A full-cycle management system for industrial equipment based on data analysis

Abstract

The present application provides a full-cycle management system for industrial equipment based on data analysis, which involves the field of full-cycle management of industrial equipment, and includes the following modules: a sensor data acquisition module, which is used to receive and process data transmitted by corrosion and crack sensors installed on the surface of the equipment, lubricant quality sensors installed in the lubricant unit of the equipment, and current and power sensors installed in the electrical unit of the equipment; an intelligent maintenance decision module; an equipment performance optimization module; and a user feedback and continuous optimization module. By integrating sensors and real-time monitoring technology, the present application systematically collects equipment operation data, promptly detects and warns of potential faults, and uses machine learning and AI technology to intelligently recommend maintenance strategies, significantly improving the timeliness and accuracy of equipment maintenance; the system can also optimize spare parts inventory management based on data analysis, reduce inventory backlogs, ensure timely supply of spare parts, and reduce operating costs.

Description

Technical Field

[0001] The present invention relates to the field of full-cycle management of industrial equipment, and in particular to a full-cycle management system for industrial equipment based on data analysis. Background Art

[0002] In industrial equipment management, traditional methods often rely on manual inspections and empirical judgments, resulting in low maintenance efficiency and frequent equipment failures. With the development of industrial Internet of Things and big data technology, full-cycle management of industrial equipment has become possible. However, most of the existing management systems are single-function and lack comprehensive data collection, real-time monitoring, intelligent maintenance decision-making, and performance optimization. In addition, these systems often fail to make full use of machine learning and artificial intelligence technologies, resulting in inaccurate maintenance decisions and inadequate optimization of spare parts inventory management. Therefore, it is of great practical significance and application value to develop an industrial equipment full-cycle management system based on data analysis to achieve comprehensive and intelligent management of equipment.

[0003] For example, the Chinese invention patent (application number: CN202410055286.7) discloses "a full-cycle management system for industrial equipment based on data analysis", and its specification discloses: With the rapid development of modern industry, the full-cycle management of industrial equipment has gradually become the core link of enterprise production and operation management. Among them, regular inspections, as an important part of the full-cycle management of industrial equipment, play a vital role in ensuring the normal operation of equipment, preventing failures and extending the service life of equipment. In order to better manage industrial equipment throughout its entire cycle, an industrial equipment full-cycle management system based on data analysis came into being. The existing technology has been able to combine advanced data analysis technology and artificial intelligence algorithms to analyze the relevant data of regular inspections of industrial equipment to evaluate the operating status or aging degree of industrial equipment, and take corresponding update or maintenance measures when abnormal operation or serious aging is found. Although it meets the existing basic requirements, it still has certain limitations, which are specifically manifested in: 1. The regular inspection of the existing technology is only aimed at timely discovering industrial equipment that has problems, and lacks the ability to fully recognize the remaining use cycle of each industrial equipment in advance. This means that the company lacks accurate predictions of possible failures and aging of industrial equipment in the future, and thus cannot formulate specific maintenance and replacement plans, resulting in uncertainty in the company's management and budget. 2. The existing technology does not clearly plan the equipment allocation fee per unit of output during the production process of industrial equipment, which makes it difficult for the company to accurately calculate the balance between equipment capacity and cost, so that the industrial equipment still presents a negative profit state when it is operating normally and not scrapped, which has a serious adverse impact on the company's production management, thereby limiting the accuracy and effectiveness of the company's equipment management and hindering its realization of more efficient and sustainable production management goals; the above patents can prove the defects of the existing technology.

[0004] Therefore, we made improvements to this and proposed a full-cycle management system for industrial equipment based on data analysis. Summary of the invention

[0005] The purpose of the present invention is to address the fact that most of the existing management systems currently have single functions and lack comprehensive data collection, real-time monitoring, intelligent maintenance decision-making and performance optimization functions; in addition, these systems often fail to fully utilize machine learning and artificial intelligence technologies, resulting in inaccurate maintenance decisions and inadequately optimized spare parts inventory management.

