Method for determining predictive maintenance opportunity decision of front-end isolated switching power supply of aging table

Abstract

The invention discloses a predictive maintenance opportunity decision determination method for an isolated switching power supply at the front end of an aging table. The method comprises the following steps: determining the periodic maintenance opportunity of the switching power supply closest to the current moment; predicting a first opportunity when the switching power supply fails; determining a periodic maintenance time window according to the periodic maintenance opportunity; determining a predicted maintenance time window according to the first opportunity; and solving a target maintenance time window of the switching power supply according to a periodic maintenance time window, the predicted maintenance time window, a preset target function and constraint conditions. According to the predictive maintenance opportunity decision determination method for the front-end isolated switching power supply of the aging station provided by the invention, the determined target maintenance time window of the switching power supply is objective and reliable.

Description

Technical Field

[0001] The present invention relates to the technical field of lossless reliability screening of integrated circuits, and in particular to a method and device for determining a predictive maintenance timing decision of an isolated switching power supply at the front end of a burn-in station. Background Art

[0002] Existing high-temperature aging products can achieve long-term monitoring of the test environment by adding long-term monitoring in the machine and overstress protection mechanisms, and can respond in time when the product fails, realizing post-maintenance based on fault data. However, due to the lack of active protection technology for high-temperature aging products, existing high-temperature aging products make it difficult for related products to achieve the integrity of the test process and the consistency of the test environment stress. It is very easy to cause the test process to be interrupted due to product failure, resulting in major property losses such as damage to millions of test devices (also known as test pieces), or the aging test is identified as a failure test due to adverse effects such as additional stress introduced during the test due to product performance degradation, resulting in ineffective waste of resources. At the same time, ensuring the quality of high-temperature aging tests can avoid over-aging and under-aging failures in integrated circuits, greatly reduce the failure rate of integrated circuits, and avoid large-scale electronic system failures and shutdowns such as new energy vehicles, civil airliners, and energy storage transmission stations due to integrated circuit failures.

[0003] As the core component of electronic systems, power supplies play a vital role, especially switching power supplies, which are widely used for their high conversion rate and small size. The switching power supply is composed of many electronic components, and its performance will be affected by these components. Related studies have found that the failure rate curve of electronic components during use is similar to the bathtub curve, and the probability of failure is higher in the early and late stages of use. As the core energy supply component of high-temperature aging products such as aging stations, the occurrence of power supply failures will inevitably affect the normal operation of the aging station. Therefore, during the use of the switching power supply of the aging station (that is, the isolated switching power supply at the front end of the aging station), it is necessary to carry out predictive maintenance activities to determine the maintenance time before the failure occurs, so as to avoid equipment damage and time and labor costs caused by downtime due to failures.

[0004] It can be seen that there is an urgent need for those skilled in the art to provide a solution for predicting the maintenance timing of the switch power supply of a burn-in station. Summary of the invention

[0005] The purpose of the embodiments of the present invention is to provide a method and device for determining a predictive maintenance timing decision of a front-end isolated switching power supply of a burn-in station, which can solve the above-mentioned problems existing in the prior art.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: An embodiment of the present invention provides a method for determining a predictive maintenance opportunity of a front-end isolated switching power supply of a burn-in station, wherein the method comprises: Determine the scheduled maintenance time of the switching power supply closest to the current moment; Predicting a first time when the switching power supply fails; Determine a regular maintenance time window based on the regular maintenance opportunity; Determining a predicted maintenance time window according to the first opportunity; The target maintenance time window of the switching power supply is solved according to the regular maintenance time window, the predicted maintenance time window, a preset objective function and constraints.

[0007] Optionally, the step of determining the periodic maintenance opportunity of the switching power supply closest to the current moment includes: Find the scheduled maintenance time closest to the current moment from the scheduled maintenance schedule in the maintenance manual of the switching power supply of the aging station; or, Determine the expected life of the switching power supply of the burn-in station; The scheduled maintenance opportunity of the switching power supply closest to the current moment is calculated based on the expected life and the average daily usage time of the switching power supply.

[0008] Optionally, the step of determining a predicted maintenance time window according to the first timing includes: Determine the difference between the first timing and half of the preset time window parameter as the lower limit value of the predicted maintenance time window; The sum of the first opportunity and half of the preset time window parameter is determined as the upper limit value of the predicted maintenance time window.

[0009] Optionally, the step of solving the target maintenance time window of the switching power supply according to the regular maintenance time window, the predicted maintenance time window, a preset objective function and constraints includes: Determine whether the scheduled maintenance time window and the predicted maintenance time window have a time window intersection; If so, determining the intersection of the time windows as the target maintenance time window of the switching power supply; If it does not exist, a target maintenance time window for the switching power supply is determined by multi-objective solution based on the regular maintenance time window, the predicted maintenance time window, a preset objective function and constraints.

[0010] Optionally, solving the switch power supply maintenance time window according to the regular maintenance time window, the predicted maintenance time window, a preset objective function and constraints includes: Setting an objective function with maintenance time as an independent variable, wherein the objective function includes: a cost function representing the maintenance cost of the aging station, a risk function representing the safety risk of damage to the experimental terminal and equipment, and a plan function representing the impact of the schedule conflict with the experimental plan; Initialize a particle swarm, wherein each particle swarm includes the following attribute information: a position for characterizing the maintenance time of the switch power supply, a speed for characterizing the change of the maintenance time in the optimization process, and an individual historical best position for characterizing the optimal maintenance time; For each particle in the particle group, updating the speed and position of the particle according to the speed, the individual historical best position and the global best position; Calculating the fitness of the particle according to the updated speed, position and objective function; Based on the comparison between the fitness and the fitness corresponding to the individual historical best position of the particle, the individual historical best position of the particle is updated; Traversing the individual historical best position of each particle in the particle group, determining the maximum value and the minimum value to generate the current maintenance time window; When the current maintenance time window meets a preset condition, the current maintenance time window is determined as a target maintenance time window for the switching power supply.

[0011] Optionally, the method further comprises: When the current maintenance time window does not meet the preset conditions, the process returns to the step of updating the speed and position of each particle in the particle swarm according to the speed, the individual historical best position and the global best position.

[0012] Optionally, the preset condition includes: a difference between an upper limit value and a lower limit value of a current maintenance time window is less than or equal to an estimated maintenance interval window size.

[0013] The embodiment of the present invention further provides a device for determining predictive maintenance timing of a front-end isolated switching power supply of a burn-in station, wherein the device comprises: A timing determination module, used to determine the periodic maintenance timing of the switching power supply closest to the current moment; A prediction module, used for predicting a first time when the switching power supply fails; A first window determination module, used to determine a regular maintenance time window according to the regular maintenance opportunity; A second window determination module, used to determine a predicted maintenance time window according to the first opportunity; The third window determination module is used to solve the target maintenance time window of the switching power supply according to the regular maintenance time window, the predicted maintenance time window, a preset objective function and constraint conditions.

