Acoustic emission detection system multi-task parallel processing method, system, equipment and medium

Abstract

The invention relates to the technical field of acoustic emission system data processing, in particular to an acoustic emission detection system multi-task parallel processing method, system and device and a medium, and the acoustic emission detection system multi-task parallel processing method comprises the steps of obtaining data output by a multi-point acoustic emission sensor in real time, and integrating to form a multi-channel acoustic emission data queue; generating a data processing request based on the multi-channel acoustic emission data queue; in response to the data processing request, preprocessing a preset data processing architecture to obtain an initialized data processing architecture meeting the data processing request; acquiring to-be-processed acoustic emission data based on the multi-channel acoustic emission data queue, and acquiring acoustic emission signal characteristics according to the to-be-processed acoustic emission data; and mapping the to-be-processed acoustic emission data to a corresponding thread pool based on acoustic emission signal features to carry out data processing architecture adaptation, and selecting a proper data processing framework to process the to-be-processed acoustic emission data. The method has the effect of improving the overall detection efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of acoustic emission system data processing, and in particular to a multi-task parallel processing method, system, equipment and medium for an acoustic emission detection system. Background Art

[0002] As an important non-destructive testing method, acoustic emission testing technology is widely used in industrial production, environmental testing and other fields. By capturing and analyzing the sound wave signals generated inside the material, it can effectively detect the internal defects and damage of the material. With the development of technology, acoustic emission testing technology has made significant progress in improving detection accuracy and reliability, greatly improving the level of production and safety management. However, although acoustic emission testing technology has shown many advantages in practical applications, it still faces challenges in detection efficiency, especially when it is necessary to monitor multiple target points at the same time, the traditional single-channel acquisition method is particularly insufficient.

[0003] At present, multi-point synchronous acquisition is achieved by increasing the number of sensors and data acquisition channels, but this is often accompanied by complex data management and processing problems. Another common practice is to introduce high-performance processing equipment, such as high-speed processors or dedicated integrated circuits, to speed up data processing. In addition, some systems try to improve data processing efficiency by optimizing signal processing algorithms. Although these methods can improve detection efficiency to a certain extent, they still have limitations in multi-task parallel processing.

[0004] However, although the existing combination of multi-point synchronous acquisition and high-performance processing equipment can partially solve the problem of detection efficiency, it still has obvious defects in practical applications. First, the surge in data volume caused by multi-point synchronous acquisition has brought tremendous pressure on data management and real-time processing. Secondly, when faced with a large amount of parallel data, the processing speed and stability of existing processing equipment are difficult to meet actual needs. Therefore, there is room for improvement. Summary of the invention

[0005] In order to monitor multiple target points simultaneously and thus improve the overall detection efficiency, the present application provides a multi-task parallel processing method, system, device and medium for an acoustic emission detection system.

[0006] The above-mentioned invention objective of the present application is achieved through the following technical solutions: A multi-task parallel processing method for an acoustic emission detection system, the multi-task parallel processing method for an acoustic emission detection system comprising the steps of: Acquire data output by multi-point acoustic emission sensors in real time, integrate them to form a multi-channel acoustic emission data queue, and generate a data processing request based on the multi-channel acoustic emission data queue; In response to the data processing request, preprocessing the preset data processing architecture to obtain an initialized data processing architecture that meets the data processing request; Acquiring to-be-processed acoustic emission data based on the multi-channel acoustic emission data queue, and acquiring acoustic emission signal features according to the to-be-processed acoustic emission data; Based on the acoustic emission signal characteristics, the acoustic emission data to be processed are mapped to a corresponding thread pool for data processing architecture adaptation, and a suitable data processing framework is selected to process the acoustic emission data to be processed.

[0007] By adopting the above technical solution, in the process of using acoustic emission detection technology to detect materials, multiple independent acoustic emission sensors are used to obtain data output by multi-point acoustic emission sensors in real time, and the data output by the multi-point acoustic emission sensors are integrated to form a multi-channel acoustic emission data queue. The multi-channel acoustic emission data queue refers to data output by multiple independent acoustic emission sensors. A data processing request is generated according to the multi-channel acoustic emission data queue. The data processing request refers to a task request for data processing of the acoustic emission data in the multi-channel acoustic emission data queue. In response to the data processing request, a data processing architecture preset in the system is preprocessed, wherein the data processing architecture includes multiple processing units, such as DSP, FPGA, etc. The data processing architecture is preprocessed so that the data processing architecture meets the current The processing requirements of acoustic emission data are improved, the adaptability of the data processing architecture and the current queue of acoustic emission data to be processed is improved, the detection efficiency is improved, the acoustic emission data to be processed is obtained according to the multi-channel acoustic emission data queue, the corresponding acoustic emission signal characteristics are obtained according to the acoustic emission data, and the acoustic emission signal characteristics are used to map the acoustic emission data to be processed in the multi-channel acoustic emission data queue to the thread pool for data processing architecture adaptation, and the acoustic emission data to be processed are processed through the data processing architecture with the highest degree of adaptation, so that each acoustic emission data to be processed is decoupled through the corresponding thread pool and distributed to the processing unit in the corresponding data processing architecture for processing, so as to realize parallel processing of data in the multi-channel acoustic emission data queue, improve data processing efficiency and orderliness, and thus improve the efficiency of the entire acoustic emission detection process.

