Method and apparatus for detecting a data set

Abstract

A method and a device for inspecting a data set, the method comprising the steps of: receiving a first thermal profile of a portion of a paving area distributed with a paving material, the first thermal profile comprising a plurality of temperature values assigned to respective measurement points; wherein the portion comprises a first sub-portion; analyzing the first thermal profile to detect a separation point of the paving material within the portion, thereby enabling a determination of a quality of the paving material, wherein the analyzing comprises: determining a first zone of measurement points arranged adjacent to each other and having temperature values within a predetermined range, wherein the first zone corresponds to the first sub-portion, and wherein the first zone is at least partially surrounded by measurement points having temperature values outside the predetermined range; determining a first analysis parameter of the first zone; and determining a first quality parameter of the sub-portion to assign the first quality parameter to the first analysis parameter.

Description

Technical Field

[0001] Embodiments of the present invention relate to a method for detecting a dataset including at least a first quality parameter and a first analytical parameter, and enabling the evaluation of the quality of paving materials. Background Technology

[0002] Another embodiment relates to corresponding equipment. Another embodiment relates to a paving machine including such equipment. The general objective of these embodiments is to improve the quality control system in the field of road construction machinery, such as asphalt paving machinery, based on temperature measurements of the newly laid paving material, such as asphalt or tar, directly behind the machine or tool (the entire slab).

[0003] Quality control is crucial in asphalt paving. The processing temperature of newly laid paving material is a significant process variable in road construction, substantially affecting performance characteristics such as pavement stability, interlayer adhesion, and service life. Asphalt paving machinery (pavers) typically distributes the paving material and pre-compacts its surface with a slab attached to and pulled by the rear of the paver. Rollers then further compact the paved surface. Factors such as environmental and weather conditions during paving, along with other factors, influence the efficiency and success of the paving operation at different stages.

[0004] Processing materials under optimal temperature conditions has long been considered important, but this process typically requires manual control and measurement by support and operators. Paving materials are usually obtained at relatively high temperatures in asphalt or tar plants. Depending on the distance the supply machinery must travel to reach the work site, as well as traffic and ambient temperatures, the asphalt can be cooled to a certain extent before delivery. Furthermore, the progress of the paving machinery and compaction machinery or rollers can vary.

[0005] Once the paving material finally reaches the paving machinery or paver, the degree of cooling can vary depending on the temperature of the paving material during transport, environmental factors, etc. In some cases, the paving material can separate within the paving machinery, resulting in relatively cold and relatively hot material trenches or accumulations within the machinery. Once these accumulations are distributed on the working surface, they can lead to undesirable, largely timely temperature gradients within the paving material. In a typical paving process, the paving material is discharged and distributed by the paving machinery or paver, then pre-compacted by a slab compactor, and then prepared for further compaction by various compaction machines. During this process, the material temperature can deviate significantly from the expected temperature. Furthermore, due to varying weather conditions or undesirable separation or poor mixing, the material temperature may be uneven from one pavement area to the next.

[0006] Due to the importance of pavement temperature during the paving process, its measurement has become increasingly crucial. Therefore, known systems measure the paving temperature behind the paving machine, particularly behind a slab pavement. Several existing techniques based on thermal imaging exist.

[0007] EP 2 789 741 A1 describes a road finishing machine with a thermal imaging device attached to a part of the machine for recording georeferenced thermal imaging data of at least one area of ​​the pavement layer. The road finishing machine includes a display on which all measurements from the thermal imaging device can be indicated, and the display provides the possibility of suggesting improved paving parameters to the operator based on the measurements from the thermal imaging device.

[0008] EP 2 982 951 A1 describes a thermal imaging module for a road finishing machine, which includes a temperature measuring device, an imaging device (means), and an evaluation unit. The evaluation unit is configured to determine a deviation area if one or more deviation criteria are met based on the sensed temperature values.

[0009] CN 102691251 A describes an infrared detection system and method for separating asphalt temperature during asphalt paving. This system provides real-time monitoring of temperature measurement during asphalt paving. The monitoring results can be used to identify adverse factors occurring during asphalt paving and to formulate solutions in a timely manner. These adverse factors can be controlled, and their effects can be reduced or completely eliminated, thus ensuring paving quality.

[0010] WO 00 / 70150 A1 describes a pavement temperature monitoring system having a temperature sensor mounted on the rear end of a paving vehicle, allowing the entire width of the formed pad to be scanned or imaged. A display device is capable of receiving multiple electrical signals from the temperature sensor and generating and displaying a graphic image of the temperature distribution of the formed pad.

[0011] DE 10 2008 058 481 A1 describes an asphalt system in which the navigation of construction vehicles is based on a so-called location-temperature model. This system determines where compaction vehicles are best positioned based on an initial assessment and subsequent measurements of the asphalt temperature.

[0012] In addition, EP 2 990 531 A1 and EP 2 666 908 A1 describe systems and methods for road finishing machines used to determine the cooling behavior of newly laid asphalt pads.

[0013] Some existing technical documents describe suggestions to machine operators regarding adjustments to machine parameters when the measured temperature of newly laid paving material is below or above a predetermined temperature. However, it is not true that these suggestions to machine operators are always correct, as none of the aforementioned existing technical documents address the exact root cause of such temperature deviations or analyze the actual and real symptoms of thermal separation of the paving material that occurs during the paving process. Adjusting the correct machine parameters relies primarily on the experience of the machine operator or paving workers to ensure that the paving material is laid by the paving machine under optimal conditions.

[0014] Another prior art document is EP 3 456 880 A1, which describes a method for controlling the quality of paving materials. Here, for example, thermal distribution or thermal patterns are identified and analyzed based on the orientation of the thermal pattern in order to draw conclusions from that thermal pattern. However, there are many different patterns that can achieve such conclusions, where, according to the prior art, only a limited number of error types are known. Therefore, an improved method is needed. Summary of the Invention

[0015] The purpose of this invention is to find a concept for enhancing the selection of storage pattern / thermal separation scenarios.

[0016] This objective is achieved through the subject matter of the independent claims.

[0017] An implementation provides a method for detecting a dataset including at least a first quality parameter and a first analytical parameter, enabling the evaluation of the quality of paving material distributed along a paving area using a paving machine. The method includes the basic steps of receiving a first thermal distribution and analyzing the first thermal distribution. The first thermal distribution belongs to a portion of the paving area where paving material is distributed; the first thermal distribution includes multiple temperature values ​​assigned to corresponding measurement points, wherein this portion includes a first sub-portion. Analyzing the first thermal distribution has the purpose of detecting separation points of the paving material within this portion, thereby enabling the determination of the quality of the paving material. The analysis includes: - Determine a first region of measuring points arranged adjacent to each other and having temperature values ​​within a predetermined range, wherein the first region corresponds to a first sub-part, and wherein the first region is at least partially surrounded by measuring points having temperature values ​​outside the predetermined range; - Determine the first analytical parameters for the first zone (e.g., the orientation of the first zone relative to the direction of travel or average temperature); and - Determine the first quality parameter of the sub-section (e.g., a parameter describing the error type of the paving material at the first sub-section) to assign the first quality parameter to the first analysis parameter.

[0018] According to an implementation, the method includes the step of storing a first analytical parameter together with a first quality parameter; optionally, the method includes the step of sending the first analytical parameter together with the first quality parameter to store the first analytical parameter and the first quality parameter on a server.

[0019] According to a preferred embodiment, the analysis step includes a self-learning algorithm and / or is based on artificial intelligence.

