CN116090802B - Train inspection task intelligent distribution and scheduling system oriented to vehicle bottom part identification - Google Patents

Train inspection task intelligent distribution and scheduling system oriented to vehicle bottom part identification Download PDF

Info

Publication number
CN116090802B
CN116090802B CN202310384076.8A CN202310384076A CN116090802B CN 116090802 B CN116090802 B CN 116090802B CN 202310384076 A CN202310384076 A CN 202310384076A CN 116090802 B CN116090802 B CN 116090802B
Authority
CN
China
Prior art keywords
vehicle
fault
competence
capability
overhaul
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
Application number
CN202310384076.8A
Other languages
Chinese (zh)
Other versions
CN116090802A (en
Inventor
李威
王占生
舒冬
杨鸿泰
赵兴伟
种传强
刘曦洋
骆礼伦
周虎
谢钦
占俊
陈东
周顺新
赵文涛
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Suzhou Rail Transit Group Co ltd
Chengdu Shengkai Technology Co ltd
Huazhong University of Science and Technology
China Railway Siyuan Survey and Design Group Co Ltd
Original Assignee
Suzhou Rail Transit Group Co ltd
Chengdu Shengkai Technology Co ltd
Huazhong University of Science and Technology
China Railway Siyuan Survey and Design Group Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Suzhou Rail Transit Group Co ltd, Chengdu Shengkai Technology Co ltd, Huazhong University of Science and Technology, China Railway Siyuan Survey and Design Group Co Ltd filed Critical Suzhou Rail Transit Group Co ltd
Priority to CN202310384076.8A priority Critical patent/CN116090802B/en
Publication of CN116090802A publication Critical patent/CN116090802A/en
Application granted granted Critical
Publication of CN116090802B publication Critical patent/CN116090802B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06311—Scheduling, planning or task assignment for a person or group
    • G06Q10/063112—Skill-based matching of a person or a group to a task
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
    • G06Q50/40—
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/60—Type of objects

Abstract

The invention discloses an intelligent distribution and scheduling system of train inspection tasks for vehicle bottom part identification, which comprises an intelligent inspection robot, a data analysis system and an inspection task decision scheduling system; the intelligent inspection robot performs image acquisition and image recognition on the bottom of the train and transmits data to the data analysis system; the data analysis system carries out fault identification under the condition that the cleanliness meets the requirement and compiles the analysis result into a vehicle inspection report; on the premise that the maintainer has the capability of independently completing the vehicle fault, analyzing the competence degree, and carrying out grading and task allocation; the comprehensive capacity of the overhauling staff can be accurately mastered by controlling the overhauling operation quality, the capacity of the overhauling staff is fully utilized, the efficiency is improved, and the waste of overhauling resources is reduced.

