CN117421620B - Interaction method of tension state data - Google Patents
Interaction method of tension state data Download PDFInfo
- Publication number
- CN117421620B CN117421620B CN202311732848.9A CN202311732848A CN117421620B CN 117421620 B CN117421620 B CN 117421620B CN 202311732848 A CN202311732848 A CN 202311732848A CN 117421620 B CN117421620 B CN 117421620B
- Authority
- CN
- China
- Prior art keywords
- data
- chain
- state data
- influence
- chain state
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 230000003993 interaction Effects 0.000 title claims abstract description 15
- 238000012544 monitoring process Methods 0.000 claims abstract description 6
- 238000004364 calculation method Methods 0.000 claims description 8
- 230000005856 abnormality Effects 0.000 claims description 5
- 238000010606 normalization Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 2
- 230000002159 abnormal effect Effects 0.000 description 15
- 238000010586 diagram Methods 0.000 description 6
- 238000012937 correction Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000005452 bending Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000000758 substrate Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000003245 coal Substances 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 238000006467 substitution reaction 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
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23211—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with adaptive number of clusters
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01L—MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER, MECHANICAL EFFICIENCY, OR FLUID PRESSURE
- G01L5/00—Apparatus for, or methods of, measuring force, work, mechanical power, or torque, specially adapted for specific purposes
- G01L5/0028—Force sensors associated with force applying means
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
- G01M13/02—Gearings; Transmission mechanisms
- G01M13/023—Power-transmitting endless elements, e.g. belts or chains
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Probability & Statistics with Applications (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Complex Calculations (AREA)
Abstract
The invention relates to the technical field of electronic digital data processing, in particular to an interaction method of tension state data, which comprises the following steps: obtaining the influence degree of the data points according to the data values of the data points, adjusting the distance between the chain state data by using the influence degree to obtain the influence parameters of the chain state data, adjusting the data values and the direction values of the data points by using the average value of the influence parameters, clustering, further obtaining the early warning degree according to the clustering clusters, and carrying out state monitoring on the chain by using the early warning degree. The invention solves the problem of inaccurate data value and direction value of data points in the chain state data caused by the mutual influence relationship between adjacent positions due to the continuity of the chain, improves the accuracy of clustering results obtained by clustering according to the data value and the direction value of the data points, further improves the accuracy of detecting the tension state of the chain, and ensures the normal operation of the chain of the scraper.
Description
Technical Field
The invention relates to the technical field of electronic digital data processing, in particular to an interaction method of tension state data.
Background
Usually, coal is transported by using a scraper, and a chain of the scraper is a key component of the scraper, and tension on the chain is critical to normal operation of the scraper, so that the running state of the chain needs to be detected, so that the chain is maintained in time, and the chain is prevented from being interrupted or unstable.
When detecting the running state of the chain, abnormal data points can be separated after the chain is clustered due to excessive wear and interference of other positions of the chain, so that the obtained chain state data are clustered to obtain abnormal data and early warning is carried out.
However, due to the fact that factors affecting each other exist among all positions of the chain, the corresponding chain state data of all positions of the chain are inaccurate, and further the clustering result of the chain state data is inaccurate, so that the running state of the chain is inaccurate to detect, and normal running of the chain of the scraper can not be guaranteed.
Disclosure of Invention
The invention provides an interaction method of tension state data, which aims to solve the existing problems.
The invention relates to an interaction method of tension state data, which adopts the following technical scheme:
an embodiment of the present invention provides a method for interaction of tension state data, the method comprising the steps of:
acquiring chain state data at different positions on a chain, wherein one position corresponds to one chain state data, and one data point in the chain state data corresponds to one time point, one data value and one direction value;
obtaining the influence degree of the data points according to the data value of the corresponding data point at any time point in the chain state data, and adjusting the distance between the chain state data by utilizing the influence degree to obtain the influence parameter of the chain state data;
obtaining neighborhood influence parameters of the chain state data according to the influence parameter mean values of the plurality of chain state data, wherein the neighborhood influence parameters are used for describing the influence degree of all the chain state data at adjacent positions of the chain state data at corresponding time points; respectively adjusting the data value and the direction value of the data points by using the neighborhood influence parameters to obtain a corrected data value and a corrected direction value of the data points, clustering the data points of the chain state data to obtain a plurality of cluster clusters, and obtaining the early warning degree of the corresponding position of the chain state data on the chain according to the quantity of the chain state data of the data points in the cluster clusters, wherein the early warning degree is used for describing the probability of the occurrence of the tension state abnormality at the corresponding position of the chain state data;
and monitoring the state of the chain by utilizing the early warning degree.
