Industrial big data intelligent analysis method and system based on cloud computing

Abstract

The invention belongs to the field of industrial big data, relates to a data analysis technology, is used for solving the problem that in the prior art, targeted acquisition network construction cannot be carried out on different types of industrial workshops, and particularly relates to an industrial big data intelligent analysis method and system based on cloud computing, and the system comprises an acquisition end, a processing end and an analysis end. The acquisition end comprises an acquisition network building module and a data acquisition server, the processing end comprises a data preprocessing module and a cloud computing performance detection module, and the analysis end comprises a cloud computing performance evaluation module and an optimization analysis module; according to the invention, acquisition network establishment is carried out on an industrial system, statistics is carried out on various data acquisition tendency parameters of production workshops, and targeted acquisition network establishment is carried out on each production workshop in combination with the data acquisition tendency parameters of all the production workshops. And the production workshops with different data acquisition tendentiousness can establish acquisition networks matched with the requirements of the production workshops, so that the data acquisition and transmission efficiency is improved.

Description

Technical Field

[0001] The present invention belongs to the field of industrial big data, relates to data analysis technology, and specifically is an intelligent analysis method and system for industrial big data based on cloud computing. Background Art

[0002] Industrial big data refers to all kinds of data, related technologies and applications generated in various links of the entire product life cycle from customer needs to sales, orders, plans, R & D, design, manufacturing, procurement, supply, inventory, shipping and delivery, after-sales service, operation and maintenance, scrapping and recycling and remanufacturing in the industrial field around the intelligent manufacturing model.

[0003] For example, the invention patent with the publication number CN118626555A discloses an industrial big data analysis method based on Spark. It adopts a distributed storage method. On the basis of ensuring high reliability and high availability of data, by utilizing the parallel computing and in-memory computing advantages of Spark, it significantly improves the speed and efficiency of data processing; However, this industrial big data analysis method cannot build a targeted acquisition network for different types of industrial workshops, resulting in a low matching degree between the data acquisition and transmission method and the workshop type and function, and low data acquisition and transmission efficiency. At the same time, it cannot evaluate and optimize the computing performance of the cloud computing platform, resulting in the inability to improve the cloud computing performance. Summary of the Invention

[0004] The purpose of the present invention is to provide an intelligent analysis method and system for industrial big data based on cloud computing, which is used to solve the problem in the prior art that a targeted acquisition network cannot be built for different types of industrial workshops.

[0005] The technical problem that the present invention needs to solve is: how to provide an intelligent analysis method and system for industrial big data based on cloud computing that can build a targeted acquisition network for different types of industrial workshops.

[0006] The purpose of the present invention can be achieved through the following technical solutions: An intelligent analysis system for industrial big data based on cloud computing includes a collection end, a processing end, and an analysis end. The collection end includes an acquisition network building module and a data collection server. The processing end includes a data preprocessing module and a cloud computing performance detection module. The analysis end includes a cloud computing performance evaluation module and an optimization analysis module; The acquisition network building module is used to build an acquisition network for the industrial system: mark the production workshop of the industrial system as the analysis object, obtain the real-time demand value, equipment type value, and acquisition accuracy value of the analysis object, and build a sensor acquisition network, a communication gateway acquisition network, and an interconnected communication acquisition network for the analysis object according to the real-time demand value, equipment type value, and acquisition accuracy value; The data acquisition server is used to receive the industrial monitoring data of the acquisition network and send it to the processing end; The data preprocessing module is used to preprocess the industrial monitoring data: the preprocessing process includes data cleaning, data integration, and data transformation, data cleaning; The cloud computing performance detection module is used to perform performance detection and analysis on the cloud computing platform: generate an analysis period, set a number of detection time points with equal time intervals within the analysis period, obtain the occupancy data ZY, response data XY, and throughput data TT of the cloud computing platform at the detection time points, and perform numerical calculations to obtain the performance coefficient XN of the cloud computing platform, and send the performance coefficient XN of the cloud computing platform to the analysis end; The cloud computing performance evaluation module is used to perform performance evaluation and analysis on the cloud computing platform; The optimization analysis module is used to perform optimization analysis on the cloud computing platform.