Description

Train inspection task intelligent distribution and scheduling system oriented to vehicle bottom part identification
Technical Field
The invention belongs to the field of train inspection task processing, and particularly relates to an intelligent train inspection task distribution and scheduling system for train bottom part identification.
Background
With the rapid development of urban rail transit in China, the number and the running mileage of urban rail transit trains are continuously increased. Therefore, in order to ensure the running safety of urban rail transit, the requirement on train overhaul is higher and higher.
At present, the maintenance of urban rail transit trains mainly takes manpower as the main part, and the problems of multiple repeated maintenance items, high labor intensity and the like exist. Due to different capacities of overhauling staff, the overhauling quality is uneven, even false detection and missing detection can exist, and potential safety hazards of running of the urban rail transit train are caused. And the current inspection robots cannot meet the requirements on the inspection quality and efficiency of trains, and the manual recheck is needed, so that the labor intensity is increased.
Meanwhile, the manual inspection causes the train fault data to lack reasonable collection and discretization. Therefore, the most reasonable maintenance strategy is difficult to provide for various faults of the rail transit train, so that maintenance resource waste is caused, and maintenance cost and labor cost are increased.
Disclosure of Invention
The invention aims to solve the problems that the maintenance quality and efficiency of the invention cannot meet the requirements, and the train fault data lacks reasonable collection and discretization. Therefore, the most reasonable maintenance strategy is difficult to provide for various faults of the rail transit train, so that the problems of maintenance resource waste, and increased maintenance cost and labor cost are caused.
In response to the above-identified deficiencies or improvements in the prior art, the present invention is directed to: an intelligent distribution and scheduling system for train inspection tasks facing to the identification of vehicle bottom parts comprises an intelligent inspection robot, a data analysis system and an inspection task decision scheduling system;
the intelligent inspection robot performs image acquisition and image recognition on the bottom of the urban rail transit train and transmits image data to the data analysis system;
the data analysis system firstly carries out cleanliness recognition through the received image data, carries out fault recognition under the condition that the cleanliness meets the requirement, and compiles analysis results into a vehicle inspection report;
the maintenance task decision scheduling system forms a maintenance personnel set according to the on-duty maintenance personnel conditions
Figure SMS_3
The method comprises the steps of carrying out a first treatment on the surface of the Based on maintainer->
Figure SMS_6
Capability set->
Figure SMS_9
And the relative coefficient of the ability evaluation index +.>
Figure SMS_1
Establishing maintainer->
Figure SMS_4
Capability assessment vector +.>
Figure SMS_8
Evaluating personnel capacity from multiple dimensions, and dividing capacity levels of each maintainer; the maintenance task decision scheduling system collects all received vehicle inspection reports, extracts various fault information and forms a fault set +.>
Figure SMS_10
,X n Is the nth fault; quantifying the premise that each vehicle fault is solved as the maintenance requirement evaluation of the vehicle fault, and establishing a maintenance capability evaluation vector +.>
Figure SMS_2
Finishing the maintenance requirement evaluation of the vehicle fault; the overhaul task decision scheduling system matches the overhaul personnel capability evaluation index with the vehicle fault overhaul requirement by matching the overhaul personnel capability with the vehicle fault overhaul requirement; in the clear the maintainer->
Figure SMS_5
Is provided with independent completion of vehicle failure->
Figure SMS_7
On the premise of capability of the system, analyzing competence degree to obtain a competence function matrix V; and defining the numerical value in the competence function matrix V as a competence index, and grading and task allocation are carried out.
Furthermore, the intelligent inspection robot moves in the inspection trench by identifying the navigation magnetic strips which are installed on the two sides in the inspection trench.
Further, the fault identification comprises identification and judgment of the fault position and parts, fault types and fault degrees of the train;
after determining the fault position and the fault category of the vehicle component to be detected, the data analysis system determines the fault degree of the fault component according to the expert database and the overhaul database, comprehensively forms a vehicle patrol report of the whole rail transit train, and clearly determines the overhaul levels and the overhaul priority levels of different fault components.
Further, the method is based on maintenance personnel
Figure SMS_11
Capability set->
Figure SMS_12
And the relative coefficient of the ability evaluation index +.>
Figure SMS_13
Establishing maintainer->
Figure SMS_14
Capability assessment vector +.>
Figure SMS_15
The method of (1) is as follows:
finishing the overhaul capacity evaluation of the overhaul personnel; the overhauling capability of overhauling personnel is classified and quantized into capability evaluation index according to multiple dimensions
Figure SMS_16
And forming a capability evaluation index set; the maintenance capability evaluation items of the maintenance personnel can be adjusted according to the functional positioning of different maintenance libraries, and k capability evaluation indexes form a maintenance personnel capability set
Figure SMS_17
The method comprises the steps of carrying out a first treatment on the surface of the Therefore, each maintainer has 1 overhaul capacity evaluation vector to measure each capacity evaluation index of the maintainer; therefore, the maintainer is->
Figure SMS_18
Capability assessment vector +.>
Figure SMS_19
The method comprises the following steps:
Figure SMS_20
，
Figure SMS_23
relative coefficient of index called maintainer ability evaluation, dimensionless,/->
Figure SMS_25
The meaning is that describe the maintainer +.>
Figure SMS_26
Owned kth competence evaluation index +.>
Figure SMS_22
Is a relative strength (in comparison to the average level of all service personnel); />
Figure SMS_24
The larger the indication is +.>
Figure SMS_27
The higher the k-th capability evaluation is, the stronger the k-th overhaul capability is; />
Figure SMS_28
Indicating the maintainer->
Figure SMS_21
No kth capability is available.
Further, the premise that each vehicle fault is solved is quantified as an overhaul requirement evaluation of the vehicle fault, and an overhaul capacity evaluation vector is established
Figure SMS_29
The method for finishing the maintenance requirement evaluation of the vehicle fault comprises the following steps:
considering that an overhaul task of an overhaul personnel for completing a certain vehicle fault as one or more overhaul capabilities of the overhaul personnel can meet the requirement of the vehicleThe need for a vehicle fault to be completed; quantifying the preconditions for each vehicle fault to be resolved into a service demand assessment of the vehicle fault, i.e. a service ability assessment vector
Figure SMS_30
Representing the degree of demand of the vehicle fault for different capability evaluation indexes;
Figure SMS_31
，
Figure SMS_33
the index of demand for trouble shooting of vehicles is called relative dimensionless coefficient,/->
Figure SMS_36
In the sense of describing a certain vehicle malfunction +.>
Figure SMS_38
Evaluation index of ability of kth item->
Figure SMS_34
Is a requirement level of (2); />
Figure SMS_37
The larger the indication is +.>
Figure SMS_39
The higher the k-th capability requirement is, the greater the trouble shooting difficulty is; />
Figure SMS_40
=0 repair staff->
Figure SMS_32
Complete vehicle failure->
Figure SMS_35
Is not equipped with the k-th capability.
Furthermore, the method for matching the overhauling task decision scheduling system with the overhauling personnel capability evaluation index and the vehicle fault overhauling requirement by matching the overhauling personnel capability and the vehicle fault overhauling requirement specifically comprises the following steps:
matching the capability evaluation index of the maintainer with the vehicle fault overhaul requirement, and screening out each vehicle overhaul fault
Figure SMS_41
Can be provided with maintainers who independently complete maintenance faults>
Figure SMS_42
The method comprises the steps of carrying out a first treatment on the surface of the Whether or not it passes screening with the Boolean variable +.>
Figure SMS_43
Is expressed in the form of:
Figure SMS_44
，
the formula represents:
Figure SMS_45
during the time, the maintainer is->
Figure SMS_46
Only has the vehicle fault completed independently->
Figure SMS_47
The condition is that the relative coefficient of each capability evaluation index of the overhauling personnel is more than or equal to the relative coefficient of the requirement index of the vehicle fault overhauling; when->
Figure SMS_48
In the event of failure of the vehicle>
Figure SMS_49
Assigned to maintainer->
Figure SMS_50
。
Further, in the clear, the service personnel
Figure SMS_51
Is provided with means for independently completing the failure of the vehicle/>
Figure SMS_52
On the premise of capability of (2) analyzing competence degree to obtain competence function matrix ++>
Figure SMS_53
The method of (1) is as follows: competence function matrix->
Figure SMS_54
Expressed as:
Figure SMS_55
，
Figure SMS_56
，
Figure SMS_57
，
Figure SMS_58
，
Figure SMS_60
representing a competence function in the sense of a function concerning the current service personnel and the vehicle fault requirements>
Figure SMS_63
When the relation between the current service personnel and the vehicle fault (i.e. competence) is expressed, when +.>
Figure SMS_67
When the maintenance personnel do not have the task of completing the vehicle troubleshooting alone, the competence function should be 0 (i.e. not competence to the task), the +.>
Figure SMS_62
The middle j is taken as 1 to obtain a competence function matrix +.>
Figure SMS_66
Middle V 1， j is taken to be 2 to obtain a competence function matrix +.>
Figure SMS_70
Middle V 2， j is taken to be n to obtain a competence function matrix +.>
Figure SMS_72
Middle V n ;/>
Figure SMS_59
Indicating the first part of the maintenance personnel>
Figure SMS_64
Index of evaluation of term Capacity->
Figure SMS_69
Relative to vehicle fault pair->
Figure SMS_71
Index of item ability demand->
Figure SMS_61
Utility functions of (2); />
Figure SMS_65
Utility weights representing the demands of each capability assessment index of a faulty task, the sum of which is 1, v n A competence function matrix representing the nth fault,>
Figure SMS_68
indicating the competence degree of the mth maintenance personnel to the nth fault;
the same vehicle fault is matched with a plurality of overhauling staff to obtain a plurality of competence function matrixes, if the numerical value in the competence function matrixes is larger, the matching performance of the fault and the corresponding overhauling staff is higher, namely the overhauling staff can competence in completing overhauling of the vehicle fault.
Further, if a certain vehicle failure cannot be completed by a single maintainer, the cooperation of the maintainers is considered, and two or more maintainers are used for completing the vehicle togetherOverhauling the failure of a vehicle; therefore, when multiple overhaulers cooperate to complete a vehicle fault, the capability evaluation vectors of multiple operators need to be combined, namely
Figure SMS_73
Matching the capability of the cooperators with the vehicle fault maintenance requirement, and obtaining a new competence function matrix after meeting the matching requirement;
Figure SMS_74
，
Figure SMS_75
，
Figure SMS_76
is the relative coefficient of capacity assessment of the mth service personnel's kth capacity, k=1, 2,3 …,
Figure SMS_77
is the relative coefficient of capacity assessment of the capacity of the kth service personnel, k=1, 2,3 …,
Figure SMS_78
refers to the capacity evaluation vector when the mth maintainer and the q maintainer are combined into a new maintenance unit for completing a certain maintenance task together.
Further, the matrix of the will-be-competence functions
Figure SMS_79
The numerical values in the method are defined as competence indexes, and the method for grading and task allocation comprises the following steps:
(1) Matrix of competence functions
Figure SMS_80
The numerical value in the range is defined as a competence index, and the sizes of the numerical values are graded;
(2) From competence function matrix
Figure SMS_81
Internal selection of the element belonging to the highest rank of the competence index, finding the largest value
Figure SMS_82
Corresponding maintainer->
Figure SMS_83
Distributing a vehicle fault maintenance task to the vehicle fault maintenance task;
(3) Setting f elements belonging to excellent in the e-th row in the competence function matrix V, calculating the relative competence value of each element, and taking the relative competence value as the selection probability
Figure SMS_84
Figure SMS_85
,/>
Figure SMS_86
Is a competence function matrix->
Figure SMS_87
Any one of the f excellent elements in line e,
Figure SMS_88
；
(4) The probability of selection can be determined
Figure SMS_89
Mapping to +.>
Figure SMS_90
Sector, rotating disc falling to the first reference point
Figure SMS_91
Within the sector, the +.>
Figure SMS_92
An element; at this time, the liquid crystal display device,vehicle failure corresponding to this element +.>
Figure SMS_93
Assigned to maintainer->
Figure SMS_94
Completing the distribution of a vehicle fault maintenance task; remove vehicle trouble at next dispensing->
Figure SMS_95
；
(5) Repeating the steps (2) - (4), and sequentially distributing all the vehicle overhaul faults which can be processed by the single maintainer by using the same method;
(6) Multiple persons are combined by the current maintainer to generate a new competence function matrix
Figure SMS_96
；
(7) And (3) repeating the steps (2) - (4), and sequentially distributing all the vehicle fault tasks which can be processed by cooperation of multiple persons by using the same method.
In general, the above technical solutions conceived by the present invention, compared with the prior art, enable the following beneficial effects to be obtained:
(1) The intelligent distribution and scheduling system for the train inspection tasks facing the identification of the vehicle bottom parts, disclosed by the invention, has the advantages of identifying the row cleanliness and identifying faults, analyzing whether dust blowing, sweeping and cleaning are needed, analyzing whether the current cleanliness has an influence on the fault identification, replacing manual work by a machine, reducing the manual inspection amount, and reducing the operation time and intensity of maintainers in a poor operation environment.
(2) According to the train inspection task intelligent distribution and scheduling system for the vehicle bottom part identification, the capability evaluation index of the maintainer is matched with the vehicle fault maintenance requirement, a competence function matrix is constructed, and the task distribution is ensured to meet the requirement: the comprehensive capacity of the maintainers is accurately mastered by controlling the operation quality of the maintainers, the technical capacity of the maintainers is fully utilized, the overhaul efficiency is improved, invalid overhaul is avoided, and the waste of overhaul resources is reduced.
Detailed Description
The present invention will be described in further detail with reference to the following examples in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention. In addition, the technical features of the embodiments of the present invention described below may be combined with each other as long as they do not collide with each other.
The invention relates to an intelligent distribution and scheduling system of train inspection tasks for vehicle bottom part identification, which comprises an intelligent inspection robot, a data analysis system and an inspection task decision scheduling system;
