Industrial internet data processing method based on big data

Abstract

The invention relates to an industrial internet data processing method based on big data, in particular to the technical field of industrial internet data processing, and adopts the scheme that a data collecting and processing module is used for monitoring and collecting equipment operation power G, an equipment load level FS, an equipment efficiency value XL, an equipment loss coefficient XH, an equipment maintenance index WH and an equipment operation state potential average value YXmax and avg; the operation adjustment and prediction module is used for sequentially calculating and outputting an equipment operation state evaluation value YX, an adjustment amount T and an equipment operation state prediction value YXfost, the measure formulating module is used for executing adjustment measures output by the adjustment amount T of industrial equipment, and the prediction analysis module is used for performing prediction analysis and improvement of the adjustment measures. According to the invention, through comprehensive evaluation of the equipment state, flexible detection of the abnormal state, scientific basis adjustment measures, a cyclic feedback optimization mechanism and application of a big data technology, a more intelligent and precise processing method is provided for management of industrial internet equipment.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of industrial internet data processing, and specifically relates to an industrial internet data processing method based on big data. BACKGROUND

[0002] Industrial internet is a new type of industrial production mode based on internet technology, which combines traditional industrial production systems with internet technology to realize the intelligentization, networking and informatization of industrial production systems. With the continuous development of industrial internet, the amount of data increases dramatically, which puts higher requirements on data processing capacity. In order to meet this demand, an industrial internet data processing method based on big data emerges as the times require. Big data technology has powerful data processing and analysis capabilities and can process and analyze massive, high-speed and diverse data. In the industrial internet, big data technology is widely used in equipment state monitoring, fault diagnosis and predictive maintenance fields. Through collecting and analyzing the data generated by equipment, big data technology can help more accurately understand the running state of industrial equipment and timely discover potential problems and take corresponding measures for prevention and maintenance.

[0003] In the field of industrial internet, the running state monitoring and optimization of industrial equipment are the key to ensuring production efficiency and reducing maintenance costs. However, existing technologies often only focus on single data indicators of equipment and ignore the correlation between data, which leads to incomplete evaluation of the state of industrial equipment and difficulty in accurately reflecting the real running condition of industrial equipment. In addition, when the performance of industrial equipment changes, fixed thresholds cannot accurately identify abnormal states, resulting in false positives and false negatives. Furthermore, the adjustment measures of existing industrial equipment lack scientific basis and cannot effectively improve the state of equipment. In addition, the effect of adjustment measures cannot be continuously tracked and optimized.

[0004] Therefore, the present application provides an industrial internet data processing method based on big data to solve the problems raised in the background. SUMMARY

[0005] The technical problem solved by the present application is to provide an industrial internet data processing method based on big data to realize comprehensive evaluation of the state of industrial equipment, flexible detection of abnormal states, scientific basis for adjustment measures, and intelligent adjustment purposes of improving production efficiency and reducing maintenance costs.

[0006] To solve the above problems, the present application provides the following technical solutions: An industrial internet data processing method based on big data, comprising a data collection and processing module, a running adjustment and prediction module, a measure development module and a cycle feedback and optimization module, characterized in that: The data collection processing module is configured to monitor and collect the device operating power G, the device load level FS, the device efficiency value XL, the device loss coefficient XH, the device maintenance index WH, and the potential average value YX of the device operating state of the industrial equipment in a current monitoring period, and transmit the data to the operation adjustment and prediction module. max,avg , and the reference interval {YX max -YX min}, and transmit the data to the operation adjustment and prediction module. The operation adjustment and prediction module comprises an operating state evaluation unit, an abnormal state adjustment amount output unit, and an adjustment prediction and feedback unit, and is configured to sequentially calculate and output the device operating state evaluation value YX, the adjustment amount T, and the device operating state prediction value YX fost . The measure development module is configured to output the adjustment measures of the industrial equipment according to the adjustment amount T. The prediction analysis module is configured to perform prediction analysis and improvement of the adjustment measures based on the prediction result of the device operating state prediction value YX fost .