[0007] Further, the specific process of building an acquisition network for the analysis object includes: arranging all the analysis objects in ascending order of the real-time demand value to obtain a real-time demand sequence, arranging all the analysis objects in descending order of the device type value to obtain a device type sequence, and arranging all the analysis objects in ascending order of the acquisition accuracy value to obtain an acquisition accuracy sequence; marking the serial numbers of the analysis objects in the real-time demand sequence, device type sequence, and acquisition accuracy sequence as the real-time priority value, device priority value, and accuracy priority value respectively, marking the sequence corresponding to the minimum value among the real-time priority value, device priority value, and accuracy priority value of the analysis object as the building sequence, and marking the acquisition network building type of the analysis object according to the building sequence.

[0008] Further, the specific process of marking the acquisition network building type of the analysis object includes: if the building sequence is the real-time demand sequence, build a network communication acquisition network for the analysis object; if the building sequence is the device type sequence, build a communication gateway acquisition network for the analysis object; if the building sequence is the acquisition accuracy sequence, build a sensor acquisition network for the analysis object; when there are equal values among the real-time priority value, device priority value, and accuracy priority value, the building priority order of the acquisition network is sensor acquisition network - communication gateway acquisition network - network communication acquisition network from first to last.

[0009] Further, the occupancy data ZY is the CPU occupancy rate of the cloud computing platform, the response data XY is the time from the request sent to the cloud computing platform to the result return, and the throughput data TT is the number of tasks completed by the cloud computing platform per unit time.

[0010] Further, the specific process of the cloud computing performance evaluation module for performing performance evaluation and analysis on the cloud computing platform includes: numerically calculating the performance coefficient XN at all detection time points at the end of the analysis period to obtain a performance evaluation value, and comparing the performance evaluation value with a preset performance evaluation threshold: if the performance evaluation value is greater than the performance evaluation threshold, it is determined that the computing performance of the cloud computing platform within the analysis period meets the requirements; if the performance evaluation value is less than or equal to the performance evaluation threshold, it is determined that the computing performance of the cloud computing platform within the analysis period does not meet the requirements, generating an optimization analysis signal and sending the optimization analysis signal to the optimization analysis module.

[0011] Further, the specific process of the optimization analysis module for performing optimization analysis on the cloud computing platform includes: marking the M1 detection time points with the largest numerical values of the performance coefficient XN as analysis time points, marking the analysis objects corresponding to the data calculation tasks processed by the cloud computing platform at the analysis time points as optimization objects, marking the number of times the analysis objects are marked as optimization objects as the optimization values of the analysis objects, calculating the variance of the optimization values of all analysis objects to obtain a performance optimization coefficient, and marking the computing performance optimization decision of the cloud computing platform through the performance optimization coefficient.

[0012] Further, the specific process of marking the computing performance optimization decision of the cloud computing platform includes: comparing the performance optimization coefficient with a preset performance optimization threshold: if the performance optimization coefficient is less than the performance optimization threshold, generating a hardware optimization signal and sending the hardware optimization signal to the mobile terminal of the management personnel; if the performance optimization coefficient is greater than or equal to the performance optimization threshold, marking the M2 analysis objects with the largest optimization values as update objects, generating a collection update signal and sending the collection update signal to the mobile terminal of the management personnel, and after receiving the collection update signal, the management personnel update the collection parameters, collection methods, and data transmission methods within the update objects.

[0013] The present invention also proposes an industrial big data intelligent analysis method based on cloud computing, including the following steps: Step 1: Build a collection network for the industrial system; Step 2: Receive the industrial monitoring data of the collection network through a data collection server and send it to the processing end; Step 3: Preprocess the industrial monitoring data; Step 4: Perform performance detection and analysis on the cloud computing platform; Step 5: Perform performance evaluation and analysis on the cloud computing platform, and execute Step 6 when the computing performance does not meet the requirements; Step 6: Perform optimization analysis on the cloud computing platform.

