CN116187510A

CN116187510A - Ammeter box fault prediction method, device, computer equipment and storage medium

Info

Publication number: CN116187510A
Application number: CN202211570878.XA
Authority: CN
Inventors: 杨祥勇; 温克欢; 耿博; 钟聪; 吴泽新; 周晓东; 孙文静
Original assignee: Shenzhen Power Supply Bureau Co Ltd
Current assignee: Shenzhen Power Supply Bureau Co Ltd
Priority date: 2022-12-08
Filing date: 2022-12-08
Publication date: 2023-05-30

Abstract

The application relates to an ammeter box fault prediction method, an ammeter box fault prediction device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: acquiring a plurality of groups of historical acquisition data of an ammeter box terminal; based on a plurality of groups of historical acquisition data and an objective function, determining an initial value of a linear change rate threshold parameter and an initial value of an elastic network mixing parameter; determining an initial fault prediction function according to the initial value of the linear change rate threshold parameter, the initial value of the elastic network mixing parameter and the objective function; acquiring current acquisition data of an ammeter box terminal; determining an initial prediction result according to the current acquired data and an initial fault prediction function; based on the initial prediction result, adjusting initial values of the elastic network mixing parameter and the linear change rate threshold value parameter to obtain an adjusted fault prediction function; and determining a fault prediction result of the ammeter box based on the adjusted fault prediction function. By adopting the method, the accuracy of the fault prediction result of the ammeter box can be improved.

Description

Ammeter box fault prediction method, device, computer equipment and storage medium

Technical Field

The present disclosure relates to the field of power detection technologies, and in particular, to a method, an apparatus, a computer device, a storage medium, and a computer program product for predicting a fault of an electric meter box.

Background

The ammeter box is an infrastructure for intensively installing equipment such as an ammeter, a switch, a wire and the like, plays an important role in the transportation and metering of electric power and centralized control and management of the ammeter, and can effectively ensure the safety and convenience of electricity utilization. Because work demands such as electric energy metering in the ammeter case are high to ammeter case terminal frequency of use, but ammeter incasement portion is small, and the environment is complicated, leads to ammeter case terminal to appear ageing easily because of reasons such as work generates heat and external environment, causes serious fire's result such as, influences normal metering of electric energy and energy dispatch, and has the threat to resident life safety. Therefore, accurate pre-judgment is needed for the fault of the ammeter box, and potential safety hazards are found timely.

The traditional ammeter box fault prediction method is mainly used for predicting faults of ammeter boxes according to manual experience by detecting state data of ammeter box terminals. However, the internal environment of the ammeter box is complex, and the existing method for predicting the ammeter box fault according to the manual experience is difficult to adapt to the dynamic environment in the ammeter box, so that the problem of low accuracy of the fault prediction result occurs.

Disclosure of Invention

Based on this, it is necessary to provide an ammeter box fault prediction method, an ammeter box fault prediction device, a computer readable storage medium and a computer program product capable of improving the accuracy of the ammeter box fault prediction result, aiming at the technical problem that the accuracy of the traditional ammeter box fault prediction result is low.

In a first aspect, the present application provides a method for predicting a fault of an electric meter box. The method comprises the following steps:

acquiring a plurality of groups of historical acquisition data of an ammeter box terminal;

determining an initial value of the linear change rate threshold parameter and an initial value of the elastic network mixing parameter based on a plurality of groups of historical acquisition data and an objective function comprising the linear change rate threshold parameter and the elastic network mixing parameter; determining an initial fault prediction function according to the initial value of the linear change rate threshold parameter, the initial value of the elastic network mixing parameter and the objective function;

acquiring current acquisition data of an ammeter box terminal;

determining an initial prediction result according to the current acquired data and an initial fault prediction function; based on the initial prediction result, adjusting initial values of the elastic network mixing parameter and the linear change rate threshold value parameter to obtain an adjusted fault prediction function;

And determining a fault prediction result of the ammeter box based on the adjusted fault prediction function.

In one embodiment, obtaining current acquisition data of the electricity meter box terminal includes:

collecting real-time data of the ammeter box terminal at each moment in a preset time period;

acquiring real-time data of each moment in a preset time length, and taking a first linear change rate between the real-time data of the starting moment in the preset time length and the first linear change rate of the ending moment in the preset time length relative to the starting moment as a target change rate;

if the absolute value of the difference value between any first linear change rate and the target change rate is larger than the initial value of the linear change rate threshold parameter, updating real-time data corresponding to the corresponding first linear change rate into preset data;

and determining the current acquisition data based on the updated real-time data.

In one embodiment, based on the initial prediction result, initial values of the elastic network mixing parameter and the linear change rate threshold parameter are adjusted to obtain an adjusted fault prediction function, including:

based on an initial prediction result and an initial value of a linear change rate threshold parameter, adjusting the initial value of an elastic network mixing parameter to obtain a first fault prediction function;

And predicting a first prediction result at the next moment of the cut-off moment according to the first fault prediction function and the current acquired data, and adjusting the initial value of the linear change rate threshold parameter based on the first prediction result to obtain an adjusted fault prediction function.

In one embodiment, adjusting the initial value of the elastic network hybrid parameter based on the initial prediction result and the initial value of the linear change rate threshold parameter to obtain a first failure prediction function includes:

acquiring a second linear change rate between an initial prediction result and real-time data of a starting moment in a preset duration;

determining an absolute value of a difference between the second linear rate of change and the target rate of change as a rate of change difference;

and if the change rate difference value is larger than the initial value of the linear change rate threshold parameter, adjusting the initial value of the elastic network mixing parameter based on the change rate difference value and the initial value of the linear change rate threshold parameter to obtain a first fault prediction function.

In one embodiment, based on the first prediction result, an initial value of the linear transformation rate threshold parameter is adjusted to obtain an adjusted fault prediction function, including:

determining first prediction sample data based on the current acquired data and a first prediction result, wherein the first prediction sample data is used for predicting data at the next moment of time corresponding to the first prediction result;

Continuing to execute a prediction process based on the first prediction sample data and the first fault prediction function until the number of predictions reaches a first preset number, so as to obtain a first target prediction result of the first prediction number;

respectively acquiring a second linear change rate between each first target prediction result and real-time data of the starting moment in the first prediction sample data;

averaging the second linear change rate corresponding to each first prediction result to obtain an average change rate;

and adjusting the initial value of the linear change rate threshold parameter based on the average change rate and the target change rate to obtain an adjusted fault prediction function.

In one embodiment, determining a fault prediction result of the electric meter box based on the adjusted fault prediction function includes:

determining a second prediction result according to the adjusted fault prediction function and the current acquired data;

determining second predicted sample data based on the current acquired data and a second predicted result;

continuing to execute the prediction process based on the second prediction sample data and the adjusted fault prediction function until the number of predictions reaches a second preset number, so as to obtain a prediction result of the second prediction number;

determining whether the predicted results of the second predicted quantity meet a preset fault condition;

And if the electric meter box faults are satisfied, determining that the fault prediction result of the electric meter box is the electric meter box fault.