[0020] According to a preferred embodiment, the method includes a step of selecting an analysis parameter or a segment of one or more possible analysis parameters before performing the analysis step. Possible sets of analysis parameters may include: ● The orientation of the first zone relative to the direction of travel; ●The average temperature within the first zone; ●When comparing the temperature values ​​of measurement points belonging to the surrounding area of ​​Zone 1, the relative temperature of the temperature values ​​within Zone 1; ●The size of the first zone; ●Temperature deviation within Zone 1; ●The shape of the pattern in the first area; ●There exists a second region with measurement points corresponding to the second sub-part of this section; ●Another area of ​​measurement points corresponding to another sub-section of this section; ● The distance between Zone 1 and Zone 2 or between Zone 1 and another zone; ● The relative positions of Zone 1 to Zone 2 or Zone 1 to another zone; or ● A combination of at least two or more group elements.

[0021] This pre-selection of analysis parameters helps train the detection algorithm, enabling it to perform accurate and fault-resistant quality analysis (diagnosis).

[0022] The embodiments of the present invention are based on the discovery that within a temperature distribution or thermal pattern, one or more analytical parameters, such as the shape of the pattern or the temperature deviation of points from the surrounding environment, can be determined and used in conjunction with quality information, such as information about the type of error, to determine a dataset / learning data. These steps can be performed automatically or semi-automatically, for example, using artificial intelligence. The dataset determined in the described manner enables the formation of a data foundation by which different determinations of different scenarios can be detected, for example, different data types determined based on the thermal distribution. As discussed above, the described method can be based on a self-learning algorithm, and therefore artificial intelligence can be used to implement the described method. This facilitates the continuous enhancement of the dataset and improves accuracy. Another advantage is that the entire method or a large part of the method can be executed automatically. Another advantage is that the knowledge generated by the self-learning algorithm can be shared with other systems and / or transferred to other paving systems / control systems of the paving machine.

[0023] According to the implementation method, the step of determining the first region of the measurement points includes a pattern determination step. This pattern can be described using analytical parameters. Typically, these analytical parameters can be (selected from) a group including the following: ● The orientation of the first zone relative to the direction of travel; ●The average temperature within the first zone; ●When comparing the temperature values ​​of measurement points belonging to the surrounding area of ​​Zone 1, the relative temperature of the temperature values ​​within Zone 1; ●The size of the first zone; ●Temperature deviation within Zone 1; ●The shape of the pattern in the first area; ●There exists a second region with measurement points corresponding to the second sub-part of this section; ●Another area of ​​measurement points corresponding to another sub-section of this section; ● The distance between Zone 1 and Zone 2 or between Zone 1 and another zone; ● The relative positions of Zone 1 to Zone 2 or Zone 1 to another zone; or ● A combination of at least two or more group elements.

[0024] It should be noted that, according to the implementation, the analysis step is based on learning data that includes at least input data. This input data may include first analysis parameters and / or (determined) patterns (e.g., cold spots on the pavement). Optionally or additionally, the learning parameters may include first quality parameters, such as the error type of the paving material at a first sub-section. According to the implementation, the method includes the step of receiving parameters of the paving machine and / or the configuration of the paving machine. This parameter / configuration information can be used as part of the learning data. Therefore, the analysis step is based on learning data that includes at least decision parameters defining the type or number of decision nodes, wherein the decision parameters depend on the parameters of the paving machine or the configuration of the paving machine.

[0025] According to an embodiment, the method further includes, for example, receiving from the operator of the paving machine at least one instruction assigned to the quality parameters or error type of the paving material at the first sub-section. This advantageously aids in learning the system based on the operator's experience / knowledge.

[0026] According to the implementation, the receiving and analysis steps are repeated for the same paving area or another paving area, and / or wherein the receiving and analysis steps are repeated for another paving machine. This enables the system to be enhanced to further scenarios (second quality parameters and second analysis parameters assigned to each other). Here, the second quality parameter / second analysis parameter can refer to a comparable scenario (when compared with the first quality parameter / first analysis parameter) or a completely new scenario.

[0027] According to one implementation, multiple measurement points within a thermal profile are arranged according to a regular grid. According to another implementation, the method is performed for multiple temperature profiles, or specifically for multiple temperature profiles that overlap with each other.

[0028] Another embodiment provides an apparatus for detecting a dataset including at least a first quality parameter and a first analysis parameter. The apparatus includes an interface for receiving a first thermal distribution and a computing unit for analyzing the first thermal distribution to detect separation points of paving material within a portion. As discussed above, the analysis processed by the computing unit is performed.

[0029] According to the implementation method, the computing unit is based on artificial intelligence and / or configured to execute a self-learning algorithm.

[0030] It should be noted that, according to the implementation method, the training of the artificial intelligence algorithm is performed in the cloud or on a mainframe computer. This means that images / heat distributions are recorded by the corresponding construction machinery and sent to a central unit as training data. Labeling can be performed manually or automatically by assigning appropriate quality parameters to the images used as training data. The quality parameters, together with the images, form the training data. The improved software can then be sent to the corresponding construction machinery, for example, as an update. Based on the new training data, the update algorithm executed on the construction machinery can be improved to determine problem points based on the heat distribution. The background to "outsourcing" the training algorithm is that this process typically requires high computing power.

[0031] The above implementation is based on paired analytical and quality data that enable accurate identification of problem points. This dataset can be enhanced by adding appropriate changes to command / construction machinery parameters that allow avoidance of the identified problem points. This enhanced dataset can also be sent to the construction machinery. The effectiveness of the recommended / command / changed machinery parameters can be verified by the implementation algorithm used to assess pavement quality based on heat distribution. This newly recorded data can be used again as training data. In this case, the command / machinery parameters are considered when executing the learning algorithm (e.g., on a mainframe computer).

[0032] According to one embodiment, the device includes a thermal distribution camera or asphalt temperature scanner configured to record the thermal distribution of a portion of the paved area when guided thereto. According to another embodiment, the device includes a mobile device and / or display configured to output information and / or instructions; additionally or optionally, the device includes a mobile device or control unit for receiving information about quality parameters from an operator. According to yet another embodiment, the device may include a wireless communication module configured to exchange with a server a set of first analysis parameters and first quality parameters.

[0033] Another embodiment provides a computer program for performing the methods described above. An additional embodiment provides a paving machine that includes the equipment discussed above.

[0034] Before discussing embodiments of the invention in detail with reference to the accompanying drawings, applications of the above embodiments will be discussed with reference to application examples. The above embodiments enable the detection of a dataset including at least a first quality parameter and a first analysis parameter. Based on this dataset, the quality of paving materials can be evaluated. Application examples describe how this evaluation process can be performed. According to a basic application example, a method for controlling the quality of paving materials distributed along a paving area using a paving machine is provided.

[0035] The method comprises two basic steps: receiving at least one thermal distribution belonging to a portion of a paved area where paving material is distributed from, for example, an infrared camera, and analyzing the at least one thermal distribution to detect separation points of the paving material within the portion. The thermal distribution includes multiple temperature values ​​assigned to corresponding measurement points that can be arranged according to a grid layout. The analysis comprises three sub-steps: determining a first zone of measurement points arranged adjacent to each other and having temperature values ​​within a predetermined range, wherein the first zone is at least partially surrounded by measurement points having temperature values ​​outside the predetermined range; the next sub-step is analyzing the orientation of the first zone relative to the paving machine's direction of travel (e.g., determining whether the first zone is oriented approximately along or perpendicular to the direction of travel); and the final sub-step assigning appropriate types of indications (especially error indications, etc.) to the portion based on the orientation analysis.

[0036] According to an enhanced application example, the method includes the following steps: analyzing temperature deviations within the section, for example, to determine the deviations of temperature values ​​in a first zone from minimum or maximum temperature values ​​within the section or from temperature values ​​at measurement points surrounding the zone. According to another application example, the analysis of heat distribution includes another sub-step: identifying a second zone of measurement points (laid adjacent to each other and having temperature values ​​within another predetermined range, wherein the second zone is at least partially surrounded by measurement points having temperature values ​​outside the other predetermined range, or wherein the second zone is adjacent to the first zone) and analyzing the orientation of the second zone relative to the direction of travel.

