CN109822597B - Full-automatic intelligent inspection robot of data center - Google Patents
Full-automatic intelligent inspection robot of data center Download PDFInfo
- Publication number
- CN109822597B CN109822597B CN201910296725.2A CN201910296725A CN109822597B CN 109822597 B CN109822597 B CN 109822597B CN 201910296725 A CN201910296725 A CN 201910296725A CN 109822597 B CN109822597 B CN 109822597B
- Authority
- CN
- China
- Prior art keywords
- information
- inspection
- module
- routing inspection
- sub
- 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
Abstract
The invention provides a full-automatic intelligent inspection robot of a data center, which is integrated with detection modules aiming at different monitored objects, and can synchronously acquire corresponding detection data through the detection modules with different functions in the inspection process of the full-automatic intelligent inspection robot in the data center and also can calculate and process the detection data in real time; in addition, the full-automatic intelligent inspection robot can optimize and adjust corresponding inspection lines in real time based on detection data from detection modules with different functions and area division information of the data center, and can switch the inspection lines according to possible abnormal conditions in the current operation process of the data center.
Description
Technical Field
The invention relates to the technical field of data center monitoring, in particular to a full-automatic intelligent inspection robot of a data center.
Background
The data center is a system carrier which is used by computer hardware and software to process and store relevant data information. The data center has powerful data processing and data storage functions, and is widely applied to a plurality of different big data analysis occasions or individual privacy data processing occasions such as bank customer data information processing, financial industry data information processing or internet enterprise user data information processing. Whether the running state of the data center is normal or not is directly related to the stability and safety of data processing work of related industries or enterprises. Generally, a data center generally comprises two important components, namely a data processing system and a power system; the data processing system uses the combination of corresponding computer hardware and operation software as a carrier to realize the analysis and processing of different types of big data, and the power system provides corresponding power energy support for the data processing system. The stability and the persistence of the power energy provided by the power system for the data processing system directly influence the stability of the operation of the data processing system, namely the quality of the power supply performance of the power system directly influences the operation state of the data center. The data processing system and the power system are mutually combined to form a core component of the data center. Since the data center is created for large data processing and storage, the data center has a rather complicated structure in both the data processing system part and the power system part, and if a certain part of the data center fails, the potential safety operation of the data center is hidden.
In order to ensure the normal cloud center of the data center, real-time running state information of the data center needs to be acquired, and related industries or enterprises are equipped with corresponding engineering personnel or monitor equipment is installed inside the data center to monitor the data center in a controllable manner in real time, so that the working states of different areas of the data center can be acquired in time through the patrol of the engineering personnel or the video monitor equipment, and abnormal conditions can be rapidly checked and maintained when the local abnormality of the data center occurs. However, the above monitoring means are implemented based on manual monitoring or simple electronic monitoring equipment, so that the obtained monitoring result cannot comprehensively and accurately reflect the actual operation state of the data center; in addition, the monitoring means is only limited to monitoring in the aspect of images, and actually, factors influencing the operation state of the data center are in many aspects, and the required monitoring result cannot be accurately obtained only by means of manual monitoring or simple electronic monitoring equipment, and the monitoring means has certain time lag.
Disclosure of Invention
In the process of monitoring the operation state of the data center, the conventional manual monitoring or simple electronic video monitoring equipment cannot monitor the data center from multiple aspects, and the conventional monitoring means not only needs to be matched with a large amount of subsequent analysis and calculation work to obtain a corresponding monitoring result, but also cannot comprehensively, accurately and real-timely reflect the operation state of the data center, so that the conventional monitoring means consumes a large amount of manpower and material resources, and the correspondingly obtained monitoring result cannot meet the corresponding requirements on accuracy and real-time performance. In addition, the data center is affected by a plurality of internal factors or external factors during the operation process, the internal factors or the external factors usually need special equipment to realize monitoring, so that a plurality of different special equipment need to be equipped to accurately obtain corresponding monitoring information during the monitoring process of the data center, the monitoring information needs subsequent calculation processing to be converted into a human-recognizable monitoring result, and higher requirements are provided for the monitoring equipment of the data center.
Aiming at the defects in the prior art, the invention provides a full-automatic intelligent inspection robot of a data center, which is integrated with detection modules aiming at different monitored objects, and can synchronously acquire corresponding detection data through the detection modules with different functions in the inspection process inside the data center and also can calculate and process the detection data in real time; in addition, aiming at the complexity of the internal structure of the data center, the full-automatic intelligent inspection robot can optimize and adjust the corresponding inspection lines in real time based on the detection data from the detection modules with different functions and the region division information of the data center, and can switch the inspection lines according to the possible abnormal conditions in the current operation process of the data center, so that the full-automatic intelligent inspection robot can be ensured to be quickly positioned and reach the position where the abnormal conditions occur in the data center, and necessary detection operation is carried out on the subsequent inspection and maintenance of the abnormal conditions.