Further, the method for obtaining the influence degree of the data point according to the data value of the corresponding data point at any time point in the chain state data comprises the following specific steps:
firstly, recording corresponding data points at the same time point in all the chain state data as simultaneous data points;
then, the influence degree of the data points in the chain state data at any time point is obtained, and the specific calculation method comprises the following steps:
wherein,indicate->The influence degree of the data points at the corresponding time points in the chain state data; />Indicate->Data values of data points at corresponding time points in the chain state data; />Representing the data value mean of all the chain state data at the same time data points at the corresponding time points; />Representing the identity of all chain status data at the corresponding time pointStandard deviation of data values of time data points; />Representing absolute value symbols; />Representing a linear normalization function.
Further, the method for obtaining the influence parameters of the chain state data by adjusting the distance between the chain state data by using the influence degree comprises the following specific steps:
firstly, obtaining an influence range of a data point according to the influence degree;
then, obtaining influence data of the chain state data according to the influence range of the data points; acquiring Euclidean distance between chain state data and corresponding arbitrary influence data; the method for acquiring the influence parameters of the chain state data on the influence data at any time point comprises the following steps of:
wherein,indicate->The number of pairs of chain state data->Influence parameters of the influence data; />Indicate->Chain status data and->The Euclidean distance between the individual impact data; />Indicate->The degree of influence of the data points of the individual chain state data; />An exponential function based on a natural constant is represented.
Further, the method for obtaining the influence range of the data point according to the influence degree comprises the following specific steps:
presetting a super parameter R0, marking the product of the super parameter R0 and the influence degree of the data points in the chain state data at any time point as a first value, and rounding down the first value to obtain the influence range of the data points at the corresponding time point.
Further, the method for obtaining the influence data of the chain state data according to the influence range of the data points comprises the following specific steps:
at any time point, acquiring corresponding positions of the chain state data, wherein the left side and the right side of the corresponding positions are respectively corresponding toThe chain status data, recorded as +.>Influence data of the individual chain status data.
Further, the method for obtaining the neighborhood influence parameters of the chain state data according to the influence parameter mean value of the plurality of chain state data comprises the following specific steps:
acquiring influence parameters of the chain state data at any position, which are influenced by the plurality of chain state data, and recording the average value of all the influence parameters of the chain state data at any position, which are influenced by the plurality of chain state data, as a neighborhood influence parameter of the chain state data.
Further, the method for obtaining the corrected data value and the corrected direction value of the data point by respectively adjusting the data value and the direction value of the data point by using the neighborhood influence parameters comprises the following specific steps:
and multiplying the neighborhood influence parameters of the chain state data with the data value and the direction value of the data point respectively at any time point to obtain the corrected data value and the corrected direction value of the data point.
Further, the clustering is performed on the data points of the chain state data to obtain a plurality of clusters, and the early warning degree of the corresponding position of the chain state data on the chain is obtained according to the quantity of the chain state data to which the data points belong in the clusters, comprising the following specific methods:
firstly, clustering data points of chain state data at all time points by using an ISODATA algorithm according to Euclidean distance between corrected data values and corrected direction values of the data points to obtain a plurality of cluster clusters; acquiring state parameters of the cluster according to the chain state data of the data points in the cluster;
then, the early warning degree of the corresponding position of the chain state data is obtained, and the specific calculation method comprises the following steps:
wherein,indicate->Early warning degrees of corresponding positions of the chain state data; />Indicate->The number of all data points in the individual chain status data; />Indicate->The first part of the chain status data>The time points correspond to state parameters of the cluster to which the data points belong; />Representing the number of all chain status data; />An exponential function based on a natural constant is represented.
Further, the method for obtaining the state parameters of the cluster according to the state data of the chains to which the data points belong in the cluster comprises the following specific steps:
the cluster comprises a plurality of data points, the data points belong to the same chain state data, and the number of the chain state data of all the data points in the cluster is recorded as the state parameter of the cluster.
Further, the method for monitoring the state of the chain by utilizing the early warning degree comprises the following specific steps:
firstly, constructing a two-dimensional rectangular coordinate system, taking the index position of a sensor as an abscissa, taking the early warning degree as an ordinate, drawing an image of the early warning degree of a position corresponding to chain state data obtained by each sensor on a chain of a scraper machine, and recording the image as an early warning degree image;
then, when the early warning degree appears in the early warning degree image to be larger than a preset threshold valueAnd when the warning degree image is detected, the corresponding sensor in the warning degree image is marked and an alarm is sent out.
