Apparatus for determining the actual state and / or the remaining service life of structural components of a work machine
Patent Information
- Authority / Receiving Office
- TR · TR
- Patent Type
- Patents
- Current Assignee / Owner
- LIEBHERR COMPONENTS BIBERACH GMBH
- Filing Date
- 2022-04-29
- Publication Date
- 2026-06-22
AI Technical Summary
Existing sensor-based monitoring systems for construction machinery struggle to reliably distinguish critical from non-critical damage in structural components, leading to unreliable condition assessments and complex maintenance processes that require skilled personnel, often resulting in unplanned downtime and high repair costs.
A device that generates synthetic damage characteristics from design data and adapts them using real condition information, employing an AI system to create a self-learning database for accurate condition and remaining service life determination, allowing untrained personnel to plan maintenance effectively.
Enables reliable and timely maintenance planning by accurately distinguishing between critical and non-critical damage, reducing downtime and repair costs through a self-learning system that adapts to real-world conditions.
Abstract
Description
[0001] The present invention relates to a device for determining the current state and / or remaining service life of structural components, for example large slewing bearings, of a working machine, in particular a construction, material handling and / or conveying machine, comprising sensors for acquiring state information relating to the structural component and an evaluation device for evaluating the acquired state information and determining the current state and / or remaining service life by comparing the acquired state information with predetermined damage characteristics.
[0002] For construction machinery such as excavators, cranes, dump trucks, bulldozers, or cable excavators, or material handling machines or conveying systems like forklifts and loaders, or other large construction machines such as surface milling machines or ship cranes, predicting the remaining service life or the time remaining until a structural component needs to be replaced is both important and difficult. If a piece of construction machinery breaks down on a construction site, for example, because a bearing seizes or overheats, a suitable replacement machine often cannot be procured and delivered to the site immediately. This leads to delays on the construction site during the repair time required. Often, not only are the tasks of the broken-down machine itself suspended, but other processes also experience delays due to the interconnectedness of the various construction machines.A similar problem arises with the aforementioned material handling machines and conveyor systems.
[0003] Often, it is only individual components or structural parts that are easy to replace and would not cause major subsequent delays if the replacement can be planned in a timely manner, but on the other hand, they can also cause major repair costs if other machine components are also affected when the small structural part breaks.
[0004] It is perfectly normal for structural components to show a certain amount of wear over time without necessarily requiring replacement. As long as the component's function is maintained and no failure is imminent, such wear and tear, which is harmless to operation, is accepted in order to maximize its service life. These minor, tolerable signs of wear can include small hairline cracks that do not affect strength, or minor surface chips or pitting on less functionally relevant surfaces. However, such wear and tear can also manifest as other component changes, such as a decrease in elasticity or increased bearing play.
[0005] Depending on how the structural components of a machine are monitored, it can be very difficult to distinguish critical damage from non-critical damage, as the signal response of the component-monitoring sensors can show more or less significant changes even with minor component modifications.
[0006] Furthermore, a wide variety of damage and associated damage characteristics can occur in the structural components, which can manifest themselves in correspondingly different anomalies in the sensor data. For example, vibrations resulting from normal, so to speak, uniform wear on the gears of a transmission stage can differ from vibrations caused, for instance, by a single, more severely damaged tooth in a gear pair. Yet another vibration pattern can result from a lack of lubrication and the associated stiffness due to overheating, or from uneven running caused by contamination or excessive bearing clearance.
[0007] Therefore, sensor-based monitoring systems for construction machinery have already been proposed, designed to objectify the determination of the actual state of construction machinery based on measured sensor data. For example, it is known to monitor certain operating parameters of the construction machine and to issue an error code in the event of irregularities or unusual values of the measured operating parameters (see, for example, JP-OS-8-144 312). However, such error codes are inherently not very informative or reliable, since, for example, a brief exceedance of a permissible speed, such as can occur when driving downhill on a construction site access road, does not yet allow for a reliable conclusion about any resulting engine damage.
[0008] German patent application DE 44 47 288 A1 discloses a machine fault diagnosis system and method. The system uses a combination of neural networks, expert systems, physical models, and fuzzy logic.
