Condition monitoring of a packaging machine for liquid foods

Abstract

A monitoring device for evaluating the status of a packaging machine for producing packages of a liquid food product includes a signal interface (200a) for connecting to a plurality of vibration sensors (20) within the packaging machine. The monitoring device includes logic (203-205) for receiving measurement signals (SS1-SSm) from the vibration sensors (20) and deriving event timing signals MES indicative of predefined operational events of the packaging machine, each operational event corresponding to a mechanical action by a respective component within the packaging machine as it operates to produce a package. The monitoring device further includes logic (203-205) for, by using the MES and in the measurement signals (SS1-SSm), identifying a signal value associated with each component and evaluating the signal value with respect to a status evaluation of the respective component. Thus, providing and using the MES facilitates status evaluation of individual components within the packaging machine.

Description

[Technical Field]

[0001] The present disclosure relates generally to condition monitoring of packaging machines configured and operated for the production of packages of liquid food products, and in particular to techniques for condition monitoring based on measurement signals from a plurality of vibration sensors within the packaging machine. [Background technology]

[0002] The industrial production and packaging of liquid foods is automated and involves advanced process control of food packaging machines to achieve high-volume production. Safe and reliable operation of food packaging machines is crucial, as malfunctions and subsequent production stoppages can have a serious impact on production costs and product quality. Early detection of malfunctions is crucial to avoid performance degradation and damage to machinery or even loss of human life. Therefore, accurate condition monitoring of food packaging machines is generally necessary to help operators make the right decisions in emergency actions and preventive maintenance, service, and repair.

[0003] The inherent mechanical complexity of food packaging machines makes the task of condition monitoring quite challenging. Attempts have been made to perform frequency or time-frequency analysis of vibration data from sensors within food packaging machines to detect sudden and incipient failure conditions. Each sensor tends to pick up vibrations from multiple different mechanical components within the packaging machine, resulting in the resulting vibration data containing a complex mixture of vibrations generated within the food packaging machine. While frequency or time-frequency analysis of vibration data from multiple sensors can help indicate the presence of a sudden or incipient failure condition for the packaging machine as a whole, the analysis generally does not reveal the one component out of the typically hundreds of components in a packaging machine that requires maintenance or inspection. In other words, existing techniques for condition monitoring of food packaging machines lack specificity regarding the source or cause of current or developing failure conditions. Summary of the Invention [Problem to be solved by the invention]

[0004] It is an object to at least partially overcome one or more limitations of the prior art.

[0005] One object is to provide a technique for condition monitoring with improved specificity of machines for the production of packages of liquid food products.

[0006] A further object is to provide a technique that is simple, efficient and robust. [Means for solving the problem]

[0007] One or more of these objects, as well as further objects that may become apparent from the following description, are at least partly achieved by a method for monitoring a packaging machine, a computer-readable medium, and a monitoring device according to the independent claims, embodiments thereof being defined by the dependent claims.

[0008] A first aspect of the present disclosure is a method for monitoring a packaging machine operating to produce packages of a liquid food product. The method includes: receiving measurement signals from a plurality of vibration sensors within the packaging machine; and obtaining event timing signals indicative of predefined operational events of the packaging machine, each of the predefined operational events corresponding to a mechanical action by a respective component within the packaging machine as it operates to produce a package. The method further includes: using the event timing signals and in the measurement signals, identifying a signal value associated with each component; and evaluating the signal value with respect to a condition assessment of each component.

[0009] The first aspect is based on the insight that the specificity of condition monitoring can be improved by accessing event timing signals that are indicative of the mechanical actions performed by the packaging machine during operation and that point to the machine components involved in each mechanical action. The event timing signals can then be used as a basis for identifying signal values ​​in the measurement signals that are specific to individual machine components and that can therefore perform condition assessments related to individual machine components within the packaging machine. When event timing signals are available, the identification of signal values ​​can result from a simple, efficient, and robust time-domain match of the respective measurement signals with the event timing signals.

[0010] A second aspect of the present disclosure is a computer-readable medium comprising computer instructions that, when executed by a processor, cause the processor to perform the method of the first aspect or any embodiment thereof.

