A method for predicting future spare parts demand based on ship equipment maintenance history

Abstract

This invention discloses a method for predicting future spare parts demand based on historical maintenance records of ship equipment. It employs a Poisson process to simulate maintenance workload and a compound Poisson process to simulate the number of spare parts consumed during each maintenance, establishing a spare parts consumption model. Historical maintenance records are then substituted into the spare parts consumption model, and the future spare parts consumption quantity is calculated using either the mean method or the peak prediction method. The jump intensity parameter is estimated based on historical maintenance data. The probability of replacement maintenance is statistically analyzed using historical maintenance data as an estimate of the replacement maintenance probability, and the spare parts consumption quantity within the future time period is calculated. This serves as a reference for spare parts carrying capacity for the next ocean-going mission. This method minimizes the impact of complex and tedious reliability calculations, reliability data collection, and human error on the safety of ocean-going voyages, improving the efficiency and digital management of ship maintenance support.

Description

Technical Field

[0001] This invention belongs to the field of ship maintenance and support, and relates to the prediction of ship equipment maintenance workload. Specifically, it is a method for predicting future spare parts demand based on the historical maintenance records of ship equipment. Background Technology

[0002] Existing methods for predicting the demand for spare parts for ship equipment mostly employ traditional reliability data analysis methods, primarily focusing on Time Between Failures (TBF) data. This type of data is more suitable for data analysis at the component level during the development and testing phases of equipment. However, for the analysis and prediction of spare parts for maintenance during the operational phase of ship equipment, direct application is difficult due to the complexity of ship systems, the diversity of operating environments and mission profiles, and the inaccuracy of data acquisition. Using failure count data offers better fault tolerance and robustness; therefore, this paper proposes a method for predicting future spare parts demand based on the historical maintenance records of ship equipment. Summary of the Invention

[0003] The purpose of this invention is to overcome the shortcomings of existing technologies and to propose a method for predicting future spare parts demand based on the historical maintenance records of ship equipment, in order to provide accuracy in predicting future spare parts for ships and to maximize the availability of spare parts while ensuring the maintenance of the ship.

[0004] To solve the above-mentioned technical problems, the technical solution adopted by the present invention is as follows:

[0005] On the one hand, this invention provides a method for predicting future spare parts demand based on historical maintenance records of ship equipment, the specific steps of which are as follows:

[0006] Establish a spare parts consumption model, as follows:

[0007] Formula (5)

[0008] Spare parts consumption within time length t Expectations For the first i Repair method for this fault Indicates time t Timely maintenance workload E ( ) indicates expectation. For maintenance workload The jump strength parameter, p, is the probability of replacement repair. t The duration;

[0009] By substituting the ship's equipment maintenance history into the spare parts consumption model, the future spare parts consumption quantity is calculated using the mean method or the peak prediction method.

[0010] Furthermore, the method for establishing the spare parts consumption model is as follows:

[0011] Define time length t Maintenance work performed within N ( t It is an independent incremental process that obeys the jump strength parameter. The Poisson process, therefore the maintenance workload N ( t ) expectations As a statistical value of maintenance workload;

[0012] definition{ Y i ，i = 1, 2, 3… N ( t )} represents the quantity of spare parts consumed in each maintenance operation, and is a set of independent and identically distributed random variables independent of the stochastic process { N ( t ), t ≥ 0}, representing the expected number of spare parts consumed per maintenance. As a statistical value of the quantity of spare parts consumed;

[0013] Spare parts consumption within time t It conforms to a compound Poisson process, and the calculation formula is as follows:

[0014] Formula (1)

[0015] Using the expected consumption of spare parts within time t as the spare parts prediction amount, the spare parts consumption model of formula (5) is obtained.

[0016] Furthermore, the method for calculating spare parts consumption using the mean method is as follows:

[0017] The jump strength parameter was calculated based on historical maintenance data. estimated value ;

[0018] The probability of part replacement repair is estimated by statistically analyzing historical repair data.

[0019] Through estimated values Estimated value The formula for calculating the spare parts consumption within a future time period t is as follows:

[0020] .

[0021] Furthermore, maintenance workload The expected calculation formula yields the jump strength parameter. estimated value The calculation formula is as follows:

[0022] .

[0023] Furthermore, parameter probabilities p estimated value The calculation formula is as follows:

[0024] .

