A power distribution cabinet intelligent early warning system and method based on data analysis

Abstract

The application discloses a power distribution cabinet intelligent early warning system and method based on data analysis, relates to the technical field of intelligent early warning, and mainly has the following scheme: collecting operation state parameter data, state image data, environmental condition data and historical data of each region of a power distribution cabinet; judging whether an operation state is abnormal; when the judgment result is abnormal, generating an early warning instruction one; calculating the expected service life of equipment and judging whether to generate an early warning instruction two; calculating an estimated maintenance time interval and judging whether to generate an early warning instruction three; and when the early warning instruction one, the early warning instruction two and the early warning instruction three are generated, alarming, which is beneficial to reasonably planning a power distribution cabinet renewal cycle, reducing a failure occurrence rate, prolonging the service life of equipment and improving power supply stability.

Description

Technical Field

[0001] This invention relates to the field of intelligent early warning technology, specifically to an intelligent early warning system and method for power distribution cabinets based on data analysis. Background Technology

[0002] With rapid economic development and accelerated industrialization and urbanization, electricity demand continues to grow. Distribution cabinets, as devices for distributing and controlling electricity, play a crucial role in various industrial, commercial, and residential sectors. They are responsible for distributing electrical energy from the grid to different electrical devices and for protecting and controlling circuits; their safe operation is directly related to the safety of personnel and equipment. A malfunction in a distribution cabinet can disrupt production, daily life, and social order. Therefore, improving the reliability and safety of distribution cabinets has become a top priority. Traditional distribution cabinet monitoring relies mainly on manual inspections and periodic maintenance. This method has long inspection cycles, is prone to missed inspections and misjudgments, and struggles with real-time monitoring. With the development of intelligent manufacturing, intelligentization has become the development trend for distribution cabinet early warning systems. Summary of the Invention

[0003] (a) Technical problems to be solved

[0004] To address the shortcomings of existing technologies, this invention provides a data analysis-based intelligent early warning system and method for power distribution cabinets, which collects operational status parameter data from various areas of the power distribution cabinet. The system collects status image data, environmental condition data, and historical data; it determines whether any abnormalities have occurred in the operating status, and generates an early warning command when the determination result is abnormal. Expected lifespan of computing equipment And based on the expected service life of the equipment Determine whether to generate a warning instruction 2 ; Calculate the estimated maintenance interval Based on the estimated maintenance interval and baseline maintenance time interval Determine whether to generate an early warning instruction (3) Generate early warning command 1 Warning Instruction 2 and warning instructions three It can issue alarms in real time, solving the problems of difficulty in real-time monitoring, high missed detection rate and false judgment rate, and low detection efficiency.

[0005] (II) Technical Solution

[0006] To achieve the above objectives, the present invention provides the following technical solution: an intelligent early warning system for power distribution cabinets based on data analysis, comprising:

[0007] The data acquisition module is used to acquire the operating status parameter data of each area of ​​the power distribution cabinet. Status image data, environmental condition data, and historical data; among which, For real-time data collection The first region The first running status parameter One data point; These are the serial numbers for different regions. i These are the serial numbers for different types of operating status parameters. This refers to the sequence number of the data collection period;

[0008] The data judgment module is used to calculate the running status parameter data. Normal state threshold According to the normal state threshold Determine running status parameter data Is there any anomaly? If abnormal data is detected, calculate the operating status parameter data per unit time starting from the current time. Percentage of abnormal data Preset abnormal threshold Based on the percentage of abnormal data and abnormal threshold Determine if any abnormalities have occurred in the operational status; if the determination result is abnormal, generate an early warning command. ;

[0009] The data analysis module uses status image data, environmental control data, and initial service life data. Expected lifespan of computing devices And based on the expected service life of the equipment Determine whether to generate a warning instruction 2 ; estimate maintenance intervals by calculating historical data Based on the estimated maintenance interval and baseline maintenance time interval Determine whether to generate an early warning instruction (3) ;

[0010] The early warning module is used to receive early warning commands. Warning Instruction 2 and warning instructions three And alarms were triggered separately.