[0011] A third aspect of the present disclosure is a monitoring device including a signal interface for connecting to a plurality of vibration sensors in a packaging machine, and logic configured to control the monitoring device to perform the method of the first aspect or any embodiment thereof.

[0012] Further objects, as well as embodiments, features, aspects and advantages of the present invention will become apparent from the following detailed description and drawings.

[0013] Embodiments will now be described, by way of example, with reference to the accompanying schematic drawings in which: [Brief explanation of the drawings]

[0014] [Figure 1A] 1 is a side view of a roll-fed carton packaging machine, according to an example. [Figure 1B] 1B shows a perspective view of the flow of material through the packaging machine of FIG. 1A. [Figure 1C] 1B is a side view of a mechanism for transverse sealing of the packaging machine of FIG. 1A. FIG. [Figure 2A-2B]FIG. 1 is a block diagram of a monitoring device for assessing the condition of a packaging machine, according to some embodiments. [Figure 3] FIG. 1 is a flow diagram of a method for condition assessment of a packaging machine, according to some embodiments. [Figure 4A] 1 is a graph of a model event signal representing a time sequence of mechanical events in a packaging machine. [Figure 4B] 1 illustrates groups of events caused by different mechanical components within a packaging machine. [Figure 5] A composite graph of the measured signal (top) and the model event signal (bottom). [Figures 6A-6B] 1 is a graph of signal magnitude as a function of time for signals generated by a packaging machine including healthy and failed mechanical components, respectively; DETAILED DESCRIPTION OF THE INVENTION

[0015] Embodiments will now be described more fully below with reference to the accompanying drawings, which show some, but not all, embodiments. Indeed, the invention may be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will satisfy applicable legal requirements.

[0016] It is also understood that, where possible, any advantage, feature, function, device, and / or operational aspect of any of the embodiments described and / or contemplated herein may be included in any of the other embodiments described and / or contemplated herein, and / or vice versa. Further, where possible, unless otherwise expressly stated, any term appearing in the singular herein is also intended to include the plural and / or vice versa. As used herein, "at least one" means "one or more," and these phrases are intended to be interchangeable. Thus, the terms "a" and / or "an" mean "at least one" or "one or more," even if the phrases "one or more" or "at least one" are also used herein. As used herein, unless the context requires otherwise, the word "comprise" or variations thereof, such as "comprises" or "comprising," are used inclusively, i.e., to specify the presence of stated features but not to exclude the presence or addition of additional features in various embodiments. As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0017] As used herein, "liquid food" refers to any food that is non-solid, semi-liquid, or pourable at room temperature, including beverages such as fruit juices, wine, beer, soda, as well as dairy products, sauces, oils, creams, custards, soups, pastes, etc., and also solid foods in liquids such as pulses, fruits, tomatoes, stews, etc.

[0018] As used herein, "package" refers to any package or container suitable for hermetically enclosing a liquid food product, including, but not limited to, cardboard or packaging laminate, containers formed of, for example, cellulose-based materials, and containers made of or containing plastic materials.

[0019] Like numbers refer to like elements throughout.

[0020] 1A is a side view of a machine 10 for packaging liquid food products. Machine 10 is an example of a roll-fed, carton-based packaging system. In the illustrated example, machine 10 includes an infeed section 11 that holds one or more reels of carton-based sheet material, a micro-injection molding section 12 for applying molded opening devices to the sheet material, a bath section 13 for sterilizing the sheet material, an aseptic chamber 14, a tube-forming section 15 for forming the sheet material into tubes, a filling section 16 for filling, sealing, and cutting the tube-shaped material, and an outfeed section 17 for outputting packages.

