A comprehensive management and optimization system for the Industrial Internet

Abstract

The present invention discloses a comprehensive management and optimization system for the industrial Internet, which relates to the technical field of industrial equipment management. By extracting historical fault data of multiple continuous historical periods from maintenance and transportation logs, analyzing and processing them, a historical high-fault set is obtained, and high-fault frequency value analysis and processing are performed on multiple high-frequency fault periods in the historical high-fault set to obtain sub-period comparison values. The sub-period comparison values ​​can reflect the overall characteristics of the historical high-frequency sub-periods with the same ranking after being divided by different high-frequency fault periods in terms of stability of fault frequency change and trend similarity, which is conducive to identifying the fault laws of the historical high-frequency sub-periods with the same ranking after being divided by different high-frequency fault periods, and provides data support for the maintenance of industrial equipment in future periods.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial equipment management, and in particular to a comprehensive management and optimization system for the Industrial Internet. Background Art

[0002] In the field of industrial production, the stable operation of industrial equipment is crucial to production efficiency, product quality and the economic benefits of the enterprise. With the rapid development of industrial Internet technology, realizing intelligent management of the industrial equipment production process has become an inevitable trend.

[0003] In the existing technology, operational failures of industrial equipment are usually handled only after they occur, and there is a lack of evaluation of failures based on the behavioral data of industrial equipment. Therefore, this application analyzes the stability of the changing trends of multiple historical failure data, which is beneficial for enterprises (maintenance personnel) to plan and manage the estimated failure frequency of future equipment, and helps to identify the characteristic laws of changes in multiple historical failure data. After determining its stability, it is used as a basis to predict the failure probability of industrial equipment in future cycle periods, and complete the prediction of failure frequency in future time periods, which is beneficial to enterprises' efficient management of industrial equipment.

[0004] To this end, the present invention provides a comprehensive management and optimization system for the Industrial Internet. Summary of the Invention

[0005] The object of the present invention is to provide a comprehensive management and optimization system for the industrial Internet to solve at least one of the above-mentioned problems of the prior art.

[0006] A comprehensive management and optimization system for the industrial Internet includes the following steps:

[0007] High-demand screening module: Analyzes and processes historical fault data within multiple consecutive historical periods and the corresponding historical periods to obtain a set of historical high-fault events;

[0008] The historical period is divided into several continuous historical periods of equal length, and the value of the historical fault frequency in the historical period that is greater than or equal to the rated fault frequency is recorded as the high fault frequency value;

[0009] Mark the historical period corresponding to the high fault frequency value as the high fault frequency period;

[0010] Type analysis module: Constructs an analysis matrix based on the high-frequency fault periods and high-fault frequency values ​​within the historical high-fault set, processes the historical fault frequency data within the analysis matrix, and outputs the sub-period change type;

[0011] Pattern analysis module: processes the patterns of stable sub-periods and fluctuating sub-periods within multiple high-frequency fault periods to obtain periodic change signals or non-periodic change signals based on industrial equipment faults;

[0012] Prediction processing module: Based on periodic change signals and non-periodic change signals, it obtains the predicted high-frequency effective values ​​under different periodic changes and completes the prediction of industrial equipment failures in the future period.

[0013] A further solution of the present invention is to obtain the historical high fault set in the following manner:

[0014] Sort multiple historical periods according to the chronological order of the maintenance and delivery logs and form a historical set T;

[0015] Based on any historical period in the historical set T, multiple high-frequency fault periods are integrated and counted in the time sequence of the historical period to obtain a historical high-fault set.

[0016] A further solution of the present invention is to obtain the analysis matrix in the following manner:

[0017] In the historical high fault set, each high fault frequency period is divided into several historical high frequency sub-periods of equal length;

[0018] The historical high-frequency sub-periods divided by each fault high-frequency period are sorted by matrix to obtain the analysis matrix , where the row data in the analysis matrix R represents the historical high-frequency sub-periods divided within each fault high-frequency period, the column data in the analysis matrix R represents the historical high-frequency sub-periods divided within different fault high-frequency periods, n represents the total number of historical high-frequency sub-periods within each fault high-frequency period, and m represents the total number of fault high-frequency periods.

[0019] A further solution of the present invention is to quantify the historical fault frequency data in the analysis matrix, and the process is as follows:

[0020] Extract the column data in the analysis matrix R and get the set ;

[0021] Get The historical fault frequencies corresponding to the two endpoints of the historical high-frequency sub-period are added and averaged to obtain the unit change mean;

[0022] Iterating over a collection All historical high-frequency sub-periods within The processing method of historical high-frequency sub-periods until the collection Until the acquisition of the unit change mean corresponding to all historical high-frequency sub-periods is completed;

[0023] The variance of all unit change means is calculated to obtain the change stability value.

