An intelligent unit operation optimization prediction method and system

Abstract

The present invention relates to the technical field of performance prediction, and discloses an intelligent unit operation optimization prediction method and system. A plurality of operation data collection points are pre-deployed on the intelligent unit equipment to collect equipment operation change data; the equipment operation change data sequence is determined according to the equipment operation change data, and the equipment operation change data deviation factor is calculated; a plurality of equipment operation change data deviation factor sets are determined, and a sub-operation performance prediction coefficient is calculated; all sub-operation performance prediction coefficients are extracted, deployed on a data tree, and the operation performance prediction coefficient is calculated; based on the operation performance prediction coefficient and the preset operation performance prediction coefficient, it is judged whether the operation state of the intelligent unit equipment needs to be optimized, and a comprehensive operation performance prediction of the intelligent unit can be performed, the performance prediction accuracy and prediction efficiency can be improved, the production interruption and loss caused by the sudden shutdown of the intelligent unit can be avoided, and the enterprise can arrange the maintenance time and interval of the intelligent unit more reasonably.

Description

Technical Field

[0001] The present invention relates to the technical field of performance prediction, and in particular to an intelligent unit operation optimization prediction method and system. Background Art

[0002] A unit usually refers to a system consisting of multiple machines or equipment, which is used to achieve specific functions or production processes. The following are several common types of units: generator sets, refrigeration units, compressor units, air source heat pump hot water units, fresh air units, etc. In short, units play a vital role in modern industry and life. Whether it is energy conversion, temperature control or air quality assurance, various units have their unique functions and advantages, providing solid support for people's production and life. However, in actual production, the use time of intelligent units increases, and the performance continues to decline. If they are not effectively maintained, it will affect the production efficiency of the enterprise.

[0003] In the existing methods, a model is established between the intelligent unit and various influencing factors. These factors include physical parameters (such as temperature, pressure, etc.), working environment conditions (such as humidity, dust concentration, etc.), and historical operation data. By monitoring these input variables in real time, the model is used to predict the output performance of the intelligent unit, so as to determine whether the intelligent unit is in normal operation and possible performance degradation in the future. However, as the use time increases, the internal structure and performance will change. The original mathematical model or machine learning model cannot accurately describe the performance state after this change, resulting in low accuracy in predicting the performance of the intelligent unit. Some complex prediction models, such as deep learning models, have high prediction accuracy, but require a lot of computing resources for training and calculation. A lot of manpower, material and financial resources are required. Summary of the invention

[0004] The embodiment of the present invention provides an intelligent unit operation optimization prediction method and system. The present invention can perform comprehensive operation performance prediction on the intelligent unit, improve performance prediction accuracy and prediction efficiency, avoid production interruption and loss caused by sudden shutdown of the intelligent unit, and enable enterprises to more reasonably arrange maintenance time and intervals of the intelligent unit.

[0005] In order to achieve the above object, the present invention provides an intelligent unit operation optimization prediction method, comprising:

[0006] Determine the intelligent unit equipment for which the performance prediction is to be performed, pre-deploy a plurality of operation data collection points on the intelligent unit equipment, and collect the equipment operation change data of the intelligent unit equipment based on the operation data collection points;

[0007] Determine an equipment operation change data sequence according to the equipment operation change data corresponding to each operation data collection point, and calculate an equipment operation change data deviation factor of each equipment operation change data in the equipment operation change data sequence;

[0008] Performing an integrated analysis on the equipment operation change data deviation factor, determining a plurality of equipment operation change data deviation factor sets based on the integrated analysis result, and calculating the sub-operation performance prediction coefficient corresponding to the operation data collection point according to the equipment operation change data deviation factor sets;

[0009] Determine a data tree, extract all sub-operation performance prediction coefficients, deploy all sub-operation performance prediction coefficients to the data tree, and calculate the operation performance prediction coefficient of the intelligent unit equipment based on the deployment result, wherein the data tree includes a main data trunk, a left data branch, and a right data branch;

[0010] Based on the relationship between the operating performance prediction coefficient and the preset operating performance prediction coefficient, it is determined whether the operating state of the intelligent unit equipment needs to be optimized.

[0011] Furthermore, when calculating the device operation change data deviation factor of each device operation change data in the device operation change data sequence, it includes:

[0012] Calculate the equipment operation change data deviation factor for each equipment operation change data according to the following formula:

[0013] ;

[0014] Among them, p is the equipment operation change data deviation factor, e is a constant, u is the equipment operation change data, and u1 is the preset equipment operation change data.

[0015] Furthermore, when the device operation change data deviation factor is integrated and analyzed, and a plurality of device operation change data deviation factor sets are determined based on the integrated analysis result, the method includes:

[0016] Randomly select a first device operation change data deviation factor as a first cluster center, and determine a first cluster distance from all remaining device operation change data deviation factors to the first cluster center;

[0017] All first clustering distances are sorted by numerical value, and a first clustering distance sequence is constructed based on the sorting results;

[0018] Determine a first sequence mean of the first cluster distance sequence, and mark the sequence mean in the first cluster distance sequence as a first sequence marking point;

[0019] The maximum first cluster distance and the first cluster distance in the first sequence annotation point are used as the first sub-cluster distance sequence, and the equipment operation change data deviation factors corresponding to the first y first cluster distances are selected as the first cluster distance to be fused;

[0020] The minimum first cluster distance and the first cluster distance in the first sequence of annotation points are used as the second sub-cluster distance sequence, and the equipment operation change data deviation factors corresponding to the first y-2 first cluster distances are selected as the second cluster distance to be fused;

[0021] Determine a first sub-device operation change data deviation factor set based on the first device operation change data deviation factor, the first to-be-fused cluster distance, and the second to-be-fused cluster distance;

[0022] Randomly select a second device operation change data deviation factor as a second cluster center, and determine a second cluster distance from all remaining device operation change data deviation factors to the second cluster center;

[0023] All the second clustering distances are sorted by numerical value, and a second clustering distance sequence is constructed based on the sorting results;

[0024] Determine a second sequence mean of the second cluster distance sequence, and mark the second sequence mean in the second cluster distance sequence as a second sequence marking point;

[0025] The maximum second cluster distance and the second cluster distance in the second sequence annotation point are used as the third sub-cluster distance sequence, and the equipment operation change data deviation factors corresponding to the first y second cluster distances are selected as the third cluster distance to be fused;