[0025] Furthermore, the method for calculating future spare parts consumption using peak forecasting is as follows:

[0026] Calculate the probability distribution of future spare parts consumption;

[0027] Calculate the number of spare parts to carry k The spare parts fulfillment rate at that moment;

[0028] Calculate the number of spare parts to carry k The spare parts utilization rate at that moment;

[0029] Select a quantity of spare parts with high spare parts fulfillment and utilization rates. k As for future spare parts needs.

[0030] Furthermore, record P i ( t () indicates time t internal consumption i The probability of carrying a spare part, then k The spare parts availability rate at this moment is:

[0031]

[0032] carry k The spare part utilization rate at time t for ≥1 spare part is:

[0033] .

[0034] On the other hand, the present invention provides an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the method for predicting future spare parts demand based on the ship equipment maintenance history as described above.

[0035] On the other hand, the present invention provides a non-transitory computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method for predicting future spare parts demand based on the historical maintenance history of ship equipment as described above.

[0036] On the other hand, the present invention provides a computer program product, including a computer program that, when executed by a processor, implements the method for predicting future spare parts demand based on the ship equipment maintenance history as described in any of the preceding claims.

[0037] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0038] This invention employs a Poisson process to simulate easily collected maintenance workload and a compound Poisson process to simulate the number of spare parts consumed in each maintenance operation. It transforms historical maintenance data from manual experience into big data processing, eliminating reliance on complex reliability calculations and tedious reliability data collection for ship equipment. Anyone can use the model of this invention to predict the spare parts demand for long-distance voyages, minimizing the impact of complex reliability calculations, tedious reliability data collection, and human experience-based misjudgments on the safety of long-distance voyages, and improving the efficiency and digital management of ship maintenance support. Attached Figure Description

[0039] Figure 1 This is a schematic diagram of the method for predicting future spare parts demand based on the historical maintenance records of ship equipment, as described in this invention.

[0040] Figure 2 This is a flowchart of the process of establishing a spare parts consumption model in this invention.

[0041] Figure 3 This is a probability prediction chart for the consumption of spare parts for a certain type of control valve.

[0042] Figure 4 This is the result of an analysis of the fulfillment rate and utilization rate of spare parts for a certain type of control valve. Detailed Implementation

[0043] The embodiments of the present invention will be described in further detail below with reference to the accompanying drawings and examples. The following examples are for illustrative purposes only and should not be construed as limiting the scope of the invention.

[0044] In the description of this invention, it should be noted that the terms "center," "longitudinal," "lateral," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0045] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "connected" and "linked" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0046] The method of the present invention was verified by conducting a case study on the consumption data of a certain type of control valve spare parts during the 6th and 7th ocean voyages of a certain ship. The maintenance record information during the ocean voyage was provided in the form of spreadsheets, as shown in Tables 1 and 2.

[0047] Table 1. Consumption data of a certain type of control valve spare parts during the 6th ocean-going mission of a certain ship.

[0048] Serial Number batch Ship serial number Failure date name major system Fault phenomenon Fault impact Cause of the fault Detection method Repair methods Repair unit Exclusion Date 1 6 1 2010 / 6 / 30 regulating valve electromechanical host crack Impact on tasks vibration artificial Replacement expert 2010 / 7 / 1 2 6 1 2010 / 6 / 30 regulating valve electromechanical host vibration Impact on safety Missing parts artificial In situ expert 2010 / 7 / 1 3 6 2 2010 / 7 / 4 regulating valve electromechanical host leakage Impact on tasks seal artificial In situ crew 2010 / 7 / 4 4 6 2 2010 / 7 / 5 regulating valve electromechanical host leakage Impact on tasks aging artificial Replacement expert 2010 / 7 / 5 5 6 1 2010 / 7 / 11 regulating valve electromechanical host leakage Impact on tasks corrosion artificial Replacement expert 2010 / 7 / 11 6 6 1 2010 / 7 / 15 regulating valve electromechanical host blockage Impact on tasks Dirt and blockage artificial In situ crew 2010 / 7 / 16 7 6 2 2010 / 8 / 17 regulating valve electromechanical host Peeling Impact on tasks vibration artificial In situ crew 2010 / 8 / 17 8 6 1 2010 / 8 / 26 regulating valve electromechanical host high temperature Impact on tasks cool down artificial In situ crew 2010 / 8 / 27 9 6 2 2010 / 8 / 30 regulating valve electromechanical host leakage Impact on tasks seal artificial In situ crew 2010 / 8 / 30 10 6 2 2010 / 9 / 25 regulating valve electromechanical host leakage Impact on tasks seal artificial In situ crew 2010 / 9 / 25 11 6 3 2010 / 10 / 15 regulating valve electromechanical host leakage Impact on tasks crack artificial Replacement crew 2010 / 10 / 15 12 6 2 2010 / 11 / 2 regulating valve electromechanical host leakage Impact on tasks corrosion artificial Replacement crew 2010 / 11 / 2 13 6 4 2010 / 11 / 10 regulating valve electromechanical host noise Impact on tasks seal artificial In situ crew 2010 / 11 / 11 14 6 2 2010 / 11 / 15 regulating valve electromechanical host leakage Impact on tasks Defective parts artificial Replacement crew 2010 / 11 / 15 15 6 1 2010 / 11 / 23 regulating valve electromechanical host blockage Impact on tasks Dirt and blockage artificial In situ crew 2010 / 11 / 25

