Data security tracing method and system based on artificial intelligence

Abstract

The invention is suitable for the technical field of power system optimization, and provides a data security tracing method and system based on artificial intelligence, and the method comprises the steps: determining the current operation state of target equipment when the three-phase voltage of the target equipment is unbalanced, acquiring a torque fluctuation historical log, historical vibration data of a specified area and an initial electrical stability parameter applied to a corresponding voltage regulator of the target equipment; according to the invention, the problem of insufficient data tracking and tracing accuracy of power equipment under the condition of three-phase voltage imbalance can be effectively solved. According to the method, the torque fluctuation and vibration characteristic data are combined, the first optimization parameter and the second optimization parameter are extracted respectively, the dynamic response characteristics of the mechanical system and the electrical system are quantified, and the comprehensiveness and accuracy of the data in the traceability process are ensured.

Description

Technical Field

[0001] The present invention belongs to the technical field of power system optimization, and particularly relates to a data security traceability method and system based on artificial intelligence. Background Art

[0002] In the operation of modern power equipment, the balance of three-phase voltages has an important impact on the performance and safety of the equipment. However, the problem of three-phase voltage imbalance frequently occurs in the operation of power equipment, and the resulting electrical and mechanical abnormalities often have a significant impact on the overall stability of the system and the accuracy of data traceability. In the prior art, data security traceability mainly relies on data collection and analysis of electrical systems. For example, by real-time monitoring of electrical parameters such as voltage fluctuations and negative sequence voltage content, the source of abnormalities is determined and its impact on the equipment is evaluated. However, this method ignores the complex coupling effect between the mechanical system and the electrical system and is difficult to comprehensively reflect the true state of equipment operation.

[0003] In practical applications, abnormalities in the mechanical system (such as rotor imbalance and bearing wear) often lead to changes in equipment vibration and torque fluctuations, and these abnormalities will have a significant interference on electrical parameters, further exacerbating the errors in the data traceability process. However, most of the data security traceability methods in the prior art rely on single electrical data for analysis, failing to effectively capture the interaction between the mechanical and electrical systems, resulting in limitations in the accuracy and comprehensiveness of the traceability results. In addition, the ability to fuse and analyze multi-dimensional data under complex working conditions is weak, and the prior art cannot meet the actual needs of high-precision traceability. Summary of the Invention

[0004] The purpose of the present invention is to provide a data security traceability method and system based on artificial intelligence, aiming to solve the problems proposed in the background art.

[0005] The present invention is implemented as follows. A data security traceability method based on artificial intelligence, the method includes:

[0006] When a three-phase voltage imbalance occurs in the target device, determine the current operating state of the target device, obtain its torque fluctuation historical log, historical vibration data of a specified area, and initial electrical stability parameters applied to the corresponding voltage regulator of the target device;

[0007] Parse the torque fluctuation historical log, extract the current torque fluctuation value of the target device and the set of historical torque fluctuation values under specified working conditions, analyze whether the current torque fluctuation value exceeds a preset threshold of the average value of the set of historical torque fluctuation values. If so, generate a trend feature of the torque fluctuation value according to the time series, determine whether the trend feature meets the preset conditions. If it meets, calculate the characteristic quantity of the trend change and use it as the first optimization parameter;

[0008] Analyze the historical vibration data, extract the set of vibration characteristic data under the specified working conditions, and analyze whether the trend of its change is consistent with the trend characteristics of the torque fluctuation value. If they are consistent, obtain the deviation value between the current vibration characteristic value and the preset standard value, and use it as the second optimization parameter;

[0009] Combine the first optimization parameter and the second optimization parameter to correct the initial electrical stability parameter and generate the optimized electrical stability parameter.

[0010] As a further limitation of the technical solution of the embodiment of the present invention, the specified working condition refers to the working condition that is consistent with the current operating state of the target device but not in the three-phase voltage unbalance condition.

[0011] As a further limitation of the technical solution of the embodiment of the present invention, the steps of parsing the historical torque fluctuation log, extracting the current torque fluctuation value of the target device and the set of historical torque fluctuation values under the specified working conditions, analyzing whether the current torque fluctuation value exceeds the preset threshold of the average value of the set of historical torque fluctuation values, if so, generating the trend characteristic of the torque fluctuation value according to the time series, and judging whether the trend characteristic meets the preset conditions, and if it meets, calculating the characteristic quantity of the trend change and using it as the first optimization parameter include:

[0012] Parse the historical torque fluctuation log, extract the current torque fluctuation value of the target device, and the historical torque fluctuation values of the first preset number of specified working conditions, and form a set of historical torque fluctuation values with these historical torque fluctuation values;

[0013] Calculate the average value of the set of historical torque fluctuation values, and judge whether the current torque fluctuation value exceeds the preset threshold of the average value. If so, generate the change trend of the historical torque fluctuation value based on the time series, that is, the trend characteristic of the torque fluctuation value;

[0014] Analyze the change trend of the historical torque fluctuation value, judge whether it shows a continuous increase. If so, calculate its average slope and use the slope as the first optimization parameter.

[0015] As a further limitation of the technical solution of the embodiment of the present invention, the steps of analyzing the historical vibration data, extracting the set of vibration characteristic data under the specified working conditions, analyzing whether the trend of its change is consistent with the trend characteristic of the torque fluctuation value, and if they are consistent, obtaining the deviation value between the current vibration characteristic value and the preset standard value and using it as the second optimization parameter include:

[0016] Parse the historical vibration data, extract the vibration characteristic data of the second preset number of specified working conditions, and form a set of vibration characteristic data;

[0017] Analyze the change trend of the vibration characteristic data set, and determine whether it is consistent with the trend characteristics of the torque fluctuation value. If it is consistent, extract the current vibration characteristic value of the target device, and compare it with the preset standard value corresponding to the specified area under the current operating state of the target device;

[0018] Calculate the deviation value between the current vibration characteristic value and the preset standard value, and quantify this deviation value as the second optimization parameter.

[0019] As a further limitation of the technical solution of the embodiment of the present invention, the step of combining the first optimization parameter and the second optimization parameter to correct the initial electrical stability parameter to generate the optimized electrical stability parameter includes:

[0020] Retrieve the electrical stability parameter adjustment formula, and correct the initial electrical stability parameter based on the first optimization parameter and the second optimization parameter to generate the optimized electrical stability parameter;

[0021] Apply the optimized electrical stability parameter to the voltage regulator corresponding to the target device.

[0022] As a further limitation of the technical solution of the embodiment of the present invention, the electrical stability parameter adjustment formula is: , where S optimized refers to the optimized electrical stability parameter, S initial refers to the initial electrical stability parameter, P1 refers to the first optimization parameter, k1 refers to the adjustment coefficient of the first optimization parameter, P2 refers to the second optimization parameter, and k2 refers to the adjustment coefficient of the second optimization parameter;

[0023] In the electrical stability parameter adjustment formula:

[0024] , where N refers to the total number of historical torque fluctuation values in the historical torque fluctuation value set, T history,i refers to the i-th historical torque fluctuation value in the historical torque fluctuation value set;

[0025] , where V current refers to the current vibration characteristic value, V baseline refers to the preset standard value.