[0021] FIG. 1B generally illustrates the operating principle of the machine 10 of FIG. 1A, which may be deployed for continuous packaging of liquid food products. Packaging material arrives on a reel 100 of sheet material at a factory where a packaging machine is installed. The machine 10 unrolls the packaging material and feeds it into a bath 102 containing, for example, hydrogen peroxide to sterilize the packaging material. Alternatively, sterilization may be performed using low-voltage electron beam (LVEB) technology. After sterilization, the packaging material is formed into a tube 104. More specifically, the longitudinal ends are successively attached to one another in a process often referred to as longitudinal sealing. Once the tube 104 is formed, the machine fills the tube with the liquid food product. The machine forms packages 106 from the food-containing tubes 104 by transversely sealing the ends of the tube 104 and severing the sealed sections as they are formed. The machine may perform different forming operations during and / or after transverse sealing to form the packages 106.

[0022] There are several critical processes that run in parallel in a roll-fed packaging system, which can cause quality issues in the packages produced if, for example, these processes are not properly coordinated or if there are worn machine parts. One critical process in machine 10 is filling section 16, which is illustrated in more detail by way of example in FIG. 1C . To produce packages 106 from tube 104, forming flaps 160 a, 160 b may be used in combination with sealing jaws 162 a, 162 b. Each sealing jaw 162 a, 162 b includes a sealing device 164 a, 164 b and a knife 166 a, 166 b or other cutting element for separating the formed package from tube 104. Each combination of forming flaps 160a, 160b and sealing jaws 162a, 162b defines a respective machine unit 1a, 1b, which is driven, for example, by a chain mechanism (not shown) that moves along with the tube. FIG. 1C shows the first and second stages of the package formation process. In the first stage, forming flaps 160a begin to form the tube into the shape of the package, and the tube is filled with liquid food, for example, via a pipe (not shown) extending into the tube. Also in the first stage, sealing jaws 162a are operated to form a transverse seal by using sealing device 164a. In the second stage, forming flaps 160b are held in place to form the package shape. Also in the second stage, sealing jaws 162b are operated to form a transverse seal by using sealing device 164b. Once the transverse seal is complete, knife 166b is operated to cut the lower portion of tube 104, with both ends now closed by the transverse seal.

[0023] The machine 10 of FIGS. 1A - 1C is merely given as an example of a packaging machine. Another well - known type of packaging machine implements a so - called blank - supply packaging system, where a plurality of packaging materials ( "blanks") with two ends welded are supplied to the packaging machine to form a folded sleeve, an open sleeve is made, folded and sealed to form a bottom, filled with liquid food, and sealed and folded to form a package.

[0024] In the following, embodiments of a technique for state monitoring of a packaging machine will be described with reference to the machine 10 of FIGS. 1A - 1C. However, the state - monitoring technique may be applied to any machine in a production line for packaging liquid food, including but not limited to machines for supplying and / or manipulating packaging materials, filling machines with any type of packaging system, capping machines, accumulator machines, straw - attaching machines, secondary packaging machines, etc.

[0025] State monitoring operates, for example, as shown in FIG. 1C, on sensor signals ( "measurement signals") from a plurality of vibration sensors 20 attached to, integrated with, or otherwise included in the machine 10 to be monitored. The vibration sensor may be of any type that can generate an output signal indicative of vibration. In this specification, "vibration" refers to any trembling or swaying movement of any mechanical component within the machine 10. Non - limiting examples of the vibration sensor 20 include accelerometers, orientation sensors, position sensors, force sensors, and microphones. Further, a torque sensor arranged to measure torque within a rotating system, for example, within a drive mechanism for a moving component of the machine 10, may be used as a vibration sensor.

[0026] When operable to produce packages, machine 10 is a highly dynamic system with many moving parts and significant mechanical interactions both among the moving parts and between the moving and stationary parts. If one or more mechanical components within machine 10 begin to malfunction, the vibrations detected by sensors 20 tend to change, which may be detected by analyzing the sensor signals in the time and / or frequency domains. However, it should be understood that each vibration sensor 20 tends to pick up vibrations from many different sources in its surroundings. Therefore, it can be difficult to identify a specific mechanical component that needs to be replaced based on the sensor signals from vibration sensors 20. Therefore, the effectiveness of maintenance and inspections is highly dependent on the experience of the operator, and there is a significant risk of extended production downtime. Embodiments of the present invention seek to mitigate this problem.