[0007] Further, the calculation formula of the operating state evaluation unit is as follows: ; Wherein: YX is the device operating state evaluation value; G is the device operating power; G max is the maximum device operating power; FS is the device load level; XL is the device efficiency value; XH is the device loss coefficient; The square root operation has a nonlinear characteristic, which is used to amplify small differences and reduce large differences. In the device operating state evaluation, when the device operating power G is close to the maximum device operating power G max , even a slight change in power will have a great impact on the evaluation result, thereby emphasizing the efficient operation of the industrial equipment. The square root operation is used to comprehensively evaluate the operating burden and efficiency of the industrial equipment. The higher the YX value, the better the current operating state of the industrial equipment. The lower the YX value, the worse the current operating state of the industrial equipment.

[0008] Further: based on the calculation formula of the running state evaluation unit, and in the initial stage of the industrial equipment operation, the best and worst equipment operation power G, equipment load level FS, equipment efficiency value XL and equipment loss coefficient XH of each industrial equipment running state are respectively brought into the calculation formula, to obtain the maximum evaluation value YX max and the minimum evaluation value YX min of the equipment running state, and the interval of {YX max -YX min} is set as the reference interval of the industrial equipment running state.

[0009] Further: the calculation formula of the equipment load level FS, equipment efficiency value XL and equipment loss coefficient XH is as follows: FS=DF / F max ; XL=OUT / IN; XH=SN / KN; Wherein: DF is the current load value, F max is the maximum load value; OUT is the average output power of the equipment, and IN is the average input power of the equipment; SN is the used life, and KN is the total life.

[0010] Further: the calculation formula of the abnormal state adjustment amount output unit is as follows: ; WH=WC / WZ; Wherein: T is the adjustment amount; T is a positive value, indicating that the adjustment measures of increasing power and optimizing the industrial equipment need to be taken; T is a negative value, indicating that the adjustment measures of reducing load and maintaining the industrial equipment need to be taken; T is 0, indicating that the running state of the current industrial equipment is in an ideal state, and no additional adjustment is needed; YX min is the minimum evaluation value of the equipment running state; WH is the equipment maintenance index; WZ is the maintenance period; WC is the maintenance frequency, which reflects the total number of times of maintaining the industrial equipment within the maintenance period WZ; for reflecting the power demand of the industrial equipment under a given load; the operation of the square root and The root operation is similar to the root operation of the device efficiency, and can reduce the interference of abnormal values on the performance evaluation result.

[0011] Further, the calculation formula of the adjustment prediction and feedback unit is as follows: ; Wherein: YX fost is the device running state prediction value; YX max,avg is the device running state potential average value, YX max,avg reflects the average degree of all values exceeding the device running state maximum evaluation value YX max of the current industrial equipment in the historical monitoring period, and is used to measure the potential ability of the industrial equipment exceeding the reference interval {YX max -YX min}; YX max is the device running state maximum evaluation value; is used to evaluate the promotion degree of the adjustment amount T to the potential running state of the industrial equipment.

[0012] Further, the processing and analysis of the device running state prediction value YX fost and the reference interval {YX max -YX min} are as follows: If the value of YX fost is within the reference interval {YX max -YX min}, it indicates that the adjustment measure output by the adjustment amount T is effective, and the running state of the industrial equipment will be improved in the future; If the value of YX fost is high and exceeds the device running state maximum evaluation value YX max , it indicates that the industrial equipment has potential ability, and the value of the device running state potential average value YX max,avg needs to be adjusted; If the value of YX fost is low and lower than the device running state minimum evaluation value YX min , it indicates that the adjustment measure output by the adjustment amount T is not good, and the running state of the industrial equipment is still poor in the future, at which time the adjustment scheme needs to be re-evaluated and the industrial equipment needs to be replaced.

[0013] Further, the devices used by the data collection processing module include data acquisition sensors and data transmission devices. The devices used by the running adjustment and prediction module include data processing software and data transmission devices. The device used by the measure making module includes an intelligent executor; The device used by the prediction analysis module includes data analysis software and data transmission equipment.