The technical scheme of the invention has the beneficial effects that: the method has the advantages that the influence relation among corresponding chain state data at a plurality of positions of the chain is analyzed, the data value and the direction value of the data points in the chain state data are adjusted, the problem that the data value and the direction value of the data points in the chain state data are inaccurate due to the fact that the adjacent positions form the mutual influence relation caused by the continuity of the chain is avoided, the accuracy of clustering results obtained by clustering according to the data value and the direction value of the data points is improved, the accuracy of tension state detection of the chain is further improved, and the normal running of the chain of the scraper is guaranteed.
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 showing the steps of a method for interacting tension state data according to the present invention;
FIG. 2 is a schematic view ofSchematic drawing;
FIG. 3 is a schematic view ofA corresponding schematic diagram on the chain;
FIG. 4 is a schematic view of a chain being subjected to an abnormal impact of a foreign object;
fig. 5 is a schematic diagram of a chain transport weight.
Detailed Description
In order to further describe the technical means and effects adopted by the present invention to achieve the preset purpose, the following detailed description refers to the specific implementation, structure, characteristics and effects of a tension state data interaction method 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 tension state data interaction method provided by the invention with reference to the accompanying drawings.
Referring to fig. 1, a flowchart illustrating a method for interacting tension state data according to an embodiment of the present invention is shown, the method includes the following steps:
step S001: chain state data at different positions on the chain is acquired.
It should be noted that, when the tension corresponding to any position of the chain is too high in the working process of the chain of the scraper, the position has the risk of chain breakage; when the corresponding tension at any position of the chain is too small, the position has the risk of piling the chain; when any position of the chain is subjected to abnormal impact, the chain is also at risk of breakage; the relationship between the chain position and the tension in this embodiment is referred to asRelation, will->The corresponding diagram of the relation is->A diagram, as shown in fig. 2; />The corresponding schematic diagram of the diagram on the chain is shown in fig. 3.
Specifically, in order to implement the interaction method of tension state data provided in this embodiment, the chain state data needs to be collected first, and the specific process is as follows:
the method comprises the steps of acquiring tension at a plurality of positions of a chain by using a sensor, recording time sequence data of the tension at different positions of the chain as chain state data, wherein one position corresponds to one chain state data, and storing the acquired chain state data, and one data point in the chain state data corresponds to one time point, one data value and one direction value.
The sensor for acquiring the chain state data is a strain sensor, and the data value and the direction value of the data point respectively represent the magnitude and the direction of the tension applied to the corresponding position of the chain state data at the corresponding time point.
It should be noted that the chain status data of the chain is very important for maintaining and monitoring the performance and safety of the chain drive system. By detecting the tension of the chain, problems in the chain can be detected early, such as uneven stress distribution of the chain caused by too high or too low tension at certain positions of the chain, uneven tension distribution possibly causing bending or twisting of the chain, especially between rolling parts of a chain transmission system, which bending or twisting may cause a breaking risk of the chain in uneven stress areas.
It should be noted that, the distance interval between every two sensors is preset to be 10cm, and the acquisition time interval of each sensor is 2 seconds/time.
Thus, the chain state data is obtained through the method.
Step S002: and obtaining the influence degree of the data points according to the data value of the corresponding data point at any time point in the chain state data, and adjusting the distance between the chain state data by utilizing the influence degree to obtain the influence parameters of the chain state data.
It should be noted that, for the chain state data of different positions in the chain, the degree of abnormality of the data needs to be determined, and the degree of abnormality of the chain state data of each position determines the degree to which the chain state data of the position needs to be pre-warned, however, the degree of abnormality of the chain state data of each position depends on the number of data in the cluster after all the chain state data are clustered, and the more the data indicates that the data point is more normal, and otherwise abnormal. Because the data with larger similarity degree are clustered into one type when the data are clustered, but abnormal data points in the chain state data influence the size and the tension direction of the data corresponding to adjacent positions, so that the adjacent data points become abnormal points, the influence range and the influence size of the chain state data need to be acquired, and the surrounding chain state data are adjusted according to the influence range and the influence size, so that the clustering result is more accurate.