[0026] An artificial intelligence-based data security traceability system, the system includes: a data acquisition module, a first optimization parameter determination module, a second optimization parameter determination module, and a stability parameter correction module, where:

[0027] A data acquisition module, configured to determine the current operating state of a target device when a three-phase voltage imbalance occurs in the target device, obtain its historical torque fluctuation log, historical vibration data in a specified area, and initial electrical stability parameters applied to the corresponding voltage regulator of the target device;

[0028] A first optimization parameter determination module, configured to parse the historical torque fluctuation log, extract the current torque fluctuation value of the target device and the set of historical torque fluctuation values under specified operating conditions, analyze whether the current torque fluctuation value exceeds a preset threshold of the average value of the set of historical torque fluctuation values, and if so, generate a trend feature of the torque fluctuation value according to the time series, and determine whether the trend feature meets the preset conditions. If it meets, calculate the characteristic quantity of the trend change and use it as the first optimization parameter;

[0029] The specified operating conditions refer to the operating conditions that are the same as the current operating state of the target device but without a three-phase voltage imbalance;

[0030] A second optimization parameter determination module, configured to analyze the historical vibration data, extract the set of vibration characteristic data under specified operating conditions, analyze whether its change trend is consistent with the trend feature of the torque fluctuation value, and if so, obtain the deviation value between the current vibration characteristic value and the preset standard value and use it as the second optimization parameter;

[0031] A stability parameter correction module, configured to correct the initial electrical stability parameters by combining the first optimization parameter and the second optimization parameter to generate optimized electrical stability parameters.

[0032] As a further limitation of the technical solution of the embodiment of the present invention, the first optimization parameter determination module specifically includes:

[0033] A historical log parsing unit, configured to parse the historical torque fluctuation log, extract the current torque fluctuation value of the target device and the historical torque fluctuation values under a first preset number of specified operating conditions, and form a set of historical torque fluctuation values with these historical torque fluctuation values;

[0034] A trend feature generation unit, configured to calculate the average value of the set of historical torque fluctuation values and determine whether the current torque fluctuation value exceeds the preset threshold of the average value. If so, generate the change trend of the historical torque fluctuation value based on the time series, that is, the trend feature of the torque fluctuation value;

[0035] A first optimization parameter calculation unit, configured to analyze the change trend of the historical torque fluctuation value, determine whether it shows a continuous increase, and if so, calculate its average slope and use the slope as the first optimization parameter.

[0036] As a further limitation of the technical solution of the embodiment of the present invention, the second optimization parameter determination module specifically includes:

[0037] A vibration data analysis unit, configured to analyze historical vibration data, extract vibration characteristic data of a specified working condition with a second preset quantity, and form a vibration characteristic data set;

[0038] A numerical comparison unit, configured to analyze the change trend of the vibration characteristic data set, determine whether it is consistent with the trend characteristic of the torque fluctuation value, and if so, extract the current vibration characteristic value of the target device and compare it with a preset standard value corresponding to a specified area in the current operating state of the target device;

[0039] A second optimization parameter calculation unit, configured to calculate the deviation value between the current vibration characteristic value and the preset standard value, and quantify the deviation value as a second optimization parameter.

[0040] As a further limitation of the technical solution of the embodiment of the present invention, the stable parameter correction module specifically includes:

[0041] A stable parameter optimization unit, configured to retrieve an electrical stable parameter adjustment formula, and correct the initial electrical stable parameter based on the first optimization parameter and the second optimization parameter to generate an optimized electrical stable parameter;

[0042] An optimized stable parameter application unit, configured to apply the optimized electrical stable parameter to the voltage regulator corresponding to the target device;

[0043] The electrical stable parameter adjustment formula is: , where S optimized refers to the optimized electrical stable parameter, S initial refers to the initial electrical stable parameter, P1 refers to the first optimization parameter, k1 refers to the adjustment coefficient of the first optimization parameter, P2 refers to the second optimization parameter, and k2 refers to the adjustment coefficient of the second optimization parameter;

[0044] In the electrical stable parameter adjustment formula:

[0045] , where N refers to the total number of historical torque fluctuation values in the historical torque fluctuation value set, T history,i refers to the i-th historical torque fluctuation value in the historical torque fluctuation value set;

[0046] , where V current refers to the current vibration characteristic value, V baseline refers to the preset standard value.

[0047] Compared with the prior art, the present invention has the following beneficial effects:

[0048] The present invention can effectively solve the problem of insufficient accuracy in data tracking and traceability of power equipment under the condition of unbalanced three-phase voltage. The present invention combines torque fluctuation and vibration characteristic data, extracts the first optimization parameter and the second optimization parameter respectively, quantifies the dynamic response characteristics of the mechanical system and the electrical system, and ensures the comprehensiveness and accuracy of data during the traceability process. Compared with the prior art's traceability method that solely relies on electrical data, the present invention incorporates mechanical operation characteristics into the data traceability framework, realizes the joint analysis of mechanical and electrical data, and provides richer multi-dimensional support.

[0049] Generate trend characteristics through time series analysis, combine with the calculation of vibration data deviation, and dynamically optimize the initial electrical stability parameters to make them more accurately reflect the actual operating conditions of the target equipment. The optimized electrical stability parameters can not only trace the source of abnormal data, but also intelligently analyze the correlation between mechanical wear and electrical imbalance, improving the accuracy and intelligence level of traceability.

[0050] Through data tracking, trend analysis and parameter optimization, the present invention improves the limitation of the prior art's traceability technology that relies solely on single electrical data, significantly improves the reliability and accuracy of traceability, and is widely applicable to the monitoring and fault analysis of power equipment such as industrial motors and fans. Brief Description of the Drawings

[0051] Figure 1 It is a flowchart of the method provided by the embodiment of the present invention;

[0052] Figure 2 It is a flowchart of determining the first optimization parameter for adjusting the initial electrical stability parameters in the method provided by the embodiment of the present invention;

[0053] Figure 3 It is a flowchart of determining the second optimization parameter for adjusting the initial electrical stability parameters in the method provided by the embodiment of the present invention;

[0054] Figure 4 It is a flowchart of correcting the initial electrical stability parameters based on the first optimization parameter and the second optimization parameter in the method provided by the embodiment of the present invention;

[0055] Figure 5 It is an application architecture diagram of the system provided by the embodiment of the present invention;

[0056] Figure 6 It is a structural block diagram of the first optimization parameter determination module in the system provided by the embodiment of the present invention;

[0057] Figure 7 It is a structural block diagram of the second optimization parameter determination module in the system provided by the embodiment of the present invention;

[0058] Figure 8It is the structural block diagram of the stable parameter correction module in the system provided by the embodiment of the present invention. Detailed implementation manners

[0059] In order to make the objectives, technical solutions and advantages of the present invention more clear and understandable, 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.

[0060] Figure 1 It shows the flowchart of the method provided by the embodiment of the present invention.