[0037] Typically, some application examples can be based on the discovery that there are certain standards for the orientation and temperature deviation of temperature points in the inspected paving area, enabling real-time analysis of thermal data, identification of potential causes of separation, and automated communication providing possible solutions to paving personnel. To support paving personnel, identification patterns (especially error patterns, etc.) within the thermal distribution are identified and assigned to predetermined pattern types or predetermined error types. The assignment of pattern types or error types enables the output of instructions / hints to paving personnel to avoid typical causes of the corresponding type of pattern or error (thermal separation). An example of such communication to paving personnel could be real-time warnings to paving operators or paving supervisors in the event of severe separation problems. The main advantage is that the described system analyzes thermal data and provides recommendations automatically without the assistance of paving personnel. Therefore, it is independent of the experience of the machine operator, paving personnel, or paving expert. Application examples of the present invention also have the advantage that the system continuously and uninterruptedly analyzes the measured temperature distribution. When considering the prior art, it cannot be guaranteed that the machine operator will always be watching the operation and display unit's display and detecting every possible problem during the paving process. Continuous monitoring has improved the overall quality of the roads to be produced.

[0038] Depending on the application example, the analysis of temperature deviation may have different variations. For example, to analyze temperature deviation, a sub-step may be performed to determine the temperature gradient from a measurement point belonging to a first zone to a measurement point outside that zone, to detect whether the temperature gradient is below or above a predetermined threshold, such as 25 degrees Fahrenheit (150°F vs. 175°F) or 50 degrees Fahrenheit (150°F vs. 200°F) (approximately 14°C or 28°C). In the United States, the 25-degree Fahrenheit and 50-degree Fahrenheit thresholds are standard variations of the “moderate” and “severe” categories, so these threshold definitions must be considered as examples and can vary depending on other paving practices with different materials, widths, and depths. For example, on a 150-foot section, the classification of below 25 degrees Fahrenheit (14 degrees Celsius) is best for many U.S. paving practices for minimal or no separation; between 25 and 50 degrees Fahrenheit (14 and 28 degrees Celsius) for moderate separation; and above 50 degrees Fahrenheit (28 degrees Celsius) for severe separation. However, it must be noted that these temperature and distance variations are selected based on studies performed on projects comprising average U.S. paving practices. Optionally or additionally, point-to-point comparisons can be performed for two different sections. According to another application example, all temperature values ​​for a section can be analyzed to determine the lowest and highest temperatures within that section. This allows for comparison of a temperature value in one section with the highest or lowest temperature value within that section.

[0039] According to the application example, different patterns or error indications can be detected. Here, a distinction can be made between five types (Type A to Type E). For example, when the first zone is arranged perpendicular or substantially perpendicular to the direction of travel, a Type A error or pattern indication can be detected. Another indicator of a Type A error or pattern is the vertical arrangement of the first zone and a temperature variation below, for example, a predetermined threshold of about 25 degrees Fahrenheit or 50 degrees Fahrenheit (about 14 degrees Celsius or 28 degrees Celsius). A Type A error or pattern results in minimal to moderate load-end separation, which is considered a rougher location in the paving material and / or a higher air gap. According to the application example, instructions can be output to the paving machine operator. These instructions may include one of the following notes: - Ensure rows overlap when placed; - Ensure the row placement is not at an extreme distance in front of the paver; and - Ensure that the stacking height in the paving machine hopper and / or material transfer vehicle hopper remains consistent and at an acceptable level.

[0040] According to the application example, when the first and second zones are arranged perpendicular to the direction of travel and when at least one cold zone is arranged between the first and second zones, a type B error or pattern can be indicated. A cold zone includes a temperature value that is at least 50 degrees Fahrenheit (at least 28 degrees Celsius) lower than the temperature values ​​of the first and second zones. Another indicator of a type B error or pattern is the combination of the aforementioned arrangement of the first, second, and cold zones with a high temperature variation, for example, above a predetermined threshold of about 50 degrees Fahrenheit (about 28 degrees Celsius). A type B error or pattern indicates severe load end separation. In the case of a type B error or pattern, according to a further application example, the method may include the additional step of outputting an instruction to an operator having the following: - Ensure rows overlap when placed; - Ensure that rows are not placed a distance in front of the paving material before the paving machine receives the paving material, thus preventing extreme cooling; - Ensure that the paving machine hopper and / or material transfer vehicle hopper are not depleted and that the hopper wings are not folded between loads; and - Ensure proper multi-point loading of the truck.

[0041] According to the application example, errors or patterns of type C can be identified and indicated. Type C errors or patterns exist when the first and second zones are arranged laterally / along the direction of travel and when one or more cold zones are arranged in between. Another additional indicator is a temperature variation above, for example, a predetermined threshold of about 50 degrees Fahrenheit (about 28 degrees Celsius) (seen throughout the section). This type C error or pattern leads to incorrect separation and may be caused by prolonged stops and excessive leveling heating at slow paving speeds. In this case, the method can output instructions to the operator including: - Minimize the stopping time; and - Monitor the thermal image of the entire printing plate surface when it stops, and reduce the temperature of the entire printing plate.

[0042] Based on the application example, an error or pattern of type D can be indicated, where the first zone extends laterally and is centered along the direction of travel. An additional indicator is temperature variation below approximately 50 degrees Fahrenheit (approximately 28 degrees Celsius). In this case, the method can output instructions to the operator including the following: - Inspect the material movement on site to determine if further extensions are necessary for consistent flow; - Consider adding mainframe expansion; and - Ensure the recoil pedal is in good working order.

[0043] According to the application example, when the first, second, and third zones divide the section into different zones along the direction of travel (i.e., at least three vertically arranged zones), a type E error or pattern can be indicated. Here, an additional indicator is a temperature change above, for example, a predetermined threshold of approximately 50 degrees Fahrenheit (approximately 28 degrees Celsius). A type E error or pattern results in load-to-load separation. Here, the method can output instructions to the operator: Ensure consistent trucking operations; and Ensure consistent operation of the mixing equipment.

[0044] Regarding the above method, it should be noted that, according to the application example, multiple parts of the area are investigated using this method. Because the analysis is performed sequentially and separately, these parts often overlap, with the overlap caused by the paving machine traveling in the direction of travel.

[0045] Another application example provides an apparatus for performing the above-described method, namely, an apparatus for detecting the quality of paving material distributed along a paving area. This apparatus includes at least an interface for receiving heat distribution and a calculator for performing its analysis.

[0046] According to application examples, the device may additionally include a thermal distribution camera or asphalt temperature scanner for reproducing one or more thermal distributions. According to additional application examples, the device may include a location sensor, such as a GPS sensor for continuously measuring the position of a paving machine and adding location information to the temperature distribution, and for providing recommendations by the temperature measurement system of the present invention. According to another application example, the device includes a mobile device or display for outputting information / instructions. This mobile device or display enables the monitoring of the present invention. According to another application example, the device includes a wireless communication module configured to send real-time warnings via a wireless communication link to the following in the event of severe separation problems and / or no separation problems: - Mobile devices (smartphones and / or smartwatches) of supervisors at the construction site. - Computers, tablets, etc., located in monitoring areas that are either far from or near the construction site; - One or more roller compactor operators following the asphalt paver enable communication with the roller compactor operator regarding issues during the asphalt paving process. The roller compactor operator can then, for example, adjust, modify, or optimize the roller compactor's parameters, settings, etc.; and / or - A remote data server allows, for example, notifications to truck drivers and / or asphalt mixing equipment workers regarding issues with asphalt materials.

[0047] For example, real-time alerts can be sent via a CAN-WLAN gateway module (wireless communication module), which is located on the machine and serves as the interface between the machine's communication bus system (e.g., CAN (Controller Area Network)) and the wireless communication system (e.g., WLAN, Bluetooth).

[0048] In the absence of separation issues, such as when there is no (error) indication in the specified segment or a distance of approximately 150 feet, such a real-time alert can output a positive message or acknowledgment.

