Cost and service life joint optimization-oriented equipment condition-based maintenance method and device

Abstract

The invention discloses an equipment on-condition maintenance method and device oriented to cost and life joint optimization, and relates to the technical field of equipment PHM. The method comprises the steps that an equipment maintenance cost evaluation function is established, and the optimal maintenance time difference corresponding to the lowest total maintenance cost is calculated; and on the basis of the optimal maintenance time difference, carrying out equipment performance prediction under an on-condition maintenance plan, and calculating the remaining runnable time of the equipment when the performance is failed, thereby obtaining a life prediction estimated value of the equipment under the optimal on-condition maintenance plan. According to the method, the maintenance cost, the repair cost and the shutdown cost generated in the equipment maintenance process are comprehensively considered, a more scientific condition-based maintenance plan is made by taking cost optimization as a direct target, and meanwhile, based on a performance prediction model, the optimal service life prediction of the equipment is realized on the basis of the maintenance plan, so that the maintenance efficiency is improved. And an accurate predictive maintenance technical support is provided for a user, so that the scientificity and the economical efficiency of operation and maintenance work are effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment prognostics and health management (PHM). In view of the actual demand for cost reduction and efficiency improvement during the operation and maintenance process of equipment, a condition-based maintenance method, device, and computer equipment for the joint optimization of cost and life of equipment are proposed. Background Art

[0002] With the continuous improvement of the complexity, integration, automation, and precision of equipment systems, issues related to their reliability, maintainability, and full-life cycle maintenance management have received increasing attention. Against this background, equipment maintenance strategies have gone through the following four main development stages: 1. Traditional reactive maintenance after the event: The maintenance method in this stage is passive, usually performing repairs after equipment failures occur. However, this method may not only lead to insufficient reliability in equipment operation but also cause significant economic losses and safety risks. 2. Preventive over-maintenance based on high reliability requirements: To meet the high reliability requirements of equipment, a time-based maintenance strategy is adopted to regularly replace parts that have not yet failed, so as to improve the operation reliability of equipment. However, although this over-maintenance method improves reliability, it brings a significant increase in maintenance costs. 3. Condition-based maintenance: Different from traditional maintenance strategies, this method monitors physical quantities of equipment operation status to identify early signs of failures, thereby avoiding the occurrence of serious failures. This strategy achieves the accuracy of maintenance and reduces unnecessary maintenance costs. It mainly formulates maintenance plans based on data monitored by equipment sensors, focusing on extending equipment life and improving effectiveness, but lacks systematic consideration of the comprehensive impact of historical maintenance records and maintenance costs.

[0003] Despite the continuous evolution of maintenance strategies, differences in factors such as equipment operation and usage habits and working environments make it difficult for equipment to maintain a healthy state in the long term. In addition, equipment performance usually shows a non-linear decline trend during its life cycle, especially in the middle and late stages of service. Conventional periodic maintenance plans cannot fully exert the usage effectiveness of equipment and may even increase maintenance costs due to untimely or excessive maintenance.

[0004] Therefore, designing a condition-based maintenance method that can directly optimize maintenance costs, improve the service effectiveness of equipment, and further optimize the predicted life of equipment has become the core goal and future key direction in the development of equipment PHM technology. Summary of the Invention

[0005] In view of the above problems and technical requirements, the present inventor has proposed a condition-based maintenance method, device and computer equipment for the joint optimization of cost and life of equipment, aiming to comprehensively consider the historical maintenance records of the equipment and the maintenance costs, repair costs and downtime costs generated during the maintenance process. Based on the periodic maintenance time as the benchmark and cost optimization as the direct goal, a more scientific condition-based maintenance plan is formulated. At the same time, based on the performance prediction model, the optimal life prediction of the equipment is realized on the basis of this maintenance plan, providing accurate predictive maintenance technical support for users, thereby effectively improving the scientificity and economy of operation and maintenance work. The technical solution of the present invention is as follows:

[0006] In the first aspect, the present application provides a condition-based maintenance method for the joint optimization of cost and life of equipment, including the following steps:

[0007] Establish an equipment maintenance cost evaluation function, and calculate the optimal maintenance time difference corresponding to the lowest total maintenance cost, providing guidance for the condition-based maintenance plan for operation and maintenance personnel; then, based on the optimal maintenance time difference, carry out the performance prediction of the equipment under the condition-based maintenance plan, and calculate the remaining operable time of the equipment when the performance reaches failure, so as to obtain the life prediction estimate value of the equipment under the optimal condition-based maintenance plan. The overall analysis process is as Figure 1 shown.