[0008] In a preferred example, the present application may be further configured as follows: before acquiring the data output by the multi-point acoustic emission sensor in real time, the multi-task parallel processing method of the acoustic emission detection system further includes: Acquire detection environment information in real time, and acquire environmental characteristic data based on the detection environment information; The environmental characteristic data is input into a preset parameter correction model to obtain a parameter correction value, and the parameter correction value is input into an acoustic emission sensor to set the working parameters of the acoustic emission sensor.

[0009] By adopting the above technical scheme, in the process of acoustic emission testing of the test material, the test environment information is obtained in real time. The test environment information refers to the specific situation of the current test environment. The test environment information is analyzed to obtain environmental characteristic data. The environmental characteristic data refers to the environment type and the corresponding environmental data, such as temperature, humidity and other specific environmental data. The environmental characteristic data is input into a preset parameter correction model, and the parameter correction model is used to obtain the parameter correction value. The parameter correction value refers to the numerical value of the adjustment of the working parameters of the acoustic emission sensor. The parameter correction value is input into the acoustic emission sensor, and the working parameters of the acoustic emission sensor are set. During the detection process, the working parameters of the acoustic emission sensor can be dynamically adjusted in real time according to the detection environment, which is conducive to improving the accuracy of the detection results.

[0010] In a preferred example, the present application may be further configured as follows: after acquiring the data output by the multi-point acoustic emission sensor in real time and before integrating to form a multi-channel acoustic emission data queue, the multi-task parallel processing method of the acoustic emission detection system further includes: Receive data output by a multi-point acoustic emission sensor in real time, perform denoising and filtering on the data output by the multi-point acoustic emission sensor, and obtain processed data; A multi-channel acoustic emission data queue is formed based on the processed data integration.

[0011] By adopting the above technical scheme, the multi-point acoustic emission sensor transmits an acoustic signal to the material to be detected, which is reflected by the material to be detected, and the reflected signal is received in real time to obtain data output by the multi-point acoustic emission sensor. The data output by the multi-point acoustic emission sensor is denoised and filtered to remove interference data. Interference data is generally generated by the detection environment. Therefore, denoising and filtering are performed on the received data output by the multi-point acoustic emission sensor to eliminate the interference effect of the current detection environment on the data. The processed data is integrated to form a multi-channel acoustic emission data queue, thereby improving the accuracy of the data.

[0012] In a preferred example, the present application may be further configured as follows: in response to the data processing request, preprocessing the preset data processing architecture to obtain an initialized data processing architecture that meets the data processing request, specifically including: In response to the data processing request, obtaining status information of each processing unit in the data processing architecture; A processing priority is set for each processing unit based on the status information of each processing unit to form a processing unit queue, thereby obtaining an initialized data processing architecture that meets the data processing request.

[0013] By adopting the above technical solution, before using the data processing architecture to process the data output by the multi-point acoustic emission sensor, respond to the data processing request and obtain the status information of each processing unit in the data processing architecture. The status information of each processing unit refers to the processing status of the processing unit, that is, the processing capacity of the current processing unit. According to the status information of each processing unit, a priority is set for each processing unit, and the processing unit with a large processing capacity is set to the optimal level. According to the corresponding priority, multiple processing units are integrated to form a processing unit queue, forming an initialized data processing architecture that meets the data processing request, thereby facilitating the selection of a processing unit with a large processing capacity for data processing, improving processing efficiency, and thus improving overall detection efficiency.

[0014] In a preferred example, the present application can be further configured as follows: based on the acoustic emission signal characteristics, the acoustic emission data to be processed is mapped to a corresponding thread pool for data processing architecture adaptation, and a suitable data processing framework is selected to process the acoustic emission data to be processed, specifically including: Determine the type of acoustic emission data to be processed based on the acoustic emission signal characteristics, and construct a mapping relationship between the acoustic emission data to be processed and the thread pool according to the type of acoustic emission data to be processed; According to the mapping relationship between the acoustic emission data to be processed and the thread pool, the acoustic emission data to be processed and the data processing architecture in the thread pool are adapted and processed, and the highest processing unit with the highest degree of adaptation is selected; A data distribution relationship between the acoustic emission data to be processed and the highest processing unit is established, and data processing is performed on the acoustic emission data to be processed according to the data distribution relationship.

