self-test or internal adjustment.

[0055] The measurements can be performed, for example, as part of a hardware system maintenance program at a manufacturer's site. However, it is also conceivable that the measurements are performed by the user, i.e., the customer.

[0056] In a further aspect of the present invention, the analysis module is configured to determine specific measurements to be taken based on the device health score and / or the remaining service life. In other words, the analysis module can be configured to select only those tests to be performed on the hardware system as part of maintenance that are actually necessary. In this way, the time required to perform maintenance can be significantly reduced.

[0057] In particular, the analysis module is configured to determine the device health score for the hardware system, the remaining service life of the hardware system, and / or the user recommendation for operating the hardware system based on measurement results obtained from the measurements. The measurement results can be used, for example, to improve the accuracy of the rules determined as explained above. As a further example, the machine learning model described above can be trained using the measurement results.

[0058] According to a further aspect of the present invention, the analysis module is configured to determine, based on the plurality of operating parameters, a device health score for a hardware subsystem of the hardware system, a remaining service life of a subsystem of the hardware system, and / or a user recommendation for operating a subsystem of the hardware system. This enables the user to easily monitor individual components and / or devices of the hardware system. This enables targeted maintenance of the hardware system, for example, for targeted tests and / or the targeted replacement of individual components and / or devices of the hardware system.

[0059] The analysis module may in fact be configured to determine a respective DHS, a respective RUL and / or a respective user recommendation for several subsystems of the hardware system.

[0060] In other words, the analysis module is configured to perform root cause analysis by determining which subsystem(s) are actually causing a deterioration in the health of the hardware system. This allows for targeted replacement of only the subsystem(s) that actually need to be replaced, which also leads to faster maintenance work and thus less downtime of the hardware system. Furthermore, hardware system maintenance can be performed more cost-effectively and with a lower environmental impact.

[0061] The analysis module can be configured to schedule maintenance and / or a replacement hardware subsystem and / or a replacement hardware system based on the determined device health score of the hardware system and / or the determined remaining service life of the hardware system. Thus, the analysis module can automatically determine an optimal time for performing the maintenance. Alternatively or additionally, the analysis module can be configured to automatically order the replacement hardware subsystem or the replacement hardware system for the time of the planned maintenance, thus avoiding any downtime for the user while performing measurements using the hardware system.

[0062] In one embodiment of the present invention, the analysis module is configured to determine a confidence value associated with the device health score, the remaining useful life, and / or the user recommendation, wherein the confidence value is an indicator of the reliability of the device health score, the remaining useful life, and / or the user recommendation being determined. Thus, the user is provided with an easily understandable measure of the reliability of the DHS, the RUL, and / or the user recommendation being obtained.

[0063] For example, the confidence value can be a number between 0% (which indicates minimum reliability) and 100% (which indicates maximum reliability).

[0064] The confidence value can be displayed visibly on the display along with the DHS, RUL and / or user recommendation.

[0065] The maintenance system may further comprise a communication module, wherein the communication module is configured to exchange data between the maintenance system and the hardware system, and wherein the exchanged data comprises service information and / or verification information obtained from the hardware system. For example, the service information and / or verification information may be used to increase the accuracy of the rules determined as explained above. As a further example, the machine learning model described above may be trained using the service information and / or verification information.

[0066] In fact, the user of the hardware system can choose which data he wants to pass on to the maintenance system.

[0067] The term "service" information is used here and below to refer to information related to a maintenance service cycle. The service information may include, for example, the date of the last service(s), a tentative date for the next service, etc.

[0068] The term "test information" refers to information related to measurements performed by the hardware system. The test information may include, for example, test results of a self-test, results of an internal adjustment, and / or measurement results of measurements performed by the hardware system on a test object.

[0069] In one embodiment of the present invention, the hardware system is embodied as one or more measuring instruments. In other words, the hardware system can be a measuring system configured to perform measurements on a test object.

[0070] For example, the hardware system may be implemented as or comprise an oscilloscope, in particular a digital oscilloscope, a spectrum analyzer, a power analyzer, a vector network analyzer, an RF front-end, an external RF front-end, a signal generator, a radar target simulator, a LiDAR target simulator, an over-the-air (OTA) test system, a beamforming antenna, a mobile radio cell simulator, etc.

