Substation equipment operating status monitoring method and system based on voiceprint recognition

Abstract

The present invention discloses a method and system for monitoring the operating status of substation equipment based on voiceprint recognition, which belongs to the field of dynamic monitoring technology; the operating voiceprint data and operating time period of all substation equipment in the substation during historical operation are obtained, and an operating time point set is constructed; based on the operating time point and the operating voiceprint data, a voiceprint drift model is constructed; the current operating time point of the substation equipment and the operating voiceprint data corresponding to the current operating time point are obtained; the operating voiceprint data corresponding to all operating time points matching the current operating time point are obtained, and the comprehensive voiceprint difference is calculated; the comprehensive difference of all substation equipment in the substation within the current operating time point is obtained, the comprehensive difference similarity between different substation equipment is calculated, a threshold is preset, and linkage warnings are analyzed and carried out between substation equipment, which not only improves the accuracy and real-time performance of substation equipment operating status monitoring, but also enhances the intelligence level of abnormal linkage identification and warning response.

Description

Technical Field

[0001] The present invention relates to the field of dynamic monitoring technology, and in particular to a method and system for monitoring the operating status of substation equipment based on voiceprint recognition. Background Art

[0002] As the core hub of the power grid, substations require real-time monitoring and intelligent diagnosis of their equipment's operating status, making them crucial for ensuring safe and stable grid operation. Traditional condition monitoring methods rely heavily on electrical parameters (such as current, voltage, and temperature) and visual recognition. While these methods have established a robust system in practice, they still face challenges such as coarse perception granularity, high response latency, and delayed anomaly recognition when faced with complex and changing operating environments, inter-device interactions, and sudden abnormal events. In recent years, with the advancement of voiceprint recognition, acoustic feature extraction, and multi-source data fusion, voiceprint-based device status recognition has become a research hotspot. These methods analyze the acoustic characteristics generated by equipment during operation and offer advantages such as high non-invasiveness, convenient data collection, and wide device adaptability. They are gradually being explored and applied in fields such as wind power, hydropower, and rail transit.

[0003] However, in the substation sector, voiceprint-based state recognition methods are still in the preliminary research stage. Existing technologies mostly focus on anomaly detection of a single device or instantaneous judgment based on short-term sound characteristics. They lack systematic modeling of the operational voiceprint of the device throughout its life cycle and correlation analysis between multiple devices. On the one hand, existing technologies often ignore the "voiceprint drift" phenomenon caused by the evolution of the device's operational voiceprint over time, resulting in insufficient accuracy and robustness in anomaly detection. On the other hand, substation equipment often operates in a collaborative manner. When a potential anomaly occurs in a certain device, its neighboring or associated devices often also exhibit certain changes in voiceprint response. Existing solutions have difficulty effectively capturing and modeling this inter-device linkage behavior. In addition, the deep integration of voiceprint data and time information, the dynamic comparison of multiple rounds of historical data, and the quantitative evaluation of multi-dimensional voiceprint differences are still immature, limiting the practical application and intelligent development of voiceprint recognition in substation operational status monitoring. Summary of the Invention

[0004] The purpose of the present invention is to provide a method and system for monitoring the operating status of substation equipment based on voiceprint recognition, so as to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0006] A method for monitoring the operating status of substation equipment based on voiceprint recognition includes the following steps: Step S1: obtaining the operating voiceprint data and operating time period of all substation equipment in the substation during historical operation, and constructing an operating time point set; Step S2: constructing a voiceprint drift model based on the operating time point and the operating voiceprint data corresponding to the operating time point; Step S3: obtaining the current operating time point of the substation equipment and the operating voiceprint data corresponding to the current operating time point; obtaining the operating voiceprint data corresponding to all operating time points that match the current operating time point, and calculating the comprehensive voiceprint difference; Step S4: obtaining the comprehensive difference of all substation equipment in the substation within the current operating time point, calculating the comprehensive difference similarity between different substation equipment, presetting a threshold, analyzing and performing linkage warning between substation equipment.

