A method and system for evaluating the performance optimization effect of hydraulic lubrication and drag reduction operating components

Abstract

The present invention provides a method and system for evaluating the performance optimization effect of a hydraulic lubrication and drag reduction operating component, which relates to the field of mechanical technology. The method comprises the following steps: obtaining parameter data of the hydraulic lubrication and drag reduction operating component and constructing a component digital twin model; using the component digital twin model, simulating and evolving the hydraulic lubrication and drag reduction operating component, and respectively obtaining performance data of the hydraulic lubrication and drag reduction operating component before and after performance optimization; using the niche theory to analyze the performance of the hydraulic lubrication and drag reduction operating component before and after performance optimization according to the performance data of the hydraulic lubrication and drag reduction operating component before and after performance optimization; and evaluating the performance optimization effect of the hydraulic lubrication and drag reduction operating component according to the analysis result to obtain an evaluation result. The present invention evaluates the performance optimization effect based on the result of in-depth analysis, thereby ensuring the scientific nature and practical significance of the evaluation result.

Description

Technical Field

[0001] The present invention relates to the field of mechanical technology, and in particular to a method and system for evaluating the performance optimization effect of a hydraulic lubrication and drag reduction operating component. Background Art

[0002] In the context of modern industry, hydraulic lubrication and drag reduction technology is a key element and its importance cannot be underestimated. The hydraulic system, as the heart of the mechanical device, has a direct impact on the efficiency and reliability of the equipment by transmitting power and controlling movement. With the transformation of the manufacturing industry to automation and intelligence, the performance requirements of hydraulic systems have reached an unprecedented level. Traditionally, the maintenance of hydraulic systems relies on regular inspections and post-maintenance, which often leads to waste of resources and unplanned downtime, seriously restricting the efficiency and capacity of the production line. In recent years, with the integration and application of cutting-edge technologies such as the Internet of Things (IoT), big data analysis and artificial intelligence (AI), the operation and maintenance mode of hydraulic systems is undergoing fundamental changes. Smart sensors can monitor the temperature, pressure and contamination of hydraulic oil, as well as the operating status of pumps and valves in real time, and transmit data to the central control system via wireless networks. With the help of machine learning algorithms, these systems can analyze historical data, predict potential failures, and achieve predictive maintenance, thereby significantly reducing the unplanned downtime of equipment and improving overall production efficiency. In addition, intelligent hydraulic systems can also automatically adjust parameters according to actual working conditions, optimize energy use, further reduce operating costs, and enhance the competitiveness of enterprises.

[0003] At present, traditional technologies are often limited by technology and cost when collecting operating data of hydraulic systems, and are unable to monitor all key performance indicators in real time and comprehensively. Especially in complex or extreme operating environments, existing technologies often find it difficult to accurately simulate the behavior of components under various operating conditions, which not only limits the in-depth understanding of component performance, but also leads to insufficient prediction capabilities for future performance changes and difficulty in effectively responding to emergencies. Therefore, existing technologies have significant limitations in terms of hydraulic system performance optimization and fault prediction.

[0004] Currently, no effective solution has been proposed for the problems in the related technologies. Summary of the invention

[0005] In view of this, the present invention provides a method and system for evaluating the performance optimization effect of a hydraulic lubrication and drag reduction operating component to solve the above-mentioned problems.

[0006] In order to solve the above problems, the specific technical solutions adopted by the present invention are as follows:

[0007] According to one aspect of the present invention, a method for evaluating the performance optimization effect of a hydraulic lubrication and drag reduction operating component is provided, and the method for evaluating the performance optimization effect of a hydraulic lubrication and drag reduction operating component comprises the following steps:

[0008] S1. Obtain parameter data of hydraulic lubrication and drag reduction operation components and build a digital twin model of the components;

[0009] S2. Using the component digital twin model, simulate the evolution of the hydraulic lubrication and drag reduction operating components, and obtain the performance data of the hydraulic lubrication and drag reduction operating components before and after performance optimization;

[0010] S3. Based on the performance data of the hydraulic lubrication drag reduction operating parts before and after the performance optimization, the performance of the hydraulic lubrication drag reduction operating parts before and after the performance optimization is analyzed using the niche theory;

[0011] S4. Evaluate the performance optimization effect of the hydraulic lubrication drag reduction operating components according to the analysis results to obtain evaluation results;

[0012] Preferably, obtaining parameter data of hydraulic lubrication and drag reduction operating components and constructing a component digital twin model comprises the following steps:

[0013] S11, using a graph theory statistical method to pre-process the parameter data of the hydraulic lubrication drag reduction operating component to obtain a parameter relationship diagram;

[0014] S12, performing feature enhancement processing on the parameter relationship graph by using a spatial convolution method, and extracting feature information;

[0015] S13. Use fuzzy neural network and logarithmic neural network to analyze and process feature information and build a digital twin model of components.

[0016] Preferably, using the component digital twin model to simulate the evolution of the hydraulic lubrication and drag reduction operating component, and obtaining the performance data of the hydraulic lubrication and drag reduction operating component before and after performance optimization includes the following steps:

[0017] S21, respectively obtaining simulation parameters of the hydraulic lubrication drag reduction operating component before and after performance optimization;

[0018] S22, according to the simulation parameters before and after optimization, using the component digital twin model to respectively perform operation simulation on the hydraulic lubrication drag reduction operation components;

[0019] S23. Record various performance data generated by the component digital twin model during the simulation process of a preset time period.

[0020] Preferably, using a graph theory statistical method to pre-process the parameter data of the hydraulic lubrication drag reduction operating component to obtain a parameter relationship diagram includes the following steps:

[0021] S111, performing data cleaning processing on parameter data of hydraulic lubrication drag reduction operation components;

[0022] S112, projecting the cleaned parameter data into a BIM-based three-dimensional model using an LOD method to form a data projection;

[0023] S113, expanding the parameter data projected in the BIM-based three-dimensional model according to the time series to form the original statistical results of the graph sequence;

[0024] S114. Use the path analysis method in graph theory to analyze the original statistical results of the graph sequence, identify the propagation paths between parameters and construct a parameter relationship diagram.

