CN112865303A - Self-sensing and self-diagnosing intelligent self-healing method for ship regional power distribution power system - Google Patents
Self-sensing and self-diagnosing intelligent self-healing method for ship regional power distribution power system Download PDFInfo
- Publication number
- CN112865303A CN112865303A CN202110011568.3A CN202110011568A CN112865303A CN 112865303 A CN112865303 A CN 112865303A CN 202110011568 A CN202110011568 A CN 202110011568A CN 112865303 A CN112865303 A CN 112865303A
- Authority
- CN
- China
- Prior art keywords
- self
- ship
- healing
- unit
- power system
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 60
- 238000004092 self-diagnosis Methods 0.000 claims abstract description 21
- 230000008569 process Effects 0.000 claims abstract description 18
- 238000012545 processing Methods 0.000 claims abstract description 13
- 230000008520 organization Effects 0.000 claims abstract description 10
- 238000013178 mathematical model Methods 0.000 claims abstract description 6
- 238000011084 recovery Methods 0.000 claims description 26
- 230000002068 genetic effect Effects 0.000 claims description 21
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000003745 diagnosis Methods 0.000 claims description 10
- 108090000623 proteins and genes Proteins 0.000 claims description 10
- 238000010248 power generation Methods 0.000 claims description 9
- 230000003044 adaptive effect Effects 0.000 claims description 7
- 238000000137 annealing Methods 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims description 6
- 238000011156 evaluation Methods 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 claims description 4
- 230000008030 elimination Effects 0.000 claims description 4
- 238000003379 elimination reaction Methods 0.000 claims description 4
- 238000002922 simulated annealing Methods 0.000 claims description 4
- 210000000349 chromosome Anatomy 0.000 claims description 3
- 238000001514 detection method Methods 0.000 claims description 3
- 230000035772 mutation Effects 0.000 claims description 3
- 238000012805 post-processing Methods 0.000 claims description 3
- 230000002265 prevention Effects 0.000 claims description 3
- 230000008439 repair process Effects 0.000 claims description 3
- 238000012502 risk assessment Methods 0.000 claims description 3
- 230000001629 suppression Effects 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 abstract description 4
- 238000011160 research Methods 0.000 abstract description 4
- 238000011217 control strategy Methods 0.000 abstract description 3
- 230000007123 defense Effects 0.000 abstract 1
- 230000006870 function Effects 0.000 description 7
- 230000008901 benefit Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000002955 isolation Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000009402 cross-breeding Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000036039 immunity Effects 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000002028 premature Effects 0.000 description 1
- 230000001681 protective effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 235000008113 selfheal Nutrition 0.000 description 1
- 230000026676 system process Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00032—Systems characterised by the controlled or operated power network elements or equipment, the power network elements or equipment not otherwise provided for
- H02J13/00036—Systems characterised by the controlled or operated power network elements or equipment, the power network elements or equipment not otherwise provided for the elements or equipment being or involving switches, relays or circuit breakers
- H02J13/0004—Systems characterised by the controlled or operated power network elements or equipment, the power network elements or equipment not otherwise provided for the elements or equipment being or involving switches, relays or circuit breakers involved in a protection system
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02H—EMERGENCY PROTECTIVE CIRCUIT ARRANGEMENTS
- H02H3/00—Emergency protective circuit arrangements for automatic disconnection directly responsive to an undesired change from normal electric working condition with or without subsequent reconnection ; integrated protection
- H02H3/02—Details
- H02H3/06—Details with automatic reconnection
- H02H3/066—Reconnection being a consequence of eliminating the fault which caused disconnection
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a self-sensing and diagnosing intelligent self-healing method for a ship regional distribution power system, which researches the active control and fault defense of intelligent self-healing of faults of the ship regional distribution power system, provides a self-healing control technology of hierarchical and partitioned coordination, implements corresponding coordinated self-healing in different regions and different levels of ships aiming at different functional regions, adopts a supervisory control strategy in computer control, adopts an intelligent self-healing organization as an upper computer to sample various operating parameters in ship operation in real time, carries out complex data processing according to a mathematical model describing the ship operation process, finds out a fault optimal self-healing scheme in the ship operation process, inputs the fault optimal self-healing scheme to a self-healing task allocation unit to carry out task allocation control, improves the control capability of each region on the faults, and realizes self-sensing, self-diagnosis, self-decision and self-healing of the ship power system, the purposes of safe, stable, high-quality and efficient operation of the ship regional power distribution power system are achieved.
Description
Technical Field
The invention relates to the technical field of ship regional distribution power systems, in particular to a self-sensing and self-diagnosing intelligent self-healing method for a ship regional distribution power system.