It should be noted that, under the normal running state of the chain, the values of the chain state data of the chain at all positions are relatively close, and the tension direction is along the current running direction of the chain. When the chain is operated in an abnormal state, as shown in fig. 4 and 5, when a foreign matter abnormal impact or heavy load is transported at a certain position of the chain, the tension of the chain at the corresponding position is greatly changed, and the chain state data near the position is changed to some extent due to the physical continuity of the chain. Therefore, it is necessary to calculate the degree of influence thereof on the surrounding data at the present time from the chain state data acquired at each time of each position.
Specifically, in step (1), first, corresponding data points at the same time point in all the chain state data are recorded as simultaneous data points.
Then, the influence degree of the data points in the chain state data at any time point is obtained, and the specific calculation method comprises the following steps:
wherein,indicate->The influence degree of the data points at the corresponding time points in the chain state data; />Indicate->Data values of data points at corresponding time points in the chain state data; />Representing the data value mean of all the chain state data at the same time data points at the corresponding time points; />Representing standard deviations of data values of simultaneous data points in all chain state data at corresponding time points; />Representing absolute value symbols; />Representing a linear normalization function.
It should be noted that the number of the substrates,represents +.>The larger the difference between the value of the chain state data of each position and the average value of all the chain state data acquired at the moment, the more abnormal the chain state data of the position is, namely the greater the influence degree of the chain state data of the position on surrounding data is.
It should be noted that the number of the substrates,the smaller the standard deviation, namely the discrete degree, of all the chain state data collected at the moment is, the lower the discrete degree of all the chain state data collected at the moment is, and the larger the discrete degree of all the chain state data collected at the moment is, the higher the discrete degree of all the chain state data collected at the moment is. In view of the above-mentioned, it is desirable,then the +.>The degree of outlier of the values of the chain state data of each position indicates the time point +.>The more abnormal the chain state data of each position, the greater the degree of influence on surrounding data, and vice versaThe smaller the value, the description of the time +.>The more normal the chain state data at each location, the less the degree of influence on the surrounding data.
The greater the degree of influence of the chain state data at one position on the certain chain on the surrounding data, the higher the degree of abnormal impact of the foreign matter or the higher the mass of the transported heavy object, the greater the influence range and the influence size of the chain state data at any position on the surrounding data, so the influence range and the influence size of the chain state data at any position on the surrounding data are calculated according to the influence degree of the chain state data at any position on the surrounding data.
Step (2), firstly, obtaining the influence range of data points in the chain state data at any time point, wherein the specific calculation method comprises the following steps:
wherein,indicate->The range of influence of the data points of the individual chain state data; />Representing preset super parameters; />Indicate->The degree of influence of the data points of the individual chain state data; />Representing rounding down symbols.
It should be noted that a preset oneSuper parameterWherein the present embodiment is +.>For the purpose of illustration, the embodiment is not specifically limited, wherein +.>Depending on the particular implementation.
Then, at any time point, the corresponding position of the chain state data is obtained, and the left and right adjacent sides are respectively correspondingThe chain status data, recorded as +.>Influence data of the individual chain state data; acquiring Euclidean distance between chain state data and corresponding arbitrary influence data; the method for acquiring the influence parameters of the chain state data on the influence data at any time point comprises the following steps of:
wherein,indicate->The number of pairs of chain state data->Influence parameters of the influence data; />Indicate->Chain status data and->The Euclidean distance between the individual impact data; />Indicate->The degree of influence of the data points of the individual chain state data; />An exponential function based on a natural constant is represented.
It should be noted that, at any time point, the greater the influence degree of the chain state data on the chain state data at the adjacent position, the greater the influence range; the larger the Euclidean distance between the chain state data and the influence data is, the smaller the influence of the chain state data on the data value of the data point in the influence data is.
So far, the influencing parameters of the chain state data are obtained through the method.
Step S003: obtaining neighborhood influence parameters of the chain state data according to the influence parameter mean values of the plurality of chain state data, respectively adjusting the data value and the direction value of the data points by utilizing the neighborhood influence parameters to obtain a corrected data value and a corrected direction value of the data points, clustering the data points of the chain state data to obtain a plurality of clusters, and obtaining the early warning degree of the corresponding position of the chain state data on the chain according to the quantity of the chain state data of the data points in the clusters.
When the chain state data of one position affects the chain state data of an adjacent position, that is, the chain state data of the adjacent position is affected by the chain state data of the position, the chain state data of the same position may be affected by the chain state data of a plurality of positions, so that the influence of the chain state data of each position on the surrounding data and the influence of the chain state data of each position on the surrounding data need to be obtained according to the influence range of the chain state data of each position and the influence of the chain state data of each position on the surrounding data.