[0025] Preferably, performing feature enhancement processing on the parameter relationship graph by using a spatial convolution method and extracting feature information comprises the following steps:

[0026] S121, mapping the position and time information of each node in the parameter relationship graph into a four-dimensional space, and constructing a four-dimensional space-time data structure;

[0027] S122, performing a spatial convolution operation on each data point in the four-dimensional space-time data structure based on a preset convolution kernel to obtain spatial convolution data;

[0028] S123. Analyze the spatial convolution data to identify and extract feature information in the parameter relationship diagram.

[0029] Preferably, using fuzzy neural network and logarithmic neural network to analyze and process feature information and construct a component digital twin model includes the following steps:

[0030] S131, preprocessing the feature information using a sixth-order polynomial deep iterative regression algorithm;

[0031] S132, inputting the preprocessed feature information into the fuzzy neural network and the logarithmic neural network respectively, and obtaining the output of the fuzzy neural network and the output of the logarithmic neural network after processing;

[0032] S133, fusing the output of the fuzzy neural network and the output of the logarithmic neural network to obtain fused feature information;

[0033] S134. Based on the fused feature information, a digital twin model of the component is constructed using a simulation model.

[0034] Preferably, according to the performance data of the hydraulic lubrication drag reduction operating component before and after the performance optimization, using the niche theory to analyze the performance of the hydraulic lubrication drag reduction operating component before and after the performance optimization includes the following steps:

[0035] S31, establishing a performance index set of the hydraulic lubrication drag reduction operating component before and after optimization according to the performance data of the hydraulic lubrication drag reduction operating component before and after optimization;

[0036] S32, performing a change trend analysis on each performance data in the performance index set of the hydraulic lubrication drag reduction operating component before and after optimization, and using the trend analysis result as the potential value of the ecological niche;

[0037] S33. Use the performance data of the performance index set of the hydraulic lubrication drag reduction operating component before and after optimization as the state value of the ecological niche, and use the ecological niche calculation formula to calculate the ecological niche values ​​of the hydraulic lubrication drag reduction operating component before and after optimization, and use the ecological niche value as the performance value of the hydraulic lubrication drag reduction operating component.

[0038] Preferably, performing a change trend analysis on each performance data in the performance index set of the hydraulic lubrication drag reduction operating component before and after optimization, and using the trend analysis result as the potential value of the ecological niche includes the following steps:

[0039] S321, using a time series method to perform data decomposition on each performance data in the performance index set before and after the optimization of the hydraulic lubrication drag reduction operation component;

[0040] S322, identifying and extracting trend components after decomposition of each performance data;

[0041] S323, calculating the change rate of each performance data according to the extracted trend component;

[0042] S324. Use the calculated change rate as the potential value of each performance data niche.

[0043] Preferably, the niche calculation formula is:

[0044] ;

[0045] In the formula, F i Indicates the ecological niche value of hydraulic lubrication and drag reduction operating components;

[0046] R i and R j Respectively represent i performance indicators and j The potential value of each performance indicator;

[0047] X i and X j All represent dimension conversion coefficients;

[0048] Y i Representation and Y j Respectively represent i performance indicators and j The state value of a performance indicator;

[0049] m Represents the number of performance indicators in the performance indicator set of hydraulic lubrication and drag reduction working components.

[0050] Preferably, based on the analysis results, the performance optimization effect of the hydraulic lubrication drag reduction operating component is evaluated, and obtaining the evaluation results includes the following steps:

[0051] S41, comparing all performance data performance values ​​of the performance index set before and after the optimization of the hydraulic lubrication drag reduction operation component;

[0052] S42. Calculate the optimization rate of each performance indicator in the performance indicator set according to the comparison result;

[0053] S43. Based on the optimization rate of each performance indicator and according to a preset evaluation threshold, determine whether the optimization effect of each performance indicator in the performance indicator set meets expectations.

[0054] According to another aspect of the present invention, a hydraulic lubrication drag reduction operating component performance optimization effect evaluation system is provided, the hydraulic lubrication drag reduction operating component performance optimization effect evaluation system comprises: a model construction module, a simulation evolution module, a performance analysis module and a performance evaluation module, and the model construction module, the simulation evolution module, the performance analysis module and the performance evaluation module are connected in sequence;

[0055] Model building module, used to obtain parameter data of hydraulic lubrication and drag reduction operating components and build digital twin models of the components;

[0056] The simulation evolution module is used to simulate and evolve the hydraulic lubrication and drag reduction operating components using the component digital twin model, and obtain the performance data of the hydraulic lubrication and drag reduction operating components before and after performance optimization;

[0057] A performance analysis module is used to analyze the performance of hydraulic lubrication drag reduction operating components before and after performance optimization using the niche theory according to the performance data of the hydraulic lubrication drag reduction operating components before and after performance optimization;

[0058] The performance evaluation module is used to evaluate the performance optimization effect of the hydraulic lubrication and drag reduction operating components according to the analysis results to obtain the evaluation results.

[0059] The beneficial effects of the present invention are:

[0060] 1. The present invention obtains parameter data of hydraulic lubrication and drag reduction operating components and constructs a digital twin model of the components, thereby ensuring that the performance evaluation is based on a highly accurate and comprehensive data model. The digital twin technology allows simulation of real-world operating conditions, improves the authenticity and reliability of the simulation, and performs simulation evolution through the digital twin model. It is possible to obtain and compare performance data before and after optimization without actually intervening in the operation of the components, which not only saves costs but also reduces damage or wear to the components during the test. The niche theory is used to analyze performance data, providing a novel perspective to evaluate the performance changes of components. The niche theory helps quantify the adaptability and efficiency of components in their operating environment, making the performance evaluation more in-depth and multi-dimensional. The performance optimization effect is evaluated based on the results of the in-depth analysis, ensuring the scientific nature and practical significance of the evaluation results.

