Nuclear power plant prediction type maintenance method and system

Abstract

The invention discloses a prediction type maintenance method and system for a nuclear power plant. The method comprises the following steps: configuring a parameter threshold for a first object, and setting an exception handling rule; the method comprises the following steps: collecting first object operation data, and performing first preprocessing; and predicting and classifying the health state of the first object according to a processing result, and generating a work order. The nuclear power plant prediction type maintenance method and system provided by the invention are helpful for predicting equipment faults, optimizing time and resources to reduce maintenance and operation costs, and improving the performance and reliability of equipment; equipment asset performance and normal operation time are optimized, and cost can be reduced; the early warning of potential faults is helpful for reducing faults, in-plan maintenance or out-of-plan shutdown. The visibility of the continuous state is improved, so that the reliability and durability of the equipment in the whole life cycle are improved; indexes such as average fault interval time and average repair time can be effectively improved, and the income and profitability of enterprises are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of nuclear power plant operation management, and in particular to a predictive maintenance method and system for a nuclear power plant. Background Art

[0002] As a traditional and widely used strategy for the maintenance and management of nuclear power plant equipment, scheduled planned maintenance prevents failures by regularly inspecting, maintaining and replacing equipment parts, thereby reducing equipment downtime, extending equipment life and ensuring stable operation of the system. The existing preventive maintenance strategy for nuclear power plants has the following disadvantages:

[0003] Increased costs: Regular maintenance requires companies to inspect and maintain equipment before any obvious failure occurs, which means additional manpower, material and time costs.

[0004] Excessive maintenance: Performing maintenance at fixed times or cycles may lead to excessive maintenance, that is, replacing or repairing equipment parts when they are still in good condition, which not only wastes resources but may also introduce new failure points.

[0005] Lack of specificity: Regular maintenance is usually based on the average life of the equipment or the maintenance cycle recommended by the manufacturer. However, the actual usage conditions, environment and degree of wear of each device may be different. This one-size-fits-all approach cannot accurately reflect the actual maintenance needs of individual equipment.

[0006] Poor planning flexibility: Regular maintenance plans are usually pre-set. If special circumstances arise (such as a sudden increase in equipment load or environmental changes), the maintenance plan cannot be adjusted in time, resulting in a disconnect between maintenance activities and actual needs.

[0007] Insufficient data utilization: Without full use of equipment operation data and performance analysis, scheduled maintenance may not fully utilize the advantages of modern data analysis and predictive technologies, thereby missing opportunities to improve maintenance efficiency and reduce costs. Summary of the invention

[0008] In view of the above-mentioned problems, the present invention is proposed.

[0009] Therefore, the technical problem solved by the present invention is that the existing preventive maintenance strategy of nuclear power plants has disadvantages including increased costs, excessive maintenance, lack of specificity, poor planning flexibility, and insufficient data utilization, and these disadvantages need to be urgently addressed.

[0010] To solve the above technical problems, the present invention provides the following technical solutions: A predictive maintenance method for a nuclear power plant, comprising: configuring a parameter threshold for a first object and setting an exception handling rule.

[0011] Collect the first object operation data and perform the first pre-processing.

[0012] The health status of the first object is predicted and classified according to the processing result, and a work order is generated.

[0013] As a preferred solution of the predictive maintenance method for nuclear power plants described in the present invention, the configuration parameter thresholds include configuring upper and lower limit control values ​​for each parameter to classify the parameters.

[0014] As a preferred solution of the predictive maintenance method for nuclear power plants described in the present invention, the setting of abnormality handling rules includes configuring corresponding detection rules for different types of parameters.

[0015] As a preferred solution of the predictive maintenance method for nuclear power plants described in the present invention, the collecting of the operating data of the first object includes establishing a collection interface for equipment operating parameters and setting a collection cycle according to the parameter type.

[0016] As a preferred solution of the predictive maintenance method for nuclear power plants described in the present invention, the first pre-processing is a process for improving data quality.

[0017] As a preferred solution of the predictive maintenance method for nuclear power plants described in the present invention, the first object includes but is not limited to nuclear power plant equipment, and the first object operation data includes equipment code, operation parameters, parameter values ​​and timestamp.

[0018] As a preferred embodiment of the predictive maintenance method for nuclear power plants described in the present invention, the health status of the first object is predicted and classified based on the processing results, and a work order is generated, including assigning a fault value of 0 to the parameters that are judged to be qualified, directly assigning a fault value of 1 to the main parameters that are judged to be unqualified, and assigning a fault value of a weighted value to the common parameters that are judged to be unqualified.