[0014] The effects of the above scheme are as follows: 1、The running state evaluation unit can comprehensively consider multiple indexes of industrial equipment operating power G, equipment load level FS, equipment efficiency value XL, and equipment loss coefficient XH, thereby realizing comprehensive evaluation of the industrial equipment state, and this helps to improve the accuracy and reliability of the evaluation.

[0015] 2、The minimum evaluation value YX of the equipment running state in the abnormal state adjustment amount output unit min can be adjusted according to the monitoring situation of the actual monitoring period, thereby realizing the flexibility of abnormal detection, and through the output adjustment amount T, the abnormal state of the industrial equipment can be more accurately identified, and the corresponding adjustment measures are output.

[0016] 3、The adjustment prediction and feedback unit of the present application provides a scientific basis for the adjustment measures through the equipment running state prediction value YX fost , which ensures the accuracy and effectiveness of the adjustment measures, and helps to improve the industrial equipment state and reduce the maintenance cost, and by setting the reference interval of the industrial equipment state value {YX max -YX min}, and comparing the equipment running state prediction value YX fost with the interval, the continuous tracking and optimization of the effect of the adjustment measures are realized, and this cyclic feedback mechanism helps to continuously improve the algorithm model and improve the intelligent level of industrial equipment management.

[0017] 4、The present application applies big data technology to industrial internet equipment management, and through the algorithm model, the equipment data is deeply mined and analyzed, thereby realizing the accurate evaluation of the industrial equipment state, the abnormal detection, and the scientific formulation of the adjustment measures, which helps to improve the production efficiency, reduce the maintenance cost, and promote the intelligent development of the industrial internet. BRIEF DESCRIPTION OF DRAWINGS

[0018] Fig. 1 is the main method flow diagram of the industrial internet data processing method of the present application; Fig. 2 is the covering data diagram of the running state data in the present application; Fig. 3 is the adjustment measure diagram of different results of the adjustment amount T in the present application. DETAILED DESCRIPTION

[0019] The technical solutions in the embodiments of the present application will be clearly and completely introduced below with reference to the drawings in the embodiments of the present application.

[0020] Embodiment one, please refer to Figs. 1-3 The industrial internet data processing method based on big data comprises a data collection and processing module, a running adjustment and prediction module, a measure making module and a cycle feedback and optimization module, and has the characteristics that: The data collection and processing module is used for monitoring and collecting the device operation power G, the device load level FS, the device efficiency value XL, the device loss coefficient XH, the device maintenance index WH and the potential average value YX of the device running state of the industrial equipment in a current monitoring period. max,avg , and the reference interval {YX max -YX min} is transmitted to the running adjustment and prediction module. The running adjustment and prediction module comprises a running state evaluation unit, an abnormal state adjustment amount output unit and an adjustment prediction and feedback unit, and is used for sequentially calculating the device running state evaluation value YX, the adjustment amount T and the device running state prediction value YX fost . The measure making module is used for executing the adjustment measures output by the industrial equipment according to the adjustment amount T. The prediction analysis module is used for performing prediction analysis and improvement of the adjustment measures on the prediction result of the device running state prediction value YX fost . The devices used by the data collection and processing module comprise data acquisition sensors and data transmission equipment. The devices used by the running adjustment and prediction module comprise data processing software and data transmission equipment. The devices used by the measure making module comprise intelligent actuators. The devices used by the prediction analysis module comprise data analysis software and data transmission equipment.

[0021] In this embodiment, the processing method realizes accurate evaluation of the running state of the industrial equipment, abnormality detection, adjustment amount calculation, prediction and feedback and cycle optimization through a series of ordered steps, modules and units and corresponding device support, and this method not only improves the efficiency and accuracy of the management of the industrial equipment, but also provides strong support for the intelligent development of the industrial internet.