[0061] 2. The present invention reveals the intrinsic connections and mutual influences between parameters through the path analysis method of graph theory, which increases the depth of understanding of system behavior. Through the four-dimensional space-time data structure and spatial convolution operation, it can more accurately capture and analyze complex changes in time and space, thereby extracting more representative and predictive feature information. By using neural networks to process pre-processed feature information, the model's ability to recognize nonlinear and complex patterns can be improved.

[0062] 3. The present invention can analyze and understand performance data more comprehensively by introducing niche theory into performance evaluation. By performing detailed trend analysis on performance data through time series analysis, key trend components of performance changes can be identified and extracted, which is helpful to predict future performance changes and provide a basis for continuous improvement. By comparing the performance data before and after optimization and calculating the performance optimization rate, the effect of the improvement can be specifically quantified, providing a direct quantitative indicator for judging the actual benefits of the optimization measures. Using niche value as a measure of performance can not only evaluate the current performance status, but also predict the performance of components under possibly changing operating conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in 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. In the drawings:

[0064] Figure 1 is a flow chart of a method for evaluating the performance optimization effect of a hydraulic lubrication and drag reduction operating component according to an embodiment of the present invention;

[0065] Figure 2It is a principle block diagram of a hydraulic lubrication and drag reduction operating component performance optimization effect evaluation system according to an embodiment of the present invention.

[0066] In the figure:

[0067] 1. Model building module; 2. Simulation evolution module; 3. Performance analysis module; 4. Performance evaluation module. DETAILED DESCRIPTION

[0068] In order to enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this application.

[0069] According to an embodiment of the present invention, a method and system for evaluating the performance optimization effect of a hydraulic lubrication and drag reduction operating component are provided.

[0070] The present invention is further described with reference to the accompanying drawings and specific embodiments. Figure 1 As shown, according to one embodiment of the present invention, a method for evaluating the performance optimization effect of a hydraulic lubrication and drag reduction operating component is provided, and the method for evaluating the performance optimization effect of a hydraulic lubrication and drag reduction operating component comprises the following steps:

[0071] S1. Obtain parameter data of hydraulic lubrication and drag reduction operation components and build a digital twin model of the components;

[0072] It should be noted that the parameter data of hydraulic lubrication drag reduction operating components include geometric parameters, physical parameters, operating parameters, environmental parameters, etc. Geometric parameters include geometric characteristic data such as size, shape, structure, etc. Physical parameters include material properties, such as density, hardness, elastic modulus, etc. Physical quantities such as mass and volume of components. Operating parameters include operating status data of components during operation, such as speed, pressure, temperature, etc. Lubrication status of components, such as lubricant type, lubrication method, lubrication cycle, etc.

[0073] Obtaining parameter data of hydraulic lubrication and drag reduction components and building a digital twin model of the components includes the following steps:

[0074] S11, using a graph theory statistical method to pre-process the parameter data of the hydraulic lubrication drag reduction operating component to obtain a parameter relationship diagram;

[0075] As a preferred implementation, the parameter data of the hydraulic lubrication drag reduction operating component is pre-processed using a graph theory statistical method to obtain a parameter relationship diagram, including the following steps:

[0076] S111, performing data cleaning processing on parameter data of hydraulic lubrication drag reduction operation components;

[0077] It should be noted that data cleaning includes:

[0078] Missing value processing: For records with many missing values ​​that have little impact on the analysis results, you can choose to delete them. For important missing values, you can use the mean, median, mode to fill them, or use interpolation, regression prediction and other methods to fill them.

[0079] Outlier processing: identify outliers in the data by using methods such as box plots and Z-score, and then choose to delete, replace, or retain outliers according to the specific situation. If the outliers are caused by measurement errors or data entry errors, they should be deleted or replaced; if the outliers are caused by real situations and have a significant impact on the analysis results, they should be retained.

[0080] Inconsistency and error handling: Obvious errors in the data (such as unit errors, numerical errors, etc.) should be corrected. And ensure that the data is in a unified format for subsequent processing and analysis.

[0081] For some parameter data, standardization or normalization is required to eliminate the influence of dimension and improve the accuracy and comparability of data analysis.

[0082] S112, projecting the cleaned parameter data into a BIM-based three-dimensional model using an LOD method to form a data projection;

[0083] Specifically, the cleaned parameter data is projected into a 3D model based on BIM (Building Information Modeling) using the LOD (Level of Detail) method. The process of data projection involves combining the parameter data with the geometric, physical and functional information of the BIM model to display the characteristics and status of the hydraulic lubrication and drag reduction operating components at different levels of detail, including the following steps:

[0084] For hydraulic lubrication drag reduction components, the appropriate LOD level is determined according to the specific stage in the project life cycle and the required level of information detail. For example, only LOD100 or LOD200 models are required in the preliminary design stage, while LOD300 or higher models are required in the construction or operation and maintenance stage.

[0085] Based on the determined LOD level, prepare or modify the BIM model to match the required level of detail, including adding or deleting model elements, adjusting the geometry and size of the model, and specifying the physical properties of materials;

[0086] Integrate the cleaned parameter data with the BIM model, including associating the parameter data (such as hydraulic performance parameters, lubrication conditions, drag reduction effects, etc.) with the corresponding elements in the BIM model;

[0087] In the BIM model, the display and properties of the model elements are adjusted according to the parameter data to form a data projection, including using different colors, textures, transparency or labels to distinguish model elements with different parameter values. In this way, the performance status and characteristics of the hydraulic lubrication and drag reduction operating components can be intuitively displayed in the BIM model.

[0088] S113, expanding the parameter data projected in the BIM-based three-dimensional model according to the time series to form the original statistical results of the graph sequence;

[0089] Specifically, the parameter data related to the hydraulic lubrication and drag reduction operating components, including the data of time series information, are extracted from the 3D model of BIM; the extracted time series data are analyzed to identify the trends, seasonal changes, periodic patterns or other important features in the data, and the results of the time series analysis are presented in a visual way to form the original statistical results of the graph sequence, including line graphs, bar graphs, scatter graphs, heat maps and other forms.

