Electromechanical Equipment Full Life Cycle Management System

Abstract

The present invention provides a full life cycle management system for electromechanical equipment, comprising: an acquisition module, configured to acquire the current stage of the electromechanical equipment in the full life cycle, and determine the device variable parameters and device measurement parameters that need to be monitored currently; an offset module, configured to acquire the operating state and environmental parameters of the electromechanical equipment, and determine a measurement parameter offset value based on the operating state and environmental parameters; offset the device measurement parameters based on the measurement parameter offset value to obtain offset measurement parameters; a measurement module, configured to determine a corresponding parameter measurement device based on the device variable parameters; control the parameter measurement device to measure the device variable parameters of the electromechanical equipment with the offset measurement parameters to obtain a parameter set; and a control module, configured to analyze the parameter set and control the operation of the electromechanical equipment based on the analysis result. In the present invention, the defects of inaccurate data measurement and resource waste in the current full life cycle management process are overcome.

Description

Technical Field

[0001] The present invention relates to the technical field of measuring variables, and particularly to a full life cycle management system for electromechanical equipment. Background Art

[0002] In the process of full life cycle management of electromechanical equipment, the measurement of variable parameters on electromechanical equipment plays a crucial role.

[0003] In traditional electromechanical equipment management, the monitoring and maintenance of equipment often rely on manual operation and simple sensor feedback. However, this management method has many limitations. On the one hand, when monitoring the variable parameters of electromechanical equipment, a fixed measurement mode and measurement cycle are usually adopted without considering the life cycle stage, operating state and actual environmental conditions of the equipment.

[0004] This is likely to cause the following problems:

[0005] Data inaccuracy: Since the characteristics of the equipment are different at different stages and in different environments, using a unified measurement mode and cycle cannot accurately capture the key information of the equipment during critical periods or in special environments.

[0006] Resource waste: For some equipment that is in a stable operation state for a long time, data will be over-measured, increasing the burden of data storage and processing, resulting in unnecessary resource waste; at the same time, in some high-risk or high-load situations, due to insufficient measurement frequency, abnormalities of the equipment may not be detected in time, resulting in potential faults that cannot be eliminated in time. Summary of the Invention

[0007] The main purpose of the present invention is to provide a full life cycle management system for electromechanical equipment, aiming to overcome the defects of inaccurate data measurement and resource waste in the current full life cycle management process.

[0008] To achieve the above purpose, the present invention provides a full life cycle management system for electromechanical equipment, including:

[0009] An acquisition module, configured to acquire the current stage of the electromechanical equipment in the full life cycle; based on the current stage, determine the equipment variable parameters and equipment measurement parameters that need to be monitored currently;

[0010] A deviation module, configured to acquire the operating state and environmental parameters of the electromechanical equipment, determine a measurement parameter deviation value based on the operating state and environmental parameters; offset the equipment measurement parameters based on the measurement parameter deviation value to obtain offset measurement parameters;

[0011] A measurement module, configured to determine a corresponding parameter measurement device based on the device variable parameters; control the parameter measurement device to measure the device variable parameters of the electromechanical device with the offset measurement parameters, so as to obtain a parameter set;

[0012] A control module, configured to analyze the parameter set and control the operation of the electromechanical device based on the analysis result.

[0013] Further, the device measurement parameters include a measurement mode and a measurement period.

[0014] Further, determining a measurement parameter offset value based on the operating state and environmental parameters includes:

[0015] Performing feature extraction on the operating state to obtain an operating state feature;

[0016] Performing feature extraction on the environmental parameters to obtain an environmental feature;

[0017] Performing feature fusion processing on the operating state feature and the environmental feature to obtain a fusion feature;

[0018] Inputting the fusion feature into a pre-trained machine learning model to output a corresponding measurement parameter offset value; the measurement parameter offset value includes an adjustment amount of the measurement mode and an adjustment amount of the measurement period.

[0019] Further, analyzing the parameter set and controlling the operation of the electromechanical device based on the analysis result includes:

[0020] Mining the mutual influence relationship between different types of device variable parameters in the parameter set based on data mining technology to form associated state information;

[0021] Evaluating the current risk assessment level of the electromechanical device according to the associated state information and combining the historical data of the electromechanical device by means of a combination of a rule-based inference system and a machine learning algorithm;

[0022] Generating a dynamic control strategy for the risk assessment level to obtain a control instruction set;

[0023] Transmitting the control instruction set to the corresponding execution components of the electromechanical device through a distributed control system to control the operation of the electromechanical device.

[0024] Further, the device variable parameters include shape parameters, mechanical parameters, electrical parameters, and thermal parameters.

[0025] Further, the system further includes:

[0026] A generation module, configured to generate an offset curve based on the offset measurement parameters; sequentially add each parameter in the parameter set to a matrix to generate a parameter matrix; perform a transformation on the parameter matrix based on the analysis result to obtain a transformation matrix.

[0027] An encryption module, configured to generate a management key based on the offset curve and the transformation matrix; encrypt the parameter set based on the management key and store it in a management database.

[0028] Further, generating a management key based on the offset curve and the transformation matrix includes:

[0029] Mine the curve characteristics of the offset curve to obtain a curve identifier.

[0030] Reshape the spatial structure of the transformation matrix to obtain a matrix spatial structure encoding.

[0031] Perform a random interleaving process on the curve identifier and the matrix spatial structure encoding to obtain interleaved information.

[0032] Based on a custom encryption mapping table, map each element in the interleaved information to a new element, and combine them to form a management key; wherein, the encryption mapping table is updated according to different electromechanical devices and time.

[0033] Further, generating a management key based on the offset curve and the transformation matrix includes:

[0034] Construct an undirected graph for the offset curve to obtain an offset curve undirected graph; wherein, each data point of the offset curve is set as an undirected graph node, and an edge is connected between adjacent nodes.

[0035] Convert the transformation matrix into a directed graph to obtain a transformation matrix directed graph; wherein, the matrix elements are used as directed graph nodes, and an edge is formed by a large element pointing to a small element, and the edge weight is determined by the absolute value of the element difference.

[0036] Merge the offset curve undirected graph and the transformation matrix directed graph to obtain a merged graph.

