CN115859667A - Automobile cable loss prediction method and device based on neural network and storage medium - Google Patents
Automobile cable loss prediction method and device based on neural network and storage medium Download PDFInfo
- Publication number
- CN115859667A CN115859667A CN202211639592.2A CN202211639592A CN115859667A CN 115859667 A CN115859667 A CN 115859667A CN 202211639592 A CN202211639592 A CN 202211639592A CN 115859667 A CN115859667 A CN 115859667A
- Authority
- CN
- China
- Prior art keywords
- cable
- loss
- data
- automobile
- temperature
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Abstract
The invention discloses a neural network-based automobile cable loss prediction method, a neural network-based automobile cable loss prediction device and a storage medium, wherein the method comprises the following steps: acquiring environmental data, first temperature data and second temperature data of an automobile cable; calculating according to the first temperature data to obtain a current stability coefficient, and calculating according to the second temperature data to obtain a temperature distribution coefficient; multiplying the current stability coefficient and the temperature distribution coefficient to obtain a risk coefficient of the automobile cable; calculating according to the environmental data and the risk coefficient to obtain a loss degree sequence of the automobile cable; and inputting the loss degree sequence into a preset loss degree prediction model to obtain the loss degree of the automobile cable at the next moment output by the loss degree prediction model. According to the method, the loss degree of the automobile cable is predicted in real time through the neural network model according to the current stability coefficient of the automobile cable in time and the temperature distribution characteristic in space and the influence of automobile environmental factors, so that the cable problem can be found in time and risk early warning can be performed.
Description
Technical Field
The invention relates to the technical field of automobile cables, in particular to an automobile cable loss prediction method and device based on a neural network and a storage medium.
Background
In the use process of the new energy automobile, frequent current exchange is caused by input and output of current in the battery, so that the temperature is greatly increased, the automobile cable is further fatigued, the plastic deformation is increased, the shrinkage is increased, and the insulation life and the performance of the automobile cable are influenced. The temperature change of the sheath material is smaller than that of insulation, but the fatigue creep can also influence the service life of the new energy automobile cable to a certain extent.
However, in the prior art, the service condition of the cable in the new energy automobile can only be monitored regularly, the operation process is relatively complicated, and the regular monitoring cannot deal with risks caused by emergency situations.
Disclosure of Invention
The invention aims to solve the technical problem of providing a neural network-based automobile cable loss prediction method, a device and a storage medium, determining the loss of a cable in the using process according to the current stability coefficient of the automobile cable in time and the temperature distribution characteristics in space and combining the influence of automobile environmental factors, and predicting the loss degree of the automobile cable in real time through a neural network model, so that the cable problem can be found in time and risk early warning can be carried out.
In order to achieve the above object, an embodiment of the present invention provides an automobile cable loss prediction method based on a neural network, including:
acquiring environmental data, first temperature data and second temperature data of an automobile cable; the first temperature data is temperature change data in time, and the second temperature data is temperature change data in space;
calculating to obtain a current stability coefficient of the automobile cable according to the first temperature data, and calculating to obtain a temperature distribution coefficient of the automobile cable according to the second temperature data;
multiplying the current stability coefficient and the temperature distribution coefficient to obtain a risk coefficient of the automobile cable;
calculating to obtain a loss degree sequence of the automobile cable according to the environment data and the risk coefficient;
and inputting the loss degree sequence into a preset loss degree prediction model to obtain the loss degree of the automobile cable at the next moment output by the loss degree prediction model.
As an improvement of the above scheme, the calculation formula of the current stability coefficient is as follows:
wherein Q represents the current stability factor of the automotive cable, T i Which is indicative of a first temperature of the liquid,
represents an average value of the first temperature data, n represents the number of the first temperature data, and e represents an index.
As an improvement of the above scheme, the calculation formula of the temperature distribution coefficient is as follows:
wherein W represents the temperature distribution coefficient of the automotive cable, H i Which is indicative of the second temperature, is,
represents the average value of the second temperature data, H Max Maximum value, H, of the second temperature data Min Represents the minimum value of the second temperature data, m represents the number of the second temperature data, and e represents an index.
As an improvement of the above scheme, if the environmental data includes environmental temperature data and environmental humidity data, the calculating according to the environmental data and the risk coefficient to obtain the loss degree sequence of the automobile cable specifically includes:
according to the environmental temperature data, the environmental humidity data and a formula
Calculating to obtain an environmental influence factor;
wherein S represents an environmental influence factor, P i Denotes the ambient temperature, P Max Maximum value, P, representing ambient temperature data Min Minimum value, L, representing ambient temperature data i Denotes the ambient humidity, L Max Maximum value, L, representing ambient humidity data Min A minimum value representing ambient humidity data;
multiplying the environmental influence factor and the risk coefficient to obtain the loss degree of each automobile cable;
and summarizing the loss degrees of all automobile cables in the automobile to obtain a loss degree sequence of the automobile cables.
