An intelligent system for analyzing extended warranty of equipment

Abstract

This invention discloses an intelligent system for analyzing and extending equipment warranties, belonging to the field of computer and intelligent manufacturing technology. The system includes a basic equipment configuration module, a warranty extension analysis module, a profitability analysis module, a user maintenance willingness estimation module, an equipment usage status estimation module, and an equipment maintenance monitoring module. Equipment spare parts are divided into detectable and non-detectable spare parts. Intelligent sensors are used to continuously monitor detectable spare parts, constructing an aging model of the equipment. By constructing models of equipment aging status, equipment maintenance status, equipment usage status, and user maintenance willingness, the system analyzes the profitability of the manufacturing enterprise during the warranty period, intelligently derives a reasonable setting for warranty extension, and dynamically adjusts the equipment warranty period accordingly. It can calculate the warranty extension based on the user's emphasis on equipment maintenance, maximizing benefits for both the manufacturing enterprise and the user.

Description

Technical Field

[0001] This invention relates to an intelligent system for analyzing and extending the warranty period of equipment, belonging to the field of computer and intelligent manufacturing technology. Background Technology

[0002] The Industrial Internet (IIoT) is a new type of infrastructure, application model, and industrial ecosystem that deeply integrates next-generation information and communication technologies with the industrial economy. Through comprehensive connectivity of people, machines, things, and systems, it constructs a new manufacturing and service system covering the entire industrial chain and value chain, providing a pathway for the digital, networked, and intelligent development of industry and even the broader industrial sector. With the rapid development of the IIoT, more and more sensors are being deployed in intelligent devices, enabling users and manufacturers to obtain real-time operational status data. Based on this detailed data, they can extend the value chain, such as through equipment maintenance, lifespan prediction, and personalized services. Among these, predicting and setting the optimal equipment warranty period is a crucial task.

[0003] The warranty period for equipment is essentially a "commitment" made by the manufacturer to the user after delivery. After delivery, provided the user uses the equipment normally under specified conditions, repair or replacement services will be provided if the equipment malfunctions or parts are damaged. For equipment manufacturers, an excessively long warranty period can lead to increased maintenance costs and excessive spare parts inventory, creating a significant burden. Conversely, a warranty period that is too short may cause users to worry about product quality issues leading to decreased sales. Therefore, setting a reasonable warranty period allows companies to achieve a balance between costs and sales volume, maximizing efficiency. Furthermore, different users utilize equipment in different ways and with varying frequencies. A fixed warranty period is insufficient to accommodate diverse user scenarios, necessitating different warranty periods for different users.

[0004] Currently, fixed-term warranties remain the primary approach. Since equipment is no longer under the control of the manufacturer after delivery, it's difficult for the manufacturer to assess the user's usage and the equipment's operational status. With the widespread application of big data, the Industrial Internet of Things, intelligent systems, and sensors, a bridge can be built between users and manufacturers through trusted shared data and algorithmic models. This allows for the dynamic creation of a predictable and adjustable warranty period, satisfying both cost control for manufacturers and ensuring users receive maximum maintenance support. Summary of the Invention

[0005] The purpose of this invention is to address the shortcomings and deficiencies of existing technologies by solving the technical problem of how to analyze equipment condition and set the optimal extended warranty period, particularly issues such as fixed warranty periods, lack of consideration for the actual condition of spare parts during warranty extensions, and failure to consider user maintenance preferences. This invention proposes an intelligent system for analyzing and extending equipment warranties. This system constructs models of equipment aging status, equipment maintenance status, equipment usage status, and user maintenance preferences. It analyzes the profitability of manufacturers during the warranty period, intelligently derives a reasonable setting for warranty extensions, and dynamically adjusts the equipment warranty period accordingly to maximize benefits for both manufacturers and users.

[0006] The objective of this invention is achieved through the following technical solution.

[0007] An intelligent system for analyzing and extending equipment warranty periods includes a basic equipment configuration module, a warranty extension analysis module, a profitability analysis module, a user maintenance willingness estimation module, an equipment usage status estimation module, and an equipment maintenance status detection module.

