CN112862295A - Bridge and tunnel maintenance autonomous decision-making method based on Q learning - Google Patents
Bridge and tunnel maintenance autonomous decision-making method based on Q learning Download PDFInfo
- Publication number
- CN112862295A CN112862295A CN202110141634.9A CN202110141634A CN112862295A CN 112862295 A CN112862295 A CN 112862295A CN 202110141634 A CN202110141634 A CN 202110141634A CN 112862295 A CN112862295 A CN 112862295A
- Authority
- CN
- China
- Prior art keywords
- maintenance
- bridge
- tunnel
- road
- health state
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000012423 maintenance Methods 0.000 title claims abstract description 75
- 238000000034 method Methods 0.000 title claims abstract description 19
- 230000036541 health Effects 0.000 claims abstract description 45
- 238000012549 training Methods 0.000 claims abstract description 13
- 238000011156 evaluation Methods 0.000 claims abstract description 4
- 230000009471 action Effects 0.000 claims description 9
- 230000008439 repair process Effects 0.000 claims description 9
- 239000013598 vector Substances 0.000 claims description 6
- 230000000694 effects Effects 0.000 description 2
- 230000003862 health status Effects 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
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
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
- G06Q10/20—Administration of product repair or maintenance
-
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0283—Price estimation or determination
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/08—Construction
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Game Theory and Decision Science (AREA)
- Accounting & Taxation (AREA)
- Educational Administration (AREA)
- Operations Research (AREA)
- Finance (AREA)
- Quality & Reliability (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a Q learning-based road bridge and tunnel maintenance autonomous decision method; the method comprises the following steps: 1. establishing an index system for evaluating the health state of the road, bridge and tunnel; 2. evaluating the health state of the road, bridge and tunnel according to an index system; 3. acquiring health state data { X. }ofthe road, bridge and tunnel, recording maintenance decisions at corresponding moments and cost y. generated by the maintenance decisions, and forming a historical data set of the health state and the maintenance cost of the road, bridge and tunnel; 4. judging whether a Q learning model exists or not and whether the Q learning model needs to be updated or not; 5. training or updating a Q learning model; 6. using Q learning model, according to health statusIndex XtObtaining maintenance decision at(ii) a 7. Performing maintenance decision atEntering step 2, reacquiring the health state evaluation X of the road, bridge and tunnel according to the state transitiont+1. The method comprehensively considers the health state indexes and the maintenance cost of the roads, bridges and tunnels, and realizes the maintenance decision of the roads, bridges and tunnels under the aim of minimizing the maintenance cost.
Description
Technical Field
The invention relates to the technical field of road, bridge and tunnel maintenance, in particular to a Q learning-based road, bridge and tunnel maintenance autonomous decision-making method.
Background
The healthy road, bridge and tunnel state is the premise of ensuring high efficiency of material circulation and smooth trip of the masses. Therefore, it is of great significance to scientifically make maintenance decisions of the road, bridge and tunnel to ensure that the road, bridge and tunnel are in a healthy state.
However, as a main person and an operation unit of the bridge and tunnel, there is a concern about how to balance the relationship between the state of the bridge and the tunnel and the maintenance cost, that is, how to maintain the state of the bridge and tunnel while maintaining the state of the bridge and tunnel at a low maintenance cost.
The existing road bridge and tunnel maintenance decision method is mostly based on various health status indexes, and the required cost can be rarely considered comprehensively. In practice, in order to comprehensively consider the health status of roads, bridges and tunnels and maintenance cost, the final decision may need to depend on the subjective experience and judgment of experts.
Therefore, in the decision-making problem of road, bridge and tunnel maintenance, how to save maintenance cost and get rid of subjective judgment restriction, and the realization of autonomous decision-making of road, bridge and tunnel maintenance becomes a technical problem which needs to be solved urgently by technical personnel in the field.
Disclosure of Invention
In view of the above defects in the prior art, the invention provides a Q-learning-based autonomous decision-making method for maintaining a bridge and a tunnel in a healthy state and spending minimum maintenance cost, so as to make a suitable autonomous decision-making scheme for maintaining the bridge and the tunnel and obtain maximum economic and social benefits.