Specifically, in step (1), first, the chain state data at any position is subjected to influence parameters corresponding to a plurality of chain state data at any time point, and the average value of all the influence parameters corresponding to the plurality of chain state data at any time point is recorded as a neighborhood influence parameter of the chain state data at the corresponding time point.
It should be noted that, the neighborhood influence parameter is used to describe the extent to which the chain state data is influenced by all the chain state data at the adjacent position at the corresponding time point, and the larger the neighborhood influence parameter is, the larger the extent to which the chain state data is influenced by all the chain state data at the adjacent position at the corresponding time point is, and vice versa is.
It should be noted that, since the chain of the scraper machine has a closed loop shape, the sensors at the first position and the last position are adjacent after being arranged in sequence, so that when the influence of the chain state data at each position on the chain state data at the adjacent position is analyzed, the situation of out-of-boundary exists, that is, the situation of no chain state data at the adjacent position does not exist.
It should be noted that, since the chain is continuous, the chain state data will generally show a certain scale of change during the working process, that is, the data value of the data point in the chain state data is not only determined by the corresponding position but also affected by the adjacent position, so the chain state data of each position needs to be corrected according to the influence of the surrounding data of the chain state data.
Then, a correction data value and a correction direction value of a corresponding data point in the chain state data at any time point are obtained, and the specific calculation method comprises the following steps:
in the method, in the process of the invention,indicate->The corrected data values of the data points at the corresponding time points in the chain state data; />Represents +.>Neighborhood impact parameters for the individual chain state data; />Indicate->Data values of data points at corresponding time points in the chain state data; />Indicate->Correcting direction values of data points at corresponding time points in the chain state data; />Represent the firstThe direction value of the data point at the corresponding time point in the individual chain state data.
Step (2), firstly, clustering data points of chain state data at all time points by using an ISODATA algorithm according to Euclidean distance between corrected data values and corrected direction values of the data points to obtain a plurality of clusters, wherein one cluster comprises a plurality of data points, the plurality of data points belong to the same chain state data, and the quantity of the chain state data of all the data points in the cluster is recorded as the state parameter of the cluster.
It should be noted that, the state parameter is used to describe the fluctuation degree of the stress at the position corresponding to the chain state data at all time points, the smaller the state parameter of the cluster is, the smaller the quantity of the chain state data of the data points in the cluster is, the higher the consistency of the correction data value and the correction direction value of the data points in the chain state data in the cluster is, the smaller the fluctuation degree of the stress at the position corresponding to the chain state data is, and otherwise, the larger the fluctuation degree of the stress at the position corresponding to the chain state data is.
Then, the early warning degree of the corresponding position of the chain state data is obtained, and the specific calculation method comprises the following steps:
wherein,indicate->Early warning degrees of corresponding positions of the chain state data; />Indicate->The number of all data points in the individual chain status data; />Indicate->The first part of the chain status data>The time points correspond to state parameters of the cluster to which the data points belong; />Representing the number of all chain status data; />An exponential function based on a natural constant is represented.
The early warning degree is used for describing the probability of abnormal tension state at the position corresponding to the chain state data; because the part of the chain with abnormal tension is smaller, the fewer the number of data points in a cluster obtained by clustering the chain state data, the greater the probability of abnormal tension state of the chain state data in the cluster, the greater the corresponding early warning degree, and conversely, the smaller the early warning degree.
So far, the early warning degree of the corresponding position of each chain state data is obtained through the method.
Step S004: and monitoring the state of the chain by utilizing the early warning degree.
Specifically, firstly, a two-dimensional rectangular coordinate system is constructed, the index positions of the sensors are taken as the abscissa, the early warning degree is taken as the ordinate, an image of the early warning degree of the position corresponding to the chain state data obtained by each sensor on the chain of the scraper is drawn, and the image is recorded as an early warning degree image.
Then, when the early warning degree appears in the early warning degree image to be larger than a preset threshold valueAnd when the warning degree image is detected, the corresponding sensor in the warning degree image is marked and an alarm is sent out.
The threshold value is preset empiricallyThe present embodiment is not particularly limited, as the case may be.
This embodiment is completed.