[0008] 1. Basic Equipment Configuration Module: This module is responsible for equipment configuration, spare parts configuration, intelligent device sensor configuration, configuration of association between observable devices and monitoring sensors, configuration of stop maintenance conditions, and configuration of abnormal spare parts status.

[0009] Equipment configuration includes the equipment's standard warranty period, minimum maintenance frequency, and current maintenance period.

[0010] Spare parts configuration: Equipment spare parts can be divided into two categories: those that cannot be monitored by sensors and those that can be monitored by sensors, called monitorable spare parts accessories. Specifically, the relationship between the equipment (machine) and the monitorable spare parts accessories can be represented as a machine tuple:<accessory_1,accessory_2,...,accessory_N> , where N is the number of monitorable spare parts.

[0011] Smart sensor configuration: The device is equipped with smart sensors to monitor its operating status. Specifically, a smart sensor can be represented by a sensor tuple:<sensor_1,sensor_2,...,sensor_M> M represents the number of smart sensors. Specifically, the data that each smart sensor can detect can be represented as: <smart sensor ID, data type, generation interval, maximum value of information that can be detected, and minimum value of information that can be detected>.

[0012] Device status calculation rule configuration: Each smart sensor can only detect a portion of the device data. The relationship between sensors and spare parts can be represented as: <device number accessory_ID, smart sensor list sensor_list><a_1,a_2,...,a_M> The relationship between smart sensors (sensor_relation)<b_1,b_2,...,b_M> > where a_i∈(0,1), if a=0, it means it is unrelated to the sensor, and a=1 means it is related to the sensor; when a=1, b∈[0,1], representing the weight of the accessory_i state,

[0013] Because different sensors acquire data with varying ranges, time sequences, and contributions, data normalization is necessary. Specifically, the normalization method is: value_final = value_current / (value_max - value_min), where value_final is the normalized value, and value_current is the current data of the device. The status (Status(accessory_i)) of accessory_i is then shown in the following formula:

[0014]

[0015] Where j represents the j-th sensor.

[0016] Spare Parts Abnormal Status Configuration: During equipment use, due to differences in usage conditions, some abnormal situations (errors) may be detected. The occurrence of abnormal situations will cause the status of spare parts related to smart sensors to age faster.

[0017] Specifically, aging state tuples can be used to represent it:<error_ID,accessory_ID,aging> , where aging refers to accelerated aging.

[0018] Aging Status Classification Configuration: During the device's lifecycle, status information is collected. Based on the collected data and the Weibull distribution, the aging status of the device is predicted. Since the Weibull distribution is a continuous curve, to simplify calculations, the continuous status is transformed into discrete statuses, dividing the aging process into K states. Specifically, the aging status of each spare part can be represented as follows: <accessory_i,status_list<status_1,status_2,...,status_k> ,status_stop,status_interval>, where status_k represents the highest value of each status, status_stop represents the status of stopping maintenance, and status_interval represents the maintenance interval.

[0019] Maintenance stop condition configuration: When S components of the device reach the set threshold β, the manufacturer will stop maintenance. β is set according to actual needs; maintenance will stop when β components reach status_stop.

[0020] 2. Equipment maintenance monitoring module, including spare parts maintenance strategy, spare parts maintenance plan, and equipment status after maintenance.

[0021] Among them, the maintenance strategy for spare parts is as follows: Equipment maintenance can delay and reduce the aging of equipment to a certain extent. The maintenance of each spare part can be represented by a maintenance strategy tuple: <number, spare part, status, maintenance method, recovery, reward>.

[0022] Spare parts maintenance plan: A maintenance plan includes maintenance strategies for multiple spare parts. A maintenance plan can be represented as a tuple:<Strategy_1,Strategy_2,...,Strategy_L> , where L is the Lth maintenance strategy included in the maintenance plan. Each maintenance plan can only maintain one spare part once.

[0023] Post-maintenance equipment status: After executing a maintenance strategy, the aging status of spare parts will revert. After maintenance, the detectable status changes to Si = max(status_(i-2), status_i-recovery). `recovery` represents the recovered data. Since even after equipment maintenance, its status cannot be restored to its previous optimal state, the `max` function is used to take the maximum value between the two previous states and the recovered state.