[0015] By adopting the above technical scheme, the type of acoustic emission data to be processed is obtained by extracting features from the acoustic emission data to be processed, and a mapping relationship between the acoustic emission data to be processed and the thread pool is constructed according to the type of the acoustic emission data to be processed. According to the mapping relationship, the acoustic emission data to be processed and the data processing architecture in the thread pool are adapted to speed up the speed of allocating the acoustic emission data to be processed to the data processing architecture. At the same time, the data processing architecture can be adapted according to the type of the acoustic emission data to be processed, and the processing efficiency of the acoustic emission data can be further improved. The data distribution relationship between the highest processing unit and the acoustic emission data to be processed is used to distribute the acoustic emission data to be processed, so as to realize dynamic operation and maintenance of the distribution process of the acoustic emission data to be processed and improve the intelligence of the data processing architecture.

[0016] In a preferred example, the present application may be further configured as follows: after mapping the acoustic emission data to be processed to a corresponding thread pool based on the acoustic emission signal characteristics to adapt the data processing architecture, and selecting a suitable data processing framework to process the acoustic emission data to be processed, the acoustic emission detection system multi-task parallel processing method further includes: Acquire a data processing state of a processing unit in a data processing architecture, and determine whether the processing unit is in an end state based on the data processing state; If so, the remaining acoustic emission data processing capacity is obtained in real time, and the data processing architecture is polled based on the acoustic emission data processing capacity to facilitate adaptation to the processing unit in the idle state.

[0017] By adopting the above technical solution, the data processing status of the current processing unit in the data processing architecture is monitored in real time to obtain the data processing status, and it is determined whether the processing unit is in the end state. If not, the data processing unit is used to continue to process the acoustic emission data. If so, the remaining acoustic emission data processing amount is obtained in real time, and the data processing architecture is polled according to the remaining acoustic emission data processing amount, that is, a data processing request is issued to the processing unit that is currently idle and meets the remaining acoustic emission data processing amount, so as to continue the acoustic emission data processing in time and improve the overall detection efficiency.

[0018] The second object of the invention is achieved by the following technical solutions: A multi-task parallel processing system for an acoustic emission detection system, the multi-task parallel processing system for an acoustic emission detection system comprising: An acoustic emission data acquisition module, used for acquiring data output by multi-point acoustic emission sensors in real time, integrating the data to form a multi-channel acoustic emission data queue, and generating a data processing request based on the multi-channel acoustic emission data queue; A data processing architecture preprocessing module, used to respond to the data processing request, preprocess the preset data processing architecture, and obtain an initialized data processing architecture that meets the data processing request; An acoustic emission signal feature acquisition module, which acquires the acoustic emission data to be processed based on the multi-channel acoustic emission data queue, and acquires the acoustic emission signal features according to the acoustic emission data to be processed; The acoustic emission data processing module is used to map the acoustic emission data to be processed to the corresponding thread pool for data processing architecture adaptation based on the acoustic emission signal characteristics, and select a suitable data processing framework to process the acoustic emission data to be processed.

[0019] By adopting the above technical solution, in the process of using acoustic emission detection technology to detect materials, multiple independent acoustic emission sensors are used to obtain data output by multi-point acoustic emission sensors in real time, and the data output by the multi-point acoustic emission sensors are integrated to form a multi-channel acoustic emission data queue. The multi-channel acoustic emission data queue refers to data output by multiple independent acoustic emission sensors. A data processing request is generated according to the multi-channel acoustic emission data queue. The data processing request refers to a task request for data processing of the acoustic emission data in the multi-channel acoustic emission data queue. In response to the data processing request, a data processing architecture preset in the system is preprocessed, wherein the data processing architecture includes multiple processing units, such as DSP, FPGA, etc. The data processing architecture is preprocessed so that the data processing architecture meets the current The processing requirements of acoustic emission data are improved, the adaptability of the data processing architecture and the current queue of acoustic emission data to be processed is improved, the detection efficiency is improved, the acoustic emission data to be processed is obtained according to the multi-channel acoustic emission data queue, the corresponding acoustic emission signal characteristics are obtained according to the acoustic emission data, and the acoustic emission signal characteristics are used to map the acoustic emission data to be processed in the multi-channel acoustic emission data queue to the thread pool for data processing architecture adaptation, and the acoustic emission data to be processed are processed through the data processing architecture with the highest degree of adaptation, so that each acoustic emission data to be processed is decoupled through the corresponding thread pool and distributed to the processing unit in the corresponding data processing architecture for processing, so as to realize parallel processing of data in the multi-channel acoustic emission data queue, improve data processing efficiency and orderliness, and thus improve the efficiency of the entire acoustic emission detection process.

[0020] The third objective of the present application is achieved through the following technical solutions: A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the multi-task parallel processing method of the acoustic emission detection system are implemented.

[0021] The fourth objective of the present application is achieved through the following technical solutions: A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the multi-task parallel processing method of the acoustic emission detection system.