The following examples were usedThe model is used only to represent the negative correlation and constraint model outputsThe result of (2) is->In the section, other models with the same purpose can be replaced in the implementation, and the embodiment only uses +.>The model is described as an example, without specific limitation, wherein +.>Refers to the input of the model.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the invention, but any modifications, equivalent substitutions, improvements, etc. within the principles of the present invention should be included in the scope of the present invention.
Claims (6)
1. A method of interaction of tension state data, the method comprising the steps of:
acquiring chain state data of different positions on a chain of the scraper, wherein one position corresponds to one chain state data, and one data point in the chain state data corresponds to one time point, one data value and one direction value;
obtaining the influence degree of the data points according to the data value of the corresponding data point at any time point in the chain state data, and adjusting the distance between the chain state data by utilizing the influence degree to obtain the influence parameter of the chain state data;
obtaining neighborhood influence parameters of the chain state data according to the influence parameter mean values of the plurality of chain state data, wherein the neighborhood influence parameters are used for describing the influence degree of all the chain state data at adjacent positions of the chain state data at corresponding time points; respectively adjusting the data value and the direction value of the data points by using the neighborhood influence parameters to obtain a corrected data value and a corrected direction value of the data points, clustering the data points of the chain state data to obtain a plurality of cluster clusters, and obtaining the early warning degree of the corresponding position of the chain state data on the chain according to the quantity of the chain state data of the data points in the cluster clusters, wherein the early warning degree is used for describing the probability of the occurrence of the tension state abnormality at the corresponding position of the chain state data;
the state of the chain is monitored by utilizing the early warning degree;
the method for obtaining the influence degree of the data point according to the data value of the corresponding data point at any time point in the chain state data comprises the following specific steps:
firstly, recording corresponding data points at the same time point in all the chain state data as simultaneous data points;
then, the influence degree of the data points in the chain state data at any time point is obtained, and the specific calculation method comprises the following steps:
wherein,indicate->The influence degree of the data points at the corresponding time points in the chain state data; />Indicate->Data values of data points at corresponding time points in the chain state data; />Representing the data value mean of all the chain state data at the same time data points at the corresponding time points; />Representing standard deviations of data values of simultaneous data points in all chain state data at corresponding time points; />Representing absolute value symbols; />Representing a linear normalization function;
the method for obtaining the influence parameters of the chain state data by adjusting the distance between the chain state data by using the influence degree comprises the following specific steps:
firstly, obtaining an influence range of a data point according to the influence degree;
then, obtaining influence data of the chain state data according to the influence range of the data points; acquiring Euclidean distance between chain state data and corresponding arbitrary influence data; the method for acquiring the influence parameters of the chain state data on the influence data at any time point comprises the following steps of:
wherein,indicate->The number of pairs of chain state data->Influence parameters of the influence data; />Indicate->Chain status data and->Euler between individual influence dataA distance; />Indicate->The degree of influence of the data points of the individual chain state data; />An exponential function based on a natural constant;
the method for obtaining the influence range of the data points according to the influence degree comprises the following specific steps:
presetting a super parameter R0, marking the product of the super parameter R0 and the influence degree of data points in the chain state data at any time point as a first numerical value, and rounding down the first numerical value to obtain the influence range of the data points at the corresponding time point;
the method for obtaining the influence data of the chain state data according to the influence range of the data points comprises the following specific steps:
at any time point, acquiring corresponding positions of the chain state data, wherein the left side and the right side of the corresponding positions are respectively corresponding toThe chain status data, recorded as +.>Influence data of the individual chain status data.
2. The method for interaction of tension state data according to claim 1, wherein the method for obtaining the neighborhood influence parameters of the chain state data according to the influence parameter mean value of the plurality of chain state data comprises the following specific steps:
acquiring influence parameters of the chain state data at any position, which are influenced by the plurality of chain state data, and recording the average value of all the influence parameters of the chain state data at any position, which are influenced by the plurality of chain state data, as a neighborhood influence parameter of the chain state data.
3. The method for interaction of tension state data according to claim 1, wherein the adjusting the data value and the direction value of the data point by using the neighborhood influence parameter to obtain the corrected data value and the corrected direction value of the data point comprises the following specific steps:
and multiplying the neighborhood influence parameters of the chain state data with the data value and the direction value of the data point respectively at any time point to obtain the corrected data value and the corrected direction value of the data point.