In order to achieve the aim, the invention discloses a road bridge and tunnel maintenance autonomous decision-making method based on Q learning; the method comprises the following steps:
step 1, establishing an index system for evaluating the health state of a road, bridge and tunnel;
step 2, evaluating the health state of the road, bridge and tunnel according to an index system, and recording an index vector at the time of t as Xt(ii) a Wherein the continuous index vector is discretized;
step 3, collecting health state data { X. } of the road, bridge and tunnel, recording maintenance decisions at corresponding moments and cost y. generated by the maintenance decisions, and forming a historical data set of the health state and the maintenance cost of the road, bridge and tunnel; if the maintenance is not carried out at the moment t, the historical maintenance cost y at the moment t is concentrated in the historical data of the health state and the maintenance costt=0;
Step 4, judging whether a Q learning model exists or not, and if not, entering step 5; if yes, further judging whether the Q learning model is periodically updated; if the Q learning model needs to be updated, entering a step 5, otherwise, entering a step 6;
step 5, retraining the Q learning model based on the historical data set of the health state and maintenance cost of the road, bridge and tunnel;
step 6, utilizing the Q learning model according to the health state index XtObtaining maintenance decision at;
Step 7, executing the maintenance decision atEntering step 2, reacquiring the health state evaluation X of the road, bridge and tunnel according to the state transitiont+1。
Preferably, the step 5 comprises the following steps:
step 5.1, establishing a Q table of the health state indexes of the roads, bridges and tunnels and maintenance decisions;
step 5.2, randomly selecting the health state X of the road, the bridge and the tunnel0Starting a new round of training;
step 5.3, for any of said health states XiT, T being a specified upper decision period limit, the decision action a being made using an epsilon-greedy policyiT, T is the specified upper decision period limit;
step 5.4, according to the decision action aiTo obtain a new health state Xi+1And the resulting maintenance cost yi(ii) a To minimize the maintenance cost spent in a given decision period, the reward for this decision is recorded as r (X)i,ai)=-yi;
And 5.5, updating the Q value, specifically as follows:
Q(Xi,ai)←(1-a)Q(Xi,ai)+a(r(Xi,ai)+γMax{Q(Xi+1,ai)});
wherein a is a learning rate, and a belongs to [0,1 ];
γ is the reward discount factor, and γ ═ 0, 1;
step 5.6, when the training number in the round does not exceed the upper limit of the decision period, i.e. i is less than or equal to T, the state is transferred, i.e. Xi←Xi+1Returning to the step 5.3; otherwise, returning to the step 5.2, starting a new round of training until the Q table is converged, and ending the training.
More preferably, in said step 5.3, said decision action aiIncluding no maintenance, daily maintenance, minor repair, intermediate repair, major repair and reconstruction and extension.
The invention has the beneficial effects that:
the method comprehensively considers the health state indexes and the maintenance cost of the roads, bridges and tunnels, and realizes the maintenance decision of the roads, bridges and tunnels under the aim of minimizing the maintenance cost.
According to the method, the dependence of artificial experience is eliminated by establishing an effective Q learning model, and the autonomous decision of road, bridge and tunnel maintenance can be carried out.
The invention sets up a periodic updating mechanism of the Q learning model, and makes the decision more scientific and reasonable through continuous data acquisition and energization.
The conception, the specific structure and the technical effects of the present invention will be further described with reference to the accompanying drawings to fully understand the objects, the features and the effects of the present invention.
Drawings
FIG. 1 shows a flow chart of an embodiment of the present invention.
FIG. 2 is a diagram illustrating relationships between variables in Q learning model training according to an embodiment of the present invention.
Detailed Description
Examples
As shown in fig. 1, a Q-learning-based autonomous decision-making method for maintaining roads, bridges and tunnels; the method comprises the following steps:
step 1, establishing an index system for evaluating the health state of a road, bridge and tunnel;
step 2, evaluating the health state of the road, bridge and tunnel according to an index system, and recording an index vector at the time of t as Xt(ii) a Wherein, discretizing continuous index vectors;
step 3, collecting health state data { X. } of the road, bridge and tunnel, recording maintenance decisions at corresponding moments and cost y. generated by the maintenance decisions, and forming a historical data set of the health state and the maintenance cost of the road, bridge and tunnel; if the maintenance is not carried out at the moment t, the historical maintenance cost y at the moment t is concentrated in the historical data of the health state and the maintenance costt=0;
Step 4, judging whether a Q learning model exists or not, and if not, entering step 5; if yes, further judging whether to periodically update the Q learning model; if the Q learning model needs to be updated, entering a step 5, otherwise, entering a step 6;
step 5, retraining the Q learning model based on the historical data set of the health state and maintenance cost of the road, bridge and tunnel;
step 6, utilizing a Q learning model according to the health state index XtObtaining maintenance decision at;
Step 7, executing maintenance decision atEntering step 2, reacquiring the health state evaluation X of the road, bridge and tunnel according to the state transitiont+1。
The method comprehensively considers the health state indexes and maintenance cost of the road, the Q learning model is set for periodic updating, the decision is more scientific and reasonable through continuous data acquisition and energization, and the road, bridge and tunnel maintenance decision is realized under the aim of minimum maintenance cost.