[0024] 3. Equipment usage status estimation module, responsible for continuous monitoring of equipment status, continuous monitoring of equipment anomalies, and prediction of the current status of equipment.

[0025] Continuous monitoring of device status: Continuously detect the status of the device and obtain the data on the intelligent sensor. Further, since the data acquisition time intervals of each sensor are different, the data within a time period needs to be smoothed, that is, the average value is calculated, and the median, maximum value, and minimum value are recorded simultaneously.

[0026] Continuous monitoring of device anomalies: Let the last maintenance time be \(T_m\). Since the last maintenance, continuously monitor the anomalies of the device, and record the occurred anomalies, anomaly times, and accelerated aging status: <error.type, error.time, error.aging>, where aging is obtained from the "spare part anomaly status configuration". For accessor_i, its error list is error_list_i.

[0027] Estimate the current status of the device: Let the current time be \(T_c\).

[0028] The estimated device condition is: status_final(accessory_i) = Status(accessory_i) + ∑ a∈error_list_i (a.aginig * (a.time - \(T_m\)) / (\(T_c\) - \(T_m\))). This formula makes the anomalies closer in time have a greater impact on the status.

[0029] 4. User maintenance willingness estimation module, responsible for estimating the user's cooperation degree and the user's maintenance willingness.

[0030] Estimation of user cooperation degree: Record the normal maintenance frequency (non-fault repair) Maintain_number of the user after the device is delivered to the user. The production enterprise monitors the status of the device through the device. When the system enters the next maintenance cycle, the cycle start time is \(T_m\), and the production enterprise communicates and negotiates with the user. Set the time threshold as \(T_d\), and the time for the user to perform device maintenance is \(T_c\) after notification. Let the user's cooperation degree be cooperate. When \(T_c - T_m < T_d\), record cooperate = 1. When \(T_{md} - T_m > T_d\), the user's cooperation degree is cooperate = 1 - (\(T_{md} - T_m - T_d\)) / \(T_d\).

[0031] Estimation of user maintenance willingness: The user's maintenance willingness is determined by the maintenance frequency and the user's cooperation degree. The user's willingness value is Value_wish = a * Maintain_number / maintain_number_min + (1 - a) * cooperate. Here, a is the weight, and a ∈ [0, 1].

[0032] 5. Profit situation analysis module, responsible for analyzing the expected maintenance content and the expected profit situation.

[0033] Expected maintenance content analysis: Obtain the status of observable equipment status_final(accessory_i). Since each spare part is in a different state, the maintenance point of the equipment needs to be calculated based on the status of each equipment.

[0034] First, obtain the maintenance status `status_k` where `status_final(accessory_i)` is located. Based on the Weibull distribution, predict the possible status `status_j` of the spare part in the current warranty period `warranty_current`. Obtain the number of maintenance cycles required: `maintain_number = (jk) % maintain_interval`. Finally, based on the maintenance strategy for each spare part, obtain the maintenance details for that spare part.

[0035] Because the maintenance benefits are negative in some cases, the total cost is minimized.

[0036] Expected Profitability Analysis: Based on the content maintained, the corresponding maintenance costs are calculated. Expected profit can be expressed as:

[0037] 6. Warranty Extension Analysis Module, including predicting the maximum warranty period based on revenue, predicting the maximum warranty period based on the number of damages, and estimating warranty extension scenarios.

[0038] When a manufacturer repairs equipment, it needs to appropriately extend the warranty period.

[0039] Predict the maximum warranty period based on revenue: Assume the current warranty_balance = warranty_current. According to the method in the expected maintenance content analysis, increase the value of the current warranty_balance so that the reward_total in the expected profit situation is 0. The warranty_balance at this point is the equilibrium point.

[0040] Predict the longest warranty period based on the number of damaged parts: Based on the Weibull distribution, predict the time it takes for S parts to reach an unmaintainable state as status_time.

[0041] Estimated warranty extension: Take the minimum value of warranty_balance and status_time.

[0042] The relationship between the above modules is as follows:

[0043] The basic equipment configuration module provides the foundational configurations for other modules. The equipment maintenance monitoring module monitors the real-time status of the equipment, providing data support for the equipment usage status estimation module and the user maintenance willingness estimation module.