[0019] The total fault value is obtained by weighted summation, and the equipment health status is classified into healthy, relatively healthy, and fault precursor.

[0020] Filter out the equipment that is in a state of precursor to failure and generate a maintenance work order.

[0021] The work order content includes the equipment code, abnormal operating parameters and their details, and recommended maintenance measures. The work order is assigned to the corresponding maintenance team, the progress of the work order processing is tracked, the maintenance completion time and results are recorded, and the maintenance is completed.

[0022] A predictive maintenance system for a nuclear power plant, characterized in that it includes:

[0023] The parameter module is configured to configure parameter thresholds for the first object and to set exception handling rules.

[0024] The collection module collects the operation data of the first object and performs a first pre-processing.

[0025] The prediction module predicts and classifies the health status of the first object according to the processing result and generates a work order.

[0026] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0027] A computer-readable storage medium stores a computer program, which implements the steps of the method described above when executed by a processor.

[0028] The beneficial effects of the present invention are as follows: It helps to foresee equipment failures, optimize time and resources to reduce maintenance and operating costs, and improve equipment performance and reliability. It optimizes equipment asset performance and uptime, which helps reduce costs. Early warning of potential failures helps reduce failures, planned maintenance or unplanned downtime. The improvement of continuous status visibility helps to improve the reliability and durability of equipment throughout its life cycle. It can effectively improve indicators such as mean time between failures and mean time to repair, and increase corporate revenue and profitability. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0030] Figure 1 An overall flow chart of a predictive maintenance method and system for a nuclear power plant provided in the first embodiment of the present invention.

[0031] Figure 2 A statistical distribution diagram of equipment operating parameter values ​​of a predictive maintenance method and system for a nuclear power plant provided in the first embodiment of the present invention.

[0032] Figure 3 A structural block diagram of equipment operating parameter values ​​of a predictive maintenance method and system for a nuclear power plant provided in the first embodiment of the present invention. DETAILED DESCRIPTION

[0033] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0034] Example 1, reference Figure 1 to Figure 3 , as an embodiment of the present invention, provides a predictive maintenance method for a nuclear power plant, comprising:

[0035] S1: Configure parameter thresholds for the first object and set exception handling rules.

[0036] In the present invention, the equipment operating parameter list is first determined. The system lists all the operating parameters that need to be monitored based on the equipment ledger and technical manual, including key parameters such as temperature, pressure, vibration, and operating time.

[0037] Then configure the upper and lower limit thresholds, use the historical operation data and the standards provided by the equipment supplier to configure the upper and lower limit control values ​​of each parameter, such as Figure 2 As shown, including:

[0038] Upper Control Line (UCL): Indicates the upper limit of the operating parameter, such as the maximum allowable value of the temperature parameter.

[0039] Lower Control Line (LCL): Indicates the lower limit of the operating parameter, such as the minimum allowable value of the pressure parameter.

[0040] For example, the temperature operating range is set to 40℃≤t≤80℃, and the operating time limit is x≤48 hours.

[0041] Set parameter categories and weights:

[0042] Main parameters: Parameters directly related to the core functions of the equipment (such as the main shaft vibration value of a nuclear power pump). If the main parameters are abnormal, the equipment is directly judged to be unhealthy.

[0043] Common parameters: parameters that indirectly affect the health of the equipment (such as operating time). The weight values ​​of common parameters are determined by expert scoring, with a weight range of 0 to 1 and a total weight of 1.

[0044] Configure exception handling rules. For different types of operating parameters, configure their exception detection rules, for example:

[0045] Continuous point exceeding limit rules (such as 5 consecutive points increasing or exceeding upper and lower limits).

[0046] Sudden change rules (such as changes that are more than twice the recent average change).

[0047] Long-term deviation rules (such as multiple consecutive points deviating from the center line).

[0048] The first object includes, but is not limited to, nuclear power plant equipment, and may also be chemical production equipment and rail transportation equipment.

[0049] In an optional embodiment of the present invention, the first object is a chemical production equipment. For the chemical production equipment, the key parameters need to be set around the operating status and process requirements of the chemical equipment, mainly including the following categories:

[0050] Temperature parameters: The operating temperature range of the chemical reactor, for example 50℃≤t≤200℃, the corresponding upper and lower limits (UCL and LCL) are determined by the chemical process requirements and material properties.