[0014] The present invention has the following beneficial effects: The acquisition network construction module can build an acquisition network for the industrial system, count the data acquisition tendency parameters of each production workshop, and then build a targeted acquisition network for each production workshop by combining the data acquisition tendency parameters of all production workshops. Production workshops with different data acquisition tendencies can all build acquisition networks that match their needs, improving the efficiency of data acquisition and transmission; The cloud computing performance detection module can perform performance detection and analysis on the cloud computing platform, count and calculate various computing performance parameters of the cloud computing platform to obtain a performance coefficient, and feedback the quality of the computing performance of the cloud computing platform according to the performance coefficient. Combine the performance evaluation module to evaluate its computing performance and perform optimization analysis when necessary; The optimization analysis module can perform optimization analysis on the cloud computing platform, screen the optimization objects according to the performance coefficient, then calculate the optimization values of all optimization objects to obtain a performance optimization coefficient, and mark the optimization decision of the cloud computing platform through the performance optimization coefficient, improving the optimization efficiency of the computing performance of the cloud computing platform. Brief Description of the Drawings

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0016] Figure 1 It is the system block diagram of Embodiment 1 of the present invention; Figure 2 It is the acquisition and transmission schematic diagram of industrial big data in Embodiment 1 of the present invention; Figure 3 It is the method flowchart of Embodiment 2 of the present invention. Detailed Embodiments

[0017] The following will clearly and completely describe the technical solutions of the present invention in combination with the embodiments. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0018] Embodiment 1: As Figure 1As shown, the industrial big data intelligent analysis system based on cloud computing includes a collection end, a processing end, and an analysis end. The collection end includes a collection network construction module and a data collection server. The processing end includes a data preprocessing module and a cloud computing performance detection module. The analysis end includes a cloud computing performance evaluation module and an optimization analysis module.

[0019] The collection network construction module is used to construct a collection network for the industrial system: mark the production workshop of the industrial system as the analysis object, obtain the real-time demand value, equipment type value, and collection accuracy value of the analysis object. The real-time demand value of the analysis object is the minimum value of the transmission delay requirements of all equipment collection parameters in the analysis object. The equipment type value of the analysis object is the number value of all equipment types in the analysis object. The collection accuracy value of the analysis object is the minimum value of the collection accuracy requirements of all equipment collection parameters in the analysis object; Arrange all the analysis objects in ascending order of the real-time demand value to obtain a real-time demand sequence, arrange all the analysis objects in descending order of the equipment type value to obtain an equipment type sequence, and arrange all the analysis objects in ascending order of the collection accuracy value to obtain a collection accuracy sequence; mark the serial numbers of the analysis objects in the real-time demand sequence, equipment type sequence, and collection accuracy sequence as the real-time priority value, equipment priority value, and accuracy priority value respectively, and mark the sequence corresponding to the minimum value among the real-time priority value, equipment priority value, and accuracy priority value of the analysis object as the construction sequence.

[0020] If the construction sequence is the real-time demand sequence, construct a network communication collection network for the analysis object; if the construction sequence is the equipment type sequence, construct a communication gateway collection network for the analysis object; if the construction sequence is the collection accuracy sequence, construct a sensor collection network for the analysis object; When there are cases where the real-time priority value, equipment priority value, and accuracy priority value are the same, the construction priority of the collection network is in the order from the later to the earlier: sensor collection network - communication gateway collection network - network communication collection network; count the data collection tendency parameters of each production workshop, and then construct a targeted collection network for each production workshop in combination with the data collection tendency parameters of all production workshops. Production workshops with different data collection tendencies can all construct a collection network that matches their needs, improving the efficiency of data collection and transmission.

[0021] Such as Figure 2As shown in the figure, the data acquisition server is used to receive the industrial monitoring data of the acquisition network and send it to the processing end: when the acquisition network of the analysis object is a networked communication acquisition network, the data acquisition server directly acquires and forwards the industrial monitoring data through Ethernet or serial communication; when the acquisition network of the analysis object is a communication gateway acquisition network, the industrial communication gateway performs message conversion between various network protocols, converts different types of device communication protocols into a standard protocol, and the data acquisition server directly acquires and forwards the industrial monitoring data through the industrial communication gateway; when the acquisition network of the analysis object is a sensor acquisition network, the sensor measures and acquires various physical quantities and converts them into electrical signals, and the data acquisition server directly acquires and forwards the industrial monitoring data through wireless communication.