[0007] As a preferred solution of the substation equipment operation status monitoring method based on voiceprint recognition described in the present invention, all substation equipment in the substation is obtained, and voiceprint vibration sensors are deployed inside the substation equipment, wherein one voiceprint vibration sensor is deployed corresponding to each substation equipment; the operation voiceprint data of the substation equipment collected by the voiceprint vibration sensor is stored in the substation background monitoring system;

[0008] The historical operation data log of the substation equipment is retrieved from the substation background monitoring system. The historical operation data log includes the operation voiceprint data and operation time period of the substation equipment during historical operation. The operation time period is evenly divided into several operation time points, and an operation time point set is constructed. The operation time point set corresponding to the historical n-th operation is recorded as ,in, It represents the i-th running time point corresponding to the n-th running in history, and I represents the total number of running time points.

[0009] As a preferred solution of the method for monitoring the operating status of substation equipment based on voiceprint recognition according to the present invention, based on the i-th operating time point corresponding to the n-th historical operation and running time points The corresponding running voiceprint data is used to build the voiceprint drift model corresponding to the nth historical run, as follows:

[0010] Run-time point set Traverse to obtain the running voiceprint data corresponding to each running time point, and arrange them in the order of running time points;

[0011] The arranged running voiceprint data is normalized, and based on the normalized running voiceprint data, a voiceprint drift model is constructed, which is recorded as ,in, Indicates the voiceprint drift model corresponding to the nth historical run, Indicates the normalized running time point The corresponding running voiceprint data, I represents the total number of running time points.

[0012] As a preferred solution of the method for monitoring the operating status of substation equipment based on voiceprint recognition according to the present invention, the current operating time point of the substation equipment and the operating voiceprint data corresponding to the current operating time point are obtained and recorded as and ; Obtain the voiceprint drift model corresponding to N historical operations, preset the operation time point matching rule, and extract the current operation time point of the substation equipment from the voiceprint drift model based on the operation time point matching rule The matching running time point; the running time point matching rule is as follows: , then determine the running time point With the current running time point Matches, where Indicates the preset runtime tolerance threshold. Indicates the mth running time point corresponding to the nth running time in history;

[0013] Get the current running time point The running voiceprint data corresponding to all the running time points that match, and the current running time point Corresponding running voiceprint data Perform difference comparison and calculate the comprehensive voiceprint difference. The calculation formula is as follows:

[0014] ;

[0015] in, Indicates the comprehensive difference, M indicates the difference from the current running time point The total number of running voiceprint data corresponding to all matching running time points, Indicates the running time point The corresponding running voiceprint data, Represents the preset exponential decay factor.

[0016] It should be noted that this formula uses the threshold Filter historical time points close to the current time point to ensure that the compared voiceprint data is in similar operating conditions (such as the same load period) to quantify the current operating time point Voiceprint data and historical matching time points The core design includes time decay weighting and difference accumulation and normalization, among which, the exponential function , giving higher weight to historical data with close time, and time difference The smaller the value, the greater the weight, and vice versa. The difference in voiceprints after weighted accumulation of the molecular part , the denominator normalizes the sum of the weights to ensure that the result is not affected by the amount of matching data (M); this formula combines time attenuation with voiceprint differences, solving the problem that traditional methods ignore "voiceprint drift" (gradual changes in voiceprints caused by equipment aging and environmental changes). For example, due to internal wear of a transformer, the voiceprint characteristics may change slowly. The formula can distinguish normal drift from sudden anomalies by weighting historical data.

[0017] As a preferred solution of the method for monitoring the operating status of substation equipment based on voiceprint recognition according to the present invention, the current operating time point is obtained. The comprehensive difference of all substation equipment in the substation is calculated by using cosine similarity to calculate the comprehensive difference similarity between different substation equipment. A comprehensive difference similarity threshold is preset and all substation equipment with a comprehensive difference similarity greater than or equal to the comprehensive difference similarity threshold is marked as similar equipment.

[0018] Based on comprehensive difference , preset comprehensive difference threshold, if the comprehensive difference If the value is greater than or equal to the comprehensive difference threshold, it is determined that the substation equipment has abnormal voiceprint drift at the current operating time point, that is, the substation equipment has abnormal operating status at the current operating time point, and a unified warning is issued for equipment similar to the substation equipment;

[0019] Acquire the operating voiceprint data of substation equipment at the operating time in real time, and conduct dynamic monitoring of the operating status of all substation equipment in the substation.