[0049] Table 2. Consumption data of a certain type of control valve spare parts during the 7th ocean-going mission of a certain ship.

[0050] Serial Number batch Ship number Failure date name major system Fault phenomenon Fault impact Cause of the fault Detection method Repair methods Repair unit Exclusion Date 16 7 2 2011 / 2 / 17 regulating valve electromechanical host blockage Impact on tasks Dirt and blockage artificial In situ crew 2011 / 2 / 18 17 7 2 2011 / 2 / 18 regulating valve electromechanical host leakage Impact on tasks aging artificial Replacement crew 2011 / 2 / 18 18 7 4 2011 / 2 / 28 regulating valve electromechanical host Peeling Impact on tasks vibration artificial In situ expert 2011 / 2 / 28 19 7 2 2011 / 3 / 1 regulating valve electromechanical host crack Impact on tasks quality artificial Replacement crew 2011 / 3 / 1 20 7 3 2011 / 3 / 7 regulating valve electromechanical host leakage Impact on tasks aging artificial Replacement expert 2011 / 3 / 7 21 7 1 2011 / 3 / 11 regulating valve electromechanical host low temperature Impact on tasks seal artificial In situ expert 2011 / 3 / 12 22 7 1 2011 / 3 / 13 regulating valve electromechanical host high temperature Impact on tasks Dirt and blockage artificial In situ crew 2011 / 3 / 13 23 7 2 2011 / 4 / 5 regulating valve electromechanical host high temperature Impact on tasks seal artificial Replacement crew 2011 / 4 / 5 24 7 1 2011 / 4 / 13 regulating valve electromechanical host low temperature Impact on tasks aging artificial Replacement crew 2011 / 4 / 15 25 7 1 2011 / 4 / 15 regulating valve electromechanical host low pressure Impact on tasks leakage artificial In situ crew 2011 / 4 / 16 26 7 2 2011 / 4 / 27 regulating valve electromechanical host blockage Impact on tasks Dirt and blockage artificial In situ crew 2011 / 4 / 27 27 7 4 2011 / 5 / 2 regulating valve electromechanical host Peeling Impact on tasks aging artificial Replacement crew 2011 / 5 / 2 28 7 2 2011 / 5 / 12 regulating valve electromechanical host leakage Impact on tasks Wear artificial Replacement crew 2011 / 5 / 12 29 7 2 2011 / 8 / 24 regulating valve electromechanical host high temperature Impact on tasks Dirt and blockage artificial In situ crew 2011 / 8 / 24 30 7 2 2011 / 8 / 25 regulating valve electromechanical host Give way Impact on tasks seal artificial In situ crew 2011 / 8 / 2E

[0051] like Figure 1 As shown, this invention provides a method for predicting future spare parts demand based on historical maintenance records of ship equipment. The specific steps are as follows:

[0052] S100. Establish a spare parts consumption model, flowchart as follows: Figure 2 As shown, the specific process is as follows:

[0053] S110, Definition 1 (Definition of maintenance workload, Poisson process): Time length t Maintenance work performed within N ( t The number of maintenance operations is an independent incremental process that follows the jump intensity parameter. The Poisson process, therefore the maintenance workload N( t ) expectations As a statistical value of maintenance workload;

[0054] S120, Definition 2 (Spare Parts Consumption Definition, Composite Poisson Process): Define { Y i ，i = 1, 2, 3… N ( t )} represents the quantity of spare parts consumed in each maintenance operation, and is a set of independent and identically distributed random variables independent of the stochastic process { N ( t ), t ≥ 0}, representing the expected number of spare parts consumed per maintenance. As a statistical value of the quantity of spare parts consumed;

[0055] Spare parts consumption It conforms to a compound Poisson process, and the calculation formula is as follows:

[0056] Formula (1)

[0057] S130, Definition of Probability for Parts Replacement and Repair: When ship equipment malfunctions, the probability is used to determine the cause of the malfunction. p Perform replacement repairs with a probability of 1− p Perform in-situ repair operations.

