CN116697039A - Self-adaptive control method and system for single-stage high-speed transmission - Google Patents
Self-adaptive control method and system for single-stage high-speed transmission Download PDFInfo
- Publication number
- CN116697039A CN116697039A CN202310979905.7A CN202310979905A CN116697039A CN 116697039 A CN116697039 A CN 116697039A CN 202310979905 A CN202310979905 A CN 202310979905A CN 116697039 A CN116697039 A CN 116697039A
- Authority
- CN
- China
- Prior art keywords
- data
- dimension
- segment
- compressed
- obtaining
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 65
- 230000005540 biological transmission Effects 0.000 title claims abstract description 39
- 238000007906 compression Methods 0.000 claims abstract description 122
- 230000006835 compression Effects 0.000 claims abstract description 120
- 230000008859 change Effects 0.000 claims abstract description 35
- 238000013500 data storage Methods 0.000 claims description 21
- 238000004458 analytical method Methods 0.000 claims description 18
- 230000011218 segmentation Effects 0.000 claims description 16
- 230000003044 adaptive effect Effects 0.000 claims description 15
- 238000012544 monitoring process Methods 0.000 claims description 10
- 238000001514 detection method Methods 0.000 claims description 8
- 238000003745 diagnosis Methods 0.000 claims description 8
- 238000004891 communication Methods 0.000 claims description 7
- 238000012216 screening Methods 0.000 claims description 5
- 230000009471 action Effects 0.000 claims description 4
- 230000008569 process Effects 0.000 abstract description 16
- 238000013144 data compression Methods 0.000 abstract description 8
- 238000012545 processing Methods 0.000 abstract description 7
- 238000004364 calculation method Methods 0.000 description 9
- 230000000694 effects Effects 0.000 description 3
- 238000010606 normalization Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 230000006837 decompression Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F16—ENGINEERING ELEMENTS AND UNITS; GENERAL MEASURES FOR PRODUCING AND MAINTAINING EFFECTIVE FUNCTIONING OF MACHINES OR INSTALLATIONS; THERMAL INSULATION IN GENERAL
- F16H—GEARING
- F16H61/00—Control functions within control units of change-speed- or reversing-gearings for conveying rotary motion ; Control of exclusively fluid gearing, friction gearing, gearings with endless flexible members or other particular types of gearing
- F16H61/02—Control functions within control units of change-speed- or reversing-gearings for conveying rotary motion ; Control of exclusively fluid gearing, friction gearing, gearings with endless flexible members or other particular types of gearing characterised by the signals used
- F16H61/0202—Control functions within control units of change-speed- or reversing-gearings for conveying rotary motion ; Control of exclusively fluid gearing, friction gearing, gearings with endless flexible members or other particular types of gearing characterised by the signals used the signals being electric
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F16—ENGINEERING ELEMENTS AND UNITS; GENERAL MEASURES FOR PRODUCING AND MAINTAINING EFFECTIVE FUNCTIONING OF MACHINES OR INSTALLATIONS; THERMAL INSULATION IN GENERAL
- F16H—GEARING
- F16H63/00—Control outputs from the control unit to change-speed- or reversing-gearings for conveying rotary motion or to other devices than the final output mechanism
- F16H63/40—Control outputs from the control unit to change-speed- or reversing-gearings for conveying rotary motion or to other devices than the final output mechanism comprising signals other than signals for actuating the final output mechanisms
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Mechanical Engineering (AREA)
- Theoretical Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Compression, Expansion, Code Conversion, And Decoders (AREA)
Abstract
The invention relates to the technical field of data processing, in particular to a self-adaptive control method and a self-adaptive control system for a single-stage high-speed transmission, comprising the following steps: obtaining the characteristic degree according to the dimension data; obtaining characteristic dimensions according to the characteristic degree; obtaining a data segment according to the characteristic dimension; obtaining a compressed segment according to the data segment; obtaining dimension change weights according to the feature dimensions; obtaining a distribution difference factor according to the dimension change weight; obtaining a compression efficiency difference factor according to the number of compression segments; obtaining fitting necessity according to the compression efficiency difference factor and the distribution difference factor; obtaining contribution according to fitting necessity; obtaining an initial fitting weight value according to the contribution degree; obtaining a fitting weight value according to the initial fitting weight value; obtaining a least square model parameter according to the fitting weight value; and storing according to the least square model parameters. The invention more effectively avoids the loss of data in the data compression process, thereby reducing the error between the decoded data and the original data.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a self-adaptive control method and system of a single-stage high-speed transmission.
Background
With the increasing prominence of environmental problems, the electric automobile gradually becomes an ideal choice for green travel due to the advantages of lower emission, low noise, high energy efficiency and the like of the electric automobile; in the field of electric automobiles, a single-stage high-speed transmission plays a key role as a transmission device; however, in the actual running process, various working conditions can cause the change of parameters such as load, rotating speed and the like, so that the transmission performance is influenced, and therefore, the sensor data is adjusted in real time by adopting the self-adaptive control system, and the optimization of the transmission performance is very important.
In the adaptive control system of the traditional single-stage high-speed transmission, the sensors are required to acquire key parameter data such as load, rotating speed, temperature and the like to acquire accuracy, and the corresponding acquired sensor data is required to be continuously stored for providing historical data for the operation of equipment, so that the performance and stability under different use conditions can be analyzed conveniently, and the control strategy is optimized. The traditional sensor data compression algorithm adopts a revolving door compression algorithm, and the revolving door compression algorithm is a data compression method suitable for time series, and can better keep the sensor data characteristics and greatly ensure the compression rate of data. However, in the revolving door compression algorithm, a plurality of lengths of fixed segments are carried out on data, each segment of data is represented by an end-to-end straight line according to the set tolerance, but the detected straight line is adopted to replace the data segment by the method, so that the data compression rate is greatly improved, but a lot of data information in original data is lost, and further, larger errors are generated when the performance and stability of the current single-stage high-speed transmission are analyzed through historical data. Therefore, in the self-adaptive control system of the single-stage high-speed transmission, the acquired sensor data is subjected to self-adaptive revolving door compression processing, so that the effect of accurate control can be achieved.
Disclosure of Invention
The invention provides a self-adaptive control method and a self-adaptive control system for a single-stage high-speed transmission, which are used for solving the existing problems.
