CN112948203B - Elevator intelligent inspection method based on big data - Google Patents
Elevator intelligent inspection method based on big data Download PDFInfo
- Publication number
- CN112948203B CN112948203B CN202110149069.0A CN202110149069A CN112948203B CN 112948203 B CN112948203 B CN 112948203B CN 202110149069 A CN202110149069 A CN 202110149069A CN 112948203 B CN112948203 B CN 112948203B
- Authority
- CN
- China
- Prior art keywords
- data
- inspection
- real
- standard
- elevator
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3065—Monitoring arrangements determined by the means or processing involved in reporting the monitored data
- G06F11/3072—Monitoring arrangements determined by the means or processing involved in reporting the monitored data where the reporting involves data filtering, e.g. pattern matching, time or event triggered, adaptive or policy-based reporting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3003—Monitoring arrangements specially adapted to the computing system or computing system component being monitored
- G06F11/3013—Monitoring arrangements specially adapted to the computing system or computing system component being monitored where the computing system is an embedded system, i.e. a combination of hardware and software dedicated to perform a certain function in mobile devices, printers, automotive or aircraft systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3051—Monitoring arrangements for monitoring the configuration of the computing system or of the computing system component, e.g. monitoring the presence of processing resources, peripherals, I/O links, software programs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
- G06F11/3409—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment for performance assessment
-
- 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
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- Computing Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Computer Hardware Design (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Indicating And Signalling Devices For Elevators (AREA)
Abstract
The invention discloses an elevator intelligent inspection method based on big data, which comprises the following steps: transmitting historical elevator operation data and real-time operation data of a plurality of elevator operation control centers to a big data system; the big data system performs element screening on the historical operating data to obtain necessary data required by inspection; the big data system performs data integration on the necessary data required by the inspection to obtain standard inspection data; extracting and correlating the inspection elements of the standard inspection data to obtain an inspection element correlation matrix; performing optimization operation on the inspection element incidence matrix to obtain an intelligent inspection pre-estimation model; and carrying out intelligent tracking inspection on the real-time operation data according to the intelligent inspection pre-estimation model.
Description
Technical Field
The invention relates to the technical field of big data elevator inspection, in particular to an intelligent elevator inspection method based on big data.
Background
The safety problem of the elevator is related to personal safety and personal interests of each person, and elevator inspection is an important technical guarantee for elevator safety; when an elevator accident happens, great pressure is brought to the inspection technology of the elevator; under the condition that the quantity of the elevators is rapidly increased and the data volume is expanded, big data becomes an important technical direction for solving the problem of elevator inspection; the method for establishing the intelligent elevator inspection is an important application field of big data.
Disclosure of Invention
A series of concepts in a simplified form are introduced in the summary section, which is described in further detail in the detailed description section. This summary of the invention is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used as an aid in determining the scope of the claimed subject matter.
In order to at least partially solve the problems, the invention provides an elevator intelligent inspection method based on big data, which comprises the following steps:
s100, transmitting historical operation data and real-time operation data of the elevators of a plurality of elevator operation control centers to a big data system;
s200, the big data system performs element screening on the historical operating data to obtain necessary data required by inspection;
s300, the big data system integrates the necessary data required by the inspection to obtain standard inspection data;
s400, extracting and associating the inspection elements of the standard inspection data to obtain an inspection element association matrix;
s500, carrying out optimization operation on the inspection element incidence matrix to obtain an intelligent inspection pre-estimation model;
s600, carrying out intelligent tracking inspection on the real-time operation data according to the intelligent inspection pre-estimation model.
Preferably, the S100 includes:
s101, establishing data transmission channels of the plurality of elevator operation control centers and the big data system;
s102, transmitting the historical operating data and the real-time operating data which need to be intelligently checked by the big data system to the big data system through the data transmission channel;
s103, the big data system carries out big data processing on the historical operation data and the real-time operation data of the plurality of elevator operation control centers; the historical operating data includes: standard inspection data, non-standard inspection data and historical interference data; the real-time operating data comprises: real-time operating state data, real-time data to be inspected and real-time interference data.