As shown in fig. 2, in certain embodiments, step 5 comprises the steps of:
step 5.1, establishing a Q table of the health state indexes of the roads, bridges and tunnels and maintenance decisions;
step 5.2, randomly selecting the health state X of the road, the bridge and the tunnel0Starting a new round of training;
step 5.3, for any health State XiT, T being a specified upper decision period limit, the decision action a being made using an epsilon-greedy policyiT, T is the specified upper decision period limit;
step 5.4, according to decision action aiTo obtain a new health state Xi+1And the resulting maintenance cost yi(ii) a To minimize the maintenance cost spent in a given decision period, the reward for this decision is recorded as r (X)i,ai)=-yi;
And 5.5, updating the Q value, specifically as follows:
Q(Xi,ai)←(1-a)Q(Xi,ai)+a(r(Xi,ai)+γMax{Q(Xi+1,ai)});
wherein a is a learning rate, and a belongs to [0,1 ];
γ is the reward discount factor, and γ ═ 0, 1;
step 5.6, when the training number in the round does not exceed the upper limit of the decision period, i.e. i is less than or equal to T, the state is transferred, i.e. Xi←Xi+1Returning to the step 5.3; otherwise, returning to the step 5.2, starting a new round of training until the Q table is converged, and ending the training.
In some embodiments, in step 5.3, decision action aiIncluding no maintenance, daily maintenance, minor repair, intermediate repair, major repair and reconstruction and extension.
The foregoing detailed description of the preferred embodiments of the invention has been presented. It should be understood that numerous modifications and variations could be devised by those skilled in the art in light of the present teachings without departing from the inventive concepts. Therefore, the technical solutions available to those skilled in the art through logic analysis, reasoning and limited experiments based on the prior art according to the concept of the present invention should be within the scope of protection defined by the claims.
Claims (3)
1. A bridge and tunnel maintenance autonomous decision method based on Q learning; the method comprises the following steps:
step 1, establishing an index system for evaluating the health state of a road, bridge and tunnel;
step 2, evaluating the health state of the road, bridge and tunnel according to an index system, and recording an index vector at the time of t as Xt(ii) a Wherein the continuous index vector is discretized;
step 3, collecting health state data { X. } of the road, bridge and tunnel, recording maintenance decisions at corresponding moments and cost y. generated by the maintenance decisions, and forming a historical data set of the health state and the maintenance cost of the road, bridge and tunnel; if the maintenance is not carried out at the moment t, the historical maintenance cost y at the moment t is concentrated in the historical data of the health state and the maintenance costt=0;
Step 4, judging whether a Q learning model exists or not, and if not, entering step 5; if yes, further judging whether the Q learning model is periodically updated; if the Q learning model needs to be updated, entering a step 5, otherwise, entering a step 6;
step 5, retraining the Q learning model based on the historical data set of the health state and maintenance cost of the road, bridge and tunnel;
step 6, utilizing the Q learning model according to the health state index XtObtaining maintenance decision at;
Step 7, executing the maintenance decision atEntering step 2, reacquiring the health state evaluation X of the road, bridge and tunnel according to the state transitiont+1。
2. The method for autonomously deciding the maintenance of the road, bridge and tunnel based on the Q learning as claimed in claim 1, wherein the step 5 comprises the following steps:
step 5.1, establishing a Q table of the health state indexes of the roads, bridges and tunnels and maintenance decisions;
step 5.2, randomly selecting the health state X of the road, the bridge and the tunnel0Start to newTraining in a round;
step 5.3, for any of said health states XiT, T being a specified upper decision period limit, the decision action a being made using an epsilon-greedy policyiT, T is the specified upper decision period limit;
step 5.4, according to the decision action aiTo obtain a new health state Xi+1And the resulting maintenance cost yi(ii) a To minimize the maintenance cost spent in a given decision period, the reward for this decision is recorded as r (X)i,ai)=-yi;
And 5.5, updating the Q value, specifically as follows:
Q(Xi,ai)←(1-a)Q(Xi,ai)+a(r(Xi,ai)+γMax{Q(Xi+1,ai)});
wherein a is a learning rate, and a belongs to [0,1 ];
γ is the reward discount factor, and γ ═ 0, 1;
step 5.6, when the training number in the round does not exceed the upper limit of the decision period, i.e. i is less than or equal to T, the state is transferred, i.e. Xi←Xi+1Returning to the step 5.3; otherwise, returning to the step 5.2, starting a new round of training until the Q table is converged, and ending the training.