[0071] The hardware system may further include electrical connectors, cables, signal distributors, signal combiners, directional couplers, etc.

[0072] According to the present invention, the object is further achieved by a method for analyzing and / or generating health information for a hardware system. The method comprises the following steps: - Recording several operating parameters of the hardware system by means of a recording module, wherein the several operating parameters are relevant for a health status of the hardware system, - Forwarding the multiple operating parameters to an analysis module and - Determining a device health score for the hardware system, a remaining useful life of the hardware system and / or a user recommendation for operating the hardware system using the analysis module based on the plurality of operating parameters.

[0073] In particular, the maintenance system described above may be configured to carry out the process for analyzing and / or creating health information.

[0074] Regarding the further advantages and characteristics of the process, reference is made to the above explanations regarding the maintenance system, which also apply to the process and vice versa.

[0075] According to one aspect of the present invention, the device health score, the remaining useful life, and / or the user recommendation is / are determined according to predetermined rules based on a deterministic algorithm. Based on the predetermined rules or the deterministic algorithm, the DHS, the RUL, and / or the user recommendation can be reliably determined for any set of operating parameters, e.g., by extrapolating the rules to unknown sets of operating parameters.

[0076] In one embodiment of the present invention, the device health score, the remaining useful life, and / or the user recommendation are determined using a machine learning technique. Thus, the DHS, the RUL, and / or the user recommendation may be determined using a machine learning module comprising a machine learning model that is pre-trained and / or trainable to determine the DHS, the RUL, and / or the user recommendation based on the operating parameters as described above.

[0077] Measurements can be taken on the hardware system, thereby obtaining at least a subset of the plurality of operating parameters. In other words, measurements can be taken on the hardware system using external measuring devices, i.e., measuring devices provided separately from the hardware system, to obtain the subset of the plurality of operating parameters. In this way, operating parameters of the hardware system can be determined that may not be accessible via a self-test or internal adjustment.

[0078] According to another aspect of the present invention, at least a subset of the plurality of operating parameters is determined by the hardware system by means of a self-test and / or by means of an internal adaptation.

[0079] The foregoing aspects and many of the attendant advantages of the claimed subject matter will be more readily appreciated when considered in conjunction with the following detailed description and the accompanying drawings, in which: - Fig. 1 schematically shows a maintenance system according to the present invention and - Fig. 2 is a flowchart of a method for analyzing and / or creating health information for a hardware system according to the present invention.

[0080] The detailed description set forth below, in conjunction with the accompanying drawings, wherein like numerals refer to like elements, is intended as a description of various embodiments of the disclosed subject matter and is not intended to be the only embodiments. Each embodiment described in this disclosure is merely exemplary or illustrative and should not be construed as preferred or advantageous over other embodiments. The illustrative examples given herein are not intended to be exhaustive or to limit the claimed subject matter to the precise forms disclosed.

[0081] For example, in the context of the present disclosure, the phrase "A and / or B and / or C" means (A), (B), (C), (A and B), (A and C), (B and C), or (A, B, and C), including all other possible permutations when more than three elements are listed. In other words, the term "A and / or B" generally means "A and / or B," such as "A" alone, "B" alone, or "A and B."

[0082] In Fig. 1 schematically shows a maintenance system 10 for maintaining a hardware system 12.

[0083] Overall, the maintenance system 10 is configured to analyze and / or create status information for the hardware system 12.

[0084] In the Fig. In the embodiment shown in Figure 1, the hardware system 12 is a measuring system that is configured to perform measurements on a test object.

[0085] For example, the hardware system 12 may be implemented as an oscilloscope, in particular as a digital oscilloscope, as a spectrum analyzer, as a power analyzer, as a vector network analyzer, as an RF front end, as an external RF front end, as a signal generator, as a radar target simulator, as a LiDAR target simulator, as an over-the-air (OTA) test system, as a beamforming antenna, as a mobile radio cell simulator, etc., or may comprise such a system.

[0086] The hardware system 12 may further include electrical connectors, cables, signal splitters, signal combiners, directional couplers, etc.

[0087] In the Fig. 1, the hardware system 12 comprises a measuring device 14 and a signal generator 16.