[0049] According to an embodiment, the method further includes the step of outputting instructions to paving workers based on a first quality parameter. This serves the purpose of implementing actions or changing parameters of construction machinery based on the quality parameter; additionally or optionally, the method further includes the step of determining a first analysis parameter (again) after outputting the instruction, after implementing the action, or after changing the parameters.

[0050] The advantage of this application example is that it provides contractors with a means to actively influence the quality of paving material distributed along the paving area using a paving machine. Attached Figure Description

[0051] Hereinafter, embodiments of the invention will be discussed with reference to the accompanying drawings, wherein, Figure 1a A schematic representation of a paving machine is shown, here including an asphalt paving machine according to a first application example, which is a device for controlling the quality of the distributed paving material. Figure 1b A schematic representation of a paved area is shown to illustrate the principle of analyzing heat distribution according to a first application example; Figure 2 A schematic representation of a control unit belonging to a device used for quality control is shown; Figure 3 A schematic illustration of different temperature levels indicating heat distribution is shown; Figures 4 to 8 A schematic thermal distribution of a distributed pavement belonging to areas assigned to different pattern types or error types is shown to illustrate the principle of determining different pattern types or error types within the thermal distribution based on an application example. Figure 9 The schematic thermal distribution of the symptoms of distributed pavement separation is shown. Figure 10 A schematic flowchart is shown, illustrating a method for detecting datasets that enable the assessment of the quality of paving materials; Figure 11a A schematic block diagram of a computing unit according to a basic implementation is shown, which can be used to determine a dataset; and Figure 11b It shows the relationship with Figure 11a The computing unit is equivalent to the computing unit, but the computing unit is enhanced according to the enhanced implementation method. Schematic block diagram of the computing unit. Detailed Implementation

[0052] The invention will now be discussed with reference to the accompanying drawings, wherein the same reference numerals are provided for elements having the same or similar functions, such that their descriptions are mutually applicable and interchangeable. Before discussing embodiments of the invention, the background of the self-learning algorithm will be discussed.

[0053] Embodiments of the present invention begin with a method for controlling the quality of paving material distributed along a paving area using a paving machine and a device for detecting the quality of paving material distributed along a paving area using a paving machine (such as a quality control system in the field of road construction machinery, as disclosed in EP 3456880A1, for example, asphalt paving machinery, based on temperature measurement of newly laid paving material such as asphalt or tarpaulin directly behind the machine or tool (platform)). Embodiments provide a learning mode based on artificial intelligence / self-learning algorithms. To parse thermal data in real time in the software of the operating and display unit, thermal data patterns need to be stored in the memory of the operating and display unit for comparison with currently measured temperature distributions. These comparison data can be generated by artificial intelligence / self-learning algorithms, thereby enabling the identification or addition of new thermal data patterns (new thermal distribution layouts describing the root causes of thermal separation). Optionally, the machine operator, paving worker, or paving expert must verify the decisions made by the system.

[0054] exist Figure 1a The diagram schematically illustrates a road finishing machine 10, such as an asphalt paver. The direction of travel of the road finishing machine 10 is indicated by arrow F on the ground 120. To distribute paving material onto the ground 120 and form a road surface 50, the machine 10 includes a flat plate 15 attached to its rear end.

[0055] Furthermore, the machine 10 includes a temperature measuring unit 20 located at its rear end, which may be, for example, a thermal distribution camera or an asphalt temperature scanner. An optional weather station 40 is also arranged in the area of ​​the temperature measuring unit 20, which exemplarily determines the wind speed and ambient temperature in the area of ​​the road trimmer 10. The temperature measuring unit 20 measures the temperature of the surface 110 of the newly paved road surface 50 on the laterally restricted road width B (i.e., laterally to the direction of travel of the road trimmer 10) via its outer edges 111 and 112. Therefore, the measurements are recorded at measuring points 100, schematically shown and preferably, but not necessarily, arranged at equal distances d laterally and / or along the direction of travel of the road trimmer 10.

[0056] Depending on the precise implementation of the measuring unit 20, the measuring point 100 can be arranged to record a two-dimensional temperature distribution or can only be arranged transverse to the direction of travel F, such that a two-dimensional heat distribution is recorded during travel along the direction of travel F and consists of multiple measurements along the direction of travel F.

[0057] Figure 1a The road finishing machine 10 may include an operation and display unit 30 electrically connected to the temperature measurement unit 20, the operation and display unit 30 including at least a CPU for performing analysis. Figure 1aAs shown, the operation and display unit 30 can be installed near the control platform of the paving machine. However, the operation and display unit 30 can also be installed at any other point on the machine, for example, and preferably at the flat plate 15, so that paving workers can easily view the display screen. The operation and display unit 30 is equivalent to a mobile computer and includes at least a microcontroller, one or more memory units (RAM, ROM, flash memory, etc.), and one or more input and output devices, such as a touch screen. Figure 2 As shown, the operation and display unit 30 graphically displays the measured temperature distribution of the surface 110 of the newly paved road surface 50 on the output device (display screen). Figures 4 to 9 An example of this graphical representation is shown and described in more detail later.

[0058] The machine operator or paving worker (not shown) can see the measured temperature distribution of the newly paved road 50 on the display screen of the operation and display unit 30. Figure 2 An example of the front side 201 of the operation and display unit 30 is shown. In the central area is a display screen 202, preferably a touch screen. Multiple input keys 205 are located to the left, right, and below the display screen 202. In the central area of ​​the display screen 202, a measured temperature distribution 204 is graphically displayed. Several symbols 203 are shown above, to the right, and below the temperature distribution 204. Some symbols 203 indicate data or information about the current paving process, such as a paving machine speed of 2 m / min, a wind speed of 1 m / min, and a humidity of 41%.

[0059] The information displayed in unit 30 is highly useful for operators or paving workers, and it must be continuously monitored. To improve reliability, automated control of paving quality can be implemented when rules for interpreting thermal patterns exist. (See reference...) Figure 1b Discuss this method.

[0060] Figure 1b A schematic diagram of paving area 47 is shown, along which paving material 15 has been distributed using a paving machine traveling in the direction of travel F. (See also: Regarding...) Figure 1a The discussed method involves analyzing the surface 110 of the newly paved road 50 using a thermal distribution camera or an asphalt temperature scanner. The device used to determine the thermal distribution captures at least a portion of an area 47, marked by reference numeral 49. In the portion 49 where multiple measuring points 100 are arranged, a corresponding temperature value is obtained for each measuring point.

[0061] Measurement points that are arranged adjacent to each other and have comparable temperatures (i.e., temperature values ​​within a predetermined range, i.e., between 170 degrees Celsius and 190 degrees Celsius) can be grouped into a common area.

[0062] Here, a first zone 51a and a second zone 51b are illustrated exemplarily. The first zone 51a is arranged perpendicular to the direction of travel F, i.e., laterally relative to the road surface 15, while zone 51b is arranged along the direction of travel F. Both zones 51a and 51b are typically surrounded by multiple measuring points with temperature values ​​outside a predetermined range. Alternatively, the two zones may be arranged adjacent to each other, such that only a few measuring points or almost no measuring points outside the predetermined range are arranged between the two zones. Generally, it should be noted that each zone 51a and 51b is formed by the temperature deviation between a local point and the surrounding environment.

[0063] The orientation of zones 51a and 51b along their arrangement provides a good indication of the cause of temperature changes. Another indicator of different causes is the temperature deviation itself. Several methods can be performed here. For example, the temperature deviation between zone (e.g., 51a) and its surrounding environment can be analyzed. According to another method, the temperature deviation between the two zones 51a and 51b can be detected. Optionally or additionally, the average temperature within a zone (e.g., within zone 51a) can be compared with the lowest or highest temperature value of section 49.

[0064] Regarding each zone 51a and 51b, it should be noted that the temperature deviation within zones 51a and 51b is typically 30% or 20%, or at least 10% according to a preferred embodiment, wherein the percentage refers to the mean of the average temperature within zones 51a and 51b.