[0022] The data preprocessing module is used to preprocess the industrial monitoring data: the preprocessing process includes data cleaning, data integration, and data transformation. Data cleaning: includes handling missing values and smoothing noisy data. Methods for handling missing values include ignoring, manual filling, using global variables or average values for filling; smoothing noisy data can use methods such as binning, clustering, and regression. Data integration: integrates the data from multiple data sources into a consistent storage to solve data inconsistency and redundancy problems. Data transformation: normalizes the data, eliminates redundant attributes, and projects the data into a smaller subspace for more efficient processing and analysis.

[0023] The cloud computing performance detection module is used to perform performance detection and analysis on the cloud computing platform: generate an analysis period, set several detection time points with equal time intervals within the analysis period, and obtain the occupancy data ZY, response data XY, and throughput data TT of the cloud computing platform at the detection time points. The occupancy data ZY is the CPU occupancy rate of the cloud computing platform, the response data XY is the time from the request sent to the cloud computing platform to the result return, and the throughput data TT is the number of tasks completed by the cloud computing platform per unit time; obtain the performance coefficient XN of the cloud computing platform through the formula XN = w1×TT - w2×ZY - w3×XY, where w1, w2, and w3 are all proportionality coefficients, and w1 > w2 > w3 > 1; send the performance coefficient XN of the cloud computing platform to the analysis end.

[0024] The cloud computing performance evaluation module is used to evaluate and analyze the performance of the cloud computing platform: at the end of the analysis period, the performance evaluation value is obtained by numerically calculating the performance coefficients XN at all detection time points, and the performance evaluation value is compared with the preset performance evaluation threshold: if the performance evaluation value is greater than the performance evaluation threshold, it is determined that the computing performance of the cloud computing platform meets the requirements during the analysis period; if the performance evaluation value is less than or equal to the performance evaluation threshold, it is determined that the computing performance of the cloud computing platform does not meet the requirements, an optimization analysis signal is generated and sent to the optimization analysis module; the computing performance parameters of the cloud computing platform are statistically calculated to obtain performance coefficients, and the computing performance of the cloud computing platform is fed back according to the performance coefficients, and its computing performance is evaluated in combination with the performance evaluation module, and optimization analysis is carried out when necessary.

[0025] The optimization analysis module is used to optimize and analyze the cloud computing platform: the M1 detection time points with the largest numerical values of the performance coefficient XN are marked as analysis time points, the analysis objects corresponding to the data processing and calculation tasks of the cloud computing platform at the analysis time points are marked as optimization objects, the number of times the analysis objects are marked as optimization objects is marked as the optimization value of the analysis objects, the variance of the optimization values of all analysis objects is calculated to obtain the performance optimization coefficient, and the performance optimization coefficient is compared with the preset performance optimization threshold: if the performance optimization coefficient is less than the performance optimization threshold, a hardware optimization signal is generated and sent to the mobile terminal of the management personnel; if the performance optimization coefficient is greater than or equal to the performance optimization threshold, the M2 analysis objects with the largest optimization value are marked as update objects, a collection update signal is generated and sent to the mobile terminal of the management personnel, and after receiving the collection update signal, the management personnel update the collection parameters, collection methods and data transmission methods in the update objects; the optimization objects are screened according to the performance coefficients, and then the optimization values of all optimization objects are calculated to obtain the performance optimization coefficient, and the optimization decision of the cloud computing platform is marked through the performance optimization coefficient to improve the optimization efficiency of the computing performance of the cloud computing platform.

[0026] Embodiment 2: As Figure 3 shown, the present invention also proposes an industrial big data intelligent analysis method based on cloud computing, including the following steps: Step 1: Build a collection network for the industrial system: Build a sensor collection network, a communication gateway collection network and an interconnected communication collection network for the analysis object according to the real-time demand value, the device type value and the collection accuracy value. Step 2: Receive the industrial monitoring data of the collection network through the data collection server and send it to the processing end. Step 3: Preprocess the industrial monitoring data: The preprocessing process includes data cleaning, data integration and data transformation. Step 4: Perform performance detection and analysis on the cloud computing platform: Generate an analysis period, set several detection time points with equal time intervals within the analysis period, and obtain the performance coefficient XN of the cloud computing platform at the detection time points. Step 5: Perform performance evaluation and analysis on the cloud computing platform, and execute Step 6 when the computing performance does not meet the requirements. Step 6: Perform optimization analysis on the cloud computing platform.