[0037] Mine the graph features of the merged graph to obtain a graph feature set; perform a feature set transformation on the graph feature set to obtain an intermediate encoding.

[0038] Adjust the encoding of the intermediate encoding to obtain the management key.

[0039] The electromechanical equipment full - life - cycle management system provided by the present invention includes: an acquisition module, configured to acquire the current stage of the electromechanical equipment in the full life cycle; based on the current stage, determine the current equipment variable parameters and equipment measurement parameters to be monitored; an offset module, configured to acquire the operating state and environmental parameters of the electromechanical equipment, and determine a measurement parameter offset value based on the operating state and environmental parameters; offset the equipment measurement parameters based on the measurement parameter offset value to obtain offset measurement parameters; a measurement module, configured to determine the corresponding parameter measurement equipment based on the equipment variable parameters; control the parameter measurement equipment to measure the equipment variable parameters of the electromechanical equipment with the offset measurement parameters to obtain a parameter set; a control module, configured to analyze the parameter set and control the operation of the electromechanical equipment based on the analysis result. In the present invention, by combining the stage of the current electromechanical equipment in the full life cycle, the current operating state and environmental parameters, the equipment measurement parameters are dynamically adjusted, overcoming the defects of inaccurate data measurement and resource waste in the current full - life - cycle management process. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 is the structural block diagram of the electromechanical equipment full - life - cycle management system in an embodiment of the present invention;

[0041] Figure 2 is the step schematic diagram of the electromechanical equipment full - life - cycle management method in an embodiment of the present invention;

[0042] Figure 3 is the structural schematic block diagram of a computer device in an embodiment of the present invention.

[0043] The implementation, functional features and advantages of the present invention will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0044] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0045] Refer to Figure 1 , in an embodiment of the present invention, a kind of electromechanical equipment full - life - cycle management system is provided, including:

[0046] An acquisition module, configured to acquire the current stage of the electromechanical equipment in the full life cycle; based on the current stage, determine the current equipment variable parameters and equipment measurement parameters to be monitored;

[0047] An offset module, configured to obtain the operating state and environmental parameters of the electromechanical device, determine a measurement parameter offset value based on the operating state and environmental parameters; offset the device measurement parameters based on the measurement parameter offset value to obtain offset measurement parameters;

[0048] A measurement module, configured to determine a corresponding parameter measurement device based on the device variable parameters; control the parameter measurement device to measure the device variable parameters of the electromechanical device with the offset measurement parameters to obtain a parameter set;

[0049] A control module, configured to analyze the parameter set and control the operation of the electromechanical device based on the analysis result.

[0050] In this embodiment, a full-life cycle management system for electromechanical devices is proposed, aiming to achieve comprehensive, dynamic, and intelligent management of electromechanical devices, covering the entire life cycle from device startup, operation to final maintenance and update. The system flexibly adjusts measurement and control strategies according to different stages, operating states, and environmental conditions of the device through the collaborative work of multiple functional modules, so as to improve the performance, reliability, and maintenance efficiency of the device.

[0051] The above-mentioned acquisition module is mainly responsible for identifying the specific stage of the electromechanical device in the full-life cycle, including the initial installation and commissioning stage, normal operation stage, aging stage with frequent failures, maintenance stage, and final scrapping stage of the device, etc. According to the determined current stage, further clarify the device variable parameters and device measurement parameters that need to be monitored currently. Device variable parameters can be various physical quantities that can reflect the device performance and operating state, such as temperature, pressure, vibration, current, rotational speed, etc.; device measurement parameters involve the relevant parameters for measuring these variables, such as measurement mode (continuous measurement, intermittent measurement, etc.) and measurement period (time interval). By combining the life cycle stage of the device to determine the monitored parameters and measurement methods, it ensures that the most valuable data can be obtained targeted at different stages, avoiding the problems of data redundancy or missing key information caused by fixed measurement parameters and measurement periods in traditional systems.

[0052] The above-mentioned offset module fully considers the actual operating conditions of the electromechanical equipment and the environmental conditions. The operating conditions can cover the load conditions of the equipment, the operating speed, the wear state of the equipment components, etc.; the environmental parameters include external environmental factors such as temperature, humidity, air pressure, and electromagnetic interference. By comprehensively evaluating these operating conditions and environmental parameters, the offset value of the measurement parameter is determined. According to the actual operating conditions of the equipment and the influence of the external environment, the measurement parameters of the equipment are dynamically adjusted. For example, when the equipment is in a high-load operating state or in a high-temperature and high-humidity environment, it may be necessary to shorten the measurement cycle or adjust the measurement mode to more closely monitor the performance changes of the equipment and prevent the risk of failures caused by rapid changes in the equipment performance under extreme conditions. Finally, the offset value of the measurement parameter is applied to the measurement parameters of the equipment to obtain the offset measurement parameters, making the measurement parameters more targeted and adaptable and providing a basis for subsequent accurate measurements.

[0053] The above-mentioned measurement module selects appropriate parameter measurement equipment according to the equipment variable parameters. Different equipment variable parameters require different measurement equipment, such as a temperature sensor for measuring temperature, a pressure sensor for measuring pressure, a vibration sensor for measuring vibration, an ammeter for measuring current, etc.

[0054] The offset measurement parameters are used to control the parameter measurement equipment to perform measurement operations on the electromechanical equipment. Through the dynamically adjusted offset measurement parameters, the parameter measurement equipment can measure the equipment more precisely and obtain a set of parameters that are more in line with the current state of the equipment. This set of parameters contains a series of measured values of the equipment variable parameters obtained according to the adjusted measurement mode and period, providing data support for subsequent analysis and control.

[0055] The above-mentioned control module deeply analyzes the set of parameters obtained from the measurement module. The analysis process involves statistical analysis, feature extraction, pattern recognition, etc. of the measurement data to accurately evaluate the current operating state of the equipment. For example, by analyzing the temperature parameter, it can be judged whether the equipment has overheating; by analyzing the vibration parameter, it can be found whether there are problems such as imbalance or component looseness in the equipment.