[0058] Repair time and replacement time are relatively short compared to the interval between failures and can be ignored. Based on the above modeling assumptions and according to Definition 2, the spare parts consumption process for ship equipment maintenance can be verified. X(t) , t ≥ 0} is a composite Poisson process. In this case, the stochastic process in Definition 2 { Yi, i = 1, 2, 3…} is a Bernoulli process. Yi = 1 indicates that the fault was repaired by replacing the part, while Yi = 0 indicates repair in place.

[0059] Poisson process N ( t The parameter of ) is λ, and according to the mathematical expectation of the Poisson process, then N ( t The expectation is:

[0060] Formula (2)

[0061] Based on the statistics of historical maintenance records, the estimated value of parameter λ can be obtained.

[0062] Formula (3)

[0063] Similarly, based on historical repair records, whether the repair involved replacement or in-situ repair, and the Bernoulli process { Yi, i Properties and parametric probabilities of { =1, 2, 3…} p The estimated value is:

[0064] Formula (4)

[0065] S140. Obtain the spare parts consumption model. If the mean value prediction method is used, the average consumption amount is taken as the prediction result. The average consumption amount can be used as... express, Y i It is a Bernoulli process, according to the expectations of a Bernoulli process. He (1), N ( t )and Yi They are mutually independent, thus the expectation of the composite Poisson process can be obtained. As a spare parts consumption model:

[0066] Formula (5)

[0067] For spare parts consumption, This represents the amount of spare parts consumed within a time period t. For the first i Repair method for this fault Indicates time t Timely maintenance workload E Expressing expectations, For maintenance workload The jump strength parameter, p, is the probability of replacement repair. t The duration;

[0068] S200. By substituting the ship's equipment maintenance history into the spare parts consumption model, the future spare parts consumption quantity is calculated using the mean method or the peak prediction method.

[0069] The method for calculating spare parts consumption using the mean method is as follows:

[0070] S210, the jump strength parameter is calculated based on historical maintenance data. estimated value Using the spare parts data of a certain type of control valve from the 6th batch of ocean-going missions, the estimated value of λ can be obtained using formulas (2) and (3). It is 0.1049 per day.

[0071] S211. The probability of part replacement repair is estimated by statistically analyzing historical repair data. Using the spare parts data of a certain type of control valve from the 6th batch of ocean-going missions, the estimated value of parameter p can be obtained using formula (4). It is 0.4.

[0072] S212, through estimated values Estimated value The formula for calculating the spare parts consumption within a future time period t (188 days) is as follows:

[0073] =7.89.

[0074] In the 7th batch of ocean-going missions, the number of participating vessels was the same as in the 6th batch, and the duration was the same. The actual number of spare parts consumed in the 7th batch of ocean-going missions was 7, which is close to the predicted result of 7.89.

[0075] The method for calculating future spare parts consumption using peak forecasting is as follows:

[0076] S220, Calculate the probability distribution of future spare parts consumption;

[0077] According to formula (1), spare parts consumption is a complex Poisson process, so the probability of spare parts consumption can be expressed by the following formula:

[0078]

[0079] Where length t Maintenance work performed within N ( t Obey the strength parameter The Poisson process, { Y i ，i = 1,2, 3… N ( t The number of spare parts consumed in each maintenance is a Bernoulli process, and { Y i ，i = 1, 2, 3… N ( t Independent of stochastic processes { N ( t ), t Since ≥ 0, according to the properties of probability, we have:

[0080]

[0081] Right now:

[0082] This indicates the quantity of spare parts consumed. The probability of.

[0083] Using maintenance record data from the sixth batch of ocean-going missions, It is 0.1049. Since 0.4 is a constant, the peak probability is related to... Consistent, therefore can be drawn The probability prediction chart for spare parts consumption is 0.1049 (e.g.) Figure 3 As can be seen from this, the maximum probability of occurrence occurs when the number of spare parts consumed is 7. Therefore, the predicted result is 7, which is exactly the same as the actual number of spare parts consumed in the 7th batch of ocean missions, which is 7.