[0061] Specifically, a data security traceability method based on artificial intelligence, the method specifically includes the following steps:

[0062] Step S100, when a three-phase voltage imbalance occurs in the target device, determine the current operating state of the target device, obtain its torque fluctuation historical log, historical vibration data of a specified area, and the initial electrical stability parameters applied to the corresponding voltage regulator of the target device.

[0063] In the embodiment of the present invention, the target device can be devices such as industrial motors, fans, water pumps, compressors, etc. These devices have high requirements for the balance of three-phase voltage during operation, and the three-phase voltage imbalance will directly affect their operating performance and lifespan. For example, an industrial motor will experience phenomena such as increased rotor vibration and increased torque fluctuation due to three-phase voltage imbalance, further causing problems such as decreased equipment efficiency or overheating.

[0064] The current operating state can be the real-time operating condition state of the target device, including parameters such as operating power, rotational speed, and load change. It is preferably the stable operating state of the device under a specific load, such as a constant power output or a constant rotational speed state. In this state, it is easier to identify the direct impact of three-phase voltage imbalance on the device operation.

[0065] The specified area should be the area in the target device that can best reflect the abnormal vibration of the rotor. For example, the bearing part or the winding end area of the motor rotor. These areas are usually sensitive points of the coupling effect of mechanical vibration and electrical imbalance, and can effectively capture the abnormal characteristics of the device operating state. The torque fluctuation historical log and the historical vibration data of the specified area can be obtained through sensors deployed inside or around the device. The torque fluctuation data can be collected by a torque sensor installed on the rotating shaft and its time series is recorded; the historical vibration data is collected by an acceleration sensor or a vibration sensor, and the vibration amplitude, frequency, etc. information of the specified area is recorded according to its dynamic characteristics.

[0066] The voltage regulator corresponding to the target device is used to regulate the three-phase voltage received by the device, ensuring the balance and stability of the voltage to reduce the impact of voltage fluctuations on the operating state of the device. The voltage regulator dynamically adjusts the output voltage according to the operating requirements of the target device, such as compensating for negative sequence components or adjusting the voltage phase difference, thereby improving the operating efficiency and stability of the device.

[0067] The initial electrical stability parameters can be basic parameters describing the electrical operating state of the device, such as negative sequence voltage content, three-phase current balance degree, system harmonic distortion rate, etc. Preferably, it is an index that can quantify the degree of voltage imbalance, such as the ratio of negative sequence voltage content or the three-phase current imbalance coefficient. These parameters directly reflect the potential impact of three-phase voltage imbalance on the device operation. At the same time, by expanding and optimizing the dynamic range of the parameters, a wider adjustment space can be provided for subsequent optimization calculations.

[0068] In the prior art, the application of voltage regulators has been widely used for the regulation of three-phase voltage imbalance, but most are based on fixed control strategies and lack dynamic adjustment capabilities. In particular, they fail to fully combine the torque fluctuations and vibration data of the target device for optimization. The prior art mainly focuses on the one-way compensation of electrical parameters and does not conduct in-depth research on the specific impacts of mechanical and electrical coupling.

[0069] Furthermore, the artificial intelligence-based data security traceability method further includes the following steps:

[0070] Step S200: Parse the torque fluctuation historical log, extract the current torque fluctuation value of the target device and the set of historical torque fluctuation values under specified working conditions, analyze whether the current torque fluctuation value exceeds the preset threshold of the average value of the set of historical torque fluctuation values. If so, generate the trend characteristics of the torque fluctuation value according to the time series, judge whether the trend characteristics meet the preset conditions. If they meet, calculate the characteristic quantity of the trend change and use it as the first optimization parameter.

[0071] The specified working conditions refer to the working conditions that are the same as the current operating state of the target device but without three-phase voltage imbalance.

[0072] Specifically, Figure 2 The flowchart shows the determination of the first optimization parameter for adjusting the initial electrical stability parameters.

[0073] Among them, parsing the torque fluctuation historical log, extracting the current torque fluctuation value of the target device and the set of historical torque fluctuation values under specified working conditions, analyzing whether the current torque fluctuation value exceeds the preset threshold of the average value of the set of historical torque fluctuation values. If so, generating the trend characteristics of the torque fluctuation value according to the time series, judging whether the trend characteristics meet the preset conditions. If they meet, calculating the characteristic quantity of the trend change and using it as the first optimization parameter specifically includes the following steps:

[0074] Step S201: Analyze the torque fluctuation historical log, extract the current torque fluctuation value of the target device and the historical torque fluctuation values under the first preset number of specified working conditions, and form a set of historical torque fluctuation values with these historical torque fluctuation values.

[0075] Step S202: Calculate the average value of the set of historical torque fluctuation values, and determine whether the current torque fluctuation value exceeds the preset threshold of this average value. If so, generate the change trend of the historical torque fluctuation value based on the time series, that is, the trend characteristic of the torque fluctuation value.

[0076] Step S203: Analyze the change trend of the historical torque fluctuation value, and determine whether it shows a continuous increase. If so, calculate its average slope and use this slope as the first optimization parameter.

[0077] In the embodiment of the present invention, the torque fluctuation value is usually obtained by real-time acquisition through a torque sensor installed on the rotating shaft of the target device. The sensor will record the force conditions of the rotating shaft at different time points and generate a fluctuation curve of the torque changing with time. If the sensor data does not directly provide the torque fluctuation value, the specific torque fluctuation value can be calculated by analyzing the change rate of the torque with time (such as the first derivative of the torque) or the amplitude of the torque deviating from the average value.

[0078] The setting basis of the first preset number is the operating characteristics of the target device and the statistical law of historical data. Generally speaking, the preset number needs to ensure sufficient sample data to reflect the torque fluctuation law under the specified working conditions, and at the same time avoid introducing redundancy or affecting the calculation efficiency due to too many sample numbers. For example, for a device with obvious periodic torque fluctuations, the data volume within a complete operating cycle can be selected as the preset number to cover the operating characteristics of the target device.

[0079] Calculating the average value of the set of historical torque fluctuation values and determining whether the current torque fluctuation value exceeds the preset threshold of the average value aims to identify whether there is an abnormality in the current torque fluctuation. The setting basis of the preset threshold includes the design specifications of the target device, operating experience, or a reasonable fluctuation range obtained through statistical analysis of historical data. This process ensures that further trend analysis is only started when the torque fluctuation exceeds the normal range, thereby improving the pertinence and efficiency of the calculation.

[0080] Analyzing the change trend of the historical torque fluctuation value and determining whether it shows a continuous increase aims to evaluate whether there is an obvious temporal cumulative effect in the torque fluctuation abnormality. If the trend shows a continuous increase, it may indicate that the operating environment or load state of the target device is deteriorating. For example, the mechanical system may be gradually damaged or the load pressure may increase. The significance of setting this step lies in distinguishing occasional abnormalities from persistent abnormalities through trend analysis and providing a more reliable basis for subsequent optimization.