[0090] S114. Use the path analysis method in graph theory to analyze the original statistical results of the graph sequence, identify the propagation paths between parameters and construct a parameter relationship diagram.

[0091] Specifically, the path analysis method in graph theory is used to analyze the original statistical results of the graph sequence, identify the propagation path between parameters and construct the parameter relationship diagram, including the following steps:

[0092] Each parameter is considered as a node in the graph theory, which represents different performance indicators, operating states or environmental conditions of hydraulic lubrication drag reduction components;

[0093] According to the original statistical results of the graph sequence, the correlation or causal relationship between different parameters is analyzed. If there is an obvious correlation or causal relationship between two parameters, an edge is established between their corresponding nodes. The weight of the edge can represent the strength or importance of the relationship between the parameters.

[0094] All nodes and edges are combined to form a parameter relationship graph, which intuitively shows the interaction and dependency between different parameters;

[0095] In graph theory, a path is a series of edges and nodes that connect two nodes. Path analysis can identify the propagation paths between parameters. Specifically:

[0096] Identify all paths and find all paths connecting any two nodes.

[0097] The importance of each path is evaluated based on the edge weight and the length of the path. Shorter paths or edges with larger weights generally indicate stronger relationships.

[0098] Identify the critical paths that have the greatest impact on the performance of hydraulic lubrication and drag reduction components. These paths represent the most important propagation paths or cause-effect chains between parameters.

[0099] S12, performing feature enhancement processing on the parameter relationship graph by using a spatial convolution method, and extracting feature information;

[0100] As a preferred implementation, the parameter relationship graph is subjected to feature enhancement processing by a spatial convolution method, and the feature information is extracted, including the following steps:

[0101] S121, mapping the position and time information of each node in the parameter relationship graph into a four-dimensional space, and constructing a four-dimensional space-time data structure;

[0102] Specifically, in three-dimensional space, three mutually perpendicular axes are usually selected as coordinate axes, such as the X-axis, Y-axis, and Z-axis. These axes represent different spatial directions; for each node in the parameter relationship diagram, its coordinate values ​​on the X-axis, Y-axis, and Z-axis are assigned according to its position or relative position in the actual space. These coordinate values ​​can be specific values ​​or offsets relative to a reference point.

[0103] In four-dimensional space, in addition to the three-dimensional spatial coordinates, a time dimension (usually represented as the T axis) needs to be added. This time dimension is used to represent the change of parameters over time. For each node, its time information needs to be quantified into a specific value. This value can be a time point (such as the specific date and time of a certain moment) or a time interval (such as the length of time since a reference time point). The quantified time information is used as the coordinate value of the node on the T axis. In this way, each node has a complete coordinate (X, Y, Z, T) in the four-dimensional space; then the four-dimensional coordinates (X, Y, Z, T) of each node are filled into the pre-selected data structure to obtain a four-dimensional space-time data structure.

[0104] S122, performing a spatial convolution operation on each data point in the four-dimensional space-time data structure based on a preset convolution kernel to obtain spatial convolution data;

[0105] It should be noted that a convolution kernel is a small matrix, usually with a specific shape and weights, which is used to slide over the data and perform weighted summation to generate a new data representation. One or more convolution kernels are pre-set according to the characteristics of the four-dimensional spatiotemporal data structure and the type of features to be extracted.

[0106] The process of performing a spatial convolution operation on each data point in the four-dimensional spatiotemporal data structure based on a preset convolution kernel includes the following steps:

[0107] For each data point in the four-dimensional spatiotemporal data structure, select an area adjacent to it as the convolution area. The size of this area should match the size of the convolution kernel.

[0108] Apply the convolution kernel to the selected convolution area and perform weighted summation. Specifically, multiply each weight in the convolution kernel by the data point at the corresponding position, and add the results to get a new value;

[0109] For each data point in the four-dimensional space-time data structure, the above convolution operation is performed. The results of all convolution operations are combined to form new spatial convolution data.

[0110] S123. Analyze the spatial convolution data to identify and extract feature information in the parameter relationship diagram.

[0111] Specifically, analyzing the spatial convolution data, identifying and extracting feature information in the parameter relationship graph includes the following steps:

[0112] Use visualization tools or programming libraries to convert spatial convolution data into graphical forms, such as 3D scatter plots, heat maps, or contour maps. Observe the visualization charts to pay attention to the distribution of data, dense areas, and any abnormal values ​​or outliers.

[0113] Look for patterns in visual charts that represent characteristic information, such as clusters, trend lines, or periodic changes, and use statistical methods to identify characteristics, such as calculating the mean, median, standard deviation, or correlation coefficient of the data;

[0114] According to the identified features, specific feature indicators are set, such as cluster center, slope of trend line or frequency of periodic change, and a numerical value is assigned to each feature indicator for further analysis or modeling. All extracted features are combined into a feature vector, which represents the key feature information in the parameter relationship diagram.

[0115] S13. Use fuzzy neural network and logarithmic neural network to analyze and process feature information and build a digital twin model of components.

[0116] As a preferred implementation, the fuzzy neural network and the logarithmic neural network are used to analyze and process the feature information, and the component digital twin model is constructed, including the following steps:

[0117] S131, preprocessing the feature information using a sixth-order polynomial deep iterative regression algorithm;

[0118] It should be noted that the sixth-order polynomial deep iterative regression algorithm is an algorithm that can fit complex nonlinear relationships. Its core idea is to use high-order polynomial functions to capture nonlinear patterns in the data and adjust parameters through an iterative optimization process to achieve the best fitting effect.