[0084] S221. Calculate the number of spare parts to carry. k The spare parts fulfillment rate at that moment;

[0085] remember P i ( t () indicates time t Consumption i The probability of carrying a spare part, then k The spare parts availability rate at this moment is:

[0086]

[0087] S222, Calculate the number of spare parts to carry k The spare parts utilization rate at that moment;

[0088] carry k The spare part utilization rate at time t for ≥1 spare part is:

[0089]

[0090] S223. Select a quantity of spare parts with both high spare parts fulfillment rate and spare parts utilization rate. k As for future spare parts needs.

[0091] Calculate S k ( t )and U k ( t The values ​​of ) are plotted in the same histogram, such as Figure 4 As shown: by Figure 4 It can be seen that when carrying 7 spare parts, the spare parts satisfaction rate is around 85%, while the utilization rate is 90%. To reduce risk, it is recommended to carry 9 spare parts, at which point the satisfaction rate is close to 95%, and the utilization rate is also greater than 80%. When carrying more than 10 spare parts, the satisfaction rate is very high, but the utilization rate drops significantly, resulting in low efficiency.

[0092] The above embodiments are for illustrative purposes only and are not intended to limit the scope of the invention. Although the invention has been described in detail with reference to the embodiments, those skilled in the art should understand that various combinations, modifications, or equivalent substitutions of the technical solutions of the invention do not depart from the spirit and scope of the invention and should be covered within the scope of the claims of the invention.

Claims

1. A method for predicting future spare parts demand based on historical maintenance records of ship equipment, characterized in that, The specific steps are as follows: Establish a spare parts consumption model, as follows: Official (5) Spare parts consumption within time length t Expectations For the first i Repair method for this fault Indicates time t Timely maintenance workload E ( ) indicates expectation. For maintenance workload The jump strength parameter, p, is the probability of replacement repair. t The duration; By substituting the ship equipment maintenance history into the spare parts consumption model, the future spare parts consumption quantity is calculated using the mean method or the peak prediction method. The method for establishing the spare parts consumption model is as follows: Define time length t Maintenance work performed within N ( t It is an independent incremental process that obeys the jump strength parameter. The Poisson process, in terms of maintenance workload N ( t ) expectations As a statistical value of maintenance workload; definition{ Y i ，i = 1, 2, 3… N ( t )} represents the quantity of spare parts consumed in each maintenance operation, and is a set of independent and identically distributed random variables independent of the stochastic process { N ( t ), t ≥ 0}, representing the expected number of spare parts consumed per maintenance. As a statistical value of the quantity of spare parts consumed; Spare parts consumption within time t It conforms to a compound Poisson process, and the calculation formula is as follows: Official (1) Using the expected consumption of spare parts within time t as the spare parts prediction amount, the spare parts consumption model of formula (5) is obtained.

2. The method for predicting future spare parts demand based on historical maintenance records of ship equipment as described in claim 1, characterized in that: The method for calculating spare parts consumption using the mean method is as follows: The jump strength parameter was calculated based on historical maintenance data. estimated value ; The probability of part replacement repair is estimated by statistically analyzing historical repair data. Through estimated values Estimated value The formula for calculating the spare parts consumption within a future time period t is as follows: 。 3. The method for predicting future spare parts demand based on historical maintenance records of ship equipment as described in claim 2, characterized in that: Maintenance workload The expected calculation formula yields the jump strength parameter. estimated value The calculation formula is as follows: 。 4. The method for predicting future spare parts demand based on historical maintenance records of ship equipment as described in claim 2, characterized in that: Parameter probability p estimated value The calculation formula is as follows: 。 5. The method for predicting future spare parts demand based on the historical maintenance history of ship equipment according to any one of claims 1-4, characterized in that, The method for calculating future spare parts consumption using peak forecasting is as follows: Calculate the probability distribution of future spare parts consumption; Calculate the number of spare parts to carry k The spare parts fulfillment rate at that moment; Calculate the number of spare parts to carry k The spare parts utilization rate at that moment; Select a quantity of spare parts with high spare parts fulfillment and utilization rates. k As for future spare parts needs.

6. The method for predicting future spare parts demand based on historical maintenance records of ship equipment as described in claim 5, characterized in that: remember P i ( t () indicates time t internal consumption i The probability of carrying a spare part, then k The spare parts availability rate at this moment is: carry k The spare part utilization rate at time t for ≥1 spare part is: 。 7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the method for predicting future spare parts demand based on the ship equipment maintenance history as described in any one of claims 1 to 6.

8. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the method for predicting future spare parts demand based on the maintenance history of ship equipment as described in any one of claims 1 to 6.

9. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the method for predicting future spare parts demand based on the maintenance history of ship equipment as described in any one of claims 1 to 6.

Images