[0065] The aforementioned automated method for controlling paving quality includes the steps of determining corresponding zones 51a and / or 51b and analyzing the orientation of the first zone. Based on the orientation and, according to a further example, in conjunction with temperature deviation, the assignment of instructions (specifically, error indications, etc.) can be performed for the corresponding portion 49.

[0066] Starting with this assignment across the corresponding pattern type or error type (Type A to Type E), instructions can be output to the operator to help them improve the recent situation. The output instructions can be executed using the display unit 30 or a mobile device.

[0067] Below, we will discuss... Figures 4 to 9 Different temperature distributions are discussed, where each temperature distribution can be assigned to a corresponding pattern indicator or error indicator. Figures 4 to 9 The figures show several different measured temperature distributions of the new road surface 50 and the newly paved road surface 50 on the road width B. The different shaded lines in the figures represent the different temperatures measured on the surface of the new road surface 50. Figure 3 The shaded temperature gradients indicate different temperatures. Other temperature gradients (e.g., color gradients, such as rainbow temperature color gradients or iron temperature color gradients) are known, for example, see [link to relevant documentation]. Figure 2 Reference number 206.

[0068] exist Figure 3 And still Figures 4 to 9 In the diagram, hot temperatures are marked with a closer shading line, and cold temperatures are marked with a lighter shading line. Hot temperatures refer to temperatures of approximately 356 degrees Fahrenheit (approximately 180 degrees Celsius), and cold temperatures refer to temperatures of approximately 203 degrees Fahrenheit (approximately 95 degrees Celsius).

[0069] Distance B' and direction F' (only when Figure 4 The above is shown but applies to all. Figures 4 to 9 The road width B corresponds to the newly paved surface 50 and the travel direction F of the road repair machine 10 (see...). Figure 1a ). Figures 4 to 9 The various thermal separation problems that may occur during the paving process are illustrated in detail. The measured temperature distribution, thermal separation problems, their root causes, and possible solutions are described in more detail below.

[0070] Some sections of the following description relate to so-called stockpiled paving. In this type of paving machine, the hot paving material is not dumped directly into the paving machine hopper. Instead, the hot paving material is placed directly on the road in front of the paving machine as a stockpile. This stockpiled paving machine is equipped with a loading conveyor that picks up the paving material and loads it into the hopper. The paving material is then moved by a second conveyor to a position in front of a transverse auger conveyor and a slab leveling plate, where it is received directly from a dump truck in the same general manner as paving machines with hoppers.

[0071] Figure 4 The typical temperature distribution for a type A pattern indication or error indication is shown. Here, the thermal variation level shows the minimum to moderate load end separation, which is generally considered a rougher location in the asphalt material and will have high air voids, making the asphalt more susceptible to the effects of oxidation, moisture penetration, or premature damage leading to cracking and potholes.

[0072] Variation in temperature range (e.g., Figure 4 Rows 401 to 404) transverse to the travel direction F and F' of the road finishing machine 10 have different temperature deviations (levels of thermal variation). As can be seen in this example, the overall temperature deviation is limited to about 50 degrees Fahrenheit (about 28 degrees Celsius).

[0073] To improve the situation shown, there are three possible solutions. If it is a stacked paving project, ensure that the rows overlap during placement. If it is a stacked paving project, ensure that the rows are not placed at extreme distances in front of the paver. Ensure that the stack height in the paver hopper and / or the material transfer vehicle (material feeder) hopper remains consistent and at an acceptable level.

[0074] Figure 5This illustrates the level of thermal change with severe end-load thermal separation, which affects the long-term durability of asphalt pavement concrete structures. The pattern or error indication is Type B.

[0075] The thermal pattern shows various temperature segments with high temperature deviations (levels of thermal change) transverse to the travel directions F, F' of the road finishing machine 10 (see rows 501 to 509). Small segments of cold temperature are between some rows (see 510 and 511) and also near the outer edge (see 512 and 513).

[0076] Possible solutions are: If it is stacked paving, ensure that rows overlap during placement. If it is stacked paving, ensure that rows are not placed a distance in front of the paver before the paver receives the material, which could cause extreme cooling. Ensure that the paver hopper and / or material transfer vehicle (material feeder) hoppers are not depleted and that the hopper wings are not folded between loads. If the material is finally dumped into the paver hopper, ensure proper multi-point loading of the truck. Environmental conditions may necessitate the use of a material transfer vehicle (material feeder) in operations involving remixing and separating materials.

[0077] about Figure 6 We will discuss patterns or errors of type C. Figure 6 The thermal images show spurious separation caused by prolonged stops and excessive leveling heating at low paving speeds. Figure 6 Two distinct regions, 601 and 602, with various temperature ranges are shown. In region 601, several temperature ranges with high temperature deviations (levels of thermal change) exist. Ranges 603 and 604 are in the intermediate temperature range of approximately 140°C to 150°C. Ranges 605 and 606 are in the high temperature range of approximately 170°C to 180°C and extend transversely to the travel directions F and F' of the road repair machine 10. Ranges 607 and 608 are points in the low temperature range of approximately 95°C to 105°C. In region 602, two temperature ranges, 609 and 610, are mainly present in the high temperature range adjacent to the travel directions F and F' of the road repair machine 10.

[0078] A possible solution is to minimize the downtime. Monitor the thermal image of the entire printed surface at the time of stop, and reduce the temperature of the entire plate if possible.

[0079] about Figure 7 We will discuss the pattern or error of type D. Figure 7 The temperature distribution with some thermal stripe areas is shown. Figure 7The images show minimal variations caused by stripes, but moderate to severe thermal stripes can cause continuous separation across the entire pad. Four regions 701 to 704 are primarily shown within the intermediate temperature range, with region 705 showing a linear region adjacent to the travel directions F, F' of the road trimmer 10, which is also within the intermediate temperature range. Linear region 705 begins in 702 and ends in 703. Furthermore, the region defined by segment 706 shows a centerline region within a very high temperature range (up to 180 degrees Celsius).

[0080] Possible solutions include: checking material movement at the sides to determine if screw conveyor extension is necessary for consistent flow. If material is moving forward at the end gate, adding a main frame extension may also be considered. Check the centerline stripes to ensure the backflush pedal is in good condition. If the backflush pedal is in good condition, increase the flow gate and / or screw conveyor height.

[0081] Figure 8 The region tilt is described as pattern or error type E. Figure 8 A thermal image of a road surface with load-to-load separation is shown. Figure 8 Three distinct zones 801, 802, and 803 with various temperature bands are shown. Zones 801 and 802 show several main temperature bands 804 to 807 in the intermediate and high temperature ranges and transverse to the travel directions F, F' of the road paving machine 10. A small boundary indicating the paving machine's stop exists between zones 802 and 803. Zone 803 shows a level of no thermal variation comparable to the other two zones 801 and 802. Possible solutions include: ensuring consistent truck transport operations; and ensuring consistent operation of mixed equipment.

[0082] For the sake of completeness only, Figure 9 The diagram illustrates the temperature distribution from minimal separation to no separation. It can be seen that the level of thermal change is consistently below approximately 25 degrees Fahrenheit (approximately 14 degrees Celsius) or lower.

[0083] As discussed above, temperature pattern analysis can be automatically performed, for example, via the operation and display unit 30 (see Figure 1) or the CPU of the temperature measurement system. Based on this analysis, the system can output or display instructions to operators and workers using mobile devices. These instructions can include real-time updates for each load. Real-time alerts can include further information, such as potential causes of separation analyzed and / or suggested solutions for paving workers. In addition to the alerts and information provided, truck drivers and / or asphalt mixing plant workers can adjust, modify, or optimize parameters, settings, etc., of the asphalt production and transportation process. These can, for example, change the temperature of the asphalt mixing process or minimize the number of trucks en route from the asphalt mixing plant to the construction site (to minimize the waiting time of asphalt trucks in front of the asphalt pavers).