In a second aspect, the present application further provides an ammeter box fault prediction apparatus. The device comprises:

the historical data acquisition module is used for acquiring a plurality of groups of historical acquisition data of the ammeter box terminal;

the initial function determining module is used for determining an initial value of the linear change rate threshold parameter and an initial value of the elastic network mixing parameter based on a plurality of groups of historical acquisition data and an objective function comprising the linear change rate threshold parameter and the elastic network mixing parameter; determining an initial fault prediction function according to the initial value of the linear change rate threshold parameter, the initial value of the elastic network mixing parameter and the objective function;

the current data acquisition module is used for acquiring current acquisition data of the ammeter box terminal;

the adjusting function acquisition module is used for determining an initial prediction result according to the current acquired data and the initial fault prediction function; based on the initial prediction result, adjusting initial values of the elastic network mixing parameter and the linear change rate threshold value parameter to obtain an adjusted fault prediction function;

and the result determining module is used for determining the fault prediction result of the electric meter box based on the adjusted fault prediction function.

In a third aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor which when executing the computer program performs the steps of:

acquiring current acquisition data of an ammeter box terminal;

In a fourth aspect, the present application also provides a computer-readable storage medium. The computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:

acquiring current acquisition data of an ammeter box terminal;

In a fifth aspect, the present application also provides a computer program product. The computer program product comprises a computer program which, when executed by a processor, implements the steps of:

Acquiring current acquisition data of an ammeter box terminal;

According to the method, the device, the computer equipment, the storage medium and the computer program product for predicting the fault of the electric meter box, through acquiring multiple groups of historical acquisition data of the terminal of the electric meter box, based on the multiple groups of historical acquisition data and an objective function comprising a linear change rate threshold parameter and an elastic network mixing parameter, an initial value of the linear change rate threshold parameter and an initial value of the elastic network mixing parameter are determined, and an initial fault prediction function is determined according to the initial value of the linear change rate threshold parameter, the initial value of the elastic network mixing parameter and the objective function. The initial fault prediction function determined based on the historical acquisition data can be used for predicting the fault of the ammeter box, and is beneficial to improving the accuracy of a fault prediction result. Acquiring current acquisition data of an ammeter box terminal, and determining an initial prediction result according to the current acquisition data and an initial fault prediction function; and adjusting initial values of the elastic network mixing parameter and the linear change rate threshold parameter based on the initial prediction result to obtain an adjusted fault prediction function. The adjusted fault prediction function is obtained by adjusting initial values of the elastic network mixing parameter and the linear change rate threshold parameter based on an initial prediction result predicted by the initial fault prediction function, and the fault prediction result of the electric meter box is determined based on the adjusted fault prediction function, so that the accuracy of the fault prediction result is further improved.

Drawings

FIG. 1 is an application environment diagram of an ammeter box fault prediction method in one embodiment;

FIG. 2 is a flow chart of a method for predicting failure of an electrical meter box according to one embodiment;

FIG. 3 is a schematic diagram of a sub-process of S203 in one embodiment;

FIG. 4 is a schematic flow chart of the sub-process of S204 in one embodiment;

FIG. 5 is a schematic diagram of a sub-process of S402 in one embodiment;

FIG. 6 is a schematic diagram of a sub-process of S404 in one embodiment;

FIG. 7 is a schematic diagram of a sub-process of S205 in one embodiment;

FIG. 8 is a general flow diagram of a method for predicting failure of an electrical meter box in one embodiment;

FIG. 9 is a schematic diagram of the acquisition step of the current acquisition data in one embodiment;

FIG. 10 is a block diagram of an apparatus for predicting failure of an electrical meter box in one embodiment;

FIG. 11 is an internal block diagram of a computer device in one embodiment.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.

The ammeter box fault prediction method provided by the embodiment of the application can be applied to an application environment shown in fig. 1. Wherein the terminal 102 communicates with the meter box 104 via a network. The method for predicting the fault of the electric meter box provided in the embodiment of the present application may be executed by the terminal 102 or the server alone, or may be executed by the terminal 102 and the server cooperatively, so that the terminal 102 alone performs the following steps: the terminal 102 acquires a plurality of groups of historical acquisition data of an ammeter box terminal; determining an initial value of the linear change rate threshold parameter and an initial value of the elastic network mixing parameter based on a plurality of groups of historical acquisition data and an objective function comprising the linear change rate threshold parameter and the elastic network mixing parameter; determining an initial fault prediction function according to the initial value of the linear change rate threshold parameter, the initial value of the elastic network mixing parameter and the objective function; acquiring current acquisition data of an ammeter box terminal; determining an initial prediction result according to the current acquired data and an initial fault prediction function; based on the initial prediction result, adjusting initial values of the elastic network mixing parameter and the linear change rate threshold value parameter to obtain an adjusted fault prediction function; and determining a fault prediction result of the ammeter box based on the adjusted fault prediction function. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, internet of things devices, and portable wearable devices, where the internet of things devices may be smart speakers, smart televisions, smart air conditioners, smart vehicle devices, and the like. The portable wearable device may be a smart watch, smart bracelet, headset, or the like. The server may be implemented as a stand-alone server or as a server cluster composed of a plurality of servers.

In one embodiment, as shown in fig. 2, there is provided an ammeter box fault prediction method, which is illustrated by taking the terminal 102 in fig. 1 as an example, and includes the following steps:

s201, acquiring multiple groups of historical acquisition data of the ammeter box terminals.

The ammeter box terminal refers to a wiring terminal in the ammeter box. The history acquisition data is the history data acquired by the terminal in the history time period. Each set of historical acquisition data comprises at least one historical acquisition data. The type of the historical collected data includes at least one of a voltage flowing through the meter box terminal, a current flowing through the meter box terminal, or a temperature of the meter box terminal. The terminal obtains a plurality of groups of historical acquisition data of the ammeter box terminal through the sensor. Illustratively, multiple sets of historical voltage acquisition data of the electric meter box terminals are obtained through a voltage sensor, multiple sets of historical current acquisition data of the electric meter box terminals are obtained through a current sensor, and multiple sets of historical temperature acquisition data of the electric meter box terminals are obtained through a temperature sensor.

S202, determining an initial value of a linear change rate threshold parameter and an initial value of an elastic network mixing parameter based on a plurality of groups of historical acquisition data and an objective function comprising the linear change rate threshold parameter and the elastic network mixing parameter; and determining an initial fault prediction function according to the initial value of the linear change rate threshold parameter, the initial value of the elastic network mixing parameter and the objective function.

Wherein the objective function is a function for ammeter box fault prediction. The objective function comprises a linear change rate threshold parameter and an elastic network mixing parameter, the terminal respectively inputs each set of historical acquisition data in a plurality of sets of historical acquisition data into the objective function, and an initial value of the linear change rate threshold parameter and an initial value of the elastic network mixing parameter are obtained through solving. And the terminal brings the initial value of the linear change rate threshold parameter obtained by solving and the initial value of the elastic network mixing parameter into the objective function to obtain an initial fault prediction function. The initial fault prediction function is determined based on the historical collected data and the objective function and is used for predicting the fault of the electric meter box.