[0022] Embodiment two, please refer to Figs. 1-3 The calculation formula of the running state evaluation unit is as follows: ; Among them: YX is the device running state evaluation value. G represents the operating power of the equipment; G max This refers to the maximum operating power of the equipment. FS represents the device load level; XL represents the equipment efficiency value; XH is the equipment loss coefficient; Square root operations have non-linear characteristics and are used to amplify small differences and reduce large differences. In equipment operating status evaluation, when the equipment operating power G approaches its maximum operating power G... max Even small power changes can have a significant impact on the evaluation results, thus emphasizing the efficient operation of industrial equipment; Used for comprehensive evaluation of the operating load and efficiency of industrial equipment; A higher YX value indicates a better operating status of the current industrial equipment; A low YX value indicates a worse operating condition of the current industrial equipment; Based on the calculation formula of the operating status assessment unit, and in the initial stage of industrial equipment operation, the optimal and worst operating power G, equipment load level FS, equipment efficiency value XL, and equipment loss coefficient XH of each piece of industrial equipment are respectively substituted into the calculation formula. The calculation formula yields the maximum evaluation value YX of the equipment's operating status. max Minimum evaluation value YX for equipment operating status min and {YX max -YX min The range of} is set as a reference range for the operating status of industrial equipment; The formulas for calculating the equipment load level FS, equipment efficiency value XL, and equipment loss coefficient XH are as follows: FS=DF / F max ; XL = OUT / IN; XH = SN / KN; in: DF represents the current load value, F max This is the maximum load value; OUT represents the average output power of the device, and IN represents the average input power of the device. SN represents the number of years used, and KN represents the total service life.

[0023] In the algorithm of this embodiment, The calculation section is used to evaluate the equipment operating power G and the equipment maximum operating power G. maxThe ratio reflects the power utilization efficiency of industrial equipment. The higher the ratio, the more the industrial equipment is operating close to its maximum capacity. However, an excessively high ratio also means that the industrial equipment is in an overloaded state. Therefore, this calculation part is to measure the operating status of the equipment in the power dimension. As a factor in the operating status assessment unit, it affects the final equipment operating status assessment value YX. The calculation section combines the equipment load level FS and the equipment efficiency value XL to comprehensively evaluate the equipment's operating burden and efficiency. The equipment load level FS reflects the current workload of the industrial equipment, while the equipment efficiency value XL reflects the efficiency of the industrial equipment in completing these tasks. Adding these two parameters together yields a comprehensive index used to evaluate the overall performance of the equipment during operation. As another factor in the operating status evaluation unit, it is combined with the power usage efficiency factor to jointly determine the equipment operating status evaluation value YX of the industrial equipment. Finally, the equipment loss coefficient XH is subtracted from this comprehensive index to reflect the performance decline of the equipment due to aging and wear. This outputs the equipment operating status assessment value YX, which is used to determine whether the industrial equipment is in a normal or abnormal state, and provides a basis for subsequent abnormal state detection and adjustment calculation. In this embodiment, the operating status assessment unit covers multiple key aspects of equipment operation, ensuring a comprehensive assessment of the equipment status. Among them, the equipment operating power G reflects the energy consumption of industrial equipment, the equipment load level FS reflects the actual operating burden of industrial equipment, the equipment efficiency value XL comprehensively considers the efficiency, stability and reliability of equipment, and the equipment loss coefficient XH reveals the wear and aging degree of industrial equipment. Through precise mathematical calculations, the operating status assessment unit can calculate the equipment operating status assessment value YX of the real-time status of industrial equipment. This value not only reflects the current status of the equipment, but can also be compared with historical data to reveal the changing trend of the equipment status. By collecting real-time operating data from industrial equipment, the operating status assessment unit can dynamically update the equipment operating status assessment value YX, ensuring timely understanding of the current status of the industrial equipment. When the equipment operating status assessment value YX is not within the reference range {YX}... max -YX min When this happens, an early warning mechanism can be triggered so that timely measures can be taken to prevent equipment failure.