[0084] According to another example, network technology can be used to execute the output of instructions so that if the separation problem is caused by faulty asphalt mixture, instructions can be sent to the asphalt mixing equipment.

[0085] Although in the above example the temperature measurement unit has been characterized as a heat distribution camera or asphalt temperature scanner pointing to the newly laid asphalt pad behind the asphalt paver, it should be noted that other measurement principles (such as using multiple sensors) are also possible if the measurement principle enables the capture of heat distribution.

[0086] According to another implementation, a so-called learning mode can be used. The purpose of this learning mode (also known as a teaching mode) is to add new heat data patterns (describe new heat distributions of thermally separated resources) to an already available dataset or to generate new datasets. According to a preferred implementation, this learning mode is performed automatically or semi-automatically, for example, using artificial intelligence or typically self-learning algorithms.

[0087] Below, for reference Figure 10 The corresponding method 1000 will be discussed.

[0088] Figure 10 A method 1000 for detecting a dataset is shown, the dataset including at least a first quality parameter (e.g., describing the type of error) and a first analytical parameter (e.g., a specific thermal pattern or a parameter that generally enables conclusions about the quality of the road surface, wherein the analytical parameter is, for example, determinable within an image / thermal distribution).

[0089] The first quality parameter and the first analysis parameter together describe the identifiable condition, for example, including typical errors and typical parameters used to identify said errors. The first quality parameter, or typically one or more quality parameters, can be information about the error / error type or can also be a measurement value, such as the uniformity of the pavement. The analysis parameter describes the parameters used to characterize a first zone (e.g., a point) in which errors can be detected. The zone is defined as a set of measurement points arranged adjacent to each other and having all temperature values ​​within a predetermined range (e.g., at least 10% higher than the temperature value of a measurement point partially surrounding the first zone). When viewed in a localized manner, the first zone corresponds to a first sub-section of a portion of the paved area. The first sub-section is the area where the first quality parameter is determined. The two parameters (the first quality parameter and the first analysis parameter) together form a dataset, based on which the quality of the paving material can be evaluated using the system described above. The determination of the dataset (semi-automatic / automatic) can be accomplished using method 1000, which includes two basic steps 1100 and 1200.

[0090] In step 1100, a first thermal distribution is received for a portion of a paved area containing paving material. This portion includes a first sub-section. It is assumed that a locally constrained quality condition exists within the first sub-section, for example, an error exists. Temperature values ​​of points in the first sub-section are included in the first thermal distribution, wherein a first zone of the measurement points is assigned to the first sub-section. In other words, the first thermal distribution includes multiple temperature values ​​assigned to corresponding measurement points of this portion, wherein the selection of temperature values ​​refers to measurement points in the first zone and belonging to the first sub-section. Of course, in addition to the first sub-section (the portion of interest / to be analyzed), the entire portion may include other / second sub-sections that can be assigned to other / second zones within the thermal distribution.

[0091] The next fundamental step is to analyze the first heat distribution. This step is in Figure 10 The reference numeral 1200 is used to indicate this step. This analytical step 1200 includes three sub-steps 1210, 1220, and 1230.

[0092] In step 1210, a first region is determined, consisting of measurement points that are adjacent to each other and have a temperature range within a predetermined range. This first region is at least partially surrounded by measurement points with temperatures outside the predetermined range, for example, forming a second region or a continuous area. For example, the first region can be interpreted as points with very high temperature values, i.e., so-called hot spots across the entire temperature distribution.

[0093] In the next step 1220, a first characteristic analysis parameter for the first region is determined. For example, the average temperature of the temperature values ​​within the first region or the relative temperature of the temperature values ​​within the first region can be determined as the first characteristic analysis parameter when compared with temperature values ​​at measurement points belonging to the vicinity of the first region. Alternatively or additionally, the geometry of the first region (e.g., orientation relative to the direction of travel of the first region or the size or shape of the first region) can be determined as a characteristic analysis parameter. One or more of these analysis parameters are used to enable the identification of regions where comparable identifiable conditions / comparable errors are assumed to occur. Preferably, the first region is described in detail using more than one or all analysis parameters.

[0094] For the sub-section corresponding to the first zone within the first thermal distribution, a quality parameter, such as uniformity or error type, is determined in step 1220. Depending on the implementation, this quality parameter can be determined manually (i.e., by an operator). Possible variations include manual measurement, such as separation uniformity, or visual inspection. The result of step 1220 is the assignment of a corresponding first analytical parameter or a first set of corresponding analytical parameters to the corresponding quality parameter.

[0095] In step 1230, the combination of analysis parameters and quality parameters is stored, for example, locally or on a server.

[0096] According to the implementation, it is advantageous to repeat these steps 1100 and 1200 for multiple comparable cases. For example, if the same quality parameter, such as the same error type, is found at different sub-sections (see step 1230), the self-running algorithm can discover similarities within the analysis parameters in order to train itself to determine the relevant error type. For example, if it is determined that corresponding areas belonging to the same error type have the same orientation, the algorithm can be trained in such a way that the orientation indicates the corresponding error type. Alternatively, temperature deviations between temperature values ​​within a point or temperature deviations between the average temperatures of points compared to the average temperature outside the point can be considered. For example, when the temperature deviation of a point from the surrounding environment is greater than 10 degrees and when the orientation has an angle (e.g., 90°) relative to the direction of travel, the algorithm can discover that a corresponding error belonging to the corresponding error type typically occurs. If these two analysis parameters can be determined whenever a corresponding error is found, the correlation between the two analysis parameters among multiple analysis parameters can be deduced by using this method, and which corresponding threshold indicates the presence of a certain condition. Since there are multiple possible analysis parameters, the correlation between a single parameter or a combination of single parameters with respect to the error type can be trained using training data. The parameters can be one or more in a group: ● The orientation of the first zone relative to the direction of travel; ●The average temperature within the first zone; ● The relative temperature of the temperature value within the first zone when compared with the temperature values ​​of measurement points belonging to the surrounding area of ​​the first zone; ●The size of the first zone; ●Temperature deviation within Zone 1; ●The shape of the pattern in the first area; ●There exists a second region with measurement points corresponding to the second sub-part of this section; ●Another area of ​​measurement points corresponding to another sub-section of this section; ● The distance between Zone 1 and Zone 2, or between Zone 1 and another zone; and ● The relative positions from Zone 1 to Zone 2 or from Zone 1 to another zone.

[0097] It should be noted that different analytical parameters can be relevant for different types of errors.

[0098] In summary, steps 1100 and 1200 are preferably repeated for different cases of mapping comparable error types to analytical parameters in order to identify which analytical parameters and which value of the analytical parameters indicates the corresponding case / error. Furthermore, steps 1100 and 1200 are preferably repeated for different cases of mapping different error types to analytical parameters in order to identify which analytical parameters indicate different cases / errors. These error types, or generally quality parameters, together with one or more analytical parameters, form so-called training data, enabling the training of the algorithm.

[0099] According to a further implementation, the dataset for the corresponding situation can be stored as a solution, such as the paving machine parameters to be changed in order to avoid the determined error.

[0100] Starting with this central process of determining the analytical parameters, conclusions about the quality of the road surface (driving direction, point orientation, temperature difference between different zones) can be drawn. This process can be enhanced as follows. Generally, the above method 1000 enables the extraction of analytical parameters from temperature distribution or another image (e.g., a color image of the road surface). These are uncommon or undesirable parameters. During the diagnostic phase, quality parameters and optionally potential measurements can be determined. After this measurement is performed, the road surface image changes, for example, becoming more uniform. Therefore, the corresponding analytical parameters will fall below the corresponding thresholds, and the road surface quality will be within specifications. This process can be described as follows: - Determine or use the analysis parameters; - Analyze images, for example, thermal records about analytical parameters; - Perform diagnostics to identify road surface quality issues, i.e., determine quality parameters; - Provide information about potential measurements to resolve quality issues; - Conduct measurements; - As a result of the implementation, the corresponding analysis parameters are changed; - Receive new images and analyze the parameters again.