[0011] In the preferred scheme of the above-mentioned intelligent early warning system for distribution cabinets based on data analysis: normal state threshold The value is Among them, the minimum value of the calculation parameter is calculated. The formula used is:

[0012]

[0013] in, It is the first i The minimum value of each running status parameter; It is the first i The rated values ​​of each operating status parameter; This is the fluctuation ratio coefficient, with a value ranging from 0.05 to 0.1;

[0014] Calculate the maximum value of the parameter The formula used is:

[0015]

[0016] in, It is the first i The maximum value of each running status parameter.

[0017] In the preferred embodiment of the above-mentioned intelligent early warning system for distribution cabinets based on data analysis: the distribution cabinet is divided into... Each region is denoted as [number]. , Real-time collection of operating status parameter data for each area of ​​the power distribution cabinet Determine the running status parameter data The criteria for whether something is abnormal are:

[0018]

[0019] in, , i and All values ​​are positive integers.

[0020] In the preferred scheme of the above-mentioned intelligent early warning system for distribution cabinets based on data analysis: calculate the percentage of abnormal data. The formula used is:

[0021]

[0022] in, For the first The first region The percentage of abnormal data for each running status parameter; unit of time The first internal collection The first region The number of data points whose operating status parameters exceed the normal state threshold, with values ​​being positive integers; unit of time The first internal collection The first region The total number of running status parameter data, with values ​​taking positive integers;

[0023] The criteria for determining whether an abnormality has occurred in the operating status are as follows:

[0024]

[0025] in, For the first The first region Abnormal thresholds for each running status parameter.

[0026] In the preferred embodiment of the above-mentioned intelligent early warning system for distribution cabinets based on data analysis: the estimated service life of the equipment is calculated. The method is as follows:

[0027] Status image data includes pixel deviation rate of worn areas. Wear texture entropy value The fuzzy value associated with wear ; Calculate the equipment wear coefficient using status image data The formula used is:

[0028]

[0029] in, Equipment No. n The wear coefficient for each area ranges from 0 to 1. For the first n Each region in a unit period Inner Pixel deviation rate of the images; For the first n Each region in a unit period Inner The wear texture entropy value of the image; For the first n Each region in a unit period Inner The blurriness of the image; For a unit period The total number of images captured internally, with a value that is a positive integer; Pixel deviation rate in the worn area The weighting coefficients range from 0.2 to 0.5. entropy value of wear texture The weighting coefficients range from 0.3 to 0.6. Wear-related fuzzy value The weighting coefficients range from 0.2 to 0.6; and 1;

[0030] Calculate environmental impact factors The formula used is:

[0031]

[0032] Among them, environmental impact factors The value ranges from 0 to 1; For a unit period Internal and external environmental temperature data sequences; For a unit period Internal and external environmental humidity data series;

[0033] Based on the degree of equipment wear and environmental impact factors Calculate the impact coefficient of equipment lifespan The formula used is:

[0034]

[0035] Among them, the equipment lifespan impact coefficient The value ranges from 0 to 1;

[0036] Preset initial service life Based on the equipment lifespan impact coefficient and initial service life Expected lifespan of computing devices The formula used is:

[0037] .

[0038] In the preferred scheme of the above-mentioned intelligent early warning system for distribution cabinets based on data analysis: determine whether to generate an early warning command. The specific standards are as follows:

[0039]

[0040] in, Initial service life The adjustment factor, which varies with usage time, ranges from 0.2 to 0.6.