As an improvement of the above scheme, the training method of the loss degree prediction model specifically includes:
inputting the loss degree sequence into a time sequence convolution network to obtain an output value of the time sequence convolution network;
and optimizing the time sequence convolution network according to a preset confidence coefficient and a loss function by taking the output value as a label to obtain a loss degree prediction model.
As an improvement of the above, the method further comprises:
calculating to obtain the similarity degree between different cables according to the current stability coefficient and the risk coefficient;
calculating to obtain the sample distance between the cables according to the similarity;
and grouping the automobile cables according to the sample distance based on a K-Means clustering method, and setting a corresponding threshold value for each group.
As an improvement of the above, the method further comprises:
comparing the degree of loss of the automotive cable to a threshold value for each group;
and when the loss degree of the automobile cable reaches one group of threshold values, carrying out risk early warning processing.
The embodiment of the invention also provides an automobile cable loss prediction device based on the neural network, which comprises the following steps:
the data acquisition module is used for acquiring environmental data, first temperature data and second temperature data of the automobile cable; the first temperature data is temperature change data in time, and the second temperature data is temperature change data in space;
the first calculation module is used for calculating a current stability coefficient of the automobile cable according to the first temperature data and calculating a temperature distribution coefficient of the automobile cable according to the second temperature data;
the second calculation module is used for multiplying the current stability coefficient and the temperature distribution coefficient to obtain a risk coefficient of the automobile cable;
the third calculation module is used for calculating a loss degree sequence of the automobile cable according to the environment data and the risk coefficient;
and the prediction module is used for inputting the loss degree sequence into a preset loss degree prediction model to obtain the loss degree of the automobile cable at the next moment output by the loss degree prediction model.
The embodiment of the present invention further provides an automobile cable loss prediction apparatus based on a neural network, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, the automobile cable loss prediction apparatus based on the neural network implements any one of the above automobile cable loss prediction methods based on the neural network.
The embodiment of the invention also provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program runs, the device where the computer-readable storage medium is located is controlled to execute any one of the above-mentioned neural network-based automobile cable loss prediction methods.
Compared with the prior art, the automobile cable loss prediction method, the automobile cable loss prediction device and the automobile cable loss storage medium based on the neural network have the advantages that: the method comprises the steps of obtaining environmental data, first temperature data and second temperature data of the automobile cable; the first temperature data is temperature change data in time, and the second temperature data is temperature change data in space; calculating to obtain a current stability coefficient of the automobile cable according to the first temperature data, and calculating to obtain a temperature distribution coefficient of the automobile cable according to the second temperature data; multiplying the current stability coefficient and the temperature distribution coefficient to obtain a risk coefficient of the automobile cable; calculating to obtain a loss degree sequence of the automobile cable according to the environmental data and the risk coefficient; and inputting the loss degree sequence into a preset loss degree prediction model to obtain the loss degree of the automobile cable at the next moment output by the loss degree prediction model. According to the embodiment of the invention, the loss of the cable in the using process is determined according to the current stability coefficient of the automobile cable in time and the temperature distribution characteristics in space and the influence of automobile environmental factors, and the loss degree of the automobile cable is predicted in real time through a neural network model, so that the cable problem can be found in time and risk early warning is carried out.
Drawings
FIG. 1 is a schematic flow chart diagram illustrating a method for predicting a cable loss of an automobile based on a neural network according to a preferred embodiment of the present invention;
FIG. 2 is a schematic structural diagram of a preferred embodiment of an automobile cable loss prediction device based on a neural network provided by the invention;
fig. 3 is a schematic structural diagram of another preferred embodiment of the automotive cable loss prediction device based on the neural network provided by the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, fig. 1 is a schematic flowchart illustrating a method for predicting a cable loss of an automobile based on a neural network according to a preferred embodiment of the present invention. The automobile cable loss prediction method based on the neural network comprises the following steps:
s1, acquiring environmental data, first temperature data and second temperature data of an automobile cable; the first temperature data is temperature change data in time, and the second temperature data is temperature change data in space;
s2, calculating to obtain a current stability coefficient of the automobile cable according to the first temperature data, and calculating to obtain a temperature distribution coefficient of the automobile cable according to the second temperature data;
s3, multiplying the current stability coefficient and the temperature distribution coefficient to obtain a risk coefficient of the automobile cable;
s4, calculating according to the environmental data and the risk coefficient to obtain a loss degree sequence of the automobile cable;
and S5, inputting the loss degree sequence into a preset loss degree prediction model to obtain the loss degree of the automobile cable at the next moment output by the loss degree prediction model.