[0119] Among them, preprocessing the feature information using the sixth-order polynomial deep iterative regression algorithm includes the following steps:

[0120] Preprocess the feature information, including checking whether there are missing values, outliers, or noise in the feature information;

[0121] A model is initialized using the sixth-order polynomial deep iterative regression algorithm, and the feature information is used as input to perform iterative calculations using the sixth-order polynomial deep iterative regression algorithm. In each iteration, the algorithm updates the model's weights and biases based on the current data and model parameters to gradually approach the true distribution of the data;

[0122] The preprocessed feature information is extracted from the model preprocessed by the sixth-order polynomial deep iterative regression algorithm.

[0123] S132, inputting the preprocessed feature information into the fuzzy neural network and the logarithmic neural network respectively, and obtaining the output of the fuzzy neural network and the output of the logarithmic neural network after processing;

[0124] Specifically, the pre-processed feature information is input into the fuzzy neural network respectively including:

[0125] Arrange the preprocessed feature information into an input format acceptable to the fuzzy neural network, such as a matrix or tensor;

[0126] Fuzzy neural networks process fuzzy numbers or fuzzy sets, so the pre-processed feature information needs to be fuzzified. Fuzzification includes converting numerical features into fuzzy membership functions, such as using Gaussian functions, triangular functions, or trapezoidal functions to represent the fuzziness of features;

[0127] The fuzzified feature information is input into the input layer of the fuzzy neural network. The feature information is transmitted layer by layer in the network, processed by the hidden layer, and finally reaches the output layer. In the forward propagation process, the fuzzy neural network uses fuzzy logic rules or fuzzy reasoning system to process the input feature information.

[0128] After being processed by the fuzzy neural network, the output layer will give the processing result, and the output is a fuzzy number, fuzzy set or clear numerical value.

[0129] The preprocessed feature information is input into the logarithmic neural network respectively, including:

[0130] Arrange the preprocessed feature information into an input format acceptable to the logarithmic neural network

[0131] Apply natural logarithm (base e) or common logarithm (base 10) transformations to the features that need to be transformed. The transformed data is more in line with the input requirements or internal processing mechanism of the logarithmic neural network;

[0132] The logarithmic transformed feature information is input into the input layer of the logarithmic neural network. The feature information is transmitted layer by layer in the logarithmic neural network and processed by the hidden layer. The logarithmic neural network uses a specific activation function and weight matrix to process the input feature information. After being processed by the logarithmic neural network, the output layer will give the processing result.

[0133] S133, fusing the output of the fuzzy neural network and the output of the logarithmic neural network to obtain fused feature information;

[0134] Specifically, fusing the output of the fuzzy neural network with the output of the logarithmic neural network to obtain the fused feature information includes the following steps:

[0135] Align the output of the fuzzy neural network and the output of the logarithmic neural network in terms of dimension and format;

[0136] According to the weighted average fusion strategy, the output of the fuzzy neural network and the output of the logarithmic neural network are fused. For example, the weighted sum of the outputs of the two networks is calculated as the fused feature information;

[0137] Perform necessary processing on the fused feature information, such as standardization and normalization, to ensure the consistency and comparability of the feature information.

[0138] S134. Based on the fused feature information, a digital twin model of the component is constructed using a simulation model.

[0139] It should be noted that based on the simulation platform, according to the physical characteristics and operating principles of the component, its simulation model is constructed, and the fused feature information is used as input or parameter and integrated into the simulation model. These feature information are used to adjust the parameters of the model, initialization conditions or as external excitation, run the simulation model, and verify the model based on the operating data of the actual component. The parameters or structure of the model are adjusted as needed to improve the accuracy and reliability of the model. Once the simulation model has been verified and reaches the expected accuracy, it can be regarded as a digital twin model of the component. This digital twin model can reflect the status and behavior of the physical component in real time or near real time.

[0140] S2. Using the component digital twin model, simulate the evolution of the hydraulic lubrication and drag reduction operating components, and obtain the performance data of the hydraulic lubrication and drag reduction operating components before and after performance optimization;

[0141] As a preferred implementation, using a component digital twin model to simulate and evolve a hydraulic lubrication and drag reduction operating component, and obtaining performance data of the hydraulic lubrication and drag reduction operating component before and after performance optimization includes the following steps:

[0142] S21, respectively obtaining simulation parameters of the hydraulic lubrication drag reduction operating component before and after performance optimization;

[0143] S22, according to the simulation parameters before and after optimization, using the component digital twin model to respectively perform operation simulation on the hydraulic lubrication drag reduction operation components;

[0144] S23. Record various performance data generated by the component digital twin model during the simulation process of a preset time period.

[0145] For example, suppose a hydraulic lubrication and drag reduction component is being optimized to reduce friction and wear during operation. The component digital twin model is used to simulate the evolution of the hydraulic lubrication and drag reduction component to obtain the performance data of the hydraulic lubrication and drag reduction component before and after performance optimization. The specific implementation steps are as follows:

[0146] The simulation parameters of the component before optimization were obtained, such as the hydraulic pressure of 10MPa, the use of ordinary lubricating oil, and the original design of the drag reduction structure. At the same time, the simulation parameters after optimization were also obtained, such as the hydraulic pressure adjusted to 8MPa, the use of high-performance lubricating oil, and the improved design of the drag reduction structure.

[0147] Using the digital twin model, a simulation is first performed based on the pre-optimization parameters to simulate the operation of the component in its original state. Then, another simulation is performed based on the optimized parameters to simulate the operation of the component after the improvement.

[0148] Record the performance data generated during the two simulations.

