Spare part consumption monitoring and scheduling method based on calorific value, equipment and medium

Abstract

The invention provides a spare part consumption monitoring and scheduling method and device based on a calorific value and a medium, and the method comprises the steps: obtaining historical spare part information of each department in a preset time period, and carrying out the preprocessing of the historical spare part information; dividing the spare part information according to the time ID and seasons, then performing seasonal spare part consumption analysis to obtain seasonal consumption data, and analyzing the spare part information according to the time ID and spare part consumption in different time periods within one day to obtain time period analysis data; constructing a spare part consumption calorific value library of each department based on the seasonal consumption data and the time period analysis data; establishing a calorific value model according to the spare part consumption calorific value library of each department, and generating a scheduling strategy based on the calorific value model. According to the technical scheme provided by the invention, real-time monitoring and early warning of spare part consumption can be realized.

Description

Technical Field

[0001] This document relates to the field of spare parts consumption technology, and in particular to a spare parts consumption monitoring and scheduling method, equipment and medium based on calorific value. Background Art

[0002] In the spare parts management system, reserving the necessary number of spare parts is the basis for ensuring the normal operation of the equipment. The management of spare parts in the existing technology only focuses on the spare parts surplus and consumption rate, and cannot present the actual emergency status of the spare parts. In addition, due to factors such as the temperature and humidity of the environment in which the equipment is located, the frequency of use and the vulnerability of the equipment are higher than normal values. In this case, the consumption of the spare parts will also increase accordingly, and the consumption of spare parts will also be different in different time periods of the day. Therefore, if the warning can only be issued based on the increase in current usage, and there is a lack of in-depth analysis and judgment of the overall situation, this will easily lead to the triggering of warnings in some normal cases of increased usage, thereby causing unnecessary panic. Therefore, a spare parts consumption monitoring and scheduling method that can consider multi-dimensional factors such as seasons and time periods is needed to solve the above problems. Summary of the invention

[0003] The present invention provides a spare parts consumption monitoring and scheduling method, device and medium based on calorific value. By collecting historical data and building a spare parts calorific value library, the problem of monitoring and scheduling according to the consumption quantity of different spare parts types, different seasons and different time periods is solved.

[0004] The present invention provides a spare parts consumption monitoring and scheduling method based on calorific value, comprising:

[0005] Obtain historical spare parts information of each department within a preset time period and pre-process the historical spare parts information, wherein the historical spare parts information includes: time ID, inventory quantity, spare parts ID and validity period;

[0006] Perform seasonal spare parts consumption analysis on the spare parts information after dividing it by season according to the time ID to obtain seasonal consumption data; analyze the spare parts consumption in different time periods of a day according to the time ID to obtain time period analysis data;

[0007] Building a spare parts consumption calorific value library for each department based on the seasonal consumption data and time period analysis data;

[0008] A calorific value model is established according to the calorific value library of spare parts consumption of each department, and a scheduling strategy is generated based on the calorific value model.

[0009] The present invention provides an electronic device, comprising:

[0010] processor; and,

[0011] A memory is arranged to store computer executable instructions, which, when executed, cause the processor to perform the steps of the above-mentioned spare parts consumption monitoring and scheduling method based on calorific value.

[0012] An embodiment of the present invention provides a storage medium for storing computer executable instructions, which, when executed, implement the steps of the above-mentioned spare parts consumption monitoring and scheduling method based on calorific value.

[0013] By adopting the embodiment of the present invention, the equipment usage and spare parts consumption patterns in different seasons are analyzed to avoid misjudgment caused by seasonal changes. The equipment usage frequency and spare parts consumption in different time periods of the day are considered to provide more fine-grained warnings. The thermal value library is established using historical data, and the warning threshold is adjusted dynamically to improve the accuracy of the warning. Combined with multi-dimensional data (such as temperature and humidity, production activities, etc.), a more comprehensive analysis and judgment is provided. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate one or more embodiments of this specification or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0015] Figure 1 The present invention is a flowchart of a method for monitoring and scheduling spare parts consumption based on calorific value according to an embodiment of the present invention. DETAILED DESCRIPTION

[0016] In order to enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the following will be combined with the drawings in one or more embodiments of this specification to clearly and completely describe the technical solutions in one or more embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on one or more embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this document.