[0020] The substation equipment operation status monitoring system based on voiceprint recognition includes: data acquisition module, voiceprint drift model construction module, data matching and difference calculation module, and similarity calculation and analysis early warning module;

[0021] The data acquisition module is used to obtain the operation voiceprint data and operation time period of all substation equipment in the substation during historical operation, and to construct an operation time point set;

[0022] The voiceprint drift model construction module is configured to construct a voiceprint drift model based on the running time point and the running voiceprint data corresponding to the running time point;

[0023] The data matching and difference calculation module is used to obtain the current operation time point of the substation equipment and the operation voiceprint data corresponding to the current operation time point; obtain the operation voiceprint data corresponding to all operation time points that match the current operation time point, and calculate the comprehensive voiceprint difference;

[0024] The similarity calculation and analysis warning module: obtains the comprehensive difference of all substation equipment in the current operating time point, calculates the comprehensive difference similarity between different substation equipment, presets a threshold, analyzes and performs linkage warning between substation equipment.

[0025] Furthermore, the data acquisition module includes a data acquisition unit;

[0026] The data acquisition unit: acquires all substation equipment in the substation, and arranges voiceprint vibration sensors inside the substation equipment, wherein one voiceprint vibration sensor is arranged corresponding to one substation equipment; stores the operation voiceprint data of the substation equipment collected by the voiceprint vibration sensor into the substation background monitoring system; retrieves the historical operation data log of the substation equipment from the substation background monitoring system, wherein the historical operation data log includes the operation voiceprint data and operation time period of the substation equipment during historical operation, divides the operation time period evenly into several operation time points, constructs an operation time point set, and records the operation time point set corresponding to the nth historical operation as ,in, It represents the i-th running time point corresponding to the n-th running in history, and I represents the total number of running time points.

[0027] Furthermore, the voiceprint drift model construction module includes a voiceprint drift model construction unit;

[0028] The voiceprint drift model construction unit: based on the i-th running time point corresponding to the n-th historical running and running time points The corresponding running voiceprint data is used to build the voiceprint drift model corresponding to the nth historical run. The details are as follows: Traverse to obtain the running voiceprint data corresponding to each running time point, and arrange them in the order of the running time points; normalize the arranged running voiceprint data, and build a voiceprint drift model based on the normalized running voiceprint data, which is recorded as ,in, Indicates the voiceprint drift model corresponding to the nth historical run, Indicates the normalized running time point The corresponding running voiceprint data, I represents the total number of running time points.

[0029] Furthermore, the data matching and difference calculation module includes a data matching unit and a difference calculation unit;

[0030] The data matching unit obtains the current operation time point of the substation equipment and the operation voiceprint data corresponding to the current operation time point, respectively recorded as and ; Obtain the voiceprint drift model corresponding to N historical operations, preset the operation time point matching rule, and extract the current operation time point of the substation equipment from the voiceprint drift model based on the operation time point matching rule The matching running time point; the running time point matching rule is as follows: , then determine the running time point With the current running time point Matches, where Indicates the preset runtime tolerance threshold. Indicates the mth running time point corresponding to the nth running time in history;

[0031] The difference calculation unit: obtains the difference between the current running time point The running voiceprint data corresponding to all the running time points that match, and the current running time point Corresponding running voiceprint data Perform difference comparison and calculate the comprehensive voiceprint difference.

[0032] Furthermore, the similarity calculation and analysis warning module includes a similarity calculation unit and an analysis warning unit;

[0033] The similarity calculation unit: obtains the current running time point The comprehensive difference of all substation equipment in the substation is calculated by using cosine similarity to calculate the comprehensive difference similarity between different substation equipment. A comprehensive difference similarity threshold is preset and all substation equipment with a comprehensive difference similarity greater than or equal to the comprehensive difference similarity threshold is marked as similar equipment.

[0034] The analysis and early warning unit: based on the comprehensive difference , preset comprehensive difference threshold, if the comprehensive difference If it is greater than or equal to the comprehensive difference threshold, it is determined that the substation equipment has a voiceprint drift abnormality at the current operating time point, that is, the substation equipment has an operating status abnormality at the current operating time point, and a unified early warning is issued for equipment similar to the substation equipment; the operating voiceprint data of the substation equipment at the operating time point is obtained in real time, and the operating status of all substation equipment in the substation is dynamically monitored.