[0024] Example 3, please refer to Figs. 1-3 The calculation formula for the abnormal state adjustment output unit is as follows: ; WH = WC / WZ; in: T represents the adjustment amount; If T is positive, it indicates that adjustments such as increasing power and optimizing industrial equipment are needed. A negative T value indicates that adjustments such as load reduction and industrial equipment maintenance are required. If T is 0, it means that the current operating state of the industrial equipment is already in an ideal state and no additional adjustments are needed. YX min This is the minimum assessment value for the equipment's operating status; WH stands for Equipment Maintenance Index; WZ represents the maintenance cycle; WC represents the number of maintenance operations, reflecting the total number of maintenance operations performed on industrial equipment within the maintenance cycle WZ. Used to reflect the power requirements of industrial equipment under a given load; Square root operations AND The square root operation is similar to that used to amplify small differences in device efficiency and reduce the interference of outliers on performance evaluation results.

[0025] In the algorithm of this embodiment, The calculation section is used to determine whether the industrial equipment operating status assessment value YX is lower than a threshold, thereby detecting whether the equipment is in an abnormal state. If the equipment operating status assessment value YX is lower than the minimum equipment operating status assessment value YX... min If the industrial equipment is in an abnormal state, it is considered to be in an abnormal state. As the basis for abnormal state detection, this calculation part affects the calculation of the adjustment amount T. When the industrial equipment is in an abnormal state, the adjustment amount T needs to be calculated for necessary optimization and maintenance. The calculation section is used to evaluate the ratio of equipment operating power G to equipment load level FS, and reflects the power demand of the equipment under a given load. By comparing the equipment operating power G and the equipment load level FS, the power demand of the equipment under a given load can be obtained. The higher this ratio, the more power the industrial equipment needs to maintain operation under the same load. As a factor in the calculation of adjustment amount T, it is combined with the abnormal state detection results to jointly determine the magnitude and direction of the adjustment amount. The calculation section combines the equipment efficiency value XL and the equipment maintenance index WH to assess the equipment's maintenance needs. As another factor in the calculation of the adjustment amount T, it is combined with the power demand factor to jointly determine the magnitude and direction of the adjustment amount T. At the same time, it also reflects the urgency and importance of industrial equipment in terms of maintenance. In this embodiment, the abnormal state adjustment output unit uses the minimum evaluation value YX of the device operating state. min It can promptly detect abnormal conditions of industrial equipment. Once the equipment operating status assessment value YX exceeds the minimum equipment operating status assessment value YX... min The abnormal state adjustment output unit will immediately trigger the abnormal detection mechanism; Furthermore, the abnormal state adjustment output unit uses historical data and current status of the equipment to calculate the adjustment amount T through precise mathematical calculations. This value not only reflects the degree of adjustment required for the equipment but also guides subsequent adjustment measures. Based on the adjustment amount T calculated by the abnormal state adjustment output unit, effective adjustment measures can be formulated. Measures such as increasing power, optimizing industrial equipment, reducing load, and maintaining industrial equipment aim to improve the operating status of the equipment and prevent potential failures. It is important to note that the sign and magnitude of the adjustment amount T directly guide subsequent equipment adjustment measures and can be used to take targeted maintenance and optimization measures based on the specific value of the adjustment amount T to improve the performance and stability of industrial equipment.