[0056] Based on the analysis results, the control module can perform corresponding control on the operation of the electromechanical equipment. The above control can be to adjust the operating parameters of the equipment, such as adjusting the speed of the motor or adjusting the opening of the valve; it can also be to trigger the protection mechanism of the equipment, such as starting the cooling system when it is detected that the equipment is overheating; it can also be to issue a maintenance prompt or an alarm signal to notify relevant personnel when the equipment is in an abnormal state and needs maintenance or repair.

[0057] Different from the method of using fixed measurement parameters and measurement periods in traditional electromechanical equipment management systems, the system of the present invention can dynamically adjust measurement parameters according to the operating state of the equipment and environmental conditions. This enables the system to obtain data that best reflects the actual state of the equipment under different circumstances (such as different operating stages, different loads, or environmental conditions), improving the effectiveness and accuracy of data collection and helping to detect potential problems earlier. Considering the entire life cycle of the equipment, different monitoring and management strategies are adopted at different stages. At different stages of the equipment, its performance, reliability, and failure risks are different. By adjusting monitoring parameters and control strategies according to the life cycle stage, preventive maintenance and performance optimization of the equipment can be better achieved, the service life of the equipment can be extended, and the total life cycle cost of the equipment can be reduced.

[0058] Through in-depth analysis of the parameter set, the control module can make precise control according to the actual operating conditions of the equipment. No longer limited to simple threshold judgment, but based on the comprehensive analysis results of multi-dimensional parameters, more intelligent and targeted control decisions are made, reducing the downtime of the equipment and improving the operating efficiency of the equipment and the continuity of production.

[0059] In summary, the full life cycle management system of electromechanical equipment of the present invention has significant innovation and practicality in the management of electromechanical equipment. By dynamically adjusting measurement parameters, implementing full life cycle management, and making precise control decisions, it provides strong support for the efficient and stable operation of electromechanical equipment.

[0060] In one embodiment, the equipment measurement parameters include measurement mode and measurement period.

[0061] In one embodiment, determining the measurement parameter offset value based on the operating state and environmental parameters includes:

[0062] Performing feature extraction on the operating state to obtain operating state features;

[0063] Performing feature extraction on the environmental parameters to obtain environmental features;

[0064] Performing feature fusion processing on the operating state features and environmental features to obtain fusion features;

[0065] Inputting the fusion features into a pre-trained machine learning model to output the corresponding measurement parameter offset value; the measurement parameter offset value includes the adjustment amount of the measurement mode and the adjustment amount of the measurement period.

[0066] In this embodiment, the operating state of the electromechanical device covers many aspects and is the key information reflecting the performance and working conditions of the device during actual operation. It may include, but is not limited to, the power output of the device, the operating frequency, and the operating speed of the device. These operating state information are crucial for evaluating the health status of the device, predicting potential faults of the device, and determining subsequent monitoring and management strategies.

[0067] To effectively utilize this operating state information, it is necessary to convert it into operating state features that are more representative and convenient for subsequent processing. This is because the original operating state data is usually large in quantity and complex, and directly processing them will increase the computational burden and may not clearly reflect the key features of the device.

[0068] The extracted operating state features will provide an important basis for determining the offset value of the measurement parameters subsequently. They can more intuitively display various state indicators of the current operation of the device, provide a quantitative reference for the system to evaluate whether the device is in a normal state, whether the measurement parameters need to be adjusted, and the direction and magnitude of the adjustment. At the same time, these features can be used as input information for subsequent machine learning models to help the models better understand the internal state of the device operation and then make more scientific decisions.

[0069] The environmental parameters describe the external environmental conditions in which the electromechanical device is located. Their scope is extensive and mainly includes temperature, humidity, air pressure, vibration, electromagnetic interference, dust, and the concentration of corrosive gases, etc. These environmental factors will have a significant impact on the normal operation of the device. For example, high temperature may cause thermal expansion of the device components, affecting the accuracy and performance of the device; high humidity may cause short circuits or corrosion of electrical components; strong vibration may cause loosening or damage of the mechanical components of the device; electromagnetic interference will affect the transmission and processing of electrical signals of the device; dust and corrosive gases may erode the surface and internal structure of the device, reducing the reliability and service life of the device.

[0070] To quantify the impact of these environmental factors on the device, it is necessary to extract features from the environmental parameters. For temperature, the relative position of the current temperature within the normal operating temperature range of the device (such as the degree above or below the normal range), the rate of change of temperature, and the extreme values of temperature can be extracted; for humidity, the relative humidity percentage and the change range of humidity can be extracted; for air pressure, the difference from the standard atmospheric pressure and the change trend of air pressure can be considered; for vibration, the amplitude, frequency, vibration energy, etc. of vibration can be extracted; for electromagnetic interference, the intensity, frequency distribution, and duration of interference can be measured; for dust and corrosive gas concentration, the ratio to the maximum allowable concentration or the rate of change of concentration can be calculated. Through these feature extraction operations, the environmental parameters are converted into a set of quantifiable environmental features, providing precise data support for subsequent decision-making.

[0071] The operating state of the device and its surrounding environment are not independent of each other, but are closely related and interact with each other. The device has different sensitivities to the environment under different operating states, and at the same time, the impact of environmental factors on the device also varies depending on the operating state of the device. Therefore, considering only the operating state characteristics or environmental characteristics alone cannot fully describe the actual situation of the device. Feature fusion processing aims to combine these two types of characteristics to form a more comprehensive and representative feature set.

[0072] A common method is simple concatenation, that is, combining the operating state feature vector and the environmental feature vector in sequence to form a new vector. This method is simple and direct and can completely retain the information of both types of features. Another method is weighted fusion. According to the importance of different features, different weights are assigned to the operating state features and environmental features, and then weighted summation is performed to obtain a fused feature vector. This requires certain prior knowledge of the importance of different features or determining the weights through data analysis. A more advanced approach can adopt deep learning feature fusion techniques, such as using fully connected layers or attention mechanisms in neural networks. Taking the operating state features and environmental features as inputs, it automatically learns the internal relationship between them and generates a fused feature. No matter which method is adopted, it is to represent the influence of the operating state of the device and environmental factors in a unified and more informative way.