[0006] In order to achieve the above-mentioned purpose of the invention, the present invention provides an industrial equipment full-cycle management system based on data analysis to improve the above-mentioned problems.

[0007] The specific application is as follows:

[0008] Includes the following modules:

[0009] The sensor data acquisition module is used to receive and process the data transmitted by the corrosion and crack sensors installed on the equipment surface, the lubricant quality sensors installed in the lubricant unit of the equipment, and the current and power sensors installed in the electrical unit of the equipment;

[0010] The real-time data monitoring and early warning module is used to monitor the operating data of the enterprise's target batch of industrial equipment in real time and compare the data with the preset threshold. When the data exceeds the threshold, the early warning mechanism is automatically triggered. The real-time data monitoring and early warning module also includes a data cleaning and preprocessing unit to clean and preprocess the collected equipment data, remove noise and abnormal data, and improve the accuracy and reliability of the data; and a data visualization function to visualize the processed data in the form of charts and curves;

[0011] The intelligent maintenance decision module uses machine learning and artificial intelligence technologies to automatically analyze and recommend maintenance strategies based on the information provided by the real-time data monitoring and early warning modules and the historical maintenance records of the equipment. The intelligent maintenance decision module also includes a maintenance cost prediction unit and a spare parts inventory management unit.

[0012] The equipment performance optimization module analyzes the equipment's operating data and maintenance records to identify the equipment's performance bottlenecks and potential improvement points, and proposes equipment performance optimization suggestions; the equipment performance optimization module also includes a performance simulation and emulation unit and an optimization solution implementation tracking unit;

[0013] The user feedback and continuous optimization module is used to collect user feedback and opinions on the use of the system, and continuously optimize the system units and performance based on the actual situation of equipment management; the user feedback and continuous optimization module also includes a user feedback collection and analysis unit and a system iteration upgrade unit.

[0014] As the preferred technical solution of the present application, the sensor data acquisition module is used to transmit the equipment operation data collected in real time by each sensor to the system's cloud database for storage and analysis. The cloud database evaluates the aging degree of the equipment, estimates the remaining service life, predicts future failure risks, and analyzes the reference equipment apportionment costs per unit of production based on the collected data and the equipment's historical failure information and inspection information.

[0015] As the preferred technical solution of this application, the corrosion and crack sensor in the sensor data acquisition module adopts optical and magnetic induction principles to monitor the corrosion area, crack length and depth on the equipment surface in real time; the lubricating oil quality sensor adopts electrochemical and optical principles to monitor the metal particle content, temperature, acidity and viscosity in the lubricating oil in real time; the current and power sensor adopts the Hall effect and shunt resistor principles to monitor the current and power of the equipment in real time.

[0016] As a preferred technical solution of this application, the data cleaning and preprocessing unit includes:

[0017] Missing value processing: using Lagrange interpolation technology;

[0018] Outlier detection and processing: Statistical methods based on the 3σ principle;

[0019] Data standardization: min-max scaling and z-score standardization techniques were used;

[0020] Data visualization function: Chart drawing: use Matplotlib drawing library to draw histograms, line graphs and scatter plots;

[0021] Trend analysis: ARIMA model time series analysis technology is used.

[0022] As the preferred technical solution of this application, machine learning and artificial intelligence include:

[0023] Classification algorithms: Logistic regression, support vector machine, random forest, and gradient boosted tree algorithms are used for fault prediction;

[0024] Clustering algorithm: K-means and DBSCAN algorithms are used for equipment status clustering;

[0025] Regression algorithm: Linear regression, ridge regression and Lasso regression are used for maintenance cost prediction.