[0044] The equipment usage status estimation module is used to determine the equipment's status. The user maintenance willingness estimation module is used to predict the user's maintenance willingness. These two modules work together to analyze the manufacturer's profitability during the warranty period based on the model in the profitability analysis module. Based on the profitability analysis, the warranty extension analysis module predicts the extent of warranty extensions.

[0045] Beneficial effects

[0046] This invention, compared to existing technologies, incorporates user maintenance preferences and can calculate warranty extensions based on the user's emphasis on equipment maintenance. This invention categorizes equipment spare parts into detectable and non-detectable parts, utilizes intelligent sensors to continuously monitor detectable parts, constructs an aging model of the equipment, and ultimately calculates warranty extensions. By modifying the warranty period from a fixed term to dynamic adjustment, it helps manufacturers attract customers more effectively, provides users with better maintenance services, and reduces unnecessary losses. Attached Figure Description

[0047] Figure 1 This is a schematic diagram of the system described in this invention. Detailed Implementation

[0048] The present invention will be further described and illustrated below with reference to the accompanying drawings and embodiments.

[0049] like Figure 1 As shown, an intelligent system for analyzing and extending the warranty period of equipment includes a basic equipment configuration module, a warranty extension analysis module, a profitability analysis module, a user maintenance willingness estimation module, an equipment usage status estimation module, and an equipment maintenance status detection module.

[0050] 1. Basic Equipment Configuration Module

[0051] Equipment configuration: The standard warranty period for the equipment is 28 months, the minimum number of maintenance sessions is 3 (once every 6 months), and the current maintenance period is 28 months.

[0052] Spare parts configuration: The equipment contains many spare parts, which can be divided into two categories: those that cannot be monitored by sensors and those that can be monitored by sensors. The association between the equipment and the monitorable spare parts (accessory) can be represented as the equipment machine tuple <spare part 1, spare part 2>, where the number of monitorable spare parts is 2.

[0053] Smart Sensor Configuration: Smart sensors are installed in the device to monitor its operating status. The device has two sensors <sensor 1, sensor 2>. Sensor 1 has the following attributes: <1, double, 2 seconds, maximum value 40, minimum value 10>, and Sensor 2 has the following attributes: <2, double, 3 seconds, maximum value 100, minimum value 50>.

[0054] Equipment status calculation rule configuration: Each monitoring device can only detect a portion of the equipment data. The relationship between sensors and spare parts can be represented as <Spare Part 1, sensor_list<1, 1>, sensor_relation<0.4, 0.6>>, <Spare Part 2, sensor_list<1, 1>, sensor_relation<0.5, 0.5>>. Since different sensors contribute different data ranges, time sequences, and contribution levels, the data needs to be normalized. The normalization method is value_final = value_current / (value_max - value_min), where value_final is the normalized value and value_current is the current data of the device. The status (Status(accessory_i)) of accessory_i is then shown in the formula:

[0055]

[0056] Where j represents the j-th sensor.

[0057] Stop maintenance condition configuration: When two components of the equipment reach the set value, the manufacturer will force a stop maintenance.

[0058] Spare Parts Abnormal Status Configuration: During equipment operation, due to differences in usage conditions, some abnormal conditions (errors) may be detected. The occurrence of abnormal conditions will cause the spare parts associated with that group of sensors to age faster. <Abnormality 1, Spare Part 1, Aging 1>, <Abnormality 2, Spare Part 1, Aging 0.8>, <Abnormality 3, Spare Part 1, Aging 0.6>, <Abnormality 4, Spare Part 2, Aging 1.2>, <Abnormality 5, Spare Part 2, Aging 0.9>, <Abnormality 6, Spare Part 2, Aging 0.4>.

[0059] Aging Status Classification Configuration: During the device's lifecycle, status information is collected. Based on the collected data and the Weibull distribution, the device's aging status is predicted. Since the Weibull distribution is a continuous curve, to simplify calculations, the continuous status is transformed into discrete statuses, dividing the aging process into 10 states. The aging status of each spare part can be represented as <Spare Part 1, status_list>.<status_1,status_2,...,status_k> ,status_stop,status_interval>,<spare part 2,status_list<status_1,status_2,...,status_k> , status_stop, status_interval>.

