A multi-core processor-based multi-mode industrial data acquisition method and system

Abstract

This invention discloses a multi-mode industrial data acquisition method and system based on a multi-core processor; it relates to the field of industrial data acquisition technology; it effectively improves the multi-core allocation capability of a multi-core processor for acquiring multi-mode industrial data; this invention sets up acquisition multi-modality and obtains the modal multi-core requirement value of the acquisition multi-modality; then, based on the analysis of the modal multi-core requirement value, it groups the multi-core processor to obtain multi-core processing units; and sets up a multi-core allocation mechanism for the multi-core processing units; it obtains multi-mode acquisition instructions, and based on the multi-core allocation mechanism, the multi-core processing units acquire multi-mode industrial data through the multi-mode acquisition instructions; it performs time dimension alignment processing on the multi-mode industrial data to obtain a time dimension modal industrial data sequence; and then analyzes the time dimension model industrial data sequence to obtain abnormal industrial data.

Description

Technical Field

[0001] This invention relates to the field of industrial data acquisition technology, specifically to a multi-mode industrial data acquisition method and system based on a multi-core processor. Background Technology

[0002] A multi-core processor integrates two or more complete computing engines (cores) into a single processor. In this case, the processor can support multiple processors on the system bus, with all bus control and command signals provided by the bus controller. Therefore, multi-core processors can improve the acquisition speed of multi-mode industrial data.

[0003] However, in existing technologies, when allocating different processing tasks to multiple cores for multi-modal industrial data acquisition, tasks are usually allocated to multiple cores rather than allocated to multiple cores based on tasks. This results in inaccurate multi-core allocation, which can lead to data pipeline blockage or idleness, reducing overall efficiency, especially when industrial data contains multiple data types, such as the fusion of multimodal data of different types and different sampling rates.

[0004] Therefore, in order to improve the timeliness of multi-core collaboration and the rationality of multi-mode industrial data acquisition allocation, this invention provides a multi-mode industrial data acquisition method and system based on a multi-core processor. Summary of the Invention

[0005] The purpose of this invention is to provide a multi-mode industrial data acquisition method and system based on a multi-core processor, so as to solve the problems in the background technology.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a multi-mode industrial data acquisition method based on a multi-core processor, the method comprising the following steps:

[0007] Step S1: Set up multi-modal acquisition and obtain the modal multi-core requirement value of multi-modal acquisition; then, based on the analysis of the modal multi-core requirement value, group the multi-core processors to obtain multi-core processing units;

[0008] Step S2: Set up the multi-core allocation mechanism for the multi-core processing unit; obtain multi-mode acquisition instructions, and based on the multi-core allocation mechanism, the multi-core processing unit acquires multi-modal industrial data through the multi-mode acquisition instructions;

[0009] Step S3: Perform time dimension alignment processing on the multi-modal industrial data to obtain the time dimension modal industrial data sequence;

[0010] Step S4: Analyze the industrial data sequence of the time dimension model to obtain abnormal industrial data.

[0011] Furthermore, the process of setting up multimodal data acquisition includes:

[0012] Acquire the equipment production dataset for each industrial device and map it to the corresponding industrial device; set up multimodal acquisition and perform multimodal classification on the equipment production data in the equipment production dataset to obtain the equipment multimodal data pool;

[0013] Set production monitoring data standards, identify equipment production data in the equipment multi-mode data pool according to the production monitoring data standards and mark them as production data to be monitored, and then obtain the collection multi-modal of the equipment multi-mode data pool corresponding to the production data to be monitored.

[0014] Furthermore, the process of obtaining the modal multi-kernel requirement values ​​for multimodal acquisition includes:

[0015] Acquire the same multimodal production data to be monitored, and denot it as modal production data to be monitored; schedule the industrial equipment that collects the modal production data to be monitored, and denot it as modal industrial equipment; then obtain the quantity of modal production data to be monitored corresponding to the modal industrial equipment, and denot it as modal equipment data volume; connect the modal industrial equipment in pairs by geographical location to obtain the modal connection distance; and obtain the industrial process anomaly impact level coefficient of the modal industrial equipment connected by the modal connection distance.