[0009] Document US 2021 / 072727 A1 discloses a construction machine, in particular a crane, and a method for controlling it.
[0010] Michael Osterkamp et al. (SIGNAL UND DRAHT: SIGNALLING & DATACOMMUNICATION, Vol. 109, No. 4, April 10, 2017 (2017-04-10), pages 65-72, XP055365766, DE, ISSN: 0037-4997) describe the combined use of infrared and acoustic measurement systems for the detection of bearing damage on wheelsets.
[0011] The document EP 2 402 731 A1 discloses a method for training a system for classifying a rolling bearing condition as well as a method and a system for classifying a rolling bearing condition.
[0012] The patent application DE 101 45 571 A1, filed by applicant Komatsu, further proposes a monitoring system for construction machinery designed to predict the degree of damage or abnormality in a more differentiated manner. This system involves the sensor-based monitoring of the exhaust pressure and temperature of the construction machinery's diesel engine and the analysis of the lubricating oil for specific components such as iron particles using a special analytical device. In addition to these sensor-based monitoring parameters, the patent application also considers it necessary to incorporate the results of a visual inspection performed by a skilled maintenance technician into the automated assessment of the construction machinery's current condition. This previously known monitoring system for construction machinery suffers from limited reliability in its condition assessment. The monitored exhaust gas parameters of exhaust temperature and exhaust pressure primarily only allow for the detection of problems with the diesel engine itself.On the other hand, the monitoring system is still relatively complex, as visual inspections must be carried out by maintenance staff.
[0013] The present invention therefore aims to provide an improved device for determining the current condition and / or remaining service life of a construction machine, avoiding the disadvantages of the prior art and advantageously developing the latter further. In particular, the invention seeks to achieve a reliable determination of the current condition and / or remaining service life of mobile construction machines that is easy to implement and allows for the timely initiation and planning of maintenance and repair measures, even by untrained maintenance personnel, with sufficient lead time.
[0014] According to the invention, the aforementioned problem is solved by a device according to claim 1. Preferred embodiments of the invention are the subject of the dependent claims.
[0015] To account for the diversity of possible damage characteristics, it is proposed to artificially generate synthetic damage characteristics in the form of samples or reference examples based on the design, geometry, and material data, and to continuously adapt these synthetically generated damage characteristics by feeding back real condition information obtained from sensor data. According to the invention, an active database system is provided for storing the damage characteristics. This system is connected to a determination unit for identifying the damage characteristics from the structural component's design data, as well as an adaptation unit for adjusting the predetermined damage characteristics based on the actual condition and / or remaining service life information determined by the evaluation unit.By synthetically generating damage characteristics from the design data of the structural component on the one hand, and then adapting the synthetically generated damage characteristics by feedback of the evaluated condition and / or remaining service life information on the other, a complex damage characteristic model can be created for determining the current condition and / or remaining service life, which does justice to the variety of possible damage and provides a high degree of accuracy in determining the current condition or remaining service life.
[0016] When determining synthetic damage characteristics, various design data can be used to calculate the parameters or data set that constitutes the respective damage characteristic sample. For example, for a rolling bearing, relevant damage indicators such as the rolling frequency of the bearing outer ring, a temperature profile over the operating time, or an acoustic emission pattern can be calculated from design data such as the number of rolling elements, number of rows, intended rotational speed, and / or geometric dimensions such as diameter, raceway width, or rolling circle diameter, and / or material data of the structural component such as rolling element and raceway hardness or rolling element and raceway material. Alternatively, the frequency spectrum of the envelope signal can be determined for a specific rotational speed.The determination device for determining damage characteristics from design data includes a module for determining and / or calculating kinematic frequencies from geometric data and / or operating data such as rotational speed and / or speed of movement, and optionally taking into account material data such as weight or hardness, wherein the aforementioned module preferably determines the kinematic frequencies independently of acting external forces or energies.