[0027] When the present invention is in operation, a sensor acquisition network, a communication gateway acquisition network, and an Internet communication acquisition network are built with the real-time demand value, the device type value, and the acquisition accuracy value as the analysis objects; the industrial monitoring data of the acquisition network is received by the data acquisition server and sent to the processing end; preprocessing is performed on the industrial monitoring data: the preprocessing process includes data cleaning, data integration, and data transformation; an analysis period is generated, several detection time points with equal time intervals are set within the analysis period, and the performance coefficient XN of the cloud computing platform is obtained at the detection time points; performance evaluation and analysis are performed on the cloud computing platform, and when the computing performance does not meet the requirements, optimization analysis is performed on the cloud computing platform.

[0028] The above content is only an example and explanation of the structure of the present invention. Those skilled in the art of the present technology make various modifications or supplements to the described specific embodiments or use similar methods for substitution, as long as they do not deviate from the structure of the invention or exceed the scope defined by this claim book, they should all fall within the protection scope of the present invention.

[0029] The above formulas are all obtained by collecting a large amount of data for software simulation and selecting a formula close to the true value. The coefficients in the formula are set by those skilled in the art according to the actual situation; for example: the formula XN = w1×TT - w2×ZY - w3×XY; those skilled in the art collect multiple groups of sample data and set corresponding performance optimization coefficients for each group of sample data; substitute the set performance optimization coefficients and the collected sample data into the formula, and any three formulas form a system of linear equations with three variables. Screen and take the average of the calculated coefficients to obtain the values of w1, w2, and w3 as 4.25, 2.84, and 2.33 respectively. The magnitude of the coefficient is a specific value obtained by quantifying each parameter for subsequent comparison. Regarding the magnitude of the coefficient, it depends on the amount of sample data and the preliminary setting of corresponding performance optimization coefficients for each group of sample data by those skilled in the art; as long as it does not affect the proportional relationship between the parameter and the quantified value, for example, the performance optimization coefficient is proportional to the value of the throughput data.

[0030] The preferred embodiments of the present invention disclosed above are only used to help illustrate the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only the specific embodiments. Obviously, according to the content of this specification, many modifications and variations can be made. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can well understand and utilize the present invention. The present invention is only limited by the claims and their full scope and equivalents.

Claims

1. An industrial big data intelligent analysis system based on cloud computing, characterized in that, It includes a collection end, a processing end, and an analysis end. The collection end includes a collection network construction module and a data collection server. The processing end includes a data preprocessing module and a cloud computing performance detection module. The analysis end includes a cloud computing performance evaluation module and an optimization analysis module; The collection network construction module marks the production workshop of the industrial system as the analysis object, obtains the real-time demand value, equipment type value, and collection accuracy value of the analysis object, and constructs a sensor collection network, a communication gateway collection network, and an interconnected communication collection network for the analysis object according to the real-time demand value, equipment type value, and collection accuracy value; The data collection server receives the industrial monitoring data of the collection network and sends it to the processing end; The data preprocessing module preprocesses the industrial monitoring data sent by the data collection server; The cloud computing performance detection module generates an analysis period, sets several detection time points with equal time intervals within the analysis period, obtains the occupancy data ZY, response data XY, and throughput data TT of the cloud computing platform at the detection time points, and performs numerical calculations to obtain the performance coefficient XN of the cloud computing platform, and sends the performance coefficient XN of the cloud computing platform to the analysis end; The cloud computing performance evaluation module performs performance evaluation and analysis on the cloud computing platform according to the performance coefficient XN of all detection time points; The optimization analysis module performs optimization analysis when the computing performance of the cloud computing platform does not meet the requirements.