[0073] The machine learning model needs to be trained. The training data comes from a large amount of device operation historical data, which contains the operating state characteristics, environmental characteristics of the device, and the corresponding measurement parameter offset values under different operating states and environmental conditions. These measurement parameter offset values are obtained through practical experience, experiments, or more refined analysis, and reflect how to adjust the measurement parameters to ensure effective monitoring of the device in different situations. By allowing the machine learning model to learn this data, it can master the complex relationship between the operating state and environmental characteristics and the measurement parameter offset values.

[0074] When the fused features are input into a pre-trained machine learning model, the model will perform reasoning and prediction based on the knowledge and patterns it has learned. For example, if the input fused features indicate that the device is in an environment with high power, high vibration, and high temperature, the model will determine that the device is in a high-risk state, and thus output measurement parameter offset values such as shortening the measurement period and adjusting the measurement mode to a more intensive monitoring method (such as changing from periodic measurement to continuous measurement) to monitor the device status more closely; while if the input fused features show that the device is in a stable operating state and the environmental conditions are good, the model will output an appropriate extension of the measurement period and a relaxation of the adjustment amount of the measurement mode to avoid unnecessary measurement operations and resource waste. The measurement parameter offset values here mainly include the adjustment amount of the measurement mode and the adjustment amount of the measurement period. The adjustment of the measurement mode can be converted from coarse-grained measurement to fine-grained measurement, or vice versa, and the adjustment of the measurement period can be an extension or shortening of a certain time interval.

[0075] In one embodiment, the parameter set is analyzed, and based on the analysis results, the operation of the electromechanical device is controlled, including:

[0076] Based on data mining techniques, the mutual influence relationships between different types of device variable parameters in the parameter set are mined to form associated status information;

[0077] By combining a rule-based inference system and a machine learning algorithm, according to the associated status information and in combination with the historical data of the electromechanical device, the current risk assessment level of the electromechanical device is evaluated;

[0078] A dynamic control strategy is generated for the risk assessment level to obtain a control instruction set;

[0079] The control instruction set is transmitted to the corresponding execution components of the electromechanical device through a distributed control system to control the operation of the electromechanical device.

[0080] In this embodiment, the parameter set of the electromechanical device includes various types of device variable parameters, such as temperature, pressure, vibration, current, rotational speed, etc. These parameters do not exist in isolation during the operation of the device, but are interrelated and interact with each other. However, these complex relationships may not be intuitive and are difficult to accurately grasp through simple observation or traditional analysis methods. Therefore, data mining techniques are used to find hidden patterns and relationships from a large amount of parameter data.

[0081] First, data mining techniques can process historical data in the parameter set. By using association rule mining algorithms (such as the Apriori algorithm), frequent item sets and association rules between different device variable parameters can be found. For example, it is found that when the rotational speed of a device increases, the temperature of the device also rises, and at the same time, the vibration amplitude may increase; or when the pressure increases, the current will change accordingly, etc. Clustering algorithms (such as K-Means clustering) can also be used to cluster similar parameter combinations or device operating states, find the aggregation patterns of different parameters under different operating states, and thus discover some potential mutual influence relationships.

[0082] In addition, regression analysis can be used to establish a mathematical model between different device variable parameters to quantify the relationship between them. For example, a linear or non-linear regression equation between temperature and current can be established, and statistical analysis is used to evaluate the correlation and influence degree between different parameters. After being processed by data mining techniques, the mutual influence relationships between various device variable parameters are represented in the form of association state information.

[0083] The rule-based reasoning system uses pre-set expert rules and empirical knowledge to evaluate the operating state of the device. These rules can be formulated based on industry standards, the operation manuals of device manufacturers, long-term accumulated maintenance experience, etc. For example, if the temperature of the device exceeds a certain threshold and the vibration amplitude exceeds another threshold, according to the rules, it can be judged that the device is in a high-risk state. These rules are a logical expression that clearly defines the known risk situations during the operation of the device.

[0084] However, relying solely on rules cannot cover all possible situations, especially for complex electromechanical devices and changing operating environments. Therefore, machine learning algorithms need to be combined to handle some complex relationships that are difficult to represent by rules.

[0085] Machine learning algorithms (such as neural networks, support vector machines, decision trees, etc.) can be used to learn from historical data and establish models for normal and abnormal operation of the device. By using the association state information and historical data as inputs, machine learning algorithms can discover some potential risk patterns that are difficult to represent by simple rules. For example, some devices may have a failure risk under some complex parameter combinations and change patterns, and these patterns may not be judged by simple thresholds and rules, but machine learning algorithms can identify them through learning a large amount of historical data.

[0086] Combining a rule-based inference system and machine learning algorithms can more comprehensively and accurately evaluate the current state of the device. When the current associated state information and historical data are input, the system can comprehensively consider known rules and learned complex patterns, and assign a risk assessment level to the current operating state of the device. This level can be different levels from low risk to high risk, such as safe, minor risk, medium risk, high risk, etc., to quantify the current risk degree of the device.

[0087] Different risk assessment levels correspond to different control strategies to ensure the safe and stable operation of the device. When the device is in a low-risk state, the control strategy can focus on optimizing the performance of the device and improving the operating efficiency of the device; for medium risks, some preventive maintenance measures need to be taken or the operating parameters of the device need to be adjusted; while in a high-risk state, measures need to be taken immediately to prevent device failures or damages, and even emergency shutdowns may be required.

[0088] The control instruction set is a comprehensive set of instructions that contains various operation instructions for the device. These instructions are dynamically generated according to the risk assessment level to ensure that the operation of the device can be adjusted accordingly according to the current risk state, so as to ensure the safety and reliability of the device.

[0089] The distributed control system is a system that can coordinate and control each execution component of the electromechanical device. It can manage multiple execution components, such as motor drivers, valve controllers, sensors, etc. The system has a distributed architecture and can perform data processing and control operations on different nodes, improving the reliability and response speed of the system.

[0090] After the control instruction set is generated, these instructions are transmitted to the corresponding execution components of the electromechanical device through the distributed control system. For example, the instruction to adjust the rotational speed is sent to the motor driver, and the instruction to adjust the valve opening is sent to the valve controller, etc. The distributed control system ensures the accurate transmission and timely execution of the instructions, enabling the operating state of the device to be adjusted accordingly according to the control instructions. At the same time, it can also collect the feedback information of the execution components for subsequent monitoring and evaluation, forming a closed-loop control and feedback mechanism to continuously optimize the operation management of the device.