Specifically, due to the requirement of the new energy automobile on endurance and electricity utilization, a plurality of cables are laid in the automobile frame. When the current in the battery is output, a large amount of current is continuously output, the temperature of the cable can be increased, the cable can generate heat under the power-on condition, the aging of the insulation layer of the cable can be accelerated by the overhigh temperature when the cable runs under long-term load, the service life of the cable is influenced, and therefore the temperature data of the new energy automobile cable in time needs to be acquired. According to the embodiment of the invention, the temperature probe sensor is used for acquiring the temperature data of the cable in the new energy automobile. For example, in the embodiment of the present invention, the data refresh frequency of the probe-type temperature sensor is set to 1 minute by taking one hour as a time length unit, and the first temperature data of the automobile cable, i.e., the temperature change sequence T = { T =, is obtained 1 ,T 2 ,.....,T i }. Based on that the length of the automobile cable has a certain influence on the current, the temperature data of each cable in the new energy automobile is collected by installing temperature probes at different positions of each cable and according to the probe type temperature sensor, and the temperature difference between different cables is determined. When the temperature of each cable is different in space, the insulation layer of the cable is obviously damaged, and therefore temperature data of the new energy automobile in cable space needs to be acquired. For example, in the embodiment of the invention, the probe-type temperature sensor is used to read the temperature data of the cable in the new energy automobile, the temperature probe is set at a distance of 50cm (which can be set by itself according to actual conditions), and the second temperature data of the automobile cable, that is, the temperature distribution sequence H = { H }, is obtained by taking 10 segments of distance as a length unit 1 ,H 2 ,.....,H i }. Based on long-term high temperature or humid climateAnd the loss of the cable insulator is reduced, so that environmental data of the new energy automobile is required to be acquired. According to the current output, when the current output is unstable for a period of time, the temperature of the cable is the largest, and the damage to the service life of the cable is the largest, so that the current stability coefficient of the automobile cable is calculated according to the first temperature data. When the temperature of each cable is different in space, the insulation layer of the cable is obviously damaged, and therefore the temperature distribution coefficient of the automobile cable is calculated according to the second temperature data. And multiplying the current stability coefficient and the temperature distribution coefficient to obtain a risk coefficient of the automobile cable in the power-on use process. The loss of the cable insulation is accelerated based on long-term high temperature or humid climate, so the loss degree sequence of the automobile cable is calculated by combining environmental data and risk factors. And inputting the loss degree sequence into a preset loss degree prediction model, so as to obtain the loss degree of the automobile cable at the next moment output by the loss degree prediction model.
According to the embodiment, according to the current stability coefficient of the automobile cable in time and the temperature distribution characteristic in space, the influence of automobile environmental factors is combined, the loss of the cable in the using process is determined, the loss degree of the automobile cable is predicted in real time through a neural network model, and therefore the problem of the cable can be found in time and risk early warning is carried out.
In another preferred embodiment, the current stability factor is calculated by the formula:
wherein Q represents the current stability coefficient of the automotive cable, T i Which is indicative of a first temperature of the liquid,
represents an average value of the first temperature data, n represents the number of the first temperature data, and e represents an index.
Specifically, in the embodiment of the present invention, the first temperature data acquired from the automobile cable is T = { T = { (T) } 1 ,T 2 ,.....,T i According to the current output, when the current output is unstable for a period of time, the temperature of the cable is the largest, and the damage to the service life of the cable is the largest, so that the current stability coefficient of the automobile cable is obtained through calculation according to the first temperature data
Wherein Q represents the current stability factor of the automotive cable, T i Indicates a first temperature, is present>
Represents an average value of the first temperature data, n represents the number of the first temperature data, and e represents an index. Temperature variance according to cable
To represent the temperature change due to the current fluctuation, it is shown that the more the cable temperature change per unit time is, the more the cable is damaged by frequent current fluctuation, and the current stability coefficient Q is obtained to represent the stability change of the current per unit time in combination with the average value of the temperature change per unit time.
In a further preferred embodiment, the temperature distribution coefficient is calculated by the formula:
wherein W represents the temperature distribution coefficient of the automotive cable, H i Which is indicative of the second temperature, is,
represents the average value of the second temperature data, H Max Maximum value, H, of the second temperature data Min Represents the minimum value of the second temperature data, m represents the number of the second temperature data, and e represents an index.