[0017] The aforementioned detection device also includes an adaptation module to adapt and transform vibration or frequency patterns or spectra corresponding to various types or patterns of damage to the respective system using the calculated or determined kinematics, in particular using the aforementioned kinematic frequency from geometric data. This generates adapted frequency patterns or spectra that correspond to the various types or patterns of damage of the specific system or component of interest. The initial, unadapted frequency patterns or spectra can be determined beforehand by measurement on other, real components or are known in catalog form from damage pattern libraries. For example, a damage pattern memory can be connected to the detection device, from which the detection device can retrieve the unadapted frequency patterns.The data can be read out and then adapted using the previously determined kinematic frequency or the kinematics of the specific component. The adapted frequency patterns or spectra can then be stored in a memory.
[0018] If localized damage occurs in a bearing, such as rolling element indentations, standstill corrosion, or spalling, this can be detected, for example, through vibration measurements. When rolling over local indentations, shock waves are generated, which can be calculated or estimated during synthetic analysis and can also be recorded by displacement, velocity, or acceleration sensors, or other sensors if necessary. For example, by comparing the recorded rolling frequency with previously synthetically determined rolling frequency damage patterns, the current condition or damage to the bearing can be determined.
[0019] Similarly, a structure-borne sound pattern of the structural component can be calculated, estimated, or otherwise determined from the aforementioned design data and compared with a real structure-borne sound pattern, which can be detected on the structural component using one or more structure-borne sound sensors, to determine the current state of the structural component. A structure-borne sound pattern library can also be used to determine the structure-borne sound patterns. This library contains characteristic structure-borne sound patterns for specific component and / or system types, which can then be adapted and transformed into a suitable structure-borne sound pattern based on the previously calculated or determined kinematics of the specific component or system.
[0020] Similarly, other synthetic damage characteristics of other structural components, such as the tooth engagement frequency of a drive shaft, can also be synthetically determined from design data.
[0021] Alternatively or additionally, synthetic damage characteristics can also be generated based on other system data, for example, based on a relationship between rotational speed and temperature via power data. In particular, it can be assumed that a certain temperature can be expected at a specific transmitted power at a specific rotational speed, and thus a rotational speed-temperature-power matrix can be generated. If unusual temperatures occur in certain power and / or rotational speed ranges, a specific type of damage can be deduced.
[0022] To better address the complexity of potential damage patterns, a combination module can advantageously be linked to the active database setup. This module combines the damage characteristics synthetically generated from the design data, creating combined damage characteristics that can be stored and saved in the database. Such combined damage characteristics can correspond to more complex damage patterns where the corresponding structural component exhibits not only a specific type of damage, such as spalling in the rolling bearing raceway, but also various types of damage simultaneously. For example, in addition to the aforementioned raceway spalling, bearing contamination or excessive bearing clearance, which can lead to rough running, may also occur.
[0023] The aforementioned combination module can not only combine different damage patterns of a structural component, but alternatively or additionally, it can also combine the damage characteristics of different structural components to account for the mutual influences of these damage characteristics on one another. For example, a damaged bearing and the resulting uneven running of the bearing can also influence vibrations of a gear stage supported by it and / or have an impact on the damage pattern of the gear stage, which is rotationally supported by the bearing. The combination module can therefore advantageously be configured to combine different, synthetically generated damage characteristics of a structural component and / or to combine synthetically generated damage characteristics of different structural components.The damage characteristics generated through this combination can also be stored in the database or kept available from there.
[0024] To achieve a more reliable determination of the current state or remaining service life, an advantageous embodiment of the invention can provide for a weighting of the individual and / or combined damage characteristics. In particular, each sample or synthetically generated damage characteristic can be weighted according to its probability of occurrence, i.e., the frequency of the failure cause of the respective component. Damage characteristics with a higher probability of occurrence can be weighted more heavily than damage characteristics that reflect relatively rare types of damage.
[0025] The weighting component can be configured to individually weight each synthetically generated damage characteristic. Alternatively or additionally, the weighting component can also weight combinatorially generated damage characteristics, particularly based on the probability of a specific damage combination occurring.
[0026] When evaluating the sensor-determined condition information and comparing it with the available damage characteristics, the parameters that constitute the condition information can, in principle, be evaluated in different ways or compared with the damage characteristics in different ways. For example, different parameters can be weighted differently and / or considered in different ways.