S203, acquiring current acquisition data of the ammeter box terminal.

The current acquisition data are real-time data of the ammeter box terminal acquired by the terminal in the current time period. The type of the current acquisition data includes at least one type of the types of the historical acquisition data. The terminal obtains current acquisition data of the ammeter box terminal through the sensor.

S204, determining an initial prediction result according to the current acquired data and an initial fault prediction function; and adjusting initial values of the elastic network mixing parameter and the linear change rate threshold parameter based on the initial prediction result to obtain an adjusted fault prediction function.

The terminal determines an initial prediction result according to the current acquired data and the initial fault prediction function. Specifically, the terminal inputs the current collected data into an initial fault prediction function, and the obtained result is used as an initial prediction result. The initial prediction result is prediction data at a time next to the acquisition time of the current acquisition data.

And the terminal adjusts initial values of the elastic network mixing parameter and the linear change rate threshold parameter based on the initial prediction result to obtain the adjusted elastic network mixing parameter and the adjusted linear change rate threshold parameter. And carrying the adjusted elastic network mixing parameter and the adjusted linear change rate threshold parameter into an initial fault prediction function to obtain an adjusted fault prediction function. The adjusted fault prediction function is used for obtaining a fault prediction result of the ammeter box.

S205, determining a fault prediction result of the ammeter box based on the adjusted fault prediction function.

And the terminal adopts the adjusted fault prediction function to conduct fault prediction, so as to obtain prediction data. Illustratively, the terminal performs at least one failure prediction using the adjusted failure prediction function to obtain at least one prediction data. And the terminal performs big data statistics on at least one piece of prediction data, and determines a fault prediction result of the ammeter box based on the at least one piece of prediction data. Optionally, under the condition that at least one of the prediction data is larger than a preset value, the terminal determines that the fault prediction result of the ammeter box is a meter box fault. Or under the condition that the average value of at least one piece of predicted data is larger than the preset average value, the terminal determines that the failure prediction result of the ammeter box is the meter box failure. Or, determining a fault prediction result of the ammeter box based on the median and mode of at least one prediction data.

In the electric meter box fault prediction method, by acquiring multiple groups of historical acquisition data of the electric meter box terminal, based on the multiple groups of historical acquisition data and an objective function comprising a linear change rate threshold parameter and an elastic network mixing parameter, an initial value of the linear change rate threshold parameter and an initial value of the elastic network mixing parameter are determined, and an initial fault prediction function is determined according to the initial value of the linear change rate threshold parameter, the initial value of the elastic network mixing parameter and the objective function. The initial fault prediction function determined based on the historical acquisition data can be used for predicting the fault of the ammeter box, and is beneficial to improving the accuracy of a fault prediction result. Acquiring current acquisition data of an ammeter box terminal, and determining an initial prediction result according to the current acquisition data and an initial fault prediction function; and adjusting initial values of the elastic network mixing parameter and the linear change rate threshold parameter based on the initial prediction result to obtain an adjusted fault prediction function. The adjusted fault prediction function is obtained by adjusting initial values of the elastic network mixing parameter and the linear change rate threshold parameter based on an initial prediction result predicted by the initial fault prediction function, and the fault prediction result of the electric meter box is determined based on the adjusted fault prediction function, so that the accuracy of the fault prediction result is further improved.

In one embodiment, as shown in fig. 3, obtaining current acquisition data of the electricity meter box terminals includes:

s302, collecting real-time data of the ammeter box terminal at each moment in a preset time.

The terminal collects real-time data of the ammeter box terminal at each moment in a preset time through the sensor. The current acquisition data includes at least one real-time data. The terminal collects real-time temperature data of the ammeter box terminal at each moment in a preset time through a temperature sensor. The terminal collects voltage real-time data of the ammeter box terminal at each moment in a preset time through a voltage sensor. The terminal collects current real-time data of the ammeter box terminal at each moment in a preset time through the current sensor.

S304, acquiring real-time data of each moment in the preset time length, and taking the first linear change rate of the cut-off moment in the preset time length relative to the starting moment as a target change rate, wherein the first linear change rate of the real-time data of each moment in the preset time length is relative to the starting moment in the preset time length.

The real-time data of the starting time is real-time data collected at the starting time in each time in the preset duration. The cutoff time is a cutoff time in each time within a preset time period.

The terminal acquires real-time data of each moment in a preset time length, and a first linear change rate between the real-time data of the initial moment in the preset time length is relative to the real-time data of the initial moment in the preset time length. The first linear change rate is used for representing the real-time data change degree of each moment relative to the starting moment in the preset duration. The linear change rate calculation formula is:

wherein, the liquid crystal display device comprises a liquid crystal display device,

representing a first linear rate of change, t ₀ Indicating the starting time t within a preset time period _i Indicating the respective moments within a preset time period, < > and->

Real-time data of the start moment within a preset time length, < >>

And representing real-time data of each moment in the preset time.

The terminal takes a first linear change rate of the cut-off time relative to the starting time in a preset time period as a target change rate, wherein the target change rate can be expressed as:

indicating the target rate of change, t _n Represents a stop time within a preset time period, +.>

Real-time data representing a deadline within a preset duration.

S306, if the absolute value of the difference value between any first linear change rate and the target change rate is larger than the initial value of the linear change rate threshold parameter, updating the real-time data corresponding to the corresponding first linear change rate into preset data; and determining the current acquisition data based on the updated real-time data.

The terminal respectively makes differences between the first linear change rates and the target change rates to obtain at least one difference between the first linear change rates and the target change rates. If the absolute value of the difference value between any first linear change rate and the target change rate is larger than the initial value of the linear change rate threshold parameter, updating the real-time data corresponding to the corresponding first linear change rate into preset data. In some embodiments, the preset data may be data satisfying a linear rate of change requirement in the historical acquisition data.

The terminal determines the current acquisition data based on the updated real-time data. Specifically, the terminal uses updated real-time data and non-updated data in the real-time data of each time acquired in the preset time period as current acquired data.

In this embodiment, by acquiring real-time data of each time of the ammeter box terminal within a preset time period, a first linear change rate corresponding to each time is acquired, the real-time data when the absolute value of the difference value between the first linear change rate and the target change rate is greater than the initial value of the linear change rate threshold parameter is updated to be preset data, and based on the updated real-time data, the current acquired data is determined, so that any data in the current acquired data can be ensured to meet the linear change rate requirement, that is, the absolute value of the difference value between the first linear change rate corresponding to any data in the current acquired data and the target change rate is not greater than the initial value of the linear change rate threshold parameter. Because the aging of the ammeter box terminal is not a sudden process, the change of the current collected data is usually linear, the method for determining the current collected data can remove the data which does not meet the requirement of the linear change rate, avoid the influence of abnormal data collected by the sensor on the fault prediction result, and is beneficial to improving the accuracy of the fault prediction result.