[0014] Optionally, the timing determination module includes: The first submodule is used to find the scheduled maintenance time closest to the current moment from the scheduled maintenance schedule in the maintenance manual of the switching power supply of the aging station; or The second submodule is used to determine the expected life of the switching power supply of the aging station; The third submodule is used to calculate the periodic maintenance opportunity of the switching power supply closest to the current moment according to the expected life and the average daily usage time of the switching power supply.

[0015] Optionally, the second window determining module includes: A fourth submodule, configured to determine the difference between the first timing and half of the preset time window parameter as the lower limit of the predicted maintenance time window; The fifth submodule is used to determine the sum of the first opportunity and half of the preset time window parameter as the upper limit value of the predicted maintenance time window.

[0016] Optionally, the third window determination module includes: A sixth submodule is used to determine whether the regular maintenance time window and the predicted maintenance time window have a time window intersection; A seventh submodule, for determining the intersection of the time windows as the switch power supply maintenance time window if it exists; The eighth submodule is used to determine the target maintenance time window of the switching power supply by multi-objective solution according to the regular maintenance time window, the predicted maintenance time window, the preset objective function and constraints if it does not exist.

[0017] Optionally, the eighth submodule includes: The first unit is used to set an objective function with the maintenance time as an independent variable, wherein the objective function includes: a cost function representing the maintenance cost of the aging station, a risk function representing the safety risk of damage to the experimental terminal and equipment, and a plan function representing the impact of the conflict schedule with the experimental plan; The second unit is used to initialize the particle swarm, wherein each particle swarm includes the following attribute information: a position for characterizing the maintenance time of the switch power supply, a speed for characterizing the change of the maintenance time in the optimization process, and an individual historical best position for characterizing the optimal maintenance time; A third unit is used for updating the speed and position of each particle in the particle group according to the speed, the individual historical best position and the global best position; A fourth unit is used to calculate the fitness of the particle according to the updated speed, position and objective function; A fifth unit is used for comparing the fitness with the fitness corresponding to the individual historical best position of the particle, and updating the individual historical best position of the particle; The sixth unit is used to traverse the individual historical best position of each particle in the particle group, determine the maximum value and the minimum value to generate the current maintenance time window; The seventh unit is configured to determine, when the current maintenance time window satisfies a preset condition, that the current maintenance time window is a target maintenance time window for the switching power supply.

[0018] Optionally, the eighth submodule further includes: The eighth unit is used to return to call the third unit to execute the operation of updating the speed and position of each particle in the particle group according to the speed, individual historical best position and global best position when the current maintenance time window does not meet the preset conditions.

[0019] The eighth submodule further includes: The ninth unit is used to correct the target maintenance time window based on the thermal related parameters of the aging station to obtain the final target maintenance time window, that is, the predictive maintenance time window.

[0020] Optionally, the preset condition includes: a difference between an upper limit value and a lower limit value of a current maintenance time window is less than or equal to an estimated maintenance interval window size.

[0021] An embodiment of the present invention further provides an electronic device, characterized in that it includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; the memory is used to store computer programs; the processor is used to implement any of the above-mentioned predictive maintenance timing decision-making methods for the isolated switching power supply at the front end of the aging station when executing the program stored in the memory.

[0022] The embodiment of the present invention discloses a predictive maintenance timing decision-making scheme for the front-end isolated switching power supply of the aging station, which determines the regular maintenance timing of the switching power supply (i.e., the front-end isolated switching power supply) closest to the current moment; predicts the first timing of a failure of the switching power supply; determines the regular maintenance time window based on the regular maintenance timing; determines the predicted maintenance time window based on the first timing; solves the target maintenance time window of the switching power supply based on the regular maintenance time window, the predicted maintenance time window, the preset objective function, and the constraints. Through the scheme provided by the embodiment of the present invention, the predictive maintenance timing of the switching power supply is comprehensively planned and decided by combining the regular maintenance timing and the fault prediction timing (i.e., the first timing), and the determined target maintenance timing of the switching power supply is objective and reliable. Since the target maintenance timing of the front-end isolated switching power supply of the aging station can be determined objectively and reliably, it can be repaired in time, thereby avoiding damage to the test piece due to the failure of the switching power supply during the aging test. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a flowchart showing the steps of a method for determining a predictive maintenance opportunity of an isolated switching power supply at the front end of a burn-in station according to an embodiment of the present application; Figure 2 It is a flowchart showing the steps of a method for determining a predictive maintenance opportunity of an isolated switching power supply at the front end of a burn-in station according to an embodiment of the present application; Figure 3 is a flowchart showing the steps of a method for predicting a fault of an isolated switching power supply at the front end of a burn-in station considering multiple degradation paths according to an embodiment of the present application; Figure 4 It is a structural block diagram of a device for determining predictive maintenance timing of an isolated switching power supply at the front end of a burn-in station according to an embodiment of the present application. DETAILED DESCRIPTION

[0024] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0025] In conjunction with the accompanying drawings, the method for determining the predictive maintenance timing decision of the isolated switching power supply at the front end of the aging station provided by the embodiment of the present application is described in detail through specific embodiments and application scenarios.

[0026] As attached Figure 1 As shown, the method for determining the predictive maintenance timing of the isolated switching power supply at the front end of the aging station according to the embodiment of the present application includes the following steps: Step 101: Determine the scheduled maintenance time of the switching power supply closest to the current moment.

[0027] The method for determining the timing of predictive maintenance of the isolated switching power supply at the front end of the aging station provided by the implementation of the present application can be applied to electronic devices, in which an aging station switching power supply maintenance computer program is provided. When the computer program is executed by the processor, the method for determining the timing of predictive maintenance of the isolated switching power supply at the front end of the aging station according to the embodiment of the present application is implemented. The switching power supply of the aging station described in the embodiment of the present application is an isolated switching power supply at the front end of the aging station, which can be a primary switching power supply. The switching power supply of the aging station and the primary switching power supply of the switching power supply aging station described below all refer to the isolated switching power supply at the front end of the aging station.

[0028] The aging station provided by the embodiment of the present application can perform non-destructive aging testing on the parts to be tested. In the embodiment of the present application, the maintenance timing of the switching power supply of the aging station is determined, and the timing of the next failure of the switching power supply of the aging station can be predicted in advance, thereby ensuring the safety of the parts to be tested.

[0029] The maintenance timing of the switching power supply of the aging station is determined by the periodic maintenance timing and the predicted maintenance timing (i.e., the first timing described below). The operating instructions or maintenance manual of the aging station usually include the expected life and maintenance plan of the switching power supply, i.e., the preventive maintenance plan and time window in the absence of faults, which is called the "periodic maintenance timing". Based on the fault prediction technology, the predicted time of the next fault of the switching power supply is the predicted maintenance timing.