[0024] A further solution of the present invention is to quantify the historical fault frequency data in the analysis matrix, and the process is as follows:

[0025] Any collection The adjacent historical high-frequency sub-periods within the period are combined and sorted according to the time series to obtain the element analysis group;

[0026] Extract the earliest historical high-frequency sub-period in the element analysis group, obtain the historical fault frequencies corresponding to the two endpoints of the earliest historical high-frequency sub-period, substitute the historical fault frequencies corresponding to the two endpoints of the earliest historical high-frequency sub-period into the two-dimensional coordinate system, and obtain the change line of the earliest period;

[0027] Based on the change line of the previous period, the corresponding slope is calculated using the slope formula ;

[0028] Similarly, extract the later historical high-frequency sub-periods within the element analysis group and calculate the corresponding slope using the slope formula. ;

[0029] The slope With slope Perform the difference, take the absolute value, and get the combined slope difference;

[0030] The trend similarity value was obtained by adding up the combined slope differences corresponding to all element analysis groups and taking the average.

[0031] A further solution of the present invention is to output the sub-period change type, and the process is as follows:

[0032] Add the trend similarity value and the change stability value to obtain the sub-period comparison value;

[0033] If the sub-period comparison value is greater than the sub-period comparison threshold, a period fluctuation signal is generated, and the historical high-frequency sub-period corresponding to the generated period fluctuation signal is marked as a change fluctuation sub-period;

[0034] If the sub-period comparison value is less than or equal to the sub-period comparison threshold, a period stability signal is generated, and the historical high-frequency sub-period corresponding to the generated period stability signal is marked as a change-stable sub-period.

[0035] A further solution of the present invention is to obtain regularity analysis data in the following manner:

[0036] Randomly select a high-frequency fault period;

[0037] All stable sub-periods and fluctuating sub-periods within the fault high-frequency period are sorted according to the time sequence to obtain a sub-period sequence;

[0038] Obtain the number of fluctuating sub-periods between adjacent stable sub-periods, add and average them, and calculate the ratio with the total number of high-demand sub-periods within the high-frequency fault period to obtain the number of changing intervals;

[0039] Combining adjacent high-frequency fault periods into a regularity analysis group, and sorting the adjacent high-frequency fault periods within the regularity analysis group according to their time sequence to obtain multiple regularity analysis groups;

[0040] Based on multiple groups of regularity analysis, the fault frequency interval characterization value is obtained by Euclidean distance calculation. .

[0041] A further solution of the present invention is to obtain regularity analysis data in the following manner:

[0042] In the sub-period sequence, the high fault frequency values ​​corresponding to the adjacent stable sub-periods are subtracted and the absolute value is taken to obtain the adjacent unit change value;

[0043] Extract the maximum adjacent unit change value and the minimum adjacent unit change value, and perform the difference to obtain the adjacent unit change value range;

[0044] The maximum adjacent unit change value and the minimum adjacent unit change value are added together to obtain the average value, and the ratio is calculated with the adjacent unit change value range to obtain the stable change value;

[0045] The high fault frequency characterization value is obtained by calculating the stable change value through Euclidean distance calculation .

[0046] A further solution of the present invention is that the periodic change identification process is:

[0047] The fault frequency interval characterization value Characterized by high fault frequency Perform addition and summation to obtain the regularity analysis value;

[0048] If the regularity analysis value is greater than the regularity analysis threshold, a non-periodic change signal is generated;

[0049] If the regularity analysis value is less than or equal to the regularity analysis threshold, a periodic change signal is generated.

[0050] A further solution of the present invention is to obtain the predicted high frequency effective value in the following manner:

[0051] Based on the periodic change signal, if the future period is a period of stable change, the unit change mean corresponding to the historical high-frequency sub-period is obtained, and the sum is added and averaged to obtain the predicted high-frequency effective value;

[0052] If the future period is a period of change and fluctuation, the sliding average method is used to predict and obtain the predicted high-frequency effective value corresponding to the future period;

[0053] Based on the non-periodic changing signal, the maximum high fault frequency value and the minimum high fault frequency value in the analysis matrix R are extracted, and the sum and average are taken to obtain the predicted high frequency effective value corresponding to the future period.