[0091] In one embodiment, the device variable parameters include shape parameters, mechanical parameters, electrical parameters, and thermal parameters.

[0092] In one embodiment, the system further includes:

[0093] A generation module, configured to generate an offset curve based on the offset measurement parameters; sequentially add each parameter in the parameter set to a matrix to generate a parameter matrix; transform the parameter matrix based on the analysis result to obtain a transformation matrix;

[0094] An encryption module, configured to generate a management key based on the offset curve and the transformation matrix; encrypt the parameter set based on the management key and store it in a management database.

[0095] In this embodiment, the offset measurement parameter is a measurement parameter dynamically adjusted according to the operating state and environmental conditions of the device, which can better reflect the monitoring requirements of the device under the current actual situation. Generating the offset curve is to represent these offset measurement parameters in the form of a curve, which can intuitively show the change trend of the measurement parameters over time or other dimensions. For example, for the offset measurement parameters of a certain device variable parameter (such as temperature), if its measurement period and measurement mode have been dynamically adjusted, plotting the measurement results at different time points as a curve can clearly observe the change of the monitoring strategy of this parameter at different times.

[0096] The parameter set contains the measurement values of multiple device variable parameters collected from electromechanical devices. These parameters are arranged in a certain order (such as according to different types of device variable parameters, or according to the time sequence of measurement) and stored in a matrix. The rows and columns of the matrix can respectively represent different device variable parameters and different measurement time points or sample numbers. For example, the rows of the matrix can represent different parameters such as temperature, pressure, and vibration, and the columns can represent different measurement moments. The matrix elements are the measurement values of the corresponding parameters at that moment. Converting the parameter set into a parameter matrix provides a structured data storage and processing method for subsequent analysis and processing. The matrix is a commonly used data structure in mathematics and computer processing, which is convenient for various mathematical operations and data analysis, such as matrix operations, eigenvalue decomposition, singular value decomposition, etc., and helps to analyze the state and performance of the device from multiple dimensions. At the same time, the matrix form is also convenient for storage and invocation, improving the efficiency and standardization of data processing.

[0097] After analyzing the parameter set, some analysis results regarding the device state will be obtained, and these results can be used as the basis for transforming the parameter matrix. The transformation can be in various forms. For example, according to the operating state of the device, linear transformations such as rotation, scaling, and translation are performed on the parameter matrix, or according to the risk assessment result of the device, some key parameters are weighted to obtain the transformation matrix. It can also be through some complex algorithms, such as machine learning algorithms or data mining algorithms, to perform feature transformation on the parameter matrix and extract more representative feature information.

[0098] The offset curve and transformation matrix contain rich device status information and measurement information. The process of generating a management key through them can adopt various innovative methods. For example, the key features in the offset curve and transformation matrix (such as the peaks and valleys of the curve, the eigenvalues and singular values of the matrix, etc.) can be extracted, and then these features can be converted into a management key through a certain mapping function. It is also possible to encode the data of the offset curve and transformation matrix, and then generate a key through a hash function or other encryption algorithms.

[0099] Generating a management key using the offset curve and transformation matrix makes the key closely related to the current state and measurement data of the device, increasing the uniqueness and complexity of the key and improving the security of encryption. This method avoids traditional static key generation methods, making the key more dynamic and targeted, and improving the security and anti-attack ability of the system.

[0100] Using the generated management key, encrypt the parameter set through an encryption algorithm (such as a symmetric encryption algorithm or an asymmetric encryption algorithm). The symmetric encryption algorithm can ensure the efficiency of encryption, while the asymmetric encryption algorithm can provide higher security. The encrypted parameter set is stored in the management database, ensuring the confidentiality and integrity of the data during storage.

[0101] In one embodiment, generating a management key based on the offset curve and transformation matrix includes:

[0102] Mining the curve characteristics of the offset curve to obtain a curve identifier;

[0103] Remodeling the spatial structure of the transformation matrix to obtain a matrix spatial structure encoding;

[0104] Performing a random interleaving process on the curve identifier and the matrix spatial structure encoding to obtain interleaved information;

[0105] Based on a custom encryption mapping table, map each element in the interleaved information to a new element, and combine them to form a management key; wherein, the encryption mapping table is updated according to different electromechanical devices and time.

[0106] In this embodiment, the offset curve reflects the changes in measurement parameters dynamically adjusted based on the device operating state and environmental conditions. Curve characteristic mining aims to extract representative and unique features from this offset curve for subsequent generation of a management key. These characteristics can include the shape, trend, periodicity, extreme points (maximum and minimum values), slope changes, concavity and convexity of the curve, etc.

[0107] For example, for an offset curve representing the temperature change of a device over time, by analyzing the characteristics of the curve, we can determine the temperature fluctuation range (the difference between the maximum and minimum values), the frequency of temperature change (by finding periodicity), the rate of temperature change (by calculating the slope), and whether there is a mutation point in the curve, etc. These characteristics help describe the curve from different angles and provide key information for the subsequent encryption process.

[0108] After the curve characteristics are extracted and quantified, these characteristic information are combined and encoded in some way to form a curve identifier. The curve identifier is an abstract representation of the offset curve. It is a string of numbers, letters or special symbols that represents the unique properties of the offset curve. For example, the maximum value, minimum value, cycle length, slope variation range and other information of the curve can be encoded according to certain rules to form a unique curve identifier. The importance of the curve identifier lies in its ability to concisely and accurately summarize the key information of the offset curve, providing some basic information for generating management keys. Different offset curves will have different curve identifiers, which makes the management key more targeted and unique, and also provides a basis for distinguishing different devices or different device operating states for subsequent encryption steps.

[0109] The above transformation matrix contains the information of device parameters in different dimensions, and reshaping its spatial structure is an innovative way of data processing. It involves rearranging the elements of the matrix, decomposing and reorganizing the matrix, or transforming the matrix according to the relationship between the elements of the matrix. For example, the matrix can be transposed, rows and columns can be exchanged, and the position relationship of the elements can be changed; or the matrix can be divided into blocks, the matrix can be divided into multiple sub-matrices, and they can be recombined according to the characteristics of the sub-matrices; matrix transformation methods such as singular value decomposition can also be used to extract the eigenvalues ​​and eigenvectors of the matrix, and these eigenvalues ​​and eigenvectors can be rearranged or combined.