[0016] Modal coordinates of the modal industrial equipment are formed by combining the modal equipment data volume and the industrial process anomaly impact level coefficient.

[0017] Furthermore, the process of grouping multi-core processors to obtain multi-core processing units based on the analysis of modal multi-core demand values ​​includes:

[0018] Set the unit modal multicore demand value, obtain the ratio of the modal multicore demand value to the unit modal multicore demand value and round it up as the demand coefficient, set the number of cores per unit corresponding to the unit modal multicore demand value; obtain the demand cores of the demand coefficient through the number of cores per unit; allocate the corresponding number of multicores to the demand cores according to the modal multicore demand values ​​from large to small;

[0019] If the number of allocated multi-cores is insufficient, the corresponding acquisition multi-modal will be placed in the waiting area to wait for the generation of waiting acquisition multi-modal; otherwise, no processing will be performed.

[0020] The number of cores is integrated to form a multi-core processing unit, and the multi-core processing units are connected through a preset transmission channel.

[0021] Furthermore, the process of setting up a multi-core allocation mechanism for multi-core processing units includes:

[0022] Obtain the maximum and minimum values ​​of modal connectivity distances and form a modal connectivity distance region for acquiring multimodal data; distribute the modal connectivity distance region equally according to the number of multi-cores; obtain the corresponding number of unit modal connectivity distance threshold ranges for modal connectivity distances.

[0023] Arbitrarily select one modal industrial device for multimodal data collection as the starting modal industrial device, obtain the maximum modal connection distance connected to the starting modal industrial device, and record it as the maximum modal connection distance. Then extract the starting modal industrial device and the modal industrial devices connected by the maximum modal connection distance, and integrate them to generate the extracted modal industrial device set. In this way, arbitrarily select another modal industrial device as the starting modal industrial device, obtain the maximum modal connection distance corresponding to the starting modal industrial device, and then obtain the extracted modal industrial device set.

[0024] The maximum modal connection distances are distributed within the corresponding unit modal connection distance threshold range to obtain the corresponding set of extracted modal industrial equipment, and then the number of modal industrial equipment corresponding to the unit modal connection distance threshold range is obtained.

[0025] Set a threshold for the number of modal industrial devices processed by a single core, obtain the ratio of the number of modal industrial devices to the threshold for the number of modal industrial devices, and take the value upwards as the number of allocated cores corresponding to the threshold range of unit modal connection distance;

[0026] The number of cores in the multi-core processing unit is allocated to the corresponding unit modal connection distance threshold range through the allocation number of cores. The remaining number of cores in the multi-core processing unit is sent to the waiting area to generate the number of cores to be allocated. Then, if the number of cores to be allocated in the waiting area is equal to the number of cores required for the waiting multi-modal acquisition, the number of cores to be allocated is allocated to the waiting multi-modal acquisition multi-core construction multi-core allocation mechanism with the corresponding number of cores required.

[0027] Furthermore, the process of acquiring multi-modal industrial data by the multi-core processing unit based on the multi-core allocation mechanism through multi-modal acquisition instructions includes:

[0028] The multi-mode acquisition command includes at least the acquisition period and the acquisition frequency;

[0029] Based on the multi-core allocation mechanism, the multi-core processing unit allocates the number of multi-cores to the unit modal connection distance threshold range corresponding to the multi-modal acquisition, obtains the industrial equipment of each modality within the unit modal connection distance threshold range, and collects the industrial production data of the corresponding modal industrial equipment to be monitored through the corresponding multi-modal acquisition command, and associates it with the corresponding modal industrial equipment.

[0030] The system integrates all industrial production data from the multi-core processing unit to generate multi-modal industrial data corresponding to the collected multi-modal data.

[0031] Furthermore, the process of aligning multi-modal industrial data along the time dimension to obtain a time-dimension modal industrial data sequence includes:

[0032] By merging industrial production data from the same collection time point in multi-modal industrial data, a corresponding time-dimensional modal industrial data sequence is generated.

[0033] Furthermore, the process of analyzing time-dimensional industrial data sequences to obtain abnormal industrial data includes:

[0034] The time-dimensional modal industrial data sequence is processed to obtain time-based industrial data values. A threshold for time-based industrial data values ​​is set, and abnormal industrial data is obtained through the time-based industrial data value threshold.