[0041] In the preferred scheme of the above-mentioned intelligent early warning system for distribution cabinets based on data analysis: calculating the estimated maintenance interval. The method is as follows:

[0042] Historical data must include at least fault data, which includes detection cycles. and number of failures Calculate the fault frequency adjustment factor based on the fault data. The formula used is:

[0043]

[0044] in, For the detection cycle The number of times a fault occurred; This is an adjustment factor for the fault frequency, with a value ranging from 0.2 to 0.5;

[0045] Historical data also includes equipment performance status indicators, which include testing cycles. Short-circuit current withstand capability during the first statistical analysis Power factor and the short-circuit current withstand capability at the time of the last statistical analysis Power factor Calculate the equipment aging adjustment factor based on performance status index data. The formula used is:

[0046]

[0047] in, The weighting coefficient for short-circuit current withstand capability ranges from 0.3 to 0.6. This is the weighting coefficient for the power factor, with a value ranging from 0.4 to 0.7; and =1;

[0048] Historical data also includes overload time data, which includes at least the detection cycle. Total overload time within Based on the total overload time Calculate the overload time adjustment factor The formula used is:

[0049]

[0050] in, The sum of overload times The adjustment factor ranges from 0.3 to 0.7.

[0051] Obtain the baseline maintenance interval from historical data. and based on the baseline maintenance interval Fault frequency adjustment factor Equipment aging adjustment factor and overload time adjustment factor Calculate the estimated maintenance interval The formula used is:

[0052] .

[0053] In the preferred scheme of the above-mentioned intelligent early warning system for distribution cabinets based on data analysis: whether or not an early warning command is generated. The basis for judgment is:

[0054]

[0055] in, Baseline maintenance time interval The adjustment factor, which varies over time, ranges from 0.2 to 0.6.

[0056] In the preferred scheme of the above-mentioned intelligent early warning system for distribution cabinets based on data analysis: upon receiving an early warning signal... When an abnormality occurs, the red warning light is activated to sound an alarm, and the abnormal operating parameter data and the time of the abnormality are recorded. At the same time, real-time acquisition of external and internal images of the power distribution cabinet begins, and the image data of the triggered warning area is sent to the display terminal in the duty room.

[0057] Received warning signal 2 When this occurs, the green warning light will be activated to sound an alarm, and intermittent operation will be adopted to reduce equipment load and increase maintenance frequency;

[0058] When the warning instruction three is received When necessary, activate the yellow warning light to sound an alarm, initiate temporary maintenance, record equipment information, maintenance history, and fault records, and establish a maintenance information file based on the estimated maintenance interval. Adjust the maintenance cycle.

[0059] This invention also discloses a data analysis-based intelligent early warning method for power distribution cabinets, used to implement the aforementioned intelligent early warning system, comprising the following steps:

[0060] Obtain operating status parameter data for each area of ​​the power distribution cabinet. Status image data, environmental condition data, and historical data; among which, For real-time data collection The first region The first running status parameter One data point; These are the serial numbers for different regions. i These are the serial numbers for different types of operating status parameters. The sequence number of the running status parameter value;

[0061] Calculate running status parameter data Normal state threshold According to the normal state threshold Determine running status parameter data Is there any anomaly? If abnormal data is detected, calculate the operating status parameter data per unit time starting from the current time. Percentage of abnormal data Preset abnormal threshold Based on the percentage of abnormal data and abnormal threshold Determine if any abnormalities have occurred in the operational status; if the determination result is abnormal, generate an early warning command. ;

[0062] Based on status image data, environmental conditioning data, and initial service life Expected lifespan of computing devices And determine whether to generate a warning instruction 2. ; estimate maintenance intervals by calculating historical data Based on the estimated maintenance interval and baseline maintenance time interval Determine whether to generate an early warning instruction (3) ;

[0063] Receive early warning instruction 1 Warning Instruction 2 and warning instructions three And alarms were triggered separately.

[0064] (III) Beneficial Effects

[0065] This invention provides a data analysis-based intelligent early warning system and method for power distribution cabinets, which has the following beneficial effects:

[0066] (1) Real-time acquisition of operating status parameter data for each area of ​​the distribution cabinet. Status image data, environmental condition data, and historical data can quickly locate fault areas, providing decision support for the maintenance and management of power distribution cabinets;

[0067] (2) Calculate the estimated service life of the equipment This helps to rationally plan the replacement cycle of power distribution cabinets and avoid performance degradation and safety hazards caused by equipment aging.