Preferably, the S200 includes:
s201, performing element screening on the historical elevator operation data through an element screening module of the big data system, wherein the element screening comprises the following steps:
establishing a screening principle of element screening according to the standard test data and the non-standard test data;
the screening principle is subjected to data conversion and converted into a screening principle data module for screening and identifying;
establishing an element set of the elevator inspection data according to the screening principle data module;
the set of elements of elevator inspection data includes the standard inspection data identification vector and the non-standard inspection data identification vector of elevator inspection;
according to the inspection data identification vector, identifying and screening the historical operating data; identifying the test data which conforms to the test data identification vector as the test data; identifying as historical interference data that does not conform to the test data identification vector;
s202, screening out the historical interference data in the historical elevator operation data through the element screening;
and S203, removing the historical interference data to obtain necessary data required by inspection.
Preferably, the S300 includes:
s301, performing data integration on necessary data required by inspection through a data integration and integration module of the big data system, integrating different data types of elevator inspection data, and performing integration processing on data with uneven distribution and inconsistent structure to obtain integrated data with even distribution and consistent structure;
and S302, integrating the integrated data into the inspection data to obtain standard inspection data.
Preferably, the S400 includes:
s401, extracting elements of the standard inspection data to obtain an inspection element matrix;
s402, performing difference compensation on missing inspection elements in the inspection element matrix to obtain a standard inspection element matrix;
and S403, performing correlation processing on the inspection elements in the standard inspection element matrix to obtain an inspection element correlation matrix.
Preferably, the S500 includes:
s501, updating the speed of the element correlation matrix of the inspection elements:
s502, updating the positions of the elements of the element association matrix of the checking elements:
s503, outputting the optimal inspection element association matrix through loop iteration; and performing data training through the optimal inspection element incidence matrix, and establishing an intelligent inspection pre-estimation model.
Preferably, the S600 includes:
s601, the big data system reads real-time operation data of the elevator;
s602, performing real-time data funnel screening on the real-time operation data through a data funnel module of the big data system, and screening out the real-time interference data;
and S603, screening the elements of the big data system to obtain the real-time data to be detected.
Preferably, the real-time data to be checked includes: real-time standard data to be inspected and real-time non-standard data to be inspected;
and the data integration and integration module of the big data system is used for integrating the data to be detected in the real-time standard and the data to be detected in the real-time non-standard, and the data to be detected in the real-time standard is obtained after integration and integration.
Preferably, according to the intelligent inspection estimation model, the real-time operation data is subjected to intelligent tracking inspection, and the method further comprises the following steps: and inputting the real-time standard data to be inspected into the intelligent inspection pre-estimation model, and carrying out intelligent tracking inspection on the real-time standard data to be inspected by the intelligent inspection pre-estimation model.
Preferably, the intelligent inspection pre-estimation model is right the data to be inspected of the standard is subjected to intelligent tracking inspection, and the intelligent tracking inspection method comprises the following steps: inputting the standard data to be detected into an intelligent detection estimation model, wherein the intelligent detection estimation model tracks and compares whether the detection data accords with the detection elements: if the intelligent inspection pre-estimation model performs tracking inspection, necessary factors of real-time running data of the standard data to be inspected do not accord with inspection factors, the inspection is not needed; if the intelligent inspection pre-estimation model tracks and inspects, the real-time operation data necessary factors of the standard data to be inspected accord with the inspection factors, and then inspection is needed; and the big data system sends an intelligent inspection result to the elevator operation control center.
Compared with the prior art, the invention at least comprises the following beneficial effects:
the elevator intelligent inspection method based on big data uses a big data platform, and is suitable for processing huge and complex data volume of elevator operation; element screening and data integration can be carried out, the non-standard inspection data and the historical interference data can be filtered out, necessary factors in the inspection process are obtained, and standard inspection data are obtained; the elevator operation data can be well solved: the data volume is huge, the data types are complex and various, and the data interference factors are many; intelligent training data dynamic batch integration is adopted, so that the distribution change of the data can be dynamically adjusted while being integrated within a certain range; performing joint evaluation on the quality degrees of various elevator inspection schemes from a plurality of factors; through analysis and comparison, the optimal scheme can be obtained by selecting the scheme; the optimal or equilibrium state can be reached quickly; and finally, more reasonable elevator operation inspection results and inspection result verification can be obtained.
Other advantages, objects, and features of the invention will be set forth in part in the description which follows and will become apparent to those having ordinary skill in the art upon examination of the following or may be learned from practice of the invention.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
fig. 1 is a flow chart of an elevator intelligent inspection method based on big data according to the invention.
Detailed Description
The present invention is further described in detail below with reference to the drawings and examples so that those skilled in the art can practice the invention with reference to the description.