[0035] Furthermore, the system includes the following modules:

[0036] Multi-core grouping module: used to set up multi-modal acquisition, obtain the modal multi-core requirement value of multi-modal acquisition, and then group the multi-core processors according to the analysis of the modal multi-core requirement value to obtain multi-core processing units;

[0037] Acquisition module: Used to set the multi-core allocation mechanism of the multi-core processing unit; to obtain multi-mode acquisition instructions, and based on the multi-core allocation mechanism, the multi-core processing unit acquires multi-mode industrial data through the multi-mode acquisition instructions;

[0038] Time alignment module: Performs time dimension alignment processing on multi-modal industrial data to obtain time dimension modal industrial data sequences;

[0039] Anomaly module: Used to analyze time-dimensional industrial data sequences and obtain abnormal industrial data.

[0040] Compared with the prior art, the beneficial effects of the present invention are as follows: The present invention sets up a multi-modal acquisition mode to obtain the multi-core requirement value of the multi-modal acquisition mode; then, based on the analysis of the multi-core requirement value, the multi-core processor is grouped to obtain multi-core processing units; and a multi-core allocation mechanism for the multi-core processing units is set up; multi-modal acquisition instructions are obtained, and based on the multi-core allocation mechanism, the multi-core processing units acquire multi-modal industrial data through the multi-modal acquisition instructions; the multi-modal industrial data is time-dimensional aligned to obtain a time-dimensional modal industrial data sequence; and then the time-dimensional model industrial data sequence is analyzed to obtain abnormal industrial data; thus effectively improving the multi-core allocation capability of the multi-core processor for the acquisition of multi-modal industrial data. Attached Figure Description

[0041] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0042] Figure 1 This is a flowchart of a multi-mode industrial data acquisition method based on a multi-core processor according to the present invention.

[0043] Figure 2 This is a schematic diagram of a multi-mode industrial data acquisition system based on a multi-core processor according to the present invention. Detailed Implementation

[0044] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0045] Please see Figure 1 As shown, a multi-mode industrial data acquisition method based on a multi-core processor includes the following steps:

[0046] Step S1: Set up multi-modal acquisition and obtain the modal multi-core requirement value of multi-modal acquisition; then, based on the analysis of the modal multi-core requirement value, group the multi-core processors to obtain multi-core processing units;

[0047] Step S2: Set up the multi-core allocation mechanism for the multi-core processing unit; obtain multi-mode acquisition instructions, and based on the multi-core allocation mechanism, the multi-core processing unit acquires multi-modal industrial data through the multi-mode acquisition instructions;

[0048] Step S3: Perform time dimension alignment processing on the multi-modal industrial data to obtain the time dimension modal industrial data sequence;

[0049] Step S4: Analyze the industrial data sequence of the time dimension model to obtain abnormal industrial data.

[0050] Step S1 needs further clarification; the process for acquiring multimodal data includes:

[0051] Acquire the equipment production dataset for each industrial device and map it to the corresponding industrial device; set up multimodal acquisition and perform multimodal classification on the equipment production data in the equipment production dataset to obtain the equipment multimodal data pool;

[0052] Set production monitoring data standards, identify equipment production data in the equipment multi-mode data pool according to the production monitoring data standards and mark them as production data to be monitored, and then obtain the collection multi-modality of the equipment multi-mode data pool corresponding to the production data to be monitored;

[0053] In the above embodiments, it should be further explained that the equipment production dataset is used to represent the collection of all equipment production data that industrial equipment can generate; the acquisition multimodal data includes, but is not limited to, data volume, state quantity, frequency quantity, signal quantity, etc.; for example, the analog quantity is used to represent continuously changing data volume, including but not limited to current quantity, voltage quantity, temperature quantity, etc.; the state quantity is used to represent the equipment operating status, including but not limited to start / stop status, valve opening / closing status, fault presence / absence status, etc.; the frequency quantity is used to represent the rate of change of physical quantities, including but not limited to motor speed, signal frequency, vibration frequency, etc.; the signal quantity is used to represent the transmission of control signals or alarm information, including but not limited to control command signals, alarm trigger signals, linkage feedback signals, etc.; therefore, each industrial equipment includes multiple equipment multimodal data pools, and the equipment production data included in the same equipment multimodal data pool of the same or different industrial equipment may also be different; the production monitoring data standard is used to represent the data that needs to be monitored.