[0068] (3) By calculating the estimated maintenance interval It can help staff adjust maintenance plans, which is beneficial for extending equipment life, reducing failure rate, and lowering maintenance costs;

[0069] (4) The early warning module receives an early warning command. Warning Instruction 2 Warning Instruction Three They also trigger alarms, enabling rapid response to faults and improving maintenance efficiency and power supply reliability. Attached Figure Description

[0070] Figure 1 This is a schematic diagram of the system composition of the intelligent early warning system for power distribution cabinets based on data analysis according to the present invention; Detailed Implementation

[0071] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0072] Please see Figure 1 This invention provides a data analysis-based intelligent early warning system for power distribution cabinets, comprising:

[0073] The data acquisition module is used to acquire the operating status parameter data of each area of ​​the power distribution cabinet. Status image data, environmental condition data, and historical data.

[0074] Specifically, the distribution cabinets are divided into categories based on their dimensions. Each region is denoted as [number]. , ; For real-time data collection The first region The first running status parameter One data point; These are the serial numbers for different regions. i These are the serial numbers for different types of operating status parameters. This is the sequence number of the number of times the data was collected; the operating status parameters include at least voltage, current, resistance, power, internal temperature, internal humidity, external ambient temperature, and external ambient humidity, with each parameter corresponding to a sequence number; The sequence number is used to indicate the number of times data is collected. Data is collected several times within a unit of time, and the parameters collected each time are numbered.

[0075] In the above solution, data collection through a data acquisition module can improve collection efficiency and data accuracy, while reducing labor costs.

[0076] The data judgment module is used to calculate the running status parameter data. Normal state threshold According to the normal state threshold Determine running status parameter data Is there any anomaly? If abnormal data is detected, calculate the operating status parameter data per unit time starting from the current time. Percentage of abnormal data Preset abnormal threshold Based on the percentage of abnormal data and abnormal threshold Determine if any abnormalities have occurred in the operational status; if the determination result is abnormal, generate an early warning command. ;

[0077] Specifically, the normal state threshold The value is Among them, the minimum value of the calculation parameter is calculated. The formula used is:

[0078]

[0079] in, It is the first i The minimum value of each running status parameter. i It is a positive integer; It is the first i The rated values ​​of each operating status parameter are determined by the design specifications of the distribution cabinet; This is the fluctuation ratio coefficient, with a value ranging from 0.05 to 0.1, determined based on industry standards and practical experience.

[0080] Calculate the maximum value of the parameter The formula used is:

[0081]

[0082] in, It is the first i The maximum value of each running status parameter.

[0083] Specifically, it involves judging the running status parameter data. The criteria for whether something is abnormal are:

[0084]

[0085] Specifically, calculating the percentage of outlier data The formula used is:

[0086]

[0087] Among them, unit time Determined based on data collection frequency;

[0088] The criteria for determining whether an abnormality has occurred in the operating status are as follows:

[0089]

[0090] in, For the first The first region The abnormal threshold for each operating status parameter is determined based on the equipment stability requirements.

[0091] In the above scheme, the percentage of abnormal data is calculated. This can improve the accuracy of judgment results, avoid the problem of false warnings caused by occasional data anomalies, and improve operation and maintenance efficiency and energy utilization.

[0092] The data analysis module uses status image data, environmental control data, and initial service life data. Expected lifespan of computing devices And determine whether to generate a warning instruction 2. ; estimate maintenance intervals by calculating historical data Based on the estimated maintenance interval and baseline maintenance time interval Determine whether to generate an early warning instruction (3) ;

[0093] Specifically, the expected lifespan of computing devices The method is as follows:

[0094] Status image data includes pixel deviation rate of worn areas. Wear texture entropy value The fuzzy value associated with wear .

[0095] Pixel deviation rate in worn areas By extracting mask technology, easily worn parts (such as circuit breaker contacts, busbar connectors, etc.) are accurately delineated. Then, pixel statistics tools (such as the "Pixel Statistics" module of industrial vision software VisionMaster) are used to collect a large number of pixel values ​​of unworn parts to establish a normal range. The proportion of "pixels outside the normal range" to the total number of pixels is counted as the pixel deviation rate of the worn area. The calculation method for this parameter is a known deviation rate calculation method.