[0026] Example 4, please refer to Figs. 1-3 The calculation formulas for the prediction and feedback units are adjusted as follows: ; in: YX fost Predicted values ​​for equipment operating status; YX max,avg YX represents the potential average value of the equipment's operating state. max,avg This reflects all industrial equipment exceeding the maximum assessed value YX of its operating status within the historical monitoring period. max The average degree, and used to measure industrial equipment exceeding the reference range {YX}. max -YX min} potential capabilities; YX max This is the maximum assessed value for the equipment's operating status; Used to assess the degree to which the adjustment amount T improves the potential operating condition of industrial equipment; In the algorithm of this embodiment, In the calculation section, the adjustment amount T reflects the degree of adjustment required for industrial equipment, while the potential average value YX of the equipment's operating state... max,avg Maximum evaluation value YX of equipment operating status maxThe ratio reflects the gap between the current operating state of industrial equipment and its potential capacity at its maximum operating state. Multiplying the adjustment amount T by this gap yields a predicted value, which represents the degree of improvement in the potential performance of the industrial equipment after the corresponding adjustment. This calculation provides a quantitative assessment of the impact of the adjustment measures on the potential performance of the equipment and helps to understand the effectiveness of the adjustment measures and formulate further optimization plans accordingly. The calculation section comprehensively considers equipment status, performance, and maintenance needs to predict adjusted equipment maintenance requirements, and in... Based on the calculation, the equipment maintenance index WH is introduced, which can further predict the changes in equipment maintenance needs after corresponding adjustments. The equipment maintenance index WH reflects the urgency and importance of industrial equipment maintenance. Thus, this calculation can yield a more comprehensive prediction of maintenance needs. The adjustment prediction and feedback unit in this embodiment utilizes advanced prediction algorithms and models to accurately predict the equipment operating status prediction value YX. fost This value reflects the performance of industrial equipment over a future period of time. It is obtained by comparing the predicted equipment operating status value YX. fost By comparing the actual equipment operating status assessment value YX with the next actual value, the predictive capability of the adjustment prediction and feedback unit can be verified. Furthermore, with continuous data accumulation and algorithm optimization, the predictive capability of the adjustment prediction and feedback unit will be further improved. This can be achieved by comparing the predicted equipment operating status value YX. fost With reference interval {YX max -YX min This allows for further evaluation of the effectiveness of adjustment measures, and based on the evaluation results, the adjustment measures can be optimized and improved. Specifically, if the predicted equipment operating status value YX... fost If the value is still below the lower limit of the reference range, more proactive maintenance and optimization measures are needed. The results of the adjustment prediction and feedback unit can be fed back to the operation status assessment unit to form a closed-loop system. By continuously updating the equipment operation status assessment value YX and the adjustment amount T, the status of industrial equipment can be continuously monitored and optimized.

[0027] Example 5, please refer to Figs. 1-3 Equipment operating status prediction value YX fost and reference interval {YX max -YX min The processing and analysis of} are as follows: If YX fost The value is within the reference range {YX} max -YX minIf the value is within}, it means that the adjustment measures output by the adjustment amount T are effective, and the operating status of the industrial equipment will improve in the future. If YX fost The value is high and exceeds the maximum evaluation value YX for equipment operating status. max This indicates that the industrial equipment has potential capabilities, when the potential average value YX of the equipment's operating state is... max,avg Adjust the value accordingly; If YX fost The value is low and below the minimum assessment value YX for equipment operating