The invention provides a full-automatic intelligent inspection robot of a data center, which is characterized in that: the full-automatic intelligent inspection robot comprises a main control module, a detection module and an inspection line adjusting module; wherein the content of the first and second substances,
the detection module is used for acquiring a plurality of detection information of the data center at different positions and acquiring area division information of the data center in the inspection process;
the main control module generates current optimized routing inspection line information of the data center according to the current detection information and the area division information;
the inspection line adjusting module adjusts and switches the real-time inspection line of the full-automatic intelligent inspection robot according to the optimized inspection line information;
further, the detection module comprises a plurality of equipment detection sub-modules, a plurality of internal environment detection sub-modules, a positioning module and a detection information calibration module; the equipment detection submodules are used for acquiring respective running state information of different functional equipment in the data center; the internal environment detection submodules are used for acquiring environmental data information inside the data center; the positioning module is used for acquiring real-time position information of the full-automatic intelligent inspection robot in the inspection process; the detection information calibration module is used for carrying out position calibration operation on the running state information and/or the environmental data information according to the real-time position information; the main control module performs first partition processing on the whole area of the data center according to the position calibration operation result to obtain first routing inspection area distribution which is used as part of the area division information; or
The detection module comprises a plurality of sensor submodules and a plurality of abnormal state judgment submodules, wherein the abnormal state judgment process of the abnormal state judgment submodules is as follows:
the abnormal state judging submodule marks each piece of data stored in an abnormal database in the abnormal state judging submodule, wherein the abnormal database comprises P pieces of data, each piece of data comprises N numerical environmental index values corresponding to the information of a patrol area of the robot, the area value of the patrol area, the environmental temperature of the patrol area, the environmental humidity of the patrol area, the environmental noise value of the patrol area, the altitude of the patrol area and the oxygen content of the environmental air of the patrol area, the abnormal state judging submodule marks each piece of data so as to determine the environmental index value corresponding to the abnormal state,
the sensor sub-modules acquire N numerical environment index values corresponding to the current patrol area environment, form a matrix B according to the N numerical environment index values, the matrix B is a matrix with j rows and N columns, and then carry out standardization processing on each element of the matrix B according to the following expression (1)
In the above expression (1), bstThe element values of the s-th row and the t-th column in the matrix B are shown, wherein s is 1, 2, …, j, t is 1, 2, …, n,
is b isstThe normalized value obtained by this normalization process,
is the mean value of the elements corresponding to the t-th column in the matrix B, max (B)t) Is the maximum element value, min (b), corresponding to the t-th column in the matrix bt) For the minimum element value corresponding to the t-th column in the matrix B, the above formula (1) is used to perform the corresponding normalization process on each element in the matrix B to form a new matrix B, and then the covariance corresponding to each column in the matrix B is calculated to form a new matrix Cov, wherein the expression of the matrix Cov is as follows
In the above-mentioned expression (2),
is a matrix B*Where i is 1, 2, …, n, and x is 1, 2, …, n, then the eigenvalues and eigenvectors of the matrix Cov are calculated according to the following expression (3)
|Cov-λE|＝0 (3)
In the above expression (3), E is an identity matrix, and λ is the characteristic value, followed bySubstituting the characteristic value λ into a characteristic equation to calculate a corresponding basic solution C, and then calculating a matrix B according to the following expression (4)*Degree of association between the first row and any of all other rows
In the above expression (4), ρtIs a matrix B*Degree of association between the first and t rows, CiFor the ith value in the base solution C,
is a matrix B*The first row and the ith column of the display panel,
is a matrix B*The matrix B is calculated from the above expression (4) by using the values of the elements in the ith row and the ith column, i being 1, 2, …, n, and t being 2, 3, …, j*Determining all the correlation degrees of the first row and all other rows, determining the correlation degree with the maximum value, and determining the environmental index value corresponding to the abnormal state according to the correlation degree with the maximum value;
furthermore, the full-automatic intelligent inspection robot also comprises a clock module; the clock module is used for generating clock information in the process of detecting the equipment detection sub-modules and/or the internal environment detection sub-modules, and the detection information calibration module is also used for carrying out time calibration operation on the running state information and/or the environment data information according to the clock information; the main control module is also used for carrying out second partition processing on the first routing inspection area distribution according to the time calibration operation result to obtain second routing inspection area distribution which is used as part of the area division information;
furthermore, the full-automatic intelligent inspection robot also comprises a sub-area inspection coefficient calculation module and a sub-area inspection level determination module; the sub-area routing inspection coefficient calculation module is used for calculating respective routing inspection coefficients of a plurality of corresponding sub routing inspection areas in the first routing inspection area distribution or the second routing inspection area distribution according to the running state information and/or the environment data information; the sub-region routing inspection level determining module is used for determining routing inspection priority levels of a plurality of sub routing inspection regions corresponding to the first routing inspection region distribution or the second routing inspection region distribution according to respective routing inspection coefficients of the plurality of sub routing inspection regions corresponding to the first routing inspection region distribution or the second routing inspection region distribution so as to obtain a part of the region division information;