[0051] Pressure parameters: such as the internal pressure of the reactor or storage tank, the operating range is, for example, 2MPa≤P≤6MPa, determined in combination with the equipment technical manual and process standards.

[0052] Flow parameters: such as feed flow or cooling medium flow, operating range, for example 100L / h≤Q≤500L / h, use historical process data to configure appropriate upper and lower limits.

[0053] Liquid level parameters: The tank liquid level is set to 10% ≤ L ≤ 90% to ensure a safe operating range.

[0054] Parameter classification and weight:

[0055] Main parameters: such as reaction temperature and pressure, directly affect reaction safety and equipment stability, and their weight is 1.

[0056] Common parameters: such as flow and liquid level, are indirectly related to process efficiency and equipment health, and their weight range is 0.1 to 0.5.

[0057] The abnormal detection rules of chemical equipment parameters are mainly formulated based on their dynamic operation characteristics:

[0058] Continuous deviation from the rule: When the temperature or pressure exceeds the upper or lower limit for more than 3 times in a row, an exception is triggered.

[0059] Mutation rule: If the flow parameter fluctuation range exceeds twice the design value within 10 minutes, it is judged as abnormal.

[0060] Fluctuation and instability rule: If the liquid level parameter rises and falls rapidly more than 3 times in a row within 30 minutes, an early warning is triggered.

[0061] In an optional embodiment of the present invention, the first object is rail transit equipment. For rail transit equipment, such as train braking systems and track status monitoring equipment, key parameter settings are centered around equipment operation safety:

[0062] Braking pressure parameters: such as train brake cylinder pressure, the normal operating range is set to 3.5MPa≤P≤4.5MPa, combined with the braking system design standard configuration.

[0063] Temperature parameters: such as bearing temperature, the operating range is 50℃≤T≤120℃, and the upper and lower limits are determined according to the bearing specifications and historical fault data.

[0064] Vibration parameters: Monitor the vibration acceleration of train carriages or track equipment in the range of 0.2g≤a≤1.5g, use sensors to collect data and determine limit values.

[0065] Current parameters: such as the power supply current of the track monitoring equipment, set to 5A≤I≤10A.

[0066] Main parameters: such as brake pressure, which directly affects the braking performance of the train and has a weight of 1.

[0067] Common parameters: such as vibration parameters, which reflect the potential hidden dangers of the equipment, and their weight range is 0.2 to 0.6.

[0068] The formulation of rail transit equipment parameter abnormality rules focuses on rapid response and safety assurance:

[0069] Single-point emergency rule: When the brake pressure drops below 3MPa instantly, an emergency warning is triggered immediately.

[0070] Multi-point increasing rule: If the bearing temperature shows an increasing trend for 5 consecutive data points, an exception is triggered.

[0071] High-frequency abnormality rule: If the vibration acceleration exceeds the set range more than 10 times within 1 hour, a maintenance suggestion is triggered.

[0072] S2: Collecting the first object operation data and performing a first pre-processing.

[0073] Through SCADA (Supervisory Control and Data Acquisition) or device IoT gateway, establish an interface for collecting device operating parameters. The interface protocol supports industrial standard protocols such as OPC, Modbus, and DNP3.

[0074] According to the parameter type, set different acquisition frequencies, including:

[0075] Rapidly changing parameters (such as vibration values): the acquisition frequency is 1Hz.

[0076] Slowly changing parameters (such as temperature): the collection frequency is 10 minutes / time.

[0077] The collected equipment operating parameter data include:

[0078] Device code: Identifies the device from which the data is collected.

[0079] Operating parameters: Specific indicators monitored, such as temperature.

[0080] Parameter value: the actual value collected.

[0081] Timestamp: The time when the data was collected.

[0082] Data cleaning removes obviously erroneous data (such as null values ​​caused by instrument failure or values ​​outside the physically possible range). For data with abnormal collection, interpolation or filling is performed.

[0083] Analyze and judge the collected parameter data to determine whether it meets the set standards.

[0084] The steps of anomaly detection are as follows:

[0085] For parameters with upper and lower thresholds, perform the following judgments:

[0086] Whether there are records exceeding the upper control line or the lower control line.

[0087] Are there 5 consecutive points on the same side of the center line or an increasing / decreasing trend?

[0088] Whether the fluctuation is more than twice the historical fluctuation.

[0089] For parameters with only a unidirectional threshold (such as running time), determine whether their value exceeds the set threshold.