[0110] The purpose of spatial structure reshaping is to display the structural information of the matrix from different perspectives, to dig out information that may have been overlooked in the matrix, and at the same time to change the spatial structure of the matrix, providing more possibilities for generating more complex and secure keys.

[0111] After reshaping the spatial structure of the transformation matrix, the reshaped matrix structure information is encoded. The encoding process can be carried out according to information such as the positions of the elements in the reshaped matrix, the size relationships of the elements, and the characteristics of the sub-matrices. For example, information such as the element distribution pattern of the reshaped matrix (such as the size relationships of the elements on the matrix diagonal and the element distribution in different regions of the matrix), the sum of the elements of the sub-matrices, and the arrangement order of the eigenvalues can be converted into a code. This code can be a binary code, a hexadecimal code, or other custom encoding methods to form the matrix spatial structure code. The matrix spatial structure code represents the spatial structure information of the transformation matrix in a new form. It is similar to the curve identifier, providing another dimension of information source for generating the management key, increasing the information entropy of the management key, and making the management key more difficult to crack.

[0112] Furthermore, the random interleaving process randomly shuffles and combines the elements in the curve identifier and the matrix spatial structure code, breaking their original order and structure. This can be achieved through a random number generator or a pseudo-random algorithm, which rearranges the elements of the curve identifier and the elements of the matrix spatial structure code under certain rules. The advantage of the above random interleaving process is to increase the complexity and disorder of the information, avoiding the regularity brought about by directly using the simple combination of the curve identifier and the matrix spatial structure code, making it difficult for potential attackers to crack the management key by analyzing simple combination patterns. Through random interleaving, the generated interleaved information is made more random and unpredictable, improving the security of encryption.

[0113] The above custom encryption mapping table is a key element, which establishes the correspondence between the original elements and the mapped elements. This mapping table can be a simple lookup table, for example, mapping the original numbers, letters, or symbols to other numbers, letters, or symbols. The creation of the mapping table can be based on a specific algorithm or random number generation, and it will be updated according to the characteristics of the electromechanical device (such as device number, device type) and time information (such as measurement time, system running time). The above update mechanism ensures the dynamic nature of the mapping table, enabling different electromechanical devices to use different mapping tables at different times. Even for the same interleaved information, different management keys will be generated under different device and time conditions, greatly increasing the complexity and security of encryption. For example, for different devices, the last few digits of their device numbers can be used as the basis for updating the mapping table; for different times, some mapping relationships of the mapping table are updated in units of days, hours, or minutes, so that the encryption mapping table has time sensitivity and device correlation.

[0114] Map each element in the interleaved information through an encryption mapping table, that is, replace each element with the corresponding new element in the mapping table. For example, if the interleaved information is "ABCDEF", according to the encryption mapping table, "A" is mapped to "X", "B" is mapped to "Y", etc. Finally, the mapped elements are combined in sequence to form a management key. The finally generated management key is the result of multiple information processing and transformations. It combines the characteristics of the offset curve, the spatial structure information of the transformation matrix, and through random interleaving and mapping of the dynamic mapping table, forms a key that not only contains the device operating state information but also has high security. This management key can be used for encrypted storage of the parameter set to ensure the security of the data stored in the management database.

[0115] In one embodiment, generating a management key based on the offset curve and the transformation matrix includes:

[0116] Construct an undirected graph for the offset curve to obtain an offset curve undirected graph; wherein, each data point of the offset curve is set as an undirected graph node, and edges are connected between adjacent nodes;

[0117] Convert the transformation matrix into a directed graph to obtain a transformation matrix directed graph; wherein, the matrix elements are used as directed graph nodes, the large elements point to the small elements to form edges, and the edge weights are determined by the absolute value of the element difference;

[0118] Merge the offset curve undirected graph and the transformation matrix directed graph to obtain a merged graph;

[0119] Mine the graph features of the merged graph to obtain a graph feature set; perform feature set transformation on the graph feature set to obtain an intermediate code.

[0120] Adjust the encoding of the intermediate code to obtain the management key.

[0121] In this embodiment, the offset curve contains a series of data points, and these data points represent the measurement parameter information of the device at different times or in different states. Setting each data point as a node in the undirected graph is an innovative representation method for the offset curve data. Connecting edges between adjacent nodes can reflect the continuity and relevance of the data points in terms of time or state. The above representation method helps to transform the original linear data sequence into a graph structure, so as to use the theories and algorithms of graph theory to mine the hidden relationships in the data. For example, during the measurement of device parameters, the relationship between adjacent data points may imply the continuous change trend of device performance or potential fault signals. By constructing an undirected graph, these relationships can be better observed from the perspective of the topological structure, rather than being limited to the numerical size of the data.

[0122] The advantage of the undirected graph of the offset curve is that it can show the connectivity and mutual influence between data points from a new perspective. Through the graph structure, information such as the aggregation areas of data points (which may correspond to the stable states of the device), isolated nodes (which may represent abnormal data points), and the connectivity of the graph (reflecting the coherence of parameter changes) can be more intuitively discovered.

[0123] For the transformation matrix, the matrix elements are taken as the nodes of a directed graph. According to the size relationship of the elements, the large elements point to the small elements to form edges, and the edge weights are determined by the absolute value of the element difference. This operation presents the element relationship in the matrix in the form of a directed graph, highlighting the size and change trend relationship between the elements. The above transformation converts the numerical comparison of matrix elements into connections and weights in the directed graph, providing a new way for further analyzing the structure of the matrix and the internal relationship between elements. For example, by observing the strongly connected edges (with larger edge weights) and weakly connected edges in the directed graph, the main change directions and amplitudes of the elements in the matrix can be found, which helps to reveal the differences and change patterns of device parameters in different dimensions.

[0124] The directed graph of the transformation matrix can reflect the hierarchical relationship and change trend between matrix elements, providing rich information for subsequent merging and analysis. For example, by analyzing the in-degree and out-degree distributions in the directed graph, it can be understood which elements have a strong influence on other elements and which elements are relatively independent. This is very helpful for understanding the influencing factors and mutual relationships of the device in different parameter dimensions, providing a deeper basis for subsequent management decisions and analysis.