[0017] Method Embodiment

[0018] According to an embodiment of the present invention, a spare parts consumption monitoring and scheduling method based on calorific value is provided. Figure 1 Flow chart of the spare parts consumption monitoring and scheduling method based on calorific value according to an embodiment of the present invention. Figure 1 As shown, the spare parts consumption monitoring and scheduling method based on calorific value in an embodiment of the present invention specifically includes:

[0019] S1. Obtain historical spare parts information of each department within a preset time period and pre-process the historical spare parts information, wherein the historical spare parts information includes: time ID, inventory quantity, spare parts ID and validity period;

[0020] Data collection and preprocessing in the embodiment of the present invention include: first, collecting equipment usage data and spare parts consumption data in different seasons and time periods. Data sources may include: equipment operation logs, spare parts usage records, environmental monitoring data (such as temperature and humidity), production plans, and actual production data; preprocessing the collected data, including data cleaning, missing value filling, data standardization and other operations.

[0021] S2, performing seasonal spare parts consumption analysis on the spare parts information after dividing it by season according to the time ID, obtaining seasonal consumption data, and analyzing the spare parts consumption of the spare parts information according to different time periods within a day according to the time ID, obtaining time period analysis data;

[0022] Obtaining seasonal consumption data specifically includes:

[0023] Perform seasonal analysis on historical data to identify spare parts consumption patterns in different seasons. The specific steps are as follows:

[0024] Data grouping: Group data by season (such as spring, summer, autumn, winter).

[0025] Statistical analysis: Calculate statistical indicators such as average spare parts consumption and standard deviation for each season.

[0026] Pattern Recognition: Identify seasonal patterns using time series analysis methods such as ARIMA models.

[0027] Obtaining time period analysis data specifically includes:

[0028] Analyze spare parts consumption at different times of the day to identify peak and trough periods.

[0029] The specific steps are as follows:

[0030] Data segmentation: divide the data of a day into time periods (such as morning, noon, evening, and night).

[0031] Statistical analysis: Calculate statistical indicators such as average spare parts consumption and standard deviation in each time period.

[0032] Pattern Recognition: Use time series analysis methods to identify consumption patterns over time periods.

[0033] S3. Building a spare parts consumption calorific value library for each department based on the seasonal consumption data and time period analysis data;

[0034] In the embodiment of the present invention, seasonal consumption data and time period analysis data obtained after analyzing historical spare parts information are used to establish a calorific value library, and the warning threshold is dynamically adjusted. The specific steps are as follows:

[0035] Data storage: Store the preprocessed data in the database and establish a calorific value library.

[0036] Model training: Use machine learning algorithms (such as random forest, support vector machine, etc.) to train prediction models to predict future spare parts consumption.

[0037] Threshold adjustment: Dynamically adjust the warning threshold based on the prediction results to ensure the accuracy of the warning.

[0038] The entropy weight method is used to calculate different weights between different regions:

[0039] W=[w 1 ,w 2 ,…w i ,…w n ];

[0040] where w i is the weight of the consumption in the ith region, n is the number of regions, and

[0041] For the same region, obtain the usage and consumption data of each spare part in different seasons. For different periods of the year, use the entropy weight method to calculate the different weights of each time period according to seasonal factors:

[0042] T=[t 1 ,t j …,t 4 ];

[0043] t j is the weight of the jth season;

[0044] For the same region, obtain the usage and consumption data of each spare part at different time periods within a day, divide the time periods into segments, and use the entropy weight method to calculate the different weights of each time period:

[0045] S=[s 1 ,s 2 ,…s k ,…s l ];

[0046] where s k is the weight of the kth time period, and l is the number of time periods a day is divided into;

[0047] The final calorific value is calculated according to the following formula;

[0048]

[0049] S4, establishing a calorific value model according to the spare parts consumption calorific value library of each department, and generating a scheduling strategy based on the calorific value model. The generating of the scheduling strategy based on the calorific value model specifically includes:

[0050] Compare the spare parts consumption calorific value library of each department with the preset threshold, and transfer the spare parts of the department whose spare parts consumption calorific value library is lower than the preset threshold to the department whose spare parts consumption calorific value library is higher than the preset threshold.