In one embodiment, as shown in fig. 4, based on the initial prediction result, initial values of the elastic network mixing parameter and the linear change rate threshold parameter are adjusted to obtain an adjusted fault prediction function, which includes:

and S402, adjusting the initial value of the elastic network mixing parameter based on the initial prediction result and the initial value of the linear change rate threshold parameter to obtain a first fault prediction function.

In order to improve the accuracy and precision of the fault prediction result, the initial value of the elastic network mixing parameter can be adjusted, so that a first fault prediction function is obtained. In some embodiments, the terminal adjusts the initial value of the elastic network mixing parameter according to the initial prediction result and the initial value of the linear change rate threshold parameter by obtaining a linear change rate of the initial prediction result relative to the current acquired data. And the terminal brings the initial value of the adjusted elastic network mixing parameter into the initial fault prediction function to obtain a first fault prediction function. The first fault function is used for fault prediction of the electricity meter box.

S404, predicting a first prediction result at the next moment of the cut-off moment according to the first fault prediction function and the current acquired data, and adjusting the initial value of the linear change rate threshold parameter based on the first prediction result to obtain an adjusted fault prediction function.

In order to further improve the accuracy and precision of the fault prediction result, the initial value of the linear change rate threshold parameter can be adjusted to obtain an adjusted fault prediction function.

The terminal inputs the current collected data into a first fault prediction function, and the obtained result is a first prediction result. The first prediction result is prediction data of the next moment of the cut-off moment in the preset duration. And the terminal adjusts the initial value of the linear change rate threshold parameter based on the first prediction result to obtain an adjusted fault prediction function. In some embodiments, the terminal predicts a plurality of times based on the first prediction result and the first failure prediction function, adjusts an initial value of the linear change rate threshold parameter based on a linear change rate of a result of the plurality of predictions, and thereby obtains an initial value of the adjusted linear change rate threshold parameter. And bringing the initial value of the adjusted linear change rate threshold parameter into the first fault prediction function to obtain an adjusted fault prediction function.

In this embodiment, the initial value of the elastic network mixing parameter is adjusted through the initial prediction result and the initial value of the linear change rate threshold parameter to obtain a first fault prediction function; and predicting a first prediction result at the next moment of the cut-off moment according to the first fault prediction function and the current acquired data, and adjusting the initial value of the linear change rate threshold parameter based on the first prediction result to obtain an adjusted fault prediction function. The initial value of the elastic network mixing parameter is adjusted based on the initial prediction result and the initial value of the linear change rate threshold parameter, so that the accuracy and precision of the fault prediction result are improved; and the initial value of the linear change rate threshold parameter is adjusted based on the prediction result of the first fault prediction function, so that the accuracy and precision of the fault prediction result are further improved.

In one embodiment, as shown in fig. 5, based on the initial prediction result and the initial value of the linear change rate threshold parameter, the initial value of the elastic network mixing parameter is adjusted to obtain a first fault prediction function, including:

s502, obtaining a second linear change rate between the initial prediction result and real-time data of the initial time within a preset duration.

The terminal brings the initial prediction result and real-time data of the initial time within the preset duration into a linear change rate calculation formula, and the calculated result is used as a second linear change rate. The second linear change rate is used for representing the change degree of the initial prediction result and the real-time data of the starting moment in the preset duration.

S504, an absolute value of a difference between the second linear change rate and the target change rate is determined as a change rate difference value.

The real-time data of the starting time within the preset duration of the terminal is differenced from the target change rate, and the absolute value of the obtained difference value is used as the change rate difference value.

S506, if the change rate difference value is larger than the initial value of the linear change rate threshold parameter, the initial value of the elastic network mixing parameter is adjusted based on the change rate difference value and the initial value of the linear change rate threshold parameter, and a first fault prediction function is obtained.

And the terminal compares the change rate difference value with the initial value of the linear change rate threshold parameter, and if the change rate difference value is larger than the initial value of the linear change rate threshold parameter, adjusts the initial value of the elastic network mixing parameter based on the change rate difference value and the initial value of the linear change rate threshold parameter to obtain a first fault prediction function. Illustratively, the initial values of the elastic network mixing parameters should satisfy the following conditions:

wherein ζ represents an initial value of the elastic network mixing parameter,

representing the difference in rate of change, alpha _max Representing the initial value of the linear rate of change threshold parameter. The initial value of the change rate difference value larger than the linear change rate threshold value parameter indicates that the prediction precision of the initial prediction result is not high, and the initial value of the elastic network mixing parameter can be increased, so that a first fault prediction function is obtained, and the precision of the fault prediction result is improved。

In other embodiments, if the rate of change difference is not greater than the initial value of the linear rate of change threshold parameter, the step of determining an initial prediction result based on the current collected data and the initial fault prediction function is returned to continue the prediction. The prediction precision and accuracy of the initial fault prediction function are high, and parameter adjustment of the initial fault prediction function is not needed.

In this embodiment, by obtaining a change rate difference between a second linear change rate between the initial prediction result and real-time data at the initial time within a preset duration and the target change rate, and adjusting the initial value of the elastic network mixing parameter under the condition that the change rate difference is greater than the initial value of the linear change rate threshold parameter, it is beneficial to obtain the first failure prediction function by adjusting the initial value of the elastic network mixing parameter when the prediction accuracy of the initial prediction function is not high, and to improve the accuracy and precision of the failure prediction result.

In one embodiment, as shown in fig. 6, based on the first prediction result, an initial value of the linear transformation rate threshold parameter is adjusted to obtain an adjusted fault prediction function, including:

s602, determining first prediction sample data based on the current acquired data and a first prediction result, wherein the first prediction sample data is used for predicting data at the next time of the time corresponding to the first prediction result.

The terminal determines first prediction sample data based on the current acquired data and a first prediction result, wherein the first prediction sample data is used for predicting data at the next moment of time corresponding to the first prediction result. For example, the corresponding acquisition time of the current acquisition data is from the first time to the fifth time, the time corresponding to the first prediction result is the sixth time, the first prediction sample data is the data from the second time to the sixth time, and the first prediction sample data is used for predicting the data at the seventh time.

S604, the prediction process is continuously executed based on the first prediction sample data and the first fault prediction function until the number of predictions reaches a first preset number, and a first target prediction result of the first number of predictions is obtained.

The terminal continues to execute the prediction process based on the first prediction sample data and the first fault prediction function until the number of predictions reaches a first preset number, and a first target prediction result of the first number of predictions is obtained. The terminal inputs the first prediction sample data to the first failure prediction function, and the obtained result is used as the prediction data at the seventh moment. The data from the second time to the seventh time are taken as second sample prediction data, the second sample prediction data are input into the first fault prediction function, and the obtained result is taken as prediction data of the eighth time. According to the prediction method, a first target prediction result of the first prediction number is obtained until the prediction times reach the first preset number. The first target prediction result is prediction data obtained by prediction each time.