status. min If the adjustment measure output by the adjustment amount T is not effective, it means that the industrial equipment will remain in poor condition for a period of time. In this case, it is necessary to re-evaluate the adjustment plan and consider replacing the industrial equipment. In this embodiment, the predicted value YX of the device's operating state after adjustment is obtained by adjusting the prediction and feedback unit. fost The results are fed back to the operational status assessment unit, which can update the operational status assessment value YX of the industrial equipment in real time, ensuring the accuracy and timeliness of the assessment results. Based on the prediction results of the prediction and feedback unit and the changing trend of the operational status assessment value YX, the parameters in the operational status assessment unit can be optimized and adjusted to adapt to changes in the status of industrial equipment and new operational requirements. Through the cyclical feedback mechanism of the prediction and feedback unit and the operational status assessment unit, intelligent decision-making can also be achieved, and more scientific and reasonable equipment maintenance and management strategies can be formulated based on the real-time status of the equipment and future prediction results. Specifically, by setting a reference range {YX} for the device status value max -YX min}, and the actual equipment operating status assessment value YX and the predicted equipment operating status value YX after prediction adjustment. fost By comparing with this range, deviations in equipment performance can be detected in a timely manner. This cyclical feedback mechanism prompts the implementation of necessary adjustment measures to optimize equipment performance and keep it in its best state. Over time, this continuous optimization process will continuously improve the overall performance of industrial equipment. The cyclic feedback mechanism helps to identify and resolve potential equipment failures in a timely manner, thereby avoiding failures. By regularly assessing the equipment status and taking preventive measures, the reliability of industrial equipment can be significantly improved, reducing downtime and maintenance costs caused by failures. Furthermore, through cyclic feedback and adjustment measures, the wear and aging process of industrial equipment can be slowed down, thereby extending its service life. This not only reduces the cost of replacing industrial equipment, but also reduces the risk of production interruption caused by industrial equipment upgrades. The cyclic feedback mechanism can also more accurately understand the actual condition of industrial equipment, thereby formulating more effective maintenance plans. This can not only improve the efficiency of maintenance work, but also reduce unnecessary maintenance costs and waste of resources. By setting the reference interval {YX max -YX min By comparing actual values ​​with predicted values, we can obtain intuitive feedback on the performance of industrial equipment, which helps to make more informed decisions. The cyclical feedback mechanism can also continuously seek ways to improve the performance of industrial equipment. Furthermore, by collecting and analyzing equipment status data, we can identify performance bottlenecks and areas for improvement, and take corresponding measures to improve them. This continuous improvement will help drive the continuous optimization of the entire industrial equipment management and maintenance system. In summary, the operating status assessment unit, the abnormal status adjustment output unit, the adjustment prediction and feedback unit, and their parameters have significant beneficial effects on equipment status assessment, abnormality detection and adjustment calculation, and equipment status adjustment prediction and feedback. The application of these formulas and parameters not only improves the intelligence level of industrial equipment management but also brings higher production efficiency and economic benefits. Furthermore, the resulting cyclic feedback mechanism brings many beneficial effects to industrial equipment management and maintenance. It not only helps optimize equipment performance, improve reliability, and extend service life but also enhances maintenance efficiency, strengthens decision support, and promotes continuous improvement. Therefore, when implementing equipment management and maintenance strategies, the advantages of this cyclic feedback mechanism should be fully considered and utilized.