[0035] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: in the method and system for monitoring the operating status of substation equipment based on voiceprint recognition provided by the present invention, voiceprint vibration sensors are arranged inside the substation equipment to obtain the voiceprint data of each device during its historical operation, and the operating time point set is divided according to the operating time period, providing structured, high-resolution basic data for subsequent voiceprint evolution trend modeling, thereby enhancing the feasibility of time series comparative analysis. Based on the normalized historical voiceprint data, a voiceprint drift model is constructed to characterize the regular characteristics of the equipment operation voiceprint changing over time, thereby achieving accurate modeling of the equipment's historical operating status pattern and laying a model foundation for anomaly identification. An operating time point matching rule is introduced to obtain the corresponding relationship between the current operating moment and the historical status, and the comprehensive voiceprint difference is calculated through exponential decay weighting to highlight the dynamic difference between the current state and the historical stable state, thereby improving the sensitivity and robustness of anomaly detection. Based on the comprehensive differences between all devices, the system uses cosine similarity to calculate the degree of correlation between devices, and establishes a dual-threshold mechanism for coordinated early warning. This not only enables the active identification of abnormal devices, but also builds a risk-aware network for associated devices, enhancing the system's ability to intervene early in the spread of potential faults across multiple devices. This invention, through a full-process modeling and analysis process driven by voiceprint data, not only improves the accuracy and real-time performance of substation equipment operating status monitoring, but also enhances the intelligent level of abnormal linkage identification and early warning response. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention.

[0037] Figure 1 This is a schematic diagram of the steps of the substation equipment operating status monitoring method based on voiceprint recognition of the present invention;

[0038] Figure 2 It is a structural diagram of the substation equipment operation status monitoring system based on voiceprint recognition of the present invention. DETAILED DESCRIPTION

[0039] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0040] See also Figure 1 In the first embodiment, a method for monitoring the operating status of substation equipment based on voiceprint recognition is provided. The method includes the following steps:

[0041] Step S1: Obtain the operating voiceprint data and operating time period of all substation equipment in the substation during historical operation, and construct an operating time point set.

[0042] Specifically, all substation equipment in the substation is obtained, and voiceprint vibration sensors are deployed inside the substation equipment, wherein one voiceprint vibration sensor is deployed for each substation equipment; the operation voiceprint data of the substation equipment collected by the voiceprint vibration sensor is stored in the substation background monitoring system;

[0043] Furthermore, the historical operation data log of the substation equipment is retrieved from the substation background monitoring system. The historical operation data log includes the operation voiceprint data and operation time period of the substation equipment during historical operation. The operation time period is evenly divided into several operation time points, and an operation time point set is constructed. The operation time point set corresponding to the historical n-th operation is recorded as ,in, It represents the i-th running time point corresponding to the n-th running in history, and I represents the total number of running time points.

[0044] Step S2: Constructing a voiceprint drift model based on the running time point and the running voiceprint data corresponding to the running time point.

[0045] Specifically, based on the i-th running time point corresponding to the n-th historical running time and running time points The corresponding running voiceprint data is used to build the voiceprint drift model corresponding to the nth historical run, as follows:

[0046] Run-time point set Traverse to obtain the running voiceprint data corresponding to each running time point, and arrange them in the order of running time points;

[0047] The arranged running voiceprint data is normalized, and based on the normalized running voiceprint data, a voiceprint drift model is constructed, which is recorded as ,in, Indicates the voiceprint drift model corresponding to the nth historical run, Indicates the normalized running time point The corresponding running voiceprint data, I represents the total number of running time points.

[0048] In the present invention, each time point is bound to the normalized voiceprint feature to form a "time-voiceprint" trajectory, which intuitively depicts the dynamic evolution of the equipment's operating status. If the current voiceprint is abnormal, the historical data at the same time point in the model can be traced back to analyze whether the anomaly is a periodic fluctuation (such as normal changes caused by the start and stop of the fan).