S606, respectively acquiring a second linear change rate between each first target prediction result and real-time data of the starting moment in the first prediction sample data; and averaging the second linear change rate corresponding to each first prediction result to obtain an average change rate.

The terminal respectively acquires a second linear change rate between each first target prediction result and real-time data of the starting moment in the first prediction sample data for each prediction in the preset times. And carrying real-time data of each first target prediction result and the starting moment in the first prediction sample data into a linear change rate calculation formula to calculate a second linear change rate. And the terminal averages the second linear change rate corresponding to each first prediction result to obtain the average change rate. Illustratively, the average rate of change is calculated as follows:

represents the average change rate, P represents the preset times, t _k Representing the prediction of the kth time in the preset timesEtching the substrate to be etched, wherein the etching is performed,

a first target prediction result, t ', representing the kth time in the preset times' ₀ Representing a starting time within the first predicted sample data,

real-time data of a start time within the first predicted sample data.

And S608, adjusting the initial value of the linear change rate threshold parameter based on the average change rate and the target change rate to obtain an adjusted fault prediction function.

The terminal adjusts the initial value of the linear change rate threshold parameter based on the average change rate and the target change rate to obtain an adjusted fault prediction function. Specifically, the terminal obtains a first difference value between the average change rate and the target change rate, and if the absolute value of the first difference value is smaller than the initial value of the linear change rate threshold parameter, the terminal performs first adjustment on the initial value of the linear change rate threshold parameter according to the average change rate, so as to obtain the adjusted initial value of the linear change rate threshold parameter. And if the absolute value of the first difference value is larger than the initial value of the linear change rate threshold parameter, performing second adjustment on the initial value of the linear change rate threshold parameter according to the average change rate to obtain the adjusted initial value of the linear change rate threshold parameter. Illustratively, the linear threshold adjustment formula is as follows:

Wherein γ represents the adjustment coefficient. And the terminal brings the average change rate and the target change rate into a linear threshold adjustment formula to obtain an initial value of the adjusted linear change rate threshold parameter. And carrying the initial value of the obtained adjusted linear change rate threshold parameter into a first fault prediction function to obtain an adjusted fault prediction function.

In this embodiment, the prediction process is continuously performed by using the first prediction sample data and the first fault prediction function determined based on the current collected data and the first prediction results, so as to obtain a first target prediction result of a first prediction number, and the initial value of the linear change rate threshold parameter is adjusted based on the average change rate and the target change rate determined by the second linear change rate corresponding to each first target prediction result, so as to obtain the adjusted fault prediction function. The average change rate corresponding to the prediction result based on the first fault prediction function adjusts the initial value of the linear change rate threshold parameter, and is beneficial to improving the precision and accuracy of the fault prediction result.

In one embodiment, as shown in fig. 7, determining the fault prediction result of the electric meter box based on the adjusted fault prediction function includes:

S702, determining a second prediction result according to the adjusted fault prediction function and the current acquired data.

The terminal inputs the current collected data into the adjusted fault prediction function, and the obtained result is used as a second prediction result. The second prediction result is used for representing the prediction data of the next moment of the current acquisition data. The second predicted result predicted based on the current acquired data and the second predicted result has a higher accuracy and precision than the initial predicted result.

And S704, determining second prediction sample data based on the current acquired data and a second prediction result.

The terminal determines second prediction sample data based on the current acquired data and a second prediction result. In an exemplary embodiment, the corresponding acquisition time of the current acquired data is from the first time to the fifth time, the time corresponding to the second prediction result is the sixth time, the second prediction sample data is the data from the second time to the sixth time, and the second prediction sample data is used for predicting the data at the seventh time.

S706, the prediction process is continuously executed based on the second prediction sample data and the adjusted fault prediction function until the number of predictions reaches a second preset number, and a prediction result of the second prediction number is obtained.

Referring to the prediction process in S604, the terminal continues to execute the prediction process based on the second prediction sample data and the adjusted fault prediction function until the number of predictions reaches a second preset number, so as to obtain a prediction result of the second prediction number.

S708, determining whether the predicted result of the second predicted quantity meets a preset fault condition; and if the electric meter box faults are satisfied, determining that the fault prediction result of the electric meter box is the electric meter box fault.

The terminal determines whether the predicted results of the second predicted quantity meet a preset fault condition. For example, the predetermined fault condition may be that the predicted outcome is greater than a predetermined threshold. And if each of the predicted results of the second predicted number is greater than a preset threshold, determining that the fault predicted result of the electric meter box is an electric meter box fault.

In this embodiment, a second prediction result is obtained by predicting the adjusted fault prediction function and the current collected data, second prediction sample data is determined, the prediction process is continuously executed based on the second prediction sample data and the adjusted fault prediction function, when the prediction results of the second prediction number meet preset fault conditions, the fault prediction result of the electric meter box is determined to be an electric meter box fault, the accuracy of the fault result of the electric meter box can be ensured, the judgment error caused by the deviation of the primary fault result is avoided, and the accuracy of the fault prediction result is improved.

In one embodiment, determining an initial value of the linear rate of change threshold parameter and an initial value of the elastic network mixing parameter based on the sets of historical acquisition data and an objective function comprising the linear rate of change threshold parameter and the elastic network mixing parameter comprises: aiming at each set of historical acquisition data in a plurality of sets of historical acquisition data, inputting the current set of historical acquisition data into an objective function, and determining an objective fault prediction function corresponding to the current set of historical acquisition data; acquiring the minimum value in the function values of each target fault prediction function based on the target fault prediction function corresponding to each history sample group; and taking the value of the linear change rate threshold parameter corresponding to the minimum value as an initial value of the linear change rate threshold parameter, and taking the value of the elastic network mixing parameter corresponding to the minimum value as an initial value of the elastic network mixing parameter.

The terminal inputs the current historical collection data of each group of historical collection data into the objective function, and determines an objective fault prediction function corresponding to the current historical collection data of each group. And acquiring the minimum value in the function values of each target fault prediction function based on the target fault prediction function corresponding to each history sample group. And taking the value of the linear change rate threshold parameter corresponding to the minimum value as an initial value of the linear change rate threshold parameter, and taking the value of the elastic network mixing parameter corresponding to the minimum value as an initial value of the elastic network mixing parameter. Illustratively, the objective function may be expressed by the following formula:

N represents the number of each group of historical acquisition data, the data corresponding to the deadline in each group of historical acquisition data is used as a predicted value, and other data are used as sample data; beta ₀ A Euclidean distance average value representing the sample data and the predicted value; beta represents the Euclidean distance between the sample data and the predicted value; x is x _i Representing the corresponding acquisition time of each historical acquisition data; y is _i Representing historical acquisition data, namely any one of the acquired terminal temperature, the voltage flowing through the terminal, or the current flowing through the terminal; λ represents a complex coefficient, λ can be obtained through data experiments according to historical experimental experience, and λ controls the degree of penalty, wherein 0 represents no penalty, and infinity represents complete penalty; alpha _max Representing a linear rate of change threshold parameter;

complex parameter adjustment item representing prediction result based on ammeter box fault, and when the prediction result does not meet linear change rate,/or->