[0149] S3. Based on the performance data of the hydraulic lubrication drag reduction operating parts before and after the performance optimization, the performance of the hydraulic lubrication drag reduction operating parts before and after the performance optimization is analyzed using the niche theory;

[0150] As a preferred implementation, based on the performance data of the hydraulic lubrication drag reduction operating component before and after the performance optimization, the performance of the hydraulic lubrication drag reduction operating component before and after the performance optimization is analyzed using the niche theory, including the following steps:

[0151] S31, establishing a performance index set of the hydraulic lubrication drag reduction operating component before and after optimization according to the performance data of the hydraulic lubrication drag reduction operating component before and after optimization;

[0152] It should be noted that the key indicators that can reflect the performance of the hydraulic lubrication drag reduction operating components are determined based on the performance data before and after the optimization. These indicators include friction coefficient, lubricant consumption rate, operating efficiency, component temperature, noise level, etc. The determined key performance indicators are organized into a complete indicator system. The specific values ​​of each performance indicator are respectively formed to form a performance indicator set before and after optimization.

[0153] S32, performing a change trend analysis on each performance data in the performance index set of the hydraulic lubrication drag reduction operating component before and after optimization, and using the trend analysis result as the potential value of the ecological niche;

[0154] As a preferred implementation, performing a change trend analysis on each performance data in the performance index set of the hydraulic lubrication drag reduction operating component before and after optimization, and using the trend analysis result as the potential value of the ecological niche includes the following steps:

[0155] S321, using a time series method to perform data decomposition on each performance data in the performance index set before and after the optimization of the hydraulic lubrication drag reduction operation component;

[0156] It should be noted that the commonly used time series models in the time series method include ARIMA model, seasonal decomposition model, etc. The selected time series model is used to decompose each performance indicator data before and after optimization. The decomposition usually includes the extraction of trend components, seasonal components and random components.

[0157] The trend component reflects the long-term change trend of the data, which may be upward or downward.

[0158] The seasonal component reflects the recurring pattern of variation in the data over a fixed period.

[0159] The random component reflects the random fluctuations and uncertainties in the data.

[0160] For example, assume that the friction coefficient data of hydraulic lubrication drag reduction components before and after optimization have been collected, and the seasonal decomposition model has been selected for time series decomposition.

[0161] Before optimization, the friction coefficient data showed a certain upward trend and seasonal fluctuations. Through decomposition, the trend component can be extracted, and it is found that the friction coefficient has gradually increased over the past period of time; at the same time, the seasonal component can also be extracted, and it is found that the friction coefficient will peak in certain seasons of each year (such as the high temperature season).

[0162] After optimization, the friction coefficient data is decomposed again in time series. By comparing the decomposition results before and after optimization, the impact of the optimization measures on the trend and seasonal fluctuations of the friction coefficient can be evaluated. If the optimization measures are effective, the slope of the trend component will decrease, indicating that the upward trend of the friction coefficient has been alleviated; at the same time, the peak value of the seasonal component may also decrease, indicating that the optimization measures have reduced seasonal fluctuations.

[0163] S322, identifying and extracting trend components after decomposition of each performance data;

[0164] It should be noted that in the decomposition results, the trend component is usually presented as a smooth curve, which reflects the long-term trend of the data. This curve may be rising, falling, or relatively stable. Once the trend component is identified, it can be extracted from the original data using mathematical methods or statistical software, including fitting regression lines, using moving average methods, etc.

[0165] S323, calculating the change rate of each performance data according to the extracted trend component;

[0166] For example, suppose that the trend component of the friction coefficient of the hydraulic lubrication drag reduction operating component has been extracted, and the time range before and after optimization is determined to be one week respectively;

[0167] During the period before optimization, the average value of the trend component was 0.05 (assuming this is a dimensionless friction coefficient indicator).

[0168] The average value of the trend component during the optimized time period was 0.04.

[0169] Calculated change: 0.04-0.05=-0.01.

[0170] Calculate the rate of change: (-0.01 / 0.05)*100%=-20%.

[0171] S324. Use the calculated change rate as the potential value of each performance data niche.

[0172] S33. Use the performance data of the performance index set of the hydraulic lubrication drag reduction operating component before and after optimization as the state value of the ecological niche, and use the ecological niche calculation formula to calculate the ecological niche values ​​of the hydraulic lubrication drag reduction operating component before and after optimization, and use the ecological niche value as the performance value of the hydraulic lubrication drag reduction operating component.

[0173] As a preferred implementation, the niche calculation formula is:

[0174] ;

[0175] In the formula, F i Indicates the ecological niche value of hydraulic lubrication and drag reduction operating components;

[0176] R i and R j Respectively represent i performance indicators and j The potential value of each performance indicator;

[0177] X i and X j All represent dimension conversion coefficients;

[0178] Y i Representation and Y j Respectively represent i performance indicators and j The state value of a performance indicator;

[0179] m Represents the number of performance indicators in the performance indicator set of hydraulic lubrication and drag reduction working components.

[0180] S4. Evaluate the performance optimization effect of the hydraulic lubrication drag reduction operating components according to the analysis results to obtain evaluation results;

[0181] As a preferred embodiment, based on the analysis results, the performance optimization effect of the hydraulic lubrication drag reduction working component is evaluated, and obtaining the evaluation results includes the following steps:

[0182] S41, comparing all performance data performance values ​​of the performance index set before and after the optimization of the hydraulic lubrication drag reduction operation component;

[0183] It should be noted that all performance data in the performance index set of the hydraulic lubrication drag reduction operating components before and after optimization are compared. Including friction coefficient, lubricant consumption rate, operating efficiency, component temperature, and newly added noise level indicators. For each performance indicator, its specific value before and after optimization is compared to identify changes in performance.

[0184] S42. Calculate the optimization rate of each performance indicator in the performance indicator set according to the comparison result;

[0185] It should be noted that the calculation formula for the optimization rate of each performance indicator in the performance indicator set is:

[0186] Optimization rate = (performance index after optimization - performance index value before optimization) / performance index value before optimization.

[0187] S43. Based on the optimization rate of each performance indicator and according to a preset evaluation threshold, determine whether the optimization effect of each performance indicator in the performance indicator set meets expectations.

[0188] It should be noted that for each performance indicator, its optimization rate is compared with the preset evaluation threshold. If the optimization rate is greater than or equal to the evaluation threshold (for the performance indicator expected to be improved), or the optimization rate is less than or equal to the evaluation threshold (for the performance indicator expected to be reduced), it can be considered that the optimization effect of the performance indicator has met the expectations.