The invention discloses a self-adaptive control method and a system for a single-stage high-speed transmission, which adopts the following technical scheme:
an embodiment of the present invention provides an adaptive control method of a single-stage high-speed transmission, including the steps of:
collecting dimension data sequences with different dimensions, wherein the dimension data sequences are composed of dimension data;
obtaining the characteristic degree of each dimension according to the difference between the dimension data of the dimension data sequence; threshold screening is carried out on the dimensions according to the characteristic degree to obtain a plurality of characteristic dimensions; segmenting the dimension data sequence according to the characteristic dimension to obtain a plurality of data segments;
compressing the data segment to obtain a plurality of compressed segments; obtaining the dimension change weight of the compressed segment according to the correlation of the feature dimension; obtaining a distribution information value of the data segment according to the dimension change weight; a distribution difference factor of the data segment according to the distribution information value;
obtaining the compression efficiency of the data segment according to the number of the compression segments of the data segment; obtaining a compression efficiency difference factor of the data segment according to the compression efficiency; obtaining the fitting necessity of the data segment according to the compression efficiency difference factor and the distribution difference factor;
Obtaining the contribution degree of the compressed data according to the fitting necessity; obtaining an initial fitting weight value of compression data in the compression section according to the contribution degree; normalizing the initial fitting weight value to obtain a fitting weight value; fitting the compression segments according to the fitting weight values to obtain a plurality of partial least square model parameters; storing in a data storage module according to the least square model parameters;
decoding is carried out according to the data of the data storage module, and the decoded data is input into the control analysis module to realize self-adaptive control.
Preferably, the feature degree of each dimension is obtained according to the difference between the dimension data of the dimension data sequence, and the specific method comprises the following steps:
recording any pair of adjacent dimension data difference values in a dimension data sequence of any one dimension in any one day as initial difference values, recording a sequence formed by the initial difference values as difference sequences, and recording the absolute value of the difference value between any pair of initial difference values with the same ordinal number in the difference sequences of any two dimensions as a first difference value;
in the method, in the process of the invention,representing the characteristic degree of the ith dimension in all days; u represents the number of acquisition days; l represents the number of all dimensions; c represents the number of times dimension data is collected within each day; / >Representing the number of numerical differences in the sequence of dimension data for the ith dimension throughout the day; />Indicating>The number of numerical differences in the dimensional data sequences of the individual dimensions; />Representing the variance of the first difference between the ith dimension and the jth dimension on the ith day; exp () represents an exponential function that bases on a natural constant.
Preferably, the step of segmenting the dimension data sequence according to the feature dimension to obtain a plurality of data segments includes the following specific steps:
presetting a first absolute value threshold, marking the absolute value of the slope difference value of each pair of adjacent two-dimensional data in the dimensional data sequence of each characteristic dimension as a first absolute value, and marking the dimensional data with the time sequence behind the adjacent two-dimensional data as an initial segmentation point if the first absolute value is larger than the first absolute value threshold;
acquiring all initial segmentation points in the dimension data sequence of each characteristic dimension in each day, marking the initial segmentation points as segmentation points, and segmenting the dimension data sequence of each dimension in each day according to all segmentation points in each day to obtain all data segments of the dimension data sequence of each dimension in each day;
all data segments of the dimensional data sequence for each dimension within each day are acquired.
Preferably, the obtaining the dimension change weight of the compressed segment according to the correlation of the feature dimension includes the following specific steps:
in the method, in the process of the invention,a dimension change weight representing an s-th compression segment of a j-th segment of data of a z-th dimension; w represents the number of dimensions of the first 6 other dimensions from large to small, of the correlation coefficient values with the dimension data sequence of the z-th dimension among all the dimension data sequences before each day; />A correlation coefficient value between the dimension data sequence representing the z-th dimension and the dimension data sequence representing the w-th dimension; />And the correlation coefficient value between the dimension data sequence of the jth data segment is removed from the z dimension and the dimension data sequence of the jth data segment is removed from the w dimension.
Preferably, the obtaining the distribution information value of the data segment according to the dimension change weight includes the specific steps:
recording the number of compressed segments of each segment of data for each dimension as a first number; accumulating and summing absolute values of differences between original dimension data and compressed data corresponding to each compressed segment of each data segment in each dimension to form a first accumulated value; recording the dimension change weight of each compressed segment of each data segment in each dimension as a first weight;
The product of the first weight and the first accumulated value is marked as a weight product, and the accumulated value of the first quantity of the weight product is marked as a distribution information value of each data segment of each dimension.
Preferably, the method for distributing the difference factor according to the data segment of the distributed information value includes the following specific steps:
in the method, in the process of the invention,a distribution information difference factor representing a jth segment of data in a z-th dimension; />A distribution information value representing a jth segment of data in a z-th dimension; />Representing the average value of all data segment distribution information values of the z dimension;representing the data segment with the largest value of the distribution information in the z-th dimension.
Preferably, the method for obtaining the compression efficiency of the data segment according to the number of compression segments of the data segment includes the following specific steps:
recording the number of compressed segments of each segment of data for each dimension as a third number; recording the maximum space number occupied by one dimension data compressed in the unit data segment of each dimension as the maximum space amount; recording the quantity of compressed data at the head end and the tail end in the compression section in the revolving door compression algorithm and the quantity of parameters of a linear equation corresponding to the compression section as a fourth quantity;
the product of the third number, the maximum amount of space, and the fourth number is noted as the compression efficiency for each data segment for each dimension.
Preferably, the method for obtaining the compression efficiency difference factor of the data segment according to the compression efficiency includes the following specific steps:
in the method, in the process of the invention,a compression efficiency difference factor representing a jth segment of data in a z-th dimension; />Compression efficiency of a jth segment of data representing a z-th dimension; />Representing the average value of the compression efficiency of all data segments in the z dimension; />Representing the most compression efficient data segment in the z-th dimension.