Greater than 1, it is necessary to increase the penalty level, increase the influence of each history of collected data on the predicted outcome, when the predicted outcome meets the linear threshold value, the +.>

Less than 1, the penalty degree needs to be reduced, and the interpretation of the objective function is increased; ζ (0.ltoreq.ζ.ltoreq.1) represents an elastic network mixing parameter, controls how much the objective function is ridge regression or Lasso (Least absolute shrinkage and selection operator, minimum absolute reduction and selection operator) regression, ζ equals 0 represents complete ridge regression of the objective function, ζ equals 1 represents complete Lasso regression of the objective function; / >

Representing a ridge regression term; beta _l1 Representing Lasso terms. The ridge regression term is obtained by square root of the sum of squares of the beta corresponding to each sample data, and the Lasso term is the sum of the absolute values of the beta corresponding to each sample data.

In some embodiments, the historical acquisition data for each data type corresponds to an objective function, and the objective function for each data type is the same. The terminal inputs the historical collected data of each data type into the corresponding objective function, so that the corresponding fault prediction function of each data type can be trained, and when the predicted result of the corresponding fault prediction function of each data type meets the fault condition, the terminal determines that the fault prediction result of the ammeter box is ammeter box fault, and the accuracy of the ammeter box fault prediction result can be further improved.

In this embodiment, through multiple sets of historical collected data and an objective function including a linear change rate threshold parameter and an elastic network mixing parameter, a value of the linear change rate threshold parameter corresponding to a minimum value is used as an initial value of the linear change rate threshold parameter, and a value of the elastic network mixing parameter corresponding to the minimum value is used as an initial value of the elastic network mixing parameter, so as to determine an initial fault prediction function, which is favorable for improving accuracy and precision of a fault prediction result.

In one embodiment, to describe the method and effect of predicting the fault of the electric meter box in this embodiment in detail, the following description will describe one of the most detailed embodiments:

the terminal acquires a plurality of groups of historical acquisition data of the ammeter box terminal. The type of the historical collected data includes at least one of a voltage flowing through the meter box terminal, a current flowing through the meter box terminal, or a temperature of the meter box terminal. In some embodiments, the plurality of sets of historical acquisition data record voltages across the terminals of the meter box 5 minutes before the full point in time of normal operation of the meter box for the previous week

Current flowing through the terminals of the ammeter box>

Temperature of ammeter box terminal +.>

The historical acquisition data can be expressed specifically as:

wherein m represents the collected historical collection data of the terminal of the mth electric meter box, t represents the collection time,

to the point of

Historical acquisition data of monday to sunday are respectively represented, taking the historical acquisition data of monday as an example, +.>

The expression is as follows:

in some embodiments, the terminal also obtains multiple sets of fault acquisition data for the electricity meter box terminals. Six month range of fault acquisition data historyThe voltage flowing through the terminal of the meter box every minute within 5 minutes before the terminal of the meter box fails

Current flowing through the terminals of the ammeter box>

Temperature of the terminals of the electric meter box>

I.e. when it is determined that a fault has occurred, data 5 minutes before the fault is extracted from the current collected data as fault collected data.

And determining an initial value of the linear change rate threshold parameter and an initial value of the elastic network mixing parameter based on the plurality of groups of historical acquisition data and an objective function comprising the linear change rate threshold parameter and the elastic network mixing parameter, and determining an initial fault prediction function according to the initial value of the linear change rate threshold parameter, the initial value of the elastic network mixing parameter and the objective function. Illustratively, the objective function may be expressed by the following formula:

Less than 1, the penalty degree needs to be reduced, and the interpretation of the objective function is increased; ζ (0.ltoreq.ζ.ltoreq.1) represents an elastic network mixing parameter, controls how much the objective function is ridge regression or Lasso (Least absolute shrinkage and selection operator, minimum absolute reduction and selection operator) regression, ζ equals 0 represents complete ridge regression of the objective function, ζ equals 1 represents complete Lasso regression of the objective function; />

Fig. 8 is a general flow chart of the method for predicting the fault of the electric meter box. Acquiring current acquisition data of ammeter box terminal. Fig. 9 is a schematic diagram of the acquisition step of the current acquired data. The terminal collects real-time data of the ammeter box terminal at each moment in a preset time. The terminal collects real-time data of each moment in a preset time period and records the voltage of each minute in the past 5 minutes

Current->

Terminal temperature->

Acquiring real-time data of each moment in the preset time length, and taking the first linear change rate of the cut-off moment in the preset time length relative to the starting moment as a target change rate, wherein the first linear change rate is between the real-time data of the starting moment in the preset time length and the real-time data of each moment in the preset time length. If the absolute value of the difference value between any first linear change rate and the target change rate is larger than the initial value of the linear change rate threshold parameter, updating the real-time data corresponding to the corresponding first linear change rate into preset data, and determining the current acquisition data based on the updated real-time data. The linear change rate calculation formula is:

representing a first linear rate of change, t ₀ Indicating the starting time t within a preset time period _i Indicating the respective moments within a preset time period, < > and- >

Real-time data of the start moment within a preset time length, < >>

Representing a preset time periodReal-time data at each instant in time.

The terminal brings the real-time data of each moment in the preset time period and the real-time data of the initial moment in the preset time period into a linear change rate calculation formula to obtain a first linear change rate.

Real-time data representing a deadline within a preset duration. When the absolute value of the difference between the first linear change rate and the target change rate is larger than the initial value of the threshold parameter of the linear change rate, the real-time data deviation of the corresponding moment in the preset time period acquired by the terminal is excessively large. The terminal screens out data meeting the linear change rate requirement from the historical acquisition data as preset data, and replaces real-time data with overlarge deviation with the preset data, so that the current acquisition data is determined. Because the aging of the ammeter box terminal is not a sudden process, the change of the current collected data is usually linear, so that the method for determining the current collected data can remove the data which does not meet the requirement of the linear change rate, avoid the influence of abnormal data collected by the sensor on the fault prediction result, and is beneficial to improving the accuracy of the fault prediction result.

And the terminal determines an initial prediction result according to the current acquired data and the initial fault prediction function. And adjusting initial values of the elastic network mixing parameter and the linear change rate threshold parameter based on the initial prediction result to obtain an adjusted fault prediction function.