[0054] The process of obtaining the modal multi-core requirement value for multimodal acquisition includes:

[0055] Acquire the same multimodal production data to be monitored, and denot it as modal production data to be monitored; schedule the industrial equipment that collects the modal production data to be monitored, and denot it as modal industrial equipment; then obtain the quantity of modal production data to be monitored corresponding to the modal industrial equipment, and denot it as modal equipment data volume; connect the modal industrial equipment in pairs by geographical location to obtain the modal connection distance; and obtain the industrial process anomaly impact level coefficient of the modal industrial equipment connected by the modal connection distance.

[0056] The modal coordinates of the modal industrial equipment are formed by combining the modal equipment data volume and the industrial process anomaly impact level coefficient, denoted as (m). i k i ), where m represents the data volume of the modal device, k represents the industrial process abnormality impact level coefficient, and i represents the number of the modal industrial device; and m, k, and i are all natural numbers greater than 0;

[0057] The distance between two modal coordinates connected by the two coordinate points is obtained by using the distance formula between the two coordinate points, and is recorded as the modal coordinate data. The product of the modal coordinate data and the corresponding modal connection distance is obtained, and then the average value of the sum of the products of the two modal coordinates connected by all modal connection distances in the multimodal acquisition is obtained, which is recorded as the modal multi-core requirement value of the multimodal acquisition.

[0058] In the above embodiments, it should be further noted that the modal device data volume and the industrial process abnormality impact level coefficient of the modal coordinates are both dimensionless; therefore, the modal coordinate data is a dimensionless comprehensive difference value, which is only used for horizontal comparison of the degree of difference between different equipment pairs under the same mode; that is, the unit of the average of the sum of the products of the connection distances of all modal connections is meters; for example, if the modal coordinates are (31, 51) and (22, 42), then the modal coordinate data of equipment 1 and equipment 2 is 1.41, the corresponding modal connection distance is 2 meters, and the product is 2.82; if all products are 2.82, 1.23, and 5.23, then the corresponding average value is 3.03 meters.

[0059] The process of grouping multi-core processors to obtain multi-core processing units based on the analysis of modal multi-core requirements includes:

[0060] Set the unit modal multicore demand value, obtain the ratio of the modal multicore demand value to the unit modal multicore demand value and round it up as the demand coefficient, set the number of cores per unit corresponding to the unit modal multicore demand value; obtain the demand cores of the demand coefficient through the number of cores per unit; allocate the corresponding number of multicores to the demand cores according to the modal multicore demand values ​​from large to small;

[0061] If the number of allocated multi-cores is insufficient, the corresponding acquisition multi-modal will be placed in the waiting area to wait for the generation of waiting acquisition multi-modal; otherwise, no processing will be performed.

[0062] The number of cores is integrated to form a multi-core processing unit, and the multi-core processing units are connected through a preset transmission channel.

[0063] In the above embodiments, it should be further explained that the specific multi-core requirement value of the unit modality is set according to the actual situation; the core number requirement is quantified by the requirement coefficient = modality requirement value / unit requirement value and rounded up to avoid insufficient resources; the core number is then allocated in descending order of modality requirement value to prioritize high-demand modes, such as analog quantities, and improve resource utilization; the core number is allocated in descending order of modality multi-core requirement value because the requirement value directly quantifies the resource demand intensity of the mode - the higher the value, the higher the amount of data to be monitored, the complexity of equipment coordination, and the weight of fault impact, and the more urgent the demand for multi-core computing power and parallel processing capabilities.

[0064] Step S2 requires further clarification. The process of setting up the multi-core allocation mechanism for multi-core processing units includes:

[0065] Obtain the maximum and minimum values ​​of modal connectivity distances and form a modal connectivity distance region for acquiring multimodal data; distribute the modal connectivity distance region equally according to the number of multi-cores; obtain the corresponding number of unit modal connectivity distance threshold ranges for modal connectivity distances.