[0026] As the preferred technical solution of this application, the logistic regression expression is:

[0027] h θ (x) = 1 / (1+e -θTx );

[0028] Where θ is the parameter vector of the model; x is the input feature vector; h θ (x) gives the probability that input x belongs to the positive class;

[0029] The decision function of the support vector machine is:

[0030] f(x)=sign(∑ i＝1 n α i y i K(x i ,x)+b);

[0031] where α i is the Lagrange multiplier; y i is the training sample x i The label of K(x i ,x) is the kernel function used to calculate x i The similarity between and x; b is the bias term;

[0032] The expression of K-means clustering is:

[0033] J=∑ k＝1 K xi∈Ck ∑∥x i -μ k ∥ 2 ;

[0034] Where K is the number of clusters; C k is the kth cluster; x i is the data point belonging to cluster Ck; μ k is cluster C k The mean of ; ∥*∥ 2 Represents the squared Euclidean distance of vectors;

[0035] DBSCAN clustering; a density-based clustering method that determines core points, boundary points, and noise points by the number of points in the neighborhood;

[0036] The expression of linear regression is:

[0037] y=β0+β1x1+β2x2+…+βnxn+∈;

[0038] Where y is the dependent variable; x1, x2,…, xn are independent variables; β0, β1,…, βn are the coefficients of the model; ∈ is the error term.

[0039] As a preferred technical solution of this application, the performance simulation and emulation unit includes:

[0040] System modeling: physics-based models, data-driven models;

[0041] Optimization algorithm: Genetic algorithm, particle swarm optimization and simulated annealing optimization algorithm are used for parameter optimization;

[0042] Simulation platform: Use MATLAB, Python technology with NumPy and SciPy libraries to build a simulation platform;

[0043] The optimization plan implementation tracking unit includes:

[0044] A / B testing: compare the effects of different optimization solutions;

[0045] Feedback control: Closed-loop control system adjustments based on real-time data.

[0046] As the preferred technical solution of this application, the genetic algorithm specifically includes selection, crossover and mutation, and the specific formulas are as follows:

[0047] Selection: pi = f(xi) / ∑ j＝1 N f(x j );

[0048] Cross: x new =(xi1,xi2,...,xik,xj(k+1),...,xjn);

[0049] Mutation: x nk ′=x nk +δwithprobabilityμ;

[0050] Among them, f(x i ) is the fitness of the ith individual, N is the total number of individuals in the population; δ is a random small change, μ is the mutation rate;

[0051] The particle swarm optimization algorithm specifically includes speed update and position update, and its algorithm formula is as follows:

[0052] V(t+1)=W*V(t)+c1*rand*(pbest-Xi)+c2*rand*(gbest-Xi);

[0053] X(t+1)=X(t)+V(t+1);

[0054] Among them, W is the inertia coefficient, rand is a random number between 0 and 1, and c1 and c2 are acceleration coefficients.

[0055] As a preferred technical solution of this application, the user feedback collection and analysis unit includes:

[0056] Natural language processing: sentiment analysis and topic extraction for text feedback;

[0057] Questionnaire survey analysis: frequency analysis and cross-analysis statistical methods are used to implement the questionnaire survey;

[0058] The system iteration upgrade unit includes:

[0059] Incremental learning / online learning: continuous updating of the model based on new data;

[0060] User experience evaluation: Satisfaction index calculation based on user feedback.

[0061] As the preferred technical solution of the present application, the sensor power calculation formula in the sensor data acquisition module is: sensor power = sensor operating voltage × sensor operating current; the calculation formula of equipment overall efficiency (OEE) is: OEE = time operation rate × performance operation rate × qualified product rate, wherein the time operation rate reflects the time utilization of the equipment, the performance operation rate reflects the performance of the equipment, and the qualified product rate reflects the effective working condition of the equipment.

[0062] Compared with the prior art, the present invention has the following beneficial effects:

[0063] In the scheme of this application:

[0064] 1. In order to solve the problem of low equipment maintenance efficiency and accuracy in the existing technology, this application integrates multiple sensors and real-time monitoring technologies. The system can comprehensively collect equipment operation data, timely discover and warn potential faults, and significantly improve the timeliness and accuracy of equipment maintenance; at the same time, using machine learning and artificial intelligence technology, the intelligent maintenance decision module can automatically analyze data and recommend the most appropriate maintenance strategy, reducing the reliance on manual decision-making, and further improving maintenance efficiency and accuracy;