[0026] The minimum second cluster distance and the second cluster distance in the second sequence annotation point are used as the fourth sub-cluster distance sequence, and the equipment operation change data deviation factors corresponding to the first y-2 second cluster distances are selected as the fourth cluster distance to be fused;

[0027] Determine a second sub-device operation change data deviation factor set based on the second device operation change data deviation factor, the third to-be-fused cluster distance, and the fourth to-be-fused cluster distance;

[0028] Randomly select a third device operation change data deviation factor as a third cluster center, and determine a third cluster distance from all remaining device operation change data deviation factors to the third cluster center;

[0029] All third clustering distances are sorted by numerical value, and a third clustering distance sequence is constructed based on the sorting results;

[0030] Determine a third sequence mean of the third clustering distance sequence, and mark the third sequence mean in the third clustering distance sequence as a third sequence marking point;

[0031] The maximum third cluster distance and the third cluster distance in the third sequence annotation point are used as the fourth sub-cluster distance sequence, and the equipment operation change data deviation factors corresponding to the first y third cluster distances are selected as the fifth cluster distance to be fused;

[0032] The minimum third cluster distance and the third cluster distance in the third sequence annotation point are used as the sixth sub-cluster distance sequence, and the equipment operation change data deviation factors corresponding to the first y-2 third cluster distances are selected as the fifth cluster distance to be fused;

[0033] Determine a third sub-device operation change data deviation factor set based on the third device operation change data deviation factor, the fifth to-be-fused cluster distance, and the sixth to-be-fused cluster distance;

[0034] A device operation change data deviation factor set is determined based on the first sub-device operation change data deviation factor set, the second sub-device operation change data deviation factor set, and the third sub-device operation change data deviation factor set.

[0035] Further, when determining the device operation change data deviation factor set based on the first sub-device operation change data deviation factor set, the second sub-device operation change data deviation factor set and the third sub-device operation change data deviation factor set, it includes:

[0036] Calculate a first set value of a deviation factor set of the first sub-device operation change data;

[0037] Calculate a second set value of the second sub-device operation change data deviation factor set;

[0038] Calculating a third set value of the third sub-device operation change data deviation factor set;

[0039] Calculate a first set difference between the first set value and the second set value, calculate a second set difference between the first set value and the third set value, and calculate a third set difference between the second set value and the third set value;

[0040] Determine whether the first set difference, the second set difference and the third set difference are all less than a preset set difference; if so, fuse the first sub-device operation change data deviation factor set, the second sub-device operation change data deviation factor set and the third sub-device operation change data deviation factor set to obtain a device operation change data deviation factor set;

[0041] If not, randomly select the fourth equipment operation change data deviation factor, the fifth equipment operation change data deviation factor and the sixth equipment operation change data deviation factor;

[0042] Repeat the iteration to obtain a set of deviation factors of multiple equipment operation change data.

[0043] Further, when calculating the first set value of the deviation factor set of the first sub-device operation change data, it includes:

[0044] ;

[0045] Wherein, t1 is the first set value of the first sub-device operation change data deviation factor set, r is the number of device operation change data deviation factors in the first sub-device operation change data deviation factor set, e i is the i-th device operation change data deviation factor in the first sub-device operation change data deviation factor set, w is the average value corresponding to the first sub-device operation change data deviation factor set, and w2 is the variance of all device operation change data deviation factors except the i-th device operation change data deviation factor.

[0046] Further, when calculating the sub-operation performance prediction coefficient corresponding to the operation data collection point according to the equipment operation change data deviation factor set, it includes:

[0047] Setting a first calculation coefficient for the first set of values, setting a second calculation coefficient for the second set of values, and setting a third calculation coefficient for the third set of values;

[0048] The sub-operation performance prediction coefficient corresponding to the operation data collection point is calculated according to the first set value, the second set value, the third set value, the first calculation coefficient, the second calculation coefficient and the third calculation coefficient.

[0049] Further, when all sub-operation performance prediction coefficients are extracted, all sub-operation performance prediction coefficients are deployed on the data tree, and the operation performance prediction coefficient of the intelligent unit equipment is calculated based on the deployment result, it includes:

[0050] Deploy all sub-operation performance prediction coefficients to the main data trunk, left data branch and right data branch of the data tree based on the random deployment principle of the binary tree;

[0051] Extracting the sub-operation performance prediction coefficients on the left data branch as a left data branch set;

[0052] Extracting the sub-operation performance prediction coefficients on the right data branch as a right data branch set;

[0053] Extracting sub-operation performance prediction coefficients on the main data trunk as a main data trunk set;

[0054] Randomly combining the sub-operation performance prediction coefficients in the left data branch set and the right data branch set in pairs to obtain a plurality of sub-operation performance prediction coefficient sets;

[0055] Counting the number of master and sub-operation performance prediction coefficients of the master data trunk set;

[0056] The operation performance prediction coefficient of the intelligent unit equipment is calculated according to the sub-operation performance prediction coefficient set and the number of the main and sub-operation performance prediction coefficients.

[0057] Further, when calculating the operation performance prediction coefficient of the intelligent unit equipment according to the sub-operation performance prediction coefficient set and the number of the main and sub-operation performance prediction coefficients, it includes:

[0058] The operating performance prediction coefficient of the intelligent unit equipment is calculated according to the following formula:

[0059] ;

[0060] Among them, q is the operation performance prediction coefficient of the intelligent unit equipment, e is a constant, s1 is the number of sub-operation performance prediction coefficients in the left data branch set, s2 is the number of sub-operation performance prediction coefficients in the right data branch set, s3 is the number of main and sub-operation performance prediction coefficients, d is the number of sub-operation performance prediction coefficient sets, g j is a sub-operation performance prediction coefficient in the j-th sub-operation performance prediction coefficient set, h j is another sub-running performance prediction coefficient in the j-th sub-running performance prediction coefficient set, c1 max is the maximum sub-run performance prediction coefficient in the left data branch set, c2 max The maximum sub-run performance prediction coefficient in the main data stem set, c3 max is the maximum sub-run performance prediction coefficient in the right data branch set.

[0061] Further, when judging whether it is necessary to optimize the operating state of the intelligent unit equipment based on the relationship between the operating performance prediction coefficient and the preset operating performance prediction coefficient, it includes:

[0062] When the operation performance prediction coefficient is less than the preset operation performance prediction coefficient, it is determined that the operation state of the intelligent unit equipment needs to be optimized;

[0063] When the operating performance prediction coefficient is greater than or equal to the preset operating performance prediction coefficient, it is determined that there is no need to optimize the operating state of the intelligent unit equipment.