[0189] For example, suppose the following evaluation thresholds are set for hydraulic lubrication drag reduction components: the optimization rate of the friction coefficient should be greater than 20%, and the optimization rate of the lubricant consumption rate should be less than -10% (indicating that the consumption rate is expected to be reduced).

[0190] For the friction coefficient, if the calculated optimization rate is 25%, it is greater than the evaluation threshold of 20%, so it can be considered that the optimization effect of the friction coefficient has met expectations.

[0191] For the lubricant oil consumption rate, if the calculated optimization rate is -15%, it is less than the evaluation threshold of -10%, so it can be considered that the optimization effect of the lubricant oil consumption rate has also reached the expected level.

[0192] like Figure 2 As shown, according to another embodiment of the present invention, a hydraulic lubrication drag reduction operating component performance optimization effect evaluation system is provided, and the hydraulic lubrication drag reduction operating component performance optimization effect evaluation system comprises: a model building module 1, a simulation evolution module 2, a performance analysis module 3 and a performance evaluation module 4, and the model building module 1, the simulation evolution module 2, the performance analysis module 3 and the performance evaluation module 4 are connected in sequence;

[0193] Model building module 1, used to obtain parameter data of hydraulic lubrication and drag reduction operation components and build a digital twin model of the components;

[0194] The simulation evolution module 2 is used to simulate and evolve the hydraulic lubrication and drag reduction operation components using the component digital twin model, and obtain the performance data of the hydraulic lubrication and drag reduction operation components before and after performance optimization;

[0195] Performance analysis module 3, used to analyze the performance of hydraulic lubrication drag reduction operating components before and after performance optimization using niche theory according to the performance data of the hydraulic lubrication drag reduction operating components before and after performance optimization;

[0196] The performance evaluation module 4 is used to evaluate the performance optimization effect of the hydraulic lubrication drag reduction operating component according to the analysis results to obtain the evaluation results.

[0197] In summary, with the help of the above technical solutions of the present invention, the present invention obtains the parameter data of the hydraulic lubrication drag reduction operation component and constructs the component digital twin model, ensuring that the performance evaluation is based on a highly accurate and comprehensive data model. The digital twin technology allows the simulation of real-world operation conditions, improving the authenticity and reliability of the simulation. Through the simulation evolution of the digital twin model, the performance data before and after optimization can be obtained and compared without actually intervening in the operation of the component, which not only saves costs, but also reduces the damage or wear caused to the component during the test. The niche theory is used to analyze the performance data, providing a novel perspective to evaluate the performance changes of the component. The niche theory helps to quantify the adaptability and efficiency of the component in its operating environment, making the performance evaluation more in-depth and multi-dimensional. The performance optimization effect is evaluated based on the results of the in-depth analysis, ensuring the scientific nature and practical significance of the evaluation results. The present invention reveals the intrinsic connection and mutual influence between parameters through the path analysis method of graph theory, increases the depth of understanding of system behavior, and can more accurately capture and analyze complex changes in time and space through the four-dimensional spatiotemporal data structure and spatial convolution operation, thereby extracting more representative and predictive feature information. The neural network is used to process the pre-processed feature information, which can improve the model's recognition ability for nonlinear and complex patterns. The present invention can analyze and understand performance data more comprehensively by introducing the niche theory into performance evaluation. By performing detailed trend analysis on performance data through time series analysis, the key trend components of performance changes can be identified and extracted, which is helpful to predict future performance changes and provide a basis for continuous improvement. By comparing the performance data before and after optimization and calculating the performance optimization rate, the effect of the improvement can be specifically quantified, providing a direct quantitative indicator for judging the actual benefits of the optimization measures. Using the niche value as a measure of performance can not only evaluate the current performance status, but also predict the performance of components under possibly changing operating conditions.

[0198] It should be understood by those skilled in the art that the embodiments of the present invention may be provided as methods, systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware aspects. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, optical storage, etc.) containing computer-usable program code.

[0199] The specific embodiments described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for evaluating the performance optimization effect of hydraulic lubrication and drag reduction working components, characterized in that: The method for evaluating the performance optimization effect of a hydraulic lubrication drag reduction operating component comprises the following steps: S1. Obtain parameter data of hydraulic lubrication and drag reduction operation components and build a digital twin model of the components; S2. Using the component digital twin model, simulate the evolution of the hydraulic lubrication and drag reduction operating components, and obtain the performance data of the hydraulic lubrication and drag reduction operating components before and after performance optimization; S3. Based on the performance data of the hydraulic lubrication drag reduction operating parts before and after the performance optimization, the performance of the hydraulic lubrication drag reduction operating parts before and after the performance optimization is analyzed using the niche theory; S4. Evaluate the performance optimization effect of the hydraulic lubrication drag reduction operating components according to the analysis results to obtain evaluation results; The method of obtaining parameter data of hydraulic lubrication and drag reduction operating components and constructing a component digital twin model comprises the following steps: S11, using a graph theory statistical method to pre-process the parameter data of the hydraulic lubrication drag reduction operating component to obtain a parameter relationship diagram; S12, performing feature enhancement processing on the parameter relationship graph by using a spatial convolution method, and extracting feature information; S13. Analyze and process the feature information using fuzzy neural network and logarithmic neural network, and build a digital twin model of the component; The method of analyzing the performance of the hydraulic lubrication drag reduction operating component before and after the performance optimization using the niche theory comprises the following steps: S31, establishing a performance index set of the hydraulic lubrication drag reduction operating component before and after optimization according to the performance data of the hydraulic lubrication drag reduction operating component before and after optimization; S32, performing a change trend analysis on each performance data in the performance index set of the hydraulic lubrication drag reduction operating component before and after optimization, and using the trend analysis result as the potential value of the ecological niche; S33, taking the performance data of the performance index set of the hydraulic lubrication drag reduction operating component before and after optimization as the state value of the ecological niche, and using the ecological niche calculation formula to calculate the ecological niche value of the hydraulic lubrication drag reduction operating component before and after optimization, and taking the ecological niche value as the performance value of the hydraulic lubrication drag reduction operating component; The ecological niche calculation formula is: ； In the formula, F i Indicates the ecological niche value of hydraulic lubrication and drag reduction operating components; R i and R j Respectively represent i performance indicators and j The potential value of each performance indicator; X i and X j All represent dimension conversion coefficients; Y i and Y j Respectively represent i performance indicators and j The state value of a performance indicator; m Represents the number of performance indicators in the performance indicator set of hydraulic lubrication and drag reduction working components.