As shown in fig. 1, the present invention provides a big data based intelligent elevator inspection method, which comprises:
s100, transmitting historical operation data and real-time operation data of the elevators of a plurality of elevator operation control centers to a big data system;
s200, the big data system performs element screening on the historical operating data to obtain necessary data required by inspection;
s300, the big data system integrates the necessary data required by the inspection to obtain standard inspection data;
s400, extracting and correlating the inspection elements of the standard inspection data to obtain an inspection element correlation matrix;
s500, performing optimization operation on the inspection element incidence matrix to obtain an intelligent inspection pre-estimation model;
s600, carrying out intelligent tracking inspection on the real-time operation data according to the intelligent inspection pre-estimation model.
The working principle of the technical scheme is as follows: the large data platform is applied, so that the method is suitable for processing large and complex data volume; performing element screening on the historical operating data; performing data integration and integration on necessary factors in the inspection process through data integration and integration; extracting main characteristic components of the data by adopting maximum separability and recent reconfigurability; adopting intelligent training data to dynamically adjust; performing difference compensation improvement on the data to obtain a standard inspection element matrix; comprehensively evaluating the quality degree of the multi-target system scheme from a plurality of factors; obtaining a scheme of the weighted sum of the estimated values; in the operation process, each iteration is based on the condition that the target point is reached by the shortest distance and the fastest speed; and obtaining final sequential target data by adopting an ordered and unordered joint mode of a data funnel.
The beneficial effects of the above technical scheme are as follows: the large data platform is applied, and is suitable for processing the large and complex data volume of the elevator operation; element screening and data integration can be carried out, the non-standard inspection data and the historical interference data can be filtered out, necessary factors in the inspection process are obtained, and standard inspection data are obtained; the elevator operation data can be well solved: the data volume is huge, the data types are complex and various, and the data interference factors are many; intelligent training data dynamic batch integration is adopted, so that the distribution change of the data can be dynamically adjusted while being integrated within a certain range; performing combined evaluation on the quality degrees of various elevator inspection schemes from a plurality of factors; through analysis and comparison, the optimal scheme can be obtained by selecting the scheme; the optimal or equilibrium state can be reached quickly; and finally, more reasonable elevator operation inspection results and inspection result verification can be obtained.
In one embodiment, the S100 includes:
s101, establishing data transmission channels of the plurality of elevator operation control centers and the big data system;
s102, transmitting the historical operating data and the real-time operating data which need to be intelligently checked by the big data system to the big data system through the data transmission channel;
s103, the big data system carries out big data processing on the historical operation data and the real-time operation data of the plurality of elevator operation control centers; the historical operating data includes: standard inspection data, non-standard inspection data and historical interference data; the real-time operating data includes: real-time running state data, real-time data to be checked and real-time interference data.
The working principle of the technical scheme is as follows: the elevator historical operation data has huge data volume and complex and various data types, the common platform is very difficult to process, and a large data platform is applied, so that the elevator historical operation data is suitable for processing the huge and complex data volume; the big data system selects a big data system platform; the historical operating data includes: standard inspection data, non-standard inspection data and historical interference data; the real-time operating data comprises: real-time running state data, real-time data to be detected and real-time interference data; the invention adopts the functions of a data mining module, a data extraction module, a data integration, conversion and other modules of a big data system platform, constructs a task module for data processing through an embedded module of the big data system, and screens elements of the historical operating data through an element screening module of the big data system; and performing data integration and integration on necessary factors in the inspection process through an element integration module of the big data system.
The beneficial effects of the above technical scheme are as follows: the large data platform is applied, and is suitable for processing the large and complex data volume of the elevator operation; the large data system platform adopted by the invention has the functions of enriching data mining analysis and algorithm, and is suitable for solving the problem of huge data volume of historical and operating data of the elevator and intelligent prediction and inspection; the non-standard inspection data and the historical interference data can be filtered out through an element screening module of the big data system, and necessary factors in the inspection process are obtained; standard inspection data can be obtained through an element integration module of the big data system; by adopting the scheme, the problem of elevator operation data can be well solved: the data size is huge, the data types are complex and various, and the data interference factors are many, so that a relatively better platform basis is selected for the subsequent processing and operation of data.