[0064] In order to achieve the above object, the present invention also provides an intelligent unit operation optimization prediction system, comprising:

[0065] A data collection module is used to determine the intelligent unit equipment to be predicted for operation performance, pre-deploy multiple operation data collection points on the intelligent unit equipment, and collect equipment operation change data of the intelligent unit equipment based on the operation data collection points;

[0066] A first calculation module is used to determine an equipment operation change data sequence according to the equipment operation change data corresponding to each operation data collection point, and calculate the equipment operation change data deviation factor of each equipment operation change data in the equipment operation change data sequence;

[0067] A second calculation module is used to perform an integrated analysis on the equipment operation change data deviation factor, determine a plurality of equipment operation change data deviation factor sets based on the integrated analysis result, and calculate the sub-operation performance prediction coefficient corresponding to the operation data collection point according to the equipment operation change data deviation factor set;

[0068] a third calculation module, configured to determine a data tree, extract all sub-operation performance prediction coefficients, deploy all sub-operation performance prediction coefficients to the data tree, and calculate the operation performance prediction coefficient of the intelligent unit equipment based on the deployment result, wherein the data tree includes a main data trunk, a left data branch, and a right data branch;

[0069] The performance prediction module is used to determine whether it is necessary to optimize the operating state of the intelligent unit equipment based on the relationship between the operating performance prediction coefficient and the preset operating performance prediction coefficient.

[0070] Compared with the prior art, the present invention has the following beneficial effects:

[0071] The present invention discloses an intelligent unit operation optimization prediction method and system, which pre-deploys multiple operation data collection points on the intelligent unit equipment to collect equipment operation change data; determines the equipment operation change data sequence according to the equipment operation change data, and calculates the equipment operation change data deviation factor; determines multiple equipment operation change data deviation factor sets, and calculates the sub-operation performance prediction coefficient; extracts all the sub-operation performance prediction coefficients, deploys them on a data tree, and calculates the operation performance prediction coefficient; judges whether it is necessary to optimize the operation status of the intelligent unit equipment based on the operation performance prediction coefficient and the preset operation performance prediction coefficient, and can perform comprehensive operation performance prediction on the intelligent unit, improve performance prediction accuracy and prediction efficiency, avoid production interruption and loss caused by sudden shutdown of the intelligent unit, and enable the enterprise to more reasonably arrange the maintenance time and interval of the intelligent unit. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0073] Figure 1 A schematic flow chart of an intelligent unit operation optimization prediction method in an embodiment of the present invention is shown;

[0074] Figure 2 A structural schematic diagram of an intelligent unit operation optimization prediction system in an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0075] The specific implementation of the present invention is further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0076] In the description of the present application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0077] The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0078] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0079] The following is a description of preferred embodiments of the present invention with reference to the accompanying drawings.

[0080] like Figure 1 As shown, an embodiment of the present invention discloses an intelligent unit operation optimization prediction method, comprising:

[0081] S110: determining an intelligent unit device for which performance prediction is to be performed, pre-deploying a plurality of operation data collection points on the intelligent unit device, and collecting equipment operation change data of the intelligent unit device based on the operation data collection points;

[0082] In this embodiment, the intelligent unit equipment refers to the equipment in the intelligent unit that needs to perform performance prediction.

[0083] In this embodiment, according to the structure, working principle and location of key components of the intelligent unit equipment, the operation data collection points are reasonably arranged to obtain the most representative equipment operation change data. Here, the specific deployment number of operation data collection points is preferably 10.

[0084] In this embodiment, the equipment operation change data includes operating temperature, operating pressure, operating speed, operating vibration, operating energy consumption, etc.

[0085] S120: determining an equipment operation change data sequence according to the equipment operation change data corresponding to each operation data collection point, and calculating an equipment operation change data deviation factor of each equipment operation change data in the equipment operation change data sequence;

[0086] In this embodiment, there are several operation data collection points, corresponding to several equipment operation change data sequences.

[0087] In some embodiments of the present application, when calculating the device operation change data deviation factor of each device operation change data in the device operation change data sequence, it includes:

[0088] Calculate the equipment operation change data deviation factor for each equipment operation change data according to the following formula:

[0089] ;

[0090] Among them, p is the equipment operation change data deviation factor, e is a constant, u is the equipment operation change data, and u1 is the preset equipment operation change data.

[0091] In this embodiment, the preset equipment operation change data corresponds to the equipment operation change data one by one, and the preset equipment operation change data can be dynamically set according to the intelligent unit equipment. As mentioned above, the preset equipment operation change data corresponding to the operating temperature is 23°C, and the rest can be set according to the actual situation, and will not be shown one by one here.

[0092] In this embodiment, the above formula represents the gap between the actual operating state and the ideal state of the intelligent unit equipment, which is weighted in the form of an exponential function.

[0093] In this embodiment, as As the value increases, the gap between the actual operating state of the intelligent unit equipment and the ideal state increases, and the actual operating state of the equipment deviates further from the ideal state. Therefore, the greater the deviation factor of the equipment operation change data, the greater the degree of equipment performance degradation. The above formula can be used to quantify the difference between the actual operating state of the equipment and the ideal state, and to reflect the degree of deviation between the equipment operation change data and the preset equipment operation change data.

[0094] The beneficial effect of the above technical solution is: the present invention calculates the device operation change data deviation factor of each device operation change data in the device operation change data sequence, thereby providing a basis for determining the device operation change data sequence, and the device operation change data deviation factor reflects the degree of deviation of the device operation change data relative to the preset device operation change data.