[0008] Among them, the total maintenance cost includes the maintenance cost, repair cost and downtime cost generated during the maintenance process; the maintenance time difference is the difference between the planned maintenance cycle time and the actual maintenance time.

[0009] Its further technical solution is that, as Figure 2 shown, the detailed calculation process of this method includes the following steps:

[0010] Step 1: Input the current AFR (Annual Failure Rate) and MTTR (Mean Time To Repair) of the equipment to participate in the calculation of the maintenance cost, where AFR represents the frequency of failures or anomalies of the equipment within a specific time period, and MTTR is the total repair duration divided by the number of repairs, reflecting the repair efficiency after the equipment fails.

[0011] Step 2: Establish a cost optimization model for formulating a condition-based maintenance plan. The objective function H(ΔT, AFR, MTTR) of this model is an equipment maintenance cost evaluation function H about the three major parameters of the maintenance time difference ΔT, AFR, and MTTR, specifically including the annual equipment maintenance cost H 保养 generated by maintenance, failure occurrence, and failure repair 维修 repair cost H 停机 downtime cost H 保养 The objective design variable of the function H is ΔT, and the constraint conditions of the function H are H 维修 H 停机If it is the budget, the function H is expressed as:

[0012] H(ΔT, AFR, MTTR) = H 保养 + H 维修 + H 停机

[0013] Constraint: H 保养 ≤ Upper limit of maintenance budget

[0014] Lower limit of repair budget ≤ H 维修 ≤ Upper limit of repair budget

[0015] H 停机 ≤ Upper limit of downtime budget

[0016] Furthermore, two methods for calculating H 保养 , H 维修 , H 停机 are provided in the present invention:

[0017] 1) When the equipment maintenance records are complete and the data volume is sufficient, or the maintenance data of the same type of equipment in similar usage scenarios is complete, H 保养 , H 维修 , H 停机 can be obtained based on the maintenance cost, repair cost, downtime cost expenditure or loss records generated during the actual operation and maintenance process, and the optimal maintenance time difference when the total maintenance cost reaches the lowest can be selected according to the cost trend and the historical maintenance records of each period.

[0018] 2) However, when there is a lack of actual maintenance records or the data volume is insufficient, H 保养 , H 维修 , H 停机 can be characterized based on the service conditions and operation and maintenance requirements of the equipment according to the following formula to represent the relationship with the variable ΔT:

[0019] H 保养 = a1 * 365 * 24 / (T - T * S Δ2 ), -1 ≤ S ΔT ≤ 1

[0020]

[0021] Where: T represents the planned maintenance cycle time (default unit: hour); S ΔT = ΔT / T, representing the normalized maintenance time difference; e -S ΔT -1 represents the influence factor of the normalized maintenance time difference on the equipment failure rate; a1 represents the single maintenance cost, a2 represents the single fault repair cost, and a3 represents the failure rate influence factor e -SΔTThe incremental unit maintenance cost caused by -1, and a4 represents the loss of downtime cost per unit time. It should be noted that a1, a2, a3, and a4 need to be assigned values according to the actual situation of the equipment.

[0022] Step 3: Within the scope of various cost budget constraints, take the optimal maintenance time difference calculated by H(ΔT, AFR, MTTR) when the total maintenance cost is the lowest.

[0023] Step 4: Substitute the optimal maintenance time difference into the performance prediction function for the equipment status, where the equipment status data includes the maintenance time difference ΔT, the annual average failure rate AFR, the operating time, sensor data, etc. The performance prediction function is established based on the operating characteristics and its own fatigue properties of the equipment, and its function value is used as a comprehensive evaluation index for the equipment availability, such as the following calculation method.

[0024]

[0025] Where: Ratetime represents the difference between the calibrated total life and the operating time, and Runtime represents the operating time of the equipment; b1 and b2 respectively represent the impacts of the operating time and the failure rate on the equipment performance, and need to be assigned values according to the actual situation of the equipment. It should be noted that if the impact of sensor data needs to be reflected in the performance prediction function, calculation items related to sensor data can be added in the above formula form.