In one embodiment, the S200 includes:
s201, performing element screening on the historical elevator operation data through an element screening module of the big data system, wherein the element screening comprises the following steps:
establishing a screening principle of element screening according to the standard test data and the non-standard test data;
the screening principle is subjected to data conversion and converted into a screening principle data module for screening and identifying;
establishing an element set of the elevator inspection data according to the screening principle data module;
the set of elements of elevator inspection data includes the standard inspection data identification vector and the non-standard inspection data identification vector of elevator inspection;
according to the inspection data identification vector, identifying and screening the historical operating data; identifying the test data which conforms to the test data identification vector as the test data; identifying as historical interference data that does not conform to the test data identification vector;
s202, screening the historical interference data in the historical elevator operation data through the element screening;
and S203, removing the historical interference data to obtain necessary data required by inspection.
The working principle of the technical scheme is as follows: the element screening module of the big data system adopts the maximum separable type and the nearest reconstruction, and is characterized in that the maximum separable type optimization condition is the maximum variance after division; the optimization condition of the nearest reconstruction is that the distance between a point and a dividing plane is minimum; a principal feature component that can be used to extract data; the number of the adopted basic data is less than the dimensionality of the vector, the mapping numerical value after data mapping is maximally dispersed, or the smaller the entropy is, the less the information is contained; and performing element screening on unnecessary factors of the elevator historical operation data.
The beneficial effects of the above technical scheme are that: the element screening module of the big data system adopts maximum typing and nearest reconstruction, so that the back difference of data division is maximum, and the distance between a point and a division plane is minimum; the extraction of the main characteristic components is more reasonable; the number of the screened base data is less than the dimensionality of the vector, so that the dimensionality can be reduced; the mapping numerical values after data mapping are adopted to be maximally dispersed, so that the loss of samples caused by overlapping can be avoided; the entropy value maximization is adopted, the contained information is more, the unnecessary factors of the historical operation data of the elevator are subjected to element screening, and the original factors of the historical operation data of the elevator can be reserved to the greatest extent.
In one embodiment, the S300 includes:
s301, performing data integration on necessary data required by inspection through a data integration and integration module of the big data system, integrating different data types of elevator inspection data, and performing integration processing on data with uneven distribution and inconsistent structure to obtain integrated data with even distribution and consistent structure;
and S302, integrating the integrated data into the inspection data to obtain standard inspection data.
The working principle of the technical scheme is as follows: adopting an intelligent training data dynamic batch integration principle; data mining training is difficult frequently during data mining training, data is updated iteratively, and data distribution changes, so that contradiction with the data mining target is caused; the goal of data mining is to minimize the changes which make data mining difficult and difficult; therefore, the invention adopts intelligent training data dynamic batch integration, so that the distribution change of the data can be dynamically adjusted while being integrated in a certain range; the dynamic adjustment can return the data to the data cycle process at the fastest speed and the shortest path after the distribution is changed.
The beneficial effects of the above technical scheme are that: the intelligent training data is dynamically integrated in batches, so that the difficulty of data mining training which often occurs during data mining training can be obviously reduced; optimizing the problem of contradiction between data mining targets caused by the fact that data distribution changes constantly in the data iteration updating process; intelligent training data dynamic batch integration is adopted, so that the distribution change of the data can be dynamically adjusted while being integrated within a certain range; the dynamic adjustment can return to the distribution range in the data circulation process at the fastest speed and the shortest path after the distribution is changed.
In one embodiment, the S400 includes:
s401, extracting elements of the standard inspection data to obtain an inspection element matrix;
s402, performing difference compensation on missing inspection elements in the inspection element matrix to obtain a standard inspection element matrix;
and S403, performing correlation processing on the inspection elements in the standard inspection element matrix to obtain an inspection element correlation matrix.
The working principle of the technical scheme is as follows: the cleaned and integrated data is considered to have relatively complete extraction conditions, and elements, interference factors and irrelevant factors after data arrangement are cleaned or integrated; but may still be insufficient because some data may be incomplete, missing elements, or lost, and the data needs to be complemented to obtain a standard test element matrix; comprehensively evaluating the quality degree of the multi-target system scheme based on a plurality of factors; the evaluation values of the related evaluation indexes of various elevator inspection schemes are expressed in a form of incidence matrix, the weighted sum of the estimated values of the schemes is calculated, and the scheme with the maximum weighted sum of the estimated values is obtained through analysis and comparison.