[0030] An optional method for determining the periodic maintenance opportunity of the switching power supply closest to the current moment may be: Method 1: Find the scheduled maintenance time closest to the current time from the scheduled maintenance schedule in the maintenance manual of the switching power supply of the aging station; or Method 2: Determine the expected life of the switching power supply on the aging station; calculate the scheduled maintenance time of the switching power supply closest to the current time based on the expected life and the average daily usage time of the switching power supply.

[0031] If the method in method 1 does not find a regular maintenance plan, consult the user manual of the switch power supply and obtain the expected life of the switch power supply of the aging station from the manual. , then the regular maintenance time It can be set to the time when the service life is exhausted, which can be calculated by the following method:

[0032] in, The average daily usage time.

[0033] Step 102: predicting the first time when the switching power supply fails.

[0034] Since the occurrence of failures has a certain randomness, only using "regular maintenance" to make maintenance timing decisions has certain limitations. If the failure occurs before the scheduled maintenance time, it may cost manpower, material resources, and time, and affect the normal operation of the aging station; if the failure occurs after the scheduled maintenance time, early maintenance will lead to an increase in maintenance costs per unit time. In view of the fact that regular maintenance times at fixed intervals are prone to "over-maintenance" or "under-maintenance", the trend prediction technology is used in the embodiment of the present application to predict the time (i.e., the timing) when the switching power supply may fail in the future. The predicted failure time is recorded as .

[0035] Step 103: Determine a regular maintenance time window based on the regular maintenance opportunity.

[0036] Step 104: Determine a predicted maintenance time window according to the first opportunity.

[0037] Since both the regular maintenance opportunity and the first opportunity have certain uncertainties, it is reasonable to perform maintenance activities within a time window before or after this opportunity. In the embodiment of the present application, the regular maintenance time window and the predicted maintenance time window are determined based on the regular maintenance opportunity and the first opportunity, and the target maintenance time window of the switching power supply is subsequently determined based on these two time windows.

[0038] In an optional embodiment, according to the periodic maintenance opportunity, the method of determining the periodic maintenance time window may be as follows: The difference between the scheduled maintenance opportunity and half of the preset time window parameter is determined as the lower limit of the scheduled maintenance time window; the sum of the first opportunity and half of the preset time window parameter is determined as the upper limit of the predicted maintenance time window.

[0039] Example: Setting time window parameters , then the regular maintenance time window can be expressed as:

[0040] In an optional embodiment, according to the first opportunity, the method of determining the predicted maintenance time window may be as follows: The difference between the first opportunity and half of the preset time window parameter is determined as the lower limit value of the predicted maintenance time window; the sum of the first opportunity and half of the preset time window parameter is determined as the upper limit value of the predicted maintenance time window.

[0041] Example: Setting time window parameters , the predicted fault occurrence time (i.e. the first opportunity) is , then the predicted maintenance time window can be expressed as:

[0042] Step 105: Calculate the target maintenance time window of the switching power supply according to the scheduled maintenance time window, the predicted maintenance time window, the preset objective function and the constraint conditions.

[0043] In this step, the regular maintenance time window and the predicted maintenance time window are comprehensively considered, and the maintenance time window of the switch power supply of the aging station is solved by multiple constraints. The maintenance time of the switch power supply is any moment in the maintenance time window. Since the switch power supply is the core functional component of the aging station, the predicted maintenance time is made as close to the regular maintenance time as possible, while ensuring that the maintenance time belongs to the predicted maintenance time window, so as to reduce the impact of maintenance on the established test progress of the aging station.

[0044] In an optional embodiment, according to the regular maintenance time window, the predicted maintenance time window, the preset objective function and the constraint conditions, the method of solving the target maintenance time window of the switching power supply can be as follows: Determine whether the scheduled maintenance time window and the predicted maintenance time window have a time window intersection; If it exists, the intersection of the time windows is determined as the target maintenance time window of the switching power supply; if it does not exist, the target maintenance time window of the switching power supply is determined by multi-objective solution based on the regular maintenance time window, the predicted maintenance time window, the preset objective function and the constraints.

[0045] When the regular maintenance time window and the predictive maintenance time window have a time window intersection, the predictive maintenance time window (i.e., the target maintenance time window of the switching power supply) can be expressed as:

[0046] When there is no time window intersection between the scheduled maintenance time window and the predicted maintenance time window, the predictive maintenance time window is mainly based on the predicted maintenance time window.

[0047] When there is no intersection between the regular maintenance time window and the predictive maintenance time window, the predictive maintenance time (i.e., the target maintenance time of the switching power supply) is determined within the predictive maintenance time window by comprehensively considering the characteristics of the aging station equipment and the application scenarios. As the maintenance time is delayed, the performance degradation of the components is aggravated, and the risk of failure continues to rise. The power supply may fail at a critical moment, resulting in test interruption; at the same time, the failure may cause damage to the aging station and the test piece, causing serious safety hazards. As the maintenance time is advanced, it is more likely to perform maintenance activities when the equipment has not failed, resulting in a waste of time and resources and an increase in maintenance costs. On the other hand, when using the aging station for testing, the test plan is usually prepared in advance. When the predictive maintenance time conflicts with the test plan, it will affect the test progress and increase the test time and labor costs. Since the test plan is formulated with reference to the maintenance plan, the degree of conflict between the predictive maintenance time and the plan can be expressed by the regular maintenance time. In summary, in order to balance various considerations, the above-mentioned cost-safety risk-test plan trade-off relationship is quantitatively expressed, the multi-objective solution of maintenance timing is carried out, and a predictive maintenance timing optimization model is constructed. Based on the constructed optimization model, the target maintenance time window of the switching power supply is finally solved.

[0048] In an optional embodiment, according to the regular maintenance time window, the predicted maintenance time window, the preset objective function and the constraint conditions, the method of solving the target maintenance time window of the switching power supply may include the following sub-steps: Sub-step 1: Set the objective function with maintenance time as the independent variable.

[0049] Among them, the objective function includes: the cost function representing the maintenance cost of the aging station , represents the risk function of the safety risk of experimental terminal and equipment damage and a planning function representing the impact of schedule conflicts with the experimental plan .

[0050] The three objective function independent variables are maintenance time, and the domains are Among them, the cost function is monotonically decreasing within the domain, and the risk function is monotonically increasing within the domain, the planning function It is related to the maintenance plan. Since the experimental risk is a strong constraint and the cost and plan are weak constraints, the quadratic form is used to fit the risk function and the linear form is used to fit the cost and plan function. The specific expression of the objective function can be shown as follows:

[0051]

[0052]

[0053] in, , , is the fitting coefficient, Domain , It is time for regular maintenance.

[0054] Sub-step 2: Initialize the particle swarm.

[0055] In sub-step 2, initialize the particle swarm and set particles, each particle group includes the following attribute information: used to characterize the location of the switch power supply maintenance time , used to characterize the speed of change of maintenance time during optimization and the individual best historical position used to characterize the optimal maintenance moment In addition, the best historical position of all particles is taken as the global best position , set the estimated maintenance interval window size to .