[0125] The undirected graph of the offset curve and the directed graph of the transformation matrix respectively reflect the information of the device from different perspectives (time series and matrix structure). Merging them can integrate data in different dimensions and provide a unified structure for a more comprehensive analysis of the device state. The merging operation can be to merge the nodes and edges of the two graphs into a new graph. To distinguish the sources, different labels or attributes can be added to the nodes and edges to identify whether they come from the offset curve or the transformation matrix. For example, for the nodes from the undirected graph of the offset curve, they can be marked as "curve nodes", and the nodes from the directed graph of the transformation matrix are marked as "matrix nodes". At the same time, for the merged graph, the connection relationships of the nodes and edges need to be reasonably processed to ensure the integrity and consistency of the information and avoid information loss or conflict.

[0126] Furthermore, graph feature mining aims to extract representative and valuable information from the merged graph. These features can include the degree of nodes (in-degree, out-degree), node connectivity, graph diameter (longest shortest path), number and size of subgraphs, graph clustering coefficient (aggregation degree of nodes), etc. Through the mining of these features, the structure and information distribution of the merged graph can be analyzed from both macroscopic and microscopic levels.

[0127] For example, the diameter of a graph can reflect the maximum span of changes in the device state, and the clustering coefficient can show the degree of aggregation of the device in different states, that is, whether the state of the device is relatively concentrated and stable or scattered and variable. These features help to grasp the operating characteristics of the device and potential problem areas as a whole.

[0128] Converting the graph feature set into an intermediate encoding is to represent the structure and feature information of the graph in a form that can be stored, processed, and encrypted. This can be achieved by encoding each feature in the graph feature set according to rules. For example, converting the number of node degrees into binary or hexadecimal encoding, converting the diameter of the graph into a specific character sequence, converting the clustering coefficient into a certain symbol representation, etc.

[0129] The process of feature set conversion transforms the complex structure and feature information of the graph into concise encoding, facilitating subsequent operations such as storage, transmission, and further encryption processing. At the same time, this encoding can retain different precisions and lengths as needed to balance the integrity of information and the simplicity of processing.

[0130] Finally, the encoding adjustment can be carried out based on various factors. For example, the intermediate encoding can be adjusted according to the unique identifier of the device, the running time of the device, the current state of the device, etc. The methods that can be adopted include operations such as adding, deleting, replacing, or rearranging the intermediate encoding. For example, adding the serial number of the device to the intermediate encoding, or performing a certain shift operation on the intermediate encoding according to the running time of the device. The above adjustments are to make the final management key more unique and time-sensitive to the device, while increasing its randomness and complexity, and improving the security of the management key.

[0131] The management key is the final generated key information used to encrypt and manage device data. It synthesizes various aspects of information of the device (through the processing of graph structure and features), and has undergone multiple encodings and adjustments, with high security and uniqueness. In the full life cycle management system of electromechanical devices, the management key can be used to encrypt and store various parameter sets of the device, ensuring the confidentiality and integrity of the data, preventing unauthorized access and tampering, and safeguarding the data security of the system.

[0132] In one embodiment, generating a management key based on the offset curve and the transformation matrix includes:

[0133] Perform data point mapping on the offset curve to obtain a mapping matrix; map the coordinates of each data point on the offset curve to the corresponding positions in a two-dimensional matrix, such that the value of the matrix element is the value of the data point, and the value corresponds to the row and column indices of the matrix. For the matrix positions not covered by the curve, the element values are set to zero. In this way, a data matrix that can completely represent the offset curve is obtained, and at the same time, the position information of the data points is retained.

[0134] Perform matrix splicing on the mapping matrix and the transformation matrix to obtain a spliced matrix; splice the mapping matrix and the transformation matrix together according to rules. For example, place the mapping matrix above or to the left of the transformation matrix to form a larger spliced matrix. This spliced matrix contains both the information of the offset curve and the information of the transformation matrix, unifying the two in structure.

[0135] Perform matrix block processing on the spliced matrix to obtain a set of block information; divide the spliced matrix into multiple sub-matrix blocks, and perform the block division according to the size range or element distribution characteristics of the matrix elements. For example, divide the area where the element values are close into one block. Statistically calculate information such as the average value of the elements, the number of elements, the maximum value, and the minimum value of each sub-matrix block, and store this information in the set of block information. At the same time, record the position information of each sub-matrix block in the spliced matrix, such as the starting row, starting column, number of rows, and number of columns of the block.

[0136] Perform information encoding on the set of block information to obtain encoded information; for each sub-matrix block information in the set of block information, convert its average value of the elements, the number of elements, the maximum value, the minimum value, and the position information into strings according to a predetermined encoding rule. For example, convert the absolute value of the average value of the elements into a hexadecimal string, and convert the number of elements into a binary string, and then splice these strings in a certain order to form the encoded information.

[0137] Perform key generation on the encoded information to obtain a management key. Use the unique identifier of the device (such as the device number) as a seed, perform a hash operation on the encoded information using a hash function (such as SHA-3), and intercept the appropriate length of the hash result as the management key. At the same time, combine the current operating status information of the device (such as operating speed, load, etc.) to perform further confusion operations on the hash result, such as circular shift or bitwise exclusive OR operation, to increase the complexity and randomness of the key.

[0138] Refer to Figure 2 , in an embodiment of the present invention, a method for the full life cycle management of electromechanical equipment is further provided, including:

[0139] Step S1, which is used to obtain the current stage of the electromechanical equipment in the full life cycle; based on the current stage, determine the device variable parameters and device measurement parameters that need to be monitored currently;

[0140] Step S2 is used to obtain the operating status and environmental parameters of the electromechanical device, determine the measurement parameter offset value based on the operating status and environmental parameters; offset the device measurement parameters based on the measurement parameter offset value to obtain the offset measurement parameters;

[0141] Step S3 is used to determine the corresponding parameter measurement device based on the device variable parameters; control the parameter measurement device to measure the device variable parameters of the electromechanical device with the offset measurement parameters to obtain a parameter set;

[0142] Step S4 is used to analyze the parameter set and control the operation of the electromechanical device based on the analysis result.