further, the full-automatic intelligent inspection robot also comprises a database module; the database module is used for storing running state information, environment data information and position information about the data center; the main control module obtains the first routing inspection area distribution specifically comprises the main control module obtaining a plurality of historical operating state information, a plurality of historical environment data information and position information from the database module, establishing a first machine learning algorithm model related to different position areas of the data center and abnormal conditions of different functional devices and/or internal environments of the data center based on the plurality of historical operating state information, the plurality of historical environment data information and the position information, and learning and analyzing the current position calibration operation result based on the first machine learning algorithm model to obtain the first routing inspection area distribution;
further, the full-automatic intelligent inspection robot also comprises a database module; the database module is used for storing running state information, environment data information, position information and clock information of the data center; the main control module obtains the second patrol distribution specifically comprises the main control module obtaining a plurality of historical running state information, a plurality of historical environment data information, position information and clock information from the database module, constructing a second machine learning algorithm model related to different time periods and abnormal conditions of internal environments of different functional devices and/or data centers on the basis of the plurality of historical running state information, the plurality of historical environment data information, the position information and the clock information, and performing learning analysis on the current time calibration operation result and the first patrol regional distribution on the basis of the second machine learning algorithm model to obtain the second patrol regional distribution;
further, the sub-inspection coefficient calculation module calculates the inspection coefficients of the sub-inspection areas corresponding to the first inspection area distribution, and specifically includes constructing a first machine learning algorithm model between the areas at different positions of the data center and abnormal conditions of different functional devices and/or internal environments of the data center, and then, based on the first machine learning algorithm model, performs learning analysis on the current running state information and/or the environmental data information to obtain the inspection coefficients; the sub-region routing inspection level determining module is used for determining routing inspection priority levels of a plurality of sub-routing inspection regions corresponding to the first routing inspection region distribution specifically, and comprises the steps of learning and analyzing a plurality of routing inspection coefficients in the first routing inspection region distribution based on the first machine learning algorithm model to obtain a plurality of probability values corresponding to abnormal conditions of the plurality of sub-regions in the first routing inspection region distribution, and determining the routing inspection priority levels according to the plurality of probability values;
further, the sub-inspection coefficient calculation module calculates the inspection coefficients of the sub-inspection areas corresponding to the second inspection area distribution, specifically includes constructing a second machine learning algorithm model between the clock information and abnormal conditions of internal environments of different functional devices and/or data centers, and then based on the second machine learning algorithm model, performs learning analysis on the current running state information and/or the environmental data information to obtain the inspection coefficients; the sub-region routing inspection level determining module is used for determining routing inspection priority levels of a plurality of sub-routing inspection regions corresponding to the second routing inspection region distribution specifically, and comprises the steps of learning and analyzing a plurality of routing inspection coefficients in the second routing inspection region distribution based on the second machine learning algorithm model to obtain a plurality of probability values corresponding to abnormal conditions of the plurality of sub-regions in the second routing inspection region distribution in different time periods, and determining the routing inspection priority levels according to the probability values;
further, the detection module comprises at least one of a sound detection submodule, an image detection submodule, a temperature and humidity detection submodule, an odor detection submodule, a suspended particle concentration detection submodule, an electromagnetic interference signal detection submodule and an infrared detection submodule; the voice detection submodule is used for acquiring voice information about internal functional equipment of the data center; the image detection submodule is used for acquiring a static image and/or a dynamic image about the internal environment of the data center; the temperature and humidity detection sub-module is used for acquiring a temperature value and/or a humidity value of the internal environment of the data center; the odor detection submodule is used for acquiring odor information of the internal environment of the data center; the suspended particle concentration detection submodule is used for acquiring a concentration value of suspended particles in the internal environment of the data center; the electromagnetic interference signal detection submodule is used for acquiring electromagnetic interference signals existing in the internal environment of the data center; the infrared detection submodule is used for acquiring infrared thermal imaging information about the functional equipment;
furthermore, the real-time routing inspection line of the full-automatic intelligent inspection robot is adjusted and switched by the inspection line adjusting module specifically comprises the inspection line adjusting module which generates optimized intermediate switching line information according to the current position information of the full-automatic intelligent inspection robot in the data center and the optimized inspection line information, and the main control module drives the full-automatic intelligent inspection robot to move from the current position to the line inlet indicated by the optimized inspection line information according to the optimized intermediate switching line information.
Compared with the prior art, the full-automatic intelligent inspection robot of the data center is integrally provided with the detection modules aiming at different monitored objects, and the full-automatic intelligent inspection robot can synchronously acquire corresponding detection data through the detection modules with different functions in the inspection process inside the data center and can also calculate and process the detection data in real time; in addition, aiming at the complexity of the internal structure of the data center, the full-automatic intelligent inspection robot can optimize and adjust the corresponding inspection lines in real time based on the detection data from the detection modules with different functions and the region division information of the data center, and can switch the inspection lines according to the possible abnormal conditions in the current operation process of the data center, so that the full-automatic intelligent inspection robot can be ensured to be quickly positioned and reach the position where the abnormal conditions occur in the data center, and necessary detection operation is carried out on the subsequent inspection and maintenance of the abnormal conditions.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic structural diagram of a full-automatic intelligent inspection robot of a data center provided by the invention.