Background
The navigation environment of a ship in the ocean is severe, various faults can occur in a distribution power system of a ship area during working, and common faults of a ship comprehensive power system include large-load disturbance, short circuit, open circuit and the like. When a ship power system fails or suffers weapon attack, the system needs to be quickly reconstructed, and a decision scheme is provided for recovering the power supply of important loads to the maximum extent, so that the reliability and the vitality of the power supply are ensured. Unlike terrestrial power systems, recovery of ship power systems particularly emphasizes real-time and global optimality. With the emergence of electric propulsion modes and high-energy weapons, the capacity of a ship electric system rises in a geometric curve, the network topology structure is more and more complex, and some simple fault recovery algorithms are not applicable any more. In order to reduce the occurrence of personnel risks and property loss on ships caused by power supply disturbance, the safe and stable operation of the ships must be ensured constantly, so that whether the ships break down or not can be accurately judged and the faults are cut off in time by the ship regional power distribution power system, and therefore the fault sensing, diagnosis and self-healing of the ship regional power distribution power system are important.
The earliest intelligent control methods appeared to be fuzzy mathematics, artificial neural networks and expert system methods; from the automatic control perspective of a ship power system, at present, domestic and foreign researches on a control method of a generator set actually mainly adopt traditional PID control, and intelligent control, robust control, optimal control, nonlinear control and other methods are focused on the researches. From the development direction of technology, intelligent control and a method for combining the intelligent control with various control methods are the development direction of a ship power system. The genetic algorithm has strong parallel computing and global searching capabilities, is suitable for solving various complex problems, plays an important role in nonlinear optimization problems due to the unique advantages of the genetic algorithm, and is applied to many fields.
The control method which is most widely applied in the design of the traditional control system is PID control, but the PID control has poor optimizing effect on a complex nonlinear system of a ship power system, and the operation quality of the ship power system is difficult to be improved to a new operation level only by applying the classical PID control. In an intelligent control method, as a universally applicable random large-range search strategy, the existing genetic algorithm has some defects, the individuals are selected according to fitness, the selection of each individual is not connected, so that a certain probability distribution is not formed, the algorithm search range is large, the convergence speed is low, the algorithm cannot be absolutely guaranteed not to be trapped in a local extreme value, premature convergence often occurs, a reasonable criterion for judging whether the current solution reaches the optimal solution is not provided, the system information and the like cannot be well utilized in the evolution process, and therefore the genetic algorithm cannot be guaranteed to converge to the globally optimal solution with the maximum probability. In addition, the method of the expert system recovers the power supply of the fault area, a huge expert knowledge base needs to be established when the expert system processes and recovers control, and for a complex system, the whole acquisition of knowledge is very difficult.
Disclosure of Invention
The invention aims to provide a self-sensing and self-diagnosing intelligent self-healing method for a ship regional distribution power system, which is used for improving the immunity and reliability of the ship regional distribution power system to faults, coping with the conditions of severe ship swinging and large hydrodynamic load change of a propulsion propeller in severe weather, helping the power system of the ship main power bear the impact of huge uncertain load, realizing the high-reliability and high-quality power supply to ships, solving the problem that a genetic algorithm falls into local optimal search, searching an optimal self-healing control scheme of the ships after the faults, realizing the intelligent self-healing of the ship self-sensing, diagnosis, decision and recovery, achieving the purposes of safe, stable, high-quality and high-efficiency operation of the ship regional distribution power system and ensuring the safe and reliable operation of the ship main propulsion power.
In order to achieve the above object, the present invention provides a self-sensing and self-diagnosing intelligent self-healing method for a ship regional distribution power system, which adopts a strategy of combining an upper computer with a direct digital control system to supervise and control the ship regional distribution power system, and comprises:
the intelligent self-healing organization unit is used as an upper computer in the supervisory control system, performs complex data calculation according to the ship operation information parameters and the fault information parameters and a mathematical model describing the ship operation process, and performs task allocation through the intelligent self-healing task allocation unit;
the intelligent self-healing task allocation unit is used as a direct digital control system in the supervisory control system, selectively allocates instructions of the upper computer to the unit for implementing the intelligent supervisory control algorithm, and controls the closed-loop operation process of the self-sensing unit, the self-diagnosis unit, the self-decision unit and the self-recovery unit;
the self-sensing unit carries out online detection and real-time evaluation on the ship regional power distribution power system, carries out data acquisition and analysis on a control object in the ship regional power distribution power system, and feeds back the acquired ship operation electrical parameters to the intelligent self-healing task allocation unit so as to make task work instructions for the self-diagnosis unit;
the self-diagnosis unit carries out fault diagnosis by using supervisory control identification of the upper computer, carries out vulnerability assessment on a ship power grid according to electrical operation parameters input by the self-sensing unit, carries out fault risk assessment on a controlled area with possible faults of a ship according to instructions of the intelligent self-healing task allocation unit after finding out the area, divides the next possible operation state of the area, extracts the operation state characteristics of the area, and feeds back the operation state characteristics to the intelligent self-healing task allocation unit so as to make task work instructions for the self-decision unit;
the self-decision unit selects a processing mode according to the ship running state transmitted by the self-diagnosis unit, if the ship running state is a state in which a fault occurs, an optimal self-healing scheme of a ship regional power distribution power system is searched, and the optimal self-healing scheme is fed back to the intelligent self-healing task allocation unit so as to make a task work instruction for the self-recovery unit;
and the self-recovery unit recovers the fault according to the fault processing information in the optimal self-recovery scheme of the self-decision unit, and preferentially ensures that the power supply of the important propulsion load is recovered.