Specifically, in the embodiment of the present invention, the second temperature number of the automobile cable is obtainedAccording to H = { H 1 ,H 2 ,.....,H i When the temperature of each cable is different in space, the insulation layer of the cable is obviously damaged, and therefore the temperature distribution coefficient of the automobile cable is calculated according to the second temperature data to be
Wherein W represents the temperature distribution coefficient of the automotive cable, H i Indicates a second temperature, <' > is present>
Represents the average value of the second temperature data, H Max Maximum value, H, of the second temperature data Min Represents the minimum value of the second temperature data, m represents the number of the second temperature data, and e represents an index. And determining the dispersion degree between the sections in the length unit according to the temperature variance collected by each section on each cable, wherein the greater the dispersion degree is, the greater the temperature difference of the length unit is, the greater the electricity utilization risk of the cable is, and determining the generated maximum temperature difference by combining the difference value between the maximum value and the minimum value of the temperature change in the length unit, thereby obtaining W which is used for expressing the temperature distribution coefficient in the length unit.
After a current stability coefficient Q and a temperature distribution coefficient W of the automobile cable are obtained through calculation, the current stability coefficient Q and the temperature distribution coefficient W are multiplied to obtain a risk coefficient U = Q W of the automobile cable in the electrifying use process. The risk coefficient of the cable is larger when the variation difference of the stability of the current in unit time is larger, and the risk coefficient of the cable is larger when the temperature distribution coefficient of the cable is larger, and U is changed along with the variation of the stability coefficient of the current and the temperature distribution coefficient.
In another preferred embodiment, the environmental data includes environmental temperature data and environmental humidity data, and the calculating the sequence of the loss degrees of the automotive cable according to the environmental data and the risk coefficient specifically includes:
according to the environmental temperature data, the environmental humidity data and a formula
Calculating to obtain an environmental influence factor;
wherein S represents an environmental influence factor, P i Denotes the ambient temperature, P Max Maximum value, P, representing ambient temperature data Min Minimum value, L, representing ambient temperature data i Indicating the ambient humidity, L Max Maximum value, L, representing ambient humidity data Min A minimum value representing ambient humidity data;
multiplying the environmental impact factor and the risk coefficient to obtain the loss degree of each automobile cable;
and summarizing the loss degrees of all automobile cables in the automobile to obtain a loss degree sequence of the automobile cables.
In particular, the loss of the cable insulator is accelerated due to long-term high temperature or humid climate, so that the environmental data of the new energy automobile is also required to be collected. The method comprises the steps of firstly collecting environmental temperature data of the new energy automobile, setting an initial temperature which can affect a cable, and when the temperature is higher, the influence on the cable is higher. Acquiring environmental temperature data according to the time unit for acquiring the cable temperature data to obtain an environmental temperature change sequence P = { P = { (P) } 1 ,P 2 ,.....,P i }. Secondly, acquiring humidity data of the new energy automobile, and setting an initial humidity to obtain a humidity change sequence L = { L = { (L) } 1 ,L 2 ,.....,L i }. When the environment temperature in the new energy automobile is higher and the humidity is higher, the influence on the service life of the cable is higher, and therefore the influence degree of the environment of the new energy automobile on the service life of the cable is calculated according to the environment temperature data and the environment humidity data to obtain the environment influence factor
Wherein S represents an environmental influence factor, P i Denotes the ambient temperature, P Max Maximum value, P, representing ambient temperature data Min Minimum value, L, representing ambient temperature data i Denotes the ambient humidity, L Max Maximum value, L, representing ambient humidity data Min Representing the minimum value of the ambient humidity data. According to the influences of different humidity and temperature, when the environment temperature in the new energy automobile is higher and the humidity is higher, the damage influence on the service life of the cable is higher. And multiplying the environmental influence factor S and the risk coefficient U to obtain the loss degree Y = U S of each automobile cable. The loss degree of the cable changes along with the change of risk factors and environmental factors of the line, and the relationship is in positive correlation. Repeating the above operations, collecting and summarizing the loss degrees of all cables in the automobile, and obtaining a change sequence Y = { Y } of the loss degrees of the cables 1 ,Y 2 ,.....,Y i }。
In another preferred embodiment, the training method of the loss degree prediction model specifically includes:
inputting the loss degree sequence into a time sequence convolution network to obtain an output value of the time sequence convolution network;
and optimizing the time sequence convolution network according to a preset confidence coefficient and a loss function by taking the output value as a label to obtain a loss degree prediction model.
Specifically, the TCN time sequence convolution network is used for predicting the cable consumption degree of the new energy automobile, and the cable consumption degree of the new energy automobile at the next moment is predicted. And inputting the obtained cable loss degree sequence of the new energy automobile as the former part of the characteristic sequence into a TCN neural network for training. And using the obtained output value as a label, so that the TCN can learn the next predicted value of the current sequence. And obtaining a cable loss degree sequence of the residual new energy automobile, and optimizing the time sequence convolution network according to a preset confidence coefficient and a loss function. The loss function of TCN is the mean square error (loss).