Fig. 2 is a schematic structural diagram of a detection module in the full-automatic intelligent inspection robot of the data center provided by the invention.
Fig. 3 is a schematic structural diagram of another detection module in the full-automatic intelligent inspection robot of the data center provided by the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, a schematic structural diagram of a full-automatic intelligent inspection robot of a data center according to an embodiment of the present invention is shown. The full-automatic intelligent inspection robot of the data center can comprise but is not limited to a main control module, a detection module and an inspection line adjusting module.
Preferably, the detection module is used for acquiring a plurality of detection information about the data center at different positions and acquiring regional division information about the data center in the inspection process.
Preferably, the main control module generates current optimized routing inspection line information about the data center according to the current detection information and the area division information.
Preferably, the routing inspection line adjusting module adjusts and switches the real-time routing inspection line of the full-automatic intelligent routing inspection robot according to the optimized routing inspection line information.
Preferably, the detection module may further include, but is not limited to, a plurality of device detection sub-modules, a plurality of internal environment detection sub-modules, a positioning module, and a detection information calibration module; the equipment detection submodules are used for acquiring respective running state information of different functional equipment in the data center; the internal environment detection submodules are used for acquiring environmental data information inside the data center; the positioning module is used for acquiring real-time position information of the full-automatic intelligent inspection robot in the inspection process; the detection information calibration module is used for carrying out position calibration operation on the running state information and/or the environmental data information according to the real-time position information; and the main control module performs first partition processing on the whole area of the data center according to the position calibration operation result to obtain first routing inspection area distribution which is used as part of the area partition information.
Preferably, the detection module comprises a plurality of sensor sub-modules and a plurality of abnormal state judgment sub-modules, wherein the abnormal state judgment process of the abnormal state judgment sub-module is as follows:
the abnormal state judging submodule marks each piece of data stored in an abnormal database in the abnormal state judging submodule, wherein the abnormal database comprises P pieces of data, each piece of data comprises N numerical environmental index values corresponding to the information of a patrol area of the robot, the area value of the patrol area, the environmental temperature of the patrol area, the environmental humidity of the patrol area, the environmental noise value of the patrol area, the altitude of the patrol area and the oxygen content of the environmental air of the patrol area, the abnormal state judging submodule marks each piece of data so as to determine the environmental index value corresponding to the abnormal state,
the sensor sub-modules acquire N numerical environment index values corresponding to the current patrol area environment, form a matrix B according to the N numerical environment index values, the matrix B is a matrix with j rows and N columns, and then carry out standardization processing on each element of the matrix B according to the following expression (1)
In the above expression (1), bstThe element values of the s-th row and the t-th column in the matrix B are shown, wherein s is 1, 2, …, j, t is 1, 2, …, n,
is b isstThe normalized value obtained by this normalization process,
is the mean value of the elements corresponding to the t-th column in the matrix B, max (B)t) Is the maximum element value, min (b), corresponding to the t-th column in the matrix bt) Is the minimum element corresponding to the t-th column in the matrix bPerforming corresponding normalization processing on each element in the matrix B through the formula (1) to form a new matrix B, and then calculating the covariance corresponding to each column in the matrix B to form a new matrix Cov, wherein the expression of the matrix Cov is as follows
In the above-mentioned expression (2),
is a matrix B*Where i is 1, 2, …, n, and x is 1, 2, …, n, then the eigenvalues and eigenvectors of the matrix Cov are calculated according to the following expression (3)
|Cov-λE|＝0 (3)
In the above expression (3), E is the identity matrix, λ is the eigenvalue, then the eigenvalue λ is substituted into the eigen equation to calculate the corresponding base solution C, and then the matrix B is calculated according to the following expression (4)*Degree of association between the first row and any of all other rows
In the above expression (4), ρtIs a matrix B*Degree of association between the first and t rows, CiFor the ith value in the base solution C,
is a matrix B*The first row and the ith column of the display panel,
is a matrix B*The values of the elements corresponding to the ith row and ith column in the tth row, where i is 1, 2, …, n and t is 2, 3, …, j, are calculated according to the above expression (4)Array B*And determining all the relevance degrees of the first row and all other rows, determining the relevance degree with the maximum value, and determining the environmental index value corresponding to the abnormal state according to the relevance degree with the maximum value.
Preferably, the full-automatic intelligent inspection robot also comprises a clock module; the clock module is used for generating clock information in the process of detecting the equipment detection sub-modules and/or the internal environment detection sub-modules, and the detection information calibration module is also used for carrying out time calibration operation on the running state information and/or the environment data information according to the clock information; and the main control module also performs second partition processing on the first routing inspection area distribution according to the time calibration operation result to obtain second routing inspection area distribution which is used as part of the area partition information.