[0081] Calculating the average slope of the line chart of historical torque fluctuation values and using it as the first optimization parameter can quantify the rate of change and trend intensity of torque fluctuations. This optimization parameter is of great significance for subsequent adjustment of the initial electrical stability parameters. The slope directly reflects the strength of the torque fluctuation trend and can be used as an important indicator of changes in the equipment operating environment. Using it in the calculation of optimization parameters can make the optimized electrical stability parameters more sensitive to reflect the actual operating state of the equipment and improve the dynamic adaptability of the adjustment strategy. In this way, the optimization parameter not only contains abnormal static information but also incorporates trend dynamic information, making the adjustment process more efficient and intelligent.

[0082] Furthermore, the artificial intelligence-based data security traceability method further includes the following steps:

[0083] Step S300: Analyze historical vibration data, extract the vibration characteristic data set under specified working conditions, and analyze whether its change trend is consistent with the trend characteristics of the torque fluctuation value. If it is consistent, obtain the deviation value between the current vibration characteristic value and the preset standard value, and use it as the second optimization parameter.

[0084] Specifically, Figure 3 The flowchart for determining the second optimization parameter for adjusting the initial electrical stability parameters is shown.

[0085] Among them, analyzing historical vibration data, extracting the vibration characteristic data set under specified working conditions, and analyzing whether its change trend is consistent with the trend characteristics of the torque fluctuation value. If it is consistent, obtaining the deviation value between the current vibration characteristic value and the preset standard value, and using it as the second optimization parameter specifically includes the following steps:

[0086] Step S301: Parse the historical vibration data, extract the second preset number of vibration characteristic data under specified working conditions, and form a vibration characteristic data set;

[0087] Step S302: Analyze the change trend of the vibration characteristic data set and determine whether it is consistent with the trend characteristics of the torque fluctuation value. If it is consistent, extract the current vibration characteristic value of the target equipment and compare it with the preset standard value corresponding to the specified area in the current operating state of the target equipment;

[0088] Step S303: Calculate the deviation value between the current vibration characteristic value and the preset standard value, and quantify this deviation value as the second optimization parameter.

[0089] In the embodiments of the present invention, the vibration characteristic data may include vibration-related parameters such as vibration amplitude, vibration frequency, acceleration, and velocity of the target device within a specified area. These data are collected by vibration sensors installed at key parts of the device and can reflect the dynamic characteristics of mechanical vibration, such as the influence of rotor eccentricity, bearing wear, or other abnormal mechanical behaviors on the operation of the device.

[0090] The basis for setting the second preset quantity is related to the operating cycle and vibration characteristics of the target device. Generally speaking, it is necessary to select the amount of data within a time window that can fully represent the vibration law of the device while avoiding an increase in computational complexity due to excessive data. The appropriate preset quantity can be set based on historical experience, statistical laws of the device operating cycle, or by analyzing the frequency distribution of the vibration data collected by the sensors.

[0091] When judging whether the change trend of the vibration characteristic data set is consistent with the trend characteristics of the torque fluctuation value, the concept of consistency should include the trend direction of the vibration characteristic data (such as synchronous increase or decrease), the similarity of the change amplitude, and the correlation of the overall time series change. An approximate trend can also be considered a kind of consistency, but the specific degree needs to be determined according to the allowable range of device operation safety. The vibration characteristic value refers to the vibration parameter value of the target device at the current moment in the specified area, such as the vibration amplitude or frequency at the current moment, and this value is used to compare with the preset standard value to judge whether the vibration is within the normal range.

[0092] The preset standard value corresponding to the specified area of the target device in the current operating state usually comes from the device design specifications, rated parameters in the operation manual, or is obtained based on the statistical analysis of historical data from long-term monitoring of the device under normal operating conditions. Different operating states may correspond to different preset standard values. For example, the vibration standard values during high-load operation and low-load operation may be different. To ensure the accuracy of the analysis, the specific standard value corresponding to the current operating state should be dynamically matched.

[0093] Calculating the deviation value between the current vibration characteristic value and the preset standard value and quantifying this deviation value as the second optimization parameter means that by quantitatively analyzing the degree of abnormality of the vibration characteristic data, it provides a key indicator for the subsequent optimization of electrical stability parameters. Introducing the deviation information of the vibration characteristic value into the optimization parameter can more comprehensively reflect the impact of mechanical abnormalities on the electrical system, thereby enhancing the pertinence and dynamic response ability of the optimization process. This method can not only improve the adaptability of the optimization parameter to the actual operating state but also provide more accurate guidance for the real-time adjustment of the device, which helps to improve the overall stability and operating efficiency of the system.

[0094] Furthermore, the artificial intelligence-based data security traceability method further includes the following steps:

[0095] Step S400: Combine the first optimization parameter and the second optimization parameter to correct the initial electrical stability parameter and generate an optimized electrical stability parameter.

[0096] Specifically, Figure 4 Fig. shows a flowchart of correcting the initial electrical stability parameter based on the first optimization parameter and the second optimization parameter.

[0097] Among them, combining the first optimization parameter and the second optimization parameter to correct the initial electrical stability parameter and generate an optimized electrical stability parameter specifically includes the following steps:

[0098] Step S401: Retrieve the electrical stability parameter adjustment formula, and correct the initial electrical stability parameter based on the first optimization parameter and the second optimization parameter to generate an optimized electrical stability parameter;

[0099] Step S402: Apply the optimized electrical stability parameter to the voltage regulator corresponding to the target device.

[0100] The electrical stability parameter adjustment formula is: , where S optimized refers to the optimized electrical stability parameter, S initial refers to the initial electrical stability parameter, P1 refers to the first optimization parameter, k1 refers to the adjustment coefficient of the first optimization parameter, P2 refers to the second optimization parameter, and k2 refers to the adjustment coefficient of the second optimization parameter;

[0101] In the electrical stability parameter adjustment formula:

[0102] , where N refers to the total number of historical torque fluctuation values in the set of historical torque fluctuation values, T history,i refers to the i-th historical torque fluctuation value in the set of historical torque fluctuation values;

[0103] , where V current refers to the current vibration characteristic value, V baseline refers to the preset standard value.

[0104] In the embodiment of the present invention, the significance of jointly optimizing the initial electrical stability parameter by combining the first optimization parameter and the second optimization parameter is that these two optimization parameters respectively reflect different aspects of the operating state of the target device. The first optimization parameter quantifies the dynamic response problem of the equipment mechanical system caused by the three-phase voltage imbalance condition by analyzing the trend characteristics of torque fluctuations; the second optimization parameter captures the potential impact of the abnormal characteristics of mechanical vibration on electrical stability through the deviation analysis of vibration characteristic values.

[0105] This combination method ensures that the optimized electrical stability parameters can not only reflect the direct state changes of the electrical system, but also incorporate the dynamic information of the mechanical system, thus achieving a more comprehensive and accurate optimization effect. In addition, the bases of the two optimized parameters are closely related to mechanical wear: the first optimized parameter comes from the wear of torque-related components and reflects the change trend of the force state of the components; the second optimized parameter reflects the mechanical vibration characteristics caused by wear of torque-related components through abnormal vibrations. This design enables the optimized parameters to not only cover the coupling of mechanical and electrical characteristics, but also more accurately capture the impact of mechanical wear on system stability.