[0054] Beneficial effects of the present invention:

[0055] 1. The present invention extracts historical fault data of multiple consecutive historical periods from maintenance and transportation logs, performs analysis and processing, obtains a historical high-fault set, analyzes the high-fault frequency values ​​of multiple high-fault time periods within the historical high-fault set, obtains historical high-demand analysis data, and performs quantification processing to obtain sub-period comparison values. The sub-period comparison values ​​reflect the overall characteristics of the stability of the fault frequency variation and trend similarity of the historical high-frequency sub-periods with the same ranking after being divided by different high-fault time periods. This is conducive to identifying the fault patterns of the historical high-frequency sub-periods with the same ranking after being divided by different high-fault time periods, and provides data support for the maintenance of industrial equipment in future cycles.

[0056] 2. The present invention selects any one of multiple high-frequency fault periods, sorts the stable sub-periods and fluctuating sub-periods within it in chronological order to form a sub-period sequence, counts the number of fluctuating sub-periods between adjacent stable sub-periods, obtains a fault frequency interval characterization value, and takes the absolute value of the difference between the high fault frequency values ​​corresponding to adjacent stable sub-periods to obtain an adjacent unit change value, and calculates the two respectively using the Euclidean formula to obtain a fault frequency interval characterization value and a high fault frequency characterization value, and adds the fault frequency interval characterization value and the high fault frequency characterization value to obtain a regularity analysis value, thereby achieving a quantitative analysis of the occurrence regularity of sub-periods and the stability of fault frequency changes in multiple high-frequency fault periods, identifying the change pattern of historical industrial equipment failures in the time series, and based on the obtained change pattern, helping equipment maintenance personnel to rationally plan maintenance plans;

[0057] 3. The present invention predicts the future fault frequency by generating periodic change signals and non-periodic change signals, obtains the predicted high-frequency effective value, and completes the prediction of the fault frequency in the future time period. On the one hand, when generating periodic change signals, through classification discussion, the future time period as a stable change period and the future time period as a fluctuating change period are predicted and processed respectively to obtain the predicted high-frequency effective value. On the other hand, when generating non-periodic change signals, the maximum high fault frequency value and the minimum high fault frequency value in the analysis matrix R are obtained, and the sum and average are added to obtain the predicted high-frequency effective value corresponding to the future time period, which is beneficial for equipment maintenance personnel to reasonably arrange maintenance time, accurately plan and manage the future operation status of industrial equipment, and help avoid the situation where equipment failures cannot be maintained in time. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0059] Figure 1 This is a flow chart of a comprehensive management and optimization method for the Industrial Internet of the present invention;

[0060] Figure 2 This is a schematic diagram of a comprehensive management and optimization system for the Industrial Internet of the present invention;

[0061] Figure 3 It is a structural diagram of a comprehensive management and optimization device for industrial Internet according to the present invention. DETAILED DESCRIPTION

[0062] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0063] Example 1

[0064] Figure 1A flowchart of a comprehensive management and optimization method for the industrial Internet provided in the first embodiment of the present invention. The embodiment of the present invention can be applied to industrial equipment to screen, extract, integrate and summarize high fault frequency values ​​based on multiple historical data to obtain a historical high fault set, and analyze the stability of the characteristic laws of high fault frequency values ​​based on the historical high fault set. The comprehensive management and optimization method for the industrial Internet can be executed by a comprehensive management and optimization system for the industrial Internet. The comprehensive management and optimization system for the industrial Internet can be implemented by software and / or hardware. The comprehensive management and optimization method for the industrial Internet can be configured in a comprehensive management and optimization device for the industrial Internet. Optionally, a comprehensive management and optimization device for the industrial Internet can be an electronic device, which can be a notebook, desktop computer, smart tablet, etc. The embodiment of the present invention does not limit this.

[0065] like Figure 1 As shown, an embodiment of the present invention provides a comprehensive management and optimization method for the industrial Internet, which specifically includes the following steps:

[0066] Step 1: Obtain historical fault data of industrial equipment over multiple consecutive historical periods through maintenance and transportation logs, and analyze and process the historical fault data and the corresponding historical periods to obtain a historical high-fault set;

[0067] It should be noted that the historical period includes but is not limited to 10 days, 30 days or 60 days, and the historical failure data includes mechanical failures, electrical failures, and control and software failures of industrial equipment;

[0068] In some embodiments, multiple historical periods are sorted according to the time sequence of the maintenance delivery logs and formed into a historical set T={ 、 、 、...... },in, Indicates the nth historical period, where n is the total number of historical periods;

[0069] Based on any historical period in the historical set T, the historical period is divided into several continuous historical periods of equal length, the historical fault frequencies within the historical period are obtained, and the historical fault frequencies within all historical periods are compared. The value with a historical fault frequency greater than or equal to the rated fault frequency is recorded as a high fault frequency value;

[0070] The rated failure frequency in the historical period is set by the staff based on experience;

[0071] Mark the historical period corresponding to the high fault frequency value as the high fault frequency period;

[0072] It should be noted that the historical fault frequency in a historical period represents the ratio of the total number of faults in the historical period to the length of the historical period;

[0073] Integrate and count multiple high-frequency fault periods in the chronological order of historical cycles to obtain a historical high-fault set;

[0074] Step 2: Based on the historical high-fault set, analyze the high-fault frequency values ​​of multiple high-fault frequency periods to obtain an analysis matrix. Quantify the historical fault frequency data in the analysis matrix to obtain sub-period comparison values, which are compared with the sub-period comparison thresholds to output stable and fluctuating sub-periods.