wherein, intelligent inspection robot sets up in the maintenance trench of train maintenance storehouse, and accessible discernment has installed navigation magnetic stripe in the maintenance trench both sides and has moved in the maintenance trench for example. The intelligent inspection robot performs image acquisition (for example, photographing acquisition is performed through a high-definition camera configured on the intelligent inspection robot) and image recognition on the bottom of the urban rail transit train, performs acquisition and detection on cleanliness, loss, deformation and foreign matters of vehicle parts, transmits image data to the data analysis system in real time through a wireless network, and can input feedback instructions to the intelligent inspection robot according to analysis results, so that the inspection robot can be instructed to perform multiple acquisition on suspected points of a vehicle to be inspected, multiple-angle image data can be acquired, accurate analysis is facilitated by the data analysis system, the data analysis system can lock fault points according to identification data, and the intelligent inspection robot is required to perform multiple-time identification on the suspected fault points. The technology can enable the machine to replace manual maintenance operation, clear the key points of the bottom of the train to be detected, avoid repeated maintenance of non-key positions and shorten maintenance time;
the data analysis system firstly carries out cleanliness recognition through the received image data, judges the cleanliness of the bottom parts of the vehicle, and judges whether the vehicle is required to be purged and cleaned or not; secondly, judging whether the cleanliness of the component has influence on fault identification or not; then, performing fault identification, wherein the fault identification comprises identification and judgment of the fault position and components of the train (for example, whether a train wheel axle is worn, deformed and cracked, whether components such as a train body underframe, a train traction rod, a gear box and the like are deformed and cracked, whether a bottom plate bolt of the urban rail transit train is lost and loosened), fault types, fault degrees and the like; after determining the fault position and the fault category of the vehicle component to be detected, the data analysis system determines the fault degree of the fault component according to the expert database and the overhaul database, comprehensively forms the vehicle patrol report of the whole rail transit train, and determines the overhaul level and the overhaul priority level of different fault components; the data analysis system transmits the vehicle inspection report to the inspection task decision scheduling system;
wherein, the maintenance task decision scheduling system forms a maintenance personnel set according to the on-duty maintenance personnel conditions
Figure SMS_97
The method comprises the steps of carrying out a first treatment on the surface of the Based on maintainer->
Figure SMS_98
Capability set->
Figure SMS_99
And the relative coefficient of the ability evaluation index +.>
Figure SMS_100
Establishing maintainer->
Figure SMS_101
Capability assessment vector +.>
Figure SMS_102
Evaluating personnel capacity from multiple dimensions, and dividing capacity levels of each maintainer;
the maintenance task decision scheduling system collects all received vehicle inspection reports, extracts various fault information and forms a fault set
Figure SMS_103
,X n Is the nth fault; quantifying the premise that each vehicle fault is solved as the maintenance requirement evaluation of the vehicle fault, and establishing a maintenance capability evaluation vector +.>
Figure SMS_104
Finishing the maintenance requirement evaluation of the vehicle fault;
the overhaul task decision scheduling system matches the overhaul personnel capability evaluation index with the vehicle fault overhaul requirement by matching the overhaul personnel capability with the vehicle fault overhaul requirement; in the clear, the maintainer
Figure SMS_105
Is provided with means for independently completing the failure of the vehicle
Figure SMS_106
On the premise of capability of the system, analyzing competence degree to obtain a competence function matrix V; defining the numerical value in the competence function matrix V as a competence index, and grading and task allocation are carried out, so that each maintenance task is completed by a proper maintenance personnel, and the maintenance task meeting allocation and scheduling requirements are ensured;
specifically, the allocation and scheduling requirements include:
(1) The capacity of the maintainer is enough to complete the fault task of a certain vehicle;
(2) Ensuring that personnel with service features can be prioritised to their vehicle failure tasks that are good at handling (i.e. relatively shorter than other service personnel than service time);
(3) Ensuring that the vehicle fault is overhauled preferentially when the overhauling time is nearly finished;
(4) Ensure the workload balance of different overhauling staff).
Wherein, based on maintenance personnel
Figure SMS_107
Capability set->
Figure SMS_108
And the relative coefficient of the ability evaluation index +.>
Figure SMS_109
Establishing maintainer->
Figure SMS_110
Capability assessment vector +.>
Figure SMS_111
The method of (1) is as follows:
finishing the overhaul capacity evaluation of the overhaul personnel; the overhauling capability of overhauling personnel is classified and quantized into capability evaluation index according to multiple dimensions
Figure SMS_112
And forming a capability evaluation index set; according to the functional positioning of different overhaul libraries, overhaul capacity evaluation items of overhaulers can be adjusted, and k capacity evaluation indexes form an overhaul capacity set +.>
Figure SMS_113
The method comprises the steps of carrying out a first treatment on the surface of the Therefore, each maintainer has 1 overhaul capacity evaluation vector to measure each capacity evaluation index of the maintainer; therefore, the maintainer is->
Figure SMS_114
Capability assessment vector +.>
Figure SMS_115
The method comprises the following steps:
Figure SMS_116
，
Figure SMS_118
relative coefficient of index called maintainer ability evaluation, dimensionless,/->
Figure SMS_120
The meaning is that describe the maintainer +.>
Figure SMS_122
Owned kth competence evaluation index +.>
Figure SMS_119
Is a relative strength (in comparison to the average level of all service personnel); />
Figure SMS_121
The larger the indication is +.>
Figure SMS_123
The higher the k-th capability evaluation is, the stronger the k-th overhaul capability is; />
Figure SMS_124
Indicating the maintainer->
Figure SMS_117
No kth capability is available.
Specifically, the premise that each vehicle fault is solved is quantified as an overhaul requirement evaluation of the vehicle fault, and an overhaul capacity evaluation vector is established
Figure SMS_125
The method for finishing the maintenance requirement evaluation of the vehicle fault comprises the following steps:
considering that an overhaul task of an overhaul personnel for completing a certain vehicle fault is considered that certain or more overhaul capabilities of the overhaul personnel can meet the requirement that the vehicle fault is completed; quantifying the preconditions for each vehicle fault to be resolved into a service demand assessment of the vehicle fault, i.e. a service ability assessment vector
Figure SMS_126
Representing the degree of demand of the vehicle fault for different capability evaluation indexes;
Figure SMS_127
，
Figure SMS_129
the index of demand for trouble shooting of vehicles is called relative dimensionless coefficient,/->
Figure SMS_133
In the sense of describing a certain vehicle malfunction +.>
Figure SMS_135
Evaluation index of ability of kth item->
Figure SMS_130
Is a requirement level of (2); />
Figure SMS_132
The larger the indication is +.>
Figure SMS_134
The higher the k-th capability requirement is, the greater the trouble shooting difficulty is; />
Figure SMS_136
=0, maintainer->
Figure SMS_128
Complete vehicle failure->
Figure SMS_131
Is not equipped with the k-th capability.
Specifically, the method for matching the overhauling task decision scheduling system with the overhauling personnel capability evaluation index and the vehicle troubleshooting requirement by matching the overhauling personnel capability and the vehicle troubleshooting requirement specifically comprises the following steps:
matching the capability evaluation index of the maintainer with the vehicle fault overhaul requirement, and screening out each vehicle overhaul fault
Figure SMS_137
Can be provided with maintainers who independently complete maintenance faults>
Figure SMS_138