[0049] Step S3: Obtain the current operating time point of the substation and the operating voiceprint data corresponding to the current operating time point; obtain the operating voiceprint data corresponding to all operating time points that match the current operating time point, and calculate the comprehensive voiceprint difference.

[0050] Specifically, the current operation time point of the substation equipment and the operation voiceprint data corresponding to the current operation time point are obtained and recorded as and ; Obtain the voiceprint drift model corresponding to N historical operations, preset the operation time point matching rule, and extract the current operation time point of the substation equipment from the voiceprint drift model based on the operation time point matching rule The matching running time point; the running time point matching rule is as follows: , then determine the running time point With the current running time point Matches, where Indicates the preset runtime tolerance threshold. Indicates the mth running time point corresponding to the nth running time in history;

[0051] Further, get the current running time point The running voiceprint data corresponding to all the running time points that match, and the current running time point Corresponding running voiceprint data Perform difference comparison and calculate the comprehensive voiceprint difference. The calculation formula is as follows:

[0052] ;

[0053] in, Indicates the comprehensive difference, M indicates the difference from the current running time point The total number of running voiceprint data corresponding to all matching running time points, Indicates the running time point The corresponding running voiceprint data, Represents the preset exponential decay factor.

[0054] In the present invention, invalid historical points (such as The system uses a time-matching mechanism (including a tolerance mechanism) to compare the current voiceprint with matching nodes in the historical drift model. It also uses an exponential decay factor to weight the difference, thereby constructing a comprehensive difference index reflecting the difference between the current state and the historical state. The introduction of a dynamic matching and decay mechanism ensures that the difference calculation not only considers distance but also reflects historical weight differences, thereby enhancing the model's sensitivity to deviations from the latest state.

[0055] Step S4: Obtain the comprehensive difference of all substation equipment in the current operating time point, calculate the comprehensive difference similarity between different substation equipment, preset thresholds, analyze and perform linkage warning between substation equipment.

[0056] Specifically, get the current running time point The comprehensive difference of all substation equipment in the substation is calculated by using cosine similarity to calculate the comprehensive difference similarity between different substation equipment. A comprehensive difference similarity threshold is preset and all substation equipment with a comprehensive difference similarity greater than or equal to the comprehensive difference similarity threshold is marked as similar equipment.

[0057] Furthermore, based on the comprehensive difference , preset comprehensive difference threshold, if the comprehensive difference If the value is greater than or equal to the comprehensive difference threshold, it is determined that the substation equipment has abnormal voiceprint drift at the current operating time point, that is, the substation equipment has abnormal operating status at the current operating time point, and a unified warning is issued for equipment similar to the substation equipment;

[0058] Acquire the operating voiceprint data of substation equipment at the operating time in real time, and conduct dynamic monitoring of the operating status of all substation equipment in the substation.

[0059] See also Figure 2 In the second embodiment, a substation equipment operation status monitoring system based on voiceprint recognition is provided, which includes: a data acquisition module, a voiceprint drift model construction module, a data matching and difference calculation module, and a similarity calculation and analysis warning module;

[0060] The data acquisition module is used to obtain the operation voiceprint data and operation time period of all substation equipment in the substation during historical operation, and to construct an operation time point set;

[0061] The voiceprint drift model construction module is configured to construct a voiceprint drift model based on the running time point and the running voiceprint data corresponding to the running time point;

[0062] The data matching and difference calculation module is used to obtain the current operation time point of the substation equipment and the operation voiceprint data corresponding to the current operation time point; obtain the operation voiceprint data corresponding to all operation time points that match the current operation time point, and calculate the comprehensive voiceprint difference;

[0063] The similarity calculation and analysis warning module: obtains the comprehensive difference of all substation equipment in the current operating time point, calculates the comprehensive difference similarity between different substation equipment, presets a threshold, analyzes and performs linkage warning between substation equipment.

[0064] Furthermore, the data acquisition module includes a data acquisition unit;

[0065] The data acquisition unit: acquires all substation equipment in the substation, and arranges voiceprint vibration sensors inside the substation equipment, wherein one voiceprint vibration sensor is arranged corresponding to one substation equipment; stores the operation voiceprint data of the substation equipment collected by the voiceprint vibration sensor into the substation background monitoring system; retrieves the historical operation data log of the substation equipment from the substation background monitoring system, wherein the historical operation data log includes the operation voiceprint data and operation time period of the substation equipment during historical operation, divides the operation time period evenly into several operation time points, constructs an operation time point set, and records the operation time point set corresponding to the nth historical operation as ,in, It represents the i-th running time point corresponding to the n-th running in history, and I represents the total number of running time points.