[0096] Wear texture entropy By filtering the "Uniform Pattern" of Local Binary Pattern (LBP), normal textures from when the parts leave the factory are excluded. For the filtered wear texture areas, the entropy value is calculated using the Gray-Level Co-occurrence Matrix (GLCM) to quantify the degree of disorder of the texture. The calculation method for this parameter is a known entropy value calculation method.

[0097] Wear-related fuzzy value Image sharpness is assessed using the variance of the Laplacian operator; the smaller the variance, the more severe the blurring, which serves as the wear-related blur value. Frequency domain analysis (FFT) or motion blur kernel (PSF) is used to screen for "motion blur caused by loose parts" and "defocus blur caused by lens contamination." This parameter is calculated using a known method for calculating blur values.

[0098] Calculate the equipment wear coefficient using status image data. The formula used is:

[0099]

[0100] in, Equipment No. n The wear coefficient for each area ranges from 0 to 1. For the first n Each region in a unit period Inner Pixel deviation rate of the images; For the first n Each region in a unit period Inner The wear texture entropy value of the image; For the first n Each region in a unit period Inner The blurriness of the image; For a unit period The total number of images captured internally, with a value that is a positive integer; Pixel deviation rate in the worn area The weighting coefficients range from 0.2 to 0.5. entropy value of wear texture The weighting coefficients range from 0.3 to 0.6. Wear-related fuzzy value The weighting coefficients range from 0.2 to 0.6; and 1;

[0101] Calculate environmental impact factors The formula used is:

[0102]

[0103] Among them, environmental impact factors The value ranges from 0 to 1; For a unit period Internal and external environmental temperature data sequences; For a unit period Internal and external environmental humidity data series;

[0104] Based on the degree of equipment wear and environmental impact factors Calculate the impact coefficient of equipment lifespan The formula used is:

[0105]

[0106] Among them, the equipment lifespan impact coefficient The value ranges from 0 to 1;

[0107] Preset initial service life Based on the equipment lifespan impact coefficient and initial service life Expected lifespan of computing devices The formula used is:

[0108]

[0109] Among them, initial service life Obtain from the equipment maintenance manual.

[0110] Specifically, it determines whether to generate a warning instruction. The specific standards are as follows:

[0111]

[0112] in, Initial service life The adjustment factor, which varies with usage time, ranges from 0.2 to 0.6 and is determined based on the equipment's usage time.

[0113] Specifically, calculating the estimated maintenance interval The method is as follows:

[0114] Historical data must include at least fault data, which includes detection cycles. and number of failures Calculate the fault frequency adjustment factor based on the fault data. The formula used is:

[0115]

[0116] It should be noted that the fault frequency adjustment factor This reflects the impact of failure frequency on maintenance intervals; the higher the failure frequency, the higher the failure frequency adjustment factor. The smaller the value, the shorter the maintenance interval; among them, For the detection cycle Number of times a fault occurs within a period of time; inspection cycle Determined based on the intensity of equipment use; This is an adjustment factor for the fault frequency, with a value ranging from 0.2 to 0.5, determined based on historical fault frequencies.

[0117] Historical data also includes equipment performance status indicators, which include testing cycles. Short-circuit current withstand capability during the first statistical analysis Power factor and the short-circuit current withstand capability at the time of the last statistical analysis Power factor Calculate the equipment aging adjustment factor based on performance status index data. The formula used is:

[0118]

[0119] It should be noted that this formula calculates the detection cycle. The rate of change of internal short-circuit current withstand capability and the rate of change of power factor are used to obtain the equipment aging adjustment factor. Equipment aging adjustment factor This reflects the impact of equipment aging on maintenance intervals and inspection cycles. The greater the rate of change in internal short-circuit current withstand capability and the rate of change in power factor, the more severe the equipment aging. Equipment aging adjustment factor The smaller the value, the shorter the maintenance interval; among which, The weighting coefficient for short-circuit current withstand capability is 0.3 to 0.6, and is determined based on the degree of influence of short-circuit current withstand capability on equipment performance status indicators. This is the weighting coefficient for the power factor, with a value ranging from 0.4 to 0.7, determined based on the degree of influence of the power factor on equipment performance indicators; and =1;

