A method for managing component life

Abstract

The invention discloses a component life management method, which relates to the field of electric power industry. The implementation of the invention realizes the supervision of the whole life cycle of the heating surface metal through the calculation of the remaining life; it can remind the operating personnel to strengthen the monitoring of the wall temperature of the heating surface that is easy to overheat and make good combustion adjustments; it can guide the maintenance personnel to focus on and reasonably replace the pipelines during the unit maintenance to ensure the smooth operation of the unit; it solves the problems of uncertainty in load growth, rapidly rising equipment construction costs, construction land difficulties and increasingly stringent environmental protection laws and regulations, so that the unit has a longer service life, saves resources, and the equipment footprint is improved, and the environment is protected to a certain extent; by visualizing and digitally presenting equipment performance and failure probability, it provides data support for equipment maintenance and promotes lean operation management; it realizes that the equipment status is knowable, visible, controllable and traceable, making the equipment management work more transparent and digital.

Description

Technical Field

[0001] The present invention relates to the technical field of electric power industry, and in particular to a component life management method. Background Art

[0002] The power industry is an industrial sector that converts primary energy such as coal, oil, natural gas, nuclear fuel, hydropower, ocean energy, wind energy, solar energy, biomass energy, etc. into electrical energy through power generation facilities, and then supplies it to users as energy through transmission, transformation and distribution systems. An industrial sector that produces, transmits and distributes electrical energy. It includes power generation, transmission, transformation, distribution and other links. The production process and consumption process of electrical energy are carried out simultaneously, and they cannot be interrupted or stored, and require unified dispatch and distribution. The power industry provides basic power for industry and other sectors of the national economy. Subsequently, a number of large and medium-sized hydropower stations were built in areas with conditions. It is a leading sector in the development of the national economy. With the acceleration of the modernization process, the power industry has developed rapidly. China's power development has entered a new stage of large power grids, large units, high parameters, ultra-high voltage, automation and informatization. Electricity has become an indispensable means of production and living for economic development and people's lives.

[0003] Existing power plants, due to the increasing number of aging units, the increase of new high-parameter units, the reform of the power industry management system, the change of the power plant maintenance system and the development of life assessment technology, urgently need to manage the life of unit components in order to solve the uncertainty of load growth, the rapid rise of equipment construction costs, the difficulty of construction land and the increasingly stringent environmental protection regulations. To this end, we propose a component life management method to solve the above problems. Summary of the invention

[0004] The purpose of the present invention is to solve the problems in the prior art such as the uncertainty of load growth, the rapid rise in equipment construction costs, the difficulty in obtaining construction land and the increasingly stringent environmental protection regulations due to the increasing number of aging units, the increase in new high-parameter units, the reform of the power industry management system, the change in the power plant maintenance system and the development of life assessment technology, and to propose a component life management method.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] A component life management method, the steps of which are as follows:

[0007] Extract historical fault data of the unit, analyze fault symptoms, and calculate the probability of equipment failure in real time;

[0008] The output error vector of the neural network model and the output error vector of the thermodynamic model are constructed respectively, and the "hyperplane" cosine angle of the error vector is obtained by applying the similarity principle as the confidence criterion of the fault warning.

[0009] According to the proportional relationship between the speed and flow rate of rotating equipment, the efficiency calculation formula and the shaft power calculation formula, the theoretical head, efficiency and shaft power curves of important auxiliary machines at different speeds are fitted;

[0010] According to the ratio of the current speed of the auxiliary machine to the rated speed, the flow-head curve, flow-efficiency curve, and flow-shaft power curve are calculated to obtain the comprehensive performance index of the auxiliary machine;

[0011] According to the temperature and service life curves of different materials of different heating surfaces of the boiler, the remaining service life of each heating surface is calculated by formula;

[0012] Based on the probability of equipment failure, boiler life status information and comprehensive performance indicators of important auxiliary equipment, operators adjust the operating mode of boilers and important auxiliary equipment to improve the operating safety of the unit.

[0013] Preferably, historical fault data of the unit is extracted to perform fault symptom analysis, and BP neural network classification, thermodynamic modeling calculation and similarity principle are applied to analyze and calculate the probability of equipment failure in real time.

[0014] Preferably, since the neural network model has high accuracy, but its generalization ability and anti-interference ability are poor: thermodynamic modeling is limited to the accuracy of field measurement points and the number of field measurement points, its accuracy is lower than that of neural network, but its generalization ability and anti-interference ability are stronger; combining the advantages of the two, the output error vector of the neural network model and the output error vector of the thermodynamic model are constructed respectively, and the "hyperplane" cosine angle of the error vector is obtained by applying the similarity principle as the confidence criterion of fault warning, and the formula is as follows:

[0015]

[0016] ΔΑ=Α-C-neural network output error vector;

[0017] ΔΒ=Β-C-thermodynamic modeling output error vector;

[0018] A-neural network output vector; B-thermodynamic modeling output vector; C-system actual vector.