[0106] By applying the initial electrical stability parameters to the corresponding voltage regulator of the target device in this way, the voltage regulator can dynamically perceive the actual operating conditions of the device, rather than solely relying on the static calculation results of electrical parameters. Combining the optimized parameters, the voltage regulator can flexibly adjust the compensation strategy according to the real-time operating state, such as more accurately adjusting the balance of the output voltage, reducing the negative-sequence voltage component, or adjusting the speed of the compensation response, thereby significantly improving the regulation effect of the voltage regulator and the overall stability of the device operation.

[0107] There is a close connection between the first optimized parameter and the second optimized parameter. They are both obtained based on the analysis of the operating history data of the target device and respectively reflect the abnormal characteristics of the device affected by the electrical imbalance condition from different dimensions. There is usually a certain synchronization between the trend of torque fluctuation and the change of vibration characteristics, and a significant change in torque fluctuation may be accompanied by an increase in mechanical vibration. Therefore, these two parameters complement each other at the information level and jointly construct the complete response characteristics of the device under abnormal conditions, providing a multi-dimensional basis for the correction of electrical stability parameters.

[0108] For example, when an industrial motor is running, the initial electrical stability parameters are obtained by real-time monitoring of the operating state of the voltage regulator, including the current three-phase voltage unbalance degree and negative-sequence voltage content. When a three-phase voltage unbalance occurs in the device, the system obtains the historical torque fluctuation data from the torque sensor, extracts the current torque fluctuation value and compares it with the historical data, and finds that the current value is significantly higher than the historical average value and the torque fluctuation shows a continuous upward trend. The first optimized parameter is calculated through trend analysis to quantify the change intensity of the torque fluctuation.

[0109] At the same time, obtain the historical vibration data of the designated area of the target device from the vibration sensor, extract the set of vibration characteristic values under the designated working conditions, and analyze whether the change trend of these values is consistent with the torque fluctuation trend. If they are consistent, further obtain the current vibration characteristic value and compare it with the preset normal vibration range to quantify the deviation value as the second optimized parameter.

[0110] Combined with the first optimization parameter and the second optimization parameter, the initial parameters are corrected by invoking the electrical stability parameter adjustment formula to generate optimized electrical stability parameters. The optimized parameters are used to guide the voltage regulator to dynamically adjust the operation strategy, such as more accurately compensating for the imbalance of three-phase voltages and optimizing the response speed to adapt to the current operating state. This optimization result ultimately makes the target device operate more stably while reducing equipment losses and operating risks caused by mechanical abnormalities and electrical imbalances.

[0111] Furthermore, Figure 5 The application architecture diagram of the system provided by the embodiment of the present invention is shown.

[0112] Among them, in another preferred embodiment provided by the present invention, a data security traceability system based on artificial intelligence includes:

[0113] A data acquisition module 100, configured to determine the current operating state of the target device, obtain its torque fluctuation historical log, historical vibration data of a specified area, and initial electrical stability parameters applied to the corresponding voltage regulator of the target device when a three-phase voltage imbalance condition occurs in the target device.

[0114] In the embodiment of the present invention, the target device can be devices such as industrial motors, fans, water pumps, compressors, etc. These devices have high requirements for the balance of three-phase voltages during operation, and the three-phase voltage imbalance condition will directly affect their operating performance and lifespan. For example, an industrial motor will exhibit phenomena such as increased rotor vibration and increased torque fluctuation due to three-phase voltage imbalance, further leading to problems such as decreased equipment efficiency or overheating.

[0115] The current operating state can be the real-time operating condition state of the target device, including parameters such as operating power, rotational speed, and load change. Preferably, it is the stable operating state of the device under a specific load, such as a constant power output or constant rotational speed state. In this state, it is easier to identify the direct impact of three-phase voltage imbalance on the device operation.

[0116] The specified area should be the area in the target device that can best reflect the abnormal vibration of the rotor. For example, the bearing part or the winding end area of the motor rotor. These areas are usually sensitive points for the coupling effect of mechanical vibration and electrical imbalance and can effectively capture the abnormal characteristics of the device operating state. The torque fluctuation historical log and the historical vibration data of the specified area can be obtained through sensors deployed inside or around the device. The torque fluctuation data can be collected by a torque sensor installed on the rotating shaft and its time series is recorded; the historical vibration data is collected by an acceleration sensor or a vibration sensor, and information such as vibration amplitude and frequency is recorded for the dynamic characteristics of the specified area.

[0117] The voltage regulator corresponding to the target device is used to regulate the three-phase voltage received by the device, ensuring the balance and stability of the voltage to reduce the impact of voltage fluctuations on the operating state of the device. The voltage regulator dynamically adjusts the output voltage according to the operating requirements of the target device, such as compensating for negative sequence components or adjusting the voltage phase difference, thereby improving the operating efficiency and stability of the device.

[0118] The initial electrical stability parameters can be the basic parameters describing the electrical operating state of the device, such as negative sequence voltage content, three-phase current balance degree, system harmonic distortion rate, etc. Preferably, it is an index that can quantify the degree of voltage imbalance, such as the ratio of negative sequence voltage content or the three-phase current imbalance coefficient. These parameters directly reflect the potential impact of three-phase voltage imbalance on the operation of the device. At the same time, by expanding and optimizing the dynamic range of the parameters, a wider adjustment space can be provided for subsequent optimization calculations.

[0119] In the prior art, the application of voltage regulators has been widely used for the regulation of three-phase voltage imbalance, but most are based on fixed control strategies and lack dynamic adjustment capabilities. In particular, they fail to fully combine the torque fluctuations and vibration data of the target device for optimization. The prior art mainly focuses on the one-way compensation of electrical parameters and does not conduct in-depth research on the specific impacts of mechanical and electrical coupling.

[0120] Furthermore, the artificial intelligence-based data security traceability system further includes:

[0121] The first optimization parameter determination module 200 is used to parse the torque fluctuation history log, extract the current torque fluctuation value of the target device and the set of historical torque fluctuation values under specified working conditions, analyze whether the current torque fluctuation value exceeds the preset threshold of the average value of the set of historical torque fluctuation values. If so, generate the trend characteristics of the torque fluctuation value according to the time series, determine whether the trend characteristics meet the preset conditions. If they meet, calculate the characteristic quantity of the trend change and use it as the first optimization parameter.

[0122] The specified working conditions refer to the working conditions that are the same as the current operating state of the target device but without three-phase voltage imbalance.

[0123] Specifically, Figure 6 The structural block diagram of the first optimization parameter determination module 200 in the system provided by the embodiment of the present invention is shown.

[0124] Among them, in the preferred embodiment provided by the present invention, the first optimization parameter determination module 200 specifically includes:

[0125] The historical log parsing unit 201 is used to parse the historical torque fluctuation log, extract the current torque fluctuation value of the target device, and the historical torque fluctuation values under the specified working conditions of the first preset quantity, and form a historical torque fluctuation value set with these historical torque fluctuation values;

[0126] The trend feature generation unit 202 is used to calculate the average value of the historical torque fluctuation value set, and judge whether the current torque fluctuation value exceeds the preset threshold of the average value. If so, it generates the change trend of the historical torque fluctuation value based on the time series, that is, the trend feature of the torque fluctuation value;

[0127] The first optimization parameter calculation unit 203 is used to analyze the change trend of the historical torque fluctuation value, judge whether it shows a continuous increase, and if so, calculate its average slope and use this slope as the first optimization parameter.