The beneficial effects of the above technical scheme are that: by adopting the element difference compensation joint incidence matrix, the difference compensation and the correlation can be carried out on the data which is cleaned or integrated but still insufficient in the element interference factors and irrelevant factors after data arrangement, so that the problems of partial data incompleteness, missing elements or loss are solved; a standard check element matrix can be obtained; the quality degree of various elevator inspection schemes can be jointly evaluated from a plurality of factors; the evaluation values of the related evaluation indexes of various elevator inspection schemes are expressed in a form of incidence matrix, the weighted sum of the estimated values of the schemes is calculated, the multi-target problem is decomposed into the importance degree comparison of two indexes, the scheme with the maximum weighted sum of the estimated values is obtained through analysis and comparison, and the optimal scheme can be obtained by selecting the scheme.
In one embodiment, the S500 includes:
s501, updating the speed of the element association matrix of the test elements:
s502, updating the positions of the elements of the correlation matrix of the inspection elements:
s503, outputting the optimal test element incidence matrix through loop iteration; and performing data training through the optimal inspection element incidence matrix, and establishing an intelligent inspection pre-estimation model.
The working principle of the technical scheme is as follows: in the operation process, each iteration is based on the fact that the target point is reached at the shortest distance and the fastest speed, the optimal memory element position of the last state of all elements is stored in a high-dimensional search space, and the new element position is used for calculating the information combination of the passing elements in the next iteration and the memory of the optimal positions of all elements; when the ratio of the speed adjusting parameter to the adjustable adjusting parameter is larger, the elements are converged quickly, otherwise, the elements are dispersed slowly; each iteration is updated in a cycle; the state of the element in the multidimensional search space is continuously changed, and the component of each dimension of the speed and the relevance is adjusted until the operation iteration limit is exceeded.
The beneficial effects of the above technical scheme are as follows: the optimal memory element position of the last state of all elements stored in the high-dimensional search space can be kept, and each iteration is based on the fact that the target point is reached at the shortest distance and the fastest speed; the new element position calculation can be the optimal position of the element for the next iteration in the operation through the information combination of the elements; the speed adjusting parameters can be adjusted, so that elements can be rapidly converged; each iteration is circularly updated in an iteration period; the requirement of function property is wide, and the adaptability is wider; the method is more suitable for the operation process with a plurality of local extreme points; the state of the element in the multidimensional search space is changed continuously, and the optimal or balanced state can be reached quickly by adjusting the speed and the components of the relevance of the speed in each dimension.
In one embodiment, the S600 includes:
s601, the big data system reads real-time operation data of the elevator;
s602, performing real-time data funnel screening on the real-time operation data through a data funnel module of the big data system, and screening out the real-time interference data;
and S603, screening the elements of the big data system to obtain the real-time data to be detected.
The working principle of the technical scheme is as follows: the method comprises the steps of filtering two complementary indexes of conversion rate and loss rate step by step from a starting point to an end point by adopting an ordered and disordered joint mode of a data funnel, and adjusting the data conversion rate; the primary stage adopts a disordered method, and the subsequent stages adopt an ordered method; primary in a broad way, obtaining primary target data; and subsequently, limiting the sequence of the steps to obtain final sequence target data.
The beneficial effects of the above technical scheme are that: filtering step by step from a starting point to an end point, and converting two complementary indexes of conversion rate and loss rate into adjustable data conversion rate by adopting an ordered and disordered combination mode of a data funnel; the primary stage adopts an unordered method, and primary target data can be quickly obtained in a wide mode; in the subsequent application stage, an ordered method is adopted, and the sequence among the steps is limited to obtain final sequence target data; to input the elevator inspection data model for verification; the primary target data can be obtained at the fastest speed, and the optimized model input data is used for verification, so that a final more reasonable verification test result can be obtained.
In one embodiment, the real-time data to be inspected includes: real-time standard data to be inspected and real-time non-standard data to be inspected; and the data integration and integration module of the big data system is used for integrating the data to be detected in the real-time standard and the data to be detected in the real-time non-standard, and the data to be detected in the real-time standard is obtained after integration and integration.
According to the intelligent inspection pre-estimation model, the real-time operation data is intelligently tracked and inspected, and the method further comprises the following steps: and inputting the real-time standard data to be inspected into the intelligent inspection pre-estimation model, and carrying out intelligent tracking inspection on the real-time standard data to be inspected by the intelligent inspection pre-estimation model.