[0051] The spare parts consumption monitoring and scheduling method further includes: generating an emergency decision based on the early warning notification, specifically including: if the spare parts consumption calorific value libraries of each department are greater than a preset threshold after the spare parts of different departments are scheduled according to the spare parts consumption calorific value library, then adjusting the production plan or increasing the spare parts inventory.

[0052] Real-time monitoring of equipment operating status and spare parts consumption, combined with historical data and prediction models for early warning. The specific steps are as follows:

[0053] Real-time monitoring: Use sensors and IoT technology to monitor equipment operating status and spare parts consumption in real time.

[0054] Warning trigger: When the monitored consumption exceeds the dynamically adjusted warning threshold, an alarm is triggered.

[0055] Early warning processing: Take corresponding measures based on the early warning information, such as adjusting production plans, increasing spare parts inventory, etc.

[0056] The embodiment of the present invention solves the problem that the prior art usually only considers the inventory quantity of spare parts and simple demand forecast. The embodiment of the present invention introduces the concept of calorific value, and comprehensively considers multiple factors such as the importance, urgency, historical demand data, and equipment operating status of spare parts. The calculation formula of calorific value can be: [\text{calorific value}=\alpha\cdot\text{importance}+\beta\cdot\text{urgency}+\gamma\cdot\text{demand forecast}+\delta\cdot\text{equipment operating status}] where α, β, γ, δ are weight coefficients, which are adjusted according to the actual situation of the enterprise.

[0057] Traditional methods mostly implement monitoring and early warning by manually checking inventory and demand, which is lagging. By adopting the spare parts consumption monitoring and scheduling method based on calorific value in the embodiment of the present invention, the calorific value changes of spare parts in each department are monitored in real time by using Internet of Things (IoT) technology and big data analysis. When the calorific value of spare parts in a department exceeds the preset threshold, the system automatically issues an early warning.

[0058] Traditional methods are usually based on experience and simple rules when allocating spare parts between departments, which is inefficient. The embodiment of the present invention adopts an intelligent allocation algorithm, such as linear programming, genetic algorithm, etc., to optimize the spare parts allocation path and quantity. The algorithm goal is to balance the calorific value of spare parts in each department. The specific objective function can be expressed as: [\min\sum_{i=1}^{n}\left|\text{calorific value}_i-\text{target calorific value}\right|], where calorific value i is the calorific value of the spare parts of the i-th department;

[0059] In the traditional method, the generation of purchasing decisions is based on historical purchasing data and simple predictions. In the embodiment of the present invention, the real-time calorific value data and prediction models of each department are combined to formulate a more accurate purchasing plan. The purchasing decision model can be expressed as: [\text{purchase quantity}=f(\text{current inventory},\text{forecast demand},\text{calorific value})], where f is a comprehensive function that takes into account factors such as current inventory, forecast demand and calorific value.

[0060] In the embodiment of the present invention, the historical data collection and processing includes: the data source is obtained by equipment operation data, historical spare parts usage data, inventory data, procurement data, etc. Data processing uses ETL (Extract, Transform, Load) tools to clean, transform and load data to ensure the accuracy and consistency of data.

[0061] In the embodiment of the present invention, the calorific value calculation module outputs the calorific value of spare parts of each department by inputting data such as the importance, urgency, demand forecast, equipment operation status, etc. of spare parts of each department. The calorific value calculation script is written in Python language, and data processing libraries such as Pandas are used for data calculation.