Optionally, if the ship operation state is a normal state, the self-decision unit selectively and purposefully performs optimization control on the operation state of the ship power grid, so as to improve the operation performance of the ship power grid.
Optionally, if the ship operation state is poor, the self-decision unit enters the warning state, so that fault discovery, diagnosis and elimination mainly based on prevention and control are achieved, possible faults are early warned to avoid accidents, the stability margin of the ship power grid and the disturbance resistance capability are improved, and passive post-processing is changed into active accident suppression.
Optionally, the self-recovery unit determines that one or more of system reconfiguration, degraded operation, fault compensation and fault switching modes are adopted for the fault in the next step, and preferentially ensures that the power supply of the important propulsion load is recovered, and under the condition that a serious accident that the ship loses power is avoided, various operations and execution sequences thereof are rapidly arranged according to instructions, including resetting setting values of various protection devices, tripping and closing of switches, so that the reconstruction of the network is realized, the protection for a new network is started after the reconstruction, and the fault is recovered to a normal operation state through a self-healing repair function.
Optionally, the control objects in the ship region power distribution power system include a power generation unit, an electric propulsion unit and other load units.
Optionally, the ship regional power distribution power system is divided into a plurality of power supply regions according to the unified distribution of the power consumption of the load and the importance degree of the ship.
Optionally, in the area distribution network structure, the important loads are directly connected to the area distribution board, and the general loads are supplied with power by the distribution boxes in each area, so that the load classification is realized.
Optionally, the self-decision unit generates an optimal self-healing scheme of the ship region power distribution power system by using a simulated annealing multi-population genetic algorithm, and the method specifically includes the following steps:
(1) carrying out binary coding on paths which can recover power supply in a large group of ship power-off areas to form gene chromosomes;
(2) initializing a population, and randomly generating N initial individuals;
(3) the system calculation is carried out, wherein gene values of individuals are mapped into a network topological structure of the system, and adaptive values of the individuals are calculated;
(4) preferentially ensuring the power supply of important loads to perform individual selection and elimination according to the fitness function;
(5) selecting excellent individuals to perform crossover and vice versa to generate a new population;
(6) judging a termination condition, if the evolution algebra reaches a maximum set value, outputting an optimal individual, and terminating the calculation; otherwise, turning to the following steps to start iteration;
(7) group adjustment, if the optimal adaptive value is kept unchanged in a certain evolutionary algebra, only the optimal individual is reserved, and other individuals are randomly generated;
(8) annealing selection, namely generating the optimal individuals in the next generation with probability p;
(9) and performing crossover and mutation operations on individuals.
Compared with the prior art, the invention has the following advantages:
the invention is suitable for the safe and reliable control requirements of the ship electric power system, and implements control on the diesel generating set and the electric propulsion motor system by using an upper computer supervision control method, thereby improving the reliability. The system structure and the control method provided by the invention fully consider the situations that the marine ship moves as required, is isolated and free of aid and has limited resources on the ship, and can transfer all resources of the ship and the power system thereof to implement intelligent self-healing under the control of an intelligent method and quickly recover power supply when the power system has a fault in order to ensure the safe navigation of the ship and ensure that the main power of the ship does not lose power from the aspect of power generation by controlling the generator set in the aspect of power generation, so that the power supply safety of the power system is greatly improved. In addition, data analysis is realized through an intelligent algorithm, the optimal operation mode of the generator can be selected under different working conditions, and how to distribute power more optimally under the condition of faults can be realized, so that the working efficiency of the generator is improved, the safety and reliability of a ship power system are improved, and the self-healing recovery capability for the faults is realized. The final aim of the intelligent self-healing method of the ship regional power distribution power system is to ensure the safe and reliable operation of the main propulsion power of the ship, and the method plays an important role in the safe navigation of the ship.
Drawings
Fig. 1 is a block diagram of a self-healing method for a self-sensing and self-diagnosing ship regional distribution power system provided by the present invention;
fig. 2 is a flow chart of an intelligent self-healing process of an improved genetic algorithm.
Detailed Description
The scheme provided by the invention is further described in detail with reference to the attached figures 1-2 and the specific embodiment. The advantages and features of the present invention will become more apparent from the following description. It is to be noted that the drawings are in a very simplified form and are all used in a non-precise scale for the purpose of facilitating and distinctly aiding in the description of the embodiments of the present invention. To make the objects, features and advantages of the present invention comprehensible, reference is made to the accompanying drawings. It should be understood that the structures, ratios, sizes, and the like shown in the drawings and described in the specification are only used for matching with the disclosure of the specification, so as to be understood and read by those skilled in the art, and are not used to limit the implementation conditions of the present invention, so that the present invention has no technical significance, and any structural modification, ratio relationship change or size adjustment should still fall within the scope of the present invention without affecting the efficacy and the achievable purpose of the present invention.