[0027] Here, a change in each parameter can be taken into account absolutely, for example, by adjusting the predetermined damage characteristics if a predetermined change threshold is exceeded. Alternatively or additionally, a summary approach can be used, for example, by adjusting the predetermined damage characteristics via the adjustment device if a predetermined change is exceeded when several parameters are considered summarily.
[0028] The adaptation device can adjust the damage characteristics in various ways to the evaluated, real condition information or using this condition information.
[0029] In a further development of the invention, the adaptation of the condition signal evaluation and / or the damage characteristics provided by the database to changing condition and / or operating conditions of the structural component or aging influences is not based on rigid criteria, but rather on a self-evolving, variable set of rules. In particular, in a further development of the invention, the aforementioned evaluation device and the adaptation device are designed as a self-learning system, or the aforementioned components form part of a self-learning system that can estimate the influence of the acquired condition and / or operating information or the real-world information patterns derived therefrom on the damage characteristics or on the damage pattern of the representing parameter set.
[0030] In particular, the evaluation unit and the aforementioned adaptation unit can be equipped with artificial intelligence or implemented in an AI system that, for example, includes a regression analysis module to estimate a relationship between the recorded condition and / or operational information and the synthetically generated condition or damage reference patterns of the machine or structural component. For example, the aforementioned regression analysis module can adapt or further develop a functional relationship between the aforementioned parameters or a curve that characterizes the dependence of the actual condition or remaining service life on the aforementioned real condition parameters, preferably by using the continuously recorded condition changes and the resulting actual condition or remaining service life forecast, and especially with the further assistance of a training set of the aforementioned parameters.The aforementioned training set of parameters can initially be predefined, e.g. obtained from one or more test runs, and / or continuously updated or expanded, particularly through data obtained during machine operation.
[0031] In particular, the device can use artificial intelligence to compare the constantly measured state response of the structural component or the entire working machine or a subassembly thereof with the characteristic state or operating behavior and / or damage pattern in order to identify damage to one or more structural components, especially cracking.
[0032] Using the AI system, the reference examples of damage characteristics of the machine or structural component(s) can be adapted, particularly depending on the recorded, real-world parameter sets of the machine and / or structural component, which reflect the actual machine condition, and their changes. This ensures that the forecast remains accurate and the error rate is minimized.
[0033] In order to better monitor the machine as a whole for damage, sensors for recording relevant condition parameters such as vibrations or structure-borne noise can be assigned to several structural components, e.g. rolling bearings, of the system.
[0034] The evaluation unit can compare the condition information of various structural components, such as different rolling bearings, to compare changes in the condition or the parameter set representing it on one structural component with corresponding changes in the condition information on one or more other structural components, and thus to detect abnormal changes in condition more precisely. Such a comparison can be performed in addition to the aforementioned adjustment of the evaluation criteria and / or the signal reference pattern.
[0035] In a further development of the invention, the structural component can be, for example, a rolling bearing or large rolling bearing, such as a center-free large rolling bearing with a diameter of more than 0.5 m or more than 1.0 m, and can be monitored with regard to the rolling frequency pattern and / or the structure-borne noise emissions and / or the temperature profile over the duty cycle and / or a noise emission pattern.
[0036] The invention is explained in more detail below with reference to a preferred embodiment and the accompanying drawings. The drawings show: Fig. 1: A representation of a device for determining the current state and / or the remaining service life of structural components of a machine according to an advantageous embodiment of the invention. Fig. 2: A representation of the device made of Fig. 1with supplementary details in the individual components of the device, Fig. 3: a representation of the frequency image corresponding to a damage pattern and its transformation to a frequency damage signature specifically adapted to the system of interest, and Fig. 4: a schematic representation of the synthetic generation of a damage characteristic starting from a fundamental vibration image generated by structural analysis and its transformation to a specific damage characteristic image.
[0037] As the figures show, the Condition Monitoring System 1 includes an active, self-implementing database 2, which provides a variety of synthetically generated damage characteristics as reference examples 3 in the form of data sets that specify different damage patterns of a structural component 4 and include parameters on which the respective damage pattern is based or which are characteristic of the respective damage pattern.