Preferably, the contribution degree of the compressed data is obtained according to the fitting necessity; obtaining an initial fitting weight value of compression data in a compression segment according to the contribution degree, wherein the initial fitting weight value comprises the following specific methods:
recording each compressed data of each compressed segment as first compressed data; the average value of all compressed data in each compressed segment is recorded as a first average value; recording the difference between the first compressed data and the first average value as a second difference;
recording the absolute value of the difference value between the original dimension data corresponding to each compressed data of each compressed segment and each compressed data as an initial absolute value; recording the absolute value average value of the difference values of all the original dimension data and the compressed data corresponding to each compressed segment as a second average value; recording the difference value between the initial absolute value and the second average value as a third difference value;
Recording the ratio of the second difference value to the third difference value as the contribution degree of each compressed data of each compressed segment;
the product of the contribution of each compressed data of each compressed segment and the necessity of fitting of each compressed segment is recorded as an initial fitting weight value of each compressed data in each compressed segment.
The embodiment of the invention provides an adaptive control system of a single-stage high-speed transmission, which comprises a sensor monitoring module, a data storage module, a control analysis module, an actuator control module, a diagnosis and fault detection module and a communication module, wherein:
the sensor monitoring module is used for collecting dimension data sequences of different dimensions;
the data storage module obtains the characteristic degree of each dimension according to the difference between the dimension data of the dimension data sequence; threshold screening is carried out on the dimensions according to the characteristic degree to obtain a plurality of characteristic dimensions; segmenting the dimension data sequence according to the characteristic dimension to obtain a plurality of data segments;
compressing the data segment to obtain a plurality of compressed segments; obtaining the dimension change weight of the compressed segment according to the correlation of the feature dimension; obtaining a distribution information value of the data segment according to the dimension change weight; a distribution difference factor of the data segment according to the distribution information value;
Obtaining the compression efficiency of the data segment according to the number of the compression segments of the data segment; obtaining a compression efficiency difference factor of the data segment according to the compression efficiency; obtaining the fitting necessity of the data segment according to the compression efficiency difference factor and the distribution difference factor;
obtaining the contribution degree of the compressed data according to the fitting necessity; obtaining an initial fitting weight value of compression data in the compression section according to the contribution degree; normalizing the initial fitting weight value to obtain a fitting weight value; fitting the compression segments according to the fitting weight values to obtain a plurality of partial least square model parameters; storing in a data storage module according to the least square model parameters;
the control analysis module decodes according to the data of the data storage module and inputs the decoded data into the control analysis module;
the actuator control module performs action execution on the relevant actuator of the single-stage high-speed transmission according to the output result obtained by the control analysis module;
the diagnosis and fault detection module monitors the working state of the whole control system;
and the communication module is used for transmitting data and instructions among the modules and communicating with other vehicle subsystems.
The technical scheme of the invention has the beneficial effects that: the method comprises the steps of segmenting a dimension data sequence according to characteristic dimensions to obtain a plurality of data segments, compressing the data segments to obtain a plurality of compressed segments, obtaining a distribution difference factor and a compression efficiency difference factor of the data segments according to the compressed segments, obtaining fitting necessity of the data segments according to the distribution difference factor and the compression efficiency difference factor, obtaining fitting weight values of each compressed data in the compressed segments according to the fitting necessity, obtaining corresponding least square model parameters, storing, and completing self-adaptive control.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of the steps of a method for adaptively controlling a single-stage high-speed transmission according to the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the present invention to achieve the preset purpose, the following description refers to the specific implementation, structure, characteristics and effects of a single-stage high-speed transmission self-adaptive control method and system according to the present invention with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following specifically describes a specific scheme of a self-adaptive control method and system for a single-stage high-speed transmission provided by the invention with reference to the accompanying drawings.
Referring to FIG. 1, a flowchart of a method for adaptively controlling a single-stage high-speed transmission according to an embodiment of the present invention is shown, the method comprising the steps of:
step S001: a sequence of dimensional data of different dimensions is acquired.
It should be noted that the adaptive control system of the single-stage high-speed transmission includes the following modules: the system comprises a sensor monitoring module, a data storage module, a control analysis module, an actuator control module, a diagnosis and fault detection module and a communication module.
The sensor monitoring module is used for collecting real-time data of a sensor of the electric automobile, such as motor rotation speed, battery state, load, temperature and the like.
The data storage module is used for storing the data acquired in the sensor monitoring module, wherein the stored data (including historical data and current data) are used for subsequently controlling the input data in the analysis module.
And the control analysis module is used for blurring input data of the PID controller according to the data in the data storage module to obtain an output result of the corresponding single-stage high-speed transmission.
And the actuator control module performs action execution on related actuators (such as a clutch, a hydraulic pump and the like) of the single-stage high-speed transmission according to the output result obtained by the control analysis module.
The diagnosis and fault detection module is used for monitoring the working state of the whole control system, such as temperature, pressure and other parameters, carrying out fault detection and diagnosis on abnormal conditions, and informing a driver to take corresponding measures through prompt or warning once the problem is found.
The communication modules are responsible for transmitting data and instructions between the various modules and for communicating with other vehicle subsystems, such as battery management systems, power stations, etc.
Specifically, before using the adaptive control system of the single-stage high-speed transmission, a plurality of dimension data sequences need to be collected through a sensor monitoring module, and the specific process of collecting the plurality of dimension data sequences is as follows:
and taking the temperature, the load, the motor rotation speed and other information of the sensor monitoring module as different dimensions, marking each value corresponding to each dimension as dimension data, acquiring dimension data of a plurality of dimensions of nearly one week, marking a sequence of time sequence ordered of the dimension data of the same dimension in all days as an initial dimension data sequence, marking a sequence of time sequence ordered of the dimension data of the same dimension in one day as a dimension data sequence, and acquiring dimension data sequences of different dimensions, wherein the sampling frequency of each dimension data is one hour, and the acquisition days are 7 days.
So far, a plurality of dimension data sequences with different dimensions are obtained.
Step S002: the feature degree of each dimension is obtained according to the dimension data sequence, the feature dimension is obtained according to the feature degree, and the dimension data sequence is segmented according to the feature dimension to obtain all data segments in the dimension data sequence of each feature dimension.
It should be noted that, although the conventional revolving door compression algorithm may divide a dimensional data sequence of a plurality of dimensions into a plurality of data segments of a fixed length, the information of each data segment is represented by an end-to-end straight line for each data segment through a tolerance set by people, so that the compression rate of the dimensional data is greatly improved, more dimensional data is lost, and the dimensional data cannot be decompressed and restored to effective dimensional data. In order to ensure that the dimensional data acquired by subsequent equipment is as comprehensive as possible, the plurality of dimensional data sequences can be integrally segmented according to the characteristic degrees of the plurality of dimensions, so that the dimensional data sequence of each dimension is divided into a plurality of segments of data segments; and wherein the degree of characteristic of each dimension is indicative of a change in dimension data for each dimension.