[0120] Historical data also includes overload time data, which includes at least the detection cycle. Total overload time within Based on the total overload time Calculate the overload time adjustment factor The formula used is:

[0121]

[0122] It should be noted that the overload time adjustment factor This reflects the impact of overload time on maintenance intervals; the longer the total overload time, the higher the overload time adjustment factor. The smaller the value, the shorter the maintenance interval; among them, The sum of overload times The adjustment factor, ranging from 0.3 to 0.7, is determined based on the importance of overload time to the equipment maintenance cycle.

[0123] Obtain the baseline maintenance interval from historical data. and based on the baseline maintenance interval Fault frequency adjustment factor Equipment aging adjustment factor and overload time adjustment factor Calculate the estimated maintenance interval The formula used is:

[0124]

[0125] Among them, the benchmark maintenance time interval Determined according to the maintenance standards for distribution cabinets.

[0126] Specifically, whether to generate a warning instruction three The basis for judgment is:

[0127]

[0128] in, Baseline maintenance time interval The adjustment factor, which varies over time, ranges from 0.2 to 0.6 and is determined based on the equipment's usage time.

[0129] In the above scheme, the expected service life of the equipment is calculated. This helps staff understand the operating status of equipment, which is beneficial for rationally planning the replacement cycle of power distribution cabinets and avoiding performance degradation and safety hazards caused by equipment aging; it also helps calculate and estimate maintenance intervals. It can help staff adjust maintenance plans, improve maintenance efficiency, ensure power supply, reduce failure rate, and lower maintenance costs.

[0130] The early warning module is used to receive early warning commands. Warning Instruction 2 and warning instructions three And each of them will trigger an alarm;

[0131] Specifically, upon receiving a warning signal When an abnormality occurs, a red warning light is activated to sound an alarm, and the abnormal operating parameters and the time of occurrence are recorded. At the same time, the cameras installed inside and outside the distribution cabinet are controlled to start collecting real-time images of the cabinet's exterior and interior, and the image data that triggers the alarm is sent to the display terminal in the duty room. This provides the duty personnel with a real-time observation perspective to understand whether there are any abnormalities such as short circuits, smoke, or fires.

[0132] Received warning signal 2 When this occurs, the green warning light will be activated to sound an alarm, and intermittent operation will be adopted to reduce equipment load and increase maintenance frequency;

[0133] When the warning instruction three is received When necessary, activate the yellow warning light to sound an alarm, initiate temporary maintenance, record equipment information, maintenance history, and fault records, and establish a maintenance information file based on the estimated maintenance interval. Adjust the maintenance cycle.

[0134] In the above solution, by numbering different areas, the collected data is distinguished according to the area number. When an anomaly is detected in the data of any area, the abnormal area can be quickly located according to the area number of the data. Based on different warning signals, staff can be helped to determine the type of fault, thereby improving maintenance efficiency.

[0135] On the other hand, the present invention also discloses a method for intelligent early warning of power distribution cabinets based on data analysis, used to implement the above-mentioned intelligent early warning system, comprising the following steps:

[0136] Obtain operating status parameter data for each area of ​​the power distribution cabinet. Status image data, environmental condition data, and historical data;

[0137] Calculate running status parameter data Normal state threshold Determine the running status parameter data. Is there any anomaly? If abnormal data is detected, calculate the operating status parameter data per unit time starting from the current time. Percentage of abnormal data Preset abnormal threshold Based on the percentage of abnormal data and abnormal threshold Determine if any abnormalities have occurred in the operational status; if the determination result is abnormal, generate an early warning command. ;

[0138] Based on status image data, environmental conditioning data, and initial service life Expected lifespan of computing devices And determine whether to generate a warning instruction 2. ; estimate maintenance intervals by calculating historical data Based on the estimated maintenance interval and baseline maintenance time interval Determine whether to generate an early warning instruction (3) ;

[0139] Receive early warning instruction 1 Warning Instruction 2 Warning Instruction Three And alarms were triggered separately.