[0066] Furthermore, the voiceprint drift model construction module includes a voiceprint drift model construction unit;

[0067] The voiceprint drift model construction unit: based on the i-th running time point corresponding to the n-th historical running and running time points The corresponding running voiceprint data is used to build the voiceprint drift model corresponding to the nth historical run. The details are as follows: Traverse to obtain the running voiceprint data corresponding to each running time point, and arrange them in the order of the running time points; normalize the arranged running voiceprint data, and build a voiceprint drift model based on the normalized running voiceprint data, which is recorded as ,in, Indicates the voiceprint drift model corresponding to the nth historical run, Indicates the normalized running time point The corresponding running voiceprint data, I represents the total number of running time points.

[0068] Furthermore, the data matching and difference calculation module includes a data matching unit and a difference calculation unit;

[0069] The data matching unit obtains the current operation time point of the substation equipment and the operation voiceprint data corresponding to the current operation time point, respectively recorded as and ; Obtain the voiceprint drift model corresponding to N historical operations, preset the operation time point matching rule, and extract the current operation time point of the substation equipment from the voiceprint drift model based on the operation time point matching rule The matching running time point; the running time point matching rule is as follows: , then determine the running time point With the current running time point Matches, where Indicates the preset runtime tolerance threshold. Indicates the mth running time point corresponding to the nth running time in history;

[0070] The difference calculation unit: obtains the difference between the current running time point The running voiceprint data corresponding to all the running time points that match, and the current running time point Corresponding running voiceprint data Perform difference comparison and calculate the comprehensive voiceprint difference.

[0071] Furthermore, the similarity calculation and analysis warning module includes a similarity calculation unit and an analysis warning unit;

[0072] The similarity calculation unit: obtains the current running time point The comprehensive difference of all substation equipment in the substation is calculated by using cosine similarity to calculate the comprehensive difference similarity between different substation equipment. A comprehensive difference similarity threshold is preset and all substation equipment with a comprehensive difference similarity greater than or equal to the comprehensive difference similarity threshold is marked as similar equipment.

[0073] The analysis and early warning unit: based on the comprehensive difference , preset comprehensive difference threshold, if the comprehensive difference If it is greater than or equal to the comprehensive difference threshold, it is determined that the substation equipment has a voiceprint drift abnormality at the current operating time point, that is, the substation equipment has an operating status abnormality at the current operating time point, and a unified early warning is issued for equipment similar to the substation equipment; the operating voiceprint data of the substation equipment at the operating time point is obtained in real time, and the operating status of all substation equipment in the substation is dynamically monitored.