The intelligent inspection pre-estimation model is right the data to be inspected of standard carry out intelligent tracking inspection, include: inputting the standard data to be detected into an intelligent detection pre-estimation model, wherein the intelligent detection pre-estimation model tracks and compares whether the detection data accords with the detection elements: if the intelligent inspection pre-estimation model performs tracking inspection, necessary factors of real-time running data of the standard data to be inspected do not accord with inspection factors, the inspection is not needed; if the intelligent inspection pre-estimation model tracks and inspects, the real-time operation data necessary factors of the standard data to be inspected accord with the inspection factors, and then inspection is needed; and the big data system sends an intelligent inspection result to the elevator operation control center.
The working principle of the technical scheme is as follows: performing data integration and integration on necessary factors in the inspection process through data integration and integration; extracting main characteristic components of the data by adopting maximum separability and recent reconfigurability; the large data platform is applied, so that the method is suitable for processing large and complex data volume; performing element screening on the historical operating data; adopting intelligent training data to dynamically adjust; performing difference compensation improvement on the data to obtain a standard inspection element matrix; in the operation process, each iteration is based on the condition that the target point is reached by the shortest distance and the fastest speed; obtaining final sequential target data by adopting an ordered and unordered combination mode of a data funnel; comprehensively evaluating the quality degree of the multi-target system scheme based on a plurality of factors; and obtaining a scheme of weighted sum maximum of the estimated values.
The beneficial effects of the above technical scheme are as follows: by using the large data platform, the problems of large data volume, complex and various data types and a plurality of data interference factors of elevator operation data can be well solved; is suitable for processing large and complex data quantity of elevator operation; element screening and data integration can be carried out, the non-standard inspection data and the historical interference data can be filtered out, necessary factors in the inspection process are obtained, and standard inspection data are obtained; intelligent training data dynamic batch integration is adopted, so that the distribution change of the data can be dynamically adjusted while being integrated within a certain range; the real-time operation data of the elevator can be intelligently tracked and inspected through an intelligent inspection pre-estimation model; performing joint evaluation on the quality degrees of various elevator inspection schemes from a plurality of factors; through analysis and comparison, the optimal scheme can be obtained by selecting the scheme; the optimal or equilibrium state can be reached quickly; and a more reasonable elevator operation inspection result can be finally obtained.
While embodiments of the invention have been disclosed above, it is not limited to the applications set forth in the description and the embodiments, which are fully applicable in various fields of endeavor to which the invention pertains, and further modifications may readily be made by those skilled in the art, it being understood that the invention is not limited to the details shown and described herein without departing from the general concept defined by the appended claims and their equivalents.
Claims (5)
1. An elevator intelligent inspection method based on big data is characterized by comprising the following steps:
s100, transmitting historical elevator operation data and real-time operation data of a plurality of elevator operation control centers to a big data system;
s200, the big data system performs element screening on the historical operating data to obtain necessary data required by inspection;
s300, the big data system integrates the necessary data required by the inspection to obtain standard inspection data;
s400, extracting and correlating the inspection elements of the standard inspection data to obtain an inspection element correlation matrix;
s500, performing optimization operation on the inspection element incidence matrix to obtain an intelligent inspection pre-estimation model;
s600, carrying out intelligent tracking inspection on the real-time running data according to the intelligent inspection pre-estimation model;
the S200 includes:
s201, performing element screening on the elevator historical operation data through an element screening module of the big data system, wherein the element screening comprises the following steps:
establishing a screening principle of element screening according to the standard test data and the non-standard test data;
the screening principle is subjected to data conversion and converted into a screening principle data module for screening and identifying;
establishing an element set of the elevator inspection data according to the screening principle data module;
the set of elements of elevator inspection data includes the standard inspection data identification vector and the non-standard inspection data identification vector of elevator inspection;