[0027] FIG. 2A illustrates a monitoring device 200 for performing condition monitoring according to some embodiments. The monitoring device 200 includes a signal interface 200a configured to be connected to the vibration sensors 20 via a wired or wireless connection. In the illustrated example, the monitoring device 200 receives sensor signals SS1-SSm from m vibration sensors via the signal interface 200a. The vibration sensors 20 may be located in a single packaging machine, such as the machine 10 of FIGS. 1A-1C, or in multiple packaging machines in a factory. The monitoring device 200 is configured to process the sensor signals SS1-SSm in consideration of a modeled event signal (MES) obtained from a memory element 201 to generate an output signal for a feedback device 202. The output signal may indicate a particular mechanical component that needs to be replaced and possibly the component's estimated remaining useful life (RUL). The feedback device 202 may include, for example, one or more of a display, a touchscreen, an indicator lamp, and a loudspeaker. The monitoring device 20 may further be connected to a control device (not shown) of the machine 10 and operable to command an emergency stop when an emergency fault condition is detected.

[0028] The modeled event signal MES is a predefined or precalculated signal indicating the timing of predefined work events within the machine 10 during the production of the packages 106. Each work event corresponds to a mechanical action by a respective component within the machine 10 during operation. The MES is therefore an event timing signal specific to the machine 10 and its operating configuration. The MES may be viewed to correlate to the time of each work event. If the machine 10 operates in a repetitive production cycle, for example, to produce one or a series of packages 106, the MES may represent the relative timing of multiple work events performed by the machine during one production cycle. In one embodiment, the MES is calculated by simulation using a mathematical model representing the machine 10 and its operation, particularly the mechanical actions performed by the machine 10 during the production of the packages 106. In another embodiment, the MES may include specialized sensors for the sole detection of work events and is determined, at least in part, based on measurements at a corresponding reference machine.

[0029] An example MES is shown in FIG. 4A , where each vertical line represents a work event on machine 10. In the illustrated example, therefore, the MES includes a series of event indicators or flags E, and the relative timing of multiple work events is given by the location of the event indicators E in the MES. Each event indicator E in the MES may correspond to a mechanical action that generates a vibration, which is detected by one or more of sensors 20 in machine 10, and therefore produces a response in at least one of sensor signals SS1-SSm. However, it is conceivable that some event indicators E do not necessarily produce such a response.

[0030] In the MES, groups of events are associated with different mechanical components of the machine 10. This is illustrated in Figure 4B, which shows groups of events associated with n different components D1-Dn in the machine 10. In the example of Figure 1C, one or more of the components D1-Dn may correspond to one or more of the flaps 160a, 160b, one or more of the sealing jaws 162a, 162b, one or more of the knives 166a, 166b, or drive elements of the respective machine units 1a, 1b, or any combination thereof.

[0031] As shown at the bottom of Figure 4B, the sum of the events of the groups of different components D1-Dn results in the MES. The association of the events of the groups to the components D1-Dn is also predefined and known from the MES. It is conceivable that a component is associated with a single event, and therefore the events of a group may include one or more events.

[0032] One aspect of the present disclosure relates to a method for monitoring a packaging machine, which is illustrated herein with reference to the flow diagram of FIG. 3 and the exemplary monitoring device 200 of FIG. 2A associated with the machine 10 of FIGS. 1A-1C. The described monitoring method 300 includes step 301 of acquiring a pre-calculated MES (Mechanical Estimation System) stored in a memory, such as memory element 201 (FIG. 2A). As described above, the MES indicates pre-defined work events of the machine 10, and each pre-defined work event corresponds to a mechanical action by a respective component D1-Dn in the machine 10 when operational. Step 302 receives sensor signals SS1-SSm from the vibration sensors 20. In one implementation, step 302 obtains the sensor signals SS1-SSm for a pre-defined period, for example, corresponding to the production cycle described above, and then provides the signals for processing by subsequent steps. In another implementation, step 302 may continuously receive signal values ​​from the vibration sensors SS1-SSm and provide the signal values ​​in near real time for processing by subsequent steps.