The method comprises the steps of carrying out a first treatment on the surface of the Whether or not it passes screening with the Boolean variable +.>
Figure SMS_139
Is expressed in the form of:
Figure SMS_140
，
the formula represents:
Figure SMS_141
during the time, the maintainer is->
Figure SMS_142
Only has the vehicle fault completed independently->
Figure SMS_143
The condition is that the relative coefficient of each capability evaluation index of the overhauling personnel is more than or equal to the relative coefficient of the requirement index of the vehicle fault overhauling; when (when)
Figure SMS_144
In the event of failure of the vehicle>
Figure SMS_145
Assigned to maintainer->
Figure SMS_146
。
In the clear, the maintainer
Figure SMS_147
Is provided with independent completion of vehicle failure->
Figure SMS_148
On the premise of capability of (2) analyzing competence degree to obtain competence function matrix ++>
Figure SMS_149
The method of (1) is as follows: competence function matrix->
Figure SMS_150
Expressed as:
Figure SMS_151
，
Figure SMS_152
，
Figure SMS_153
，
Figure SMS_154
，
Figure SMS_155
representing a competence function in the sense of a function concerning the current service personnel and the vehicle fault requirements>
Figure SMS_160
When the relation between the current service personnel and the vehicle fault (i.e. competence) is expressed, when +.>
Figure SMS_166
When the service personnel do not have the ability to complete the vehicle troubleshooting task alone, the competence function should be 0 (i.e., not competence to the task),
Figure SMS_158
the middle j is taken as 1 to obtain a competence function matrix +.>
Figure SMS_162
Middle V 1， j is taken to be 2 to obtain a competence function matrix +.>
Figure SMS_164
Middle V 2， j is taken to be n to obtain a competence function matrix +.>
Figure SMS_167
Middle V n ;/>
Figure SMS_157
Indicating the first part of the maintenance personnel>
Figure SMS_161
Index of evaluation of term Capacity->
Figure SMS_165
Relative to vehicle fault pair->
Figure SMS_168
Index of item ability demand->
Figure SMS_156
Utility functions of (2); />
Figure SMS_159
Utility weights representing the demands of each capability assessment index of a faulty task, the sum of which is 1, v n A competence function matrix representing the nth fault,>
Figure SMS_163
indicating the competence degree of the mth maintenance personnel to the nth fault;
the same vehicle fault is matched with a plurality of overhauling staff to obtain a plurality of competence function matrixes, if the numerical value in the competence function matrixes is larger, the matching performance of the fault and the corresponding overhauling staff is higher, namely the overhauling staff can competence in completing overhauling of the vehicle fault.
If a certain vehicle fault can not be completed by a single maintainer, the cooperation of the maintainers is considered, and two or more maintainers are used for jointly completing the maintenance of the vehicle fault; therefore, when multiple overhaulers cooperate to complete a vehicle fault, the capability evaluation vectors of multiple operators need to be combined, namely
Figure SMS_169
Matching the capability of the cooperators with the vehicle fault maintenance requirement, and obtaining a new competence function matrix after meeting the matching requirement;
Figure SMS_170
，
Figure SMS_171
，
Figure SMS_172
is the relative coefficient of capacity assessment of the mth service personnel's kth capacity, k=1, 2,3 …,
Figure SMS_173
is the relative coefficient of capacity assessment of the capacity of the kth service personnel, k=1, 2,3 …,
Figure SMS_174
refers to the capacity evaluation vector when the mth maintainer and the q maintainer are combined into a new maintenance unit for completing a certain maintenance task together.
Specifically, the matrix of the will-be-competent functions
Figure SMS_175
The numerical values in the method are defined as competence indexes, and the method for grading and task allocation comprises the following steps:
(1) Matrix of competence functions
Figure SMS_176
The numerical value in the range is defined as a competence index, and the sizes of the numerical values are graded;
for example, into 5 grades
Figure SMS_177
(2) From competence function matrix
Figure SMS_178
Inner selection->
Figure SMS_179
Figure SMS_180
Searching for the most important elementBig value +.>
Figure SMS_181
Corresponding maintainer->
Figure SMS_182
Distributing a vehicle fault maintenance task to the vehicle fault maintenance task;
(3) Setting f elements belonging to excellent in the e-th row in the competence function matrix V, calculating the relative competence value of each element, and taking the relative competence value as the selection probability
Figure SMS_183
Figure SMS_184
,/>
Figure SMS_185
Is a competence function matrix->
Figure SMS_186
Any one of the f excellent elements in line e,
Figure SMS_187
；
(4) The probability of selection can be determined
Figure SMS_188
Mapping to +.>
Figure SMS_189
Sector, the rotating disk falls to the +.>
Figure SMS_190
Within the sector, the +.>
Figure SMS_191
An element; at this time, the vehicle corresponding to the element is failed +.>
Figure SMS_192
Assigned to service personnel
Figure SMS_193
Completing the distribution of a vehicle fault maintenance task; remove vehicle trouble at next dispensing->
Figure SMS_194
；
(5) Repeating the steps (2) - (4), and sequentially distributing all the vehicle overhaul faults which can be processed by the single maintainer by using the same method;
(6) Multiple persons are combined by the current maintainer to generate a new competence function matrix
Figure SMS_195
；
(7) And (3) repeating the steps (2) - (4), and sequentially distributing all the vehicle fault tasks which can be processed by cooperation of multiple persons by using the same method.
After an overhaul worker obtains an overhaul task from the overhaul task decision scheduling system, the overhaul terminal is held by the hand to carry out overhaul at a corresponding position, and after the overhaul is completed, the overhaul worker checks and cancels the overhaul task on the hand terminal. After the maintenance task decision scheduling system receives maintenance task verification information fed back by the handheld terminal, the intelligent inspection robot can be instructed to identify corresponding maintenance positions, identification data are transmitted to the data analysis system in real time, the conditions before maintenance and after maintenance are compared, whether the corresponding maintenance tasks are completed or not is checked, the data after maintenance are compared with the data in the database, and whether the maintenance reaches the corresponding maintenance quality requirement or not is analyzed. The data analysis system transmits the rechecking report to the maintenance task decision system decision scheduling system, if the rechecking report is in the conclusion of 'maintenance task completion', the maintenance task decision scheduling system determines to cancel the maintenance task and records the maintenance workload to the service of the corresponding maintenance personnel; if the review report conclusion is that the maintenance task is not completed and the maintenance quality does not meet the requirement, the maintenance task decision-making system decides that the maintenance task is not approved by the scheduling system, and redistributes maintenance staff to carry out maintenance, records the maintenance result to the service of the corresponding staff, and shows that the maintenance quality has a problem, and the maintenance staff needs to strengthen training and learning of the maintenance skills of the part.
According to the invention, the capability evaluation index of the maintainer is matched with the vehicle fault overhaul requirement, and a competence function matrix is constructed, so that task allocation is ensured to meet the requirement: the comprehensive capacity of the maintainers is accurately mastered by controlling the operation quality of the maintainers, the technical capacity of the maintainers is fully utilized, the overhaul efficiency is improved, invalid overhaul is avoided, and the waste of overhaul resources is reduced.
It will be readily appreciated by those skilled in the art that the foregoing description is merely a preferred embodiment of the invention and is not intended to limit the invention, but any modifications, equivalents, improvements or alternatives falling within the spirit and principles of the invention are intended to be included within the scope of the invention.