For this time sample sequence, confidence C is used i As mass fraction and normalized to the sample weight C = { C added to 1 1 ,..,C i }。
Wherein C is the mass fraction after normalization as the loss weight.
To predict samples, y i Is a feature sample. The purpose is to ensure the convergence of the loss function, reduce the loss through continuous training and predict the accurate trend. By analogy, different temperature changes correspond to different prediction results. The significance of the TCN training is that the TCN can be used for predicting the loss degree result of the subsequent new energy automobile cable according to the data of the temperature difference condition from small to large. For the predicted result, a user can reach the output standard of the TCN according to the cable loss degree of the new energy automobile, the cable loss degree of the new energy automobile at the moment is about to reach the threshold value, and risk early warning is required to be carried out.
Preferably, the method further comprises:
calculating to obtain the similarity between different cables according to the current stability coefficient and the risk coefficient;
calculating to obtain the sample distance between the cables according to the similarity;
and grouping the automobile cables according to the sample distance based on a K-Means clustering method, and setting a corresponding threshold value for each group.
Specifically, based on in the new energy automobile cable itself will generate heat when the circular telegram, the size of electric current and the generating heat of electric wire are directly proportional, when laying the cable, according to real-time condition, probably need tie some cables together, according to implementer actual conditions length and the quantity of setting up, when the cable is tied together, because the thermal diffusivity variation, consequently the temperature can be than the temperature of single cable a lot of, and the harm to cable life is also some just in nature. The risk of cables is greater when the cable bundle length is longer and the number is greater. Therefore, the present embodiment groups the density of the cables, and when the current stability fluctuations are close, it indicates that the distances of the cables are closer, and at the same time, the risk coefficients of the cables are closer, so that the current stability of the cables and the risk coefficients of the cables are grouped into one group, and the similarity degree between different cables is calculated. The calculation formula of the similarity degree is as follows:
wherein A, B is two different cables, δ A δ B Is Pearson's similarity coefficient, and is used to represent the similarity degree of different data sequences, COV (T) A ,T B ) The greater the difference, the lower the pearson correlation coefficient and vice versa, for the overall difference of the sequences of temperature changes in the two cables. abs (U) A -U B ) The absolute difference of the risk coefficients of the two cables is A, B, and the larger the difference is, the lower the similarity is.
And calculating sample distances among the cables based on the obtained similarity degree among different cables, and grouping the cable density according to the sample distances. The calculation formula of the sample distance is as follows:
and D is the sample distance of different cable risk similarities, and when the similarity of different cables is larger, the sample distance is smaller. Otherwise, the larger the size.
Based on the sample distance, the individual density cables are grouped using the K-Means clustering method. Defining the K value as 3, all density cables are grouped in different densities.
High density group: the cable of the group has larger aggregation degree, larger density and highest risk coefficient,
medium density group: the cable density of the group is gathered in a general degree, the risk coefficient is moderate and the like.
Low density group: the cable group has the advantages of rare aggregation degree, small density and low risk coefficient.
Due to temperature variations and cable density, different thresholds need to be set for different densities of cables. Because if set up a threshold value, the damage that different groups caused the cable every time is different, can appear the error, leads to the cable to break down, consequently sets up three different threshold values with three groups according to actual conditions.
Preferably, the method further comprises:
comparing the degree of loss of the automotive cable to the threshold value of each group;
and when the loss degree of the automobile cable reaches one group of threshold values, carrying out risk early warning processing.
Specifically, the embodiment of the invention carries out risk early warning processing on the loss degree result of the automobile cable obtained by predicting the loss degree prediction model based on the three set threshold standards according to real-time detection on the loss degrees of the cables of the three types of new energy automobiles, and when the loss degree of each type of new energy automobile reaches the set threshold. The threshold value may be set according to actual conditions.
Correspondingly, the invention also provides an automobile cable loss prediction device based on the neural network, which can realize all the processes of the automobile cable loss prediction method based on the neural network in the embodiment.
Referring to fig. 2, fig. 2 is a schematic structural diagram of an automobile cable loss prediction apparatus based on a neural network according to a preferred embodiment of the present invention. The automobile cable loss prediction device based on the neural network comprises:
the data acquisition module 201 is used for acquiring environmental data, first temperature data and second temperature data of the automobile cable; the first temperature data is temperature change data in time, and the second temperature data is temperature change data in space;
the first calculating module 202 is configured to calculate a current stability coefficient of the automobile cable according to the first temperature data, and calculate a temperature distribution coefficient of the automobile cable according to the second temperature data;
the second calculating module 203 is configured to multiply the current stability coefficient and the temperature distribution coefficient to obtain a risk coefficient of the automobile cable;
a third calculating module 204, configured to calculate a loss degree sequence of the automobile cable according to the environmental data and the risk coefficient;
and the prediction module 205 is configured to input the loss degree sequence into a preset loss degree prediction model to obtain the loss degree of the automobile cable at the next time output by the loss degree prediction model.