[0056] Sub-step 3: For each particle in the particle swarm, update the particle's velocity and position according to its velocity, individual historical best position, and global best position.

[0057] In the actual implementation process, the update can be achieved through the following formula:

[0058]

[0059] in, is the inertia weight, and is the learning factor, and It is a random number between 0 and 1.

[0060] Sub-step 4: Calculate the fitness of the particle based on the updated velocity, position, and objective function.

[0061] In the actual implementation process, the weighted sum can be used to represent the fitness of the current particle, and the fitness calculation formula can be .in For the The fitness of a particle, , , is the weight coefficient.

[0062] Sub-step 5: Based on the fitness and the fitness corresponding to the individual historical best position of the particle, the individual historical best position of the particle is updated.

[0063] For each particle in the particle swarm, if the fitness of the current particle position is better than the fitness of its individual historical best position, its position is updated to the individual historical best position; if it is better than the fitness of the global optimal position, its position is updated to the global optimal position.

[0064] Sub-steps 3 to 5 are executed for each particle in the particle swarm to obtain the individual best historical position of each particle.

[0065] Sub-step 6: Traverse the individual historical best position of each particle in the particle swarm, determine the maximum and minimum values ​​to generate the current maintenance time window.

[0066] Traverse the individual best historical positions of all particles , calculate its maximum and minimum values, and determine the current maintenance window , expressed as: .

[0067] By executing sub-steps 3 to 6, the calculation of the current maintenance time window can be completed once.

[0068] Sub-step 7: When the current maintenance time window meets the preset conditions, determine the current maintenance time window as the target maintenance time window of the switching power supply, recorded as .

[0069] If the current maintenance time window meets the preset conditions, then execute sub-step 7, and the maintenance time window of the switch power supply of the aging station is ; If the current maintenance time window does not meet the preset conditions, return to execute sub-step 3 to update the speed and position of each particle in the particle swarm according to the speed, individual historical best position and global best position, until sub-step 6 is executed to recalculate a current maintenance time window; again determine whether the recalculated current maintenance time window meets the preset conditions, if so, execute sub-step 7, if not, return to execute sub-step 3.

[0070] Repeat the process of sub-step 3 to sub-step 6 once or multiple times until the generated current maintenance time window meets the preset conditions and then execute step 7.

[0071] The preset condition can be set as follows: the difference between the upper limit and the lower limit of the current maintenance time window is less than or equal to the estimated maintenance interval window size, that is, .

[0072] In a more preferred embodiment, the method of solving the target maintenance time window of the switching power supply may also include: Sub-step 8: Correct the target maintenance time window based on thermal-related parameters. The thermal-related parameters include the surface temperature data of two key components, MOSFET and capacitor, in the primary switching power supply of the aging station. By referring to the instructions for use of the aging station, the rated operating temperature of MOSFET and capacitor can be obtained. The length of time that the surface temperature of MOSFET and capacitor exceeds their respective rated operating temperatures since the current startup is counted, which is called the overlimit time, and the correction rate is calculated The formula is:

[0073] Correction rate The target maintenance time window is corrected to obtain the corrected target maintenance time window, which is recorded as , the formula is:

[0074] This time window can also be called the predictive maintenance time window of the primary switching power supply of the aging station.

[0075] The embodiment of the present application provides a method for determining the timing of predictive maintenance of the isolated switching power supply at the front end of the aging station, which determines the regular maintenance timing of the switching power supply closest to the current moment; predicts the first timing of a failure of the switching power supply; determines the regular maintenance time window based on the regular maintenance timing; determines the predicted maintenance time window based on the first timing; solves the target maintenance time window of the switching power supply based on the regular maintenance time window, the predicted maintenance time window, the preset objective function and the constraints. Through the method provided by the embodiment of the present invention, the predictive maintenance timing of the switching power supply is comprehensively planned and decided by combining the regular maintenance timing and the fault prediction timing (i.e., the first timing), and the determined target maintenance timing of the switching power supply is objective and reliable.

[0076] Combine the following Figure 2 Taking a specific example, the predictive maintenance timing decision-making scheme for the front-end isolated switching power supply of the aging station provided in this application is described, which specifically includes the following steps: Step 201: Confirm the regular maintenance time window of the primary switch power supply of the aging station through documents such as the maintenance manual.

[0077] In the embodiment of the present application, the isolated switching power supply at the front end of the aging station is taken as an example to illustrate the primary switching power supply of the aging station.

[0078] In the actual implementation process, you can refer to the maintenance manual or instructions for use of the primary switch power supply of the aging station to determine the next scheduled maintenance time closest to the current moment. The specific method is as follows: 1.1. If there is a regular maintenance schedule in the maintenance manual, the scheduled maintenance time closest to the current time is taken as the regular maintenance time, recorded as .

[0079] 1.2. If there is no maintenance plan in the relevant documents, please refer to the user manual of the switching power supply and take its expected life as , then the regular maintenance time Set to the time when the service life is exhausted, which can be calculated by the following method:

[0080] in, It is the average daily usage time in hours.

[0081] Since the timing of scheduled maintenance has a certain degree of uncertainty, it is reasonable to carry out maintenance activities within a time window before or after this time. , then the regular maintenance time window can be expressed as:

[0082] Step 202: Determine a power failure prediction result interval by using an initial prediction technique.

[0083] The power supply (ie, switching power supply) fault prediction result interval is the predicted maintenance time window mentioned above.

[0084] Since the occurrence of failures is somewhat random, there are certain limitations in making maintenance timing decisions only through "regular maintenance". If a failure occurs before the scheduled maintenance time, it may cost manpower, material resources, and time, and affect the normal operation of the aging station; if a failure occurs after the scheduled maintenance time, early maintenance will lead to an increase in maintenance costs per unit time. In view of the fact that regular maintenance times at fixed intervals are prone to "over-maintenance" or "under-maintenance", research on predictive maintenance timing determination technology is carried out. Using trend prediction technology, the time when a primary switching power supply may fail in the future is predicted, and the predicted failure time is recorded as , then the fault prediction result interval can be expressed as:

[0085] Step 203: Determine whether there is an intersection between the scheduled maintenance time window and the fault prediction result interval; if so, execute step 204; if not, execute step 205.

[0086] Taking into account the regular maintenance time window and the predictive maintenance time window (i.e., the fault prediction result interval), multiple constraints are used to solve the predictive maintenance timing of the primary switch power supply of the aging station. Since the primary switch power supply is the core functional component of the aging station, the predictive maintenance timing is made as close to the regular maintenance timing as possible, while ensuring that the maintenance timing belongs to the fault prediction time interval, so as to reduce the impact of maintenance on the established test progress of the aging station.

[0087] Step 204: taking the intersection as the predictive maintenance time window.

[0088] The predictive maintenance time window is the target maintenance time window of the switching power supply mentioned above.

[0089] When the fault prediction result interval obtained by trend prediction overlaps with the scheduled maintenance time window, the predictive maintenance opportunity is the intersection of the two intervals. At this time, the predictive maintenance time window can be expressed as:

[0090] Step 205: Solve the predictive maintenance time window with multiple objectives.