2. The industrial big data intelligent analysis system based on cloud computing according to claim 1, characterized in that The specific process of constructing a collection network for the analysis object includes: arranging all the analysis objects in ascending order of the real-time demand value to obtain a real-time demand sequence, arranging all the analysis objects in descending order of the equipment type value to obtain an equipment type sequence, and arranging all the analysis objects in ascending order of the collection accuracy value to obtain a collection accuracy sequence; marking the serial numbers of the analysis objects in the real-time demand sequence, equipment type sequence, and collection accuracy sequence as the real-time priority value, equipment priority value, and accuracy priority value respectively, marking the sequence corresponding to the minimum value among the real-time priority value, equipment priority value, and accuracy priority value of the analysis object as the construction sequence, and marking the collection network construction type of the analysis object according to the construction sequence.

3. The industrial big data intelligent analysis system based on cloud computing according to claim 2, characterized in that, The specific process of marking the collection network construction type of the analysis object includes: if the construction sequence is the real-time demand sequence, construct an interconnected communication collection network for the analysis object; if the construction sequence is the equipment type sequence, construct a communication gateway collection network for the analysis object; if the construction sequence is the collection accuracy sequence, construct a sensor collection network for the analysis object; when there are cases where the real-time priority value, equipment priority value, and accuracy priority value are the same, the construction priority order of the collection network is sensor collection network - communication gateway collection network - interconnected communication collection network.

4. The industrial big data intelligent analysis system based on cloud computing according to claim 3, characterized in that The occupancy data ZY is the CPU occupancy rate of the cloud computing platform, the response data XY is the time from the request sent to the cloud computing platform to the result return, and the throughput data TT is the number of tasks completed by the cloud computing platform per unit time.

5. The industrial big data intelligent analysis system based on cloud computing according to claim 4, characterized in that, The specific process of the cloud computing performance evaluation module for performing performance evaluation and analysis on the cloud computing platform includes: numerically calculating the performance coefficient XN at all detection time points at the end of the analysis period to obtain the performance evaluation value, and comparing the performance evaluation value with a preset performance evaluation threshold: if the performance evaluation value is greater than the performance evaluation threshold, it is determined that the computing performance of the cloud computing platform meets the requirements during the analysis period; if the performance evaluation value is less than or equal to the performance evaluation threshold, it is determined that the computing performance of the cloud computing platform does not meet the requirements, generating an optimization analysis signal and sending the optimization analysis signal to the optimization analysis module.

6. The industrial big data intelligent analysis system based on cloud computing according to claim 5, characterized in that, The specific process of the optimization analysis module for performing optimization analysis on the cloud computing platform includes: marking the M1 detection time points with the largest numerical values of the performance coefficient XN as analysis time points, marking the analysis objects corresponding to the data processing calculation tasks of the cloud computing platform at the analysis time points as optimization objects, marking the number of times the analysis object is marked as an optimization object as the optimization value of the analysis object, calculating the variance of the optimization values of all analysis objects to obtain the performance optimization coefficient, and marking the computing performance optimization decision of the cloud computing platform through the performance optimization coefficient.

7. The industrial big data intelligent analysis system based on cloud computing according to claim 6, characterized in that The specific process of marking the computing performance optimization decision of the cloud computing platform includes: comparing the performance optimization coefficient with a preset performance optimization threshold: if the performance optimization coefficient is less than the performance optimization threshold, generating a hardware optimization signal and sending the hardware optimization signal to the mobile terminal of the management personnel; if the performance optimization coefficient is greater than or equal to the performance optimization threshold, marking the M2 analysis objects with the largest optimization value as update objects, generating a collection update signal and sending the collection update signal to the mobile terminal of the management personnel, and after receiving the collection update signal, the management personnel update the collection parameters, collection methods, and data transmission methods within the update objects.

8. An intelligent analysis method for industrial big data based on cloud computing, using the intelligent analysis system for industrial big data based on cloud computing as described in claim 1, characterized in that, It includes the following steps: Step 1: Build a collection network for the industrial system; Step 2: Receive the industrial monitoring data of the collection network through the data collection server and send it to the processing end; Step 3: Preprocess the industrial monitoring data; Step 4: Perform performance detection and analysis on the cloud computing platform; Step 5: Perform performance evaluation and analysis on the cloud computing platform, and execute Step 6 when the computing performance does not meet the requirements; Step 6: Perform optimization analysis on the cloud computing platform.

Images