[0028] While the present invention has been disclosed above, it is not limited thereto. Any person skilled in the art can make various modifications and alterations without departing from the spirit and scope of the invention; therefore, the scope of protection of the present invention should be determined by the scope defined in the claims.

Claims

1. A big data-based industrial internet data processing method, comprising a data collection processing module, a running adjustment and prediction module, a measure formulation module and a cycle feedback and optimization module, characterized in that: the measure formulation module is used to output adjustment measures of an industrial equipment execution adjustment amount T; a calculation formula of the running state evaluation unit is as follows: YX = G*FS*XL*XH wherein: YX is an equipment running state evaluation value; G is an equipment operating power; FS is an equipment load level; XL is an equipment efficiency value; and XH is an equipment loss coefficient; a higher YX value reflects a better current industrial equipment running state; and a lower YX value reflects a worse current industrial equipment running state; calculation formulas of the equipment load level FS, the equipment efficiency value XL and the equipment loss coefficient XH are as follows: XL = OUT / IN; XH = SN / KN; wherein: OUT is an average equipment output power, IN is an average equipment input power; SN is a used life, and KN is a total life; a calculation formula of the abnormal state adjustment amount output unit is as follows: WH = WC / WZ; wherein: T is an adjustment amount; a positive T indicates that an increase power and industrial equipment optimization adjustment measure needs to be performed; a negative T indicates that a load reduction and industrial equipment maintenance adjustment measure needs to be performed; T = 0 indicates that a current industrial equipment running state is already in an ideal state and no additional adjustment is needed; WH is an equipment maintenance index; WZ is a maintenance period; WC is a maintenance number, and WC reflects a total number of times of maintenance of the industrial equipment within the maintenance period WZ; a calculation formula of the adjustment prediction and feedback unit is as follows: wherein: the data collection processing module uses equipment including data acquisition sensors and data transmission equipment; the running adjustment and prediction module uses equipment including data processing software and data transmission equipment; the measure formulation module uses equipment including intelligent actuators; and the prediction analysis module uses equipment including data analysis software and data transmission equipment. The data collection processing module is used for monitoring and collecting the equipment operation power G, the equipment load level FS, the equipment efficiency value XL, the equipment loss coefficient XH, the equipment maintenance index WH and the potential average value YX of the running state of the industrial equipment in the current monitoring period, and transmitting them to the running adjustment and prediction module. max,avg and the reference interval {YX max -YX min} and transmitting them to the running adjustment and prediction module. The operation adjustment and prediction module comprises an operation state evaluation unit, an abnormal state adjustment amount output unit, an adjustment prediction and feedback unit, and is used to sequentially calculate and output a device operation state evaluation value YX, an adjustment amount T, and a device operation state prediction value YX fost ; ​ The prediction analysis module is configured to perform prediction analysis and improvement of adjustment measures on the prediction result of the equipment operation state prediction value YX. fost The prediction analysis module is configured to perform prediction analysis and improvement of adjustment measures on the prediction result of the equipment operation state prediction value YX. 2.The industrial internet data processing method based on big data according to claim 1, wherein: ​ ； ​ ​ ​ G max For the maximum operating power of the device; ​ ​ ​ The square root operation has a non-linear characteristic, for amplifying small differences and reducing large differences, in the evaluation of the operating state of the equipment, when the equipment operating power G approaches its maximum equipment operating power G max , even small power variations have a greater impact on the evaluation result, thus emphasizing the high efficiency of the operation of the industrial equipment; for a comprehensive assessment of the operational burden and efficiency of industrial plants; ​ ​ 3.The industrial internet data processing method based on big data according to claim 2, characterized in that: Based on the calculation formula of the running state evaluation unit, and at the initial stage of the industrial equipment operation, the best and worst equipment operation power G, the equipment load level FS, the equipment efficiency value XL and the equipment loss coefficient XH of each industrial equipment running state are respectively brought into the The calculation formula is obtained. The maximum evaluation value YX max and the minimum evaluation value YX min of the equipment running state are obtained, and the interval of {YX max -YX min} is set as the reference interval of the industrial equipment running state. 4.The industrial internet data processing method based on big data according to claim 3, characterized in that: ​ FS = DF / F max ; ​ ​ ​ DF is the current load value, F max is the maximum load value; ​ ​ 5.The industrial internet data processing method based on big data according to claim 3, characterized in that: ​ ； ​ ​ ​ ​ ​ ​ YX min Minimum evaluation value for the device operating state; ​ ​ ​ for reflecting the power demand of the industrial plant under a given load; The operation of the square root and The operation of the square root and the operation of the logarithm are similar, which are used to amplify the small differences in the efficiency of the device and can reduce the interference of outliers on the performance evaluation results. 6.The industrial internet data processing method based on big data according to claim 5, characterized in that: ​ ； ​ YX fost is the predicted value of the device operating state; YX max,avg YX max,avg YX max YX max YX min YX YX max is the maximum evaluation value for the device operating state; to assess the degree of improvement of the potential operating state of the industrial plant by the adjustment amount T. 7.The industrial internet data processing method based on big data according to claim 6, characterized in that: The device operating state prediction value YX fost and the reference interval {YX max - YX min The processing analysis of the above is as follows: If YX fost is within the reference interval {YX max , -YX min}, it means that the adjustment measure output by the adjustment amount T is effective, and the running state of the industrial equipment will be improved in the future. If YX fost is high and exceeds the maximum evaluation value YX max for the operating state of the plant, it indicates that the plant has potential capacity, which is adjusted when the value of the potential average YX max,avg for the operating state of the plant is adjusted; If YX fost is low, and lower than the minimum evaluation value YX min of the running state of the industrial equipment, it indicates that the adjustment measure effect output by the adjustment amount T is not good, and the running state of the industrial equipment is still poor in the future period of time, at which time the adjustment scheme needs to be re-evaluated and replacement of the industrial equipment is considered. 8.The industrial internet data processing method based on big data according to claim 1, wherein: ​ ​ ​ ​

Images