[0060] 2. Equipment Maintenance Monitoring Module

[0061] Spare parts maintenance strategy: Equipment maintenance can, to some extent, delay and reduce the aging of equipment. The maintenance of each spare part can be represented by a maintenance strategy tuple: <part number, spare part, status, maintenance method, recovery, reward>.

[0062] <Maintenance Strategy 1, Spare Parts 1, 3, Maintenance Method, 1, 20>, <Maintenance Strategy 2, Spare Parts 1, 6, Maintenance Method, 2, 7>, <Maintenance Strategy 3, Spare Parts 2, 4, Maintenance Method, 1, 22>, <Maintenance Strategy 4, Spare Parts, 3, Maintenance Method, 1, 6>.

[0063] Spare parts maintenance plan: A maintenance plan includes maintenance strategies for multiple spare parts, maintenance plan 1 <repair strategy 1, repair strategy 3>, maintenance plan 2 <repair strategy 2, repair strategy 4>.

[0064] Post-maintenance equipment status: After implementing maintenance plan 2, the aging status of spare parts will be reversed.

[0065] 3. Equipment Usage Status Estimation Module

[0066] Continuously monitor the equipment's status: Continuously monitor the equipment's status and acquire data from the sensors. Since each sensor acquires data at different time intervals, the data within a time period needs to be smoothed, i.e., the average value is calculated, and the median, maximum value, and minimum value are recorded.

[0067] Continuously monitor the abnormal conditions of the device: The last maintenance time was \(T_m\). Since the last maintenance until now, continuously monitor the abnormal conditions of the device, and record the occurred abnormal conditions and abnormal times <error.type, error.time>. For accessor_i, its error list is error_list_i.

[0068] Estimate the device status: Let the current time be \(T_c\). The estimated device condition is: status_final(accessory_i) = Status(accessory_i) + ∑ a∈error_list_i (a.aginig *

[0069] (a.time - \(T_m\)) / (\(T_c\) - \(T_m\)). This formula makes the abnormal conditions closer in time have a greater impact on the status.

[0070] 4. User maintenance willingness estimation module

[0071] The current number of user maintenance: Record that since the device was delivered to the user, the normal maintenance frequency (non-fault repair) of the user is 2.

[0072] User cooperation degree: When the production enterprise monitors the status of the device through the device, when the system enters the next maintenance cycle, the starting time of the cycle is \(T_m\), and the production enterprise communicates and negotiates with the user. Set the time threshold as \(T_d\), and when the time for the user to perform maintenance is \(T_c\) after notification. Let the user cooperation degree be cooperate. When \(T_c - T_m < T_d\), record cooperate = 1. When \(T_md - T_m > T_d\), when the user cooperation degree is cooperate = 1 - (\(T_md - T_m - T_d\)) / \(T_d\).

[0073] Estimate the user's maintenance willingness: The user's maintenance willingness is determined by the maintenance frequency and the user cooperation degree. Then the user's willingness value is Value_wish = a * Maintain_number / maintain_number_min + (1 - a) * cooperate. Where a is 0.3.

[0074] 5. Profit situation analysis module:

[0075] Analysis of expected maintenance content: Obtain the observable device status status_final(accessory_i). Since each spare part is in a different state, it is necessary to calculate the maintenance points of the device according to the status of each device.

[0076] First, obtain the maintenance status `status_k` where `status_final(accessory_i)` resides. Second, based on the Weibull distribution, predict the possible status `status_j` of the spare part within the current warranty period `warranty_current`. Third, obtain the number of maintenance cycles required: `maintain_number = (jk) % maintain_interval`. Finally, based on the maintenance strategy for each spare part, obtain the maintenance details for that spare part.

[0077] Because the maintenance benefits are negative in some cases, the total cost is minimized.

[0078] Expected Profitability Analysis: Based on the content maintained, the corresponding maintenance costs are calculated. Expected profit can be expressed as...

[0079] 6. Warranty Extension Analysis Module:

[0080] When a manufacturer repairs equipment, it needs to appropriately extend the warranty period.

[0081] Predict the maximum warranty period based on revenue: Assume the current warranty_balance = warranty_current. According to the method in the expected maintenance content analysis, increase the value of the current warranty_balance so that the reward_total in the expected profit situation is 0. The warranty_balance at this point is the equilibrium point.