[0075] In some embodiments, in the historical high fault set, each high fault frequency period is divided into a number of historical high fault frequency sub-periods of equal length, wherein each high fault frequency period is divided in the same manner;

[0076] Perform matrix sorting on the historical high-frequency sub-periods divided by each fault high-frequency period to obtain the analysis matrix , where the row data in the analysis matrix R represents the historical high-frequency sub-periods divided within each fault high-frequency period (a row represents a fault high-frequency period), the column data in the analysis matrix R represents the historical high-frequency sub-periods divided within different fault high-frequency periods (a column represents the historical high-frequency sub-periods with the same ranking within different fault high-frequency periods), n represents the total number of historical high-frequency sub-periods within each fault high-frequency period, and m represents the total number of fault high-frequency periods;

[0077] For example, extract the column data in the analysis matrix R and get the set ;

[0078] Get The historical fault frequencies corresponding to the two endpoints of the historical high-frequency sub-period are added and averaged to obtain the unit change mean;

[0079] Iterating over a collection All historical high-frequency sub-periods within The processing method of historical high-frequency sub-periods until the collection Until the acquisition of the unit change mean corresponding to all historical high-frequency sub-periods is completed;

[0080] Calculate the variance of all unit change means to obtain the change stability value;

[0081] Any collection The adjacent historical high-frequency sub-periods within the period are combined and sorted according to the time series to obtain the element analysis group;

[0082] Extract the earliest historical high-frequency sub-period within the element analysis group, and obtain the historical fault frequencies corresponding to the two endpoints of the earliest historical high-frequency sub-period. Establish a two-dimensional coordinate system, where the X-axis is time and the Y-axis is fault frequency. Substitute the historical fault frequencies corresponding to the two endpoints of the earliest historical high-frequency sub-period into the two-dimensional coordinate system to obtain the change line of the earliest period.

[0083] Similarly, extract the later historical high-frequency sub-periods within the element analysis group, and obtain the historical fault frequencies corresponding to the two endpoints of the later historical high-frequency sub-periods. Establish a two-dimensional coordinate system, where the X-axis is time and the Y-axis is fault frequency. Substitute the historical fault frequencies corresponding to the two endpoints of the later historical high-frequency sub-periods into the two-dimensional coordinate system to obtain the later period change line;

[0084] Based on the change line of the previous period, the slope is calculated using the formula: , calculate the slope corresponding to the change line of the previous period ,in,( , )and( , ) is represented by the coordinates corresponding to the two endpoints of the previous high-frequency sub-period;

[0085] Based on the change line of the later period, the slope calculation formula is: , calculate the slope of the change line corresponding to the later period ,in,( , )and( , ) is represented by the coordinates corresponding to the two endpoints of the later historical high-frequency sub-period;

[0086] The slope With slope Perform the difference, take the absolute value, and get the combined slope difference;

[0087] The trend similarity value was obtained by summing and averaging the combined slope differences corresponding to all element analysis groups;

[0088] The trend similarity value is multiplied by the change stability value to obtain the sub-period comparison value;

[0089] It can be explained that the sub-period comparison value represents a comprehensive reflection of the overall characteristics of the stability of the fault frequency change and trend similarity of the historical high-frequency sub-periods with the same ranking after being divided into different high-frequency fault periods. This helps to identify the fault patterns of the historical high-frequency sub-periods with the same ranking after being divided into different high-frequency fault periods, and provides data support for equipment maintenance in future cycles.

[0090] The sub-period comparison value is compared with the sub-period comparison threshold. The process is as follows:

[0091] If the sub-period comparison value is greater than the sub-period comparison threshold, it means that the average fault frequency changes in adjacent sub-periods are significantly different, and a period fluctuation signal is generated. The historical high-frequency sub-period corresponding to the generated period fluctuation signal is marked as a change fluctuation sub-period;

[0092] If the sub-period comparison value is less than or equal to the sub-period comparison threshold, it means that the difference in the average fault frequency change between adjacent sub-periods is small, and a period stability signal is generated. The historical high-frequency sub-period corresponding to the generated period stability signal is marked as a change-stable sub-period;

[0093] An example of this is analyzing whether a historical high-frequency sub-period is a fluctuating sub-period or a stable sub-period. This aims to determine whether the corresponding fault frequency changes within each high-frequency fault period are stable and have similar trends. This helps identify fault patterns within the same-ranked historical high-frequency sub-periods within different high-frequency fault periods, providing data support for future equipment maintenance.