Claims (6)

1. An intelligent allocation and scheduling system for train inspection tasks facing to vehicle bottom part identification is characterized in that: the system comprises an intelligent inspection robot, a data analysis system and an inspection task decision scheduling system;
the intelligent inspection robot performs image acquisition and image recognition on the bottom of the urban rail transit train and transmits image data to the data analysis system;
the data analysis system firstly carries out cleanliness recognition through the received image data, carries out fault recognition under the condition that the cleanliness meets the requirement, and compiles analysis results into a vehicle inspection report;
the maintenance task decision scheduling system forms a maintenance personnel set according to the on-duty maintenance personnel conditions
Figure QLYQS_3
The method comprises the steps of carrying out a first treatment on the surface of the Based on maintainer->
Figure QLYQS_6
Capability set->
Figure QLYQS_8
And the relative coefficient of the ability evaluation index +.>
Figure QLYQS_2
Establishing maintainer->
Figure QLYQS_4
Capability assessment vector +.>
Figure QLYQS_7
Evaluating personnel capacity from multiple dimensions, and dividing capacity levels of each maintainer; the maintenance task decision scheduling system collects all received vehicle inspection reports, extracts various fault information and forms a fault set +.>
Figure QLYQS_10
,X n Is the nth fault; quantifying the premise that each vehicle fault is solved as the maintenance requirement evaluation of the vehicle fault, and establishing a maintenance capability evaluation vector +.>
Figure QLYQS_1
Finishing the maintenance requirement evaluation of the vehicle fault; the overhaul task decision scheduling system matches the overhaul personnel capability evaluation index with the vehicle fault overhaul requirement by matching the overhaul personnel capability with the vehicle fault overhaul requirement; in the clear the maintainer->
Figure QLYQS_5
Is provided with independent completion of vehicle failure->
Figure QLYQS_9
On the premise of capability of the system, analyzing competence degree to obtain a competence function matrix V; defining the numerical value in the competence function matrix V as a competence index, and carrying out grading and task allocation;
the method is based on maintenance personnel
Figure QLYQS_11
Capability set->
Figure QLYQS_12
And the relative coefficient of the ability evaluation index +.>
Figure QLYQS_13
Establishing maintainer->
Figure QLYQS_14
Capability assessment vector of (a)
Figure QLYQS_15
The method of (1) is as follows:
finishing the overhaul capacity evaluation of the overhaul personnel; the overhauling capability of overhauling personnel is classified and quantized into capability evaluation index according to multiple dimensions
Figure QLYQS_16
And forming a capability evaluation index set; according to the functional positioning of different overhaul libraries, overhaul capacity evaluation items of overhaulers can be adjusted, and k capacity evaluation indexes form an overhaul capacity set +.>
Figure QLYQS_17
K=1, 2,3 …; therefore, each maintainer has 1 overhaul capacity evaluation vector to measure each capacity evaluation index of the maintainer; therefore, the maintainer is->
Figure QLYQS_18
Capability assessment vector +.>
Figure QLYQS_19
The method comprises the following steps:
Figure QLYQS_20
，
Figure QLYQS_22
relative coefficient of index called maintainer ability evaluation, dimensionless,/->
Figure QLYQS_25
The meaning is that describe the maintainer +.>
Figure QLYQS_26
Owned kth competence evaluation index +.>
Figure QLYQS_23
Is a relative strength of (a); />
Figure QLYQS_24
The larger the indication is +.>
Figure QLYQS_27
The higher the k-th capability evaluation is, the stronger the k-th overhaul capability is; />
Figure QLYQS_28
Indicating the maintainer->
Figure QLYQS_21
No kth capability;
the premise that each vehicle fault is solved is quantified as maintenance requirement evaluation of the vehicle fault, and a maintenance capacity evaluation vector is established
Figure QLYQS_29
The method for finishing the maintenance requirement evaluation of the vehicle fault comprises the following steps:
considering that an overhaul task of an overhaul personnel for completing a certain vehicle fault is considered that certain or more overhaul capabilities of the overhaul personnel can meet the requirement that the vehicle fault is completed; quantifying the preconditions for each vehicle fault to be resolved into a service demand assessment of the vehicle fault, i.e. a service ability assessment vector
Figure QLYQS_30
Representing the degree of demand of the vehicle fault for different capability evaluation indexes;
Figure QLYQS_31
，
Figure QLYQS_33
the relative coefficient of the demand index called the vehicle trouble shooting, dimensionless,/->
Figure QLYQS_37
In the sense of describing a certain vehicle malfunction +.>
Figure QLYQS_39
Evaluation index of ability of kth item->
Figure QLYQS_34
Is a requirement level of (2); />
Figure QLYQS_36
The larger the indication is +.>
Figure QLYQS_38
The higher the k-th capability requirement is, the greater the trouble shooting difficulty is; />
Figure QLYQS_40
Indicating the maintainer->
Figure QLYQS_32
Complete vehicle failure->
Figure QLYQS_35
Is not provided with the k-th capability;
in the clear, the maintainer
Figure QLYQS_41
Is provided with independent completion of vehicle failure->
Figure QLYQS_42
On the premise of capability of (2) analyzing competence degree to obtain competence function matrix ++>
Figure QLYQS_43
The method of (1) is as follows: competence function matrix->
Figure QLYQS_44
Expressed as:
Figure QLYQS_45
，
Figure QLYQS_46
，
Figure QLYQS_47
，
Figure QLYQS_48
，
Figure QLYQS_50
representing a competence function in the sense of a function related to the current service personnel and the vehicle fault requirements when
Figure QLYQS_54
When representing the relationship between the current service personnel and the vehicle failure, when +.>
Figure QLYQS_58
When the maintenance personnel does not independently complete the vehicle trouble shooting task, the competence function is 0 +.>
Figure QLYQS_51
Middle j takes 1, namelyObtaining a competence function matrix->
Figure QLYQS_56
Middle V 1， j is taken to be 2 to obtain a competence function matrix +.>
Figure QLYQS_61
Middle V 2， j is taken to be n to obtain a competence function matrix +.>
Figure QLYQS_62
Middle V n ;/>
Figure QLYQS_49
Indicating the first part of the maintenance personnel>
Figure QLYQS_53
Index of evaluation of term Capacity->
Figure QLYQS_57
Relative to vehicle fault pair->
Figure QLYQS_60
Index of item ability demand->
Figure QLYQS_52
Utility functions of (2); />
Figure QLYQS_55