[0062] Use IoT devices and sensors to collect equipment operating status and spare parts usage in real time. Based on the heat value threshold setting, when the spare parts heat value of a department exceeds the threshold, the system automatically sends an early warning notification (such as email, SMS, etc.). Select appropriate optimization algorithms according to the actual needs of the enterprise, such as linear programming, genetic algorithms, etc. Use Python's SciPy, PuLP and other optimization libraries to implement intelligent allocation algorithms. Generate spare parts allocation plans based on the algorithm calculation results, and automatically execute allocation operations through the ERP system.

[0063] The procurement decision support system uses machine learning algorithms (such as time series analysis, regression analysis, etc.) to predict the spare parts demand of each department. It combines the predicted demand with real-time calorific value data to generate an optimized procurement plan. The demand forecasting model is implemented using machine learning libraries such as Python's Scikit-learn and TensorFlow.

[0064] Integrate each module into the enterprise's ERP system to achieve seamless data connection and process automation. Design a friendly user interface to provide functions such as heat value monitoring, early warning notification, allocation plan and procurement plan. It can be developed using front-end frameworks (such as React, Vue.js) and back-end frameworks (such as Django, Flask).

[0065] The improvements of the embodiments of the present invention include:

[0066] (1) Improvement of forward-looking demand forecasting:

[0067] Traditional method: Procurement expansion is based solely on the number of scrapped products in the current year, lacking forecasts for future demand.

[0068] The method of the embodiment of the present invention: uses historical data and machine learning algorithms to perform demand forecasting, taking into account factors such as equipment usage frequency, work intensity, and technology updates, to predict future spare parts demand.

[0069] (2) Improvement of spare parts importance classification:

[0070] Traditional method: Failure to differentiate the importance of different spare parts may result in insufficient reserves of important spare parts or excessive purchase of minor spare parts.

[0071] The method of the embodiment of the present invention introduces a spare parts importance index, and performs classification management and procurement decisions based on the criticality of equipment operation and the impact of spare parts.

[0072] (3) Improvement of calorific value difference monitoring and allocation:

[0073] Traditional method: lack of real-time monitoring and allocation mechanism for spare parts supply and demand.

[0074] Improvement method: Through calorific value difference monitoring, timely discover the imbalance between spare parts supply and demand between different departments, and make intelligent allocation to ensure the balance of spare parts supply and demand in each department.

[0075] (4) Improvement of calorific value temperature rise monitoring of the whole system:

[0076] Traditional method: does not take into account the changing trend of the company's overall spare parts demand.

[0077] Improvement method: Monitor the heating trend of the calorific value of the entire system, make purchase plans in advance, and avoid the shortage of spare parts.

[0078] In summary, this algorithm can more intuitively show the current calorific value status based on in-depth calculation and analysis of historical data. It will collect and organize the usage of spare parts in different seasons and different working days in the past, and establish a huge calorific value library. Through the analysis of these historical data, the system can accurately identify the law of increased usage and determine whether the current calorific value change is a normal phenomenon. For example, when the system detects that the frequency of use of equipment in the current season has increased, combined with the law of spare parts consumption in the historical data of the season, it can be determined that the current spare parts calorific value is within the normal range. In this way, panic situations caused by misjudgment can be avoided, allowing staff to deal with the operating status of the equipment more calmly. At the same time, it can also prevent the waste of resources caused by unnecessary calls for procurement and other operations. Enterprises can reasonably arrange the procurement and inventory management of spare parts based on the accurate judgment of the system, improve the utilization efficiency of resources, and reduce production costs.

[0079] This system can provide a way to transfer parts to each other based on calorific value. The so-called transfer based on calorific value means that by evaluating and analyzing the calorific value of spare parts in each department, the department with abundant spare parts can be accurately transferred to the department with the risk of shortage. The calorific value here is not the physical calorific value in the traditional sense, but a quantitative indicator obtained after comprehensive consideration of multiple factors such as the importance, urgency and demand of spare parts. By allocating spare parts in this way, the actual needs of each department can be met more accurately. When the calorific value of a spare part in a department shows that there is an imminent risk of shortage, the system can quickly identify which departments have abundant spare parts and relatively low calorific value, so as to make timely transfers. In this way, not only can equipment failures caused by the lack of spare parts be avoided, but also spare parts resources can be fully utilized to avoid waste.