[0026] Step 5: Assume that the personnel operate in a standardized manner and complete the maintenance work on time according to the condition-based maintenance plan. Then the generator will tend to age and fail in an ideal linear state. Calculate the equipment operating time Runtime when the performance prediction function value reaches the failure value (i.e., L = 0), so as to obtain the optimal remaining life estimate of the equipment when implementing the maintenance work according to the condition-based maintenance plan. An example of the performance evaluation within the service history of this equipment is as Figure 3 shown.

[0027] In the second aspect, the present application also provides an equipment condition-based maintenance device for joint optimization of cost and life, and this device includes:

[0028] An equipment maintenance cost evaluation module, which is used to establish an equipment maintenance cost evaluation function and calculate the optimal maintenance time difference corresponding to the lowest total maintenance cost;

[0029] An equipment performance prediction module, which is used to carry out equipment performance prediction under the condition-based maintenance plan based on the optimal maintenance time difference, and calculate the remaining operable time of the equipment when the performance reaches failure, so as to obtain the life prediction estimate of the equipment under the optimal condition-based maintenance plan;

[0030] Among them, the total maintenance cost includes the maintenance cost, repair cost, and downtime cost incurred during the maintenance process; the maintenance time difference is the difference between the planned maintenance cycle time and the actual maintenance time.

[0031] In a third aspect, the present application also provides a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements the steps of the method described in the first aspect.

[0032] The beneficial technical effects of the present invention are:

[0033] The condition-based maintenance method and device for equipment oriented to the joint optimization of cost and life proposed by the present invention can reasonably combine the equipment maintenance records and maintenance costs, formulate a condition-based maintenance plan around the goal of reducing costs and increasing efficiency of the equipment, and further carry out the optimal life prediction of the equipment under the condition-based maintenance plan, providing accurate and reasonable quantitative guidance for the user's next maintenance work and improving the service efficiency of the equipment. Description of the Drawings

[0034] Figure 1 is the overall analysis flowchart of the equipment condition-based maintenance method provided by the present application.

[0035] Figure 2 is the detailed calculation flowchart of the equipment condition-based maintenance method provided by the present application.

[0036] Figure 3 is an example diagram of performance prediction and evaluation within the service history of the equipment provided by the present application.

[0037] Figure 4 is a schematic diagram showing the relationship between the equipment maintenance cost evaluation function H and the variable ΔT provided by the present application.

[0038] Figure 5 is a schematic diagram showing the relationship between the generator performance prediction function and the running time provided by the present application. Detailed Embodiments

[0039] The following further describes the specific embodiments of the present invention with reference to the drawings.

[0040] An embodiment of the present application provides a condition-based maintenance method for equipment oriented to the joint optimization of cost and life. This method takes the maintenance of a generator in a certain factory area as an example. The generator is the main power source for the normal production and operation of the factory area. If the generator fails and stops, it will cause a certain repair cost. At the same time, the shutdown will lead to the suspension of production and operation, indirectly exacerbating the serious loss of downtime cost. Therefore, it is necessary to combine the maintenance records and operating characteristics of the generator during its service in this environment to formulate a condition-based maintenance plan for the joint optimization of cost and life.

[0041] According to the equipment instructions, the key maintenance work for the generator is lubricating oil replacement. Its planned maintenance time cycle T is 3,000 hours, its calibrated total life time is 50,000 hours, and the operating time is 28,000 hours.

[0042] According to the technical solution process provided in the invention content, the condition-based maintenance calculation process of this generator is as follows:

[0043] Step 1: It is known from the historical maintenance records that the current AFR of the generator is 0.1% and the MTTR is 48 hours.

[0044] Step 2: Establish a cost optimization model for condition-based maintenance plan formulation. It is known from the equipment instructions and maintenance records that the average single-fault repair cost a2 of this generator is 30,000 yuan, the single maintenance cost a1 is 15,000 yuan, the average daily downtime cost loss a4 is 50,000 yuan, and the unit repair cost increment a3 caused by the failure rate impact factor is 40,000 yuan. Based on the service conditions of the generator in this plant area, the following equipment maintenance cost evaluation function H is established:

[0045] min H(ΔT, AFR, MTTR) = H 保养 +H 维修 +H 停机

[0046] Where: H 保养 = 1.5 * 365 * 24 / (T - T * S ΔT ), -1 ≤ S ΔT ≤ 1

[0047]

[0048] Constraint: H 保养 ≤ 8w

[0049] 20w ≤ H 维修 ≤ 50w

[0050] H 停机 ≤ 100w

[0051] According to the second method of calculating H 保养 、H 维修 、H 停机 The relationship between the function H and the variable ΔT is obtained as Figure 4 shown.