[0128] In the embodiment of the present invention, the torque fluctuation value is usually obtained by real-time acquisition through a torque sensor installed on the rotating shaft of the target device. The sensor will record the force condition of the rotating shaft at different time points and generate a fluctuation curve of the torque changing with time. If the sensor data does not directly provide the torque fluctuation value, the specific torque fluctuation value can be calculated by analyzing the change rate of the torque with time (such as the first derivative of the torque) or the amplitude of the torque deviating from the average value.

[0129] The setting basis of the first preset quantity is the operating characteristics of the target device and the statistical law of historical data. Generally speaking, the preset quantity needs to ensure sufficient sample data to reflect the torque fluctuation law under the specified working conditions, and at the same time avoid too many sample quantities from introducing redundancy or affecting the calculation efficiency. For example, for a device with obvious periodic torque fluctuations, the data volume within a complete operating cycle can be selected as the preset quantity to cover the operating characteristics of the target device.

[0130] Calculating the average value of the historical torque fluctuation value set and judging whether the current torque fluctuation value exceeds the preset threshold of the average value aims to identify whether there is an abnormality in the current torque fluctuation. The setting basis of the preset threshold includes the design specifications of the target device, operating experience, or a reasonable fluctuation range obtained through statistical analysis of historical data. This process ensures that further trend analysis is only started when the torque fluctuation exceeds the normal range, thereby improving the pertinence and efficiency of the calculation.

[0131] Analyzing the change trend of the historical torque fluctuation value and judging whether it shows a continuous increase aims to evaluate whether there is an obvious temporal cumulative effect in the torque fluctuation abnormality. If the trend shows a continuous increase, it may indicate that the operating environment or load state of the target device is deteriorating. For example, the mechanical system may be gradually damaged or the load pressure may increase. The significance of setting this step is to distinguish occasional abnormalities from persistent abnormalities through trend analysis and provide a more reliable basis for subsequent optimization.

[0132] Calculating the average slope of the line graph of historical torque fluctuation values and using it as the first optimization parameter can quantify the rate and trend intensity of torque fluctuation changes. This optimization parameter is of great significance for subsequent adjustment of the initial electrical stability parameters. The slope directly reflects the strength of the torque fluctuation trend and can be used as an important indicator of changes in the equipment operating environment. Using it in the calculation of optimization parameters can make the optimized electrical stability parameters more sensitively reflect the actual operating state of the equipment and improve the dynamic adaptability of the adjustment strategy. In this way, the optimization parameter not only contains abnormal static information but also incorporates trend dynamic information, making the adjustment process more efficient and intelligent.

[0133] Furthermore, the artificial intelligence-based data security traceability system further includes:

[0134] A second optimization parameter determination module 300, configured to analyze historical vibration data, extract a set of vibration characteristic data under specified working conditions, analyze whether its change trend is consistent with the trend characteristics of the torque fluctuation value. If they are consistent, obtain the deviation value between the current vibration characteristic value and the preset standard value, and use it as the second optimization parameter.

[0135] Specifically, Figure 7 FIG. shows the structural block diagram of the second optimization parameter determination module 300 in the system provided by the embodiment of the present invention.

[0136] Among them, in the preferred embodiment provided by the present invention, the second optimization parameter determination module 300 specifically includes:

[0137] A vibration data analysis unit 301, configured to analyze historical vibration data, extract a second preset number of vibration characteristic data under specified working conditions, and form a set of vibration characteristic data;

[0138] A numerical comparison unit 302, configured to analyze the change trend of the set of vibration characteristic data, determine whether it is consistent with the trend characteristics of the torque fluctuation value. If they are consistent, extract the current vibration characteristic value of the target device and compare it with the preset standard value corresponding to the specified area in the current operating state of the target device;

[0139] A second optimization parameter calculation unit 303, configured to calculate the deviation value between the current vibration characteristic value and the preset standard value, and quantify this deviation value as the second optimization parameter.

[0140] In the embodiment of the present invention, the vibration characteristic data may include vibration-related parameters such as vibration amplitude, vibration frequency, acceleration, and speed of the target device in a specified area. These data are collected by vibration sensors installed at key parts of the equipment and can reflect the dynamic characteristics of mechanical vibration, such as the influence of rotor eccentricity, bearing wear, or other abnormal mechanical behaviors on the equipment operation.

[0141] The setting basis of the second preset quantity is related to the operating cycle and vibration characteristics of the target device. Generally speaking, it is necessary to select the amount of data within a time window that can fully represent the vibration law of the device, while avoiding excessive data leading to an increase in computational complexity. The appropriate preset quantity can be set based on historical experience, statistical laws of the device operating cycle, or by analyzing the frequency distribution of the vibration data collected by the sensor.

[0142] When judging whether the change trend of the vibration characteristic data set is consistent with the trend characteristics of the torque fluctuation value, the concept of consistency should include the trend direction of the vibration characteristic data (such as synchronous increase or decrease), the similarity of the change amplitude, and the correlation of the overall time series change. An approximate trend can also be considered a kind of consistency, but the specific degree needs to be determined according to the allowable range of device operation safety. The vibration characteristic value refers to the vibration parameter value of the target device at the current moment in the specified area, such as the vibration amplitude or frequency at the current moment. This value is used to compare with the preset standard value to judge whether the vibration is within the normal range.

[0143] The preset standard value corresponding to the specified area of the target device in the current operating state usually comes from the device design specifications, rated parameters in the operation manual, or is obtained based on the statistical data of long-term monitoring of the device under normal operating conditions. Different operating states may correspond to different preset standard values. For example, the vibration standard values during high-load operation and low-load operation may be different. To ensure the accuracy of the analysis, the specific standard value of the current operating state should be dynamically matched.

[0144] Calculating the deviation value between the current vibration characteristic value and the preset standard value and quantifying this deviation value as the second optimization parameter means that by quantitatively analyzing the abnormal degree of the vibration characteristic data, it provides a key index for the subsequent optimization of the electrical stability parameters. Introducing the deviation information of the vibration characteristic value into the optimization parameters can more comprehensively reflect the impact of mechanical abnormalities on the electrical system, thereby enhancing the pertinence and dynamic response ability of the optimization process. This method can not only improve the adaptability of the optimization parameters to the actual operating state, but also provide more accurate guidance for the real-time adjustment of the device, which helps to improve the overall stability and operating efficiency of the system.

[0145] Furthermore, the artificial intelligence-based data security traceability system further includes:

[0146] A stability parameter correction module 400, configured to correct the initial electrical stability parameters by combining the first optimization parameter and the second optimization parameter to generate optimized electrical stability parameters.

[0147] Specifically, Figure 8 The structural block diagram of the stability parameter correction module 400 in the system provided by the embodiment of the present invention is shown.