2. A method for evaluating the performance optimization effect of a hydraulic lubrication drag reduction operating component according to claim 1, characterized in that: The method of using the component digital twin model to simulate and evolve the hydraulic lubrication and drag reduction operating component to obtain the performance data of the hydraulic lubrication and drag reduction operating component before and after performance optimization includes the following steps: S21, respectively obtaining simulation parameters of the hydraulic lubrication drag reduction operating component before and after performance optimization; S22, according to the simulation parameters before and after optimization, using the component digital twin model to respectively perform operation simulation on the hydraulic lubrication drag reduction operation components; S23. Record various performance data generated by the component digital twin model during the simulation process of a preset time period.

3. A method for evaluating the performance optimization effect of a hydraulic lubrication and drag reduction operating component according to claim 1, characterized in that: The method of using graph theory statistics to pre-process the parameter data of the hydraulic lubrication drag reduction working component to obtain the parameter relationship diagram includes the following steps: S111, performing data cleaning processing on parameter data of hydraulic lubrication drag reduction operation components; S112, projecting the cleaned parameter data into a BIM-based three-dimensional model using an LOD method to form a data projection; S113, expanding the parameter data projected in the BIM-based three-dimensional model according to the time series to form the original statistical results of the graph sequence; S114. Use the path analysis method in graph theory to analyze the original statistical results of the graph sequence, identify the propagation paths between parameters and construct a parameter relationship diagram.

4. A method for evaluating the performance optimization effect of a hydraulic lubrication and drag reduction operating component according to claim 1, characterized in that: The method of performing feature enhancement processing on the parameter relationship graph by using the spatial convolution method and extracting feature information comprises the following steps: S121, mapping the position and time information of each node in the parameter relationship graph into a four-dimensional space, and constructing a four-dimensional space-time data structure; S122, performing a spatial convolution operation on each data point in the four-dimensional space-time data structure based on a preset convolution kernel to obtain spatial convolution data; S123. Analyze the spatial convolution data to identify and extract feature information in the parameter relationship diagram.

5. The method for evaluating the performance optimization effect of a hydraulic lubrication and drag reduction operating component according to claim 1, characterized in that: The method of analyzing and processing the feature information by using the fuzzy neural network and the logarithmic neural network and constructing the component digital twin model includes the following steps: S131, preprocessing the feature information using a sixth-order polynomial deep iterative regression algorithm; S132, inputting the preprocessed feature information into the fuzzy neural network and the logarithmic neural network respectively, and obtaining the output of the fuzzy neural network and the output of the logarithmic neural network after processing; S133, fusing the output of the fuzzy neural network and the output of the logarithmic neural network to obtain fused feature information; S134. Based on the fused feature information, a digital twin model of the component is constructed using a simulation model.

6. A method for evaluating the performance optimization effect of a hydraulic lubrication and drag reduction operating component according to claim 5, characterized in that: The method of performing a change trend analysis on each performance data in the performance index set before and after the optimization of the hydraulic lubrication drag reduction operating component and using the trend analysis result as the potential value of the ecological niche includes the following steps: S321, using a time series method to perform data decomposition on each performance data in the performance index set before and after the optimization of the hydraulic lubrication drag reduction operation component; S322, identifying and extracting trend components after decomposition of each performance data; S323, calculating the change rate of each performance data according to the extracted trend component; S324. Use the calculated change rate as the potential value of each performance data niche.

7. A method for evaluating the performance optimization effect of a hydraulic lubrication and drag reduction operating component according to claim 1, characterized in that: According to the analysis results, the performance optimization effect of the hydraulic lubrication drag reduction working component is evaluated to obtain the evaluation results, which includes the following steps: S41, comparing all performance data performance values ​​of the performance index set before and after the optimization of the hydraulic lubrication drag reduction operation component; S42. Calculate the optimization rate of each performance indicator in the performance indicator set according to the comparison result; S43. Based on the optimization rate of each performance indicator and according to a preset evaluation threshold, determine whether the optimization effect of each performance indicator in the performance indicator set meets expectations.

8. A hydraulic lubrication drag reduction working component performance optimization effect evaluation system, used to implement the hydraulic lubrication drag reduction working component performance optimization effect evaluation method described in any one of claims 1 to 7, characterized in that: The performance optimization effect evaluation system of the hydraulic lubrication drag reduction working component comprises: a model construction module, a simulation evolution module, a performance analysis module and a performance evaluation module, and the model construction module, the simulation evolution module, the performance analysis module and the performance evaluation module are connected in sequence; The model building module is used to obtain parameter data of hydraulic lubrication and drag reduction operation components and build a digital twin model of the components; The simulation evolution module is used to simulate and evolve the hydraulic lubrication and drag reduction operating components using the component digital twin model, and obtain the performance data of the hydraulic lubrication and drag reduction operating components before and after performance optimization; The performance analysis module is used to analyze the performance of the hydraulic lubrication drag reduction operating component before and after the performance optimization using the niche theory according to the performance data of the hydraulic lubrication drag reduction operating component before and after the performance optimization; The performance evaluation module is used to evaluate the performance optimization effect of the hydraulic lubrication and drag reduction operating components according to the analysis results to obtain the evaluation results.

Images