[0065] 2. In order to solve the problem of low equipment performance and production efficiency in the prior art, this application can identify performance bottlenecks and potential improvement points and put forward optimization suggestions by analyzing equipment operation data and maintenance records; the implementation of these optimization measures helps to improve the operation efficiency and production efficiency of the equipment, thereby improving the overall production benefits; in addition, the performance simulation and emulation unit can also simulate the effects of different optimization schemes to provide a scientific basis for optimization decisions;

[0066] 3. Based on historical and real-time data, the system can predict maintenance costs and spare parts demand, and optimize spare parts inventory management; this helps reduce inventory backlogs and waste, improve spare parts utilization, and thus reduce operating costs; at the same time, through accurate spare parts demand forecasting, the system can also ensure the timeliness of spare parts supply and avoid equipment downtime losses caused by spare parts shortages;

[0067] 4. Through the user feedback collection and analysis unit, this system can collect user feedback and opinions on the use of the system, promptly discover and solve system problems, and improve user satisfaction; at the same time, the system iteration upgrade unit can continuously optimize the system's functions and performance based on user feedback and actual needs, ensuring that the system always remains in the best state; this continuous optimization capability helps the system better adapt to the ever-changing market demands and user needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] Figure 1 A block diagram of the industrial equipment full-cycle management system based on data analysis provided in this application. DETAILED DESCRIPTION

[0069] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0070] As described in the background technology, most of the existing management systems have single functions and lack comprehensive data collection, real-time monitoring, intelligent maintenance decision-making, and performance optimization functions. In addition, these systems often fail to fully utilize machine learning and artificial intelligence technologies, resulting in inaccurate maintenance decisions and less optimized spare parts inventory management.

[0071] In order to solve this technical problem, the present invention provides an industrial equipment full-cycle management system based on data analysis, which is applied to the full-cycle optimization management system.

[0072] Specifically, please refer to Figure 1 The industrial equipment full-cycle management system based on data analysis specifically includes the following modules:

[0073] The sensor data acquisition module is used to receive and process the data transmitted by the corrosion and crack sensors installed on the equipment surface, the lubricant quality sensors installed in the lubricant unit of the equipment, and the current and power sensors installed in the electrical unit of the equipment;

[0074] A real-time data monitoring and early warning module is used to monitor the operating data of the target batch of industrial equipment of the enterprise in real time, and compare the data with the preset threshold value. When the data exceeds the threshold value, the early warning mechanism is automatically triggered; the real-time data monitoring and early warning module also includes a data cleaning and preprocessing unit, which cleans and preprocesses the collected equipment data, removes noise and abnormal data, and improves the accuracy and reliability of the data; and a data visualization function, which visualizes the processed data in the form of charts and curves;

[0075] An intelligent maintenance decision module, which uses machine learning and artificial intelligence technologies to automatically analyze and recommend the most appropriate maintenance strategy based on the information provided by the real-time data monitoring and early warning modules and the historical maintenance records of the equipment; the intelligent maintenance decision module also includes a maintenance cost prediction unit and a spare parts inventory management unit;

[0076] The equipment performance optimization module analyzes the equipment's operating data and maintenance records, identifies the equipment's performance bottlenecks and potential improvement points, and proposes equipment performance optimization suggestions; the equipment performance optimization module also includes a performance simulation and emulation unit and an optimization solution implementation tracking unit;

[0077] The user feedback and continuous optimization module is used to collect user feedback and opinions on the system, and continuously optimize the system's units and performance based on the actual situation of equipment management; the user feedback and continuous optimization module also includes a user feedback collection and analysis unit and a system iteration upgrade unit.

[0078] The industrial equipment full-cycle management system based on data analysis provided by the present invention integrates sensors and real-time monitoring technology, the system comprehensively collects equipment operation data, promptly discovers and warns of potential faults, and uses machine learning and AI technology to intelligently recommend maintenance strategies, thereby significantly improving the timeliness and accuracy of equipment maintenance; the system can also optimize spare parts inventory management based on data analysis, reduce inventory backlogs, ensure timely supply of spare parts, and reduce operating costs.

[0079] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings.