[0052] Step 3: Within the budget constraint range of H 保养 、H 维修 、H 停机 Take the optimal maintenance time difference of the generator calculated by H(ΔT, AFR, MTTR) when the total maintenance cost is the lowest. From Figure 4It can be seen that when the normalized maintenance time difference is equal to 0.45 (i.e., the maintenance time difference is equal to 1350 hours), the maintenance cost of the generator will reach the lowest within the cost constraint range, and the annual maintenance cost H 保养 under this maintenance plan is 80,000 yuan, the repair cost H 维修 is 220,000 yuan, and the downtime cost H 停机 is 730,000 yuan, all of which meet the requirements of the annual cost budget constraint. Therefore, the optimal maintenance time difference of the generator in the current state is 1350 hours.

[0053] Step 4: Adopt the following generator performance prediction function (which can be established according to the operating characteristics and its own fatigue attributes of the equipment. As an example, this embodiment uses a linear function to construct), and substitute the optimal maintenance time difference and the current AFR into the performance prediction function.

[0054]

[0055] Where: Ratetime = calibrated total life - operating time

[0056] = 50000 - 28000 = 22000;

[0057] AFR = 0.1%, S ΔT = 0.45.

[0058] The changing trend of the future performance of the generator with the operating time under ideal service and operation and maintenance conditions is obtained as Figure 5 shown. It can be seen from this that when the operating time reaches 21311 hours, it is predicted that the performance of the generator will reach failure.

[0059] Based on the above analysis, the condition-based maintenance plan for the generators in this plant area is as follows: the optimal maintenance time difference is 1350 hours (i.e., the maintenance cycle is 1650 hours); the predicted remaining life under this condition-based maintenance plan is: 21311 hours. This data can provide reasonable guidance for users to carry out the next maintenance work.

[0060] Based on the same inventive concept, another embodiment of this application provides an equipment condition-based maintenance device for jointly optimizing cost and lifespan, including an equipment maintenance cost assessment module and an equipment performance prediction module, where: The equipment maintenance cost assessment module is used to establish an equipment maintenance cost assessment function and calculate the optimal maintenance time interval corresponding to the lowest total maintenance cost. The total maintenance cost includes maintenance costs, repair costs, and downtime costs generated during maintenance. The equipment performance prediction module is used to carry out equipment performance prediction under the condition-based maintenance plan based on the optimal maintenance time interval, and calculate the remaining operable time of the equipment when the performance reaches failure, so as to obtain the lifespan prediction estimate value of the equipment under the optimal condition-based maintenance plan. The maintenance time interval is the difference between the planned maintenance cycle time and the actual maintenance time. The implementation solution provided by this device to solve the problem is similar to the implementation solution described in the above method. Therefore, the specific limitations of the equipment maintenance cost assessment module and the equipment performance prediction module in the embodiment of this device can refer to the limitations of the equipment condition-based maintenance method for jointly optimizing cost and lifespan in the above text, and will not be elaborated here.

[0061] Each module in the above equipment condition-based maintenance device can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in the processor in the computer device in hardware form or be independent of it, or can be stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to the above modules.

[0062] In one embodiment, a computer device is provided. This computer device can be a terminal. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Among them, the processor of this computer device is used to provide computing and control capabilities. The memory of this computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of this computer device is used to communicate with an external terminal in a wired or wireless manner. The wireless manner can be achieved through WIFI, a mobile cellular network, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it realizes an equipment condition-based maintenance method for jointly optimizing cost and lifespan. The display screen of this computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of this computer device can be a touch layer covering the display screen, or a button, a trackball, or a touchpad set on the shell of the computer device, or an external keyboard, a touchpad, or a mouse, etc.

[0063] The above are only the preferred embodiments of the present application, and the present invention is not limited to the above embodiments. It can be understood that other improvements and changes directly derived or associated by those skilled in the art without departing from the spirit and concept of the present invention shall be considered to be included within the protection scope of the present invention.

Claims

1. A condition-based equipment maintenance method for joint optimization of cost and life, characterized in that: The method comprises: Establish equipment maintenance cost evaluation function and calculate the optimal maintenance time difference corresponding to the lowest total maintenance cost; Based on the optimal maintenance time difference, the equipment performance under the condition-based maintenance plan is predicted, and the remaining operational time of the equipment when the performance reaches failure is calculated, so as to obtain an estimated life prediction value of the equipment under the optimal condition-based maintenance plan; The total maintenance cost includes the maintenance cost, repair cost and downtime cost generated during the maintenance process; the maintenance time difference is the difference between the planned maintenance cycle time and the actual maintenance time.