[0091] When there is no intersection between the fault prediction result interval and the scheduled maintenance time window, the predictive maintenance timing is based on the fault prediction result interval, and the predictive maintenance timing is determined by comprehensively considering the characteristics of the aging station equipment and the application scenario. As the maintenance timing is delayed, the performance degradation of the components is aggravated, the risk of failure continues to rise, and the power supply may fail at a critical moment, resulting in test interruption; at the same time, the failure may cause damage to the aging station and the test piece, causing serious safety hazards. As the maintenance timing is advanced, it is more likely to perform maintenance activities when the equipment has not failed, resulting in a waste of time and resources and increasing maintenance costs. On the other hand, when using the aging station for testing, the test plan is usually prepared in advance. When the predictive maintenance timing conflicts with the test plan, it will affect the progress of the test and increase the test time and labor costs. Since the test plan is formulated with reference to the maintenance plan, the degree of conflict between the predictive maintenance timing and the plan can be expressed by the scheduled maintenance timing. In summary, in order to weigh various considerations, the above-mentioned cost-safety risk-test plan trade-off relationship is quantitatively expressed, the maintenance timing multi-objective solution is performed, and a predictive maintenance timing optimization model is constructed. The particle swarm algorithm is used to implement this process, and the specific method includes the following sub-steps: Sub-step 1: Determine the objective function to be optimized , and .

[0092] Objective Function , and They represent the various costs of aging station maintenance, the safety risks of test interruption and equipment damage, and the progress impact of conflicts with the test plan. The three objective function independent variables are maintenance time, and the definition domain is Among them, the cost function is monotonically decreasing within the domain, and the risk function is monotonically increasing within the domain, the planning function It is related to the maintenance plan. Since the experimental risk is a strong constraint and the cost and plan are weak constraints, the quadratic form is used to fit the risk function and the linear form is used to fit the cost and plan function, as shown below:

[0093]

[0094]

[0095] in, , , is the fitting coefficient, Domain , It is time for regular maintenance.

[0096] Sub-step 2: Initialize the particle swarm.

[0097] set up particles, each particle contains the following properties: position , that is, the maintenance time of the aging station's power supply once; speed , reflects the change in maintenance time during the optimization process; individual historical best position , which is the optimal maintenance time. In addition, the best historical position of all particles is taken as the global optimal position , set the estimated maintenance interval window size .

[0098] Sub-step 3: Calculate the particle fitness and use the weighted sum to represent the fitness of the current particle. The formula is: .in For the The fitness of a particle, , , is the weight coefficient.

[0099] Sub-step 4: Update the particle's speed and position according to the current speed, individual best position and global best position. The update method is:

[0100]

[0101] in, is the inertia weight, and is the learning factor, and It is a random number between 0 and 1.

[0102] Sub-step 5: Update the best position.

[0103] If the fitness of the current particle position is better than the fitness of its individual historical best position, its position is updated to the individual historical best position; if it is better than the fitness of the global optimal position, its position is updated to the global optimal position.

[0104] Sub-step 6: Traverse the individual best historical positions of all particles , calculate its maximum and minimum values, and determine the current maintenance window , the method is:

[0105] Sub-step 7: Repeat sub-step 3-sub-step 6 until the current maintenance window The loop terminates when the following conditions are met: At this time, the current maintenance window is the target maintenance time window, recorded as .

[0106] Sub-step 8: Correct the target maintenance time window based on thermal-related parameters. The thermal-related parameters include the surface temperature data of two key components, MOSFET and capacitor, in the primary switching power supply of the aging station. By referring to the instructions for use of the aging station, the rated operating temperature of MOSFET and capacitor can be obtained. The length of time that the surface temperature of MOSFET and capacitor exceeds their respective rated operating temperatures since the current startup is counted, which is called the overlimit time, and the correction rate is calculated , the formula is:

[0107] Correction rate The target maintenance time window is corrected to obtain the corrected target maintenance time window, which is recorded as , the formula is:

[0108] This time window can also be called the predictive maintenance time window of the primary switching power supply of the aging station.

[0109] Determine the predictive maintenance time window of the primary switch power supply of the aging station as .

[0110] Step 206: Decision on the timing of predictive maintenance of the primary power supply of the aging station.

[0111] In this step, after determining the predictive maintenance time window of the primary switch power supply of the aging station, any moment within the window can be determined as the predictive maintenance opportunity of the primary switch power supply of the aging station.

[0112] The method for determining the timing of predictive maintenance of the isolated switching power supply at the front end of the aging station provided in this specific example should include the expected life and maintenance plan of the primary switching power supply in the instructions for use or maintenance manual of the aging station, that is, the preventive maintenance plan and time window under fault-free conditions, which is called the "regular maintenance opportunity". Based on the fault prediction technology, the predicted time of the next fault of the primary switching power supply is obtained. Combining the regular maintenance opportunity and the fault prediction time, the predictive maintenance opportunity of the primary switching power supply is planned and decided, and the determined predictive maintenance opportunity is objective and reliable.

[0113] The embodiment of the present application also provides a method for predicting a fault of an isolated switching power supply at the front end of a burn-in station taking into account multiple degradation paths, which is used to predict the first time when a fault occurs in the switching power supply described in step 102 of the above embodiment.

[0114] As attached Figure 3 As shown, the method for predicting faults of isolated switching power supplies at the front end of a burn-in station considering multiple degradation paths in an embodiment of the present application includes the following steps: Step 301: performing dimensionality reduction processing on preset timing signals of multiple aging station switching power supplies, and extracting characteristic parameters.

[0115] The switching power supply of the aging station in the embodiment of the present application is a front-end isolated switching power supply, and can also be a primary switching power supply. The aging station can also be called a high-temperature aging station.

[0116] The aging station provided in the embodiment of the present application can perform non-destructive aging testing on the parts to be tested. In the embodiment of the present application, the feature extraction and life prediction of the switching power supply of the aging station are to ensure the safety of the parts to be tested.

[0117] Among them, characteristic parameters include but are not limited to: ripple voltage, average output voltage, inductor current peak-to-peak value, inductor current peak value, capacitor current peak-to-peak value, capacitor current peak value, circuit board temperature, heat flux density, heat flow rate, thermal conductivity, thermal diffusivity, etc.

[0118] The preset timing signal can be a timing signal of the current, voltage, etc. of the switching power supply. The multiple aging station switching power supplies are multiple aging station switching power supplies with different decay rates and different fault initiation degrees.

[0119] Step 302: Calculate the similarity of the performance degradation paths of the switch power supplies of each aging station according to the characteristic parameters of each preset timing signal.

[0120] In the actual implementation process, the DTW (Dynamic Time Warping) method can be used to evaluate the similarity of the paths between the switching power supplies of multiple aging stations with different decay rates and different fault initiation degrees (that is, the similarity of the performance degradation paths of the switching power supplies of each aging station), and on this basis, the K-Means performance degradation path clustering method is introduced to achieve fast and accurate classification of the performance degradation paths of the switching power supplies of the aging station (that is, the aging test station).