Preferably, the full-automatic intelligent inspection robot further comprises a sub-region inspection coefficient calculation module and a sub-region inspection level determination module; the sub-region routing inspection coefficient calculation module is used for calculating respective routing inspection coefficients of a plurality of corresponding sub routing inspection regions in the first routing inspection region distribution or the second routing inspection region distribution according to the running state information and/or the environment data information; the sub-region routing inspection level determining module is used for determining routing inspection priority levels of a plurality of sub-routing inspection regions corresponding to the first routing inspection region distribution or the second routing inspection region distribution according to respective routing inspection coefficients of the plurality of sub-routing inspection regions corresponding to the first routing inspection region distribution or the second routing inspection region distribution so as to obtain a part of the region division information.
Preferably, the full-automatic intelligent inspection robot also comprises a database module; the database module is used for storing running state information, environment data information and position information about the data center; the main control module obtains the first routing inspection area distribution specifically comprises the main control module obtaining a plurality of historical running state information, a plurality of historical environment data information and position information from the database module, establishing a first machine learning algorithm model related to different position areas of the data center and abnormal conditions of different functional devices and/or internal environments of the data center based on the plurality of historical running state information, the plurality of historical environment data information and the position information, and learning and analyzing the current position calibration operation result based on the first machine learning algorithm model to obtain the first routing inspection area distribution.
Preferably, the full-automatic intelligent inspection robot also comprises a database module; the database module is used for storing running state information, environment data information, position information and clock information of the data center; the main control module obtains the second patrol distribution specifically comprises the main control module obtaining a plurality of historical running state information, a plurality of historical environment data information, position information and clock information from the database module, establishing a second machine learning algorithm model related to different time periods and abnormal conditions of internal environments of different functional devices and/or data centers based on the plurality of historical running state information, the plurality of historical environment data information, the position information and the clock information, and performing learning analysis on the current time calibration operation result and the first patrol regional distribution based on the second machine learning algorithm model to obtain the second patrol regional distribution.
Preferably, the sub-inspection coefficient calculation module calculates the inspection coefficients of the sub-inspection areas corresponding to the first inspection area distribution, and may specifically include constructing a first machine learning algorithm model between the areas at different positions of the data center and abnormal conditions occurring in the internal environments of different functional devices and/or the data center, and then, based on the first machine learning algorithm model, performing learning analysis on the current running state information and/or the environmental data information to obtain the inspection coefficients; in addition, the determining of the patrol priority level of the sub-region patrol inspection regions corresponding to the first patrol inspection region distribution by the sub-region patrol inspection level determining module may specifically include performing learning analysis on a plurality of patrol inspection coefficients in the first patrol inspection region distribution based on the first machine learning algorithm model to obtain a plurality of probability values corresponding to the abnormal conditions of the sub-regions in the first patrol inspection region distribution, and determining the patrol priority level according to the plurality of probability values.
Preferably, the sub-inspection coefficient calculation module calculates the inspection coefficients of the sub-inspection areas corresponding to the second inspection area distribution, specifically includes constructing a second machine learning algorithm model between the clock information and abnormal conditions of internal environments of different functional devices and/or data centers, and then based on the second machine learning algorithm model, performs learning analysis on the current running state information and/or the environmental data information to obtain the inspection coefficients; in addition, the determining of the patrol priority level of the sub-region patrol inspection regions corresponding to the second patrol inspection region distribution by the sub-region patrol inspection level determining module may specifically include performing learning analysis on a plurality of patrol inspection coefficients in the second patrol inspection region distribution based on the second machine learning algorithm model to obtain a plurality of probability values corresponding to the abnormal conditions of the sub-regions in the second patrol inspection region distribution in different time periods, and determining the patrol priority level according to the plurality of probability values.
Preferably, the detection module may further include, but is not limited to, at least one of a sound detection sub-module, an image detection sub-module, a temperature and humidity detection sub-module, an odor detection sub-module, a suspended particle concentration detection sub-module, an electromagnetic interference signal detection sub-module, and an infrared detection sub-module; the voice detection submodule is used for acquiring voice information about internal functional equipment of the data center; the image detection submodule is used for acquiring a static image and/or a dynamic image about the internal environment of the data center; the temperature and humidity detection submodule is used for acquiring a temperature value and/or a humidity value of the internal environment of the data center; the odor detection submodule is used for acquiring odor information of the internal environment of the data center; the suspended particle concentration detection submodule is used for acquiring the concentration value of suspended particles in the internal environment of the data center; the electromagnetic interference signal detection submodule is used for acquiring electromagnetic interference signals existing in the internal environment of the data center; the infrared detection submodule is used for acquiring infrared thermal imaging information about the functional device.
Preferably, the routing inspection line adjusting module adjusts and switches the real-time routing inspection line of the full-automatic intelligent routing inspection robot, and specifically includes that the routing inspection line adjusting module generates optimized intermediate switching line information according to the current position information of the full-automatic intelligent routing inspection robot in the data center and the optimized routing inspection line information, and the main control module drives the full-automatic intelligent routing inspection robot to move to the line inlet indicated by the optimal routing inspection line information from the current position according to the optimal intermediate switching line information.