[0066] Arbitrarily select one modal industrial device for multimodal data collection as the starting modal industrial device, obtain the maximum modal connection distance connected to the starting modal industrial device, and record it as the maximum modal connection distance. Then extract the starting modal industrial device and the modal industrial devices connected by the maximum modal connection distance, and integrate them to generate the extracted modal industrial device set. In this way, arbitrarily select another modal industrial device as the starting modal industrial device, obtain the maximum modal connection distance corresponding to the starting modal industrial device, and then obtain the extracted modal industrial device set.

[0067] The maximum modal connection distances are distributed within the corresponding unit modal connection distance threshold range to obtain the corresponding set of extracted modal industrial equipment, and then the number of modal industrial equipment corresponding to the unit modal connection distance threshold range is obtained.

[0068] Set a threshold for the number of modal industrial devices processed by a single core, obtain the ratio of the number of modal industrial devices to the threshold for the number of modal industrial devices, and take the value upwards as the number of allocated cores corresponding to the threshold range of unit modal connection distance;

[0069] The number of cores in the multi-core processing unit is allocated to the corresponding unit modal connection distance threshold range through the allocation number of cores. The remaining number of cores in the multi-core processing unit is sent to the waiting area to generate the number of cores to be allocated. Then, if the number of cores to be allocated in the waiting area is equal to the number of cores required for the waiting multi-modal acquisition, the number of cores to be allocated is allocated to the waiting multi-modal acquisition multi-core construction multi-core allocation mechanism with the corresponding number of cores required.

[0070] In the above embodiments, it should be further explained that the number of unit modal connection distance threshold ranges corresponding to the number of cores does not necessarily all have the maximum modal connection distance. Therefore, the allocation of the number of cores for the unit modal connection distance threshold range is not a one-to-one allocation. A maximum number of modal industrial devices that a single core can process is set, thereby obtaining the number of cores required for the number of modal industrial devices existing in the unit modal connection distance threshold range; to prevent the waste of cores for the unit modal connection distance threshold range.

[0071] The process of acquiring multi-modal acquisition instructions, and the multi-core processing unit acquiring multi-modal industrial data through multi-modal acquisition instructions based on the multi-core allocation mechanism, includes:

[0072] The multi-mode acquisition command includes at least the acquisition period and the acquisition frequency;

[0073] Based on the multi-core allocation mechanism, the multi-core processing unit allocates the number of multi-cores to the unit modal connection distance threshold range corresponding to the multi-modal acquisition, obtains the industrial equipment of each modality within the unit modal connection distance threshold range, and collects the industrial production data of the corresponding modal industrial equipment to be monitored through the corresponding multi-modal acquisition command, and associates it with the corresponding modal industrial equipment.

[0074] The system integrates all industrial production data from the multi-core processing unit to generate multi-modal industrial data corresponding to the collected multi-modal data.

[0075] In the above embodiments, it should be further explained that the multi-mode acquisition instruction is used to represent the acquisition cycle, acquisition frequency, acquisition timestamp, etc. of the modal industrial equipment; the modal connection distance is partitioned and the number of cores is dynamically allocated. Combined with the threshold of the number of single-core processing devices, the waste of core resources is avoided, and the remaining cores are transferred to the waiting area to maximize the multi-core utilization.

[0076] Step S3 requires further clarification. The process of aligning multi-modal industrial data along the time dimension to obtain a time-dimension modal industrial data sequence includes:

[0077] By merging industrial production data from the same collection time point in multi-modal industrial data, a corresponding time-dimensional modal industrial data sequence is generated.

[0078] In the above embodiments, it should be further explained that the time point is used to obtain the corresponding time point according to the acquisition cycle of the multi-mode acquisition command.

[0079] Step S4 requires further clarification. The process of analyzing the time-dimensional model of industrial data sequences to obtain abnormal industrial data includes:

[0080] The time-dimensional modal industrial data sequence is processed to obtain time-based industrial data values. A threshold for time-based industrial data values ​​is set, and abnormal industrial data is obtained through the time-based industrial data value threshold.