4. The interaction method of tension state data according to claim 1, wherein the clustering of the data points of the chain state data to obtain a plurality of clusters, and obtaining the early warning degree of the corresponding position of the chain state data on the chain according to the number of the chain state data to which the data points in the clusters belong, comprises the following specific steps:
firstly, clustering data points of chain state data at all time points by using an ISODATA algorithm according to Euclidean distance between corrected data values and corrected direction values of the data points to obtain a plurality of cluster clusters; acquiring state parameters of the cluster according to the chain state data of the data points in the cluster;
then, the early warning degree of the corresponding position of the chain state data is obtained, and the specific calculation method comprises the following steps:
wherein,indicate->Early warning degrees of corresponding positions of the chain state data; />Indicate->The number of all data points in the individual chain status data; />Indicate->The first part of the chain status data>The time points correspond to state parameters of the cluster to which the data points belong; />Representing the number of all chain status data; />An exponential function based on a natural constant is represented.
5. The method for interacting tension state data according to claim 4, wherein the step of obtaining the state parameters of the cluster according to the chain state data to which the data points in the cluster belong comprises the following specific steps:
the cluster comprises a plurality of data points, the data points belong to the same chain state data, and the number of the chain state data of all the data points in the cluster is recorded as the state parameter of the cluster.
6. The method for interaction of tension state data according to claim 1, wherein the step of monitoring the state of the chain by using the early warning degree comprises the following specific steps:
firstly, constructing a two-dimensional rectangular coordinate system, taking the index position of a sensor as an abscissa, taking the early warning degree as an ordinate, drawing an image of the early warning degree of a position corresponding to chain state data obtained by each sensor on a chain of a scraper machine, and recording the image as an early warning degree image;
then, when the early warning degree appears in the early warning degree image to be larger than a preset threshold valueAnd when the warning degree image is detected, the corresponding sensor in the warning degree image is marked and an alarm is sent out.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311732848.9A CN117421620B (en) | 2023-12-18 | 2023-12-18 | Interaction method of tension state data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311732848.9A CN117421620B (en) | 2023-12-18 | 2023-12-18 | Interaction method of tension state data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117421620A CN117421620A (en) | 2024-01-19 |
| CN117421620B true CN117421620B (en) | 2024-02-27 |
Family
ID=89531087
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311732848.9A Active CN117421620B (en) | 2023-12-18 | 2023-12-18 | Interaction method of tension state data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117421620B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6944607B1 (en) * | 2000-10-04 | 2005-09-13 | Hewlett-Packard Development Compnay, L.P. | Aggregated clustering method and system |
| CN110375646A (en) * | 2019-07-18 | 2019-10-25 | 北京壬工智能科技有限公司 | The system and method that a kind of pair of material is made an inventory |
| CN212558168U (en) * | 2020-05-25 | 2021-02-19 | 中国矿业大学 | Chain tension monitoring and fracture early warning system of scraper conveyor |
| WO2021042233A1 (en) * | 2019-09-02 | 2021-03-11 | Robert Bosch Gmbh | Remote diagnosis system, apparatus and method for power tool |
| CN116281002A (en) * | 2023-02-14 | 2023-06-23 | 华能曲阜热电有限公司 | Chain monitoring method and system for scraper powder conveyer |
| CN116664559A (en) * | 2023-07-28 | 2023-08-29 | 深圳市金胜电子科技有限公司 | Machine vision-based memory bank damage rapid detection method |
| CN116954342A (en) * | 2023-09-18 | 2023-10-27 | 惠州市鑫晖源科技有限公司 | Method for monitoring operation of power supply of omnibearing efficient heat dissipation host based on Internet of things |
| CN116975672A (en) * | 2023-09-22 | 2023-10-31 | 山东乐普矿用设备股份有限公司 | Temperature monitoring method and system for coal mine belt conveying motor |
| CN116990381A (en) * | 2023-08-02 | 2023-11-03 | 国能神东煤炭集团有限责任公司 | Scraper machine fault determination method and device and scraper machine fault determination system |