according to the inspection data identification vector, identifying and screening the historical operating data; identifying as the inspection data that conforms to the inspection data identification vector; identifying as historical interference data that does not conform to the test data identification vector;
s202, screening the historical interference data in the historical elevator operation data through the element screening;
s203, after removing the historical interference data, obtaining necessary data required by inspection;
the element screening module of the big data system adopts the maximum separable type and the nearest reconstruction, and is characterized in that the maximum separable type optimization condition is the maximum variance after division; the optimization condition of the nearest reconstruction is that the distance between a point and a dividing plane is minimum; a principal feature component that can be used to extract data; the number of the base data is less than the dimensionality of the vector, and the mapping numerical value after data mapping is maximally dispersed, or the smaller the entropy is, the less the information is contained; performing element screening on unnecessary factors of the elevator historical operation data;
the S600 includes:
s601, the big data system reads real-time operation data of the elevator;
s602, performing real-time data funnel screening on the real-time operation data through a data funnel module of the big data system, and screening out the real-time interference data;
s603, screening elements of the big data system to obtain the real-time data to be checked;
the real-time data to be inspected includes: real-time standard data to be inspected and real-time non-standard data to be inspected;
performing data integration and integration on the real-time standard data to be inspected and the real-time non-standard data to be inspected through a data integration and integration module of the big data system, and obtaining the real-time standard data to be inspected after integration and integration;
the S600 further includes: inputting the real-time standard data to be inspected into the intelligent inspection pre-estimation model, and carrying out intelligent tracking inspection on the real-time standard data to be inspected by the intelligent inspection pre-estimation model;
the intelligent inspection pre-estimation model is right the data to be inspected of standard carry out intelligent tracking inspection, include: inputting the standard data to be detected into an intelligent detection pre-estimation model, wherein the intelligent detection pre-estimation model tracks and compares whether the detection data accords with the detection elements: if the intelligent inspection pre-estimation model performs tracking inspection, the real-time operation data of the standard data to be inspected need not to be inspected if necessary factors of the standard data to be inspected do not accord with inspection factors; if the intelligent inspection pre-estimation model tracks and inspects, the necessary factors of the real-time running data of the standard data to be inspected accord with the inspection factors, and then the inspection is needed; and the big data system sends an intelligent inspection result to the elevator operation control center.
2. The intelligent inspection method for elevator based on big data as claimed in claim 1,
the S100 includes:
s101, establishing data transmission channels of the plurality of elevator operation control centers and the big data system;
s102, transmitting the historical operating data and the real-time operating data which need to be intelligently checked by the big data system to the big data system through the data transmission channel;
s103, the big data system carries out big data processing on the historical operation data and the real-time operation data of the plurality of elevator operation control centers; the historical operating data includes: standard inspection data, non-standard inspection data and historical interference data; the real-time operating data comprises: real-time running state data, real-time data to be checked and real-time interference data.
3. The big data-based elevator intelligent inspection method according to claim 1, wherein the S300 comprises:
s301, performing data integration on necessary data required by inspection through a data integration and integration module of the big data system, integrating different data types of elevator inspection data, and performing integration processing on data with uneven distribution and inconsistent structure to obtain integrated data with even distribution and consistent structure;
and S302, integrating the integrated data into the inspection data to obtain standard inspection data.
4. The big data-based elevator intelligent inspection method according to claim 1, wherein the S400 comprises:
s401, extracting elements of the standard inspection data to obtain an inspection element matrix;
s402, performing difference compensation on missing inspection elements in the inspection element matrix to obtain a standard inspection element matrix;
and S403, performing correlation processing on the inspection elements in the standard inspection element matrix to obtain an inspection element correlation matrix.