[0080] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features and technical solutions in the embodiments may be combined with each other.

[0081] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0082] Example 1, please refer to Figure 1A full-cycle management system for industrial equipment based on data analysis, in which the sensor data acquisition module is used to transmit the equipment operation data collected in real time by each sensor to the system's cloud database for storage and analysis. The cloud database evaluates the aging degree of the equipment, estimates the remaining service life, predicts future failure risks, and analyzes the reference equipment allocation fee per unit of production based on the collected data and combined with the equipment's historical failure information and inspection information, providing enterprises with decision support for equipment maintenance, updates, or technology updates.

[0083] Specifically, if Figure 1 As shown, the corrosion and crack sensors in the sensor data acquisition module adopt optical and magnetic induction principles to monitor the corrosion area, crack length and depth on the equipment surface in real time; the lubricating oil quality sensor adopts electrochemical and optical principles to monitor the metal particle content, temperature, acidity and viscosity in the lubricating oil in real time; the current and power sensor adopts the Hall effect and shunt resistance principles to monitor the current and power of the equipment in real time.

[0084] By integrating multiple sensors and real-time monitoring technologies, the system can comprehensively collect equipment operation data, promptly detect and warn of potential faults, and significantly improve the timeliness and accuracy of equipment maintenance. At the same time, using machine learning and artificial intelligence technologies, the intelligent maintenance decision module can automatically analyze data and recommend the most appropriate maintenance strategy, reducing reliance on manual decision-making and further improving maintenance efficiency and accuracy.

[0085] Please refer to Figure 1 , a full-cycle management system for industrial equipment based on data analysis, wherein the data cleaning and preprocessing unit comprises:

[0086] Missing value processing: Lagrange interpolation technology is used. The algorithm formula of Lagrange interpolation is:

[0087] L(x)=∑ i＝0 n l i (x)yi;

[0088] Among them l i (x) is the Lagrange basic polynomial, (x0,y0),(x1,y1),…,(xn,yn) are known points;

[0089] Outlier detection and processing: Statistical methods based on the 3σ principle;

[0090] Data standardization: min-max scaling and z-score standardization techniques are used. The min-max scaling and z-score standardization formulas are:

[0091] x′=(xx min ) / (xmax -x min );

[0092] z=(A-μ) / σ;

[0093] Where x is the original data value; x min is the minimum value in the data set; x max is the maximum value in the data set; x′ is the data value after min-max scaling, and its value is linearly transformed to the range of [0,1]; A is the original data value; μ is the mean of the data set; σ is the standard deviation of the data set; z is the data value after z-score standardization, also called standard score or z value;

[0094] Data visualization function: Chart drawing: use Matplotlib drawing library to draw histograms, line graphs and scatter plots;

[0095] Trend analysis: ARIMA model time series analysis technology is used.

[0096] Specifically, if Figure 1 As shown, the machine learning and artificial intelligence include:

[0097] Classification algorithms: Logistic regression, support vector machine (SVM), random forest, and gradient boosted tree (GBDT) algorithms are used for fault prediction;

[0098] Clustering algorithm: K-means and DBSCAN algorithms are used for equipment status clustering;

[0099] Regression algorithm: Linear regression, ridge regression and Lasso regression are used for maintenance cost prediction;

[0100] Reinforcement learning: used for dynamic maintenance strategy optimization;

[0101] The maintenance cost prediction functional unit includes:

[0102] Cost model construction: regression analysis and time series forecasting based on historical data;

[0103] Sensitivity analysis: Identify key factors that affect costs;

[0104] The spare parts inventory management unit includes:

[0105] Inventory optimization model: using economic order quantity model and safety stock calculation;

[0106] Inventory adjustment under predictive maintenance: Spare parts demand forecasting based on maintenance decisions.