[0088] The maintenance system 10 comprises a computing device 18 which is connected to the hardware system 12 in a signal-transmitting manner.

[0089] The term “signal-transmitting connection” is intended to refer to a wired or wireless connection designed to transmit signals between the respective devices or components.

[0090] For example, the computing device 18 may be connected to the hardware system via a local area network (LAN), a wide area network, a wireless LAN, the Internet, or any other suitable type of connection.

[0091] In the Fig. In the embodiment shown in Figure 1, the computing device 18 is connected to both the measuring device 14 and the signal generator 16 in a signal-transmitting manner.

[0092] The computing device 18 can be configured, for example, as a personal computer or as a server.

[0093] As another example, the computing device 18 may be embodied as a laptop, tablet, smartphone, or any other type of smart device.

[0094] The computing device 18 includes an analysis module 20, which may include a machine learning (ML) module.

[0095] The computing device 18 further comprises a communication module 22, wherein the communication module is configured to exchange data between the maintenance system 10 and the hardware system 12.

[0096] The computing device 18 further comprises a visualization module 24, a display 26 and a capture module 28.

[0097] It should be noted that although the analysis module 20, the communication module 22, the visualization module 24, the display 26, and the acquisition module 28 are shown as being integrated into a single computing device 18, these modules may also be distributed across multiple computing devices that are interconnected.

[0098] Furthermore, it is also conceivable that the analysis module 20, the communication module 22, the visualization module 24, the display 26 and / or the acquisition module 28 are integrated into the hardware system 12, in particular into the measuring device 14 and / or into the signal generator 16.

[0099] The functionality of the analysis module 20, the communication module 22, the visualization module 24, the display 26 and the acquisition module 28 is described in more detail below.

[0100] In this and the following, the term “module” shall mean suitable hardware, suitable software or a combination of hardware and software that is configured to provide a specific functionality.

[0101] The hardware may include, but is not limited to, a central processing unit (CPU), a graphics processing unit (GPU), a field-programmable gate array (FPGA), an application-specific integrated circuit (ASIC), or other types of electronic circuitry.

[0102] The maintenance system 10 may further include measuring equipment 30.

[0103] In general, the measurement equipment 30 is configured to make measurements on the hardware system 12, as described in more detail below.

[0104] The measurement equipment 30 may include suitable measuring instruments, electrical connectors, cables, signal splitters, signal combiners, directional couplers, etc., such that measurements can be performed on the hardware system 12.

[0105] In the Fig. In the embodiment shown in Figure 1, the measuring equipment 30 is configured to perform measurements on the measuring device 14 and the signal generator 16.

[0106] The maintenance system 10 is configured to perform a method for analyzing and / or creating status information for the hardware system 12. The method is described below with reference to Fig. 2 described.

[0107] By means of the acquisition module 28, several operating parameters of the hardware system 12 are acquired (step S1).

[0108] In general, the recorded operating parameters are relevant for the health or aging state of the hardware system 12.

[0109] The plurality of operating parameters may include a usage time, a usage counter, operating voltages, a time spent in a particular operating mode, an internal correction parameter, an equalization parameter, a filter parameter, a frequency response of one or more components, a boot counter indicating how often a component boots up, an operating time, a pre-distortion parameter, time series information, a minimum data rate, a maximum data rate, and / or voltage thresholds.

[0110] As further examples, the plurality of operating parameters may include environmental parameters associated with an environment of the hardware system, such as temperature, humidity, and / or altitude above sea level.

[0111] Alternatively or additionally, the plurality of operating parameters may include dimensional and / or physical parameters, such as physical dimensions of the hardware system, a weight, etc.

[0112] Alternatively or additionally, the multiple operating parameters may include regulatory standards that the hardware system is intended to meet, e.g., laws or industry standards.

[0113] Alternatively or additionally, the plurality of operating parameters may include time-related parameters, such as a period of time since the last failure of the hardware system, a period of time since the last maintenance was performed on the hardware system, etc.

[0114] However, it is understood that the plurality of operating parameters may include any other suitable parameters.

[0115] At least a subset of the plurality of operating parameters may be logged by the hardware system 12 during operation of the hardware system 12.

[0116] For example, the hardware system 12 may be configured to log the subset of the plurality of operating parameters at predetermined time intervals, such as every 24 hours, every twelve hours, or every four hours.