Utility weights representing the demands of each capability assessment index of a faulty task, the sum of which is 1, v n A competence function matrix representing the nth fault,>
Figure QLYQS_59
indicating the competence degree of the mth maintenance personnel to the nth fault;
the same vehicle fault is matched with a plurality of overhauling staff to obtain a plurality of competence function matrixes, if the numerical value in the competence function matrixes is larger, the matching performance of the fault and the corresponding overhauling staff is higher, namely the overhauling staff can competence in completing overhauling of the vehicle fault.
2. The intelligent distribution and dispatch system for train inspection tasks for vehicle bottom part identification of claim 1, wherein: the intelligent inspection robot moves in the inspection trench by identifying the navigation magnetic strips which are installed on the two sides in the inspection trench.
3. The intelligent distribution and dispatch system for train inspection tasks for vehicle bottom part identification of claim 1, wherein: the fault identification comprises identifying and judging the fault position, parts, fault types and fault degrees of the train;
after determining the fault position and the fault category of the vehicle component to be detected, the data analysis system determines the fault degree of the fault component according to the expert database and the overhaul database, comprehensively forms a vehicle patrol report of the whole rail transit train, and clearly determines the overhaul levels and the overhaul priority levels of different fault components.
4. The intelligent distribution and dispatch system for train inspection tasks for vehicle bottom part identification of claim 1, wherein: the method for matching the overhauling task decision scheduling system with the overhauling personnel capability evaluation index and the vehicle fault overhauling requirement by matching the overhauling personnel capability and the vehicle fault overhauling requirement specifically comprises the following steps:
matching the capability evaluation index of the maintainer with the vehicle fault overhaul requirement, and screening out each vehicle overhaul fault
Figure QLYQS_63
Can be provided with maintainers who independently complete maintenance faults>
Figure QLYQS_64
The method comprises the steps of carrying out a first treatment on the surface of the Whether or not it passes screening with the Boolean variable +.>
Figure QLYQS_65
Is expressed in the form of:
Figure QLYQS_66
，
the formula represents:
Figure QLYQS_67
during the time, the maintainer is->
Figure QLYQS_68
Only has the vehicle fault completed independently->
Figure QLYQS_69
The condition is that the relative coefficient of each capability evaluation index of the overhauling personnel is more than or equal to the relative coefficient of the requirement index of the vehicle fault overhauling; when (when)
Figure QLYQS_70
In the event of failure of the vehicle>
Figure QLYQS_71
Assigned to maintainer->
Figure QLYQS_72
。
5. The intelligent distribution and dispatch system for train inspection tasks for vehicle bottom part identification of claim 1, wherein: if a certain vehicle fault can not be completed by a single maintainer, the cooperation of the maintainers is considered, and two or more maintainers are used for jointly completing the maintenance of the vehicle fault; therefore, when multiple overhaulers cooperate to complete a vehicle fault, the capability evaluation vectors of multiple operators need to be combined, namely
Figure QLYQS_73
Matching the capability of the cooperators with the vehicle fault maintenance requirement, and obtaining a new competence function matrix after meeting the matching requirement;
Figure QLYQS_74
，
Figure QLYQS_75
，
Figure QLYQS_76
is the relative coefficient of capacity assessment of the mth service personnel's kth capacity, k=1, 2,3 …,
Figure QLYQS_77
is the relative coefficient of capacity assessment of the capacity of the kth service personnel, k=1, 2,3 …,
Figure QLYQS_78
refers to the capacity evaluation vector when the mth maintainer and the q maintainer are combined into a new maintenance unit for completing a certain maintenance task together.
6. The intelligent distribution and dispatch system for train inspection tasks for vehicle bottom part identification of claim 1, wherein:
the matrix of the will competence functions
Figure QLYQS_79
The numerical values in the method are defined as competence indexes, and the method for grading and task allocation comprises the following steps:
(1) Matrix of competence functions
Figure QLYQS_80
The numerical value in the range is defined as a competence index, and the sizes of the numerical values are graded;
(2) From competence function matrix
Figure QLYQS_81
Internal selectionThe element belonging to the highest class of competence index, searching for the maximum value +.>
Figure QLYQS_82
Corresponding maintainer->
Figure QLYQS_83
Distributing a vehicle fault maintenance task to the vehicle fault maintenance task;
(3) Setting f elements belonging to excellent in the e-th row in the competence function matrix V, calculating the relative competence value of each element, and taking the relative competence value as the selection probability
Figure QLYQS_84
,/>
Figure QLYQS_85
,/>
Figure QLYQS_86
Is a competence function matrix->
Figure QLYQS_87
Any one of the f excellent elements in line e,
Figure QLYQS_88
；
(4) The probability of selection can be determined
Figure QLYQS_89
Mapping to +.>
Figure QLYQS_90
Sector, the rotating disk falls to the +.>
Figure QLYQS_91
Within the sector, the +.>
Figure QLYQS_92
Individual elementsThe method comprises the steps of carrying out a first treatment on the surface of the At this time, the vehicle corresponding to the element is failed +.>
Figure QLYQS_93
Assigned to service personnel
Figure QLYQS_94
Completing the distribution of a vehicle fault maintenance task; remove vehicle trouble at next dispensing->
Figure QLYQS_95
；
(5) Repeating the steps (2) - (4), and sequentially distributing all the vehicle overhaul faults which can be processed by the single maintainer by using the same method;
(6) Multiple persons are combined by the current maintainer to generate a new competence function matrix
Figure QLYQS_96
；
(7) And (3) repeating the steps (2) - (4), and sequentially distributing all the vehicle fault tasks which can be processed by cooperation of multiple persons by using the same method.
CN202310384076.8A 2023-04-12 2023-04-12 Train inspection task intelligent distribution and scheduling system oriented to vehicle bottom part identification Active CN116090802B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310384076.8A CN116090802B (en) 2023-04-12 2023-04-12 Train inspection task intelligent distribution and scheduling system oriented to vehicle bottom part identification