[0082] Predict the longest warranty period based on the number of damaged parts: Based on the Weibull distribution, predict the time it takes for S parts to reach an unmaintainable state as status_time.

[0083] Expected warranty extension: In practice, the minimum value of reward_time and status_time should be taken.

[0084] The above description is merely a preferred embodiment of the present invention, and the present invention should not be limited to the content disclosed in this embodiment and the accompanying drawings. Any equivalent or modified embodiments made without departing from the spirit of the present invention fall within the scope of protection of the present invention.

Claims

1. An intelligent system for analyzing and extending the warranty period of equipment, characterized in that, It includes a basic equipment configuration module, a warranty period extension analysis module, a profitability analysis module, a user maintenance willingness estimation module, an equipment usage status estimation module, and an equipment maintenance monitoring module; Among them, the basic equipment configuration module is responsible for equipment configuration, spare parts configuration, intelligent device sensor configuration, observable device and monitoring sensor association configuration, observable device and monitoring sensor association configuration, maintenance stop condition configuration and spare parts abnormal status configuration. The equipment maintenance monitoring module includes spare parts maintenance strategies, spare parts maintenance plans, and equipment status after maintenance; The equipment usage status estimation module is responsible for continuous monitoring of equipment status, continuous monitoring of equipment anomalies, and prediction of the current equipment status. The user maintenance willingness estimation module is responsible for estimating user cooperation level and user maintenance willingness. The profitability analysis module is responsible for analyzing the expected maintenance content and the expected profitability. The warranty extension analysis module is responsible for predicting the maximum warranty period based on revenue, predicting the maximum warranty period based on the number of damages, and estimating the warranty extension situation. The relationship between the above modules is as follows: The basic equipment configuration module provides the basic configuration for other modules; the equipment maintenance monitoring module is used to monitor the real-time status of the equipment and provide data support for the equipment usage status estimation module and the user maintenance willingness estimation module. The equipment usage status estimation module is used to determine the status of the equipment; the user maintenance willingness estimation module is used to estimate the user's maintenance willingness; these two modules work together to analyze the manufacturer's profitability during the warranty period based on the model in the profitability analysis module; based on the profitability analysis, the warranty period extension is predicted using the model in the warranty period extension analysis module. The basic equipment configuration module includes the equipment's standard warranty period, minimum maintenance frequency, and current maintenance period, among which: Spare parts configuration: Equipment spare parts are divided into two categories: those that cannot be monitored by sensors and those that can be monitored by sensors, called monitorable spare parts accessories; the relationship between equipment (machine) and monitorable spare parts accessories is represented by equipment tuples:<accessory_1,accessory_2,...,accessory_N> N is the number of monitorable spare parts; Smart sensor configuration: The device is equipped with smart sensors to monitor its operating status; the smart sensor is represented by a sensor tuple:<sensor_1, sensor_2,..., sensor_M> M represents the number of smart sensors; The data that each smart sensor can detect is represented as: <smart sensor ID, data type, generation interval, maximum value of information that can be detected, and minimum value of information that can be detected>. Device status calculation rule configuration: Each smart sensor can only detect a portion of the device data. The relationship between sensors and spare parts is represented as: <device number accessory_ID, smart sensor list sensor_list><a_1,a_2,...,a_M> The relationship between smart sensors (sensor_relation)<b_1,b_2,...,b_M> >, among which If a=0, it means it is unrelated to the sensor; if a=1, it means it is related to the sensor. In the case of a=1, , representing the weight relative to the state of accessory_i. Simultaneously, the data needs to be normalized using the following method: value_final = value_current / (value_max - value_min), where value_final is the normalized value, value_current is the current data of the device, and then the state of accessory_i. As shown in the following formula: Where j represents the j-th sensor; Spare part abnormal status configuration: represented by aging status tuples:<error_ID,accessory_ID,aging> aging refers to accelerated aging; Aging status classification configuration: During the device's lifecycle, status information is collected. Based on the collected data and the Weibull