[0033] Step 303 uses the MES to identify signal values ​​associated with each component D1-Dn in the machine 10. Thus, in step 303, the MES is used as a reference to identify signal values ​​in the sensor signals SS1-SSm that represent the operation of each component D1-Dn. It can be seen that in order to use the MES as a reference, the time frame of the MES and each sensor signal SS1-SSm need to be synchronized.

[0034] In one embodiment shown in FIG. 3, step 303 may include substep 303a of matching the time points of the sensor signals SS1-SSm to the time points of the MES. In some embodiments, this time-domain matching is performed by using a reference signal SSr, which is a real-time signal generated by a reference sensor 20′ in the machine 10, as shown in FIGS. 1C and 2A. The reference sensor 20′ may be a position sensor or any other type of sensor positioned to signal a specific mechanical action that is included as an event in the MES. Thus, the reference signal SSr is generated simultaneously with the sensor signals SS1-SSm and indicates a predefined time point in the MES. In one such embodiment, step 303a compares the reference signal SSr to the sensor signals SS1-SSm and assigns predefined time points in the sensor signals SS1-SSm, thereby synchronizing with the MES. In some embodiments, the time-domain matching is instead performed by using a predefined reference signal SSr, which is retrieved from a memory, for example, memory element 201 (FIG. 2A). The predefined reference signal SSr may correspond to one of the sensor signals SS1-SSm and be aligned with the MES so that there is a known time correspondence between the time points of SSr and the time points of the MES. The predefined reference signal SSr may be generated from one or more sensor signals generated by one or more vibration sensors on a reference machine that is substantially identical to the machine 10. In one such embodiment, substep 303a may correlate the predefined reference signal SSr with the corresponding sensor signals to, for example, identify an optimal match between the signals. This correlation allows the time points of the sensor signals SS1-SSm to be aligned with the time points of the MES because the reference signal SSr has a known time correspondence with the MES. One technical advantage of using a predefined reference signal SSr is that the monitoring method 300 can be implemented on a machine 10 that does not have a reference sensor 20′. A disadvantage is that one reference signal SSr needs to be predefined for each setting of the machine 10. This disadvantage is eliminated by using the reference sensor 20′, thus increasing versatility and potentially accuracy.

[0035] 3, step 303 may include a further sub-step 303b using known associations between groups of events and components D1-Dn, as illustrated in FIG. 4B. In one embodiment, sub-step 303b associates corresponding time points of one or more of the sensor signals SS1-SSm with each component D1-Dn based on the time point of each work event of the MES, such that the corresponding time points identify one or more signal values ​​for each component D1-Dn.

[0036] Step 303 may identify a signal value for each component among all of the sensor signals SS1-SSm, or one or more selected sensor signals for each component. In one embodiment, step 303 selects one or more sensor signals for each component by using predefined associations between the sensor signals and the components, and identifies a signal value for each component from among the one or more selected sensor signals associated with each component.

[0037] Step 303 is further illustrated by the graph of FIG. 5. The upper part of FIG. 5 shows the sensor signal SS1 as a function of time obtained by step 302, and the lower part shows the MES as a function of time obtained by step 301. By locating SS1 and MES within a common time frame, it becomes possible to identify signal values ​​in SS1 corresponding to mechanical actions performed by a particular component in step 303. In one embodiment, step 303 extracts signal values ​​in SS1 that match the timing of respective work events in the MES. In another embodiment, step 303 may calculate signal values ​​in response to SS1 within a time window that matches the timing of work events in the MES. For example, the signal values ​​may be calculated as a measure of magnitude, such as average, sum, amplitude, root mean square (RMS), etc.

[0038] Step 304 evaluates the signal values ​​identified by step 303 for a condition assessment of each component. If step 304 identifies a current or future fault condition of one of the components, method 300 may proceed to step 305, which may signal the need for maintenance of the component, for example, via feedback device 202.