[0080] The core goal of this allocation method is to achieve a neutral calorific value. In the overall operation of the enterprise, the demand and supply of spare parts in various departments are constantly changing. By allocating according to the calorific value, the calorific value of spare parts in various departments can be kept in a relatively balanced state. When the calorific value of spare parts in a department is too high, it means that the department may face the risk of spare parts shortage. At this time, spare parts need to be allocated from departments with lower calorific values ​​to reduce their calorific value. Conversely, when the calorific value of spare parts in a department is too low, it can be considered to allocate excess spare parts to other departments in need to improve the overall spare parts utilization efficiency. When the overall spare parts calorific value reaches a threshold, the corresponding procurement plan can be provided according to the current calorific value of the spare parts in each department, so that the overall spare parts calorific value and the calorific value of each department can be restored to a reasonable level.

[0081] In short, this method of allocating spare parts based on calorific value provides a more scientific, accurate and efficient solution for the spare parts management of enterprises. It breaks the limitations of traditional allocation methods, makes full use of modern information technology and data analysis methods, realizes the optimal allocation of spare parts resources, and lays a solid foundation for the sustainable development of enterprises.

[0082] In the traditional spare parts procurement model, the annual procurement decision is mainly based on the number of scrapped parts that year. Although this method can meet the basic needs of enterprises to a certain extent, it has obvious limitations.

[0083] First, the purchase expansion is based solely on the number of scrapped parts in the current year, which lacks forward-looking consideration of future demand. The production and operation environment of an enterprise is dynamically changing, and factors such as the frequency of equipment use, work intensity, and technological updates may affect the demand for spare parts. If the purchase is based solely on the number of scrapped parts in the past, it is likely that the sudden increase in demand will not be met in time, resulting in a shortage of spare parts and affecting the normal production.

[0084] Second, this approach does not take into account the differences in importance between different spare parts. Some spare parts are essential to the normal operation of key equipment and may cause significant losses if they are missing, while some spare parts are relatively minor. The traditional approach cannot distinguish these differences and may result in insufficient reserves of important spare parts or excessive purchases of minor spare parts.

[0085] In contrast, this system uses the difference in calorific value and the calorific value rise of the entire system to remind purchasers, providing a more scientific and accurate method for spare parts procurement.

[0086] When the system detects a change in the difference in calorific value, it means that there is an imbalance in the supply and demand of spare parts between different departments. For example, if the calorific value of spare parts in one department increases, while the calorific value of spare parts in other departments is relatively low, the system can remind the procurement department to make targeted purchases and transfer spare parts from the abundant department to the department in need to achieve a balance between supply and demand.

[0087] The calorific value increase of the whole system is a more macro indicator, which reflects the overall trend of the spare parts demand of the whole enterprise. If the calorific value of the whole system shows an upward trend, it means that the demand for spare parts of the enterprise is increasing, which may be caused by the expansion of production scale, aging of equipment or technology upgrade. At this time, the procurement department can make procurement plans in advance according to this trend to avoid the shortage of spare parts.

[0088] By adopting the embodiments of the present invention, the following beneficial effects are achieved:

[0089] Avoid misjudgments due to seasonal changes by analyzing equipment usage and spare parts consumption patterns in different seasons. Provide more granular warnings by considering equipment usage frequency and spare parts consumption in different time periods of the day. Use historical data to establish a thermal value library, dynamically adjust the warning threshold, and improve the accuracy of warnings. Combine multi-dimensional data (such as temperature and humidity, production activities, etc.) to provide more comprehensive analysis and judgment.

[0090] Device Example 1

[0091] According to an embodiment of the present invention, there is provided an electronic device, including:

[0092] processor; and,

[0093] A memory is arranged to store computer executable instructions, which when executed cause the processor to perform the steps of the above method embodiments.