[0121] Optionally, a method for calculating the similarity of the performance degradation paths of the switch power supplies of each aging station based on the characteristic parameters of each preset timing signal may include the following sub-steps: Sub-step 1: construct parameter vectors for the characteristic parameters of each preset time series signal respectively; Sub-step 2: constructing a matrix grid according to each of the parameter vectors; For the performance parameter vector of the primary switching power supply sample of the aging station , (a, b are sample numbers, m, n are corresponding running cycle numbers), then construct a The matrix grid, matrix elements express and Distance between two points , each matrix element express and Alignment.

[0122] Sub-step 3: Based on the preset path boundary constraints, path continuity constraints, and path monotonicity constraints, find the regular minimum cost path through the matrix grid through multiple iterative adjustments.

[0123] Among them, the regularized minimum cost path can characterize the similarity of the performance degradation paths of the switching power supplies of each aging station.

[0124] When implementing sub-step 3, a regular path through the grid can be found based on the path boundary constraints, path continuity constraints, and path monotonicity constraints, and then used To express: 1. Then, based on these three constraints, the path is iterated multiple times until the path with the minimum cost is obtained. , in the denominator Used to compensate for regular paths of different lengths.

[0125] Path boundary condition constraints can be set as , , ensuring that the selected path must start from the common starting point of the sequence and end at the common ending point of the sequence.

[0126] The path continuity constraint can be set as follows: , then for the next point on the path Needs to be satisfied and ,ensure and Each coordinate in Appeared in.

[0127] The path monotonicity constraint can be set as follows: , then for the next point on the path Needs to be satisfied and ,limit The above points must be monotonically progressing over time.

[0128] The DTW method is used to calculate the similarity of characteristic time series trajectories such as ripple voltage, average output voltage, inductor current peak-to-peak value, inductor current peak value, capacitor current peak-to-peak value, capacitor current peak value, circuit board temperature, heat flux density, heat flow rate, thermal conductivity, thermal diffusivity, etc. between different aging station switching power supply samples (i.e., preset timing signals). Subsequently, the clustering method can be used to cluster the time series trajectories, so that the aging station switching power supplies can be classified according to the performance degradation trajectory.

[0129] Step 303: clustering each degradation path according to the similarity of the performance degradation paths of the switch power supplies of each aging station to obtain N degradation path sets.

[0130] N is a positive integer greater than or equal to 2. In the embodiment of the present application, N equals 2 as an example for illustration.

[0131] In an optional embodiment, clustering each degradation path according to the similarity of the performance degradation paths of the switch power supplies of each aging station to obtain N degradation path sets may include the following sub-steps: Sub-step 1: Randomly select K points from the regular minimum cost path as the centers of the initial cluster; Sub-step 2: For each point in the regularized minimum cost path, assign each point to the cluster closest to the center point; Sub-step 3: Update the center point of each cluster; An exemplary method of updating the center point of each cluster may be: for each cluster, calculating the average value of each point in the cluster; and updating the center point of the cluster to the location of the average value. The goal of updating the center point of the cluster is to minimize the squared error within the cluster.

[0132] Sub-step 4: For each point in the regularized minimum cost path, assign each point to the cluster closest to the updated center point; Sub-step 5: Determine whether the clustering stop condition is met. If not, return to sub-step 3 to update the center point of each cluster. If not reached, return to execute sub-step 3, sub-step 4 and sub-step 5, so as to update the center point again and cluster based on the updated center point.

[0133] The clustering stop condition can be flexibly set by those skilled in the art, and is not specifically limited in the embodiments of the present application. For example, the clustering stop condition can be set to: the change in the position of the cluster center point before and after the update is less than a preset value (the position of the cluster center point before and after the update no longer changes significantly), or it can be set to reach a set upper limit of the number of iterations.

[0134] This optional degradation path clustering method takes advantage of the time used for cluster centroid selection and the complexity of cluster overlapping space in K-Means, and takes the optimal point that actually exists in the data set as its centroid. Therefore, the characteristics of the trajectory corresponding to the centroid can be found, and the system samples are clustered through the performance degradation path similarity matrix of the aging station switching power supply, so as to realize the identification of the aging station switching power supply according to the performance degradation trajectory time series (i.e., the preset timing signal).

[0135] Sub-step 6: If it has been reached, the clusters of the updated center points are used as the N degenerate path sets.

[0136] Step 304: Establish N switch power supply life prediction models, and train the N switch power supply life prediction models according to the N degradation path sets respectively.

[0137] Among them, the switching power supply life prediction model includes: Input layer, Dense layer (i.e. dense layer), BiLSTM layer (i.e. bidirectional long short-term memory network layer), used to process multi-sensor monitoring signals, BiGRU layer (i.e. bidirectional gated recurrent layer), used to process operation condition data (i.e. transformation results after hidden representation), Concatenate layer (i.e. feature concatenation layer), used to fuse the outputs of BiLSTM and BiGRU layers, multi-dimensional feature maps, and output layer, used to output RUL prediction values.

[0138] In an optional embodiment, establishing N switch power supply life prediction models, and training the N switch power supply life prediction models according to N degradation path sets respectively may include the following sub-steps: Sub-step 1: Establish N switching power supply life prediction models.

[0139] When there are two performance degradation paths, two switching power supply life prediction models are established, and the switching power supply life prediction models are used to predict the remaining life of the switching power supply.

[0140] Sub-step 2: For each switching power supply life prediction model, the characteristic parameters corresponding to the degradation path in the corresponding degradation path set are used as model input.

[0141] Sub-step 3: Perform linear transformation on the input feature parameters in the fully connected layer and hide the transformation results; Among them, the input feature parameters can be regarded as multi-sensory monitoring data X i .

[0142] Sub-step 4: Construct a high-order vector based on the transformation result after the hidden representation, and send the high-order vector to the BiLSTM layer and BiGRU layer to obtain hidden feature maps of different dimensions; Among them, the number of stacked layers of BiLSTM layer and BiGRU layer is the same.

[0143] Sub-step 5: The feature vectors generated by merging the hidden features of different dimensions are input into two linear regression dense layers to generate RUL prediction values; Sub-step 6: Calculate the loss by using the error between the RUL prediction value and the RUL actual value as the loss function; Sub-step 7: updating the parameters of the switching power supply life prediction model according to the loss back propagation; Sub-step 8: Determine whether the switching power supply life prediction model after the updated parameters meets the preset accuracy; if so, determine that the training of the switching power supply life prediction model is completed; if not, return to the step of using the characteristic parameters corresponding to the degradation path in the corresponding degradation path set as the model input.