[0090] Abnormal record annotation:

[0091] For each collected record, add abnormal annotation fields, including:

[0092] Normal: The parameter value is within the upper and lower limits, with no abnormal trend.

[0093] Abnormal: The parameter value exceeds the limit or there is an abnormal trend.

[0094] Abnormal trend modeling: Use time series data analysis algorithms (such as ARIMA model or Kalman filter) to analyze the changing trend of parameters and predict possible changes in the short term in the future.

[0095] S3: Predict and classify the health status of the first object according to the processing result, and generate a work order.

[0096] Compute the fault value for each parameter:

[0097] For parameters that are judged to be qualified, the fault value is assigned to 0.

[0098] If the main parameter is judged to be unqualified, the fault value is directly assigned to 1.

[0099] For common parameters that are judged as unqualified, the fault value is the weight value.

[0100] The integrated equipment health fault value is calculated by weighted summation. The equipment health status is classified according to the calculated fault value:

[0101] Healthy: The fault value is 0. All operating parameters of the device are normal.

[0102] Healthier: The fault value is less than or equal to 0.6, indicating that the main parameters monitored by the equipment are normal, and only a few common parameters are abnormal.

[0103] Fault precursor: If the fault value is greater than 0.6, it means that the main parameters of the equipment are abnormal or most of the common parameters are abnormal, and a fault may occur in the near future.

[0104] Generates a report containing:

[0105] Device health level.

[0106] The health status of each operating parameter.

[0107] A detailed description of the exception parameters.

[0108] Analyze the health status classification results of all devices and filter out the devices that are in a state of failure precursor. Automatically generate maintenance work orders, which include equipment code, abnormal operating parameters and their details, and recommended maintenance measures (match maintenance suggestions according to parameter abnormality types).

[0109] Assign the work order to the corresponding maintenance personnel or team. Track the progress of the work order and record the completion time and results of the maintenance. Re-collect and analyze the operating parameters of the equipment after maintenance. If the health status returns to normal, close the work order.

[0110] The computer device may be a server. The computer device includes a processor, a memory, an input / output interface (I / O for short) and a communication interface. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface is connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data cluster data of a power monitoring system. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a predictive maintenance method for a nuclear power plant is implemented.

[0111] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0112] Embodiment 2 is an embodiment of the present invention, which provides a predictive maintenance method and system for a nuclear power plant. In order to verify the beneficial effects of the present invention, a scientific demonstration is carried out through simulation experiments.

[0113] In order to verify the advantages of the predictive maintenance method of nuclear power plants over the existing scheduled maintenance strategy, the cooling water pump of a nuclear power plant was selected as the experimental object. The experiment was divided into two groups: the experimental group adopted the predictive maintenance method of the present invention, and the control group adopted the traditional scheduled maintenance method.

[0114] The cooling water pumps in both the experimental and control groups were equipped with operating parameter monitoring equipment. The key parameters monitored included pump body temperature, pressure, vibration value and operating time.

[0115] Operating conditions: Two groups of cooling water pumps operate in the same environment, simulating the actual operating conditions of a nuclear power plant, with each pump operating for 16 hours a day.

[0116] Existing technology implementation process:

[0117] Configuration maintenance cycle: The cooling water pump should be fully inspected every 500 hours of operation, and all consumable parts should be replaced during the inspection.

[0118] Data collection method: Manually transcribe daily operating data and check historical data once a month.

[0119] Abnormal handling: shut down the machine and carry out emergency repairs when a sudden failure occurs.

[0120] Implementation process of the present invention:

[0121] Parameter configuration: According to the technical manual and historical data of the cooling water pump, configure the following parameter thresholds:

[0122] Temperature: 40℃≤T≤80℃;

[0123] Pressure: 1.5MPa≤P≤2.5MPa;

[0124] Vibration value: 0.5g≤V≤1.2g;

[0125] Running time: ≤48 hours per run.

[0126] Exception rule settings:

[0127] Continuous over-limit rule: The temperature exceeds the upper limit for three consecutive times, triggering an exception;

[0128] Mutation rule: A single sudden increase in vibration value exceeding 1.5 times the mean triggers an anomaly.

[0129] Data collection and cleaning: The SCADA system collects equipment parameters in real time and uploads them to the monitoring platform every hour. Abnormal data is cleaned and interpolated to ensure data integrity.