[0148] Among them, in the preferred embodiment provided by the present invention, the stable parameter correction module 400 specifically includes:

[0149] A stable parameter optimization unit 401, configured to retrieve an electrical stability parameter adjustment formula, and correct the initial electrical stability parameters based on a first optimization parameter and a second optimization parameter to generate optimized electrical stability parameters;

[0150] An optimized stable parameter application unit 402, configured to apply the optimized electrical stability parameters to the voltage regulator corresponding to the target device;

[0151] The electrical stability parameter adjustment formula is: , where S optimized refers to the optimized electrical stability parameter, S initial refers to the initial electrical stability parameter, P1 refers to the first optimization parameter, k1 refers to the adjustment coefficient of the first optimization parameter, P2 refers to the second optimization parameter, and k2 refers to the adjustment coefficient of the second optimization parameter;

[0152] In the electrical stability parameter adjustment formula:

[0153] , where N refers to the total number of historical torque fluctuation values in the set of historical torque fluctuation values, and T history,i refers to the i-th historical torque fluctuation value in the set of historical torque fluctuation values;

[0154] , where V current refers to the current vibration characteristic value, and V baseline refers to the preset standard value.

[0155] In the embodiments of the present invention, the significance of jointly optimizing the initial electrical stability parameters by combining the first optimization parameter and the second optimization parameter is that these two optimization parameters respectively reflect different aspects of the operating state of the target device. The first optimization parameter quantifies the dynamic response problem of the device's mechanical system caused by the unbalanced three-phase voltage condition by analyzing the trend characteristics of torque fluctuations; the second optimization parameter captures the potential impact of abnormal characteristics of mechanical vibration on electrical stability through the deviation analysis of vibration characteristic values.

[0156] This combination method ensures that the optimized electrical stability parameters can not only reflect the direct state changes of the electrical system, but also incorporate the dynamic information of the mechanical system, thus achieving a more comprehensive and accurate optimization effect. In addition, the bases of the two optimized parameters are closely related to mechanical wear: the first optimized parameter comes from the wear of torque-related components and reflects the changing trend of the force state of the components; the second optimized parameter reflects the mechanical vibration characteristics caused by wear of torque-related components through abnormal vibrations. This design enables the optimized parameters to not only cover the coupling of mechanical and electrical characteristics, but also capture more accurately the impact of mechanical wear on system stability.

[0157] By applying the initial electrical stability parameters to the corresponding voltage regulator of the target device in this way, the voltage regulator can dynamically perceive the actual operating conditions of the device, rather than relying solely on the static calculation results of electrical parameters. Combining the optimized parameters, the voltage regulator can flexibly adjust the compensation strategy according to the real-time operating state, such as more accurately adjusting the balance of the output voltage, reducing the negative-sequence voltage component, or adjusting the speed of the compensation response, thereby significantly improving the regulation effect of the voltage regulator and the overall stability of the device operation.

[0158] There is a close connection between the first optimized parameter and the second optimized parameter. They are both obtained based on the analysis of the operating history data of the target device and respectively reflect the abnormal characteristics of the device affected by the electrical imbalance condition from different dimensions. There is usually a certain synchronization between the trend of torque fluctuation and the change of vibration characteristics, and a significant change in torque fluctuation may be accompanied by an increase in mechanical vibration. Therefore, these two parameters complement each other at the information level and jointly construct the complete response characteristics of the device under abnormal conditions, providing a multi-dimensional basis for the correction of electrical stability parameters.

[0159] For example, during the operation of an industrial motor, the initial electrical stability parameters are obtained by real-time monitoring of the operating state of the voltage regulator, including the current three-phase voltage unbalance degree and negative-sequence voltage content. When a three-phase voltage imbalance occurs in the device, the system obtains the historical torque fluctuation data from the torque sensor, extracts the current torque fluctuation value and compares it with the historical data, and finds that the current value is significantly higher than the historical average value and the torque fluctuation shows a continuous upward trend. The first optimized parameter is calculated through trend analysis to quantify the change intensity of the torque fluctuation.

[0160] At the same time, obtain the historical vibration data of the specified area of the target device from the vibration sensor, extract the set of vibration characteristic values under the specified working conditions, and analyze whether the change trend of these values is consistent with the torque fluctuation trend. If they are consistent, further obtain the current vibration characteristic value and compare it with the preset normal vibration range to quantify the deviation value as the second optimized parameter.

[0161] Combined with the first optimization parameter and the second optimization parameter, the initial parameters are corrected by invoking the electrical stability parameter adjustment formula to generate optimized electrical stability parameters. The optimized parameters are used to guide the voltage regulator to dynamically adjust the operation strategy, such as more precisely compensating for the imbalance of three-phase voltages and optimizing the response speed to adapt to the current operating state. This optimization result ultimately makes the target device operate more stably, while reducing equipment losses and operation risks caused by mechanical abnormalities and electrical imbalances.

[0162] It should be understood that although the steps in the flowcharts of the embodiments of the present invention are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in each embodiment may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same moment, but can be executed at different moments. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least a part of other steps or sub-steps or stages of other steps.

[0163] 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 program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database or other medium used in the embodiments provided in the present application 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 (DDRSDRAM), 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 (RDRAM), etc.

[0164] The technical features of the above-described embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as falling within the scope described in this specification.

[0165] The above-described embodiments merely represent several implementation manners of the present invention. The description is relatively specific and detailed, but it should not be construed as a limitation on the scope of the patent for the present invention. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent for the present invention shall be subject to the appended claims.

[0166] The above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent replacements, and improvements made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A data security tracing method based on artificial intelligence, characterized in that: The method comprises: When the target device has a three-phase voltage imbalance condition, determine the current operating state of the target device, obtain its torque fluctuation history log, historical vibration data of the specified area, and initial electrical stability parameters applied to the corresponding voltage regulator of the target device; Parse the torque fluctuation history log, extract the current torque fluctuation value of the target device and the historical torque fluctuation value set under the specified working condition, analyze whether the current torque fluctuation value exceeds the preset threshold value of the average value of the historical torque fluctuation value set, and if so, generate the trend feature of the torque fluctuation value according to the time series, judge whether the trend feature meets the preset conditions, and if so, calculate the feature amount of the trend change and use it as the first optimization parameter; Analyze historical vibration data, extract the vibration characteristic data set under the specified working conditions, and analyze whether its change trend is consistent with the trend characteristics of the torque fluctuation value. If consistent, obtain the deviation value between the current vibration characteristic value and the preset standard value and use it as the second optimization parameter; The initial electrical stability parameters are corrected by combining the first optimization parameters and the second optimization parameters to generate optimized electrical stability parameters.

2. The data security tracing method based on artificial intelligence according to claim 1 is characterized in that: The specified operating condition refers to an operating condition that is consistent with the current operating state of the target device but is not under a three-phase voltage imbalance condition.