It should be further noted that, the feature degree of each dimension is related to the change feature of the dimension data of each dimension, and also related to the change of the dimension data of other dimensions, if the dimension data of a single dimension is changed greatly, the dimension data of other dimensions are also changed greatly at the same time, but the change degrees of the dimension data of other dimensions are not the same.
Specifically, any pair of adjacent dimension data difference amounts in a dimension data sequence of any dimension in any day are recorded as initial difference amounts, and a sequence formed by the initial difference amounts is recorded as a difference sequence, wherein the number of each difference sequence is consistent, and each dimension has one difference sequence; the absolute value of the difference between any pair of initial difference amounts with the same ordinal number in any two-dimensional difference sequences is recorded as the first difference of the two dimensions, and the embodiment describes the characteristic degree of the ith dimension in all days as an example, wherein the characteristic degree of the ith dimension in all daysThe calculation formula of (2) is as follows:
in the method, in the process of the invention,representing the characteristic degree of the ith dimension in all days; u represents the number of acquisition days; l represents the number of all dimensions; l-1 represents the number of dimensions divided by the ith dimension; c represents the number of times dimension data is collected within each day; / >Representing the number of numerical differences in the sequence of dimension data for the ith dimension throughout the day; />Indicating>The number of numerical differences in the dimensional data sequences of the individual dimensions; />Representation ofVariance of the first difference between the ith dimension and the jth dimension on the ith day; exp () represents an exponential function based on a natural constant, and in this embodiment, an exp (-) function is used to represent an inverse proportion relation and normalization processing, and an inverse proportion function and a normalization function can be selected according to actual situations; />Distribution variation and +.>If the difference is larger, the reference weight value of the ith dimension is smaller when the relation between the dimension data change of the ith dimension and the dimension data change of the jth dimension is calculated subsequently.
And acquiring the characteristic degrees of other dimensions in all days, and acquiring the characteristic degrees of all dimensions in all days.
Further, after the feature levels of all dimensions in all days are obtained, a feature level threshold T1 is preset, where in this embodiment, t1=0.65 is described as an example, and the present embodiment is not specifically limited, where T1 may be determined according to specific implementation conditions; if the feature degree of any dimension in all days is larger than the feature degree threshold, the dimension is marked as a feature dimension; and acquiring other characteristic dimensions in all days, and acquiring all characteristic dimensions in all days, wherein the characteristic dimensions in any day are consistent with the characteristic dimensions in all days.
Further, after all feature dimensions in all days are obtained, a first absolute value threshold T2 is preset, where in this embodiment is described by taking t2=0.5 as an example, and the embodiment is not specifically limited, where T2 may be determined according to specific implementation conditions; in this embodiment, description is made by taking any one characteristic dimension in any day as an example, the absolute value of the slope difference value of each pair of two adjacent dimension data in the dimension data sequence of the characteristic dimension is recorded as a first absolute value, and if the first absolute value is greater than a first absolute value threshold, dimension data with time sequence of two adjacent dimension data later is recorded as an initial segmentation point;
acquiring all initial segmentation points in the dimension data sequence of the characteristic dimension in the day; acquiring each initial segmentation point in all characteristic dimensions in the day, marking the initial segmentation points as segmentation points, and segmenting the dimension data sequences of all dimensions in the day according to all segmentation points in the day to obtain all data segments of the dimension data sequences of all dimensions in the day, wherein the dimension data sequences of all dimensions comprise a plurality of data segments, and each data segment comprises a plurality of dimension data; all data segments of the dimensional data sequence for each dimension within each day are acquired.
So far, all data segments of the dimension data sequence of each dimension in each day are acquired.
Step S003: performing revolving door compression processing on the data segments to obtain a plurality of compression segments, obtaining dimension change weights of the compression segments according to correlation of feature dimensions, obtaining distribution information values of the data segments according to the dimension change weights, and obtaining distribution difference factors of the data segments according to the distribution information values.
It should be noted that, after all the data segments of the dimensional data sequence of each dimension in each day are acquired, the predicted data compression rate may also be different for different data segments, so that in order to ensure higher compression efficiency, the fitting necessity of the fitting data of the data segments may be determined according to the predicted data compression rate, where the larger the data compression rate, the larger the fitting necessity.
It should be further noted that, because the distribution information included in each data segment is different and affects the estimated data compression rate, it is necessary to perform revolving door compression on a plurality of data segments according to a preset tolerance size, and divide each data segment into a plurality of compressed segments, where the change between the distribution information of the compressed segments and the distribution information of the corresponding data segments can be represented by the total difference between the original dimension data and all the compressed data in the compressed segments; since the data changes of the different compressed segments of each data segment are related to the original dimensional data changes of the relevant dimension of that dimension, the changes of the different compressed segments from the other dimensions need to be considered when computing the total difference.
Specifically, in this embodiment, the tolerance size T3 is preset to 0.2, which is not specifically limited in this embodiment, where T3 may be determined according to the specific implementation situation; after all data segments of the dimension data sequence of each dimension in each day are acquired, in this embodiment, the jth segment of the data segment in the dimension data sequence of the z-th dimension in any day is described by taking the compression of the data segment of the jth segment of the dimension data sequence of the z-th dimension as an example, a plurality of compression segments are obtained by performing revolving door compression according to a preset tolerance, each data in the compression segments is recorded as compression data, the data before each compression data in the compression segments is recorded as original dimension data, wherein the original dimension data corresponding to the compression segments is consistent with the number of the compression data, a revolving door compression algorithm is a known technology, and the embodiment is not described; the embodiment is described by taking the s-th compressed segment of the data segment as an example, wherein the calculation formula of the dimension change weight of the compressed segment is as follows:
in the method, in the process of the invention,a dimension change weight representing an s-th compression segment of a j-th segment of data of a z-th dimension; w represents the number of dimensions of the first 6 other dimensions from large to small of the correlation coefficient values with the dimension data sequence of the z-th dimension among all the dimension data sequences before the day; / >A correlation coefficient value between the dimension data sequence representing the z-th dimension and the dimension data sequence representing the w-th dimension; />The correlation coefficient value between the dimension data sequence representing the z dimension minus the j-th data segment and the dimension data sequence representing the w dimension minus the j-th data segment is obtained by pearson correlation coefficient, which is a known technique, and is not advanced in this embodimentThe row describes.