[0019] Preferably, according to the proportional relationship between the rotation speed and flow rate of the rotating equipment, the efficiency calculation formula and the shaft power calculation formula, the flow-head curve, flow-efficiency curve and flow-shaft power curve obtained from the performance test of important auxiliary equipment are fitted to obtain the theoretical head, efficiency and shaft power curves of the auxiliary equipment at different speeds.

[0020] Preferably, the flow-head curve, flow-efficiency curve, and flow-shaft power curve are calculated according to the ratio of the current speed of the auxiliary machine to the rated speed and plotted in a plane. At the same time, the current state point of the auxiliary machine is projected into the plane, and the distance between the point and the ordinate of the corresponding curve is compared. The comprehensive performance index of the auxiliary machine is obtained by combining the three distances.

[0021] Preferably, according to the temperature and service life curves of different materials of different heating surfaces of the boiler, the remaining service life of each heating surface is calculated by a formula, and the formula is as follows:

[0022]

[0023] W i represents the over-temperature overdraft time of each heating surface under different over-temperature ranges, n represents the temperature measurement points corresponding to different heating surfaces on site, and m represents different over-temperature ranges; w i The system counts the cumulative over-temperature time of each heating surface at different over-temperature ranges during the operation of the unit; Q n Design service life of the heating surface pipeline.

[0024] Preferably, the efficiency calculation formula is as follows:

[0025] η=ρgQH / P;

[0026] In the formula: ρ-density of the transported liquid; g-acceleration of gravity; Q-flow rate; H-lift; P-shaft power;

[0027] The shaft power calculation formula is as follows:

[0028] N = ρgQH / η;

[0029] In the formula: ρ-density of the conveyed liquid; g-acceleration of gravity; Q-flow rate; H-lift; η-efficiency; N-shaft power.

[0030] Preferably, the calculation formula for the ratio of the current speed to the rated speed is as follows:

[0031] ns=3.65n(Q)^(1 / 2) / (H)^(3 / 4);

[0032] In the formula: ns-speed ratio; n-speed; Q-flow rate; H-head.

[0033] Compared with the prior art, the present invention has the following beneficial effects:

[0034] 1. The implementation of the present invention realizes the supervision of the whole life cycle of the heating surface metal through the calculation of the remaining life; it can remind the operating personnel to strengthen the monitoring of the wall temperature of the heating surface that is prone to overheating and make good combustion adjustments; it can guide the maintenance personnel to focus on and reasonably replace the pipelines during the unit maintenance to ensure the smooth operation of the unit

[0035] 2. The present invention also solves the problems of uncertainty in load growth, rapidly rising equipment construction costs, difficulty in obtaining construction land, and increasingly stringent environmental protection laws and regulations, thereby extending the service life of the unit, saving a certain amount of funds for the power plant, improving the area occupied by the equipment, and protecting the environment to a certain extent.

[0036] 3. The present invention provides data support for equipment maintenance and promotes lean operation management by visualizing and digitally presenting equipment performance and failure probability; it makes the equipment status knowable, visible, controllable and traceable, making equipment management more transparent and digital. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 The figure is a flow chart of a component life management method proposed in the present invention. DETAILED DESCRIPTION

[0038] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0039] Reference Figure 1 , a component life management method, the steps of which are as follows:

[0040] Extract historical fault data of the unit, analyze fault signs, and apply BP neural network classification, thermodynamic modeling calculation and similarity principle to analyze and calculate the probability of equipment failure in real time;

[0041] Since the neural network model has high accuracy, but its generalization ability and anti-interference ability are poor: the thermodynamic modeling is limited to the accuracy of the field measurement points and the number of field measurement points, its accuracy is lower than that of the neural network, but its generalization ability and anti-interference ability are stronger; combining the advantages of the two, the output error vector of the neural network model and the output error vector of the thermodynamic model are constructed respectively, and the "hyperplane" cosine angle of the error vector is obtained by applying the similarity principle as the confidence criterion of the fault warning. The formula is as follows:

[0042]

[0043] ΔΑ=Α-C-neural network output error vector;

[0044] ΔΒ=Β-C-thermodynamic modeling output error vector;

[0045] A-neural network output vector; B-thermodynamic modeling output vector; C-system actual vector;

[0046] According to the proportional relationship between the speed and flow rate of rotating equipment, the efficiency calculation formula and the shaft power calculation formula, the flow-head curve, flow-efficiency curve and flow-shaft power curve obtained from the performance test of important auxiliary equipment are fitted to obtain the theoretical head, efficiency and shaft power curve of the auxiliary equipment at different speeds; the efficiency calculation formula is as follows:

[0047] η=ρgQH / P;

[0048] In the formula: ρ-density of the transported liquid; g-acceleration of gravity; Q-flow rate; H-lift; P-shaft power;

[0049] The shaft power calculation formula is as follows:

[0050] N = ρgQH / η;

[0051] In the formula: ρ-density of the transported liquid; g-acceleration of gravity; Q-flow rate; H-lift; η-efficiency; N-shaft power;