It can be seen from the above embodiments that the full-automatic intelligent inspection robot of the data center is integrally configured with detection modules for different monitored objects, and the full-automatic intelligent inspection robot can synchronously acquire corresponding detection data through the detection modules with different functions in the inspection process inside the data center, and can also perform calculation processing on the detection data in real time; in addition, aiming at the complexity of the internal structure of the data center, the full-automatic intelligent inspection robot can optimize and adjust the corresponding inspection lines in real time based on the detection data from the detection modules with different functions and the region division information of the data center, and can switch the inspection lines according to the possible abnormal conditions in the current operation process of the data center, so that the full-automatic intelligent inspection robot can be ensured to be quickly positioned and reach the position where the abnormal conditions occur in the data center, and necessary detection operation is carried out on the subsequent inspection and maintenance of the abnormal conditions.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (3)
1. The utility model provides a robot is patrolled and examined to data center's full-automatic intelligence which characterized in that: the full-automatic intelligent inspection robot comprises a main control module, a detection module and an inspection line adjusting module; wherein the content of the first and second substances,
the detection module is used for acquiring a plurality of detection information of the data center at different positions and acquiring area division information of the data center in the inspection process;
the main control module generates current optimized routing inspection line information of the data center according to the current detection information and the area division information;
the inspection line adjusting module adjusts and switches the real-time inspection line of the full-automatic intelligent inspection robot according to the optimized inspection line information;
the detection module comprises a plurality of equipment detection sub-modules, a plurality of internal environment detection sub-modules, a positioning module and a detection information calibration module; the equipment detection submodules are used for acquiring respective running state information of different functional equipment in the data center; the internal environment detection submodules are used for acquiring environmental data information inside the data center; the positioning module is used for acquiring real-time position information of the full-automatic intelligent inspection robot in the inspection process; the detection information calibration module is used for carrying out position calibration operation on the running state information and/or the environmental data information according to the real-time position information; the main control module performs first partition processing on the whole area of the data center according to the position calibration operation result to obtain first routing inspection area distribution which is used as part of the area division information; alternatively, the first and second electrodes may be,
the detection module comprises a plurality of sensor sub-modules and a plurality of abnormal state judgment sub-modules, wherein the abnormal state judgment process of the abnormal state judgment sub-modules comprises the following steps:
the abnormal state judgment submodule carries out labeling processing on each piece of data stored in an abnormal database inside the abnormal state judgment submodule, wherein the abnormal database comprises P pieces of data, each piece of data comprises N numerical environment index values corresponding to the information of a patrol area of the robot, an area value of the patrol area, the environment temperature of the patrol area, the environment humidity of the patrol area, the environment noise value of the patrol area, the altitude of the patrol area and the oxygen content of the environment air of the patrol area, the abnormal state judgment submodule carries out the labeling processing on each piece of data so as to determine the environment index value corresponding to the abnormal state,
the method comprises the following steps that the plurality of sensor sub-modules acquire N numerical environment index values corresponding to the current patrol area environment, a matrix B is formed according to the N numerical environment index values, the matrix B is a matrix with j rows and N columns, and then each element of the matrix B is subjected to standardization processing according to the following expression (1):
in the above-described expression (1),
is the element value of the s-th row and t-th column in the matrix B, wherein s =1, 2, …, j, t =1, 2, …, n,
is composed of
The normalized value obtained after the normalization process,
is the element mean value corresponding to the t-th column in the matrix B,
the maximum element value corresponding to the t-th column in the matrix b,
for the minimum element value corresponding to the t-th column in the matrix B, each element in the matrix B is normalized by the above formula (1) to form a new matrix
Then calculating said matrix
The covariance of each column in the matrix is formed
Wherein the matrix
The expression of (a) is as follows:
in the above-mentioned expression (2),
is a matrix
Wherein i =1, 2, …, n, x =1, 2, …, n, and then calculating the matrix according to the following expression (3)
Eigenvalue and eigenvector of
In the above expression (3), E is an identity matrix,
for the characteristic value, the characteristic value is then used
Substituting into the characteristic equation to calculate the corresponding basic solution C, and then calculating the matrix according to the following expression (4)
The degree of association between the first row and any of all other rows:
in the above-mentioned expression (4),
is a matrix
The degree of association between the first row and the t-th row,
for the ith value in the base solution C,
is a matrix
The first row and the ith column of the display panel,
is a matrix
The element values corresponding to the ith row and ith column in (i =1, 2, …, n, t =2, 3, …, j) are calculated as a matrix according to the above expression (4)
Determining all the correlation degrees of the first row and all other rows, determining the correlation degree with the maximum value, and determining the environmental index value corresponding to the abnormal state according to the correlation degree with the maximum value;
the full-automatic intelligent inspection robot also comprises a clock module; the clock module is used for generating clock information in the process of detecting the equipment detection sub-modules and/or the internal environment detection sub-modules, and the detection information calibration module is also used for carrying out time calibration operation on the running state information and/or the environment data information according to the clock information; the main control module is also used for carrying out second partition processing on the first routing inspection area distribution according to the time calibration operation result to obtain second routing inspection area distribution which is used as part of the area division information;