And acquiring the dimension change weight of each compressed segment of the jth segment data segment of the z dimension.
Further, according to the distribution information value from the dimension change weight of each compression segment of the jth segment of data segment of the jth dimension to the jth segment of data segment of the jth dimension, the calculation formula of the distribution information value of the jth segment of data segment of the jth dimension is:
in the method, in the process of the invention,a distribution information value representing a jth segment of data in a z-th dimension; />A number of compressed segments representing a jth segment of data segments in a z-th dimension; />An absolute value summation of differences between original dimension data and compressed data corresponding to an s-th compressed segment of a j-th segment of data representing a z-th dimension; />The dimension change weight of the s-th compressed segment of the j-th segment of data representing the z-th dimension.
Further, according to the distribution information value of the jth segment of data in the z dimension, a distribution information difference factor of the jth segment of data in the z dimension is obtained, and a calculation formula of the distribution information difference factor of the jth segment of data in the z dimension is as follows:
in the method, in the process of the invention,jth segment data representing a z-th dimensionA distribution information difference factor of the segments; />A distribution information value representing a jth segment of data in a z-th dimension; />Representing the average value of all data segment distribution information values of the z dimension;representing the data segment with the largest distribution information value in the z dimension; if->Then->The method comprises the steps of carrying out a first treatment on the surface of the If it isThen->The data segment has more information lost in the compression process by adopting the revolving door, and the fitting necessity of the data segment for fitting is larger.
Acquiring a distribution information difference factor of other data segments in the z dimension; acquiring distribution difference factors of all data segments in a z dimension; a distribution difference factor for each data segment in each dimension is obtained.
So far, the distribution difference factor of each data segment in each dimension is obtained.
Step S004: and obtaining the compression efficiency of the data segment according to the number of the compression segments of the data segment, obtaining a compression efficiency difference factor of the data segment according to the compression efficiency, and obtaining the fitting necessity of the data segment according to the compression efficiency difference factor and the distribution difference factor.
Specifically, the calculation formula of the compression efficiency of the jth segment data segment in the z dimension is as follows:
in the method, in the process of the invention,compression efficiency of a jth segment of data representing a z-th dimension; />A number of compressed segments representing a jth segment of data segments in a z-th dimension; />Representing the maximum space number occupied by compressed data of one dimension in the unit data segment of the z dimension; and 4, the number of compressed data at the head end and the tail end in the compression section in the revolving door compression algorithm and the number of parameters of a corresponding linear equation of the compression section are represented.
Further, according to the compression efficiency of the jth segment of data in the z dimension, a compression efficiency difference factor of the jth segment of data in the z dimension is obtained, and a calculation formula of the compression efficiency difference factor of the jth segment of data in the z dimension is as follows:
in the method, in the process of the invention,a compression efficiency difference factor representing a jth segment of data in a z-th dimension; />Compression efficiency of a jth segment of data representing a z-th dimension; />Representing the average value of the compression efficiency of all data segments in the z dimension; />Representing a data segment with the greatest compression efficiency in a z dimension; if->Then->The method comprises the steps of carrying out a first treatment on the surface of the If->ThenThe data segment can have a larger storage space in the compression process using the revolving door, and the fitting necessity for fitting is greater in the data segment.
Further, according to the distribution information difference factor of the jth segment data section of the z dimension and the compression efficiency difference factor of the jth segment data section of the z dimension, the necessity of the jth segment data section of the z dimension is obtained, and the calculation formula of the fitting necessity of the jth segment data section of the z dimension is as follows:
in the method, in the process of the invention,the necessity of fitting of the jth segment of data representing the z-th dimension; />A distribution information difference factor representing a jth segment of data in a z-th dimension; />The larger the distribution information difference factor is, the larger the compression efficiency difference factor is, and the larger the fitting necessity for fitting the corresponding data segment is.
Acquiring the fitting necessity of other data segments in the z dimension; acquiring the fitting necessity of all data segments in the z dimension; the necessity of fitting of all data segments in each dimension is obtained.
So far, the fitting necessity of all the data segments in each dimension is obtained through the method.
Step S005: and obtaining the contribution degree of the compressed segment according to the fitting necessity, obtaining the fitting weight value of the compressed data in the compressed segment according to the contribution degree, performing partial least squares fitting according to the fitting weight value to obtain a plurality of partial least squares model parameters, and storing the partial least squares model parameters in a data storage module according to the least squares model parameters.
After the fitting necessity of all the data segments in each dimension is obtained, the fitting necessity is required to be used as a reference value of the fitting weight value of each dimension data in a plurality of compressed segments of each data segment, and then the fitting weight value of each dimension data in each compressed segment can be obtained according to the contribution degree of each dimension data to the compressed segment in which the data segment is located.
Specifically, after the fitting necessity of all the data segments in each dimension is obtained, the fitting necessity is used as a reference value of the fitting weight value of each compressed data in a plurality of compressed segments of each data segment, and the fitting weight value of each compressed data in each compressed segment is obtained according to the contribution degree of each dimension data to the compressed segment where the dimension data is located, wherein the calculation formula of the contribution degree of the v-th compressed data in any compressed segment is as follows:
in the method, in the process of the invention,representing a contribution of the v-th compressed data of the compressed segment; />V-th compressed data representing the compressed segment; />Representing the average of all compressed data in the compressed segment; />Representing the sameThe absolute value of the difference value between the original dimension data corresponding to the v-th compressed data of the compressed segment and the v-th compressed data; / >Representing the absolute value average of the differences of the compressed segment corresponding to all the original dimension data and the compressed data.
Further, referring to the fitting necessity of the data segment, the fitting necessity of the compressed segment is obtained in a similar way, and the calculation formula of the initial fitting weight value of the v-th compressed data of the compressed segment is as follows:
in the method, in the process of the invention,an initial fitting weight value representing the v-th compressed data of the compressed segment; />Representing a contribution of the v-th compressed data of the compressed segment; />Indicating the necessity of fitting the compressed segment.