[0022] In summary, the present application includes at least one of the following beneficial technical effects: 1. In the process of using acoustic emission detection technology to detect materials, multiple independent acoustic emission sensors are used to obtain data output by multi-point acoustic emission sensors in real time, and the data output by the multi-point acoustic emission sensors are integrated to form a multi-channel acoustic emission data queue. The multi-channel acoustic emission data queue refers to data output by multiple independent acoustic emission sensors. A data processing request is generated according to the multi-channel acoustic emission data queue. The data processing request refers to a task request for data processing of the acoustic emission data in the multi-channel acoustic emission data queue. In response to the data processing request, the data processing architecture preset in the system is preprocessed, wherein the data processing architecture includes multiple processing units, such as DSP, FPGA, etc. The data processing architecture is preprocessed so that the data processing architecture meets the current acoustic emission data. According to the processing requirements, the adaptability of the data processing architecture and the current queue of acoustic emission data to be processed is improved, the detection efficiency is improved, the acoustic emission data to be processed is obtained according to the multi-channel acoustic emission data queue, the corresponding acoustic emission signal characteristics are obtained according to the acoustic emission data, and the acoustic emission signal characteristics are used to map the acoustic emission data to be processed in the multi-channel acoustic emission data queue to the thread pool for data processing architecture adaptation, and the acoustic emission data to be processed is processed through the data processing architecture with the highest degree of adaptation, so that each acoustic emission data to be processed is decoupled through the corresponding thread pool and distributed to the processing unit in the corresponding data processing architecture for processing, so as to realize parallel processing of data in the multi-channel acoustic emission data queue, improve data processing efficiency and orderliness, and thus improve the efficiency of the entire acoustic emission detection process; 2. In the process of acoustic emission testing of the test material, the test environment information is obtained in real time. The test environment information refers to the specific situation of the current test environment. The test environment information is analyzed to obtain environmental characteristic data. The environmental characteristic data refers to the environment type and the corresponding environmental data, such as temperature, humidity and other specific environmental data. The environmental characteristic data is input into the preset parameter correction model, and the parameter correction value is obtained by using the parameter correction model. The parameter correction value refers to the numerical value of the adjustment of the working parameters of the acoustic emission sensor. The parameter correction value is input into the acoustic emission sensor, and the working parameters of the acoustic emission sensor are set. In the detection process, the working parameters of the acoustic emission sensor can be dynamically adjusted in real time according to the detection environment, which is conducive to improving the accuracy of the detection results; 3. The multi-point acoustic emission sensor emits an acoustic signal to the material to be tested, which is reflected by the material to be tested, and the reflected signal is received in real time to obtain the data output by the multi-point acoustic emission sensor. The data output by the multi-point acoustic emission sensor is subjected to denoising and filtering, which can remove the interference data. The interference data is generally generated by the detection environment. Therefore, the received data output by the multi-point acoustic emission sensor is subjected to denoising and filtering, which can eliminate the interference effect of the current detection environment on the data. The processed data is integrated to form a multi-channel acoustic emission data queue, which can improve the accuracy of the data. 4. Before using the data processing architecture to process the data output by the multi-point acoustic emission sensor, respond to the data processing request and obtain the status information of each processing unit in the data processing architecture. The status information of each processing unit refers to the processing status of the processing unit, that is, the processing capacity of the current processing unit. Set the priority of each processing unit according to the status information of each processing unit, set the processing unit with large processing capacity to the optimal level, and integrate multiple processing units into a processing unit queue according to the corresponding priority, forming an initialized data processing architecture that meets the data processing request, thereby facilitating the selection of processing units with large processing capacity for data processing, improving processing efficiency, and thus improving overall detection efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 is a flow chart of a multi-task parallel processing method of an acoustic emission detection system in an embodiment of the present application; Figure 2 This is another implementation flow chart of the multi-task parallel processing method of the acoustic emission detection system in one embodiment of the present application; Figure 3 This is another implementation flow chart of the multi-task parallel processing method of the acoustic emission detection system in one embodiment of the present application; Figure 4 It is a flowchart for implementing step S20 in the multi-task parallel processing method of the acoustic emission detection system in one embodiment of the present application; Figure 5 It is a flowchart for implementing step S40 in the multi-task parallel processing method of the acoustic emission detection system in one embodiment of the present application; Figure 6 This is another implementation flow chart of the multi-task parallel processing method of the acoustic emission detection system in one embodiment of the present application; Figure 7 This is a principle block diagram of a multi-task parallel processing system of an acoustic emission detection system in one embodiment of the present application; Figure 8 It is a schematic diagram of a computer device in one embodiment of the present application. DETAILED DESCRIPTION

[0024] The present application is further described in detail below in conjunction with the accompanying drawings.

[0025] In one embodiment, if Figure 1 As shown, the present application discloses a multi-task parallel processing method for an acoustic emission detection system, which specifically includes the following steps: S10: acquiring data output by multi-point acoustic emission sensors in real time, integrating the data to form a multi-channel acoustic emission data queue, and generating a data processing request based on the multi-channel acoustic emission data queue.