[0107] Further, such as Figure 1 As shown, the logistic regression expression is:

[0108] h θ (x) = 1 / (1 + e -θTx );

[0109] Where θ is the parameter vector of the model; x is the input feature vector; h θ (x) gives the probability that input x belongs to the positive class;

[0110] The decision function of the support vector machine is:

[0111] f(x)=sign(∑ i＝1 n α i y i K(x i ,x)+b);

[0112] where α i is the Lagrange multiplier; y i is the training sample x i The label of K(x i ,x) is the kernel function used to calculate x i The similarity between and x; b is the bias term;

[0113] The expression of K-means clustering is:

[0114] J=∑ k＝1 K xi∈Ck ∑∥x i -μ k ∥ 2 ;

[0115] Where K is the number of clusters; C k is the kth cluster; x i is the data point belonging to cluster Ck; μ k is cluster C k The mean of ; ∥*∥ 2 Represents the squared Euclidean distance of vectors;

[0116] The DBSCAN clustering method is based on density, which determines the core points, boundary points and noise points by the number of points in the neighborhood.

[0117] The linear regression expression is:

[0118] y=β0+β1x1+β2x2+…+βnxn+∈;

[0119] Where y is the dependent variable; x1, x2, …, xn are independent variables; β0, β1, …, βn are the coefficients of the model; ∈ is the error term;

[0120] The expressions of the ridge regression and Lasso regression are respectively:

[0121] β=argmin β (∑ i＝1 n (y i -y^ i ) 2 +λ∑ j＝1 p β j 2 );

[0122] β=argmin β (∑ i＝1 n (y i -y^ i ) 2 +λ∑ j＝1 p ∣β j ∣);

[0123] where y i is the actual observed value; y^ i is the predicted value; λ is the regularization parameter used to control the complexity of the model; ∑ j＝1 p β j 2 is the L2 regularization term.

[0124] Example 2 further optimizes the industrial equipment full-cycle management system based on data analysis provided in Example 1. Specifically, Figure 1 As shown, the performance simulation and emulation unit includes:

[0125] System modeling: physics-based models, data-driven models;

[0126] Optimization algorithm: Genetic algorithm, particle swarm optimization and simulated annealing optimization algorithm are used for parameter optimization;

[0127] Simulation platform: Use MATLAB, Python technology with NumPy and SciPy libraries to build a simulation platform;

[0128] The optimization scheme implementation tracking unit includes:

[0129] A / B testing: compare the effects of different optimization solutions;

[0130] Feedback control: Closed-loop control system adjustments based on real-time data.

[0131] Further, such as Figure 1 As shown, the genetic algorithm specifically includes selection, crossover and mutation, and the specific formulas are as follows:

[0132] Selection: pi = f(xi) / ∑ j＝1 N f(x j );

[0133] Cross: x new =(xi1,xi2,...,xik,xj(k+1),...,xjn);

[0134] Mutation: x nk ′=x nk +δwithprobabilityμ;

[0135] Among them, f(x i ) is the fitness of the ith individual, N is the total number of individuals in the population; δ is a random small change, μ is the mutation rate;

[0136] The particle swarm optimization algorithm specifically includes speed update and position update, and its algorithm formula is as follows:

[0137] V(t+1)=W*V(t)+c1*rand*(pbest-Xi)+c2*rand*(gbest-Xi);

[0138] X(t+1)=X(t)+V(t+1);

[0139] Where W is the inertia coefficient, rand is a random number between 0 and 1, and c1 and c2 are acceleration coefficients;

[0140] The simulated annealing optimization algorithm formula is:

[0141] T = αT;

[0142] Where α is the cooling rate and T is the temperature.

[0143] Further, such as Figure 1 As shown, the user feedback collection and analysis unit includes:

[0144] Natural Language Processing (NLP): used for sentiment analysis and topic extraction of text feedback;

[0145] Questionnaire survey analysis: frequency analysis and cross-analysis statistical methods are used to implement the questionnaire survey;

[0146] The system iteration upgrade unit includes:

[0147] Incremental learning / online learning: continuous updating of the model based on new data;

[0148] User experience evaluation: Satisfaction index calculation based on user feedback.