[0094] The specific implementation method of the embodiment of the present invention is as follows: by extracting historical fault data of multiple continuous historical periods from the maintenance and transportation log, analyzing and processing them to obtain a historical high fault set, analyzing the high fault frequency values ​​of multiple fault high-frequency periods in the historical high fault set to obtain historical high-demand analysis data, and quantifying them to obtain sub-period comparison values, so as to reflect the overall characteristics of the historical high-frequency sub-periods with the same ranking after being divided by different fault high-frequency periods in terms of the stability of the fault frequency change and the similarity of the trend through the sub-period comparison values, which is conducive to identifying the fault patterns of the historical high-frequency sub-periods with the same ranking after being divided by different fault high-frequency periods, and provides data support for equipment maintenance in future periods.

[0095] Example 2

[0096] like Figure 1 As shown, based on Example 1, an embodiment of the present invention provides an artificial intelligence-based integrated energy management and optimization method, which specifically includes:

[0097] Step 3: Analyze the patterns of stable sub-periods and fluctuating sub-periods within multiple high-frequency fault periods to obtain pattern analysis data, where the pattern analysis data includes fault frequency interval characterization values ​​and high fault frequency characterization values. Quantify the pattern analysis data to obtain pattern analysis values, and compare them with the pattern analysis threshold to obtain the pattern analysis results.

[0098] The regularity analysis results include periodic change signals or non-periodic change signals;

[0099] In some embodiments, a high-frequency fault period is arbitrarily selected;

[0100] All stable sub-periods and fluctuating sub-periods within the fault high-frequency period are sorted according to the time sequence to obtain a sub-period sequence;

[0101] In the sub-period sequence, the number of fluctuating sub-periods between adjacent stable sub-periods is obtained, the sum is added and the average is taken, and the ratio is calculated with the total number of high-demand sub-periods in the high-frequency fault period to obtain the number of changing intervals;

[0102] Combining adjacent high-frequency fault periods into a regularity analysis group, and sorting the adjacent high-frequency fault periods within the regularity analysis group according to their time sequence to obtain multiple regularity analysis groups;

[0103] Substitute the number of change intervals corresponding to adjacent fault high-frequency periods into the Euclidean distance calculation formula: , calculate the fault frequency interval characterization value , where n represents the total number of regularity analysis groups, i represents the ranking of regularity analysis groups within multiple regularity analysis groups, and C i Expressed as the number of change intervals of the i-th regularity analysis group, C i-1 It is expressed as the number of change intervals of the i-1th regularity analysis group;

[0104] In the sub-period sequence, the high fault frequency values ​​corresponding to the adjacent stable sub-periods are subtracted and the absolute value is taken to obtain the adjacent unit change value;

[0105] Compare the change values ​​of all adjacent cells, extract the maximum and minimum adjacent cell change values, and perform the difference to obtain the range of adjacent cell change values;

[0106] The maximum adjacent unit change value and the minimum adjacent unit change value are added together to obtain the average value, and the ratio is calculated with the adjacent unit change value range to obtain the stable change value;

[0107] Substitute the stable change value corresponding to the high-frequency period of adjacent faults into the Euclidean distance calculation formula: , calculate the high fault frequency characterization value , where n represents the total number of regularity analysis groups, i represents the ranking of regularity analysis groups within multiple regularity analysis groups, E i Expressed as the stable change value of the i-th regularity analysis group, E i-1 It is expressed as the stable change value of the i-1th regularity analysis group;

[0108] The fault frequency interval characterization value Characterized by high fault frequency Perform addition and summation to obtain the regularity analysis value;

[0109] It can be understood that the regularity analysis value represents the stability of the intervals between the changing stable sub-periods and the changing fluctuating sub-periods within multiple high-frequency fault periods, as well as the stability of the changes in high fault frequency values ​​between adjacent changing stable sub-periods. Specifically, the fault frequency interval representation value reflects the relative stability of the number of changing fluctuating sub-periods between adjacent stable sub-periods, while the high fault frequency representation value reflects the relative stability of the change amplitude of high fault frequency values ​​within adjacent stable sub-periods. The regularity analysis value obtained by summing the two comprehensively represents the stability of the relevant time periods and fault frequency changes within multiple high-frequency fault periods.