[0026] In this embodiment, the data processing request refers to a task request for performing data processing on the acoustic emission data in the multi-channel acoustic emission data queue.

[0027] Specifically, data output by a multi-point acoustic emission sensor is acquired in real time through a plurality of independent acoustic emission sensors, and the data output by the multi-point acoustic emission sensor is integrated to form a multi-channel acoustic emission data queue. The multi-channel acoustic emission data queue refers to data output by a plurality of independent acoustic emission sensors, and a data processing request is generated according to the multi-channel acoustic emission data queue.

[0028] S20: In response to the data processing request, preprocess the preset data processing architecture to obtain an initialized data processing architecture that meets the data processing request.

[0029] Specifically, in response to a data processing request, the data processing architecture preset in the system is preprocessed, wherein the data processing architecture includes multiple processing units, such as DSP, FPGA, etc. The data processing architecture is preprocessed so that the data processing architecture meets the processing requirements of the current acoustic emission data, improves the adaptability of the data processing architecture to the current queue of acoustic emission data to be processed, and improves the detection efficiency.

[0030] S30: Acquire the acoustic emission data to be processed based on the multi-channel acoustic emission data queue, and acquire acoustic emission signal features according to the acoustic emission data to be processed.

[0031] In this embodiment, the acoustic emission signal feature refers to feature information of the acoustic emission data to be processed, such as data type, data volume, etc.

[0032] Specifically, the to-be-processed acoustic emission data is obtained according to the multi-channel acoustic emission data queue, and corresponding information such as the data type and data volume is obtained according to the acoustic emission data.

[0033] S40: Mapping the acoustic emission data to be processed to a corresponding thread pool based on the acoustic emission signal characteristics to adapt the data processing architecture, and selecting a suitable data processing framework to process the acoustic emission data to be processed.

[0034] Specifically, the acoustic emission data to be processed in the multi-channel acoustic emission data queue are mapped to the thread pool for data processing architecture adaptation by utilizing the acoustic emission signal characteristics, and the acoustic emission data to be processed are processed by the data processing architecture with the highest degree of adaptation, so that each acoustic emission data to be processed is decoupled through the corresponding thread pool and distributed to the processing unit in the corresponding data processing architecture for processing, thereby realizing parallel processing of data in the multi-channel acoustic emission data queue, improving data processing efficiency and orderliness, and thereby improving the efficiency of the entire acoustic emission detection process.

[0035] In this embodiment, in the process of using acoustic emission detection technology to detect materials, multiple independent acoustic emission sensors are used to obtain data output by multi-point acoustic emission sensors in real time, and the data output by the multi-point acoustic emission sensors are integrated to form a multi-channel acoustic emission data queue. The multi-channel acoustic emission data queue refers to data output by multiple independent acoustic emission sensors. A data processing request is generated according to the multi-channel acoustic emission data queue. The data processing request refers to a task request for data processing of the acoustic emission data in the multi-channel acoustic emission data queue. In response to the data processing request, a data processing architecture preset in the system is preprocessed, wherein the data processing architecture includes multiple processing units, such as DSP, FPGA, etc. The data processing architecture is preprocessed so that the data processing architecture meets the current acoustic emission requirements. The processing requirements of acoustic emission data are met, the adaptability of the data processing architecture and the current queue of acoustic emission data to be processed is improved, the detection efficiency is improved, the acoustic emission data to be processed is obtained according to the multi-channel acoustic emission data queue, the corresponding acoustic emission signal characteristics are obtained according to the acoustic emission data, and the acoustic emission signal characteristics are used to map the acoustic emission data to be processed in the multi-channel acoustic emission data queue to the thread pool for data processing architecture adaptation, and the acoustic emission data to be processed are processed through the data processing architecture with the highest degree of adaptation, so that each acoustic emission data to be processed is decoupled through the corresponding thread pool and distributed to the processing unit in the corresponding data processing architecture for processing, so as to realize parallel processing of data in the multi-channel acoustic emission data queue, improve data processing efficiency and orderliness, and thus improve the efficiency of the entire acoustic emission detection process.

[0036] In one embodiment, if Figure 2 As shown, before step S10, that is, before acquiring the data output by the multi-point acoustic emission sensor, the multi-task parallel processing method of the acoustic emission detection system further includes: S101: Acquire detection environment information in real time, and acquire environmental feature data based on the detection environment information.

[0037] In this embodiment, the detection environment information refers to the specific situation of the current detection environment, and the environmental characteristic data refers to the environment type and corresponding environmental data, such as temperature, humidity and other specific environmental data.

[0038] Specifically, before performing acoustic emission testing on the material to be tested, the testing environment information can be obtained in real time through sensors, and the testing environment information can be analyzed to obtain the environment type and corresponding environmental data, such as temperature, humidity and other specific environmental data.