[0149] Further, such as Figure 1 As shown, the sensor power calculation formula in the sensor data acquisition module is: sensor power = sensor operating voltage × sensor operating current; the equipment overall efficiency (OEE) calculation formula is: OEE = time operation rate × performance operation rate × qualified product rate, wherein the time operation rate reflects the time utilization of the equipment, the performance operation rate reflects the performance of the equipment, and the qualified product rate reflects the effective working condition of the equipment.

[0150] The use process of the industrial equipment full-cycle management system based on data analysis provided by the present invention is as follows:

[0151] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral one; it can be a mechanical connection, an electrical connection, or communication with each other; it can be a direct connection, or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements, unless otherwise clearly defined. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0152] Obviously, the embodiments described above are only some embodiments of the present invention, rather than all embodiments. The preferred embodiments of the present invention are given in the accompanying drawings, but they do not limit the patent scope of the present invention. The present invention can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present invention more thorough and comprehensive. Although the present invention has been described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific embodiments, or to perform equivalent replacements for some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of the present invention, directly or indirectly used in other related technical fields, is also within the scope of patent protection of the present invention.

Claims

1. A full-cycle management system for industrial equipment based on data analysis, characterized in that: Includes the following modules: The sensor data acquisition module is used to receive and process the data transmitted by the corrosion and crack sensors installed on the equipment surface, the lubricant quality sensors installed in the lubricant unit of the equipment, and the current and power sensors installed in the electrical unit of the equipment; The real-time data monitoring and early warning module is used to monitor the operating data of the target batch of industrial equipment of the enterprise in real time, and compare the data with the preset threshold value. When the data exceeds the threshold value, the early warning mechanism is automatically triggered; the real-time data monitoring and early warning module also includes a data cleaning and preprocessing unit, which cleans and preprocesses the collected equipment data, removes noise and abnormal data, and improves the accuracy and reliability of the data; And data visualization function, which can visualize the processed data in the form of charts and curves; An intelligent maintenance decision module, which uses machine learning and artificial intelligence technologies to automatically analyze and recommend maintenance strategies based on the information provided by the real-time data monitoring and early warning modules and the historical maintenance records of the equipment; the intelligent maintenance decision module also includes a maintenance cost prediction unit and a spare parts inventory management unit; Equipment performance optimization module, which analyzes the equipment's operating data and maintenance records, identifies the equipment's performance bottlenecks and potential improvement points, and provides suggestions for optimizing equipment performance; The equipment performance optimization module also includes a performance simulation and emulation unit and an optimization scheme implementation tracking unit; The user feedback and continuous optimization module is used to collect user feedback and opinions on the system, and continuously optimize the system's units and performance based on the actual situation of equipment management; the user feedback and continuous optimization module also includes a user feedback collection and analysis unit and a system iteration upgrade unit.

2. The full-cycle management system for industrial equipment based on data analysis according to claim 1 is characterized in that: The sensor data acquisition module is used to transmit the equipment operation data collected by each sensor in real time to the system's cloud database for storage and analysis. The cloud database evaluates the equipment's aging degree, estimates its remaining service life, predicts future failure risks, and analyzes the reference equipment allocation fee per unit of production based on the collected data and the equipment's historical failure information and inspection information.

3. The full-cycle management system for industrial equipment based on data analysis according to claim 2 is characterized in that: The corrosion and crack sensors in the sensor data acquisition module adopt optical and magnetic induction principles to monitor the corrosion area, crack length and depth on the equipment surface in real time; the lubricating oil quality sensor adopts electrochemical and optical principles to monitor the metal particle content, temperature, acidity and viscosity in the lubricating oil in real time; the current and power sensor adopts the Hall effect and shunt resistance principles to monitor the current and power of the equipment in real time.

4. The full-cycle management system for industrial equipment based on data analysis according to claim 3 is characterized in that: The data cleaning and preprocessing unit comprises: Missing value processing: using Lagrange interpolation technology; Outlier detection and processing: Statistical methods based on the 3σ principle; Data standardization: min-max scaling and z-score standardization techniques were used; Data visualization function: Chart drawing: use Matplotlib drawing library to draw histograms, line graphs and scatter plots; Trend analysis: ARIMA model time series analysis technology is used.