[0117] As another example, the hardware system 12 may be configured to log the subset of operating parameters based on the occurrence of certain events, such as when the hardware system 12 makes internal adjustments to its operating parameters.

[0118] In other words, the logging of the subset of operating parameters may be triggered by the corresponding events, in particular based on an impact of the respective event on the measurement capabilities of the hardware system 12.

[0119] The logged operating parameters can be transmitted to the recording module 28 via the communication module 22.

[0120] At least a subset of the plurality of operating parameters may be determined by the hardware system 12 by means of a self-test and / or by means of an internal adjustment.

[0121] For example, operating parameters measured by the hardware system 12 can be compared with predetermined threshold values ​​to assess whether these operating parameters (and thus the hardware system) pass the test or fail.

[0122] As another example, correction parameters may be determined by the hardware system 12 that relate to correcting for temperature-related drift, age-related drift, and / or other inaccuracies.

[0123] At least a subset of the plurality of operating parameters may be determined by performing measurements on the hardware system 12 using the measurement equipment 30.

[0124] In particular, operating parameters of the hardware system 12 that cannot be determined by self-tests, internal adjustments, or logging of operating parameters by the hardware system 12 can be measured using the measuring equipment 30.

[0125] It is also conceivable that operating parameters logged or measured by the hardware system 12 are forwarded to the analysis module 20. Based on these operating parameters, the analysis module 20 can determine specific measurements to be performed using the measuring equipment 30.

[0126] Optionally, service information and / or audit information may be collected from the hardware system 12.

[0127] The plurality of operating parameters as well as the service information and / or the test information are forwarded to the analysis module 20.

[0128] The plurality of operating parameters are processed by the analysis module 20, whereby a device health score (DHS) for the hardware system 12, a remaining useful life (RUL) of the hardware system 12 and / or a user recommendation for operating the hardware system 12 is determined (step S2).

[0129] The DHS, the RUL, and / or the user recommendation can be determined for the hardware system 12 as a whole. Alternatively or additionally, the DHS, the RUL, and / or the user recommendation can be determined for one or more hardware subsystems of the hardware system 12, ie, for individual devices and / or for individual components.

[0130] Overall, the DHS allows conclusions to be drawn about the health or aging state of the hardware system 12, in particular about the health state of the hardware system 12 as a whole or of individual subsystems of the hardware system 12.

[0131] The DHS can be a number within a predetermined range, e.g., a number between 0 and 100. A lower number may indicate a worse health of the hardware system than a higher number.

[0132] The RUL may provide an indication of the remaining time that the hardware system 12 can be used without experiencing a failure. Alternatively or additionally, the RUL may indicate the remaining time that the hardware system 12 can be used within optimal operating parameters.

[0133] The user recommendation may refer to operating parameters of the hardware system 12 that should be set to improve the DHS and / or extend the RUL.

[0134] For example, if a user operates the hardware system 12 outside of recommended operating ranges, e.g., with respect to temperatures or loads on the hardware system, the user recommendation may include information about the recommended operating ranges and / or steps necessary to adjust the operating parameters to the recommended operating ranges.

[0135] Another example is when a user operates the hardware system 12 outside of recommended wear metrics, such as instrument uptime, number of relay cycle changes, etc., the user recommendation may include information about the recommended wear metrics and / or steps necessary to comply with the recommended wear metrics.

[0136] The analysis module 20 may process the plurality of operating parameters based on one or more of the techniques described below.

[0137] According to a first variant, the analysis module 20 can process the plurality of operating parameters according to predetermined rules based on a deterministic algorithm. The term "predetermined rules based on a deterministic algorithm" is to be understood as meaning that a "classical" algorithm is used, i.e., an algorithm that does not employ machine learning techniques.

[0138] If necessary, the given rules can be extrapolated so that the recorded multiple operating parameters can be processed correctly.

[0139] According to a second variant, the analysis module 20 comprises a machine learning module (ML module), wherein the machine learning module comprises a machine learning model, in particular an artificial neural network or a tree-based algorithm, which is pre-trained and / or trainable to determine the DHS, the RUL and / or the user recommendation based on the operating parameters.

[0140] The artificial neural network can, for example, be an interconnected neural network.