And adjusting the initial value of the elastic network mixing parameter based on the initial prediction result and the initial value of the linear change rate threshold parameter to obtain a first fault prediction function. Specifically, the terminal obtains a second linear change rate between the initial prediction result and real-time data of the starting moment in the preset duration. And determining the absolute value of the difference between the second linear change rate and the target change rate as a change rate difference value, and if the change rate difference value is larger than the initial value of the linear change rate threshold parameter, adjusting the initial value of the elastic network mixing parameter based on the change rate difference value and the initial value of the linear change rate threshold parameter to obtain a first fault prediction function. Illustratively, the initial values of the elastic network mixing parameters should satisfy the following conditions:

wherein ζ represents an initial value of the elastic network mixing parameter,

representing the difference in rate of change, alpha _max Representing the initial value of the linear rate of change threshold parameter. The fact that the change rate difference value is larger than the initial value of the linear change rate threshold value parameter indicates that the prediction accuracy of the initial prediction result is not high, and the initial value of the elastic network mixing parameter can be increased, so that a first fault prediction function is obtained, and the accuracy of the fault prediction result is improved.

And according to the first fault prediction function and the current acquired data, predicting to obtain a first prediction result of the next moment of the cut-off moment, and adjusting the initial value of the linear change rate threshold parameter based on the first prediction result to obtain an adjusted fault prediction function. Specifically, first prediction sample data is determined based on the current acquired data and the first prediction result, where the first prediction sample data is used for predicting data at a time next to a time corresponding to the first prediction result. And continuously executing a prediction process based on the first prediction sample data and the first fault prediction function until the number of predictions reaches a first preset number, so as to obtain a first target prediction result of the first predicted number. And respectively acquiring second linear change rates between each first target prediction result and real-time data at the starting moment in the first prediction sample data, and averaging the second linear change rates corresponding to each first prediction result to obtain an average change rate. Illustratively, the average rate of change is calculated as follows:

represents the average change rate, P represents the preset times, t _k The prediction time of the kth time in the preset times is represented,

real-time data of a start time within the first predicted sample data.

And adjusting the initial value of the linear change rate threshold parameter based on the average change rate and the target change rate to obtain an adjusted fault prediction function. Illustratively, the linear threshold adjustment formula is as follows:

And determining a fault prediction result of the ammeter box based on the adjusted fault prediction function. Specifically, the terminal determines a second prediction result according to the adjusted fault prediction function and the current acquired data. And determining second prediction sample data based on the current acquired data and a second prediction result, and continuously executing a prediction process based on the second prediction sample data and the adjusted fault prediction function until the number of predictions reaches a second preset number, so as to obtain a prediction result of the second prediction number. And determining whether the predicted results of the second predicted quantity meet preset fault conditions, and if so, determining that the fault predicted result of the electric meter box is the electric meter box fault.

According to the electric meter box fault prediction method, the initial value of the linear change rate threshold parameter and the initial value of the elastic network mixing parameter are determined based on the plurality of groups of historical acquisition data of the electric meter box terminal and the objective function comprising the linear change rate threshold parameter and the elastic network mixing parameter, and the initial fault prediction function is determined according to the initial value of the linear change rate threshold parameter, the initial value of the elastic network mixing parameter and the objective function. The initial fault prediction function determined based on the historical acquisition data can be used for predicting the fault of the ammeter box, and is beneficial to improving the accuracy of a fault prediction result. Acquiring current acquisition data of an ammeter box terminal, and determining an initial prediction result according to the current acquisition data and an initial fault prediction function; and adjusting initial values of the elastic network mixing parameter and the linear change rate threshold parameter based on the initial prediction result to obtain an adjusted fault prediction function. The adjusted fault prediction function is obtained by adjusting initial values of the elastic network mixing parameter and the linear change rate threshold parameter based on an initial prediction result predicted by the initial fault prediction function, and the fault prediction result of the electric meter box is determined based on the adjusted fault prediction function, so that the accuracy of the fault prediction result is further improved.

It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.

Based on the same inventive concept, the embodiment of the application also provides an ammeter box fault prediction device for realizing the ammeter box fault prediction method. The implementation of the solution provided by the device is similar to the implementation described in the above method, so the specific limitation in the embodiments of the device for predicting an electric meter box fault provided below may be referred to the limitation of the method for predicting an electric meter box fault hereinabove, and will not be repeated herein.

In one embodiment, as shown in fig. 10, there is provided an ammeter box fault prediction apparatus 100, comprising: a historical data acquisition module 110, an initial function determination module 120, a current data acquisition module 130, an adjustment function acquisition module 140, and a result determination module 150, wherein:

a historical data acquisition module 110, configured to acquire a plurality of sets of historical acquisition data of the ammeter box terminal;

an initial function determining module 120, configured to determine an initial value of the linear change rate threshold parameter and an initial value of the elastic network mixing parameter based on the plurality of sets of historical collected data and an objective function including the linear change rate threshold parameter and the elastic network mixing parameter; determining an initial fault prediction function according to the initial value of the linear change rate threshold parameter, the initial value of the elastic network mixing parameter and the objective function;

the current data acquisition module 130 is used for acquiring current acquisition data of the ammeter box terminal;

an adjustment function obtaining module 140, configured to determine an initial prediction result according to the current collected data and an initial fault prediction function; based on the initial prediction result, adjusting initial values of the elastic network mixing parameter and the linear change rate threshold value parameter to obtain an adjusted fault prediction function;

The result determining module 150 is configured to determine a fault prediction result of the electric meter box based on the adjusted fault prediction function.

According to the electric meter box fault prediction device, the plurality of groups of historical acquisition data of the electric meter box terminal are acquired, the initial value of the linear change rate threshold parameter and the initial value of the elastic network mixing parameter are determined based on the plurality of groups of historical acquisition data and the objective function comprising the linear change rate threshold parameter and the elastic network mixing parameter, and the initial fault prediction function is determined according to the initial value of the linear change rate threshold parameter, the initial value of the elastic network mixing parameter and the objective function. The initial fault prediction function determined based on the historical acquisition data can be used for predicting the fault of the ammeter box, and is beneficial to improving the accuracy of a fault prediction result. Acquiring current acquisition data of an ammeter box terminal, and determining an initial prediction result according to the current acquisition data and an initial fault prediction function; and adjusting initial values of the elastic network mixing parameter and the linear change rate threshold parameter based on the initial prediction result to obtain an adjusted fault prediction function. The adjusted fault prediction function is obtained by adjusting initial values of the elastic network mixing parameter and the linear change rate threshold parameter based on an initial prediction result predicted by the initial fault prediction function, and the fault prediction result of the electric meter box is determined based on the adjusted fault prediction function, so that the accuracy of the fault prediction result is further improved.

In one embodiment, in acquiring the current acquisition data of the electricity meter box terminals, the current data acquisition module 130 is further configured to: collecting real-time data of the ammeter box terminal at each moment in a preset time period; acquiring real-time data of each moment in a preset time length, and taking a first linear change rate between the real-time data of the starting moment in the preset time length and the first linear change rate of the ending moment in the preset time length relative to the starting moment as a target change rate; if the absolute value of the difference value between any first linear change rate and the target change rate is larger than the initial value of the linear change rate threshold parameter, updating real-time data corresponding to the corresponding first linear change rate into preset data; and determining the current acquisition data based on the updated real-time data.