Because various technologies covered by self-healing control are organically integrated and sufficient research and discussion is lacked in the realization of the self-healing function of the ship, the invention provides a self-decision intelligent self-healing method implemented on the basis of a regional power distribution system, which is a closed loop system for self-perception diagnosis decision recovery. The invention is used for improving the safety toughness and reliability of the distribution power system in the ship area, can self-heal under intelligent self-healing control when the power system fails, quickly recovers power supply, and greatly improves the power supply safety of the ship power system. A supervisory control method based on an upper computer direct digital control system is adopted for a generator set system, an electric propulsion system and the like of an electric propulsion ship. The improved genetic algorithm adopts a method with optimal individual retention, and the population is updated when the optimal value is kept constant for a certain algebra, so that the local optimal solution can be effectively skipped. The self-sensing, self-diagnosis, self-decision and self-recovery capabilities of the ship power system are realized through the intelligent self-healing control system and method of the regional power distribution system.
The working principle of the present invention will be described with reference to the accompanying drawings.
A plurality of power generation units in the ship region power distribution power system can independently or jointly supply power to each functional region, and when part of the power generation units are damaged, the rest power generation units can maintain power supply. The attached figure 1 shows that ship loads are divided into different areas and different levels according to the self-healing control technology of hierarchical and partition coordination, an intelligent self-healing control system implements corresponding coordination self-healing in different areas and different load levels of a ship, and after important electric propulsion loads are recovered preferentially, power supply of loads such as cabin living areas is met.
In addition, the ship self-healing control adopts a strategy of combining an upper computer with a direct digital control system to monitor and control a ship regional power distribution power system, a ship intelligent self-healing organization is used as the upper computer (SSC) to continuously monitor the whole operation process, various fault information parameters and other parameters in the ship operation are sampled, and complex data processing is rapidly carried out according to a mathematical model describing the ship operation process. Particularly in a self-decision unit, in order to solve the problems that the genetic algorithm is easy to fall into local optimization and the later convergence is slow, the convergence of the genetic algorithm is improved by dissolving simulated annealing in the genetic algorithm, and a multi-population genetic algorithm is adopted and an annealing mechanism is added. The simulated annealing multi-population genetic algorithm has larger early search space, high annealing temperature and large variation range of fitness value, so that the algorithm can not fall into the local optimal condition. The search space is rapidly reduced along with the continuous reduction of the temperature, and the local search capability of the genetic algorithm can be exerted in the later period of the algorithm, so that the final result is ensured to be converged to the interval of the optimal solution.
As shown in fig. 1, the overall framework of the self-sensing and self-diagnosing intelligent self-healing method for a ship regional distribution power system provided by the invention comprises:
the intelligent self-healing organization unit 01 serves as an upper computer (SCC) in the supervisory control system, performs complex data calculation according to ship operation information parameters and fault information parameters and a mathematical model describing a ship operation process, finds out a fault optimal self-healing scheme of the ship operation process, and inputs the fault optimal self-healing scheme to the intelligent self-healing task allocation unit 02. The output value of the intelligent self-healing organization unit 01 does not directly control the whole closed-loop working unit, but automatically changes the given value of a microcomputer in a direct digital control system, and the task of the intelligent self-healing organization unit is focused on the correction and implementation of the control law.
The intelligent self-healing task allocation unit 02 is used as a direct digital control system in a supervisory control system, plays a role of controlling a task allocator, selectively allocates instructions of an upper computer, is a unit for implementing an intelligent supervisory control algorithm, directly controls the closed-loop operation process of the self-sensing unit 06, the self-diagnosis unit 07, the self-decision unit 08 and the self-recovery unit 09 through analog output, can realize multi-loop control, and can realize a complex control rule as long as a program is changed.
The self-sensing unit 06 performs online detection and real-time evaluation on the ship region distribution power system 05, performs data acquisition and analysis on control objects in the ship region distribution power system 05, such as a plurality of power generation units, a propulsion motor, and input/output of a sensor and a transmitter, and feeds back acquired ship operation electrical parameters to the intelligent self-healing task allocation unit 02 so as to make a task work instruction to the self-diagnosis unit 07.
The self-diagnosis unit 07 carries out fault diagnosis by using supervisory control and identification of an upper computer, carries out vulnerability assessment on a ship power grid according to electrical operation parameters input by the self-perception unit 06, carries out fault risk assessment on a controlled area with possible faults of a ship after finding the area, and divides a next possible operation state of the area according to instructions of the intelligent self-healing task allocation unit 02, thereby diagnosing the nature and the occurrence position of the possible faults, extracting the operation state characteristics of the area, feeding back the operation state information to the task allocation unit as well, and inputting the operation state information to the self-decision unit.