[0144] The prediction accuracy is used to evaluate the performance of the prediction model. The accuracy of the switching power supply life prediction model can be calculated using the following formula:

[0145] Among them, RUL is the actual RUL (remaining useful life); is the predicted RUL estimated by the prediction model; TUL is the actual total service life of the target circuit, which is defined as the total number of test cycles when the switching power supply of the aging station reaches the failure threshold.

[0146] The life prediction model of the switching power supply can be a multidimensional recurrent neural network (MDRNN) model. The multidimensional recurrent neural network uses momentum and adaptive learning rate to accelerate the convergence speed, and is proven to be superior to the classic stochastic gradient descent optimizer, thereby obtaining higher processing efficiency and prediction quality. The training process of the multidimensional recurrent neural network model includes: S1: extracting the characteristic parameters of the switching power supply of the aging station; S2: establishing the MDRNN multidimensional recurrent neural network model; S3: initializing the parameters of the MDRNN multidimensional recurrent neural network model; S4: iteratively training the MDRNN multidimensional recurrent neural network model based on the characteristic parameters in S1 for multiple times, and calculating the loss function after each training is completed, and adjusting the model parameters based on the calculated loss function; after multiple rounds of forward and back propagation training, after reaching the stop state, the trained MDRNN multidimensional recurrent neural network model can be used to predict the remaining life of the switching power supply.

[0147] Step 305: Based on the trained N switch power supply life prediction models, the life of the switch power supply of the aging station is predicted to obtain the remaining life of the switch power supply.

[0148] When predicting the life of the switching power supply of the aging station based on N switching power supply life prediction models, the degradation path category can be determined based on the timing signal of the switching power supply to be predicted, and the switching power supply life prediction model matching the category can be called to make an accurate prediction. The specific prediction process may include: determining the characteristic parameters of the timing signal of the switching power supply of the aging station to be predicted; determining the degradation category to which the switching power supply of the aging station to be predicted belongs; inputting the characteristic parameters into the switching power supply life prediction model of the matching category to predict the remaining service life of the switching power supply. The prediction results of this time can also be used as basic data for the accuracy of the subsequent evaluation results of the switch unit prediction model, specifically: calculating the prediction error of the model based on the remaining service life obtained from this prediction and the actual data of the remaining service life of the switching power supply; and evaluating the accuracy of the model prediction results based on the prediction error.

[0149] The embodiment of the present application provides a method for predicting faults of isolated switching power supplies at the front end of an aging station considering multiple degradation paths, which performs dimensionality reduction processing on preset timing signals of multiple switching power supplies of the aging station and extracts characteristic parameters; calculates the similarity of the performance degradation paths of the switching power supplies of each aging station based on the characteristic parameters of each preset timing signal; clusters each degradation path based on the similarity of the performance degradation paths of the switching power supplies of each aging station to obtain N degradation path sets; establishes N switching power supply life prediction models, and trains the N switching power supply life prediction models based on the N degradation path sets respectively; predicts the life of the switching power supply of the aging station based on the trained N switching power supply life prediction models to obtain the remaining life of the switching power supply. The switching power supply life prediction method of the aging station switching power supply, on the one hand, based on the MDRNN multi-dimensional recurrent neural network model, comprehensively considers the impact of the performance degradation path on the remaining service life prediction of the switching power supply, and can achieve high-precision life prediction; on the other hand, the failure mode is taken into consideration, the performance degradation path of the aging station switching power supply is identified, and the characteristic parameters of the aging station switching power supply with the same performance degradation path are brought into the same model for training and prediction, which is beneficial to improve the accuracy of the aging station switching power supply life prediction.

[0150] Figure 4 A structural block diagram of a device for determining predictive maintenance timing of an isolated switching power supply at the front end of a burn-in station to implement an embodiment of the present application.

[0151] The device for determining the predictive maintenance timing of the isolated switching power supply at the front end of the aging station provided in the embodiment of the present application includes the following functional modules: The timing determination module 401 is used to determine the periodic maintenance timing of the switching power supply closest to the current moment; wherein the switching power supply is an isolated switching power supply at the front end of the aging station; A prediction module 402, configured to predict a first timing when the switching power supply fails; A first window determination module 403, configured to determine a regular maintenance time window according to the regular maintenance opportunity; A second window determination module 404, configured to determine a predicted maintenance time window according to the first timing; The third window determination module 405 is used to solve the target maintenance time window of the switching power supply according to the regular maintenance time window, the predicted maintenance time window, a preset objective function and constraint conditions.

[0152] Optionally, the timing determination module includes: The first submodule is used to find the scheduled maintenance time closest to the current moment from the scheduled maintenance schedule in the maintenance manual of the switching power supply of the aging station; or The second submodule is used to determine the expected life of the switching power supply of the aging station; The third submodule is used to calculate the periodic maintenance opportunity of the switching power supply closest to the current moment according to the expected life and the average daily usage time of the switching power supply.

[0153] Optionally, the second window determining module includes: A fourth submodule, configured to determine the difference between the first timing and half of the preset time window parameter as the lower limit of the predicted maintenance time window; The fifth submodule is used to determine the sum of the first opportunity and half of the preset time window parameter as the upper limit value of the predicted maintenance time window.

[0154] Optionally, the third window determination module includes: A sixth submodule is used to determine whether the regular maintenance time window and the predicted maintenance time window have a time window intersection; A seventh submodule, for determining the intersection of the time windows as a target maintenance time window for the switching power supply, if any; The eighth submodule is used to determine the target maintenance time window of the switching power supply by multi-objective solution according to the regular maintenance time window, the predicted maintenance time window, the preset objective function and constraints if it does not exist.

[0155] Optionally, the eighth submodule includes: The first unit is used to set an objective function with the maintenance time as an independent variable, wherein the objective function includes: a cost function representing the maintenance cost of the aging station, a risk function representing the safety risk of damage to the experimental terminal and equipment, and a plan function representing the impact of the conflict schedule with the experimental plan; The second unit is used to initialize the particle swarm, wherein each particle swarm includes the following attribute information: a position for characterizing the maintenance time of the switch power supply, a speed for characterizing the change of the maintenance time in the optimization process, and an individual historical best position for characterizing the optimal maintenance time; A third unit is used for updating the speed and position of each particle in the particle group according to the speed, the individual historical best position and the global best position; A fourth unit is used to calculate the fitness of the particle according to the updated speed, position and objective function; A fifth unit is used for comparing the fitness with the fitness corresponding to the individual historical best position of the particle, and updating the individual historical best position of the particle; The sixth unit is used to traverse the individual historical best position of each particle in the particle group, determine the maximum value and the minimum value to generate the current maintenance time window; The seventh unit is configured to determine, when the current maintenance time window satisfies a preset condition, that the current maintenance time window is a target maintenance time window for the switching power supply.

[0156] Optionally, the eighth submodule further includes: The eighth unit is used to return to call the third unit to execute the operation of updating the speed and position of each particle in the particle group according to the speed, individual historical best position and global best position when the current maintenance time window does not meet the preset conditions.