3. The Q-learning based road, bridge and tunnel maintenance autonomous decision method according to claim 2, characterized in that in the step 5.3, the decision action aiIncluding no maintenance, daily maintenance, minor repair, intermediate repair, major repair and reconstruction and extension.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110141634.9A CN112862295B (en) | 2021-02-02 | 2021-02-02 | Bridge and tunnel maintenance autonomous decision-making method based on Q learning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110141634.9A CN112862295B (en) | 2021-02-02 | 2021-02-02 | Bridge and tunnel maintenance autonomous decision-making method based on Q learning |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112862295A true CN112862295A (en) | 2021-05-28 |
CN112862295B CN112862295B (en) | 2022-06-24 |
Family
ID=75986059
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110141634.9A Active CN112862295B (en) | 2021-02-02 | 2021-02-02 | Bridge and tunnel maintenance autonomous decision-making method based on Q learning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112862295B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116401525A (en) * | 2023-02-23 | 2023-07-07 | 兰州工业学院 | Bridge tunneling prediction maintenance method and system based on intelligent induction |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101466111A (en) * | 2009-01-13 | 2009-06-24 | 中国人民解放军理工大学通信工程学院 | Dynamic spectrum access method based on policy planning constrain Q study |
CN103327556A (en) * | 2013-07-04 | 2013-09-25 | 中国人民解放军理工大学通信工程学院 | Dynamic network selection method for optimizing quality of experience (QoE) of user in heterogeneous wireless network |
CN107153928A (en) * | 2017-06-28 | 2017-09-12 | 江苏智通交通科技有限公司 | Visual highway maintenance decision system |
CN107563669A (en) * | 2017-09-24 | 2018-01-09 | 武汉武大卓越科技有限责任公司 | A kind of highway maintenance method of decision analysis based on learning model |
CN109063870A (en) * | 2018-07-24 | 2018-12-21 | 海南大学 | Composite services policy optimization method and system based on Q study |
CN110084539A (en) * | 2018-11-30 | 2019-08-02 | 武汉大学 | Irrigation decision learning method, device, server and storage medium |
CN110213776A (en) * | 2019-05-27 | 2019-09-06 | 南京邮电大学 | A kind of WiFi discharging method based on Q study and multiple attribute decision making (MADM) |
CN110298768A (en) * | 2019-07-11 | 2019-10-01 | 成都软易达信息技术有限公司 | A kind of road and bridge maintenance aid decision-making system and maintenance process based on BIM and GIS |
EP3629105A1 (en) * | 2018-09-27 | 2020-04-01 | Bayerische Motoren Werke Aktiengesellschaft | High-level decision making for safe and reasonable autonomous lane changing using reinforcement learning |
CN112052071A (en) * | 2020-09-08 | 2020-12-08 | 福州大学 | Cloud software service resource allocation method combining reinforcement learning and machine learning |
-
2021
- 2021-02-02 CN CN202110141634.9A patent/CN112862295B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101466111A (en) * | 2009-01-13 | 2009-06-24 | 中国人民解放军理工大学通信工程学院 | Dynamic spectrum access method based on policy planning constrain Q study |
CN103327556A (en) * | 2013-07-04 | 2013-09-25 | 中国人民解放军理工大学通信工程学院 | Dynamic network selection method for optimizing quality of experience (QoE) of user in heterogeneous wireless network |
CN107153928A (en) * | 2017-06-28 | 2017-09-12 | 江苏智通交通科技有限公司 | Visual highway maintenance decision system |
CN107563669A (en) * | 2017-09-24 | 2018-01-09 | 武汉武大卓越科技有限责任公司 | A kind of highway maintenance method of decision analysis based on learning model |
CN109063870A (en) * | 2018-07-24 | 2018-12-21 | 海南大学 | Composite services policy optimization method and system based on Q study |
EP3629105A1 (en) * | 2018-09-27 | 2020-04-01 | Bayerische Motoren Werke Aktiengesellschaft | High-level decision making for safe and reasonable autonomous lane changing using reinforcement learning |