[0052] According to the ratio of the current speed of the auxiliary machine to the rated speed, the flow-head curve, flow-efficiency curve, and flow-shaft power curve are calculated and plotted in a plane. At the same time, the current state point of the auxiliary machine is projected into the plane, and the distance between the point and the ordinate of the corresponding curve is compared. The comprehensive performance index of the auxiliary machine is obtained by combining the three distances; the calculation formula for the ratio of the current speed to the rated speed is as follows:

[0053] ns=3.65n(Q)^(1 / 2) / (H)^(3 / 4);

[0054] In the formula: ns-speed ratio; n-speed; Q-flow rate; H-head;

[0055] According to the temperature and service life curves of different materials of different heating surfaces of the boiler, the remaining service life of each heating surface is calculated by the formula as follows:

[0056]

[0057] W i represents the over-temperature overdraft time of each heating surface under different over-temperature ranges, n represents the temperature measurement points corresponding to different heating surfaces on site, and m represents different over-temperature ranges; w i The system counts the cumulative over-temperature time of each heating surface at different over-temperature ranges during the operation of the unit; Q n Design the service life in combination with the heating surface pipe;

[0058] Based on the probability of equipment failure, boiler life status information and comprehensive performance indicators of important auxiliary equipment, operators adjust the operating mode of boilers and important auxiliary equipment to improve the operating safety of the unit.

[0059] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present invention.

[0060] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0061] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A component life management method, characterized in that: The steps are as follows: Extract historical fault data of the unit, analyze fault symptoms, and calculate the probability of equipment failure in real time; The output error vector of the neural network model and the output error vector of the thermodynamic model are constructed respectively, and the "hyperplane" cosine angle of the error vector is obtained by applying the similarity principle as the confidence criterion of the fault warning. According to the proportional relationship between the speed and flow rate of rotating equipment, the efficiency calculation formula and the shaft power calculation formula, the theoretical head, efficiency and shaft power curves of important auxiliary machines at different speeds are fitted; According to the ratio of the current speed of the auxiliary machine to the rated speed, the flow-head curve, flow-efficiency curve, and flow-shaft power curve are calculated to obtain the comprehensive performance index of the auxiliary machine; According to the temperature and service life curves of different materials of different heating surfaces of the boiler, the remaining service life of each heating surface is calculated by formula; According to the equipment failure probability, boiler life status information and comprehensive performance indicators of important auxiliary machines, operators adjust the operation mode of boilers and important auxiliary machines to improve the safety of unit operation; Extract historical fault data of the unit, analyze fault signs, and apply BP neural network classification, thermodynamic modeling calculation and similarity principle to analyze and calculate the probability of equipment failure in real time; Since the neural network model has high accuracy, but its generalization ability and anti-interference ability are poor: the thermodynamic modeling is limited to the accuracy and number of field measurement points, and its accuracy is lower than that of the neural network, but its generalization ability and anti-interference ability are stronger; combining the advantages of the two, the output error vector of the neural network model and the output error vector of the thermodynamic model are constructed respectively, and the "hyperplane" cosine angle of the error vector is obtained by applying the similarity principle as the confidence criterion of the fault warning. The formula is as follows: ； -Neural network output error vector; -Thermodynamic modeling output error vector; A-neural network output vector; B-thermodynamic modeling output vector; C-system actual vector; According to the proportional relationship between the rotation speed and flow rate of rotating equipment, the efficiency calculation formula and the shaft power calculation formula, the flow-head curve, flow-efficiency curve and flow-shaft power curve obtained from the performance test of important auxiliary equipment are fitted to obtain the theoretical head, efficiency and shaft power curve of the auxiliary equipment at different speeds; According to the ratio of the current speed of the auxiliary machine to the rated speed, the flow-head curve, flow-efficiency curve, and flow-shaft power curve are calculated and plotted in a plane. At the same time, the current state point of the auxiliary machine is projected into the plane, and the distance between the point and the ordinate of the corresponding curve is compared. The comprehensive performance index of the auxiliary machine is obtained by combining the three distances. According to the temperature and service life curves of different materials of different heating surfaces of the boiler, the remaining service life of each heating surface is calculated by the formula as follows: ； represents the over-temperature overdraft time of each heating surface under different over-temperature ranges, n represents the temperature measurement points corresponding to different heating surfaces on site, and m represents different over-temperature ranges; To count the accumulated over-temperature time of each heating surface at different over-temperature ranges during the operation of the unit; Combined with the design service life of the heating surface pipeline; The efficiency calculation formula is as follows: ; Where: - density of the transported liquid; g- acceleration due to gravity; Q- flow rate; H- head; P- shaft power; The shaft power calculation formula is as follows: ; Where: -density of the transported liquid; g-acceleration of gravity; Q-flow rate; H-lift; -efficiency; N-axis power; The calculation formula of the ratio of the current speed to the rated speed is as follows: ； In the formula: ns-speed ratio; n-speed; Q-flow rate; H-head.

Images