Acquiring initial fitting weight values of other compressed data in the compressed segment; acquiring initial fitting weight values of all compressed data in the compressed segment; and carrying out linear normalization processing on fitting weight values of all the compressed data in the compressed segments, marking each initial fitting weight value after processing as a fitting weight value, acquiring the fitting weight values of all the compressed data in each compressed segment, then carrying out partial least square fitting on the fitting weight values of all the compressed data in each compressed segment to obtain a partial least square fitting model and corresponding parameters of each compressed segment, and then inputting the compressed data at the head end and the tail end of each compressed segment and the parameters of the corresponding partial least square model into a data storage module for storage. The partial least squares fitting is a well-known technique, and this embodiment is not described.
Step S006: decoding is carried out according to the data of the data storage module, the decoded data is input into the control analysis module, and the follow-up module is executed to realize self-adaptive control.
Specifically, decompression is performed according to the compressed data at the head and tail ends of each compressed segment stored in the data storage module and the parameter input data of the corresponding partial least square model, all original dimension data are obtained, all original dimension data are input into the control analysis module, and the actuator control module, the diagnosis and fault detection module and the communication module are continued.
Thus, the self-adaptive control of the single-stage high-speed transmission is completed.
Through the steps, the self-adaptive control of the single-stage high-speed transmission is completed.
The embodiment provides an adaptive control system of a single-stage high-speed transmission, which comprises the following modules:
the sensor monitoring module is used for collecting dimension data sequences of different dimensions;
the data storage module obtains the characteristic degree of each dimension according to the difference between the dimension data of the dimension data sequence; threshold screening is carried out on the dimensions according to the characteristic degree to obtain a plurality of characteristic dimensions; segmenting the dimension data sequence according to the characteristic dimension to obtain a plurality of data segments;
Compressing the data segment to obtain a plurality of compressed segments; obtaining the dimension change weight of the compressed segment according to the correlation of the feature dimension; obtaining a distribution information value of the data segment according to the dimension change weight; a distribution difference factor of the data segment according to the distribution information value;
obtaining the compression efficiency of the data segment according to the number of the compression segments of the data segment; obtaining a compression efficiency difference factor of the data segment according to the compression efficiency; obtaining the fitting necessity of the data segment according to the compression efficiency difference factor and the distribution difference factor;
obtaining the contribution degree of the compressed data according to the fitting necessity; obtaining an initial fitting weight value of compression data in the compression section according to the contribution degree; normalizing the initial fitting weight value to obtain a fitting weight value; fitting the compression segments according to the fitting weight values to obtain a plurality of partial least square model parameters; storing in a data storage module according to the least square model parameters;
the control analysis module decodes according to the data of the data storage module and inputs the decoded data into the control analysis module;
the actuator control module performs action execution on the relevant actuator of the single-stage high-speed transmission according to the output result obtained by the control analysis module;
The diagnosis and fault detection module monitors the working state of the whole control system;
and the communication module is used for transmitting data and instructions among the modules and communicating with other vehicle subsystems.
According to the method and the device, the dimension data sequence is segmented according to the characteristic dimension to obtain a plurality of data segments, the data segments are compressed to obtain a plurality of compressed segments, the distribution difference factor and the compression efficiency difference factor of the data segments are obtained according to the compressed segments, then the fitting necessity of the data segments is obtained according to the distribution difference factor and the compression efficiency difference factor, the fitting weight value of each compressed data in the compressed segments is obtained according to the fitting necessity, and accordingly the corresponding least square model parameters are obtained and stored, and the self-adaptive control is completed.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Claims (10)
1. A method for adaptively controlling a single-stage high-speed transmission, comprising the steps of:
collecting dimension data sequences with different dimensions, wherein the dimension data sequences are composed of dimension data;
obtaining the characteristic degree of each dimension according to the difference between the dimension data of the dimension data sequence; threshold screening is carried out on the dimensions according to the characteristic degree to obtain a plurality of characteristic dimensions; segmenting the dimension data sequence according to the characteristic dimension to obtain a plurality of data segments;
compressing the data segment to obtain a plurality of compressed segments; obtaining the dimension change weight of the compressed segment according to the correlation of the feature dimension; obtaining a distribution information value of the data segment according to the dimension change weight; a distribution difference factor of the data segment according to the distribution information value;
obtaining the compression efficiency of the data segment according to the number of the compression segments of the data segment; obtaining a compression efficiency difference factor of the data segment according to the compression efficiency; obtaining the fitting necessity of the data segment according to the compression efficiency difference factor and the distribution difference factor;
obtaining the contribution degree of the compressed data according to the fitting necessity; obtaining an initial fitting weight value of compression data in the compression section according to the contribution degree; normalizing the initial fitting weight value to obtain a fitting weight value; fitting the compression segments according to the fitting weight values to obtain a plurality of partial least square model parameters; storing in a data storage module according to the least square model parameters;
Decoding is carried out according to the data of the data storage module, and the decoded data is input into the control analysis module to realize self-adaptive control.
2. The adaptive control method of a single-stage high-speed transmission according to claim 1, wherein the obtaining the characteristic degree of each dimension according to the difference between the dimension data of the dimension data sequence comprises the following specific steps:
recording any pair of adjacent dimension data difference values in a dimension data sequence of any one dimension in any one day as initial difference values, recording a sequence formed by the initial difference values as difference sequences, and recording the absolute value of the difference value between any pair of initial difference values with the same ordinal number in the difference sequences of any two dimensions as a first difference value;in the middle of，/>Representing the characteristic degree of the ith dimension in all days; u represents the number of acquisition days; l represents the number of all dimensions; c represents the number of times dimension data is collected within each day; />Representing the number of numerical differences in the sequence of dimension data for the ith dimension throughout the day; />Indicating>The number of numerical differences in the dimensional data sequences of the individual dimensions; />Representing the variance of the first difference between the ith dimension and the jth dimension on the ith day; exp () represents an exponential function that bases on a natural constant.