[0140] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented in software, the above embodiments can be implemented, in whole or in part, as a computer program product. Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution.

[0141] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0142] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

Claims

1. A data analysis-based intelligent early warning system for power distribution cabinets, characterized in that: include: The data acquisition module is used to acquire the operating status parameter data of each area of ​​the power distribution cabinet. Status image data, environmental condition data, and historical data; among which, For real-time data collection The first region The first running status parameter One data point; These are the serial numbers for different regions. i These are the serial numbers for different types of operating status parameters. This is the sequence number of the number of times data was collected; The data judgment module is used to calculate the running status parameter data. Normal state threshold According to the normal state threshold Determine running status parameter data Is there any anomaly? If abnormal data is detected, calculate the operating status parameter data per unit time starting from the current time. Percentage of abnormal data Preset abnormal threshold Based on the percentage of abnormal data and abnormal threshold Determine if any abnormalities have occurred in the operational status; if the determination result is abnormal, generate an early warning command. ; The data analysis module uses status image data, environmental control data, and initial service life data. Expected lifespan of computing devices And based on the expected service life of the equipment Determine whether to generate the first Warning instructions corresponding to each region ; estimate maintenance intervals by calculating historical data Based on the estimated maintenance interval and baseline maintenance time interval Determine whether to generate an early warning instruction (3) ; The early warning module is used to receive early warning commands. Warning Instruction 2 and warning instructions three And alarms were triggered separately.

2. The intelligent early warning system for power distribution cabinets based on data analysis according to claim 1, characterized in that: Normal state threshold The value is Among them, the minimum value of the calculation parameter is calculated. The formula used is: in, It is the first i The minimum value of each running status parameter; It is the first i The rated values ​​of each operating status parameter; This is the fluctuation ratio coefficient, with a value ranging from 0.05 to 0.1; Calculate the maximum value of the parameter The formula used is: in, It is the first i The maximum value of each running status parameter.

3. The intelligent early warning system for power distribution cabinets based on data analysis according to claim 2, characterized in that: The distribution cabinet is divided into Each region is denoted as [number]. , Real-time collection of operating status parameter data for each area of ​​the power distribution cabinet Determine the running status parameter data The criteria for whether something is abnormal are: in, , i and All values ​​are positive integers.

4. The intelligent early warning system for power distribution cabinets based on data analysis according to claim 3, characterized in that: Calculate the percentage of outlier data The formula used is: in, For the first The first region The percentage of abnormal data for each running status parameter; unit of time The first internal collection The first region The number of data points whose operating status parameters exceed the normal state threshold, with values ​​being positive integers; unit of time The first internal collection The first region The total number of running status parameter data, with values ​​taking positive integers; The criteria for determining whether an abnormality has occurred in the operating status are as follows: in, For the first The first region Abnormal thresholds for each running status parameter.

5. The intelligent early warning system for power distribution cabinets based on data analysis according to claim 4, characterized in that: Expected lifespan of computing devices The method is as follows: Status image data includes pixel deviation rate of worn areas. Wear texture entropy value The fuzzy value associated with wear ; Calculate the equipment wear coefficient using status image data The formula used is: in, Equipment No. n The wear coefficient for each area ranges from 0 to 1. For the first n Each region in a unit period Inner Pixel deviation rate of the images; For the first n Each region in a unit period Inner The wear texture entropy value of the image; For the first n Each region in a unit period Inner The blurriness of the image; For a unit period The total number of images captured internally, with a value that is a positive integer; Pixel deviation rate in the worn area The weighting coefficients range from 0.2 to 0.

5. entropy value of wear texture The weighting coefficients range from 0.3 to 0.