Preferably, the calculation formula of the current stability coefficient is as follows:
wherein Q represents the current stability factor of the automotive cable, T i Which is indicative of a first temperature of the liquid,
represents an average value of the first temperature data, n represents the number of the first temperature data, and e represents an index.
Preferably, the calculation formula of the temperature distribution coefficient is:
wherein W represents the temperature distribution coefficient of the automotive cable, H i Which is indicative of the second temperature, is,
represents the average value of the second temperature data, H Max Represents the maximum value of the second temperature data, H Min Represents the minimum value of the second temperature data, m represents the number of the second temperature data, and e represents an index.
Preferably, the environment data includes environment temperature data and environment humidity data, and the calculating according to the environment data and the risk coefficient to obtain the loss degree sequence of the automobile cable specifically includes:
according to the environmental temperature data, the environmental humidity data and a formula
Calculating to obtain an environmental impact factor;
wherein S represents an environmental influence factor, P i Denotes the ambient temperature, P Max Maximum value, P, representing ambient temperature data Min Minimum value, L, representing ambient temperature data i Indicating the ambient humidity, L Max Maximum value, L, representing ambient humidity data Min A minimum value representing ambient humidity data;
multiplying the environmental influence factor and the risk coefficient to obtain the loss degree of each automobile cable;
and summarizing the loss degrees of all automobile cables in the automobile to obtain a loss degree sequence of the automobile cables.
Preferably, the training method of the loss degree prediction model specifically includes:
inputting the loss degree sequence into a time sequence convolution network to obtain an output value of the time sequence convolution network;
and optimizing the time sequence convolution network according to a preset confidence coefficient and a loss function by taking the output value as a label to obtain a loss degree prediction model.
Preferably, the apparatus is further configured to:
calculating to obtain the similarity between different cables according to the current stability coefficient and the risk coefficient;
calculating to obtain the sample distance between the cables according to the similarity;
and grouping the automobile cables according to the sample distance based on a K-Means clustering method, and setting a corresponding threshold value for each group.
Preferably, the apparatus is further configured to:
comparing the degree of loss of the automotive cable to a threshold value for each group;
and when the loss degree of the automobile cable reaches one group of threshold values, carrying out risk early warning processing.
In a specific implementation, the working principle, the control flow and the realized technical effect of the neural network-based automobile cable loss prediction device provided in the embodiment of the present invention are the same as those of the neural network-based automobile cable loss prediction method in the above embodiment, and are not described herein again.
Referring to fig. 3, fig. 3 is a schematic structural diagram of another preferred embodiment of an automobile cable loss prediction apparatus based on a neural network according to the present invention. The automobile cable loss prediction device based on the neural network comprises a processor 301, a memory 302 and a computer program stored in the memory 302 and configured to be executed by the processor 301, wherein the processor 301 implements the automobile cable loss prediction method based on the neural network according to any one of the above embodiments when executing the computer program.
Preferably, the computer program may be divided into one or more modules/units (e.g., computer program 1, computer program 2, … …) that are stored in the memory 302 and executed by the processor 301 to implement the present invention. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions, which are used for describing the execution process of the computer program in the neural network based automobile cable loss prediction device.
The Processor 301 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, a discrete hardware component, etc., the general purpose Processor may be a microprocessor, or the Processor 301 may be any conventional Processor, the Processor 301 is a control center of the car cable loss prediction apparatus based on the neural network, and various interfaces and lines are used to connect various parts of the car cable loss prediction apparatus based on the neural network.
The memory 302 mainly includes a program storage area that may store an operating system, an application program required for at least one function, and the like, and a data storage area that may store related data and the like. In addition, the memory 302 may be a high speed random access memory, a non-volatile memory such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash Card (Flash Card), and the like, or the memory 302 may be other volatile solid state memory devices.
It should be noted that the above-mentioned neural network based automobile cable loss prediction apparatus may include, but is not limited to, a processor and a memory, and those skilled in the art will understand that the schematic structural diagram of fig. 3 is only an example of the above-mentioned neural network based automobile cable loss prediction apparatus, and does not constitute a limitation of the above-mentioned neural network based automobile cable loss prediction apparatus, and may include more or less components than those shown in the figure, or combine some components, or different components.
The embodiment of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium includes a stored computer program, where when the computer program runs, a device where the computer-readable storage medium is located is controlled to execute the method for predicting automobile cable loss based on a neural network according to any one of the above embodiments.