3. The adaptive control method of a single-stage high-speed transmission according to claim 1, wherein the step of segmenting the dimensional data sequence according to the characteristic dimension to obtain a plurality of data segments comprises the following specific steps:
presetting a first absolute value threshold, marking the absolute value of the slope difference value of each pair of adjacent two-dimensional data in the dimensional data sequence of each characteristic dimension as a first absolute value, and marking the dimensional data with the time sequence behind the adjacent two-dimensional data as an initial segmentation point if the first absolute value is larger than the first absolute value threshold;
acquiring all initial segmentation points in the dimension data sequence of each characteristic dimension in each day, marking the initial segmentation points as segmentation points, and segmenting the dimension data sequence of each dimension in each day according to all segmentation points in each day to obtain all data segments of the dimension data sequence of each dimension in each day;
all data segments of the dimensional data sequence for each dimension within each day are acquired.
4. The adaptive control method of a single-stage high-speed transmission according to claim 1, wherein the obtaining the dimension change weight of the compressed segment according to the correlation of the characteristic dimension comprises the following specific steps:
In (1) the->A dimension change weight representing an s-th compression segment of a j-th segment of data of a z-th dimension; w represents the number of dimensions of the first 6 other dimensions from large to small, of the correlation coefficient values with the dimension data sequence of the z-th dimension among all the dimension data sequences before each day; />A correlation coefficient value between the dimension data sequence representing the z-th dimension and the dimension data sequence representing the w-th dimension; />And the correlation coefficient value between the dimension data sequence of the jth data segment is removed from the z dimension and the dimension data sequence of the jth data segment is removed from the w dimension.
5. The adaptive control method of a single-stage high-speed transmission according to claim 1, wherein the obtaining the distribution information value of the data segment according to the dimension change weight comprises the following specific steps:
recording the number of compressed segments of each segment of data for each dimension as a first number; accumulating and summing absolute values of differences between original dimension data and compressed data corresponding to each compressed segment of each data segment in each dimension to form a first accumulated value; recording the dimension change weight of each compressed segment of each data segment in each dimension as a first weight;
The product of the first weight and the first accumulated value is marked as a weight product, and the accumulated value of the first quantity of the weight product is marked as a distribution information value of each data segment of each dimension.
6. The adaptive control method of a single-stage high-speed transmission according to claim 1, wherein the distribution difference factor according to the distribution information value includes the specific steps of:
in (1) the->A distribution information difference factor representing a jth segment of data in a z-th dimension; />A distribution information value representing a jth segment of data in a z-th dimension; />Representing the average value of all data segment distribution information values of the z dimension; />Representing the data segment with the largest value of the distribution information in the z-th dimension.
7. The adaptive control method of a single-stage high-speed transmission according to claim 1, wherein the obtaining the compression efficiency of the data segment according to the number of compression segments of the data segment comprises the following specific steps:
recording the number of compressed segments of each segment of data for each dimension as a third number; recording the maximum space number occupied by one dimension data compressed in the unit data segment of each dimension as the maximum space amount; recording the quantity of compressed data at the head end and the tail end in the compression section in the revolving door compression algorithm and the quantity of parameters of a linear equation corresponding to the compression section as a fourth quantity;
The product of the third number, the maximum amount of space, and the fourth number is noted as the compression efficiency for each data segment for each dimension.
8. The adaptive control method of a single-stage high-speed transmission according to claim 1, wherein the obtaining the compression efficiency difference factor of the data segment according to the compression efficiency comprises the following specific steps:
in (1) the->A compression efficiency difference factor representing a jth segment of data in a z-th dimension; />Compression efficiency of a jth segment of data representing a z-th dimension; />Representing the average value of the compression efficiency of all data segments in the z dimension; />Representing the most compression efficient data segment in the z-th dimension.
9. The adaptive control method of a single-stage high-speed transmission according to claim 1, wherein the contribution degree of compressed data is obtained according to necessity of fitting; obtaining an initial fitting weight value of compression data in a compression segment according to the contribution degree, wherein the initial fitting weight value comprises the following specific methods:
recording each compressed data of each compressed segment as first compressed data; the average value of all compressed data in each compressed segment is recorded as a first average value; recording the difference between the first compressed data and the first average value as a second difference;
Recording the absolute value of the difference value between the original dimension data corresponding to each compressed data of each compressed segment and each compressed data as an initial absolute value; recording the absolute value average value of the difference values of all the original dimension data and the compressed data corresponding to each compressed segment as a second average value; recording the difference value between the initial absolute value and the second average value as a third difference value;
recording the ratio of the second difference value to the third difference value as the contribution degree of each compressed data of each compressed segment;
the product of the contribution of each compressed data of each compressed segment and the necessity of fitting of each compressed segment is recorded as an initial fitting weight value of each compressed data in each compressed segment.