[0130] Health status prediction and work order generation:

[0131] The fault value of the main parameter is directly assigned as 1, and the fault value of the common parameter is assigned according to the weight;

[0132] Calculate the total fault value and classify the health status into healthy, relatively healthy, and fault precursor;

[0133] A work order is generated for the equipment with fault precursors, which contains the fault description and maintenance suggestions. The experimental results are shown in Table 1.

[0134] Table 1 Experimental results

[0135]

[0136] According to the data in the table, there are significant differences between the control group and the experimental group in terms of equipment status, maintenance efficiency and reliability:

[0137] The average temperature, pressure and vibration values ​​of the experimental group were all kept within the set reasonable range, while the parameters of the comparison group were closer to or exceeded the upper limit. In particular, the temperature and vibration values ​​of the comparison group were more than 10% higher than those of the experimental group, which may lead to increased equipment wear.

[0138] The present invention can timely capture potential problems of equipment through real-time monitoring and abnormal rule prediction, thereby avoiding high-load operation.

[0139] During the entire test period, the average monthly maintenance time for the experimental group was 56 hours, while that for the control group was 1214 hours, saving more than 50% of time costs.

[0140] Through the health status prediction function, the maintenance of the experimental group was more targeted and flexible; the comparison group had the problem of over-maintenance due to maintenance according to fixed cycles.

[0141] The experimental group had only one failure per month, while the control group had 3 to 4 failures per month, a reduction of more than 70%.

[0142] By generating work orders and repairing the precursors to failures in a timely manner, the experimental group avoided more sudden downtime, while the control group required frequent emergency repairs.

[0143] The experimental group showed obvious advantages in equipment health status monitoring, fault prediction and resource optimization. The present invention effectively solves the problems of high cost, excessive maintenance and poor flexibility in the prior art.

[0144] Embodiment 3 is an embodiment of the present invention, including a predictive maintenance system for a nuclear power plant, specifically:

[0145] A configuration parameter module is used to configure parameter thresholds for the first object and set exception handling rules;

[0146] A collection module, collecting the operation data of the first object and performing a first pre-processing;

[0147] The prediction module predicts and classifies the health status of the first object according to the processing result and generates a work order.

[0148] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A predictive maintenance method for a nuclear power plant, characterized in that: include: Configure parameter thresholds for the first object and set exception handling rules; Collecting the first object operation data and performing a first pre-processing; The health status of the first object is predicted and classified according to the processing result, and a work order is generated.

2. The predictive maintenance method for a nuclear power plant according to claim 1, characterized in that: The configuration parameter thresholds include configuring upper and lower limit control values ​​of each parameter and classifying the parameters.

3. The predictive maintenance method for a nuclear power plant according to claim 2, characterized in that: The setting of the exception handling rules includes configuring corresponding detection rules for different types of parameters.

4. The predictive maintenance method for a nuclear power plant according to claim 3, characterized in that: The collecting of the first object operation data includes establishing a collection interface for the equipment operation parameters and setting a collection period according to the parameter type.

5. The predictive maintenance method for a nuclear power plant according to claim 4, characterized in that: The first pre-processing is a process for improving data quality.

6. The predictive maintenance method for a nuclear power plant according to claim 5, characterized in that: The first object includes but is not limited to nuclear power plant equipment, and the first object operation data includes equipment code, operation parameters, parameter values ​​and timestamp.

7. The predictive maintenance method for a nuclear power plant according to claim 6, characterized in that: The predicting and classifying the health status of the first object according to the processing result and generating a work order includes assigning a fault value of 0 to a parameter that is judged to be qualified, directly assigning a fault value of 1 to a main parameter that is judged to be unqualified, and assigning a fault value of a weight value to a common parameter that is judged to be unqualified; The total fault value is obtained by weighted summation, and the equipment health status is classified into healthy, relatively healthy, and fault precursor; Filter out equipment that is in a state of precursor to failure and generate a maintenance work order; The work order content includes equipment code, abnormal operating parameters and their details, and recommended maintenance measures; the work order is assigned to the corresponding maintenance team, the progress of the work order processing is tracked, the maintenance completion time and results are recorded, and the maintenance is completed.

8. A predictive maintenance system for a nuclear power plant using the method according to any one of claims 1 to 7, characterized in that: A configuration parameter module is used to configure parameter thresholds for the first object and set exception handling rules; A collection module, collecting the operation data of the first object and performing a first pre-processing; The prediction module predicts and classifies the health status of the first object according to the processing result and generates a work order.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images