[0095] S130: performing an integrated analysis on the equipment operation change data deviation factor, determining a plurality of equipment operation change data deviation factor sets based on the integrated analysis result, and calculating the sub-operation performance prediction coefficient corresponding to the operation data collection point according to the equipment operation change data deviation factor sets;

[0096] In some embodiments of the present application, when the device operation change data deviation factor is integrated and analyzed, and multiple device operation change data deviation factor sets are determined based on the integrated analysis result, the method includes:

[0097] Randomly select a first device operation change data deviation factor as a first cluster center, and determine a first cluster distance from all remaining device operation change data deviation factors to the first cluster center;

[0098] All first clustering distances are sorted by numerical value, and a first clustering distance sequence is constructed based on the sorting results;

[0099] Determine a first sequence mean of the first cluster distance sequence, and mark the sequence mean in the first cluster distance sequence as a first sequence marking point;

[0100] The maximum first cluster distance and the first cluster distance in the first sequence annotation point are used as the first sub-cluster distance sequence, and the equipment operation change data deviation factors corresponding to the first y first cluster distances are selected as the first cluster distance to be fused;

[0101] The minimum first cluster distance and the first cluster distance in the first sequence of annotation points are used as the second sub-cluster distance sequence, and the equipment operation change data deviation factors corresponding to the first y-2 first cluster distances are selected as the second cluster distance to be fused;

[0102] Determine a first sub-device operation change data deviation factor set based on the first device operation change data deviation factor, the first to-be-fused cluster distance, and the second to-be-fused cluster distance;

[0103] Randomly select a second device operation change data deviation factor as a second cluster center, and determine a second cluster distance from all remaining device operation change data deviation factors to the second cluster center;

[0104] All the second clustering distances are sorted by numerical value, and a second clustering distance sequence is constructed based on the sorting results;

[0105] Determine a second sequence mean of the second cluster distance sequence, and mark the second sequence mean in the second cluster distance sequence as a second sequence marking point;

[0106] The maximum second cluster distance and the second cluster distance in the second sequence annotation point are used as the third sub-cluster distance sequence, and the equipment operation change data deviation factors corresponding to the first y second cluster distances are selected as the third cluster distance to be fused;

[0107] The minimum second cluster distance and the second cluster distance in the second sequence annotation point are used as the fourth sub-cluster distance sequence, and the equipment operation change data deviation factors corresponding to the first y-2 second cluster distances are selected as the fourth cluster distance to be fused;

[0108] Determine a second sub-device operation change data deviation factor set based on the second device operation change data deviation factor, the third to-be-fused cluster distance, and the fourth to-be-fused cluster distance;

[0109] Randomly select a third device operation change data deviation factor as a third cluster center, and determine a third cluster distance from all remaining device operation change data deviation factors to the third cluster center;

[0110] All third clustering distances are sorted by numerical value, and a third clustering distance sequence is constructed based on the sorting results;

[0111] Determine a third sequence mean of the third clustering distance sequence, and mark the third sequence mean in the third clustering distance sequence as a third sequence marking point;

[0112] The maximum third cluster distance and the third cluster distance in the third sequence annotation point are used as the fourth sub-cluster distance sequence, and the equipment operation change data deviation factors corresponding to the first y third cluster distances are selected as the fifth cluster distance to be fused;

[0113] The minimum third cluster distance and the third cluster distance in the third sequence annotation point are used as the sixth sub-cluster distance sequence, and the equipment operation change data deviation factors corresponding to the first y-2 third cluster distances are selected as the fifth cluster distance to be fused;

[0114] Determine a third sub-device operation change data deviation factor set based on the third device operation change data deviation factor, the fifth to-be-fused cluster distance, and the sixth to-be-fused cluster distance;

[0115] A device operation change data deviation factor set is determined based on the first sub-device operation change data deviation factor set, the second sub-device operation change data deviation factor set, and the third sub-device operation change data deviation factor set.

[0116] In this embodiment, the method for determining the clustering distance is not further described here.

[0117] In this embodiment, the first sub-cluster distance sequence does not include the first sequence annotation point.

[0118] In this embodiment, y is preferably 4.

[0119] In this embodiment, the second sub-cluster distance sequence does not include the first sequence annotation points.

[0120] In this embodiment, the third sub-cluster distance sequence does not include the second sequence annotation points.

[0121] In this embodiment, the fourth sub-cluster distance sequence does not include the third sequence annotation points.

[0122] In this embodiment, the fifth sub-cluster distance sequence does not include the fifth sequence annotation point.

[0123] In this embodiment, the first device operation change data deviation factor, the device operation change data deviation factor corresponding to the first cluster distance to be merged, and the device operation change data deviation factor corresponding to the second cluster distance to be merged are used to determine the first sub-device operation change data deviation factor set.

[0124] In this embodiment, the second device operation change data deviation factor, the device operation change data deviation factor corresponding to the third cluster distance to be merged, and the device operation change data deviation factor corresponding to the fourth cluster distance to be merged are used to determine the second sub-device operation change data deviation factor set.

[0125] In this embodiment, the third device operation change data deviation factor, the device operation change data deviation factor corresponding to the fifth cluster distance to be merged, and the device operation change data deviation factor corresponding to the sixth cluster distance to be merged are used to determine the third sub-device operation change data deviation factor set.

[0126] The beneficial effect of the above technical solution is: the present invention determines the device operation change data deviation factor set based on the first sub-device operation change data deviation factor set, the second sub-device operation change data deviation factor set and the third sub-device operation change data deviation factor set, thereby ensuring the comprehensiveness and accuracy of the determination of the third sub-device operation change data deviation factor set, and providing data support for determining the device operation change data deviation factor set.

[0127] In some embodiments of the present application, when determining a set of device operation change data deviation factors based on the first sub-device operation change data deviation factor set, the second sub-device operation change data deviation factor set, and the third sub-device operation change data deviation factor set, the method includes:

[0128] Calculate a first set value of a deviation factor set of the first sub-device operation change data;

[0129] Calculate a second set value of the second sub-device operation change data deviation factor set;

[0130] Calculating a third set value of the third sub-device operation change data deviation factor set;

[0131] Calculate a first set difference between the first set value and the second set value, calculate a second set difference between the first set value and the third set value, and calculate a third set difference between the second set value and the third set value;

[0132] Determine whether the first set difference, the second set difference and the third set difference are all less than a preset set difference; if so, fuse the first sub-device operation change data deviation factor set, the second sub-device operation change data deviation factor set and the third sub-device operation change data deviation factor set to obtain a device operation change data deviation factor set;

[0133] If not, randomly select the fourth equipment operation change data deviation factor, the fifth equipment operation change data deviation factor and the sixth equipment operation change data deviation factor;

[0134] Repeat the iteration to obtain a set of deviation factors of multiple equipment operation change data.

[0135] In this embodiment, the preset set difference value is preferably 4, and can be adaptively adjusted according to actual conditions.