The power quality index input unit 03 inputs the set ship operation electrical parameters, such as voltage, current, power, and the like, to the self-decision unit 08 together with the state characteristics acquired by the self-diagnosis unit 07. The self-decision unit 08 receives the work instruction sent by the intelligent self-healing task allocation unit 02, and selects a processing mode according to the ship running state transmitted by the self-diagnosis unit 07. Under the normal operation state, the operation state of the ship power grid is selectively and purposefully optimized and controlled, and the operation performance of the ship power grid is improved. When the operation state is bad, the operation state enters an alert state, fault discovery, diagnosis and elimination mainly based on prevention and control are achieved, possible faults are early warned to avoid accidents, the stability margin of a ship power grid and the disturbance resistance capability are improved, and passive post-processing is changed into active accident suppression. When a fault occurs, the self-decision unit 08 searches for an optimal self-healing scheme of the ship regional power distribution power system 05 according to an improved genetic algorithm, outputs fault processing information in the scheme to the self-healing unit 09, and feeds the fault processing information back to the intelligent self-healing task allocation unit 02.
If a fault occurs during the operation of the ship, at the moment, a plurality of sensors near the generator send signals, the self-recovery unit 09 determines the processing mode of the fault by combining the self-healing control scheme of the self-decision unit 08 according to the information such as the fault type, the level, the area range and the like provided by the self-diagnosis unit 07, outputs an instruction to an execution mechanism, and determines the next mode of one of system reconstruction, degraded operation, fault compensation and fault switching. The method is characterized in that the power supply of important propulsion loads is guaranteed to be restored preferentially, under the condition that severe accidents that ships lose power are avoided, various operations and execution sequences of the operations are arranged rapidly according to instructions, the operations comprise resetting of setting values of protective devices such as various relays and current limiting devices, tripping and closing of switches and the like, therefore, reconstruction of a network is achieved, protection of a new network is started after reconstruction, and the operation is restored to a normal operation state from a fault through a self-healing repair function.
As shown in fig. 1, a controlled object in the ship-area distribution power system 05 is mainly composed of a power generation unit, a power propulsion unit, and other load units. The power generating unit, which is an electric energy generating unit of the ship regional distribution power system 05, forms the most important component of the system together with the asynchronous motor driving the propeller to move. The ship regional power distribution power system 05 is divided into a plurality of power supply regions by unified distribution according to the power consumption of the load and the importance degree of the ship. The ship regional distribution power system 05 to be controlled has four generators, and supplies power to the ship regional distribution power system 05. The two propulsion motors and the propeller are used for propelling the ship to sail. The whole ship regional power distribution power system 05 is divided into four isolated power utilization regions, so that the stability and fault isolation capability of the ship regional power distribution power system 05 are enhanced.
The invention provides a self-sensing and self-diagnosing intelligent self-healing method for a ship regional power distribution power system, which comprises the following working procedures: the intelligent self-healing organization unit is used as a host computer to simulate the function of a controller in an automatic control system by adopting the concept of a hierarchical control system of the host computer and a direct digital control system in computer control, complex data calculation is carried out according to fault information parameters and ship operation information parameters and a mathematical model describing the ship operation process, the optimal self-healing scheme of the faults in the ship operation process is found out and input to the intelligent task allocation unit.
In the closed-loop operation of the present invention, a forward path and a feedback path are included. The forward path comprises a direct digital controller, namely an intelligent self-healing task allocation unit, a self-sensing unit, a self-decision unit, a self-recovery unit and a controlled object. After receiving a set value instruction sent by the intelligent self-healing organization unit, an intelligent self-healing task allocation unit (DDC) allocates the whole self-healing task, input parameters and feedback parameters are set according to the set value, an automatic decision unit carries out optimization self-healing scheme through an improved genetic algorithm, and a self-recovery unit carries out self-healing recovery on faults, so that a generator set unit in a whole ship regional power distribution power system is controlled. The feedback loop is mainly used for carrying out self-diagnosis on the output value of the system and mainly comprises a self-diagnosis unit, the self-diagnosis unit is used for comparing a series of electrical parameters to find out the weak points of possible faults in the ship system, distinguishing the running state and feeding corresponding parameter indexes back to the intelligent self-healing task allocation unit and the self-decision unit.
According to the self-healing control method, the ship regional power distribution power system is based on the ship regional power distribution power system, a ship generator set and a propulsion motor are used as main control objects, and an upper computer supervision control strategy based on an improved genetic algorithm is used for calculating the optimal self-healing scheme of the system.
The self-healing method of the regional power distribution power system aims at different functional regions, and the intelligent self-healing control system implements corresponding coordinated self-healing in different regions and different levels of a ship. In the regional distribution network structure, important loads are directly connected with regional distribution boards, and general loads are supplied with power by distribution boxes in each region, so that the grading processing of the loads is realized. The whole ship area intelligent power distribution network self-healing control system is composed of an intelligent self-healing organization unit and a task distribution unit through network communication, is executed by four closed-loop control units and controls the output power of a generator and the rotating speed of a propulsion motor, and the whole system is designed with a master station system and distributed terminal software according to the goal of realizing self-perception, self-diagnosis, self-decision and self-recovery of the intelligent power distribution network.