[0039] S102: Inputting the environmental characteristic data into a preset parameter correction model to obtain parameter correction values, inputting the parameter correction values ​​into an acoustic emission sensor, and setting working parameters of the acoustic emission sensor.

[0040] Specifically, the environmental characteristic data is input into a preset parameter correction model, and the parameter correction model is used to obtain the parameter correction value. The parameter correction value refers to the numerical value of the adjustment of the working parameters of the acoustic emission sensor. The parameter correction value is input into the acoustic emission sensor, and the working parameters of the acoustic emission sensor are set. During the detection process, the working parameters of the acoustic emission sensor can be dynamically adjusted in real time according to the detection environment, which is conducive to improving the accuracy of the detection results.

[0041] In one embodiment, if Figure 3 As shown, after acquiring the data output by the multi-point acoustic emission sensors in real time and before integrating to form a multi-channel acoustic emission data queue, the multi-task parallel processing method of the acoustic emission detection system also includes: S103: receiving data output by the multi-point acoustic emission sensor in real time, and performing denoising and filtering processing on the data output by the multi-point acoustic emission sensor to obtain processed data.

[0042] S104: Integrate the processed data to form a multi-channel acoustic emission data queue.

[0043] Specifically, the multi-point acoustic emission sensor transmits an acoustic signal to the material to be detected, which is reflected by the material to be detected, and the reflected signal is received in real time to obtain data output by the multi-point acoustic emission sensor. The data output by the multi-point acoustic emission sensor is denoised and filtered to remove interference data. Interference data is generally generated by the detection environment. Therefore, denoising and filtering are performed on the received data output by the multi-point acoustic emission sensor to eliminate the interference effect of the current detection environment on the data. The processed data is integrated to form a multi-channel acoustic emission data queue, thereby improving the accuracy of the data.

[0044] In one embodiment, if Figure 4 As shown, in step S20, that is, in response to the data processing request, the preset data processing architecture is preprocessed to obtain an initialized data processing architecture that meets the data processing request, specifically including: S21: Responding to the data processing request, obtaining status information of each processing unit in the data processing architecture.

[0045] Specifically, before using the data processing architecture to process the data output by the multi-point acoustic emission sensor, respond to the data processing request and obtain the status information of each processing unit in the data processing architecture. The status information of each processing unit refers to the processing status of the processing unit, that is, the processing capacity of the current processing unit.

[0046] S22: Setting a processing priority for each processing unit based on the status information of each processing unit to form a processing unit queue, thereby obtaining an initialized data processing architecture that meets the data processing request.

[0047] Specifically, a priority is set for each processing unit according to the status information of each processing unit, and the processing unit with large processing capacity is set to the optimal level. According to the corresponding priority, multiple processing units are integrated into a processing unit queue to form an initialized data processing architecture that meets the data processing request, thereby facilitating the selection of processing units with large processing capacity for data processing, improving processing efficiency, and further improving overall detection efficiency.

[0048] In one embodiment, if Figure 5 As shown, in step S40, the acoustic emission data to be processed is mapped to the corresponding thread pool based on the acoustic emission signal characteristics to adapt the data processing architecture, and a suitable data processing framework is selected to process the acoustic emission data to be processed, specifically including: S41: determining the type of acoustic emission data to be processed based on the acoustic emission signal characteristics, and constructing a mapping relationship between the acoustic emission data to be processed and a thread pool according to the type of acoustic emission data to be processed.

[0049] S42: According to the mapping relationship between the acoustic emission data to be processed and the thread pool, the acoustic emission data to be processed and the data processing architecture in the thread pool are adapted and processed, and the highest processing unit with the highest degree of adaptation is selected.

[0050] S43: constructing a data distribution relationship between the acoustic emission data to be processed and the highest processing unit, and performing data processing on the acoustic emission data to be processed according to the data distribution relationship.

[0051] Specifically, feature extraction is performed on the acoustic emission data to be processed to obtain the type of acoustic emission data to be processed, and a mapping relationship between the acoustic emission data to be processed and the thread pool is constructed according to the type of the acoustic emission data to be processed. According to the mapping relationship, the acoustic emission data to be processed and the data processing architecture in the thread pool are adapted to speed up the allocation of the acoustic emission data to be processed to the data processing architecture. At the same time, the data processing architecture can be adapted according to the type of the acoustic emission data to be processed, and the processing efficiency of the acoustic emission data can be further improved. Through the data distribution relationship between the highest processing unit and the acoustic emission data to be processed, data distribution is performed on the acoustic emission data to be processed, and dynamic operation and maintenance of the distribution process of the acoustic emission data to be processed is realized, thereby improving the intelligence of the data processing architecture.

[0052] In one embodiment, if Figure 6 As shown, after step S40, the road surface damage rating of the highway construction to be monitored is performed according to each of the road surface damage images included in the target BIM model, which specifically includes: S50: Acquire a data processing status of a processing unit in a data processing architecture, and determine whether the processing unit is in an end state based on the data processing status.