[0110] Compare the regularity analysis value with the regularity analysis threshold. The process is as follows:

[0111] If the regularity analysis value is greater than the regularity analysis threshold, it means that the fluctuation degree of the interval between the stable change sub-period and the fluctuating change sub-period within multiple fault high-frequency periods is large, and the fluctuation degree of the high fault frequency value between adjacent stable change sub-periods is large, generating a non-periodic change signal;

[0112] If the regularity analysis value is less than or equal to the regularity analysis threshold, it means that the fluctuation degree of the interval between the stable change sub-period and the fluctuating change sub-period within multiple fault high-frequency periods is small, and the fluctuation degree of the high fault frequency value between adjacent stable change sub-periods is small, and a periodic change signal is generated;

[0113] The specific implementation plan of the embodiment of the present invention is: select any one from multiple high-frequency fault periods, sort the internal stable change sub-periods and fluctuating change sub-periods in chronological order to form a sub-period sequence, count the number of fluctuating change sub-periods between adjacent stable change sub-periods, obtain the fault frequency interval characterization value, and take the absolute value of the difference between the high fault frequency values ​​corresponding to adjacent stable change sub-periods to obtain the adjacent unit change value, and calculate the two respectively through the Euclidean formula to obtain the fault frequency interval characterization value and the high fault frequency characterization value, add the fault frequency interval characterization value and the high fault frequency characterization value to obtain the regularity analysis value, thereby realizing the quantitative analysis of the occurrence regularity of sub-periods and the stability of fault frequency changes in multiple high-frequency fault periods, identifying the change pattern of historical equipment fault maintenance needs in the time series, and based on the obtained change pattern, helping maintenance personnel to reasonably maintain the equipment.

[0114] Example 3

[0115] like Figure 1As shown, based on Example 1 and Example 2, an embodiment of the present invention provides an integrated energy management and optimization method based on artificial intelligence;

[0116] Step 4: Based on the periodic and non-periodic signals, obtain the predicted high-frequency effective values ​​under different periodic changes to complete the prediction of industrial equipment failures in the future period;

[0117] In some embodiments, based on the periodic variation signal, if the future period is a period of stable variation, the unit variation mean corresponding to the historical high-frequency sub-period is obtained, and the sum is added and averaged to obtain the predicted high-frequency effective value;

[0118] If the future period is a period of change and fluctuation, the sliding average method is used for prediction. The process is as follows:

[0119] S1, according to the time sequence corresponding to the period, extract the high fault frequency values ​​corresponding to the first three historical high-frequency sub-periods of the future period;

[0120] S2, add and average the high fault frequency values ​​corresponding to the first three historical high-frequency sub-periods of the future period to obtain the predicted high-frequency effective value corresponding to the future period;

[0121] Based on the non-periodic changing signal, the process of obtaining the predicted high-frequency effective value is as follows:

[0122] Based on the analysis matrix R ;

[0123] Extract the maximum high fault frequency value and the minimum high fault frequency value in the analysis matrix R, add them together and take the average value to obtain the predicted high frequency effective value corresponding to the future period;

[0124] It should be noted that the significance of obtaining predicted high-frequency RMS values ​​is to help industrial equipment understand equipment failure situations at different time periods in the future in advance. For industrial equipment maintenance, this means rationally allocating maintenance resources based on the predicted high-frequency RMS values ​​to ensure sufficient maintenance personnel and equipment during equipment failure periods.

[0125] The specific implementation method of the embodiment of the present invention is: by generating periodic change signals and non-periodic change signals, predicting and processing the future fault frequency, obtaining the predicted high-frequency effective value, and completing the prediction work of the fault frequency in the future time period. On the one hand, when generating periodic change signals, through classification discussion, the future time period as a stable change period and the future time period as a fluctuating change period are predicted and processed respectively to obtain the predicted high-frequency effective value. On the other hand, when generating non-periodic change signals, the maximum high fault frequency value and the minimum high fault frequency value in the analysis matrix R are obtained, and the sum and average are added to obtain the predicted high-frequency effective value corresponding to the future time period, which is beneficial for equipment maintenance personnel to reasonably arrange maintenance time, accurately plan and manage the future operation status of industrial equipment, and help avoid the situation where equipment failures cannot be maintained in time.

[0126] Example 4

[0127] like Figure 2 As shown, based on Example 1, Example 2 and Example 3, an embodiment of the present invention provides an integrated management and optimization system for the industrial Internet, including:

[0128] High-demand screening module: obtains historical fault data within multiple consecutive historical periods through maintenance and transportation logs, analyzes and processes the historical fault data to obtain a historical set, and analyzes the historical periods within the historical set to obtain a historical high-fault set;

[0129] Type analysis module: Based on the historical high-fault set, it analyzes the high-fault frequency values ​​of multiple high-fault frequency periods to obtain an analysis matrix. It then quantifies the historical fault frequency data in the analysis matrix and outputs the sub-period change type.