[0038] How Figure 2 As shown, a reference example 3 designated as "Sample I" can contain the rolling frequency of a bearing ring, for example an outer ring of a rolling bearing, wherein the rolling frequency mentioned can contain the frequency spectrum mentioned, for example, for different degrees of damage and possibly also for the undamaged state for one or more rotational speeds.
[0039] Another reference example 3, referred to as "Sample II", can contain the damage characteristics of a drive component, for example in the form of the tooth engagement frequency of a drive shaft.
[0040] Various other reference examples may include, for example, a temperature profile of a bearing over its operating time and / or over the time after shutdown, or a sound emission spectrum of a rolling bearing, or a vibration pattern of a component, or other characteristic damage patterns.
[0041] As the figures show, a determination unit 5 can be connected to the database 2, which automatically generates the aforementioned synthetic damage characteristics from provided design data for the respective structural component 4, in particular from geometry and / or drawing and / or material and / or substance data. Such a determination unit can also estimate the damage characteristics for a given structural component, if necessary, using stored data sets for similar structural components, and / or estimate the synthetic damage characteristics for the structural component of interest from known, typical damage characteristics for a specific structural component, for example by interpolation and / or extrapolation based on the geometry data.
[0042] To synthetically generate damage characteristics, the kinematics of the specific system of interest can first be calculated. In particular, kinematic frequencies can be calculated for any machine component, such as rolling bearings, gears, or shafts. Kinematics, in this context, refers to a description of the system by its geometry and time-varying parameters, independent of forces and energies.
[0043] Considering, for example, a rolling bearing, the kinematics can be determined as follows, where geometric data such as the number of rolling elements z, the rolling element diameter DW, and the pitch circle diameter D PW at contact angle α are assumed to be known or can be obtained from a design database. The following steps can be performed to determine the kinematics of the rolling bearing: Calculation of the rotational frequency of the rolling element n W = ± n 2 ⋅ D pw D W − D W ⋅ cos 2 α D pw → Calculation of the rolling frequency on the inner ring u j = z 2 ⋅ 1 + D W ⋅ cos α D pw → Calculation of the rolling frequency on the outer ring u A = z 2 ⋅ 1 − D W ⋅ cos α D pw →
[0044] To generate a damage pattern, for example for damage to the outer ring of the rolling bearing, the following procedure can be used; see in particular also Figure 3 . Generating spectra with corresponding damage information: From calculating the rolling frequency on the outer ring uA, a damage signature for, for example, bearing outer ring damage can be generated in the frequency domain (damage patterns are known (from literature) or are available from other measurements). A normalized data set can be converted to geometric variants using kinematics. This allows the frequency pattern to be determined according to... Fig. 3 The upper part is preserved. Transforming the damage signature in the frequency domain ( f̂ ) into the time domain (f) → X (jw) -> x (t) to generate excitation shocks according to the machine damage characteristics f (uA), cf. Fig. 3 , lower part.
[0045] Alternatively or additionally, the following procedure can be used to create a damage pattern that represents outer ring damage of the rolling bearing: Generating spectra with corresponding damage information: From structural analysis (e.g., from FE simulation), the natural mode of the structure can be determined → generating the fundamental mode. f(Sch Ani ) , cf. Fig. 4 upper part Superposition of the machine damage characteristic f (u A ) and the fundamental vibration f (Sch Ani ) for the generation of synthetically generated damage characteristics / samples, see [reference]. Fig. 4 lower part.
[0046] Advantageously, by combining synthetic damage characteristics or samples, the structure-borne sound signature of a system or component of interest can be generated as early as the design phase. This eliminates the need for the complex training process required by previous monitoring systems, which relies on real machine failures and potentially artificial intelligence. Without synthetically generating a structure-borne sound signature or damage characteristic based on the design data, at least seven to eight real systems corresponding to the system of interest would have to be tested with known failure modes. In contrast, the synthetically generated damage characteristics provide the AI module with more than two-thirds of the expected damage patterns, significantly reducing the training time and effort required to refine the system.For example, the remaining, still missing or not synthetically generated damage characteristics, on the order of 20%, can be reconstructed by a self-learning system.