By adopting a supervisory control strategy, the upper computer continuously monitors the whole ship operation process by using the functions of a controller in a digital direct control system and a computer, samples various parameters (voltage, current, power, pressure, rotating speed and the like) in the ship operation, transmits the parameters to a self-decision unit to calculate the optimal self-healing scheme of the system according to an improved genetic algorithm by controlling an intelligent self-healing task allocation unit, and sends various control commands to achieve the aim of safe, stable, high-quality and efficient operation of a ship regional power distribution power system.
As shown in fig. 2, the flow of the self-decision unit generating the optimal self-healing scheme by using the improved genetic algorithm simulating annealing of multiple groups is as follows:
step 1, a self-sensing unit and a self-diagnosis unit work, online monitoring and real-time evaluation are carried out on a distribution power system of a ship region, data acquisition and analysis are carried out on a controlled object, vulnerability and risk evaluation are carried out, ship state distinguishing is carried out, the property and the occurrence position of possible faults are diagnosed according to operation electrical parameters and fault characteristics, a self-healing scheme is input into a self-decision unit to generate a self-healing scheme, the self-decision unit carries out early warning on the possible faults according to the ship operation state, an improved genetic algorithm is utilized to decide the occurred fault processing mode, and firstly, a chromosome is formed on the possible recovery path binary coding of the ship power loss region;
and 2, in order to avoid the condition of multi-path power supply of the load and shorten the coding length as much as possible, for the load with only one path of power supply, the individual gene bit adopts the codes of the numbers 0 and 1, and for the load with a standby power supply path, the gene bit adopts the codes of the numbers 0, 1 and 2, and in addition, the regional load characteristics of the ship regional power distribution power system can be used as characteristic information when the problem is solved. If a certain gene position is randomly selected, if the gene position is standby power supply, whether all loads under the same power supply feeder can be powered, especially important loads, are considered, and the affected gene position value is adjusted according to the calculation result.
And 3, initializing the ship power supply recovery path population, and randomly generating N initial individuals. All the individuals powered by the loads by adopting the normal paths contain the most optimal individual information, and a heuristic search result can be adopted to generate some individuals by combining the information and the fault parts.
And 4, calculating the individual adaptive value by the system, mapping the gene value of the individual into a network topological structure of the system, and calculating the individual adaptive value by the system according to a node potential method.
Step 5, preferentially ensuring the power supply of the important load to select and eliminate according to the fitness function;
and 6, selecting excellent individuals for cross breeding to generate a new population.
Step 7, judging whether a maximum evolution algebra set value is reached, if the evolution algebra reaches the maximum set value, outputting an optimal individual, and terminating the calculation; otherwise, the process proceeds to the following step to start iteration.
And 8, carrying out local optimal judgment and population adjustment on the evolution, and if the optimal adaptive value is kept unchanged in a certain algebra of the evolution, only keeping the optimal individual and randomly generating other individuals.
And 9, annealing selection, namely generating the optimal individuals in the next generation according to the probability, wherein the optimal individuals contain a lot of information useful for the evolution process, so that the optimal individuals are generated in the next generation according to a certain probability, and the evolution speed can be greatly accelerated.
And step 10, carrying out mutation on the individuals, and selecting the individuals according to a certain probability to carry out local heuristic optimization. If the optimizing result is better than the original individual, the operation is executed, otherwise, the step 4 is executed. Evolution stagnation is avoided, the excellent characteristics of parents are reserved, the population scale is reduced, algorithm convergence is improved, and fault recovery is accelerated.
And 7, when detecting that the evolution algebra reaches the maximum set value in the step 7, executing a step 11, and outputting an optimal self-healing scheme to a self-recovery unit for fault isolation and reconstruction.
While the present invention has been described in detail with reference to the preferred embodiments, it should be understood that the above description should not be taken as limiting the invention. Various modifications and alterations to this invention will become apparent to those skilled in the art upon reading the foregoing description. Accordingly, the scope of the invention should be determined from the following claims.