the full-automatic intelligent inspection robot also comprises a sub-region inspection coefficient calculation module and a sub-region inspection level determination module; the sub-area routing inspection coefficient calculation module is used for calculating respective routing inspection coefficients of a plurality of corresponding sub routing inspection areas in the first routing inspection area distribution or the second routing inspection area distribution according to the running state information and/or the environment data information; the sub-region routing inspection level determining module is used for determining routing inspection priority levels of a plurality of sub routing inspection regions corresponding to the first routing inspection region distribution or the second routing inspection region distribution according to respective routing inspection coefficients of the plurality of sub routing inspection regions corresponding to the first routing inspection region distribution or the second routing inspection region distribution so as to obtain a part of the region division information;
the full-automatic intelligent inspection robot also comprises a database module; the database module is used for storing running state information, environment data information and position information about the data center; the main control module obtains the first routing inspection area distribution specifically comprises the main control module obtaining a plurality of historical operating state information, a plurality of historical environment data information and position information from the database module, establishing a first machine learning algorithm model related to different position areas of the data center and abnormal conditions of different functional devices and/or internal environments of the data center based on the plurality of historical operating state information, the plurality of historical environment data information and the position information, and learning and analyzing the current position calibration operation result based on the first machine learning algorithm model to obtain the first routing inspection area distribution;
the full-automatic intelligent inspection robot also comprises a database module; the database module is used for storing running state information, environment data information, position information and clock information of the data center; the main control module obtains the second routing inspection area distribution specifically comprises the main control module obtains a plurality of historical running state information, a plurality of historical environment data information, position information and clock information from the database module, a second machine learning algorithm model related to different time periods and abnormal conditions of internal environments of different functional devices and/or data centers is built based on the plurality of historical running state information, the plurality of historical environment data information, the position information and the clock information, and learning analysis is carried out on the current time calibration operation result and the first routing inspection area distribution based on the second machine learning algorithm model to obtain the second routing inspection area distribution;
the sub-region routing inspection coefficient calculation module calculates the routing inspection coefficients of the sub-routing inspection regions corresponding to the first routing inspection region distribution, and specifically comprises the steps of constructing a first machine learning algorithm model which is related to different position regions of the data center and is in abnormal conditions with different functional devices and/or internal environments of the data center, and then learning and analyzing the current running state information and/or the environmental data information based on the first machine learning algorithm model to obtain the routing inspection coefficients; the sub-region routing inspection level determining module is used for determining routing inspection priority levels of a plurality of sub-routing inspection regions corresponding to the first routing inspection region distribution specifically, and comprises the steps of learning and analyzing a plurality of routing inspection coefficients in the first routing inspection region distribution based on the first machine learning algorithm model to obtain a plurality of probability values corresponding to abnormal conditions of the plurality of sub-regions in the first routing inspection region distribution, and determining the routing inspection priority levels according to the plurality of probability values;
the sub-region routing inspection coefficient calculation module calculates the routing inspection coefficients of the sub-routing inspection regions corresponding to the second routing inspection region distribution, specifically comprises the steps of constructing a second machine learning algorithm model between the clock information and abnormal conditions of internal environments of different functional devices and/or data centers, and then based on the second machine learning algorithm model, performing learning analysis on the current running state information and/or the environmental data information to obtain the routing inspection coefficients; the sub-region patrol inspection level determination module is used for determining patrol inspection priority levels of a plurality of sub-patrol inspection regions corresponding to the second patrol inspection region distribution, and specifically comprises the steps of performing learning analysis on a plurality of patrol inspection coefficients in the second patrol inspection region distribution based on the second machine learning algorithm model to obtain a plurality of probability values corresponding to abnormal conditions of the plurality of sub-regions in the second patrol inspection region distribution in different time periods, and determining the patrol inspection priority levels according to the probability values.
2. The fully automatic intelligent inspection robot for data centers according to claim 1, wherein: the detection module comprises at least one of a sound detection submodule, an image detection submodule, a temperature and humidity detection submodule, an odor detection submodule, a suspended particle concentration detection submodule, an electromagnetic interference signal detection submodule and an infrared detection submodule; the voice detection submodule is used for acquiring voice information about internal functional equipment of the data center; the image detection submodule is used for acquiring a static image and/or a dynamic image about the internal environment of the data center; the temperature and humidity detection sub-module is used for acquiring a temperature value and/or a humidity value of the internal environment of the data center; the odor detection submodule is used for acquiring odor information of the internal environment of the data center; the suspended particle concentration detection submodule is used for acquiring a concentration value of suspended particles in the internal environment of the data center; the electromagnetic interference signal detection submodule is used for acquiring electromagnetic interference signals existing in the internal environment of the data center; the infrared detection submodule is used for acquiring infrared thermal imaging information about the functional equipment.