CN110084539A (en) * | 2018-11-30 | 2019-08-02 | 武汉大学 | Irrigation decision learning method, device, server and storage medium |
CN110213776A (en) * | 2019-05-27 | 2019-09-06 | 南京邮电大学 | A kind of WiFi discharging method based on Q study and multiple attribute decision making (MADM) |
CN110298768A (en) * | 2019-07-11 | 2019-10-01 | 成都软易达信息技术有限公司 | A kind of road and bridge maintenance aid decision-making system and maintenance process based on BIM and GIS |
CN112052071A (en) * | 2020-09-08 | 2020-12-08 | 福州大学 | Cloud software service resource allocation method combining reinforcement learning and machine learning |
Non-Patent Citations (1)
Title |
---|
周戎: ""基于Q学习的RoboCup多智能体决策优化"", 《中国优秀博硕士学位论文全文数据库(硕士) 信息科技辑》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116401525A (en) * | 2023-02-23 | 2023-07-07 | 兰州工业学院 | Bridge tunneling prediction maintenance method and system based on intelligent induction |
CN116401525B (en) * | 2023-02-23 | 2023-09-29 | 兰州工业学院 | Bridge tunneling prediction maintenance method and system based on intelligent induction |
Also Published As
Publication number | Publication date |
---|---|
CN112862295B (en) | 2022-06-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Zang et al. | Metalight: Value-based meta-reinforcement learning for traffic signal control | |
Liang et al. | A deep reinforcement learning network for traffic light cycle control | |
CN111415048B (en) | Vehicle path planning method based on reinforcement learning | |
Xiong et al. | Learning traffic signal control from demonstrations | |
Miyamoto et al. | Development of a bridge management system for existing bridges | |
CN110415516A (en) | Urban traffic flow prediction technique and medium based on figure convolutional neural networks | |
Wang et al. | Improved particle swarm optimization to minimize periodic preventive maintenance cost for series-parallel systems | |
Gan et al. | Optimal pricing for improving efficiency of taxi systems | |
WO2021051930A1 (en) | Signal adjustment method and apparatus based on action prediction model, and computer device | |
CN112862295B (en) | Bridge and tunnel maintenance autonomous decision-making method based on Q learning | |
Khmeleva et al. | Fuzzy-logic controlled genetic algorithm for the rail-freight crew-scheduling problem | |
CN106781461A (en) | A kind of freeway net operation situation deduces thermal starting technology online | |
CN117408672A (en) | Intelligent expressway maintenance system | |
Tsai | Dynamic grey platform for efficient forecasting management | |
CN110705756B (en) | Electric power energy consumption optimization control method based on input convex neural network | |
CN114648178B (en) | Operation and maintenance strategy optimization method of electric energy metering device based on DDPG algorithm | |
CN112927522B (en) | Internet of things equipment-based reinforcement learning variable-duration signal lamp control method | |
Ming et al. | Constrained double deep Q-learning network for EVs charging scheduling with renewable energy | |
CN104102955A (en) | Electric power circuit planning method for selecting differential evolution algorithm on the basis of abstract convexity estimation | |
CN114186799A (en) | Enterprise valuation method and system based on heterogeneous graph neural network | |
Kacprzyk et al. | Involving objective and subjective aspects in multistage decision making and control under fuzziness: dynamic programming and neural networks | |
CN113627533A (en) | Power equipment maintenance decision generation method based on reinforcement learning | |
Liu et al. | Optimal Replacement Policy for Fuzzy Multi-State Element. | |
Takakuwa et al. | Autonomous Reusing Policy Selection Using Spreading Activation Model in Deep Reinforcement Learning | |
Siddique et al. | Fairness in Preference-based Reinforcement Learning |
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 |