5. The big data-based elevator intelligent inspection method according to claim 1, wherein the S500 comprises:
s501, updating the speed of the element association matrix of the test elements:
s502, updating the positions of the elements of the element association matrix of the checking elements:
s503, outputting the optimal test element incidence matrix through loop iteration; and performing data training through the optimal inspection element incidence matrix, and establishing an intelligent inspection pre-estimation model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110149069.0A CN112948203B (en) | 2021-02-03 | 2021-02-03 | Elevator intelligent inspection method based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110149069.0A CN112948203B (en) | 2021-02-03 | 2021-02-03 | Elevator intelligent inspection method based on big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112948203A CN112948203A (en) | 2021-06-11 |
| CN112948203B true CN112948203B (en) | 2023-04-07 |
Family
ID=76242319
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110149069.0A Active CN112948203B (en) | 2021-02-03 | 2021-02-03 | Elevator intelligent inspection method based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112948203B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109213752A (en) * | 2018-08-06 | 2019-01-15 | 国网福建省电力有限公司信息通信分公司 | A kind of data cleansing conversion method based on CIM |
| CN109582140A (en) * | 2018-11-23 | 2019-04-05 | 哈尔滨工业大学 | A kind of architecture indoor pathfinding element vision significance assessment system and method based on virtual reality and eye movement tracking |
| CN110543615A (en) * | 2019-09-05 | 2019-12-06 | 国网湖南省电力有限公司 | Risk factor interaction analysis method based on SPSS explanation structure model |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108763377B (en) * | 2018-05-18 | 2021-08-13 | 郑州轻工业学院 | Multi-source telemetering big data feature extraction preprocessing method based on satellite fault diagnosis |
| CN110766050B (en) * | 2019-09-19 | 2023-05-23 | 北京捷通华声科技股份有限公司 | Model generation method, text recognition method, device, equipment and storage medium |
| CN110704469B (en) * | 2019-10-22 | 2022-11-11 | 北京明智和术科技有限公司 | Updating method and updating device of early warning level and readable storage medium |
| CN110992490B (en) * | 2019-12-13 | 2023-06-20 | 重庆交通大学 | Method for automatically extracting indoor map based on CAD building plan |
| CN111667102B (en) * | 2020-05-22 | 2023-01-17 | 中国南方电网有限责任公司 | Intelligent mining algorithm for early warning of running state fault of transformer element of power system |
| CN112101682B (en) * | 2020-09-25 | 2024-04-09 | 北京百度网讯科技有限公司 | Traffic pattern prediction method, traffic pattern prediction device, server and readable medium |
-
2021
- 2021-02-03 CN CN202110149069.0A patent/CN112948203B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109213752A (en) * | 2018-08-06 | 2019-01-15 | 国网福建省电力有限公司信息通信分公司 | A kind of data cleansing conversion method based on CIM |
| CN109582140A (en) * | 2018-11-23 | 2019-04-05 | 哈尔滨工业大学 | A kind of architecture indoor pathfinding element vision significance assessment system and method based on virtual reality and eye movement tracking |
| CN110543615A (en) * | 2019-09-05 | 2019-12-06 | 国网湖南省电力有限公司 | Risk factor interaction analysis method based on SPSS explanation structure model |
Non-Patent Citations (1)
| Title |
|---|
| 面向城市基础设施智慧运管的大数据智能融合方法;孙婷婷;《电子技术与软件工程》(第12期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112948203A (en) | 2021-06-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110033021B (en) | Fault classification method based on one-dimensional multipath convolutional neural network | |
| US8095484B2 (en) | System and method for automatic virtual metrology | |
| CN110352389B (en) | Information processing apparatus and information processing method | |
| CN109472057B (en) | Product processing quality prediction device and method based on cross-process implicit parameter memory | |
| WO2018009733A1 (en) | Computer system and method for monitoring key performance indicators (kpis) online using time series pattern model | |
| CN109409425B (en) | Fault type identification method based on neighbor component analysis | |
| CN112818893A (en) | Lightweight open-set landmark identification method facing mobile terminal | |
| CN111985825A (en) | Crystal face quality evaluation method for roller mill orientation instrument | |
| CN112819107A (en) | Artificial intelligence-based fault prediction method for gas pressure regulating equipment | |
| CN113959974B (en) | Transmission method of universal near infrared spectrum model | |
| CN112948203B (en) | Elevator intelligent inspection method based on big data | |
| CN113204857A (en) | Method for predicting residual life of electronic device based on extreme gradient lifting tree algorithm | |
| CN111177644A (en) | Model parameter optimization method, device, equipment and storage medium | |
| CN115718880A (en) | Prediction method for degradation stage of complex equipment | |
| CN115392102A (en) | Method and device for establishing energy consumption prediction model and method and system for predicting energy consumption | |
| CN117934963B (en) | Gas sensor drift compensation method | |
| CN115426709B (en) | WiFi fingerprint positioning abnormal data processing method based on iForest and low-rank matrix decomposition | |
| CN112926442B (en) | Construction method for image target data set balance completion | |
| CN116777292B (en) | Defect rate index correction method based on multi-batch small sample space product | |
| CN117648657B (en) | Urban planning multi-source data optimization processing method | |
| CN113255744B (en) | Infrared target detection method and system | |
| CN114298130A (en) | Short-term wind power prediction method and device | |
| CN118172275A (en) | Artificial intelligence-based full-color starlight imaging analysis method and system | |
| CN117575412A (en) | Model training method, device, equipment and medium for charge quality prediction | |
| CN117057475A (en) | Charging station load prediction method, charging station load prediction device, storage medium and computer equipment |
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 |