3. The fully automatic intelligent inspection robot for data centers according to claim 1, wherein: the inspection line adjusting module is used for adjusting and switching the real-time inspection line of the full-automatic intelligent inspection robot, and specifically comprises the steps that the inspection line adjusting module generates optimized intermediate switching line information according to the current position information of the full-automatic intelligent inspection robot in the data center and the optimized inspection line information, and the main control module drives the full-automatic intelligent inspection robot to move to the line inlet indicated by the optimized inspection line information from the current position according to the optimized intermediate switching line information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910296725.2A CN109822597B (en) | 2019-04-14 | 2019-04-14 | Full-automatic intelligent inspection robot of data center |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910296725.2A CN109822597B (en) | 2019-04-14 | 2019-04-14 | Full-automatic intelligent inspection robot of data center |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109822597A CN109822597A (en) | 2019-05-31 |
| CN109822597B true CN109822597B (en) | 2021-01-19 |
Family
ID=66874989
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910296725.2A Active CN109822597B (en) | 2019-04-14 | 2019-04-14 | Full-automatic intelligent inspection robot of data center |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109822597B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110909653B (en) * | 2019-11-18 | 2022-03-15 | 南京七宝机器人技术有限公司 | Method for automatically calibrating screen cabinet of distribution room by indoor robot |
| CN110989604B (en) * | 2019-12-13 | 2023-06-30 | 优刻得科技股份有限公司 | Method and device for processing data by using robot and robot |
| CN115328146B (en) * | 2022-08-30 | 2024-04-02 | 安徽机电职业技术学院 | Self-adaptive path inspection method of inspection robot |
| CN116708506B (en) * | 2023-06-28 | 2023-10-27 | 广州豪特节能环保科技股份有限公司 | Intelligent monitoring method, system and storage medium for data center |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104834309B (en) * | 2015-04-10 | 2018-08-21 | 浙江工业大学 | The optimal touring control method of single mobile robot based on target following control strategy |
| US9701016B1 (en) * | 2015-08-10 | 2017-07-11 | X Development Llc | Detection of movable ground areas of a robot's environment using a transducer array |
| CN107677285B (en) * | 2017-04-11 | 2019-05-28 | 平安科技（深圳）有限公司 | The path planning system and method for robot |
| CN107193282B (en) * | 2017-06-16 | 2020-07-14 | 哈工大机器人集团北京军立方科技有限公司 | Intelligent security robot and intelligent security system |
| CN108170134A (en) * | 2017-11-15 | 2018-06-15 | 国电南瑞科技股份有限公司 | A kind of robot used for intelligent substation patrol paths planning method |
| CN109405828A (en) * | 2018-07-30 | 2019-03-01 | 浙江工业大学 | Mobile robot global optimum path planning method based on LTL-A* algorithm |
| CN108803627A (en) * | 2018-08-20 | 2018-11-13 | 国网福建省电力有限公司 | A kind of crusing robot paths planning method suitable for substation's cubicle switch room |
| CN109500827A (en) * | 2018-11-23 | 2019-03-22 | 北京中大科慧科技发展有限公司 | Machine room intelligent crusing robot |
-
2019
- 2019-04-14 CN CN201910296725.2A patent/CN109822597B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN109822597A (en) | 2019-05-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109822597B (en) | Full-automatic intelligent inspection robot of data center | |
| US20220146462A1 (en) | Method for predicting remaining life of numerical control machine tool | |
| CN108242054A (en) | A kind of steel plate defect detection method, device, equipment and server | |
| US20230152187A1 (en) | Fault signal locating and identifying method of industrial equipment based on microphone array | |
| CN109818798A (en) | A kind of wireless sensor network intruding detection system and method merging KPCA and ELM | |
| KR20190062739A (en) | Method, algorithm and device for Data analytics for predictive maintenance using multiple sensors | |
| Srinivasan et al. | Explainable AI for chiller fault-detection systems: gaining human trust | |
| US11960271B2 (en) | Power plant early warning device and method employing multiple prediction model | |
| CN109194534B (en) | Scheduling and management method for Internet of things equipment group | |
| CN108121961A (en) | Inspection Activity recognition method, apparatus, computer equipment and storage medium | |
| Chen et al. | SWIM: Speed-aware WiFi-based passive indoor localization for mobile ship environment | |
| JP2009068946A (en) | Flaw sorting apparatus, flaw sorting method and program | |
| CN110186854A (en) | A kind of foodsafety information detecting method | |
| CN110490329A (en) | A kind of extensive electricity exception data detection method and system based on machine learning | |
| CN117075650A (en) | Heat dissipation control method, system, electronic equipment, storage medium and new energy vehicle | |
| CN114662619B (en) | Bridge monitoring system based on multi-source data fusion | |
| CN116595756A (en) | Digital twinning-based intelligent operation and maintenance method and device for data center | |
| CN109657943A (en) | Dynamic assessment method, device and the electronic equipment of wind power plant operating states of the units | |
| CN114121025A (en) | Voiceprint fault intelligent detection method and device for substation equipment | |
| CN114581949A (en) | Computer room personnel monitoring method and device, computer equipment and storage medium | |
| CN112085281A (en) | Method and device for detecting safety of business prediction model | |
| Viharos et al. | Vision based, statistical learning system for fault recognition in industrial assembly environment | |
| Tout et al. | Non-stationary process monitoring for change-point detection with known accuracy: Application to wheels coating inspection | |
| Chen et al. | Anomaly Detection Method Based on Granger Causality Modeling | |
| CN109974784A (en) | Semi-automatic detection device |
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 |