[0136] In this embodiment, if the first set difference, the second set difference and the third set difference are all less than the preset set difference, the first sub-device operation change data deviation factor set, the second sub-device operation change data deviation factor set and the third sub-device operation change data deviation factor set are data fused to obtain a device operation change data deviation factor set, and these data no longer participate in subsequent random selection and calculation. Data fusion means putting all the data together to construct a set. If not, the selected first device operation change data deviation factor, the second device operation change data deviation factor and the third device operation change data deviation factor need to be recalculated, and the randomly selected fourth device operation change data deviation factor cannot be the above-mentioned randomly selected first device operation change data deviation factor. Repeat the above steps until all device operation change data deviation factors have been traversed.

[0137] The beneficial effect of the above technical solution is that: after repeated iterations, the present invention can obtain multiple sets of equipment operation change data deviation factors, and through sufficient combination, analysis and calculation of all equipment operation change data deviation factors, an objective set of equipment operation change data deviation factors is obtained, thereby ensuring the accuracy of subsequent calculations and avoiding calculation errors.

[0138] In some embodiments of the present application, when calculating the first set value of the deviation factor set of the first sub-device operation change data, it includes:

[0139] ;

[0140] Wherein, t1 is the first set value of the first sub-device operation change data deviation factor set, r is the number of device operation change data deviation factors in the first sub-device operation change data deviation factor set, e i is the i-th device operation change data deviation factor in the first sub-device operation change data deviation factor set, w is the average value corresponding to the first sub-device operation change data deviation factor set, and w2 is the variance of all device operation change data deviation factors except the i-th device operation change data deviation factor.

[0141] In this embodiment, , this part calculates the sum of the absolute differences between the deviation factor of each device operation change data and the average value. The absolute difference indicates the degree of deviation between the deviation factor of each device operation change data and the average value, and the sum indicates the degree of deviation of all device operation change data deviation factors from the average value as a whole. This part reflects the degree of dispersion of the data, that is, how far the data point is from the average value.

[0142] In this embodiment, This part first calculates the variance of each equipment operation change data deviation factor and the other equipment operation change data deviation factors after removing this factor (that is, the degree of dispersion of the remaining factors), and then averages these variances. Variance is an indicator of the degree of dispersion of data distribution. By calculating the variance, we can understand the fluctuation of the data. The purpose of averaging the variance is to obtain a standardized value so that sets of different sizes can be compared.

[0143] In this embodiment, t1 obtained by adding the two parts comprehensively reflects the overall discreteness and fluctuation of the deviation factor set of the first sub-device operation change data. Specifically, it takes into account both the direct deviation between each deviation factor and the average value and the fluctuation of the remaining factors after removing a certain deviation factor. This comprehensive consideration helps to more accurately evaluate the operation changes of the equipment, thereby providing a more reliable basis for subsequent analysis and decision-making. This formula combines absolute deviation and standardized variance to evaluate the overall discreteness and fluctuation of the deviation factor set of the equipment operation change data, providing a comprehensive and detailed analysis method that helps to more accurately understand and predict the operating status of the equipment.

[0144] In this embodiment, the calculation method of the second set value and the third set value is consistent with that of the first set value. In order to avoid redundant space, they are not repeated here. The above formula can be adaptively adjusted for calculation.

[0145] In some embodiments of the present application, when calculating the sub-operation performance prediction coefficient corresponding to the operation data collection point according to the equipment operation change data deviation factor set, it includes:

[0146] Setting a first calculation coefficient for the first set of values, setting a second calculation coefficient for the second set of values, and setting a third calculation coefficient for the third set of values;

[0147] The sub-operation performance prediction coefficient corresponding to the operation data collection point is calculated according to the first set value, the second set value, the third set value, the first calculation coefficient, the second calculation coefficient and the third calculation coefficient.

[0148] In this embodiment, the sub-operation performance prediction coefficient corresponding to the operation data collection point is calculated according to the following formula:

[0149] ;

[0150] Among them, b is the sub-operation performance prediction coefficient corresponding to the operation data collection point, n1 is the first calculation coefficient, n2 is the second calculation coefficient, n3 is the third calculation coefficient, t2 is the second set value, and t3 is the third set value.

[0151] In this embodiment, the calculation coefficient is used to reflect the contribution degree of the corresponding set value, where n1>n2>n3, and can be set according to actual needs. For example, n1 is preferably 0.8, n2 is preferably 0.6, and n3 is preferably 0.4.

[0152] In this embodiment, through these three set values ​​and their corresponding calculation coefficients, the above formula can comprehensively consider the performance of the operation data collection points. This multi-dimensional method helps to improve the accuracy and reliability of the prediction, not only considering the average level of performance, but also considering the volatility and complex characteristics of the data. The sub-operation performance prediction coefficient b finally obtained can serve as an important basis for evaluating and managing the overall performance of intelligent unit equipment.

[0153] The beneficial effect of the above technical solution is: the present invention calculates the sub-operation performance prediction coefficient corresponding to the operation data collection point according to the first set value, the second set value, the third set value, the first calculation coefficient, the second calculation coefficient and the third calculation coefficient, thereby ensuring the calculation accuracy of the sub-operation performance prediction coefficient, realizing the initial performance prediction of a single operation data collection point, and further ensuring the overall performance prediction of the intelligent unit equipment.

[0154] S140: determining a data tree, extracting all sub-operation performance prediction coefficients, deploying all sub-operation performance prediction coefficients on the data tree, and calculating the operation performance prediction coefficient of the intelligent unit equipment based on the deployment result, wherein the data tree includes a main data trunk, a left data branch, and a right data branch;

[0155] In this embodiment, the data tree includes a main data trunk, a left data branch and a right data branch, which are used to store data.

[0156] In some embodiments of the present application, when extracting all sub-operation performance prediction coefficients, deploying all sub-operation performance prediction coefficients to the data tree, and calculating the operation performance prediction coefficient of the intelligent unit equipment based on the deployment result, it includes:

[0157] Deploy all sub-operation performance prediction coefficients to the main data trunk, left data branch and right data branch of the data tree based on the random deployment principle of the binary tree;

[0158] Extracting the sub-operation performance prediction coefficients on the left data branch as a left data branch set;

[0159] Extracting the sub-operation performance prediction coefficients on the right data branch as a right data branch set;

[0160] Extracting sub-operation performance prediction coefficients on the main data trunk as a main data trunk set;

[0161] Randomly combining the sub-operation performance prediction coefficients in the left data branch set and the right data branch set in pairs to obtain a plurality of sub-operation performance prediction coefficient sets;

[0162] Counting the number of master and sub-operation performance prediction coefficients of the master data trunk set;

[0163] The operation performance prediction coefficient of the intelligent unit equipment is calculated according to the sub-operation performance prediction coefficient set and the number of the main and sub-operation performance prediction coefficients.