[0141] As another example, the tree-based algorithm can be a gradient boosted decision tree algorithm.

[0142] The multiple operating parameters are input parameters of the machine learning model. The DHS, the RUL, and / or the user recommendation are outputs of the machine learning model.

[0143] Optionally, a confidence value can be determined using the analysis module 20 (step S3).

[0144] In general, the confidence value is an indicator of the reliability of the DHS, the RUL and / or the user recommendation that are determined.

[0145] For example, the confidence value can be a number between 0% (which indicates minimum reliability) and 100% (which indicates maximum reliability).

[0146] Visualization data is generated by the visualization module 24 and the visualization data is visualized on the display 26 (step S4).

[0147] The visualization data includes information about the DHS, RUL and / or user recommendation that is determined.

[0148] Optionally, the visualization data may include information about the confidence score, so that the confidence score is visualized along with the DHS, RUL, and / or user recommendation that are determined.

[0149] Optionally, the analysis module 20 can automatically schedule maintenance and / or a replacement hardware subsystem and / or a replacement hardware system based on the determined DHS and / or the determined RUL (step S5).

[0150] The predetermined rules described above, ie the deterministic algorithm described above, can be updated or adapted (step S6).

[0151] The predefined rules can be adjusted based on the determined DHS, the determined RUL and / or the determined confidence value.

[0152] Furthermore, the predetermined rules may be adapted based on the detected operating parameters, in particular based on measurement results obtained by the measuring equipment 30, results of a self-test, results of an internal adaptation and / or logged operating parameters.

[0153] Likewise, the machine learning model can be trained or retrained based on the determined DHS, the determined RUL and / or the determined confidence value.

[0154] Furthermore, the machine learning model can be trained or retrained based on the recorded operating parameters, in particular based on measurement results obtained from the measuring equipment 30, results of a self-test, results of an internal adaptation and / or logged operating parameters.

[0155] Accordingly, the manner in which the analysis module 20 determines the DHS, the RUL and / or the user recommendation can be updated regularly, e.g., during maintenance of the hardware system 12.

[0156] In certain embodiments disclosed herein, particularly in the respective module(s) and / or unit(s), circuitry (e.g., one or more circuits) is used to implement standards, protocols, methodologies, or technologies disclosed herein, operatively connect two or more components, generate information, process information, analyze information, generate signals, encode / decode signals, convert signals, send and / or receive signals, control other devices, etc. Circuitry of any type may be used.

[0157] In one embodiment, a circuit arrangement comprises, among other things, one or more computing devices such as a processor (e.g., a microprocessor), a central processing unit (CPU), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a system on a chip (SoC), or the like, or any combination thereof, and may include discrete digital or analog circuit elements or electronics, or combinations thereof. In one embodiment, a circuit arrangement comprises hardware circuit implementations (e.g., implementations in analog circuit arrangements, implementations in digital circuit arrangements, and the like, as well as combinations thereof).

[0158] In one embodiment, circuitry comprises combinations of circuits and computer program products with software or firmware instructions stored on one or more computer-readable memories that cooperate to cause a device to execute one or more protocols, methodologies, or technologies described herein. In one embodiment, circuitry comprises circuitry, such as microprocessors or portions of a microprocessor, that requires software, firmware, and the like to operate. In one embodiment, circuitry comprises one or more processors or portions thereof and associated software, firmware, hardware, and the like.

[0159] Amounts and numbers may be referenced in this application. Unless expressly stated, such amounts and numbers are not to be considered limiting, but rather exemplary of the possible amounts or numbers in the context of this application. In this regard, the term "several" may also be used in this application to refer to a quantity or number. In this regard, the term "several" means any number greater than one, for example, two, three, four, five, etc. The terms "about," "approximately," "near," etc., mean plus or minus 5% of the stated value.