5. The full-cycle management system for industrial equipment based on data analysis according to claim 4 is characterized in that: The machine learning and artificial intelligence include: Classification algorithms: Logistic regression, support vector machine, random forest, and gradient boosted tree algorithms are used for fault prediction; Clustering algorithm: K-means and DBSCAN algorithms are used for equipment status clustering; Regression algorithm: Linear regression, ridge regression and Lasso regression are used for maintenance cost prediction.

6. The full-cycle management system for industrial equipment based on data analysis according to claim 5, characterized in that: The logistic regression expression is: h θ (x)=1 / (1+e -θTx ); Where θ is the parameter vector of the model; x is the input feature vector; h θ (x) gives the probability that input x belongs to the positive class; The decision function of the support vector machine is: f(x)=sign(∑ i＝1 n α i y i K(x i ,x)+b); where α i is the Lagrange multiplier; y i is the training sample x i The label of K(x i ,x) is the kernel function used to calculate x i The similarity between and x; b is the bias term; The expression of K-means clustering is: Where K is the number of clusters; C k is the kth cluster; x i is the data point belonging to cluster Ck; μ k is cluster C k The mean of ; ∥*∥ 2 Represents the squared Euclidean distance of vectors; The DBSCAN clustering method is based on density, which determines the core points, boundary points and noise points by the number of points in the neighborhood. The linear regression expression is: y=β0+β1x1+β2x2+…+βnxn+∈; Where y is the dependent variable; x1, x2,…, xn are independent variables; β0, β1,…, βn are the coefficients of the model; ∈ is the error term.

7. The full-cycle management system for industrial equipment based on data analysis according to claim 6 is characterized in that: The performance simulation and emulation unit comprises: System modeling: physics-based models, data-driven models; Optimization algorithm: Genetic algorithm, particle swarm optimization and simulated annealing optimization algorithm are used for parameter optimization; Simulation platform: Use MATLAB, Python technology with NumPy and SciPy libraries to build a simulation platform; The optimization scheme implementation tracking unit includes: A / B testing: compare the effects of different optimization solutions; Feedback control: Closed-loop control system adjustments based on real-time data.

8. The full-cycle management system for industrial equipment based on data analysis according to claim 7 is characterized in that: The genetic algorithm specifically includes selection, crossover and mutation, and the specific formulas are as follows: Selection: pi = f(xi) / ∑ j＝1 N f(x j ); Cross: x new =(xi1, xi2,..., xik, xj(k + 1),..., xjn); Mutation: x nk ′=x nk +δwithprobabilityμ; Among them, f(x i ) is the fitness of the ith individual, N is the total number of individuals in the population; δ is a random small change, μ is the mutation rate; The particle swarm optimization algorithm specifically includes speed update and position update, and its algorithm formula is as follows: V(t+1)=W*V(t)+c1*rand*(pbest-Xi)+c2*rand*(gbest-Xi); X(t+1)=X(t)+V(t+1); Among them, W is the inertia coefficient, rand is a random number between 0 and 1, and c1 and c2 are acceleration coefficients.

9. The full-cycle management system for industrial equipment based on data analysis according to claim 8, characterized in that: The user feedback collection and analysis unit comprises: Natural language processing: sentiment analysis and topic extraction for text feedback; Questionnaire survey analysis: frequency analysis and cross-analysis statistical methods are used to implement the questionnaire survey; The system iteration upgrade unit includes: Incremental learning / online learning: continuous updating of the model based on new data; User experience evaluation: Satisfaction index calculation based on user feedback.

10. The full-cycle management system for industrial equipment based on data analysis according to claim 9, characterized in that: The sensor power calculation formula in the sensor data acquisition module is: sensor power = sensor operating voltage × sensor operating current; the equipment overall efficiency (OEE) calculation formula is: OEE = time operation rate × performance operation rate × qualified product rate, where the time operation rate reflects the time utilization of the equipment, the performance operation rate reflects the performance of the equipment, and the qualified product rate reflects the effective working condition of the equipment.

Images