[0164] In this embodiment, the random deployment principle of the binary tree includes a recursive construction method and a hierarchical traversal construction method. Recursive construction method: Starting from the main data trunk, for each data branch, randomly select a data point as the value of its data branch. Then, for the remaining data points, continue to assign values ​​to the data branches in the same way until all data points are assigned to the corresponding positions in the data tree. For example, assuming that there is a set of data [1, 2, 3, 4, 5], first randomly select two of them as the values ​​of the main data trunk, such as 3, 4, and then randomly assign the remaining [1, 2, 5] to the left data branch and the right data branch of the main data trunk. Hierarchical traversal construction method: According to the hierarchical structure of the binary tree, data points are assigned to the main data trunk, the left data branch, and the right data branch from top to bottom and from left to right. In each layer, randomly select a data point that has not been assigned as the value of the main data trunk, the left data branch, and the right data branch, and then continue to assign it to the next layer until all data are used up. The deployment of the sub-run performance prediction coefficient can be selected according to actual conditions.

[0165] In this embodiment, the sub-operation performance prediction coefficients in the left data branch set and the right data branch set are randomly combined in pairs. If there are uncombined sub-operation performance prediction coefficients, they are deleted and do not participate in the calculation.

[0166] The beneficial effect of the above technical solution is: the present invention calculates the operating performance prediction coefficient of the intelligent unit equipment according to the sub-operating performance prediction coefficient set and the number of main and sub-operating performance prediction coefficients, thereby ensuring the calculation accuracy of the operating performance prediction coefficient. At the same time, the operating performance of the intelligent unit equipment can be reflected through the operating performance prediction coefficient, without the need for human participation in judgment, thereby reducing performance prediction errors and avoiding deviations caused by subjective judgment.

[0167] In some embodiments of the present application, when calculating the operation performance prediction coefficient of the intelligent unit equipment according to the sub-operation performance prediction coefficient set and the number of the main and sub-operation performance prediction coefficients, it includes:

[0168] The operating performance prediction coefficient of the intelligent unit equipment is calculated according to the following formula:

[0169] ;

[0170] Among them, q is the operation performance prediction coefficient of the intelligent unit equipment, e is a constant, s1 is the number of sub-operation performance prediction coefficients in the left data branch set, s2 is the number of sub-operation performance prediction coefficients in the right data branch set, s3 is the number of main and sub-operation performance prediction coefficients, d is the number of sub-operation performance prediction coefficient sets, g j is a sub-operation performance prediction coefficient in the j-th sub-operation performance prediction coefficient set, h j is another sub-running performance prediction coefficient in the j-th sub-running performance prediction coefficient set, c1 max is the maximum sub-run performance prediction coefficient in the left data branch set, c2 max The maximum sub-run performance prediction coefficient in the main data stem set, c3 max is the maximum sub-run performance prediction coefficient in the right data branch set.

[0171] In this embodiment, the sub-operation performance prediction coefficients obtained above are randomly allocated and analyzed, and the entire formula can be regarded as adjusting the obtained operation performance prediction coefficient q based on the reference value 1 according to the ratio of the number of samples in the left and right data branch sets and the difference between each sub-operation performance prediction coefficient set. This operation performance prediction coefficient q comprehensively considers the distribution of data (reflected by s1, s2, and s3) and the performance difference between each subset (reflected by the summation term), thereby providing a more comprehensive and objective equipment operation performance evaluation indicator.

[0172] In this embodiment, the above formula fully considers the actual operating conditions of the unit, including operating temperature, operating pressure, operating speed, operating vibration, operating energy consumption and other factors, and can reflect the performance change trend of the unit under different operating conditions, ensuring that it can be applied to the performance prediction of intelligent unit equipment, thereby improving the consistency with the actual operation of the unit and comprehensively reflecting the operating performance of the intelligent unit equipment.

[0173] S150: Based on the relationship between the operating performance prediction coefficient and the preset operating performance prediction coefficient, determine whether it is necessary to optimize the operating state of the intelligent unit equipment.

[0174] In some embodiments of the present application, when judging whether it is necessary to optimize the operating state of the intelligent unit equipment based on the relationship between the operating performance prediction coefficient and the preset operating performance prediction coefficient, it includes:

[0175] When the operation performance prediction coefficient is less than the preset operation performance prediction coefficient, it is determined that the operation state of the intelligent unit equipment needs to be optimized;

[0176] When the operating performance prediction coefficient is greater than or equal to the preset operating performance prediction coefficient, it is determined that there is no need to optimize the operating state of the intelligent unit equipment.

[0177] In this embodiment, the preset operating performance prediction coefficient is preferably 4, and can be adjusted according to actual needs.

[0178] In this embodiment, when the operating performance prediction coefficient is larger, the performance of the intelligent unit equipment is better, and the maintenance time and interval of the intelligent unit are extended. Conversely, when the operating performance prediction coefficient is smaller, the performance of the intelligent unit equipment is worse, and the maintenance time and interval of the intelligent unit are shortened.

[0179] The beneficial effect of the above technical solution is that the present invention can make a comprehensive operating performance prediction for the intelligent unit, improve the performance prediction accuracy and prediction efficiency, avoid production interruptions and losses caused by sudden shutdown of the intelligent unit, and enable the enterprise to arrange the maintenance time and interval of the intelligent unit more reasonably.

[0180] In order to further explain the technical idea of ​​the present invention, the technical solution of the present invention is now described in combination with specific application scenarios.