[0053] S60: If yes, obtain the remaining acoustic emission data processing capacity in real time, and perform polling processing on the data processing architecture based on the acoustic emission data processing capacity, so as to adapt to the processing unit in the idle state.

[0054] Specifically, the data processing status of the current processing unit in the data processing architecture is monitored in real time, the data processing status is obtained, and it is determined whether the processing unit is in an end state. If not, the data processing unit is used to continue to process the acoustic emission data. If so, the remaining acoustic emission data processing amount is obtained in real time, and the data processing architecture is polled according to the remaining acoustic emission data processing amount, that is, a data processing request is issued to the processing unit that is currently idle and meets the remaining acoustic emission data processing amount, so as to continue the acoustic emission data processing in a timely manner and improve the overall detection efficiency.

[0055] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0056] In one embodiment, a multi-task parallel processing system for an acoustic emission detection system is provided, and the multi-task parallel processing system for an acoustic emission detection system corresponds one-to-one to the multi-task parallel processing method for an acoustic emission detection system in the above embodiment. Figure 7 As shown, the multi-task parallel processing system of the acoustic emission detection system includes an acoustic emission data acquisition module, a data processing architecture preprocessing module, an acoustic emission signal feature acquisition module and an acoustic emission data processing module. The detailed description of each functional module is as follows: An acoustic emission data acquisition module, used for acquiring data output by multi-point acoustic emission sensors in real time, integrating the data to form a multi-channel acoustic emission data queue, and generating a data processing request based on the multi-channel acoustic emission data queue; A data processing architecture preprocessing module, used to respond to the data processing request, preprocess the preset data processing architecture, and obtain an initialized data processing architecture that meets the data processing request; An acoustic emission signal feature acquisition module, which acquires the acoustic emission data to be processed based on the multi-channel acoustic emission data queue, and acquires the acoustic emission signal features according to the acoustic emission data to be processed; The acoustic emission data processing module is used to map the acoustic emission data to be processed to the corresponding thread pool for data processing architecture adaptation based on the acoustic emission signal characteristics, and select a suitable data processing framework to process the acoustic emission data to be processed.

[0057] Optionally, also include: A detection environment information acquisition module, used to acquire detection environment information in real time, and acquire environmental feature data based on the detection environment information; The acoustic emission sensor setting module is used to input the environmental characteristic data into a preset parameter correction model, obtain parameter correction values, input the parameter correction values ​​into the acoustic emission sensor, and set the working parameters of the acoustic emission sensor.

[0058] For the specific definition of the multi-task parallel processing system of the acoustic emission detection system, please refer to the definition of the multi-task parallel processing method of the acoustic emission detection system mentioned above, which will not be repeated here. Each module in the above-mentioned multi-task parallel processing system of the acoustic emission detection system can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0059] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 8 As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store acoustic emission data and data processing architecture. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a multi-task parallel processing method for an acoustic emission detection system is implemented.

[0060] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program: Acquire data output by multi-point acoustic emission sensors in real time, integrate them to form a multi-channel acoustic emission data queue, and generate a data processing request based on the multi-channel acoustic emission data queue; In response to the data processing request, preprocessing the preset data processing architecture to obtain an initialized data processing architecture that meets the data processing request; Acquiring to-be-processed acoustic emission data based on the multi-channel acoustic emission data queue, and acquiring acoustic emission signal features according to the to-be-processed acoustic emission data; Based on the acoustic emission signal characteristics, the acoustic emission data to be processed are mapped to a corresponding thread pool for data processing architecture adaptation, and a suitable data processing framework is selected to process the acoustic emission data to be processed.

[0061] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented: Acquire data output by multi-point acoustic emission sensors in real time, integrate them to form a multi-channel acoustic emission data queue, and generate a data processing request based on the multi-channel acoustic emission data queue; In response to the data processing request, preprocessing the preset data processing architecture to obtain an initialized data processing architecture that meets the data processing request; Acquiring to-be-processed acoustic emission data based on the multi-channel acoustic emission data queue, and acquiring acoustic emission signal features according to the to-be-processed acoustic emission data; Based on the acoustic emission signal characteristics, the acoustic emission data to be processed are mapped to a corresponding thread pool for data processing architecture adaptation, and a suitable data processing framework is selected to process the acoustic emission data to be processed.

[0062] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0063] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0064] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A multi-task parallel processing method for an acoustic emission detection system, characterized in that: The multi-task parallel processing method of the acoustic emission detection system comprises the following steps: Acquire data output by multi-point acoustic emission sensors in real time, integrate them to form a multi-channel acoustic emission data queue, and generate a data processing request based on the multi-channel acoustic emission data queue; In response to the data processing request, preprocessing the preset data processing architecture to obtain an initialized data processing architecture that meets the data processing request; Acquiring to-be-processed acoustic emission data based on the multi-channel acoustic emission data queue, and acquiring acoustic emission signal features according to the to-be-processed acoustic emission data; Based on the acoustic emission signal characteristics, the acoustic emission data to be processed are mapped to a corresponding thread pool for data processing architecture adaptation, and a suitable data processing framework is selected to process the acoustic emission data to be processed.