3. The data security tracing method based on artificial intelligence according to claim 2 is characterized in that: The steps of parsing the torque fluctuation history log, extracting the current torque fluctuation value of the target device and the historical torque fluctuation value set under the specified working condition, analyzing whether the current torque fluctuation value exceeds the preset threshold value of the average value of the historical torque fluctuation value set, and if so, generating the trend feature of the torque fluctuation value according to the time series, judging whether the trend feature meets the preset condition, and if so, calculating the feature amount of the trend change and using it as the first optimization parameter include: Parsing the torque fluctuation history log, extracting the current torque fluctuation value of the target device and the historical torque fluctuation values ​​under a first preset number of specified working conditions, and forming a historical torque fluctuation value set with these historical torque fluctuation values; Calculate the average value of the historical torque fluctuation value set, and determine whether the current torque fluctuation value exceeds a preset threshold value of the average value. If so, generate a change trend of the historical torque fluctuation value based on the time series, that is, a trend feature of the torque fluctuation value; Analyze the changing trend of the historical torque fluctuation value to determine whether it shows a continuous increase. If so, calculate its average slope and use the slope as the first optimization parameter.

4. The data security tracing method based on artificial intelligence according to claim 2 is characterized in that: The steps of analyzing historical vibration data, extracting a set of vibration characteristic data under specified working conditions, analyzing whether its change trend is consistent with the trend characteristics of the torque fluctuation value, and if consistent, obtaining the deviation value between the current vibration characteristic value and the preset standard value and using it as the second optimization parameter include: parsing historical vibration data, extracting vibration characteristic data under a second preset number of specified working conditions, and forming a vibration characteristic data set; Analyze the change trend of the vibration characteristic data set to determine whether it is consistent with the trend characteristics of the torque fluctuation value. If it is consistent, extract the current vibration characteristic value of the target device and compare it with the preset standard value corresponding to the specified area of ​​the target device under the current operating state; The deviation between the current vibration characteristic value and the preset standard value is calculated, and the deviation is quantified as a second optimization parameter.

5. The data security tracing method based on artificial intelligence according to claim 1 is characterized in that: The steps of correcting the initial electrical stability parameter by combining the first optimization parameter and the second optimization parameter to generate the optimized electrical stability parameter include: Retrieving an electrical stability parameter adjustment formula, and correcting the initial electrical stability parameter based on the first optimization parameter and the second optimization parameter to generate an optimized electrical stability parameter; Apply the optimized electrical stability parameters to the target device's corresponding voltage regulator.

6. The data security tracing method based on artificial intelligence according to claim 5 is characterized in that: The electrical stability parameter adjustment formula is: , where S optimized Refers to the optimized electrical stability parameters, S initial refers to the initial electrical stability parameter, P1 refers to the first optimization parameter, k1 refers to the adjustment coefficient of the first optimization parameter, P2 refers to the second optimization parameter, and k2 refers to the adjustment coefficient of the second optimization parameter; In the electrical stability parameter adjustment formula: , where N refers to the total number of historical torque fluctuation values ​​in the historical torque fluctuation value set, T history,i Refers to the i-th historical torque fluctuation value in the historical torque fluctuation value set; , where V current Refers to the current vibration characteristic value, V baseline Refers to the preset standard value.

7. A data security tracing system based on artificial intelligence, characterized in that: The system comprises: a data acquisition module, a first optimization parameter determination module, a second optimization parameter determination module and a stability parameter correction module, wherein: A data acquisition module is used to determine the current operating state of the target device when a three-phase voltage imbalance occurs in the target device, obtain its torque fluctuation history log, historical vibration data of a specified area, and initial electrical stability parameters applied to the corresponding voltage regulator of the target device; A first optimization parameter determination module is used to parse the torque fluctuation history log, extract the current torque fluctuation value of the target device and the historical torque fluctuation value set under the specified working condition, analyze whether the current torque fluctuation value exceeds the preset threshold of the average value of the historical torque fluctuation value set, and if so, generate the trend feature of the torque fluctuation value according to the time series, judge whether the trend feature meets the preset condition, and if so, calculate the feature amount of the trend change and use it as the first optimization parameter; The specified operating condition refers to an operating condition that is consistent with the current operating state of the target device but is not under a three-phase voltage imbalance condition; The second optimization parameter determination module is used to analyze historical vibration data, extract a set of vibration characteristic data under specified working conditions, and analyze whether its change trend is consistent with the trend characteristics of the torque fluctuation value. If consistent, the deviation value between the current vibration characteristic value and the preset standard value is obtained and used as the second optimization parameter; The stability parameter correction module is used to correct the initial electrical stability parameter by combining the first optimization parameter and the second optimization parameter to generate an optimized electrical stability parameter.

8. The data security tracing system based on artificial intelligence according to claim 7 is characterized in that: The first optimization parameter determination module specifically includes: a historical log parsing unit, configured to parse the torque fluctuation historical log, extract the current torque fluctuation value of the target device and the historical torque fluctuation values ​​under a first preset number of specified working conditions, and form a historical torque fluctuation value set with these historical torque fluctuation values; A trend feature generating unit, used for calculating an average value of a set of historical torque fluctuation values, and determining whether a current torque fluctuation value exceeds a preset threshold value of the average value, and if so, generating a change trend of the historical torque fluctuation values, i.e., a trend feature of the torque fluctuation values, based on a time series; The first optimization parameter calculation unit is used to analyze the change trend of the historical torque fluctuation value to determine whether it shows a continuous increase. If so, the average slope is calculated and the slope is used as the first optimization parameter.

9. The artificial intelligence-based data security tracing system according to claim 8 is characterized in that: The second optimization parameter determination module specifically includes: A vibration data analysis unit, used to analyze historical vibration data, extract vibration characteristic data under a second preset number of specified working conditions, and form a vibration characteristic data set; A numerical comparison unit is used to analyze the change trend of the vibration characteristic data set to determine whether it is consistent with the trend characteristics of the torque fluctuation value. If it is consistent, the current vibration characteristic value of the target device is extracted and compared with the preset standard value corresponding to the specified area of ​​the target device under the current operating state; The second optimization parameter calculation unit is used to calculate the deviation between the current vibration characteristic value and the preset standard value, and quantify the deviation as the second optimization parameter.

10. The data security tracing system based on artificial intelligence according to claim 9 is characterized in that: The stability parameter correction module specifically includes: A stability parameter optimization unit, used to retrieve an electrical stability parameter adjustment formula, modify the initial electrical stability parameter based on the first optimization parameter and the second optimization parameter, and generate an optimized electrical stability parameter; An optimized stability parameter application unit, used for applying the optimized electrical stability parameters to a voltage regulator corresponding to a target device; The electrical stability parameter adjustment formula is: , where S optimized Refers to the optimized electrical stability parameters, S initial refers to the initial electrical stability parameter, P1 refers to the first optimization parameter, k1 refers to the adjustment coefficient of the first optimization parameter, P2 refers to the second optimization parameter, and k2 refers to the adjustment coefficient of the second optimization parameter; In the electrical stability parameter adjustment formula: , where N refers to the total number of historical torque fluctuation values ​​in the historical torque fluctuation value set, T history,i Refers to the i-th historical torque fluctuation value in the historical torque fluctuation value set; , where V current Refers to the current vibration characteristic value, V baseline Refers to the preset standard value.

Images