Claims (8)
1. The utility model provides a regional distribution electric power system intelligence self-healing method of boats and ships of self-perception and diagnosis which characterized in that adopts the strategy of host computer combination direct digital control system to carry out supervisory control to regional distribution electric power system of boats and ships, includes:
the intelligent self-healing organization unit is used as an upper computer in the supervisory control system, performs complex data calculation according to the ship operation information parameters and the fault information parameters and a mathematical model describing the ship operation process, and performs task allocation through the intelligent self-healing task allocation unit;
the intelligent self-healing task allocation unit is used as a direct digital control system in the supervisory control system, selectively allocates instructions of the upper computer to the unit for implementing the intelligent supervisory control algorithm, and controls the closed-loop operation process of the self-sensing unit, the self-diagnosis unit, the self-decision unit and the self-recovery unit;
the self-sensing unit carries out online detection and real-time evaluation on the ship regional power distribution power system, carries out data acquisition and analysis on a control object in the ship regional power distribution power system, and feeds back the acquired ship operation electrical parameters to the intelligent self-healing task allocation unit so as to make task work instructions for the self-diagnosis unit;
the self-diagnosis unit carries out fault diagnosis by using supervisory control identification of the upper computer, carries out vulnerability assessment on a ship power grid according to electrical operation parameters input by the self-sensing unit, carries out fault risk assessment on a controlled area with possible faults of a ship according to instructions of the intelligent self-healing task allocation unit after finding out the area, divides the next possible operation state of the area, extracts the operation state characteristics of the area, and feeds back the operation state characteristics to the intelligent self-healing task allocation unit so as to make task work instructions for the self-decision unit;
the self-decision unit selects a processing mode according to the ship running state transmitted by the self-diagnosis unit, if the ship running state is a state in which a fault occurs, an optimal self-healing scheme of a ship regional power distribution power system is searched, and the optimal self-healing scheme is fed back to the intelligent self-healing task allocation unit so as to make a task work instruction for the self-recovery unit;
and the self-recovery unit recovers the fault according to the fault processing information in the optimal self-recovery scheme of the self-decision unit, and preferentially ensures that the power supply of the important propulsion load is recovered.
2. The self-sensing and diagnosing intelligent self-healing method for the ship regional distribution power system according to claim 1, wherein if the ship operation state is a normal state, the self-decision unit selectively and purposefully performs optimization control on the operation state of the ship power grid to improve the operation performance of the ship power grid.
3. The self-sensing and diagnosing intelligent self-healing method for the ship regional distribution power system according to claim 1, wherein if the ship operation state is bad, the self-decision unit enters a warning state to discover, diagnose and eliminate faults mainly based on prevention and control, pre-warns possible faults to avoid accidents, improves the stability margin of the ship power grid and the capability of resisting disturbance, and changes passive post-processing into active suppression of accidents.
4. The self-sensing and self-diagnosing intelligent self-healing method for the ship regional power distribution power system according to claim 1, wherein the self-recovery unit determines to adopt one or more of system reconfiguration, degraded operation, fault compensation and fault switching modes for the fault in the next step, preferentially ensures to recover the power supply of an important propulsion load, and rapidly arranges various operations and execution sequences thereof according to instructions under the condition of avoiding a serious accident that the ship loses power, including resetting setting values of various protection devices, tripping and closing of a switch, so as to realize the reconfiguration of the network, starts protection for a new network after reconfiguration, and recovers from the fault to a normal operation state through a self-healing repair function.
5. The self-aware, self-diagnostic intelligent self-healing method for ship regional distribution power system according to claim 1, wherein the control objects in the ship regional distribution power system include power generation units, electric propulsion units and other load units.
6. The self-sensing and self-diagnosing intelligent self-healing method for the ship regional distribution power system according to claim 5, wherein the ship regional distribution power system is divided into a plurality of power supply regions according to the unified distribution of the load power consumption and the importance degree of the ship.
7. The self-sensing and self-diagnosing intelligent self-healing method for a ship regional distribution power system according to claim 6, wherein in a regional distribution network structure, important loads are directly connected with regional distribution boards, and common loads are supplied by branch boxes in each region, so that the load grading processing is realized.
8. The self-perception and diagnosis ship regional distribution power system intelligent self-healing method according to claim 1, wherein the self-decision unit generates the optimal self-healing scheme of the ship regional distribution power system by using a simulated annealing multi-population genetic algorithm, and the method comprises the following specific steps:
(1) carrying out binary coding on paths which can recover power supply in a large group of ship power-off areas to form gene chromosomes;
(2) initializing a population, and randomly generating N initial individuals;
(3) the system calculation is carried out, wherein gene values of individuals are mapped into a network topological structure of the system, and adaptive values of the individuals are calculated;
(4) preferentially ensuring the power supply of important loads to perform individual selection and elimination according to the fitness function;
(5) selecting excellent individuals to perform crossover and vice versa to generate a new population;