[0039] It can be seen that step 303 can identify signal values ​​corresponding to time-separate peaks in the sensor signals SS1-SSm. Such signal values, identified separately for each component, enable any conventional analytical technique to be applied in step 304 for identifying sudden fault and incipient fault conditions of specific components in machine 10 and estimating the RUL of individual components in machine 10. A sudden fault condition refers to a component malfunction or failure condition that requires immediate attention by maintenance personnel and possibly shuts down machine 10. An incipient fault condition refers to a state or condition of a respective component that is so imperfect that a degrading or catastrophic failure may (or may not) ultimately be the expected outcome if corrective action is not taken.

[0040] In one embodiment shown in FIG. 3, step 304 may include substep 304a of calculating one or more parameter values ​​for each component based on the signal values ​​determined by step 303 for each component, and substep 304b of analyzing the one or more parameter values ​​for a condition assessment of each component. In some embodiments, the one or more parameter values ​​may include one or more of: variance, mean, peak area, energy, power, RMS, kurtosis, crest factor, skewness, spectral kurtosis, and standard deviation. Substep 304b may include comparing the one or more parameter values ​​to respective thresholds. The thresholds may be set to detect a sudden fault condition for each component. Alternatively or additionally, substep 304b may include trending and forecasting one or more parameter values ​​over time for detecting an incipient fault condition for each component. As shown in FIG. 3, method 300 may repeat steps 302-304a to generate a time series of parameter values, e.g., trends and forecasts, for analysis by step 304b. For example, step 304b may compare hourly or daily parameter values ​​for incipient fault condition detection.

[0041] To illustrate the changes in vibration that can occur as a component deteriorates, Figures 6A-6B show a power signal, which represents the squared amplitude of the vibration signal, and contains two time-separated peaks (circled) due to the mechanical work performed by a particular component. In Figure 6A, the component is healthy. In Figure 6B, the component has failed, and the magnitude of the two peaks has increased significantly.

[0042] It will be appreciated that the analysis in step 304 can be performed at different levels of complexity depending on the available sensor data and the desired output. Those skilled in the art can select from a large number of well-known analytical techniques for condition assessment, including, but not limited to, statistical methods such as regression-based methods, Wiener processes, gamma processes, Markovian-based methods, stochastic filtering-based methods, covariate-based hazard methods, Hidden Markov Model-based methods, etc. Step 304 may also include machine learning (ML) or deep learning (DL) for fault condition detection and / or RUL estimation.

[0043] Returning to FIG. 2A, monitoring device 200 may include logic configured to implement method 300 of FIG. 3. In the illustrated example, the logic includes a set of modules or units 203-205. Signal adaptor 203 is configured to perform steps 301, 302, and 303a to synchronize sensor signals SS1-SSm with the MES. Signal value extractor 204 is configured to perform step 303b to extract one or more signal values ​​for each component from sensor signals SS1-SSm by using the synchronized MES. Analyzer 205 is configured to perform step 304 to evaluate the signal values ​​for a condition assessment of each component.

[0044] Each of modules 203-205 may be implemented in hardware or a combination of software and hardware. In some embodiments, monitoring device 200 may be implemented in a software-controlled computing device, such as that shown in FIG. 2B. In the example of FIG. 2B, monitoring device 200 includes processor 210 and computer memory 212. Processor 210 may include, for example, one or more of a CPU (“Central Processing Unit”), a DSP (“Digital Signal Processor”), a microprocessor, a microcontroller, an ASIC (“Application-Specific Integrated Circuit”), a combination of discrete analog and / or digital components, or some other programmable logic device, such as an FPGA (“Field Programmable Gate Array”). A control program 212A, including computer instructions, is stored in memory 212 and executed by processor 210 to perform the monitoring method, such as the example described above. A control program 212A may be provided to the monitoring device 200 on a computer-readable medium 20, which may be a tangible (non-transitory) article of manufacture (e.g., magnetic media, optical disk, read-only memory, flash memory, etc.) or a propagated signal. As shown in FIG. 2B, the memory 212 may also store data 212B for use by the processor 210, such as the MES, predefined reference signals SSr, etc. The monitoring device 200 further includes a communication interface 214, which may include a signal interface 200a (FIG. 2A), as well as further signal interfaces for communicating with the feedback device 202 and / or the controller of the machine 10, and / or the external memory element 201, if present.