[0047] To accommodate more complex damage patterns or signs of wear, the active, self-implementing database 2 is advantageously assigned a combination module 6, which combines the damage characteristics synthetically determined by the determination device 5 from the design data and thereby generates combinatorial damage characteristics.
[0048] Advantageously, the damage characteristics, for example the synthetically generated damage characteristics and / or the combinatorially determined damage characteristics, can be given a weighting that can be generated by a weighting module 7, in particular on the basis of the probability of an occurrence of a respective damage event.
[0049] The aforementioned database 2 or the building blocks assigned to it for determining the damage characteristics, i.e., in particular the determination device 5 and / or the combination building block 6 and / or the weighting building block 7, can be part of a self-learning AI system 8 or be formed by such an AI system 8, which is equipped with artificial intelligence and can estimate or determine a relationship between a specific state parameter or several state parameters of a structural component and a damage pattern of the structural component or its current state and / or remaining service life, wherein the AI system can, for example, have a regression analysis building block in order to adapt the aforementioned relationship between a parameter or a set of parameters and the current state or remaining service life of the structural component based on changes occurring.
[0050] As the figures further show, the Condition Monitoring System 1 also includes a sensor system 9, which can include various sensors for measuring or recording relevant state variables or parameters of the structural component 4 of interest, whereby the sensors mentioned can be of a different design depending on the structural component.
[0051] For example, the aforementioned sensor system 9 can include a structure-borne sound sensor and / or a displacement sensor and / or a velocity sensor and / or an acceleration sensor and / or a temperature sensor in order to be able to detect corresponding state variables on the structural component 4 or associated surrounding components, such as vibration data, temperature data, lubricant data, noise emission data or other relevant state information of the structural component 4.
[0052] The aforementioned condition information, which is acquired and provided by the sensor 9, can be evaluated by an evaluation unit 10 and compared with the damage characteristics provided by the database 2 in order to determine the current condition and / or the remaining service life of the structural component 4. How Figure 2 As shown, the aforementioned evaluation device 10 can include an evaluation module 11 that compares actually measured damage or condition characteristics with the synthetic damage characteristics from the reference examples 3 or the combinatorial damage characteristics derived therefrom. A pre-analysis and / or processing module 12 can be provided upstream of such an evaluation module 11, which processes and / or pre-analyzes the sensor-acquired condition information, for example, by means of a filter or other signal processing components.
[0053] Based on the evaluation of the evaluation unit 10, a forecast and / or trend analysis module 13 can provide a forecast for the current state and / or a trend for the current state of the structural component and / or the entire machine, cf. Figure 1 and Figure 2 .
[0054] As the figures show, the Condition Monitoring System 1 also includes an adaptation device 14, which adapts the damage characteristics provided by the database 2 based on the evaluations of the evaluation device 10 or on the basis of the specific condition and / or remaining service life information.
[0055] The aforementioned adaptation device 14 is preferably part of a self-learning AI system or is formed by such an AI system 8, which provides for feedback of real machine state data and / or integration into the existing reference examples 3 by means of artificial intelligence.
[0056] In particular, the AI system 8 can adapt the synthetic damage characteristics and / or the damage characteristics derived from them combinatorially depending on relevant machine condition and / or environmental parameters, especially, for example, depending on the age of the structural component 4, the machine and / or operating condition, and changes in environmental influences. This ensures that the forecast remains accurate and the error rate is minimized.
[0057] The Condition Monitoring System 1 therefore relies in particular on a data analysis model based on synthetically generated machine operating characteristics.
[0058] For this purpose, synthetic operating characteristics in the form of samples are artificially generated based on the design of a component / product. Each sample corresponds to a specific damage characteristic of a particular component (e.g., rolling frequency of the outer bearing ring, tooth engagement frequency of the drive shaft, etc.) which can be calculated from geometry / drawing data.