| CN117056764A (en) * | 2023-10-11 | 2023-11-14 | 唐山市南堡经济开发区航天万源新能源有限公司 | Intelligent protection method and system for generator set |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107941537B (en) * | 2017-10-25 | 2019-08-27 | 南京航空航天大学 | A kind of mechanical equipment health state evaluation method |
| DE102020112651A1 (en) * | 2020-05-11 | 2021-11-11 | Volume Graphics Gmbh | Computer-implemented method for condition monitoring of a device for examining objects |
-
2023
- 2023-12-18 CN CN202311732848.9A patent/CN117421620B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6944607B1 (en) * | 2000-10-04 | 2005-09-13 | Hewlett-Packard Development Compnay, L.P. | Aggregated clustering method and system |
| CN110375646A (en) * | 2019-07-18 | 2019-10-25 | 北京壬工智能科技有限公司 | The system and method that a kind of pair of material is made an inventory |
| WO2021042233A1 (en) * | 2019-09-02 | 2021-03-11 | Robert Bosch Gmbh | Remote diagnosis system, apparatus and method for power tool |
| CN212558168U (en) * | 2020-05-25 | 2021-02-19 | 中国矿业大学 | Chain tension monitoring and fracture early warning system of scraper conveyor |
| CN116281002A (en) * | 2023-02-14 | 2023-06-23 | 华能曲阜热电有限公司 | Chain monitoring method and system for scraper powder conveyer |
| CN116664559A (en) * | 2023-07-28 | 2023-08-29 | 深圳市金胜电子科技有限公司 | Machine vision-based memory bank damage rapid detection method |
| CN116990381A (en) * | 2023-08-02 | 2023-11-03 | 国能神东煤炭集团有限责任公司 | Scraper machine fault determination method and device and scraper machine fault determination system |
| CN116954342A (en) * | 2023-09-18 | 2023-10-27 | 惠州市鑫晖源科技有限公司 | Method for monitoring operation of power supply of omnibearing efficient heat dissipation host based on Internet of things |
| CN116975672A (en) * | 2023-09-22 | 2023-10-31 | 山东乐普矿用设备股份有限公司 | Temperature monitoring method and system for coal mine belt conveying motor |
| CN117056764A (en) * | 2023-10-11 | 2023-11-14 | 唐山市南堡经济开发区航天万源新能源有限公司 | Intelligent protection method and system for generator set |
Non-Patent Citations (3)
| Title |
|---|
| 刮板取料机链轮张力对功耗的影响;李波;;起重运输机械;20151120(第11期);全文 * |
| 刮板输送机链条自动张紧系统的研究与应用;于忠厚;山西焦煤科技;20141215;全文 * |
| 李波 ; .刮板取料机链轮张力对功耗的影响.起重运输机械.2015,(第11期),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117421620A (en) | 2024-01-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020134032A1 (en) | Method for detecting abnormality of service system, and apparatus therefor | |
| CN110895526A (en) | Method for correcting data abnormity in atmosphere monitoring system | |
| CN111542846A (en) | Failure prediction system and failure prediction method | |
| CN111401573B (en) | Working condition state modeling and model correcting method | |
| CN110057406B (en) | Multi-scale self-adaptive mechanical equipment trend early warning method | |
| CN116839682B (en) | Cable processing and manufacturing real-time monitoring system based on Internet of things | |
| CN112987675A (en) | Method, device, computer equipment and medium for anomaly detection | |
| CN116881745B (en) | Pressure transmitter abnormality monitoring method based on big data | |
| CN110648480B (en) | Single variable alarm system and method based on change rate | |
| CN112766429B (en) | Method, device, computer equipment and medium for anomaly detection | |
| CN109753027A (en) | It is a kind of industry manufacture in parameter monitoring method and device | |
| CN112629905A (en) | Equipment anomaly detection method and system based on deep learning and computer medium | |
| JP5895457B2 (en) | Anomaly monitoring system and anomaly monitoring method | |
| CN114167838A (en) | Multi-scale health assessment and fault prediction method for servo system | |
| CN111709181B (en) | Method for predicting fault of polyester filament yarn industrial production process based on principal component analysis | |
| CN116335925B (en) | Data enhancement-based intelligent regulation and control system for underground coal mine emulsification pump station | |
| CN117421620B (en) | Interaction method of tension state data | |
| KR102045626B1 (en) | Apparatus and method for evaluating conditions of equipment | |
| CN103777519B (en) | A kind of production process method of quality control based on self starting technologies | |
| CN117556364A (en) | Mining ore pressure safety intelligent monitoring system | |
| CN113646718B (en) | Abnormality detection device and abnormality detection method | |
| CN116701846A (en) | Hydropower station dispatching operation data cleaning method based on unsupervised learning | |
| CN116503025A (en) | Business work order flow processing method based on workflow engine | |
| CN115146675B (en) | Rotary machine migration diagnosis method under variable working condition of depth multi-feature dynamic countermeasure | |
| TWI745912B (en) | Blast furnace abnormality determination device, blast furnace abnormality determination method and blast furnace operation method |
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 |