[0181] Correspondingly, such as Figure 2 As shown, the present application also provides an intelligent unit operation optimization prediction system, including:

[0182] A data collection module is used to determine the intelligent unit equipment to be predicted for operation performance, pre-deploy multiple operation data collection points on the intelligent unit equipment, and collect equipment operation change data of the intelligent unit equipment based on the operation data collection points;

[0183] A first calculation module is used to determine an equipment operation change data sequence according to the equipment operation change data corresponding to each operation data collection point, and calculate the equipment operation change data deviation factor of each equipment operation change data in the equipment operation change data sequence;

[0184] A second calculation module is used to perform an integrated analysis on the equipment operation change data deviation factor, determine a plurality of equipment operation change data deviation factor sets based on the integrated analysis result, and calculate the sub-operation performance prediction coefficient corresponding to the operation data collection point according to the equipment operation change data deviation factor set;

[0185] a third calculation module, configured to determine a data tree, extract all sub-operation performance prediction coefficients, deploy all sub-operation performance prediction coefficients to the data tree, and calculate the operation performance prediction coefficient of the intelligent unit equipment based on the deployment result, wherein the data tree includes a main data trunk, a left data branch, and a right data branch;

[0186] The performance prediction module is used to determine whether it is necessary to optimize the operating state of the intelligent unit equipment based on the relationship between the operating performance prediction coefficient and the preset operating performance prediction coefficient.

[0187] In the description of the above embodiments, specific features, structures, materials or characteristics may be combined in a suitable manner in any one or more embodiments or examples.

[0188] Although the present invention has been described above with reference to the embodiments, various modifications may be made thereto and parts thereof may be replaced with equivalents without departing from the scope of the present invention. In particular, as long as there is no structural conflict, the various features in the embodiments disclosed by the present invention may be used in combination with each other in any manner, and the fact that these combinations are not fully described in this specification is only for the sake of omitting space and saving resources.

[0189] Those skilled in the art can understand that the above are only preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions recorded in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An intelligent unit operation optimization prediction method, characterized in that: include: Determine the intelligent unit equipment for which the performance prediction is to be performed, pre-deploy a plurality of operation data collection points on the intelligent unit equipment, and collect the equipment operation change data of the intelligent unit equipment based on the operation data collection points; Determine an equipment operation change data sequence according to the equipment operation change data corresponding to each operation data collection point, and calculate an equipment operation change data deviation factor of each equipment operation change data in the equipment operation change data sequence; Performing an integrated analysis on the equipment operation change data deviation factor, determining a plurality of equipment operation change data deviation factor sets based on the integrated analysis result, and calculating the sub-operation performance prediction coefficient corresponding to the operation data collection point according to the equipment operation change data deviation factor sets; Determine a data tree, extract all sub-operation performance prediction coefficients, deploy all sub-operation performance prediction coefficients to the data tree, and calculate the operation performance prediction coefficient of the intelligent unit equipment based on the deployment result, wherein the data tree includes a main data trunk, a left data branch, and a right data branch; Based on the relationship between the operating performance prediction coefficient and the preset operating performance prediction coefficient, it is determined whether the operating state of the intelligent unit equipment needs to be optimized.

2. The intelligent unit operation optimization prediction method according to claim 1 is characterized in that: When calculating the device operation change data deviation factor of each device operation change data in the device operation change data sequence, it includes: Calculate the equipment operation change data deviation factor for each equipment operation change data according to the following formula: ； Among them, p is the equipment operation change data deviation factor, e is a constant, u is the equipment operation change data, and u1 is the preset equipment operation change data.

3. The intelligent unit operation optimization prediction method according to claim 1 is characterized in that: When the equipment operation change data deviation factor is integrated and analyzed, and a plurality of equipment operation change data deviation factor sets are determined based on the integrated analysis result, the method includes: Randomly select a first device operation change data deviation factor as a first cluster center, and determine a first cluster distance from all remaining device operation change data deviation factors to the first cluster center; All first clustering distances are sorted by numerical value, and a first clustering distance sequence is constructed based on the sorting results; Determine a first sequence mean of the first cluster distance sequence, and mark the sequence mean in the first cluster distance sequence as a first sequence marking point; The maximum first cluster distance and the first cluster distance in the first sequence annotation point are used as the first sub-cluster distance sequence, and the equipment operation change data deviation factors corresponding to the first y first cluster distances are selected as the first cluster distance to be fused; The minimum first cluster distance and the first cluster distance in the first sequence of annotation points are used as the second sub-cluster distance sequence, and the equipment operation change data deviation factors corresponding to the first y-2 first cluster distances are selected as the second cluster distance to be fused; Determine a first sub-device operation change data deviation factor set based on the first device operation change data deviation factor, the first to-be-fused cluster distance, and the second to-be-fused cluster distance; Randomly select a second device operation change data deviation factor as a second cluster center, and determine a second cluster distance from all remaining device operation change data deviation factors to the second cluster center; All the second clustering distances are sorted by numerical value, and a second clustering distance sequence is constructed based on the sorting results; Determine a second sequence mean of the second cluster distance sequence, and mark the second sequence mean in the second cluster distance sequence as a second sequence marking point; The maximum second cluster distance and the second cluster distance in the second sequence annotation point are used as the third sub-cluster distance sequence, and the equipment operation change data deviation factors corresponding to the first y second cluster distances are selected as the third cluster distance to be fused; The minimum second cluster distance and the second cluster distance in the second sequence annotation point are used as the fourth sub-cluster distance sequence, and the equipment operation change data deviation factors corresponding to the first y-2 second cluster distances are selected as the fourth cluster distance to be fused; Determine a second sub-device operation change data deviation factor set based on the second device operation change data deviation factor, the third to-be-fused cluster distance, and the fourth to-be-fused cluster distance; Randomly select a third device operation change data deviation factor as a third cluster center, and determine a third cluster distance from all remaining device operation change data deviation factors to the third cluster center; All third clustering distances are sorted by numerical value, and a third clustering distance sequence is constructed based on the sorting results; Determine a third sequence mean of the third clustering distance sequence, and mark the third sequence mean in the third clustering distance sequence as a third sequence marking point; The maximum third cluster distance and the third cluster distance in the third sequence annotation point are used as the fourth sub-cluster distance sequence, and the equipment operation change data deviation factors corresponding to the first y third cluster distances are selected as the fifth cluster distance to be fused; The minimum third cluster distance and the third cluster distance in the third sequence annotation point are used as the fifth sub-cluster distance sequence, and the equipment operation change data deviation factors corresponding to the first y-2 third cluster distances are selected as the sixth cluster distance to be fused; Determine a third sub-device operation change data deviation factor set based on the third device operation change data deviation factor, the fifth to-be-fused cluster distance, and the sixth to-be-fused cluster distance; A device operation change data deviation factor set is determined based on the first sub-device operation change data deviation factor set, the second sub-device operation change data deviation factor set, and the third sub-device operation change data deviation factor set.