2. The equipment condition-based maintenance method for joint optimization of cost and life according to claim 1 is characterized in that: The establishing of the equipment maintenance cost evaluation function comprises: Construct an equipment maintenance cost evaluation function H based on the maintenance time difference ΔT, the annual average failure rate AFR, and the mean fault repair time MTTR. Function H includes the annual maintenance cost H of equipment generated by maintenance, failure occurrence, and fault repair. 保养 , maintenance cost H 维修 , downtime cost H 停机 ; The target design variable of function H is the ΔT, and the constraint condition of function H is H 保养 , H 维修 , H 停机 The budget of , then the function H is expressed as: H(ΔT,AFR,MTTR)=H 保养 +H 维修 +H 停机 Constraint: H 保养 ≤ Maintenance budget upper limit Maintenance budget lower limit ≤ H 维修 ≤Maintenance budget ceiling H 停机 ≤ downtime budget limit.

3. The equipment condition-based maintenance method for joint optimization of cost and life according to claim 2 is characterized in that: The H 保养 , H 维修 , H 停机 The calculation methods include: If the equipment maintenance records are complete and the data volume is sufficient, or the maintenance data of the same type of equipment in similar usage scenarios is complete, H is obtained based on the maintenance cost, repair cost, downtime cost expenditure or loss record incurred during the actual operation and maintenance process. 保养 , H 维修 , H 停机 , and select the optimal maintenance time difference when the total maintenance cost is lowest based on the cost trend and historical maintenance records of each period.

4. The equipment condition-based maintenance method for joint optimization of cost and life according to claim 2 is characterized in that: The H 保养 , H 维修 , H 停机 The calculation method also includes: In the absence of actual maintenance records or insufficient data, according to the service conditions and operation and maintenance requirements of the equipment, H is represented based on the following formula 保养 , H 维修 , H 停机 Relationship with variable ΔT: H 保养 =a1*365*24 / (T-T*S ΔT ),-1≤S ΔT ≤1 Where: T represents the planned maintenance cycle time; S ΔT =ΔT / T, which represents the normalized maintenance time difference; represents the influence factor of the normalized maintenance time difference on the equipment failure rate; a1 represents the single maintenance cost, a2 represents the single fault repair cost, a3 represents the unit maintenance cost increment, and a4 represents the downtime cost loss per unit time.

5. The equipment condition-based maintenance method for joint optimization of cost and life according to claim 1 is characterized in that: Based on the optimal maintenance time difference, equipment performance prediction under the condition-based maintenance plan is carried out, including: Substituting the optimal maintenance time difference into a performance prediction function related to equipment status, wherein equipment status data includes maintenance time difference ΔT, annual average failure rate AFR, and operating time; The performance prediction function is established according to the equipment operation characteristics and its own fatigue properties, and its function value is used as a comprehensive evaluation index of equipment availability.

6. The equipment condition-based maintenance method for joint optimization of cost and life according to claim 5 is characterized in that: The performance prediction function L is expressed as: Where: Ratetime represents the difference between the total calibrated life and the running time, Runtime represents the equipment running time; S ΔT =ΔT / T, which represents the normalized maintenance time difference; represents the influence factor of the normalized maintenance time difference on the equipment failure rate; a3 represents the unit maintenance cost increment, b1 and b2 represent the influence of the operating time and the failure rate on the equipment performance respectively; Calculate the Runtime value corresponding to when L=0 as the estimated value of the optimal remaining life of the equipment.

7. A condition-based maintenance device for equipment aimed at joint optimization of cost and life, characterized in that: The device comprises: Equipment maintenance cost evaluation module, used to establish equipment maintenance cost evaluation function and calculate the optimal maintenance time difference corresponding to the lowest total maintenance cost; An equipment performance prediction module is used to carry out equipment performance prediction under a condition-based maintenance plan based on the optimal maintenance time difference, and calculate the remaining operational time of the equipment when the performance reaches failure, thereby obtaining an estimated life prediction value of the equipment under the optimal condition-based maintenance plan; The total maintenance cost includes the maintenance cost, repair cost and downtime cost generated during the maintenance process; the maintenance time difference is the difference between the planned maintenance cycle time and the actual maintenance time.

8. 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 6 are implemented.

Images