The embodiment of the invention provides a method, a device and a storage medium for predicting the loss of an automobile cable based on a neural network, wherein the method comprises the steps of obtaining environmental data, first temperature data and second temperature data of the automobile cable; the first temperature data is temperature change data in time, and the second temperature data is temperature change data in space; calculating to obtain a current stability coefficient of the automobile cable according to the first temperature data, and calculating to obtain a temperature distribution coefficient of the automobile cable according to the second temperature data; multiplying the current stability coefficient and the temperature distribution coefficient to obtain a risk coefficient of the automobile cable; calculating to obtain a loss degree sequence of the automobile cable according to the environment data and the risk coefficient; and inputting the loss degree sequence into a preset loss degree prediction model to obtain the loss degree of the automobile cable at the next moment output by the loss degree prediction model. According to the embodiment of the invention, the loss of the cable in the using process is determined according to the current stability coefficient of the automobile cable in time and the temperature distribution characteristics in space and the influence of automobile environmental factors, and the loss degree of the automobile cable is predicted in real time through a neural network model, so that the cable problem can be found in time and risk early warning is carried out.
It should be noted that the above-described system embodiments are merely illustrative, where the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. In addition, in the drawings of the embodiment of the system provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, and may be specifically implemented as one or more communication buses or signal lines. One of ordinary skill in the art can understand and implement without inventive effort.
While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention.
Claims (10)
1. A method for predicting the loss of an automobile cable based on a neural network is characterized by comprising the following steps:
acquiring environmental data, first temperature data and second temperature data of an automobile cable; the first temperature data is temperature change data in time, and the second temperature data is temperature change data in space;
calculating to obtain a current stability coefficient of the automobile cable according to the first temperature data, and calculating to obtain a temperature distribution coefficient of the automobile cable according to the second temperature data;
multiplying the current stability coefficient and the temperature distribution coefficient to obtain a risk coefficient of the automobile cable;
calculating to obtain a loss degree sequence of the automobile cable according to the environment data and the risk coefficient;
and inputting the loss degree sequence into a preset loss degree prediction model to obtain the loss degree of the automobile cable at the next moment output by the loss degree prediction model.
2. The neural network-based automotive cable loss prediction method of claim 1, wherein the current stability coefficient is calculated by the formula:
wherein Q represents the current stability factor of the automotive cable, T i Which is indicative of a first temperature of the liquid,
represents an average value of the first temperature data, n represents the number of the first temperature data, and e represents an index.
3. The neural network-based automotive cable loss prediction method according to claim 2, wherein the temperature distribution coefficient is calculated by the formula:
wherein W represents the temperature distribution coefficient of the automotive cable, H i Which is indicative of the second temperature, is,
represents the average value of the second temperature data, H Max Represents the maximum value of the second temperature data, H Min Represents the minimum value of the second temperature data, m represents the number of the second temperature data, and e represents an index.
4. The method according to claim 3, wherein the environmental data includes environmental temperature data and environmental humidity data, and the calculating according to the environmental data and the risk coefficient to obtain the loss degree sequence of the car cable specifically includes:
according to the environmental temperature data, the environmental humidity data and a formula
Calculating to obtain an environmental impact factor;
wherein S represents an environmental influence factor, P i Denotes the ambient temperature, P Max Maximum value, P, representing ambient temperature data Min Minimum value, L, representing ambient temperature data i Denotes the ambient humidity, L Max Maximum value, L, representing ambient humidity data Min A minimum value representing ambient humidity data;
multiplying the environmental influence factor and the risk coefficient to obtain the loss degree of each automobile cable;
and summarizing the loss degrees of all automobile cables in the automobile to obtain a loss degree sequence of the automobile cables.
5. The automobile cable loss prediction method based on the neural network as claimed in claim 4, wherein the training method of the loss degree prediction model specifically comprises:
inputting the loss degree sequence into a time sequence convolution network to obtain an output value of the time sequence convolution network;
and optimizing the time sequence convolution network according to a preset confidence coefficient and a loss function by taking the output value as a label to obtain a loss degree prediction model.
6. The neural network-based automotive cable loss prediction method of claim 1, further comprising:
calculating to obtain the similarity degree between different cables according to the current stability coefficient and the risk coefficient;
calculating to obtain the sample distance between the cables according to the similarity;
and grouping the automobile cables according to the sample distance based on a K-Means clustering method, and setting a corresponding threshold value for each group.
7. The neural network-based automotive cable loss prediction method of claim 6, further comprising:
comparing the degree of loss of the automotive cable to a threshold value for each group;
and when the loss degree of the automobile cable reaches one group of threshold values, carrying out risk early warning processing.