[0101] Determining or validating analytical parameters is important for analyses performed using artificial intelligence.

[0102] The background is independent of the analysis parameters, and an AI image recognition algorithm trained accordingly can be used to analyze images and extract diagnoses. In this case, the training dataset only includes images that enable the performance of diagnoses and corresponding quality parameters. This process is called "labeling" and can be human-supported, for example, by selecting the analysis parameters on which the labeling should be performed. In the absence of human support, the differences between different quality cases can be misleading. For example, an AI algorithm trained to distinguish between images of huskies and wolves could be based on incorrect parameters, such as background, because huskies are often recorded in winter landscapes. When such incorrect parameters are automatically determined by the AI ​​algorithm, most decisions can be correct, but are placed on completely wrong parameters because the algorithm cannot distinguish between huskies and wolves, but rather distinguishes animals in winter landscapes or animals in another landscape. Therefore, according to the implementation method, the analysis parameters are pre-selected.

[0103] Regarding the measurements / instructions to be output to paving workers, it should be noted that, according to the implementation, the validity of these measurements can be demonstrated. For example, the same quality parameters of the corresponding images taken after the measurement can be determined to demonstrate the success of the action taken. According to the implementation, information about the corresponding analysis parameters can be output to, for example, a central unit that performs algorithm training to evaluate the proposed measurements. According to another implementation, parameters of changes in the construction machinery / road surface can be monitored and fed back to the training algorithm along with the analysis parameters, and optionally along with the quality parameters, to monitor which parameters lead to which results under what circumstances. A system implemented in this way can continuously learn to identify new problem points and continuously improve the effectiveness of selected solutions (e.g., changing machine parameters).

[0104] Method 1000 can preferably be accomplished by forming a neural circuit of artificial intelligence. Here, multiple analytical parameters determined for each case (point) are used as input parameters of the neural circuit, wherein nodes are determined based on the correlation of the corresponding analytical parameters with respect to comparable quality parameters. Figure 11a and Figure 11b This illustrates such a black box as an artificial intelligence-based computing unit.

[0105] Figure 11aA computing unit 1400 is shown that receives at least a first thermal distribution IR from an interface 1410 connected to an infrared camera 1420 (a general temperature sensor). The temperature distribution may be an infrared image IR of a corresponding portion of a road surface comprising at least a first sub-section. This first sub-section is analyzed in parallel with a temperature analysis, for example, performed by an operator. Based on this analysis, a quality parameter QP is generated and forwarded to the computing unit 1400. These two parameters, IR and QP, are input parameters. These input parameters are IR1, IR2, IR3, IR4, IR5, IR6, IR7, IR8, IR9, IR1 ... n and QP1, QP2, QP3 and QP n Preferably, it is accepted for various situations, such as multiple sub-sections or sections. These sections can be determined using the same paving area or different paving areas using the same or different paving machines.

[0106] Based on at least one pair of parameters IR1 / OQ1, IR2 / OQ2, or IR3 / OQ3, corresponding datasets are generated that are assigned to each other. Assuming QP1 and QP13 describe comparable quality parameters, such as the same error type, the similarity between analytical parameters can be determined, i.e., the similarity between IR1 and IR3. Each pair of IR1 and QP1, and IR3 and QP3, forms a corresponding dataset, e.g., dataset case 1 and dataset case 1'. Both datasets can be used to describe the corresponding error type. By having multiple such datasets, all analytical parameters and relevant analytical parameters within the corresponding threshold / threshold range (greater than 120 degrees or in the range of 115 to 130 degrees) can be determined. Multiple datasets "sit.1" improve the efficiency and accuracy of determining the corresponding case. Of course, depending on the implementation, different cases can be determined, e.g., belonging to different quality parameters. Here, datasets IR2 and QP2 generate datasets describing different cases, here case 2 (dataset "sit.2").

[0107] Note that datasets sit.2 and sit.1' are marked with a shaded line because they are analyzed based on the basic implementation of multiple ER pair analysis. n and QP n Optional only.

[0108] Figure 11b Another configuration of computing unit 1400 is shown. This computing unit receives the same input parameters IR and OP to determine their corresponding datasets. However, according to Figure 11bThe computing unit 1400 in this implementation further enables it to receive decision parameters as part of the learning data. These decision parameters can be, for example, parameters determined using different sensors. For instance, the decision parameters may depend on the operating parameters of the paving machine or the configuration of the paving machine. For example, the width of the screen or the temperature of the paving material may have an impact. These decision parameters can be used as input parameters or can be used to adapt nodes, such as the number of nodes to be combined or analysis parameters.

[0109] According to the implementation, the determination algorithm determined using training data has multiple decision layers. For example, in the first decision layer, it can be determined whether the detection area has an orientation. In the next decision, it can be determined whether the orientation is perpendicular or parallel to the direction of travel. Within the next decision layer, it can be determined whether the area is a hot or cold area. By using these decisions, the situation can be clearly assigned to quality parameters. However, other analysis parameters or another order may have the same result. The self-learning algorithm makes it possible to find out which parameters and which order lead to high determination efficiency and accuracy. The background is that the order of the corresponding decisions can have an effect; for example, the error resulting in a separation point parallel to the direction of travel may have a temperature value with a low or medium temperature level. The temperature along the direction of travel from one end to the other varies due to the different cooling durations at different locations within the point along the direction of travel. Therefore, the determination of longitudinal points along the direction of travel can make some analyses of absolute temperature values, for example, outdated. Therefore, it may be beneficial to determine the orientation first (i.e., one of the first decision layers). By using multiple training data, cross-references between the corresponding analysis parameters can be found. Preferably, this is done by artificial intelligence methods that enable the use of big data (large amounts of training data).

[0110] Although some aspects have been described in the context of the device, it is clear that these aspects also represent a description of the corresponding method, wherein a block or device corresponds to a method step or feature of the method step. Similarly, aspects described in the context of method steps also represent a description of a corresponding block or item or feature of the corresponding device. Some or all of the method steps can be performed by (or using) hardware devices such as microprocessors, programmable computers, or electronic circuits. In some implementations, some or one of the most important method steps can be performed by such a device.

[0111] Depending on certain implementation requirements, embodiments of the present invention can be implemented in hardware or software. This implementation can be performed using a digital storage medium (e.g., floppy disk, DVD, Blu-ray, CD, ROM, PROM, EPROM, EEPROM, or flash memory) having electronically readable control signals stored thereon that cooperate (or are capable of cooperating with) a programmable computer system to cause the corresponding method to be executed. Therefore, the digital storage medium can be computer-readable.

[0112] Some embodiments of the invention include a data carrier having an electronically readable control signal that is capable of cooperating with a programmable computer system to enable the execution of one of the methods described herein.

[0113] Typically, embodiments of the present invention can be implemented as a computer program product having program code that, when run on a computer, is operable to perform one of these methods. The program code may, for example, be stored on a machine-readable medium.

[0114] Other embodiments include a computer program stored on a machine-readable medium for performing one of the methods described herein.

[0115] In other words, the implementation of the method of the present invention is therefore a computer program having program code that, when run on a computer, performs one of the methods described herein.

[0116] Therefore, a further embodiment of the method of the present invention is a data carrier (or digital storage medium, or computer-readable medium) comprising a computer program recorded thereon for performing one of the methods described herein. The data carrier, digital storage medium, or recording medium is typically tangible and / or non-transitional.

[0117] Therefore, a further embodiment of the method of the present invention represents a data stream or signal sequence for executing a computer program that performs one of the methods described herein. The data stream or signal sequence may, for example, be configured to be transmitted via a data communication connection (e.g., via the Internet).

[0118] Further embodiments include a processing means, such as a computer or programmable logic device, configured or adapted to perform one of the methods described herein.

[0119] A further embodiment includes a computer on which a computer program for executing one of the methods described herein is installed.