2. The multi-task parallel processing method of the acoustic emission detection system according to claim 1 is characterized in that: Before acquiring the data output by the multi-point acoustic emission sensor in real time, the multi-task parallel processing method of the acoustic emission detection system further includes: Acquire detection environment information in real time, and acquire environmental characteristic data based on the detection environment information; The environmental characteristic data is input into a preset parameter correction model to obtain a parameter correction value, and the parameter correction value is input into an acoustic emission sensor to set the working parameters of the acoustic emission sensor.

3. The multi-task parallel processing method of the acoustic emission detection system according to claim 2 is characterized in that: After acquiring the data output by the multi-point acoustic emission sensors in real time and before integrating to form a multi-channel acoustic emission data queue, the multi-task parallel processing method of the acoustic emission detection system further includes: Receive data output by a multi-point acoustic emission sensor in real time, perform denoising and filtering on the data output by the multi-point acoustic emission sensor, and obtain processed data; A multi-channel acoustic emission data queue is formed based on the processed data integration.

4. The multi-task parallel processing method of the acoustic emission detection system according to claim 1 is characterized in that: The responding to the data processing request, preprocessing the preset data processing architecture to obtain an initialized data processing architecture that meets the data processing request, specifically includes: In response to the data processing request, obtaining status information of each processing unit in the data processing architecture; A processing priority is set for each processing unit based on the status information of each processing unit to form a processing unit queue, thereby obtaining an initialized data processing architecture that meets the data processing request.

5. The multi-task parallel processing method of the acoustic emission detection system according to claim 1, characterized in that: The step of mapping the acoustic emission data to be processed to a corresponding thread pool based on the acoustic emission signal characteristics to adapt the data processing architecture, and selecting a suitable data processing framework to process the acoustic emission data to be processed specifically includes: Determine the type of acoustic emission data to be processed based on the acoustic emission signal characteristics, and construct a mapping relationship between the acoustic emission data to be processed and the thread pool according to the type of acoustic emission data to be processed; According to the mapping relationship between the acoustic emission data to be processed and the thread pool, the acoustic emission data to be processed and the data processing architecture in the thread pool are adapted and processed, and the highest processing unit with the highest degree of adaptation is selected; A data distribution relationship between the acoustic emission data to be processed and the highest processing unit is established, and data processing is performed on the acoustic emission data to be processed according to the data distribution relationship.

6. The multi-task parallel processing method of the acoustic emission detection system according to claim 1, characterized in that: After mapping the acoustic emission data to be processed to a corresponding thread pool based on the acoustic emission signal characteristics to adapt the data processing architecture and selecting a suitable data processing framework to process the acoustic emission data to be processed, the acoustic emission detection system multi-task parallel processing method further includes: Acquire a data processing state of a processing unit in a data processing architecture, and determine whether the processing unit is in an end state based on the data processing state; If so, the remaining acoustic emission data processing capacity is obtained in real time, and the data processing architecture is polled based on the acoustic emission data processing capacity to facilitate adaptation to the processing unit in the idle state.

7. A multi-task parallel processing system for an acoustic emission detection system, characterized in that: The multi-task parallel processing system of the acoustic emission detection system includes: An acoustic emission data acquisition module, used for acquiring data output by multi-point acoustic emission sensors in real time, integrating the data to form a multi-channel acoustic emission data queue, and generating a data processing request based on the multi-channel acoustic emission data queue; A data processing architecture preprocessing module, used to respond to the data processing request, preprocess the preset data processing architecture, and obtain an initialized data processing architecture that meets the data processing request; An acoustic emission signal feature acquisition module, which acquires the acoustic emission data to be processed based on the multi-channel acoustic emission data queue, and acquires the acoustic emission signal features according to the acoustic emission data to be processed; The acoustic emission data processing module is used to map the acoustic emission data to be processed to the corresponding thread pool for data processing architecture adaptation based on the acoustic emission signal characteristics, and select a suitable data processing framework to process the acoustic emission data to be processed.

8. The multi-task parallel processing system of the acoustic emission detection system according to claim 7, characterized in that: Also includes: A detection environment information acquisition module, used to acquire detection environment information in real time, and acquire environmental feature data based on the detection environment information; The acoustic emission sensor setting module is used to input the environmental characteristic data into a preset parameter correction model, obtain parameter correction values, input the parameter correction values ​​into the acoustic emission sensor, and set the working parameters of the acoustic emission sensor.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the multi-task parallel processing method of an acoustic emission detection system as claimed in any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of a multi-task parallel processing method for an acoustic emission detection system as claimed in any one of claims 1 to 6 are implemented.

Images