[0074] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0075] Finally, it should be noted that the above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art will be able to modify the technical solutions described in the aforementioned embodiments or substitute equivalents for some of the technical features. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. A method for monitoring the operating status of substation equipment based on voiceprint recognition, characterized in that: The method comprises the following steps: Step S1: Obtain the historical operation voiceprint data and operation time period of all substation equipment in the substation, and construct an operation time point set; Step S2: constructing a voiceprint drift model based on the running time point and the running voiceprint data corresponding to the running time point; Step S3: Obtain the current operating time point of the substation equipment and the operating voiceprint data corresponding to the current operating time point; obtain the operating voiceprint data corresponding to all operating time points that match the current operating time point, and calculate the comprehensive voiceprint difference; Step S4: Obtain the comprehensive difference of all substation equipment in the current operation time point, calculate the comprehensive difference similarity between different substation equipment, preset thresholds, analyze and perform linkage warning between substation equipment; The specific implementation process of step S2 includes: Based on the RT of the i-th running time point corresponding to the n-th historical running time i and running time point RT i The corresponding running voiceprint data is used to build the voiceprint drift model corresponding to the nth historical run, as follows: STP n Traverse to obtain the running voiceprint data corresponding to each running time point, and arrange them in the order of running time points; Normalize the arranged running voiceprint data, and build a voiceprint drift model based on the normalized running voiceprint data, which is recorded as PM n ={[RT i ,RVP(RT i )]|i∈[1,I]}, where PM n Indicates the voiceprint drift model corresponding to the nth historical run, RVP(RT i ) represents the normalized running time point RT i The corresponding running voiceprint data, I represents the total number of running time points; The specific implementation process of step S3 includes: Get the current operation time point of the substation equipment and the operation voiceprint data corresponding to the current operation time point, respectively recorded as RT cur and RVP(RT cur ); obtain the voiceprint drift model corresponding to the N historical operations, preset the operation time point matching rule, and extract the current operation time point RT of the substation equipment from the voiceprint drift model based on the operation time point matching rule. cur Matching runtime point; the runtime point matching rule is as follows: if |RT m -RT cur |≤δ, then determine the running time point RT m and the current running time point RT cur Match, where δ represents the preset runtime tolerance threshold, RT m Indicates the mth running time point corresponding to the nth running time in history; Get the current running time point RT cur The running voiceprint data corresponding to all the running time points that match, and the current running time point RT cur Corresponding running voiceprint data RVP(RT cur ) to compare the difference and calculate the comprehensive voiceprint difference. The calculation formula is as follows: Where ΔCV cur Indicates the comprehensive difference, M indicates the difference from the current running time point RT cur The total number of running voiceprint data corresponding to all matching running time points, RVP (RT m ) represents the running time point RT m The corresponding running voiceprint data, λ represents the preset exponential decay factor.

2. The method for monitoring the operating status of substation equipment based on voiceprint recognition according to claim 1 is characterized in that: The specific implementation process of step S1 includes: Obtain all substation equipment in the substation and deploy voiceprint vibration sensors inside the substation equipment, where one voiceprint vibration sensor is deployed for each substation equipment; store the operating voiceprint data of the substation equipment collected by the voiceprint vibration sensor into the substation background monitoring system; The historical operation data log of the substation equipment is retrieved from the substation background monitoring system. The historical operation data log includes the operation voiceprint data and operation time period of the substation equipment during historical operation. The operation time period is evenly divided into several operation time points, and an operation time point set is constructed. The operation time point set corresponding to the historical n-th operation is recorded as STP n ={RT i |i∈[1,I]}, where RT i It represents the i-th running time point corresponding to the n-th running in history, and I represents the total number of running time points.

3. The method for monitoring the operating status of substation equipment based on voiceprint recognition according to claim 2 is characterized in that: The specific implementation process of step S4 includes: Get the current running time RT cur The comprehensive difference of all substation equipment in the substation is calculated by using cosine similarity to calculate the comprehensive difference similarity between different substation equipment. A comprehensive difference similarity threshold is preset and all substation equipment with a comprehensive difference similarity greater than or equal to the comprehensive difference similarity threshold is marked as similar equipment. Based on the comprehensive difference ΔCV cur , preset comprehensive difference threshold, if comprehensive difference ΔCV cur If the value is greater than or equal to the comprehensive difference threshold, it is determined that the substation equipment has abnormal voiceprint drift at the current operating time point, that is, the substation equipment has abnormal operating status at the current operating time point, and a unified warning is issued for equipment similar to the substation equipment; Acquire the operating voiceprint data of substation equipment at the operating time in real time, and conduct dynamic monitoring of the operating status of all substation equipment in the substation.

4. A substation equipment operating status monitoring system based on voiceprint recognition, which executes a substation equipment operating status monitoring method based on voiceprint recognition as described in any one of claims 1 to 3, characterized in that: The system includes: a data acquisition module, a voiceprint drift model construction module, a data matching and difference calculation module, and a similarity calculation and analysis warning module; The data acquisition module is used to obtain the operation voiceprint data and operation time period of all substation equipment in the substation during historical operation, and to construct an operation time point set; The voiceprint drift model construction module is configured to construct a voiceprint drift model based on the running time point and the running voiceprint data corresponding to the running time point; The data matching and difference calculation module is used to obtain the current operation time point of the substation equipment and the operation voiceprint data corresponding to the current operation time point; obtain the operation voiceprint data corresponding to all operation time points that match the current operation time point, and calculate the comprehensive voiceprint difference; The similarity calculation and analysis warning module: obtains the comprehensive difference of all substation equipment in the current operating time point, calculates the comprehensive difference similarity between different substation equipment, presets a threshold, analyzes and performs linkage warning between substation equipment.