[0120] A further embodiment of the invention includes a device or system configured to transmit (e.g., electronically or optically) a computer program for performing one of the methods described herein to a receiver. The receiver may be, for example, a computer, a mobile device, a storage device, etc. The device or system may, for example, include a file server for transmitting the computer program to the receiver.

[0121] In some embodiments, a programmable logic device (e.g., a field-programmable gate array) may be used to perform some or all of the functions described herein. In some embodiments, the field-programmable gate array may cooperate with a microprocessor to perform one of the methods described herein. Generally, these methods are preferably performed by any hardware device.

[0122] The above embodiments are merely illustrative of the principles of the invention. It should be understood that modifications and variations of the arrangements and details described herein will be readily apparent to those skilled in the art. Therefore, its purpose is limited only by the scope of the following claims, and not by the specific details presented through the description and explanation of the embodiments herein.

Claims

1. A method for detecting the quality of paving material distributed along a paving area using a paving machine, comprising the following steps: A first thermal distribution is received on a portion of the paving area where the paving material is distributed, the first thermal distribution including a plurality of temperature values ​​assigned to corresponding measurement points; wherein, the portion includes a first sub-portion; Analyzing the first heat distribution to detect separation points of the paving material within the portion, thereby enabling the determination of the quality of the paving material, wherein the analysis includes: - Determine a first region of the measuring points arranged adjacent to each other and having temperature values ​​within a predetermined range, wherein the first region corresponds to the first sub-part, wherein the first region is at least partially surrounded by measuring points having temperature values ​​outside the predetermined range, and wherein the step of determining the first region of the measuring points includes a pattern determination step; - Determine the first analytical parameters for the first region; and - Determine a first quality parameter for the first sub-part to assign the first quality parameter to the first analysis parameter, wherein the first analysis parameter enables conclusions about the quality of the road surface to be obtained; The analysis step is based on learning data that includes at least learning parameters and at least input data, wherein the input data includes the first analysis parameter or pattern as the first analysis parameter, and wherein the learning parameter includes the first quality parameter or the error type of the paving material at the first sub-section as the first quality parameter. The method includes a step of selecting an analysis parameter or a segment of one or more possible analysis parameters as a sub-step for determining the first analysis parameter. The analysis parameter is selected from or includes at least one parameter from one or more parameters in the group, wherein the group includes: The orientation of the first region relative to the direction of travel; The average temperature of the temperature values ​​within the first zone; The relative temperature of the temperature value within the first zone when compared with the temperature value of the measurement points belonging to the surrounding area of ​​the first zone; The size of the first region; Temperature deviation within the first zone; The shape of the pattern in the first region; There exists a second region containing measurement points corresponding to the second sub-part of the aforementioned portion; Another area of ​​measurement points corresponding to another sub-part of the aforementioned portion; The distance from the first zone to the second zone or from the first zone to another zone; and The relative positions of the first zone to the second zone or the first zone to another zone; or A combination of at least two or more group elements.

2. The method according to claim 1, wherein, The method includes the step of storing the first analytical parameter together with the first quality parameter; and / or wherein the method includes the step of sending the first analytical parameter together with the first quality parameter to store the first analytical parameter and the first quality parameter on a server.

3. The method according to claim 1, wherein, The analysis steps include self-learning algorithms and / or artificial intelligence-based methods.

4. The method according to claim 1, wherein, The method includes a step of selecting the analysis parameter or a segment of one or more possible analysis parameters prior to performing the analysis.

5. The method according to claim 1, wherein, The method further includes the step of receiving parameters of the paving machine and / or the configuration of the paving machine.

6. The method according to claim 1, wherein, The first quality parameter is a parameter describing the type of error in the paving material at the first sub-section; and / or The step of determining the first quality parameter includes a sub-step of receiving instructions or information from the operator of the paving machine.

7. The method according to claim 1, wherein, The analysis steps are based on learning data that includes at least decision parameters defining the type or number of decision nodes, wherein the decision parameters depend on the parameters of the paving machine or the configuration of the paving machine.

8. The method according to claim 1, wherein, The method further includes the step of receiving at least one instruction assigned to the quality parameter or error type of the paving material at the first sub-section.

9. The method according to claim 1, wherein, The receiving and analysis steps are repeated for the same paving area or another paving area, and / or the receiving and analysis steps are repeated for another paving machine.

10. The method according to claim 9, wherein, Repetition enables the identification of multiple comparable datasets for comparable scenarios and / or repetition enables the identification of multiple different datasets for different scenarios.

11. The method according to claim 1, wherein, Multiple measurement points within the thermal distribution are arranged according to a regular grid.

12. The method according to claim 1, wherein, The method may be performed for multiple temperature distributions, or for multiple temperature distributions that overlap with each other.

13. The method according to claim 1, wherein, The method further includes the steps of outputting instructions to the paving machine operator based on the first quality parameter and / or performing actions or changing the parameters of the construction machinery based on the first quality parameter; and / or The method further includes the step of determining the first analysis parameter after outputting the instruction, after performing the action, or after changing the parameter.

14. The method according to claim 1, wherein, The first quality parameter characterizes the quality of the road surface.

15. A computer-readable digital storage medium storing a computer program having program code for performing the method according to claim 1.

16. An apparatus for detecting the quality of paving material distributed along a paving area, the apparatus comprising: An interface for receiving a first thermal distribution of a portion of the paving area on which the paving material is distributed, the first thermal distribution including a plurality of temperature values ​​assigned to corresponding measurement points; wherein, the portion includes a first sub-portion; and A computing unit is configured to analyze the first heat distribution to detect separation points of the paving material within the portion, thereby enabling the determination of the quality of the paving material, wherein the analysis includes: - Determine a first region of the measuring points arranged adjacent to each other and having temperature values ​​within a predetermined range, wherein the first region corresponds to the first sub-part, wherein the first region is at least partially surrounded by measuring points having temperature values ​​outside the predetermined range, and wherein the step of determining the first region of the measuring points includes a pattern determination step; - Determine the first analytical parameters for the first region; and - Determine a first quality parameter for the first sub-part to assign the first quality parameter to the first analysis parameter, wherein the first analysis parameter enables conclusions about the quality of the road surface to be obtained; The analysis is based on learning data that includes at least learning parameters and at least input data, wherein the input data includes the first analysis parameter or pattern as the first analysis parameter, and wherein the learning parameter includes the first quality parameter or the error type of the paving material at the first sub-part as the first quality parameter. The analysis includes selecting a segment of an analysis parameter or one or more possible analysis parameters as part of determining the first analysis parameter; The analysis parameter is selected from or includes at least one parameter from one or more parameters in the group, wherein the group includes: The orientation of the first region relative to the direction of travel; The average temperature of the temperature values ​​within the first zone; The relative temperature of the temperature value within the first zone when compared with the temperature value of the measurement points belonging to the surrounding area of ​​the first zone; The size of the first region; Temperature deviation within the first zone; The shape of the pattern in the first region; There exists a second region containing measurement points corresponding to the second sub-part of the aforementioned portion; Another area of ​​measurement points corresponding to another sub-part of the aforementioned portion; The distance from the first zone to the second zone or from the first zone to another zone; and The relative positions of the first zone to the second zone or the first zone to another zone; or A combination of at least two or more group elements.

17. The device according to claim 16, wherein, The computing unit is based on artificial intelligence and / or configured to execute self-learning algorithms.

18. The device according to claim 16, wherein, The device includes a thermal distribution camera or asphalt temperature scanner configured to record the thermal distribution of the portion when guided to the paved area.

19. The device according to claim 16, wherein, The device includes a mobile device and / or a display configured to output information and / or instructions; and / or The device includes a mobile unit or control unit that receives information about quality parameters from the operator.

20. The device according to claim 16, wherein, The device includes a wireless communication module configured to exchange with a server a set including the first analysis parameters and the first quality parameters.

21. A paving machine for distributing paving material, comprising the device according to claim 16.

Images