Claims

1. 1. A method of monitoring a packaging machine (10) operating to produce packages (106) of a liquid food product, comprising: receiving (302) measurement signals (SS1-SSm) from a plurality of vibration sensors (20) within the packaging machine (10); obtaining (301) from a memory device (201) within the packaging machine (10) an event timing signal (MES) indicative of predefined work events of the packaging machine (10), each of the predefined work events corresponding to a mechanical action by a respective component (D1-Dn) in the packaging machine (10) as it operates to produce the package (106); and associating a point in time with each of the predefined work events. determining (303) signal values ​​associated with the respective components (D1-Dn) in the measurement signals (SS1-SSm) by using the event timing signal (MES) obtained from the memory element (201), the determining (303) including synchronizing (303a) the measurement signals (SS1-SSm) with the event timing signal (MES); and Evaluating the signal value (304) with respect to a state evaluation of each of the components (D1-Dn). A method comprising:

2. 2. The method of claim 1, wherein the mechanical action produces a response in at least one of the measurement signals (SS1 to SSm).

3. 3. The method of claim 1 or 2, wherein the event timing signal (MES) is generated by simulating the packaging machine (10) and executing its operations to produce the package.

4. The method described in claim 1, wherein the event timing signal (MES) represents the relative timing of multiple work events performed by the packaging machine during one production cycle, and the multiple work events are associated with respective components in the packaging machine.

5. A method as described in claim 1, comprising receiving a reference signal (SSr) from a reference sensor (20') in the packaging machine (10) that is simultaneous with the measurement signals (SS1 to SSm) and indicates a predefined point in time in the event timing signal (MES).

6. The identifying (303) further includes associating (303b) corresponding times of one or more of the measurement signals (SS1-SSm) with the respective components (D1-Dn) based on the times relative to the respective predefined work events relative to the event timing signal.

2. The method of claim 1, comprising:

7. 10. The method of claim 1, further comprising: searching for a predefined reference signal (SSr) that corresponds to one of the measurement signals (SS1-SSm) and matches the event timing signal (MES); and correlating the predefined reference signal (SSr) with the one of the measurement signals (SS1-SSm) to synchronize the measurement signal (SS1-SSm) with the event timing signal (MES).

8. 10. The method of claim 1, further comprising receiving, from a reference sensor (20') in the packaging machine (10), a reference signal (SSr) that is coincident with the measurement signals (SS1-SSm) and indicates a predefined point in time in the event timing signal (MES), and comparing the reference signal (SSr) with the measurement signals (SS1-SSm) to assign the predefined point in time to the measurement signals (SS1-SSm) to synchronize the measurement signals (SS1-SSm) with the event timing signal (MES).

9. The method according to any one of claims 1 to 8, wherein determining (303) the signal values ​​comprises determining signal values ​​corresponding to temporally separated peaks of the measurement signals (SS1 to SSm).

10. 10. The method of claim 1, wherein the evaluating (304) comprises calculating (304a) one or more parameter values ​​related to the signal value, and analyzing (304b) the one or more parameter values ​​with respect to the condition assessment.

11. 11. The method of claim 10, wherein the one or more parameter values ​​comprise one or more of variance, mean, peak area, energy, power, root mean square, kurtosis, crest factor, skewness, spectral kurtosis, and standard deviation.

12. 12. The method of claim 10 or 11, wherein the analyzing comprises at least one of comparing the one or more parameter values ​​to respective thresholds and analyzing changes in the one or more parameter values ​​over time.

13. 13. The method of any one of claims 1 to 12, further comprising signaling (305) a need for maintenance of the respective component (D1-Dn) when the evaluating (304) indicates a current or future fault condition of the respective component (D1-Dn).

14. A computer-readable medium comprising computer instructions (212A) that, when executed by a processor (210), cause the processor (210) to perform the method of any one of claims 1 to 13.

15. 14. A monitoring device comprising: a signal interface (200a; 214) for connecting to a plurality of vibration sensors (20) in a packaging machine (10); and logic (203, 204, 205) configured to control the monitoring device to perform the method of any one of claims 1 to 13.

Images