In one embodiment, in adjusting the initial values of the elastic network hybrid parameter and the linear change rate threshold parameter based on the initial prediction result, the adjustment function obtaining module 140 is further configured to: based on an initial prediction result and an initial value of a linear change rate threshold parameter, adjusting the initial value of an elastic network mixing parameter to obtain a first fault prediction function; and predicting a first prediction result at the next moment of the cut-off moment according to the first fault prediction function and the current acquired data, and adjusting the initial value of the linear change rate threshold parameter based on the first prediction result to obtain an adjusted fault prediction function.

In one embodiment, in adjusting the initial value of the elastic network hybrid parameter based on the initial prediction result and the initial value of the linear change rate threshold parameter to obtain the first failure prediction function, the adjustment function obtaining module 140 is further configured to: acquiring a second linear change rate between an initial prediction result and real-time data of a starting moment in a preset duration; determining an absolute value of a difference between the second linear rate of change and the target rate of change as a rate of change difference; and if the change rate difference value is larger than the initial value of the linear change rate threshold parameter, adjusting the initial value of the elastic network mixing parameter based on the change rate difference value and the initial value of the linear change rate threshold parameter to obtain a first fault prediction function.

In one embodiment, in adjusting the initial value of the linear transformation rate threshold parameter based on the first prediction result to obtain the adjusted fault prediction function, the adjustment function obtaining module 140 is further configured to: determining first prediction sample data based on the current acquired data and a first prediction result, wherein the first prediction sample data is used for predicting data at the next moment of time corresponding to the first prediction result; continuing to execute a prediction process based on the first prediction sample data and the first fault prediction function until the number of predictions reaches a first preset number, so as to obtain a first target prediction result of the first prediction number; respectively acquiring a second linear change rate between each first target prediction result and real-time data of the starting moment in the first prediction sample data; averaging the second linear change rate corresponding to each first prediction result to obtain an average change rate; and adjusting the initial value of the linear change rate threshold parameter based on the average change rate and the target change rate to obtain an adjusted fault prediction function.

In one embodiment, in determining a fault prediction result for the electricity meter box based on the adjusted fault prediction function, the result determination module 150 is configured to: determining a second prediction result according to the adjusted fault prediction function and the current acquired data; determining second predicted sample data based on the current acquired data and a second predicted result; continuing to execute the prediction process based on the second prediction sample data and the adjusted fault prediction function until the number of predictions reaches a second preset number, so as to obtain a prediction result of the second prediction number; determining whether the predicted results of the second predicted quantity meet a preset fault condition; and if the electric meter box faults are satisfied, determining that the fault prediction result of the electric meter box is the electric meter box fault.

The above-mentioned various modules in the electricity meter box fault prediction device may be implemented in whole or in part by software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.

In one embodiment, a computer device is provided, which may be a terminal, and the internal structure thereof may be as shown in fig. 11. The computer device includes a processor, a memory, an input/output interface, a communication interface, a display unit, and an input means. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input/output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless mode can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program, when executed by a processor, implements a method for predicting a fault in an electrical meter box.

It will be appreciated by those skilled in the art that the structure shown in fig. 11 is merely a block diagram of a portion of the structure associated with the present application and is not limiting of the computer device to which the present application applies, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.

In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of the method embodiments described above when the computer program is executed.

In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when executed by a processor, carries out the steps of the method embodiments described above.

In an embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the steps of the method embodiments described above.

It should be noted that, the user information (including, but not limited to, user equipment information, user personal information, etc.) and the data (including, but not limited to, data for analysis, stored data, presented data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party, and the collection, use and processing of the related data are required to comply with the related laws and regulations and standards of the related countries and regions.

Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the various embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the various embodiments provided herein may include at least one of relational databases and non-relational databases. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic units, quantum computing-based data processing logic units, etc., without being limited thereto.

The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.

The above examples only represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the present application. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application shall be subject to the appended claims.

Claims

1. A method for predicting a fault in an electrical meter box, the method comprising:

determining an initial value of the linear change rate threshold parameter and an initial value of the elastic network mixing parameter based on the plurality of sets of historical acquisition data and an objective function comprising the linear change rate threshold parameter and the elastic network mixing parameter; determining an initial fault prediction function according to the initial value of the linear change rate threshold parameter, the initial value of the elastic network mixing parameter and the objective function;

Acquiring current acquisition data of an ammeter box terminal;

determining an initial prediction result according to the current acquired data and the initial fault prediction function; based on the initial prediction result, adjusting initial values of the elastic network mixing parameter and the linear change rate threshold parameter to obtain an adjusted fault prediction function;

2. The method of claim 1, wherein the obtaining current collected data for the electrical meter box terminal comprises:

acquiring real-time data of each moment in the preset time length, and taking a first linear change rate between the real-time data of the starting moment in the preset time length and the first linear change rate of the ending moment in the preset time length relative to the starting moment as a target change rate;

3. The method of claim 2, wherein adjusting initial values of the elastic network mixing parameter and the linear rate of change threshold parameter based on the initial prediction result to obtain an adjusted fault prediction function comprises:

based on the initial prediction result and the initial value of the linear change rate threshold parameter, adjusting the initial value of the elastic network mixing parameter to obtain a first fault prediction function;

4. A method according to claim 3, wherein said adjusting the initial value of the elastic network mixing parameter based on the initial prediction result and the initial value of the linear change rate threshold parameter to obtain a first failure prediction function comprises:

acquiring a second linear change rate between the initial prediction result and real-time data of the starting moment in the preset duration;

5. A method according to claim 3, wherein said adjusting the initial value of the linear rate of change threshold parameter based on the first prediction result to obtain an adjusted fault prediction function comprises:

determining first prediction sample data based on the current acquired data and the first prediction result, wherein the first prediction sample data is used for predicting data at a time next to a time corresponding to the first prediction result;

6. The method of claim 1, wherein determining a fault prediction result for an electrical meter box based on the adjusted fault prediction function comprises:

determining second predicted sample data based on the current acquired data and the second predicted result;

continuing to execute a prediction process based on the second prediction sample data and the adjusted fault prediction function until the number of predictions reaches a second preset number, and obtaining a prediction result of the second prediction number;

7. An ammeter box fault prediction device, the device comprising:

the initial function determining module is used for determining an initial value of the linear change rate threshold parameter and an initial value of the elastic network mixing parameter based on the plurality of groups of historical acquisition data and an objective function comprising the linear change rate threshold parameter and the elastic network mixing parameter; determining an initial fault prediction function according to the initial value of the linear change rate threshold parameter, the initial value of the elastic network mixing parameter and the objective function;

the adjustment function acquisition module is used for determining an initial prediction result according to the current acquired data and the initial fault prediction function; based on the initial prediction result, adjusting initial values of the elastic network mixing parameter and the linear change rate threshold parameter to obtain an adjusted fault prediction function;

and the result determining module is used for determining a fault prediction result of the electric meter box based on the adjusted fault prediction function.

8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 6 when the computer program is executed.

9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.

10. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.