[0143] In this embodiment, for the specific implementation of each step in the above method embodiment, please refer to that described in the above system embodiment, and details are not described herein again.

[0144] Refer to Figure 3 , in the embodiment of the present invention, a computer device is further provided. This computer device can be a server, and its internal structure can be as Figure 3 shown. The computer device includes a processor, a memory, a display screen, an input device, a network interface, and a database connected through a system bus. Among them, the processor of the computer design is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the corresponding data in this embodiment. The network interface of the computer device is used to communicate with an external terminal through a network connection. The computer program, when executed by the processor, implements the above method.

[0145] Those skilled in the art can understand that Figure 3 the structure shown in

[0146] is only a block diagram of a part of the structure related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied.

[0147] In summary, the present invention provides a full life cycle management system for electromechanical equipment in an embodiment, including: an acquisition module, configured to acquire the current stage of the electromechanical equipment in the full life cycle; determine the device variable parameters and device measurement parameters that need to be monitored currently based on the current stage; an offset module, configured to acquire the operating state and environmental parameters of the electromechanical equipment, and determine a measurement parameter offset value based on the operating state and environmental parameters; offset the device measurement parameters based on the measurement parameter offset value to obtain offset measurement parameters; a measurement module, configured to determine a corresponding parameter measurement device based on the device variable parameters; control the parameter measurement device to measure the device variable parameters of the electromechanical equipment with the offset measurement parameters to obtain a parameter set; a control module, configured to analyze the parameter set and control the operation of the electromechanical equipment based on the analysis result. In the present invention, by combining the stage of the full life cycle of the current electromechanical equipment, the current operating state and environmental parameters, the device measurement parameters are dynamically adjusted, overcoming the defects of inaccurate data measurement and resource waste in the current full life cycle management process.

[0148] Those of ordinary skill in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above method embodiments. Among them, any reference to a memory, storage, database, or other medium provided in the present invention and the embodiments can include non-volatile and / or volatile memories. Non-volatile memories can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memories can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM, etc.

[0149] It should be noted that in this text, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, apparatus, article or method comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, apparatus, article or method. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, apparatus, article or method comprising such element.

[0150] The above are only the preferred embodiments of the present invention, and do not limit the patent scope of the present invention accordingly. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present invention.

Claims

1. An electromechanical equipment full life cycle management system, characterized in that, Including: An acquisition module, configured to acquire the current stage of the electromechanical device in the entire life cycle; Based on the current stage, determine the device variable parameters and device measurement parameters that need to be monitored currently; An offset module, configured to acquire the operating state and environmental parameters of the electromechanical device, and determine a measurement parameter offset value based on the operating state and environmental parameters; Offset the device measurement parameters based on the measurement parameter offset value to obtain offset measurement parameters; A measurement module, configured to determine a corresponding parameter measurement device based on the device variable parameters; control the parameter measurement device to measure the device variable parameters of the electromechanical device with the offset measurement parameters to obtain a parameter set; A control module, configured to analyze the parameter set and control the operation of the electromechanical device based on the analysis result; A generation module, configured to generate an offset curve based on the offset measurement parameters; Add each parameter in the parameter set to a matrix in sequence to generate a parameter matrix; Transform the parameter matrix based on the analysis result to obtain a transformed matrix; An encryption module, configured to generate a management key based on the offset curve and the transformed matrix; Encrypt the parameter set based on the management key and then store it in a management database.

2. The full life cycle management system for electromechanical equipment according to claim 1, characterized in that The device measurement parameters include a measurement mode and a measurement period.

3. The full-life-cycle management system for electromechanical equipment according to claim 1, characterized in that Determining the measurement parameter offset value based on the operating state and environmental parameters includes: Extract features from the operating state to obtain operating state features; Extract features from the environmental parameters to obtain environmental features; Perform feature fusion processing on the operating state features and environmental features to obtain fusion features; Input the fusion features into a pre-trained machine learning model and output a corresponding measurement parameter offset value; the measurement parameter offset value includes an adjustment amount of the measurement mode and an adjustment amount of the measurement period.

4. The electromechanical equipment full life cycle management system according to claim 1, characterized in that Analyzing the parameter set and controlling the operation of the electromechanical device based on the analysis result includes: Mining the mutual influence relationship between different types of device variable parameters in the parameter set based on data mining technology to form associated state information; Evaluating the current risk assessment level of the electromechanical device according to the associated state information and combining the historical data of the electromechanical device through a combination of a rule-based inference system and a machine learning algorithm; Generate a dynamic control strategy for the risk assessment level to obtain a control instruction set; Transmit the control instruction set to the corresponding execution components of the electromechanical device through a distributed control system to control the operation of the electromechanical device.

5. The full life cycle management system for electromechanical equipment according to claim 1, characterized in that The device variable parameters include shape parameters, mechanical parameters, electrical parameters, and thermal parameters.

6. The full life cycle management system for electromechanical equipment according to claim 1, characterized in that Generating a management key based on the offset curve and the transformed matrix includes: Mining the curve characteristics of the offset curve to obtain a curve identifier; Reshape the spatial structure of the transformed matrix to obtain a matrix spatial structure code; Perform random interleaving processing on the curve identifier and the matrix spatial structure code to obtain interleaved information; Based on a custom encryption mapping table, each element in the interleaved information is mapped to a new element, and the management key is formed by combination; wherein, the encryption mapping table is updated according to different electromechanical devices and time.

7. The full life cycle management system for electromechanical equipment according to claim 1, characterized in that Generating a management key based on the offset curve and the transformation matrix includes: Constructing an undirected graph for the offset curve to obtain an offset curve undirected graph; wherein, each data point of the offset curve is set as an undirected graph node, and edges are connected between adjacent nodes; Converting the transformation matrix into a directed graph to obtain a transformation matrix directed graph; wherein, the matrix elements are used as directed graph nodes, and edges are formed by large elements pointing to small elements, and the edge weights are determined by the absolute value of the element difference; Merging the offset curve undirected graph and the transformation matrix directed graph to obtain a merged graph; Mining graph features of the merged graph to obtain a graph feature set; performing feature set transformation on the graph feature set to obtain an intermediate code; Adjusting the encoding of the intermediate code to obtain the management key.

Images