10. An adaptive control system for a single-stage high-speed transmission, the system comprising:
the sensor monitoring module is used for collecting dimension data sequences of different dimensions;
the data storage module obtains the characteristic degree of each dimension according to the difference between the dimension data of the dimension data sequence; threshold screening is carried out on the dimensions according to the characteristic degree to obtain a plurality of characteristic dimensions; segmenting the dimension data sequence according to the characteristic dimension to obtain a plurality of data segments;
compressing the data segment to obtain a plurality of compressed segments; obtaining the dimension change weight of the compressed segment according to the correlation of the feature dimension; obtaining a distribution information value of the data segment according to the dimension change weight; a distribution difference factor of the data segment according to the distribution information value;
Obtaining the compression efficiency of the data segment according to the number of the compression segments of the data segment; obtaining a compression efficiency difference factor of the data segment according to the compression efficiency; obtaining the fitting necessity of the data segment according to the compression efficiency difference factor and the distribution difference factor;
obtaining the contribution degree of the compressed data according to the fitting necessity; obtaining an initial fitting weight value of compression data in the compression section according to the contribution degree; normalizing the initial fitting weight value to obtain a fitting weight value; fitting the compression segments according to the fitting weight values to obtain a plurality of partial least square model parameters; storing in a data storage module according to the least square model parameters;
the control analysis module decodes according to the data of the data storage module and inputs the decoded data into the control analysis module;
the actuator control module performs action execution on the relevant actuator of the single-stage high-speed transmission according to the output result obtained by the control analysis module;
the diagnosis and fault detection module monitors the working state of the whole control system;
and the communication module is used for transmitting data and instructions among the modules and communicating with other vehicle subsystems.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310979905.7A CN116697039B (en) | 2023-08-07 | 2023-08-07 | Self-adaptive control method and system for single-stage high-speed transmission |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310979905.7A CN116697039B (en) | 2023-08-07 | 2023-08-07 | Self-adaptive control method and system for single-stage high-speed transmission |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116697039A true CN116697039A (en) | 2023-09-05 |
| CN116697039B CN116697039B (en) | 2023-09-29 |
Family
ID=87824314
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310979905.7A Active CN116697039B (en) | 2023-08-07 | 2023-08-07 | Self-adaptive control method and system for single-stage high-speed transmission |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116697039B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116974258A (en) * | 2023-09-25 | 2023-10-31 | 常熟理工学院 | Production process monitoring method based on multidimensional data |
| CN117478018A (en) * | 2023-12-28 | 2024-01-30 | 山东拓新电气有限公司 | Variable-frequency double-wheel milling machine speed regulation method and system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110995275A (en) * | 2019-11-20 | 2020-04-10 | 安徽省安泰科技股份有限公司 | Improved algorithm for revolving door compression algorithm |
| CN113191003A (en) * | 2021-05-08 | 2021-07-30 | 上海核工程研究设计院有限公司 | Nuclear power real-time data trend fitting algorithm |
| CN114282443A (en) * | 2021-12-28 | 2022-04-05 | 浙江大学 | Residual service life prediction method based on MLP-LSTM supervised joint model |
| CN115659070A (en) * | 2022-12-28 | 2023-01-31 | 鸿基骏业环保科技有限公司 | Water flow data transmission method based on NB-IOT intelligent water meter |
| CN115766607A (en) * | 2022-11-08 | 2023-03-07 | 陕西通信规划设计研究院有限公司 | Data compression transmission method based on 5G Internet of things |
| CN115987295A (en) * | 2023-03-20 | 2023-04-18 | 河北省农林科学院 | Crop monitoring data efficient processing method based on Internet of things |
-
2023
- 2023-08-07 CN CN202310979905.7A patent/CN116697039B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110995275A (en) * | 2019-11-20 | 2020-04-10 | 安徽省安泰科技股份有限公司 | Improved algorithm for revolving door compression algorithm |
| CN113191003A (en) * | 2021-05-08 | 2021-07-30 | 上海核工程研究设计院有限公司 | Nuclear power real-time data trend fitting algorithm |
| CN114282443A (en) * | 2021-12-28 | 2022-04-05 | 浙江大学 | Residual service life prediction method based on MLP-LSTM supervised joint model |
| CN115766607A (en) * | 2022-11-08 | 2023-03-07 | 陕西通信规划设计研究院有限公司 | Data compression transmission method based on 5G Internet of things |
| CN115659070A (en) * | 2022-12-28 | 2023-01-31 | 鸿基骏业环保科技有限公司 | Water flow data transmission method based on NB-IOT intelligent water meter |
| CN115987295A (en) * | 2023-03-20 | 2023-04-18 | 河北省农林科学院 | Crop monitoring data efficient processing method based on Internet of things |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116974258A (en) * | 2023-09-25 | 2023-10-31 | 常熟理工学院 | Production process monitoring method based on multidimensional data |
| CN116974258B (en) * | 2023-09-25 | 2023-12-08 | 常熟理工学院 | Production process monitoring method based on multidimensional data |
| CN117478018A (en) * | 2023-12-28 | 2024-01-30 | 山东拓新电气有限公司 | Variable-frequency double-wheel milling machine speed regulation method and system |
| CN117478018B (en) * | 2023-12-28 | 2024-03-01 | 山东拓新电气有限公司 | Variable-frequency double-wheel milling machine speed regulation method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116697039B (en) | 2023-09-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116697039B (en) | Self-adaptive control method and system for single-stage high-speed transmission | |
| CN109597315B (en) | Method, equipment and system for identifying health degradation state of mechanical equipment | |
| CN117278643B (en) | Vehicle-mounted cloud calibration data transmission system based on cloud edge cooperation | |
| CN117235557B (en) | Electrical equipment fault rapid diagnosis method based on big data analysis | |
| CN111079989A (en) | Water supply company water supply amount prediction device based on DWT-PCA-LSTM | |
| CN116226484B (en) | Ultrafiltration water treatment device monitoring data management system | |
| CN116320042B (en) | Internet of things terminal monitoring control system for edge calculation | |
| CN113361766B (en) | Multi-mode precipitation prediction method integrated with machine learning | |
| CN103346797B (en) | A kind of real-time compression method for gear distress signal | |
| CN116010900A (en) | Multi-scale feature fusion gearbox fault diagnosis method based on self-attention mechanism | |
| CN116842364A (en) | Rolling bearing fault method for asynchronous motor | |
| CN113821875A (en) | Intelligent vehicle fault real-time prediction method and system based on end cloud cooperation | |
| CN117574305B (en) | Real-time monitoring method and system for running state of equipment | |
| CN116400870A (en) | On-site construction on-line management system based on Internet of things | |
| CN110874665A (en) | Control device and method for wind generating set | |
| CN116975503A (en) | Soil erosion information management method and system | |
| CN116467577A (en) | Fan gear box fault diagnosis method based on MTF and improved dense connection network | |
| CN117407681B (en) | Time sequence data prediction model establishment method based on vector clustering | |
| CN116596129A (en) | Electric vehicle charging station short-term load prediction model construction method | |
| CN113435235B (en) | Equipment state representation extraction method based on recursive fusion encoder | |
| CN116450592B (en) | Working condition self-adaptive compression method and system based on industrial big data characteristics | |
| CN107862394A (en) | A kind of equipment active maintenance support Synergistic method | |
| CN113468818A (en) | Method and device for monitoring winding running state of wind generating set | |
| CN114201825A (en) | Method and system for evaluating equipment performance degradation state based on combination characteristics | |
| CN110059289B (en) | Engineering vehicle load power prediction method based on Kalman filtering neural network |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20240111 Address after: 239000, No. 314, Lingxi Road, Chuzhou City, Anhui Province Patentee after: ANHUI C-E-CARS YANGZI AUTOMOBILE Co.,Ltd. Address before: 100000 1017, Floor 10, Building 2, Yard 46, Tianshui Street, Daxing District, Beijing Patentee before: Dedian Beidou Electric Vehicle Co.,Ltd. |