[0059] By combining specific, synthetic samples, a complex picture of all possible, measurable forms of damage is generated. This database can subsequently be compared with the measured damage characteristics (e.g., via structure-borne sound, etc.) and the condition of the component assessed. Due to the large number of variations, the comparison is performed using artificial intelligence (AI) or a comparable feature recognition system.
[0060] The samples or reference examples of the damage characteristics, as well as their combination, can be stored in advance in a comparison database and assigned to the respective component.
[0061] In a further development stage, each sample can be weighted according to the probability of occurrence (frequency of the failure cause of the respective component).
[0062] Depending on the system's learning capability, the sample database of damage characteristics can be expanded. Furthermore, the system can be "rewarded" through subsequent damage analysis to improve the recognition rate for related samples (e.g., from other, but similar components).
Claims
1. An apparatus for determining the actual state and / or the remaining service life of structural components (4), for example large-diameter rolling bearings, of a work machine, in particular a construction machine, a material-handling machine and / or a conveyor machine, comprising a sensor system (9) for acquiring state information relating to the structural component (4), and an evaluation device (10) for evaluating the acquired state information and determining the actual state and / or the remaining service life on the basis of a comparison with predetermined damage characteristics, wherein an active database device (2) is provided for storing the damage characteristics, to which a determination device (5) for determining the damage characteristics from design data of the structural component (4), and an adjustment device (14) for adjusting the predetermined damage characteristics on the basis of the state and / or the remaining service life information determined by the evaluation device (10) are connected, characterized in that the determination device (5) is configured, for determining synthetic damage characteristics, to determine kinematic frequencies of the structural component (4) from geometry data of the structural component (4) in order to generate a damage frequency image for the structural component (4) from the kinematic frequencies, wherein the determination device (5) comprises an adjustment module configured to transform frequency patterns corresponding to different damage patterns and / or types into adapted frequency patterns corresponding to different damage patterns and / or types of the specific structural component (4) based on the geometry data of the structural component (4).
2. The apparatus according to the foregoing claim, wherein the determination device (5) for synthetically determining the damage characteristics comprises a structural analysis module for determining fundamental oscillation of the structural component (4) and comprises a superimposition module for superimposing frequency patterns indicative of different damage patterns and / or types on the determined fundamental oscillation in order to generate synthetically generated damage characteristics adapted to the structural component (4) by said superimposition.
3. The apparatus according to the foregoing claim, wherein the evaluation device (10) and / or the adjustment device (14) are configured as a self-learning system and / or as part of a self-learning system (8) which feeds back the sensorily detected state information and / or the actual states and / or remaining service lives derived therefrom to the database (2) and / or integrates them into the damage characteristics stored by the database (2).
4. The apparatus according to the foregoing claim, wherein the self-learning system comprises a regression analysis module for determining the influence of determined damage patterns and / or determined actual states on damage characterizing parameters of the structural component such as structure-borne sound signal reference patterns, roll-over frequency patterns or tooth mesh frequency patterns of the structural component by regression analysis.
5. The apparatus according to one of the two foregoing claims, wherein the self-learning system (8) comprises a KI-based estimation module for estimating correlations between acquired actual state information patterns and synthetically generated damage characteristics and / or between acquired actual state information patterns and a damage pattern or a remaining service life of the structural component.
6. The apparatus according to one of the foregoing claims, wherein a combination module (6) for combining the damage characteristics synthetically generated by the determination device (5) and providing combinatorial damage characteristics is associated with the determination device (5), wherein the evaluation device (10) is configured to match the state information acquired by the sensor system (9) with the combinatorial damage characteristics.
7. The apparatus according to one of the foregoing claims, wherein a weighting module (7) for weighting the damage characteristics on the basis of an occurrence probability of a damage event corresponding to the damage characteristic is associated with the determination device (5).
8. The apparatus according to one of the foregoing claims, wherein the sensor system (9) comprises at least one sensor from the group of sensors: oscillation sensors, temperature sensors, lubricant sensors, structure-borne sound sensors, acceleration sensors, displacement sensors and speed sensors, the adjustment device (14) being configured to adjust the damage characteristics stored by the database (2) depending on at least one signal from the at least one said sensor.