[0081] In the above embodiments, it should be further explained that the processing of the time-dimensional modal industrial data sequence to obtain the time industrial data value includes, but is not limited to, the instantaneous value direct extraction method, the sliding window statistical value calculation method, the time series difference change rate calculation method, etc.; abnormal industrial data is obtained by comparing the time industrial data value with the time industrial data value threshold.

[0082] Please see Figure 2 As shown, the present invention also provides a multi-mode industrial data acquisition system based on a multi-core processor, the system comprising the following modules:

[0083] Multi-core grouping module: used to set up multi-modal acquisition, obtain the modal multi-core requirement value of multi-modal acquisition, and then group the multi-core processors according to the analysis of the modal multi-core requirement value to obtain multi-core processing units;

[0084] Acquisition module: Used to set the multi-core allocation mechanism of the multi-core processing unit; to obtain multi-mode acquisition instructions, and based on the multi-core allocation mechanism, the multi-core processing unit acquires multi-mode industrial data through the multi-mode acquisition instructions;

[0085] Time alignment module: Performs time dimension alignment processing on multi-modal industrial data to obtain time dimension modal industrial data sequences;

[0086] Anomaly module: Used to analyze time-dimension model industrial data sequences and obtain abnormal industrial data.

[0087] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A multi-core processor based multi-modal industrial data acquisition method, characterized in that, The method includes the following steps: Step S1: Set up multi-modal acquisition and obtain the modal multi-core requirement value of multi-modal acquisition; then, based on the analysis of the modal multi-core requirement value, group the multi-core processors to obtain multi-core processing units; Step S2: Set up the multi-core allocation mechanism for the multi-core processing unit; obtain multi-mode acquisition instructions, and based on the multi-core allocation mechanism, the multi-core processing unit acquires multi-modal industrial data through the multi-mode acquisition instructions; Step S3: Perform time dimension alignment processing on the multi-modal industrial data to obtain the time dimension modal industrial data sequence; Step S4: Analyze the industrial data sequence of the time dimension model to obtain abnormal industrial data; The process of obtaining the modal multi-kernel requirement values ​​for multimodal acquisition includes: Acquire the same multimodal production data to be monitored, and denot it as modal production data to be monitored; schedule the industrial equipment that collects the modal production data to be monitored, and denot it as modal industrial equipment; then obtain the quantity of modal production data to be monitored corresponding to the modal industrial equipment, and denot it as modal equipment data volume; connect the modal industrial equipment in pairs by geographical location to obtain the modal connection distance; and obtain the industrial process anomaly impact level coefficient of the modal industrial equipment connected by the modal connection distance. Modal coordinates of modal industrial equipment are formed by combining the modal equipment data volume and the industrial process anomaly impact level coefficient. The process of grouping multi-core processors to obtain multi-core processing units based on the analysis of modal multi-core requirements includes: Set the unit modal multicore demand value, obtain the ratio of the modal multicore demand value to the unit modal multicore demand value and round it up as the demand coefficient, set the number of cores per unit corresponding to the unit modal multicore demand value; obtain the demand cores of the demand coefficient through the number of cores per unit; allocate the corresponding number of multicores to the demand cores according to the modal multicore demand values ​​from large to small; If the number of allocated multi-cores is insufficient, the corresponding acquisition multi-modal will be placed in the waiting area to wait for the generation of waiting acquisition multi-modal; otherwise, no processing will be performed. The number of cores is integrated to generate a multi-core processing unit, and the multi-core processing units are connected through a preset transmission channel; The process of setting up a multi-core allocation mechanism for a multi-core processing unit includes: Obtain the maximum and minimum values ​​of modal connectivity distances and form a modal connectivity distance region for acquiring multimodal data; distribute the modal connectivity distance region equally according to the number of multi-cores; obtain the corresponding number of unit modal connectivity distance threshold ranges for modal connectivity distances. Arbitrarily select one modal industrial device for multimodal data acquisition as the starting modal industrial device, obtain the maximum modal connection distance connected to the starting modal industrial device, and record it as the maximum modal connection distance. Then extract the starting modal industrial device and the modal industrial devices connected by the maximum modal connection distance, and integrate them to generate the extracted modal industrial device set. In this way, arbitrarily select one of the remaining modal industrial devices as the starting modal industrial device, obtain the maximum modal connection distance corresponding to the starting modal industrial device, and then obtain the extracted modal industrial device set. The maximum modal connection distances are distributed within the corresponding unit modal connection distance threshold range to obtain the corresponding set of extracted modal industrial equipment, and then the number of modal industrial equipment corresponding to the unit modal connection distance threshold range is obtained. Set a threshold for the number of modal industrial devices processed by a single core, obtain the ratio of the number of modal industrial devices to the threshold for the number of modal industrial devices, and take the value upwards as the number of allocated cores corresponding to the threshold range of unit modal connection distance; The number of cores in the multi-core processing unit is allocated to the corresponding unit modal connection distance threshold range through the allocation number of cores. The remaining number of cores in the multi-core processing unit is sent to the waiting area to generate the number of cores to be allocated. Then, if the number of cores to be allocated in the waiting area is equal to the number of cores required for the waiting multi-modal acquisition, the number of cores to be allocated is allocated to the waiting multi-modal acquisition multi-core construction multi-core allocation mechanism with the corresponding number of cores required.