4. The intelligent unit operation optimization prediction method according to claim 3 is characterized in that: When determining the device operation change data deviation factor set based on the first sub-device operation change data deviation factor set, the second sub-device operation change data deviation factor set, and the third sub-device operation change data deviation factor set, the method includes: Calculate a first set value of a deviation factor set of the first sub-device operation change data; Calculate a second set value of the second sub-device operation change data deviation factor set; Calculating a third set value of the third sub-device operation change data deviation factor set; Calculate a first set difference between the first set value and the second set value, calculate a second set difference between the first set value and the third set value, and calculate a third set difference between the second set value and the third set value; Determine whether the first set difference, the second set difference and the third set difference are all less than a preset set difference; if so, fuse the first sub-device operation change data deviation factor set, the second sub-device operation change data deviation factor set and the third sub-device operation change data deviation factor set to obtain a device operation change data deviation factor set; If not, randomly select the fourth equipment operation change data deviation factor, the fifth equipment operation change data deviation factor and the sixth equipment operation change data deviation factor; Repeat the iteration to obtain a set of deviation factors of multiple equipment operation change data.

5. The intelligent unit operation optimization prediction method according to claim 4 is characterized in that: When calculating the first set value of the deviation factor set of the first sub-device operation change data, it includes: ； Wherein, t1 is the first set value of the first sub-device operation change data deviation factor set, r is the number of device operation change data deviation factors in the first sub-device operation change data deviation factor set, e i is the i-th device operation change data deviation factor in the first sub-device operation change data deviation factor set, w is the average value corresponding to the first sub-device operation change data deviation factor set, and w2 is the variance of all device operation change data deviation factors except the i-th device operation change data deviation factor.

6. The intelligent unit operation optimization prediction method according to claim 4 is characterized in that: When calculating the sub-operation performance prediction coefficient corresponding to the operation data collection point according to the equipment operation change data deviation factor set, it includes: Setting a first calculation coefficient for the first set of values, setting a second calculation coefficient for the second set of values, and setting a third calculation coefficient for the third set of values; The sub-operation performance prediction coefficient corresponding to the operation data collection point is calculated according to the first set value, the second set value, the third set value, the first calculation coefficient, the second calculation coefficient and the third calculation coefficient.

7. The intelligent unit operation optimization prediction method according to claim 1 is characterized in that: When all sub-operation performance prediction coefficients are extracted, all sub-operation performance prediction coefficients are deployed on the data tree, and the operation performance prediction coefficients of the intelligent unit equipment are calculated based on the deployment results, it includes: Deploy all sub-operation performance prediction coefficients to the main data trunk, left data branch and right data branch of the data tree based on the random deployment principle of the binary tree; Extracting the sub-operation performance prediction coefficients on the left data branch as a left data branch set; Extracting the sub-operation performance prediction coefficients on the right data branch as a right data branch set; Extracting sub-operation performance prediction coefficients on the main data trunk as a main data trunk set; Randomly combining the sub-operation performance prediction coefficients in the left data branch set and the right data branch set in pairs to obtain a plurality of sub-operation performance prediction coefficient sets; Counting the number of master and sub-operation performance prediction coefficients of the master data trunk set; The operation performance prediction coefficient of the intelligent unit equipment is calculated according to the sub-operation performance prediction coefficient set and the number of the main and sub-operation performance prediction coefficients.

8. The intelligent unit operation optimization prediction method according to claim 7 is characterized in that: When calculating the operation performance prediction coefficient of the intelligent unit equipment according to the sub-operation performance prediction coefficient set and the number of the main and sub-operation performance prediction coefficients, it includes: The operating performance prediction coefficient of the intelligent unit equipment is calculated according to the following formula: ； Among them, q is the operation performance prediction coefficient of the intelligent unit equipment, e is a constant, s1 is the number of sub-operation performance prediction coefficients in the left data branch set, s2 is the number of sub-operation performance prediction coefficients in the right data branch set, s3 is the number of main and sub-operation performance prediction coefficients, d is the number of sub-operation performance prediction coefficient sets, g j is a sub-operation performance prediction coefficient in the j-th sub-operation performance prediction coefficient set, h j is another sub-running performance prediction coefficient in the j-th sub-running performance prediction coefficient set, c1 max is the maximum sub-run performance prediction coefficient in the left data branch set, c2 max The maximum sub-run performance prediction coefficient in the main data stem set, c3 max is the maximum sub-run performance prediction coefficient in the right data branch set.

9. The intelligent unit operation optimization prediction method according to claim 1 is characterized in that: When judging whether it is necessary to optimize the operating state of the intelligent unit equipment based on the relationship between the operating performance prediction coefficient and the preset operating performance prediction coefficient, it includes: When the operation performance prediction coefficient is less than the preset operation performance prediction coefficient, it is determined that the operation state of the intelligent unit equipment needs to be optimized; When the operating performance prediction coefficient is greater than or equal to the preset operating performance prediction coefficient, it is determined that there is no need to optimize the operating state of the intelligent unit equipment.

10. An intelligent unit operation optimization prediction system, applied to the intelligent unit operation optimization prediction method according to any one of claims 1 to 9, characterized in that: include: A data collection module is used to determine the intelligent unit equipment to be predicted for operation performance, pre-deploy multiple operation data collection points on the intelligent unit equipment, and collect equipment operation change data of the intelligent unit equipment based on the operation data collection points; A first calculation module is used to determine an equipment operation change data sequence according to the equipment operation change data corresponding to each operation data collection point, and calculate the equipment operation change data deviation factor of each equipment operation change data in the equipment operation change data sequence; A second calculation module is used to perform an integrated analysis on the equipment operation change data deviation factor, determine a plurality of equipment operation change data deviation factor sets based on the integrated analysis result, and calculate the sub-operation performance prediction coefficient corresponding to the operation data collection point according to the equipment operation change data deviation factor set; a third calculation module, configured to determine a data tree, extract all sub-operation performance prediction coefficients, deploy all sub-operation performance prediction coefficients to the data tree, and calculate the operation performance prediction coefficient of the intelligent unit equipment based on the deployment result, wherein the data tree includes a main data trunk, a left data branch, and a right data branch; The performance prediction module is used to determine whether it is necessary to optimize the operating state of the intelligent unit equipment based on the relationship between the operating performance prediction coefficient and the preset operating performance prediction coefficient.

Images