Claims

[1] Maintenance system for maintaining a hardware system (12), wherein the maintenance system (10) comprises a recording module (28) and an analysis module (20), wherein the detection module (28) is configured to detect a plurality of operating parameters of the hardware system (12), wherein the plurality of operating parameters are relevant to a health status of the hardware system (12), wherein the acquisition module (28) is configured to forward the plurality of operating parameters to the analysis module (20), and wherein the analysis module (20) is configured to determine a device health score for the hardware system (12), a remaining useful life of the hardware system (12), and / or a user recommendation for operating the hardware system (12) based on the plurality of operating parameters. [2] Maintenance system according to claim 1, wherein the analysis module (20) is configured to analyze the operating parameters, whereby rules for determining the device health score, the remaining service life and / or the user recommendation are obtained, and wherein the analysis module (20) is configured to extrapolate the obtained rules to unknown data sets of operating parameters, in particular wherein operating parameters used to obtain the rules correspond to at least one known hardware system having a known state of health. [3] Maintenance system according to one of the preceding claims, wherein the analysis module (20) comprises a machine learning module, the machine learning module comprising a machine learning model that is pre-trained and / or trainable to determine the device health score, the remaining useful life and / or the user recommendation based on the operating parameters. [4] Maintenance system according to one of the preceding claims, further comprising a visualization module (24) and a display (26) connected to the visualization module (24), wherein the visualization module (24) is configured to generate visualization data, wherein the visualization data comprises information about the device health score, the remaining service life and / or the user recommendation, and wherein the display (26) is configured to display the visualization data. [5] A maintenance system according to any one of the preceding claims, wherein the plurality of operating parameters comprise a usage time, a usage counter, operating voltages, a time spent in a particular operating mode, an internal correction parameter, an equalization parameter, a filter parameter, a frequency response of one or more components, a boot counter indicating how often a component boots up, an operating time, a pre-distortion parameter, time series information, a minimum data rate, a maximum data rate and / or voltage thresholds. [6] Maintenance system according to one of the preceding claims, wherein the hardware system (12) is configured to determine at least a subset of the plurality of operating parameters by means of a self-test and / or by means of an internal adaptation. [7] Maintenance system according to one of the preceding claims, wherein the maintenance system (10) is configured to perform measurements on the hardware system (12), whereby at least a subset of the plurality of operating parameters is obtained, in particular wherein the analysis module (20) is configured to determine, on the basis of the device health score and / or on the basis of the remaining service life, specific measurements to be performed, and / or wherein the analysis module (20) is configured to determine, on the basis of measurement results obtained by means of the measurements, the device health score for the hardware system (12), the remaining service life of the hardware system (12) and / or the user recommendation for operating the hardware system (12). [8] Maintenance system according to one of the preceding claims, wherein the analysis module (20) is configured to determine, on the basis of the plurality of operating parameters, a device health score for a hardware subsystem of the hardware system (12), a remaining useful life of a subsystem of the hardware system (12) and / or a user recommendation for operating a subsystem of the hardware system (12). [9] Maintenance system according to one of the preceding claims, in which the analysis module (20) is configured to schedule maintenance and / or a replacement hardware subsystem and / or a replacement hardware system based on the determined device status point value of the hardware system (12) and / or based on the determined remaining service life of the hardware system (12). [10] Maintenance system according to one of the preceding claims, wherein the analysis module (20) is configured to determine a confidence value associated with the device health score, the remaining service life and / or the user recommendation, wherein the confidence value is an indicator of a reliability of the device health score, the remaining service life and / or the user recommendation that are determined. [11] Maintenance system according to one of the preceding claims, further comprising a communication module (22), wherein the communication module (22) is arranged to exchange data between the maintenance system (10) and the hardware system (12), and wherein the exchanged data comprises service information and / or test information obtained from the hardware system (12). [12] Maintenance system according to one of the preceding claims, in which the hardware system (12) is designed as a measuring instrument or as several measuring instruments. [13] A method for analyzing and / or creating health information for a hardware system (12), the method comprising the following steps: Detecting a plurality of operating parameters of the hardware system (12) by means of a detection module (28), wherein the plurality of operating parameters are relevant to a health state of the hardware system (12), Forwarding the plurality of operating parameters to an analysis module (20) and Determining a device status point value for the hardware system (12), a remaining useful life of the hardware system (12) and / or a user recommendation for operating the hardware system (12) by means of the analysis module (20) on the basis of the plurality of operating parameters, in particular wherein the device health score, the remaining useful life and / or the user recommendation is / are determined according to predetermined rules on the basis of a deterministic algorithm and / or wherein the device health score, the remaining useful life and / or the user recommendation is / are determined using a machine learning technique.

Images