[0130] Regularity analysis module: Analyzes the regularity of the sub-period change types to obtain regularity analysis data, quantifies the regularity analysis data to obtain regularity analysis values, and compares them with regularity analysis thresholds to obtain regularity analysis results;

[0131] The regularity analysis results include periodic change signals or non-periodic change signals;

[0132] Prediction processing module: Based on the results of regularity analysis, obtain the predicted high-frequency effective value, obtain the fault assessment within the future change and fluctuation period, and complete the prediction of the fault frequency in the future period.

[0133] Example 5

[0134] Reference Figure 3An embodiment of the present invention further provides a computer device 3, comprising: a memory 302, a processor 301, and a computer program 303 stored on the memory 302. When the computer program 303 is executed on the processor 301, an integrated management and optimization system for the industrial Internet as described in any one of the above methods is implemented.

[0135] The computer device 3 may be a desktop computer, a notebook computer, a PDA, a cloud server or other computing devices. The computer device 3 may include, but is not limited to, a processor 301 and a memory 302. Those skilled in the art will understand that Figure 3 This is merely an example of the computer device 3 and does not constitute a limitation on the computer device 3 . The computer device 3 may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the computer device 3 may also include input and output devices, network access devices, etc.

[0136] The processor 301 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. A general-purpose processor may be a microprocessor or any conventional processor.

[0137] In some embodiments, the memory 302 may be an internal storage unit of the computer device 3, such as a hard drive or memory of the computer device 3. In other embodiments, the memory 302 may also be an external storage device of the computer device 3, such as a plug-in hard drive, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash memory card, etc. equipped on the computer device 3. Furthermore, the memory 302 may include both an internal storage unit of the computer device 3 and an external storage device. The memory 302 is used to store an operating system, application programs, a boot loader, data, and other programs, such as the program code of the computer program. The memory 302 may also be used to temporarily store data that has been output or is about to be output.

[0138] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0139] The above is a detailed description of an embodiment of the present invention. However, the content described is only a preferred embodiment of the present invention and should not be considered to limit the scope of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A comprehensive management and optimization system for the industrial Internet, characterized by: The following steps are involved: High-demand screening module: Analyzes and processes historical fault data within multiple consecutive historical periods and the corresponding historical periods to obtain a set of historical high-fault events; The historical period is divided into several continuous historical periods of equal length, and the value of the historical fault frequency greater than or equal to the rated fault frequency in the historical period is recorded as the high fault frequency value; Mark the historical period corresponding to the high fault frequency value as the high fault frequency period; Type analysis module: Constructs an analysis matrix based on the high-frequency fault periods and high-fault frequency values ​​within the historical high-fault set, processes the historical fault frequency data within the analysis matrix, and outputs the sub-period change type; The analysis matrix is ​​obtained as follows: In the historical high fault set, each high fault frequency period is divided into several historical high frequency sub-periods of equal length; Perform matrix sorting on the historical high-frequency sub-periods divided by each fault high-frequency period to obtain the analysis matrix , where the row data in the analysis matrix R represents the historical high-frequency sub-periods divided within each fault high-frequency period, the column data in the analysis matrix R represents the historical high-frequency sub-periods divided within different fault high-frequency periods, n represents the total number of historical high-frequency sub-periods within each fault high-frequency period, and m represents the total number of fault high-frequency periods; Extract the column data in the analysis matrix R and get the set ; Get The historical fault frequencies corresponding to the two endpoints of the historical high-frequency sub-period are added and averaged to obtain the unit change mean; will be collected The variance of the unit change mean corresponding to all historical high-frequency sub-periods is calculated to obtain the change stability value; will be collected Combine any adjacent historical high-frequency sub-periods within the period and sort them according to the time series to obtain the element analysis group; Extract the slope of the change line of the previous period corresponding to the previous high-frequency sub-period in the element analysis group ; Extract the slope of the change line of the later period corresponding to the later period of the historical high-frequency sub-period within the element analysis group ; The slope With slope Perform the difference and take the absolute value to get the combined slope difference. Add the combined slope differences corresponding to all element analysis groups and take the average to get the trend similarity value. Add the trend similarity value and the change stability value to obtain the sub-period comparison value; If the sub-period comparison value is greater than the sub-period comparison threshold, a period fluctuation signal is generated, and the historical high-frequency sub-period corresponding to the generated period fluctuation signal is marked as a change fluctuation sub-period; If the sub-period comparison value is less than or equal to the sub-period comparison threshold, a period stability signal is generated, and the historical high-frequency sub-period corresponding to the generated period stability signal is marked as a change-stable sub-period; Pattern analysis module: processes the patterns of stable sub-periods and fluctuating sub-periods within multiple high-frequency fault periods to obtain periodic or non-periodic variation signals of industrial equipment faults; Prediction processing module: Based on periodic change signals and non-periodic change signals, it obtains the predicted high-frequency effective values ​​under different periodic changes and completes the prediction of industrial equipment failures in the future period.