(6) judging a termination condition, if the evolution algebra reaches a maximum set value, outputting an optimal individual, and terminating the calculation; otherwise, turning to the following steps to start iteration;
(7) group adjustment, if the optimal adaptive value is kept unchanged in a certain evolutionary algebra, only the optimal individual is reserved, and other individuals are randomly generated;
(8) annealing selection, namely generating the optimal individuals in the next generation with probability p;
(9) and performing crossover and mutation operations on individuals.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110011568.3A CN112865303A (en) | 2021-01-06 | 2021-01-06 | Self-sensing and self-diagnosing intelligent self-healing method for ship regional power distribution power system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110011568.3A CN112865303A (en) | 2021-01-06 | 2021-01-06 | Self-sensing and self-diagnosing intelligent self-healing method for ship regional power distribution power system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112865303A true CN112865303A (en) | 2021-05-28 |
Family
ID=76004138
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110011568.3A Pending CN112865303A (en) | 2021-01-06 | 2021-01-06 | Self-sensing and self-diagnosing intelligent self-healing method for ship regional power distribution power system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112865303A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112947374A (en) * | 2021-02-09 | 2021-06-11 | 上海海事大学 | Intelligent self-healing control method for electric propulsion of regional distribution ship |
| CN118473098A (en) * | 2024-07-09 | 2024-08-09 | 河南深蓝静行光电科技有限公司 | Intelligent power management module of ship computer |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102645615A (en) * | 2012-04-26 | 2012-08-22 | 中国人民解放军海军工程大学 | Marine electric power system fault diagnosis method based on quantum genetic algorithm |
| CN104578427A (en) * | 2015-01-27 | 2015-04-29 | 国家电网公司 | Fault self-healing method for power distribution network containing microgrid power source |
| CN105514925A (en) * | 2015-12-09 | 2016-04-20 | 国网甘肃省电力公司检修公司 | 750kv substation fault recovery method based on genetic algorithm |
| CN110994597A (en) * | 2019-11-26 | 2020-04-10 | 国电南瑞科技股份有限公司 | Method, system and device for automatically generating self-healing control strategy of power distribution network |
-
2021
- 2021-01-06 CN CN202110011568.3A patent/CN112865303A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102645615A (en) * | 2012-04-26 | 2012-08-22 | 中国人民解放军海军工程大学 | Marine electric power system fault diagnosis method based on quantum genetic algorithm |
| CN104578427A (en) * | 2015-01-27 | 2015-04-29 | 国家电网公司 | Fault self-healing method for power distribution network containing microgrid power source |
| CN105514925A (en) * | 2015-12-09 | 2016-04-20 | 国网甘肃省电力公司检修公司 | 750kv substation fault recovery method based on genetic algorithm |
| CN110994597A (en) * | 2019-11-26 | 2020-04-10 | 国电南瑞科技股份有限公司 | Method, system and device for automatically generating self-healing control strategy of power distribution network |
Non-Patent Citations (1)
| Title |
|---|
| 刘凯;李文佩;程潜善;方华亮;: "基于启发式规则和人工免疫的智能配电网自愈", 武汉大学学报(工学版), no. 02, 1 April 2016 (2016-04-01), pages 218 - 222 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112947374A (en) * | 2021-02-09 | 2021-06-11 | 上海海事大学 | Intelligent self-healing control method for electric propulsion of regional distribution ship |
| CN118473098A (en) * | 2024-07-09 | 2024-08-09 | 河南深蓝静行光电科技有限公司 | Intelligent power management module of ship computer |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112865303A (en) | Self-sensing and self-diagnosing intelligent self-healing method for ship regional power distribution power system | |
| CN110311398B (en) | Connection topology, control system and method of novel energy storage battery system | |
| CN102681442B (en) | Intelligent fault-tolerant control system and control method for zonal power distribution of full-electric boat | |
| CN110994604A (en) | Electric power system transient stability evaluation method based on LSTM-DNN model | |
| Zhang et al. | Deep reinforcement leaming for short-term voltage control by dynamic load shedding in china southem power grid | |
| CN101739025A (en) | Immunity genetic algorithm and DSP failure diagnostic system based thereon | |
| Zhang et al. | Application of simulated annealing genetic algorithm-optimized back propagation (BP) neural network in fault diagnosis | |
| CN110619321B (en) | Charging pile technical condition diagnosis method and system based on deep neural network | |
| CN110350510A (en) | A kind of power distribution network service restoration method considering failure disturbance degree | |
| CN114678860A (en) | Power distribution network protection control method and system based on deep reinforcement learning | |
| CN114169395B (en) | Method for constructing dominant instability mode recognition model of power system and application | |
| CN112327098A (en) | Power distribution network fault section positioning method based on low-voltage distribution network comprehensive monitoring unit | |
| CN112733962A (en) | Intelligent fault diagnosis and reconstruction method for ship regional power distribution power system | |
| CN111917111B (en) | Method, system, equipment and storage medium for online evaluation of distributed photovoltaic power supply acceptance capacity of power distribution network | |
| Wang et al. | Multi-agent and ant colony optimization for ship integrated power system network reconfiguration | |
| CN113945796B (en) | Power distribution network fault positioning method, terminal equipment and storage medium | |
| Liu et al. | Review of grid stability assessment based on AI and a new concept of converter-dominated power system state of stability assessment | |
| CN109449985B (en) | Microgrid control method and system | |
| CN118472964A (en) | Reactive power/voltage control method of power distribution network with self-adaptive topology change | |
| CN201666923U (en) | Device for processing DSP failure diagnosis of electric power system by using immune genetic algorithm | |
| CN117057623A (en) | Comprehensive power grid safety optimization scheduling method, device and storage medium | |
| CN112947374A (en) | Intelligent self-healing control method for electric propulsion of regional distribution ship | |
| CN114298429A (en) | Power distribution network scheme aided decision-making method, system, device and storage medium | |
| CN112865301A (en) | Intelligent immune self-healing method and system for ship regional distribution power system | |
| CN105550495A (en) | Method for evaluating ship navigation increasing resistance level |
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 |