5. The substation equipment operation status monitoring system based on voiceprint recognition according to claim 4 is characterized by: The data acquisition module includes a data acquisition unit; The data acquisition unit: acquires all substation equipment in the substation, and deploys voiceprint vibration sensors inside the substation equipment, wherein one voiceprint vibration sensor is deployed corresponding to one substation equipment; stores the operation voiceprint data of the substation equipment collected by the voiceprint vibration sensor into the substation background monitoring system; retrieves the historical operation data log of the substation equipment from the substation background monitoring system, wherein the historical operation data log includes the operation voiceprint data and operation time period of the substation equipment during historical operation, evenly divides the operation time period into several operation time points, constructs an operation time point set, and records the operation time point set corresponding to the nth historical operation as STP n ={RT i |i∈[1,I]}, where RT i It represents the i-th running time point corresponding to the n-th running in history, and I represents the total number of running time points.

6. The substation equipment operation status monitoring system based on voiceprint recognition according to claim 5 is characterized by: The voiceprint drift model construction module includes a voiceprint drift model construction unit; The voiceprint drift model construction unit: based on the i-th running time point PT corresponding to the n-th historical running i and running time point RT i The corresponding running voiceprint data is used to build the voiceprint drift model corresponding to the nth historical run. The details are as follows: n Traverse to obtain the running voiceprint data corresponding to each running time point, and arrange them in the order of running time points; Normalize the arranged running voiceprint data, and build a voiceprint drift model based on the normalized running voiceprint data, which is recorded as PM n ={[RT i ,RVP(RT i )]|i∈[1,I]}, where PM n Indicates the voiceprint drift model corresponding to the nth historical run, RVP(RT i ) represents the normalized running time point RT i The corresponding running voiceprint data, I represents the total number of running time points.

7. The substation equipment operation status monitoring system based on voiceprint recognition according to claim 6 is characterized by: The data matching and difference calculation module includes a data matching unit and a difference calculation unit; The data matching unit obtains the current operation time point of the substation equipment and the operation voiceprint data corresponding to the current operation time point, respectively denoted as RT cur and RVP(RT cur ); obtain the voiceprint drift model corresponding to the N historical operations, preset the operation time point matching rule, and extract the current operation time point RT of the substation equipment from the voiceprint drift model based on the operation time point matching rule. cur Matching runtime point; the runtime point matching rule is as follows: if |RT m -RT cur |≤δ, then determine the running time point RT m and the current running time point RT cur Match, where δ represents the preset runtime tolerance threshold, RT m Indicates the mth running time point corresponding to the nth running time in history; The difference calculation unit: obtains the difference between the current running time point RT cur The running voiceprint data corresponding to all the running time points that match, and the current running time point RT cur Corresponding running voiceprint data RVP(RT cur ) to compare the differences and calculate the comprehensive voiceprint difference.

8. The substation equipment operation status monitoring system based on voiceprint recognition according to claim 7 is characterized by: The similarity calculation and analysis warning module includes a similarity calculation unit and an analysis warning unit; The similarity calculation unit: obtains the current running time point RT cur The comprehensive difference of all substation equipment in the substation is calculated by using cosine similarity to calculate the comprehensive difference similarity between different substation equipment. A comprehensive difference similarity threshold is preset and all substation equipment with a comprehensive difference similarity greater than or equal to the comprehensive difference similarity threshold is marked as similar equipment. The analysis and early warning unit: based on the comprehensive difference ΔCV cur , preset comprehensive difference threshold, if comprehensive difference ΔCV cur If the value is greater than or equal to the comprehensive difference threshold, it is determined that the substation equipment has abnormal voiceprint drift at the current operating time point, that is, the substation equipment has abnormal operating status at the current operating time point, and a unified warning is issued for equipment similar to the substation equipment; Acquire the operating voiceprint data of substation equipment at the operating time in real time, and conduct dynamic monitoring of the operating status of all substation equipment in the substation.

Images