6. Wear-related fuzzy value The weighting coefficients range from 0.2 to 0.6; and 1; Calculate environmental impact factors The formula used is: Among them, environmental impact factors The value ranges from 0 to 1; For a unit period Internal and external environmental temperature data sequences; For a unit period Internal and external environmental humidity data series; Based on the degree of equipment wear and environmental impact factors Calculate the impact coefficient of equipment lifespan The formula used is: Among them, the equipment lifespan impact coefficient The value ranges from 0 to 1; Preset initial service life Based on the equipment lifespan impact coefficient and initial service life Expected lifespan of computing devices The formula used is: 。 6. The intelligent early warning system for power distribution cabinets based on data analysis according to claim 5, characterized in that: Determine whether to generate a warning instruction 2 The specific standards are as follows: in, Initial service life The adjustment factor, which varies with usage time, ranges from 0.2 to 0.

6.

7. The intelligent early warning system for distribution cabinets based on data analysis according to claim 6, characterized in that: Calculate the estimated maintenance interval The method is as follows: Historical data must include at least fault data, which includes detection cycles. and number of failures Calculate the fault frequency adjustment factor based on the fault data. The formula used is: in, For the detection cycle The number of times a fault occurred; This is an adjustment factor for the fault frequency, with a value ranging from 0.2 to 0.5; Historical data also includes equipment performance status indicators, which include testing cycles. Short-circuit current withstand capability during the first statistical analysis Power factor and the short-circuit current withstand capability at the time of the last statistical analysis Power factor Calculate the equipment aging adjustment factor based on performance status index data. The formula used is: in, The weighting coefficient for short-circuit current withstand capability ranges from 0.3 to 0.

6. This is the weighting coefficient for the power factor, with a value ranging from 0.4 to 0.7; and =1; Historical data also includes overload time data, which includes at least the detection cycle. Total overload time within Based on the total overload time Calculate the overload time adjustment factor The formula used is: in, The sum of overload times The adjustment factor ranges from 0.3 to 0.

7. Obtain the baseline maintenance interval from historical data. and based on the baseline maintenance interval Fault frequency adjustment factor Equipment aging adjustment factor and overload time adjustment factor Calculate the estimated maintenance interval The formula used is: 。 8. The intelligent early warning system for power distribution cabinets based on data analysis according to claim 7, characterized in that: Should a warning instruction be generated? The basis for judgment is: in, Baseline maintenance time interval The adjustment factor, which varies over time, ranges from 0.2 to 0.

6.

9. The intelligent early warning system for power distribution cabinets based on data analysis according to claim 8, characterized in that: Received warning signal 1 When an abnormality occurs, the red warning light is activated to sound an alarm, and the abnormal operating parameter data and the time of the abnormality are recorded. At the same time, real-time acquisition of external and internal images of the power distribution cabinet begins, and the image data of the triggered warning area is sent to the display terminal in the duty room. Received warning signal 2 When this occurs, the green warning light will be activated to sound an alarm, and intermittent operation will be adopted to reduce equipment load and increase maintenance frequency; When the warning instruction three is received When necessary, activate the yellow warning light to sound an alarm, initiate temporary maintenance, record equipment information, maintenance history, and fault records, and establish a maintenance information file based on the estimated maintenance interval. Adjust the maintenance cycle.

10. A data analysis-based intelligent early warning method for distribution cabinets, used to implement the intelligent early warning system for distribution cabinets according to any one of claims 1-9, characterized in that: Includes the following steps: Obtain operating status parameter data for each area of ​​the power distribution cabinet. Status image data, environmental condition data, and historical data; Calculate running status parameter data Normal state threshold Determine the running status parameter data. Is it abnormal? When abnormal data occurs, the operating status parameter data per unit time is calculated starting from the current time. Percentage of abnormal data Preset abnormal threshold Based on the percentage of abnormal data and abnormal threshold Determine if any abnormalities have occurred in the operational status; if the determination result is abnormal, generate an early warning command. ; Based on status image data, environmental conditioning data, and initial service life Expected lifespan of computing devices And based on the expected service life of the equipment Determine whether to generate a warning instruction 2 ; estimate maintenance intervals by calculating historical data Based on the estimated maintenance interval and baseline maintenance time interval Determine whether to generate an early warning instruction (3) ; Receive early warning instruction 1 Warning Instruction 2 Warning Instruction Three And alarms were triggered separately.

Images