[0157] The eighth submodule further includes: The ninth unit is used to correct the target maintenance time window based on the thermal related parameters of the aging station to obtain the final target maintenance time window, that is, the predictive maintenance time window.

[0158] Optionally, the preset condition includes: a difference between an upper limit value and a lower limit value of a current maintenance time window is less than or equal to an estimated maintenance interval window size.

[0159] The embodiments of the present application provide Figure 4 The predictive maintenance timing decision-making device for the isolated switching power supply at the front end of the aging station shown can achieve Figure 1 To avoid repetition, the various processes implemented by the method embodiment are not described here.

[0160] The embodiment of the present application provides a device for determining the predictive maintenance timing decision of the isolated switching power supply at the front end of the aging station, which determines the regular maintenance timing of the switching power supply closest to the current moment; predicts the first timing of the failure of the switching power supply; determines the regular maintenance time window based on the regular maintenance timing; determines the predicted maintenance time window based on the first timing; solves the target maintenance time window of the switching power supply based on the regular maintenance time window, the predicted maintenance time window, the preset objective function and the constraint conditions. Through the device provided by the embodiment of the present invention, the predictive maintenance timing of the switching power supply is comprehensively planned and decided by combining the regular maintenance timing and the fault prediction timing (i.e., the first timing), and the determined switching power supply maintenance timing is objective and reliable.

[0161] An embodiment of the present invention further provides an electronic device, including a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus.

[0162] Memory, used to store computer programs; The processor is used to implement the predictive maintenance opportunity determination method for the front-end isolated switching power supply of the aging station shown in the above method embodiment when executing the program stored in the memory.

[0163] The communication bus mentioned in the above terminal may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus may be divided into an address bus, a data bus, a control bus, etc.

[0164] The communication interface is used for communication between the above terminal and other devices.

[0165] The memory may include a random access memory (RAM) or a non-volatile memory, such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0166] In another embodiment provided by the present invention, a computer-readable storage medium is also provided, in which instructions are stored. When the computer-readable storage medium is executed on an electronic device, the electronic device implements the method for determining the predictive maintenance timing decision of the isolated switching power supply at the front end of the aging station as described in any of the above embodiments.

[0167] In another embodiment provided by the present invention, a computer program product containing instructions is also provided. When the computer program product is run on an electronic device, the electronic device implements the method for determining the predictive maintenance timing decision of the front-end isolated switching power supply of the aging station described in any of the above embodiments.

[0168] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0169] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for determining the timing of predictive maintenance of a front-end isolated switching power supply of a burn-in station, characterized in that: The method comprises: Determine the scheduled maintenance time of the switching power supply closest to the current moment; Predicting a first time when the switching power supply fails; Determine a regular maintenance time window based on the regular maintenance opportunity; Determining a predicted maintenance time window according to the first opportunity; The target maintenance time window of the switching power supply is solved according to the regular maintenance time window, the predicted maintenance time window, a preset objective function and constraints.

2. The method according to claim 1, characterized in that The steps to determine the most recent scheduled maintenance opportunity for the switching power supply include: Find the scheduled maintenance time closest to the current moment from the scheduled maintenance schedule in the maintenance manual of the switching power supply of the aging station; or, Determine the expected life of the switching power supply of the burn-in station; The scheduled maintenance opportunity of the switching power supply closest to the current moment is calculated based on the expected life and the average daily usage time of the switching power supply.

3. The method according to claim 1, characterized in that: The step of determining a predicted maintenance time window according to the first opportunity includes: Determine the difference between the first timing and half of the preset time window parameter as the lower limit value of the predicted maintenance time window; The sum of the first opportunity and half of the preset time window parameter is determined as the upper limit value of the predicted maintenance time window.

4. The method according to claim 1, characterized in that The step of solving the target maintenance time window of the switching power supply according to the regular maintenance time window, the predicted maintenance time window, the preset objective function and the constraint conditions comprises: Determine whether the scheduled maintenance time window and the predicted maintenance time window have a time window intersection; If so, determining the intersection of the time windows as the target maintenance time window of the switching power supply; If it does not exist, a target maintenance time window for the switching power supply is determined by multi-objective solution based on the regular maintenance time window, the predicted maintenance time window, a preset objective function and constraints.

5. The method according to claim 4, characterized in that Solving the target maintenance time window of the switching power supply according to the regular maintenance time window, the predicted maintenance time window, a preset objective function and constraints, including: Setting an objective function with maintenance time as an independent variable, wherein the objective function includes: a cost function representing the maintenance cost of the aging station, a risk function representing the safety risk of damage to the experimental terminal and equipment, and a plan function representing the impact of the schedule conflict with the experimental plan; Initialize a particle swarm, wherein each particle swarm includes the following attribute information: a position for characterizing the maintenance time of the switch power supply, a speed for characterizing the change of the maintenance time in the optimization process, and an individual historical best position for characterizing the optimal maintenance time; For each particle in the particle group, updating the speed and position of the particle according to the speed, the individual historical best position and the global best position; Calculating the fitness of the particle according to the updated speed, position and objective function; Based on the comparison between the fitness and the fitness corresponding to the individual historical best position of the particle, the individual historical best position of the particle is updated; Traversing the individual historical best position of each particle in the particle group, determining the maximum value and the minimum value to generate the current maintenance time window; When the current maintenance time window meets a preset condition, the current maintenance time window is determined as a target maintenance time window for the switching power supply.

6. The method according to claim 5, characterized in that The method further comprises: When the current maintenance time window does not meet the preset conditions, the process returns to the step of updating the speed and position of each particle in the particle swarm according to the speed, the individual historical best position and the global best position.

7. The method according to claim 5, characterized in that The preset condition includes: the difference between the upper limit value and the lower limit value of the current maintenance time window is less than or equal to the estimated maintenance interval window size.

8. A device for determining the predictive maintenance timing of an isolated switching power supply at the front end of a burn-in station, characterized in that: The device comprises: A timing determination module, used to determine the periodic maintenance timing of the switching power supply closest to the current moment; A prediction module, used for predicting a first time when the switching power supply fails; A first window determination module, used to determine a regular maintenance time window according to the regular maintenance opportunity; A second window determination module, used to determine a predicted maintenance time window according to the first opportunity; The third window determination module is used to solve the target maintenance time window of the switching power supply according to the regular maintenance time window, the predicted maintenance time window, a preset objective function and constraint conditions.

9. The device according to claim 8, characterized in that The timing determination module comprises: The first submodule is used to find the scheduled maintenance time closest to the current moment from the scheduled maintenance schedule in the maintenance manual of the switching power supply of the aging station; or The second submodule is used to determine the expected life of the switching power supply of the aging station; The third submodule is used to calculate the periodic maintenance opportunity of the switching power supply closest to the current moment according to the expected life and the average daily usage time of the switching power supply.

10. An electronic device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; Memory, used to store computer programs; The processor is used to implement the predictive maintenance timing decision-making method for the front-end isolated switching power supply of the aging station as described in any one of claims 1-8 when executing the program stored in the memory.

Images