2. The comprehensive management and optimization system of the industrial Internet according to claim 1 is characterized in that: The method for obtaining the historical high fault collection is as follows: Sort multiple historical periods according to the chronological order of the maintenance and delivery logs and form a historical set T; Based on any historical period in the historical set T, multiple high-frequency fault periods are integrated and counted in the time sequence of the historical period to obtain a historical high-fault set.

3. The comprehensive management and optimization system of the industrial Internet according to claim 1 is characterized in that: The historical fault frequency data in the analysis matrix is ​​quantified as follows: Iterating over a collection All historical high-frequency sub-periods within The processing method of historical high-frequency sub-periods until the collection Until the acquisition of the unit change mean corresponding to all historical high-frequency sub-periods is completed.

4. The comprehensive management and optimization system of the industrial Internet according to claim 1 is characterized in that: The historical fault frequency data in the analysis matrix is ​​quantified as follows: Extract the earliest historical high-frequency sub-period in the element analysis group, obtain the historical fault frequencies corresponding to the two endpoints of the earliest historical high-frequency sub-period, substitute the historical fault frequencies corresponding to the two endpoints of the earliest historical high-frequency sub-period into the two-dimensional coordinate system, and obtain the change line of the earliest period; Based on the change line of the previous period, the corresponding slope is calculated using the slope formula ; Extract the later historical high-frequency sub-periods within the element analysis group and calculate the corresponding slope using the slope formula .

5. The comprehensive management and optimization system of the industrial Internet according to claim 1 is characterized in that: The method for obtaining regularity analysis data is as follows: Randomly select a high-frequency fault period; All stable sub-periods and fluctuating sub-periods within the fault high-frequency period are sorted according to the time sequence to obtain a sub-period sequence; Obtain the number of fluctuating sub-periods between adjacent stable sub-periods, add and average them, and calculate the ratio with the total number of historical high-frequency sub-periods within the high-frequency fault period to obtain the number of changing intervals; Combining adjacent high-frequency fault periods into a regularity analysis group, and sorting the adjacent high-frequency fault periods within the regularity analysis group according to their time sequence, to obtain multiple regularity analysis groups; Based on multiple groups of regularity analysis, the fault frequency interval characterization value is obtained by Euclidean distance calculation. .

6. The comprehensive management and optimization system of the industrial Internet according to claim 5, characterized in that: The method for obtaining regularity analysis data is as follows: In the sub-period sequence, the high fault frequency values ​​corresponding to adjacent stable sub-periods are subtracted and the absolute value is taken to obtain the adjacent unit change value; Extract the maximum adjacent unit change value and the minimum adjacent unit change value, and perform the difference to obtain the adjacent unit change value range; The maximum adjacent unit change value and the minimum adjacent unit change value are added together to obtain the average value, and the ratio is calculated with the adjacent unit change value range to obtain the stable change value; The high fault frequency characterization value is obtained by calculating the stable change value through Euclidean distance calculation .

7. The comprehensive management and optimization system of the industrial Internet according to claim 6 is characterized in that: The periodic change identification process is: The fault frequency interval characterization value and high fault frequency characterization value Perform addition and summation to obtain the regularity analysis value; If the regularity analysis value is greater than the regularity analysis threshold, a non-periodic change signal is generated; If the regularity analysis value is less than or equal to the regularity analysis threshold, a periodic change signal is generated.

8. The comprehensive management and optimization system of the industrial Internet according to claim 1 is characterized in that: The method for obtaining the predicted high-frequency effective value is as follows: Based on the periodic change signal, if the future period is a stable change sub-period, the unit change mean corresponding to the historical high-frequency sub-period is obtained, and the sum is added to obtain the average to obtain the predicted high-frequency effective value; If the future period is a variable fluctuation sub-period, the sliding average method is used to predict and obtain the predicted high-frequency effective value corresponding to the future period; Based on the non-periodic changing signal, the maximum high fault frequency value and the minimum high fault frequency value in the analysis matrix R are extracted, and the sum and average are taken to obtain the predicted high frequency effective value corresponding to the future period.

Images