2. The multi-core processor based multi-modal industrial data acquisition method according to claim 1, wherein, The process of setting up multimodal data acquisition includes: Acquire the equipment production dataset for each industrial device and map it to the corresponding industrial device; set up multimodal acquisition and perform multimodal classification on the equipment production data in the equipment production dataset to obtain the equipment multimodal data pool; Set production monitoring data standards, identify equipment production data in the equipment multi-mode data pool according to the production monitoring data standards and mark them as production data to be monitored, and then obtain the collection multi-modal of the equipment multi-mode data pool corresponding to the production data to be monitored.

3. The multi-mode industrial data acquisition method based on a multi-core processor according to claim 1, characterized in that, The process of acquiring multi-modal industrial data by the multi-core processing unit based on the multi-core allocation mechanism through the multi-modal acquisition command includes: The multi-mode acquisition command includes at least the acquisition period and the acquisition frequency; Based on the multi-core allocation mechanism, the multi-core processing unit allocates the number of multi-cores to the unit modal connection distance threshold range corresponding to the multi-modal acquisition, obtains the industrial equipment of each modality within the unit modal connection distance threshold range, and collects the industrial production data of the corresponding modal industrial equipment to be monitored through the corresponding multi-modal acquisition command, and associates it with the corresponding modal industrial equipment. The system integrates all industrial production data from the multi-core processing unit to generate multi-modal industrial data corresponding to the collected multi-modal data.

4. The multi-mode industrial data acquisition method based on a multi-core processor according to claim 3, characterized in that, The process of aligning multi-modal industrial data to obtain time-dimension modal industrial data sequences includes: By merging industrial production data from the same collection time point in multi-modal industrial data, a corresponding time-dimensional modal industrial data sequence is generated.

5. The multi-mode industrial data acquisition method based on a multi-core processor according to claim 4, characterized in that, The process of analyzing time-dimensional industrial data sequences to obtain anomalous industrial data includes: The time-dimensional modal industrial data sequence is processed to obtain time-based industrial data values. A threshold for time-based industrial data values ​​is set, and abnormal industrial data is obtained through the time-based industrial data value threshold.

6. A multi-mode industrial data acquisition system based on a multi-core processor, used to implement the multi-mode industrial data acquisition method based on a multi-core processor as described in any one of claims 1-5, characterized in that, The system includes the following modules: Multi-core grouping module: used to set up multi-modal acquisition, obtain the modal multi-core requirement value of multi-modal acquisition, and then group the multi-core processors according to the analysis of the modal multi-core requirement value to obtain multi-core processing units; Acquisition module: Used to set the multi-core allocation mechanism of the multi-core processing unit; to obtain multi-mode acquisition instructions, and based on the multi-core allocation mechanism, the multi-core processing unit acquires multi-mode industrial data through the multi-mode acquisition instructions; Time alignment module: Performs time dimension alignment processing on multi-modal industrial data to obtain time dimension modal industrial data sequences; Anomaly module: Used to analyze time-dimensional industrial data sequences and obtain abnormal industrial data.

Images