[0094] Device Example 2

[0095] According to an embodiment of the present invention, a storage medium is provided for storing computer executable instructions, which, when executed, implement the steps of the above-mentioned spare parts consumption monitoring and scheduling method based on calorific value.

[0096] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A spare parts consumption monitoring and scheduling method based on calorific value, characterized in that include: Obtain historical spare parts information of each department within a preset time period and pre-process the historical spare parts information, wherein the historical spare parts information includes: time ID, inventory quantity, spare parts ID and validity period; Perform seasonal spare parts consumption analysis on the spare parts information after dividing it by season according to the time ID to obtain seasonal consumption data; analyze the spare parts consumption in different time periods of a day according to the time ID to obtain time period analysis data; Building a spare parts consumption calorific value library for each department based on the seasonal consumption data and time period analysis data; A calorific value model is established according to the calorific value library of spare parts consumption of each department, and a scheduling strategy is generated based on the calorific value model.

2. The method according to claim 1, characterized in that The preprocessing of the historical spare parts information specifically includes: performing data cleaning, missing value filling and data standardization operations on the historical spare parts information.

3. The method according to claim 1, characterized in that The seasonal spare parts consumption analysis is performed after dividing the spare parts information into seasons according to the time information, and obtaining seasonal consumption data specifically includes: The data were grouped into spring, summer, autumn and winter seasons, and statistical indicators such as the average spare parts consumption and standard deviation were calculated for each season. Time series analysis methods were used to identify seasonal patterns and calculate the predicted consumption for each season.

4. The method according to claim 1, characterized in that The analyzing the spare parts information according to the spare parts consumption in different time periods within a day according to the time information, and obtaining the time period analysis data specifically includes: Divide the data of a day into time periods, calculate the statistical indicators of spare parts in each time period, use time series analysis methods to identify the consumption pattern within the time period, and calculate the predicted consumption for each time period in a day.

5. The method according to claim 1, characterized in that The construction of the spare parts consumption calorific value library of each department based on the seasonal consumption data and the time period analysis data specifically includes: The entropy weight method is used to calculate different weights between different regions: In=[in1,in2,…in i ,…In n ]; where w i is the weight of the consumption in the ith region, n is the number of regions, and For the same region, obtain the usage and consumption data of each spare part in different seasons. For different periods of the year, use the entropy weight method to calculate the different weights of each time period according to seasonal factors: T=[t1,t j …,t4]; t j is the weight of the jth season; For the same region, obtain the usage and consumption data of each spare part at different time periods within a day, divide the time periods into segments, and use the entropy weight method to calculate the different weights of each time period: S=[s1,s2,…s k ,…s l ]; where s k is the weight of the kth time period, and l is the number of time periods a day is divided into; The final calorific value is calculated according to the following formula; 6. The method according to claim 1, characterized in that The establishment of a calorific value model according to the spare parts consumption calorific value library of each department specifically includes: The prediction model is trained using machine learning algorithms to predict spare parts consumption within a preset time period in the future.

7. The method according to claim 1, characterized in that The generating of the scheduling strategy based on the calorific value model specifically includes: Compare the spare parts consumption calorific value library of each department with the preset threshold, and transfer the spare parts of the department whose spare parts consumption calorific value library is lower than the preset threshold to the department whose spare parts consumption calorific value library is higher than the preset threshold.

8. The method according to claim 1, characterized in that The spare parts consumption monitoring and scheduling method further includes: generating an emergency decision based on the early warning notification, specifically including: if the spare parts consumption calorific value libraries of each department are greater than a preset threshold after the spare parts of different departments are scheduled according to the spare parts consumption calorific value library, then adjusting the production plan or increasing the spare parts inventory.

9. An electronic device, comprising: processor; as well as, A memory arranged to store computer executable instructions, which, when executed, cause the processor to perform the steps of the spare parts consumption monitoring and scheduling method based on calorific value as claimed in any one of claims 1 to 8.

10. A storage medium for storing computer executable instructions, wherein the computer executable instructions, when executed, implement the steps of the spare parts consumption monitoring and scheduling method based on calorific value as claimed in any one of claims 1 to 8.

Images