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310384076.8A CN116090802B (en) 2023-04-12 2023-04-12 Train inspection task intelligent distribution and scheduling system oriented to vehicle bottom part identification

Publications (2)

Publication Number Publication Date
CN116090802A CN116090802A (en) 2023-05-09
CN116090802B true CN116090802B (en) 2023-06-27

Family

ID=86212448

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310384076.8A Active CN116090802B (en) 2023-04-12 2023-04-12 Train inspection task intelligent distribution and scheduling system oriented to vehicle bottom part identification

Country Status (1)

Country Link
CN (1) CN116090802B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112330163B (en) * 2020-11-09 2023-07-07 北京元心科技有限公司 Task allocation method, system, electronic device and computer readable storage medium
CN117474191B (en) * 2023-12-28 2024-04-05 成都秦川物联网科技股份有限公司 GIS (geographic information system) inspection management method based on intelligent water meter, internet of things system and device

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104637021A (en) * 2013-11-08 2015-05-20 广州市地下铁道总公司 Condition-maintenance-mode city rail vehicle auxiliary maintenance system
CN107862763A (en) * 2017-11-06 2018-03-30 中国人民解放军国防科技大学 train safety early warning evaluation model training method, module and monitoring evaluation system

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11327475B2 (en) * 2016-05-09 2022-05-10 Strong Force Iot Portfolio 2016, Llc Methods and systems for intelligent collection and analysis of vehicle data
CN107364459B (en) * 2017-06-28 2019-06-25 北京康拓红外技术股份有限公司 A kind of rolling stock column inspection intelligent robot operating system and method
CN110733539B (en) * 2019-10-14 2024-02-27 中铁第四勘察设计院集团有限公司 Intelligent train inspection system and method for urban rail transit vehicle base
EP3889777A1 (en) * 2020-03-31 2021-10-06 Accenture Global Solutions Limited System and method for automating fault detection in multi-tenant environments
CN112860952B (en) * 2020-12-17 2023-06-20 成都盛锴科技有限公司 Method and system for positioning and overhauling parts by inspection robot
CN112633758B (en) * 2020-12-31 2024-01-26 重庆电子工程职业学院 Intelligent on-line management system for maintenance personnel
CN114493154A (en) * 2021-12-30 2022-05-13 佳都科技集团股份有限公司 Fault maintenance work order distribution method and device based on rail transit
CN114735044A (en) * 2022-03-14 2022-07-12 苏州视恺智能科技有限公司 Intelligent railway vehicle inspection robot

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104637021A (en) * 2013-11-08 2015-05-20 广州市地下铁道总公司 Condition-maintenance-mode city rail vehicle auxiliary maintenance system
CN107862763A (en) * 2017-11-06 2018-03-30 中国人民解放军国防科技大学 train safety early warning evaluation model training method, module and monitoring evaluation system

Also Published As

Publication number Publication date
CN116090802A (en) 2023-05-09

Similar Documents

Publication Publication Date Title
CN116090802B (en) Train inspection task intelligent distribution and scheduling system oriented to vehicle bottom part identification
CN105083331B (en) Operation management system for locomotive running preparation
WO2021185177A1 (en) Method for evaluating health status of petrochemical atmospheric oil storage tank using data from multiple sources
CN110222437A (en) Appraisal procedure, device and the storage medium of train car team health status
CN103559555B (en) A kind of method for optimizing its product plan maintenance intervals for seating plane manufacturer
CN106327062A (en) Method for evaluating state of power distribution network equipment
CN105222879B (en) The long-range self-diagnosable system and its self-diagnosing method of complicated dynamic weighing sensing network
CN109522962B (en) Chemical plant safety quantitative evaluation method
CN115018384A (en) Building site security risk assessment method and system
KR102063796B1 (en) Used car grade diagnostic method
CN107230020B (en) Method for evaluating work organization efficiency of high-speed rail dispatcher and related method and system thereof
CN112329955A (en) Calculation method for determining equipment maintenance grade
CN116452154B (en) Project management system suitable for communication operators
CN113628024A (en) Financial data intelligent auditing system and method based on big data platform system
CN111553581B (en) Equipment maintainability evaluation model based on entropy value
CN116168356B (en) Vehicle damage judging method based on computer vision
CN110766248B (en) Workshop artificial factor reliability assessment method based on SHEL and interval intuitionistic fuzzy assessment
CN112732773B (en) Method and system for checking uniqueness of relay protection defect data
CN115496233A (en) Markov model-based data middlebox operation fault prediction method
CN114399203B (en) Transformer substation maintenance task processing method and system, terminal device and storage medium
CN101377454A (en) Method for comprehensively evaluating mine ventilation system based on gray cluster analysis
CN114021969B (en) Agricultural enterprise safety production risk index analysis system
CN116629657A (en) Equipment maintenance guarantee resource allocation scheme evaluation method and device
CN114398257A (en) Method and device for determining software test validity measurement
CN116485238A (en) Comprehensive evaluation method for use quality of aviation 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