distribution, the device's aging status is predicted. Since the Weibull distribution is a continuous curve, the continuous status is transformed into discrete statuses, dividing the aging situation into K states. The aging status of each spare part is represented as follows: <accessory_i,status_list<status_1,status_2,...,status_k> ,status_stop,status_interval>, where status_k represents the highest value of each state, status_stop represents the state where maintenance has stopped, and status_interval represents the maintenance interval; Maintenance stop condition configuration: When S components of the device reach the set threshold β, the manufacturer will stop maintenance; β is set according to actual needs, and maintenance will stop when β components reach status_stop. In the equipment usage status estimation module: Continuous equipment status monitoring: Continuously monitor the status of the equipment and acquire data from the smart sensors; each sensor acquires data at different time intervals, so the data within a time period needs to be smoothed, the average value is calculated, and the median, maximum value, and minimum value are recorded. Continuous equipment anomaly monitoring: Let the time since the last maintenance be T_m; continuously monitor equipment anomalies from the last maintenance to the present, and record the anomalies, their times, and accelerated aging conditions.<error.type,error.time,error.aging> The aging parameter is obtained from the "Spare Parts Abnormal Status Configuration"; for accessor_i, its error list is error_list_i. Predict the current state of the equipment: Let the current time be... ; The equipment condition is estimated as follows: This means that the closer the anomaly is, the greater its impact on the state; In the user maintenance willingness estimation module: User cooperation level estimation: Record the normal maintenance frequency Maintain_number after the equipment is delivered to the user; the manufacturer monitors the equipment status through the equipment, and when the system enters the next maintenance cycle, the cycle start time is T_m, and the manufacturer communicates and negotiates with the user; set the time threshold T_d, and the time for the user to perform equipment maintenance is T_c after notification; let the user's cooperation level be cooperative, when T_c-T_m < T_d, record cooperative=1, when T_md-T_m>T_d, the user's cooperation level is cooperative=1-(T_md - T_m - T_d) / T_d; User maintenance willingness estimation: User maintenance willingness is determined by maintenance frequency and user cooperation level. The user's willingness value is Value_wish = a* Maintain_number / maintain_number_min + (1-a)* cooperate; where a is the weight. ; In the profitability analysis module: Expected maintenance content analysis: Obtain the observable device status status_final(accessory_i). Since each spare part is in a different state, calculate the maintenance point of the device based on the status of each device. First, obtain the maintenance status `status_k` where `status_final(accessory_i)` is located; based on the Weibull distribution, predict the possible status `status_j` of the spare part in the current warranty period `warranty_current`; obtain the number of maintenance required `maintain_number = (j - k)% maintain_interval`; finally, based on the maintenance strategy for each spare part, obtain the maintenance content for that spare part; `Reward(accessory_i) =` ; Expected Profitability Analysis: Based on the content maintained, the corresponding maintenance costs are calculated; the expected profit is expressed as: Reward_total = Value_wish * ; In the warranty extension analysis module: Predict the maximum warranty period based on revenue: Assume the current warranty_balance = warranty_current. Based on the expected maintenance content, increase the value of the current warranty_balance so that the expected revenue in the Reward_total is 0. At this point, the warranty_balance is the equilibrium point. Predict the maximum warranty period based on the number of damaged parts: Based on the Weibull distribution, predict the time it takes for S parts to reach an unmaintainable state as status_time; Estimated warranty extension: Take the minimum value of warranty_balance and status_time.

2. The intelligent system for analyzing and extending the warranty period of equipment as described in claim 1, characterized in that, The equipment maintenance monitoring module includes: Spare parts maintenance strategy: For the maintenance of each spare part, the maintenance strategy tuple is used: <number, spare part, status, maintenance method, recovery, reward>. Spare parts maintenance plan: A maintenance plan includes maintenance strategies for multiple spare parts; a maintenance plan is represented as a tuple:<Strategy_1,Strategy_2,...,Strategy_L> , where L is the Lth maintenance strategy included in the maintenance plan; each maintenance plan can only maintain one spare part once; Post-maintenance equipment status: After executing a maintenance strategy, the aging status of spare parts will be rolled back; after maintenance, the detectable status changes to Si = max(status_(i-2),status_i-recovery); recovery is the data after recovery; the max function is used to take the maximum value of the two previous states of the current state and the recovered state.

Images