8. An automobile cable loss prediction device based on a neural network, comprising:
the data acquisition module is used for acquiring environmental data, first temperature data and second temperature data of the automobile cable; the first temperature data is temperature change data in time, and the second temperature data is temperature change data in space;
the first calculation module is used for calculating a current stability coefficient of the automobile cable according to the first temperature data and calculating a temperature distribution coefficient of the automobile cable according to the second temperature data;
the second calculation module is used for multiplying the current stability coefficient and the temperature distribution coefficient to obtain a risk coefficient of the automobile cable;
the third calculation module is used for calculating a loss degree sequence of the automobile cable according to the environment data and the risk coefficient;
and the prediction module is used for inputting the loss degree sequence into a preset loss degree prediction model to obtain the loss degree of the automobile cable at the next moment output by the loss degree prediction model.
9. An automobile cable loss prediction device based on a neural network, which is characterized by comprising a processor and a memory, wherein the memory stores a computer program, and the computer program is configured to be executed by the processor, and the processor executes the computer program to realize the automobile cable loss prediction method based on the neural network according to any one of claims 1 to 7.
10. A computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and wherein when the computer program is executed by an apparatus, the apparatus implements the neural network-based automobile cable loss prediction method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211639592.2A CN115859667A (en) | 2022-12-20 | 2022-12-20 | Automobile cable loss prediction method and device based on neural network and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211639592.2A CN115859667A (en) | 2022-12-20 | 2022-12-20 | Automobile cable loss prediction method and device based on neural network and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115859667A true CN115859667A (en) | 2023-03-28 |
Family
ID=85674409
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211639592.2A Pending CN115859667A (en) | 2022-12-20 | 2022-12-20 | Automobile cable loss prediction method and device based on neural network and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115859667A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116705184A (en) * | 2023-05-29 | 2023-09-05 | 上海海德利森科技有限公司 | Liquid hydrogen evaporation loss prediction method, device, equipment and medium |
-
2022
- 2022-12-20 CN CN202211639592.2A patent/CN115859667A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116705184A (en) * | 2023-05-29 | 2023-09-05 | 上海海德利森科技有限公司 | Liquid hydrogen evaporation loss prediction method, device, equipment and medium |
| CN116705184B (en) * | 2023-05-29 | 2024-04-05 | 上海海德利森科技有限公司 | Liquid hydrogen evaporation loss prediction method, device, equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115859667A (en) | Automobile cable loss prediction method and device based on neural network and storage medium | |
| CN111191671B (en) | Electrical appliance waveform detection method, system, electronic equipment and storage medium | |
| CN107121943B (en) | Method and device for obtaining health prediction information of intelligent instrument | |
| CN112838247A (en) | Fuel cell system power model prediction calculation method, device, medium and equipment | |
| CN111638988A (en) | Cloud host fault intelligent prediction method based on deep learning | |
| CN114720764A (en) | Harmonic analysis method and system based on real-time monitoring data of electric meter | |
| CN114818831A (en) | Bidirectional lithium ion battery fault detection method and system based on multi-source perception | |
| CN113815481B (en) | Battery pack selection method and device, electronic equipment and storage medium | |
| CN108932554B (en) | Configuration optimization method and device for wind power plant flow field measurement points | |
| CN110991774A (en) | Electric quantity load prediction method and device | |
| CN116361628A (en) | Fault category intelligent analysis method and device based on VFD room | |
| CN108009647B (en) | Device record processing method and device, computer device and storage medium | |
| KR101867222B1 (en) | Non-Intrusive Appliance Load Monitoring Method and Device using Influence of Complex Sensors on State of Appliance | |
| Chou et al. | Automatic appliance classification for non-intrusive load monitoring | |
| CN113487086B (en) | Method, device, computer equipment and medium for predicting residual service life of equipment | |
| CN116150666B (en) | Energy storage system fault detection method and device and intelligent terminal | |
| CN117471227A (en) | Automobile wire harness parameter performance test method and test system | |
| CN111768023B (en) | Probability peak load estimation method based on smart city electric energy meter data | |
| CN111967421B (en) | Method and device for classifying periodic power transitions and conventional equipment starting events | |
| CN114236276B (en) | Method and system for remotely testing electric appliance | |
| CN115063255B (en) | Operation and maintenance resource optimal allocation method, device and system for offshore wind farm | |
| CN117055394A (en) | Data acquisition management method and system in smart home | |
| Yang et al. | Missing Data Completion Based on Nonlinear Feature Space Mapping for the Power Grid | |
| CN117148225A (en) | Transformer fault detection method | |
| CN117520896A (en) | Cable accessory fault diagnosis method, device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |