A predictive maintenance method and system applied to warehousing logistics system

Abstract

The present invention discloses a predictive maintenance method and system applied to a warehousing and logistics system, which relates to the technical field of warehousing and logistics, including calculating the continuous operating time, cumulative operating time, cumulative load, continuous load and the average of the number of days from the last maintenance or repair of various equipment when they are damaged, and further calculating the weight coefficient of the corresponding average; calculating the risk coefficient of each equipment and the risk threshold of various equipment; calculating the weight coefficient of the temperature, speed and load average; calculating the maintenance risk coefficient and maintenance risk threshold of the risk equipment; and predicting the potential failure and life of the equipment by specifically analyzing the working records and real-time working status of each equipment, avoiding production interruption caused by equipment failure, and improving the efficiency of warehousing and logistics.

Description

Technical Field

[0001] The present invention relates to the technical field of warehousing and logistics, and in particular to a predictive maintenance method and system applied to a warehousing and logistics system. Background Art

[0002] Warehousing and logistics systems are an indispensable and important part of modern enterprise operations, responsible for the storage, management and transportation of goods. However, with the rapid development of the logistics industry and the continuous expansion of the scale of warehousing and logistics systems, equipment maintenance and management have become one of the important issues facing enterprises. Traditional maintenance methods usually involve repairing equipment after it fails, which not only causes downtime and production losses, but also increases maintenance costs and reduces equipment life. Therefore, predictive maintenance methods have gradually become an important development direction for the maintenance of warehousing and logistics systems.

[0003] In the Chinese invention application with application publication number CN111832993A, a predictive maintenance method for a warehousing logistics system and related components are disclosed, including obtaining historical business data and historical field data of the warehousing logistics system, and

[0004] Generate FMEA forms with historical field data, and then evaluate the risk factor of the warehousing and logistics system; select key subsystems with high risk factors, key components with high risk factors, and problems with key components; set data acquisition nodes according to the selected key subsystems, key components, and problems with key components; use data acquisition nodes to collect field data, and filter out field data containing fault data for storage and preprocessing to obtain a sample set, and divide the sample set into a training set, a validation set, and a test set; input the training set into a stacked autoencoder neural network model for learning; use the stacked autoencoder neural network model to perform predictive maintenance on the warehousing and logistics system.

[0005] In the above invention application, the historical business data and historical field data are used to query the failure time, operation and maintenance cost, and asset depreciation rate of each node equipment in the warehousing and logistics system, determine the maintenance cost of each node equipment, and select the node equipment with the highest operation and maintenance cost and the node equipment with the highest input-output ratio as candidate node equipment. This is a method for determining the equipment risk factor based on maintenance cost. However, in practice, it is not only equipment with high operation and maintenance costs that needs to be paid attention to. Damage to some equipment with low operation and maintenance costs will still lead to the paralysis of the entire warehousing and logistics system, thereby affecting logistics efficiency.

[0006] To this end, the present invention provides a predictive maintenance method and system applied to a warehousing logistics system. Summary of the invention

[0007] 1. Technical issues to be resolved

[0008] In view of the deficiencies in the prior art, the present invention provides a predictive maintenance method and system for a warehousing and logistics system. By specifically analyzing the working records and real-time working status of each device, the present invention can better understand the operating characteristics and failure modes of the equipment. Such data can help predict the potential failures and life of the equipment, promptly discover and deal with equipment failures or performance degradation problems, extend the service life of the equipment, improve the reliability and stability of the equipment, avoid production interruptions due to equipment failures, help maintain production continuity, and improve warehousing and logistics efficiency, thereby solving the technical problems recorded in the background technology.

[0009] (II) Technical solution

[0010] To achieve the above objectives, the present invention is implemented through the following technical solutions: a predictive maintenance method and system applied to a warehousing logistics system, comprising the following steps:

[0011] Get the continuous running time of each device when it is damaged , Cumulative running time , cumulative load , continuous load and the number of days since the last maintenance or repair , calculate the mean continuous running time of various equipment damage , Cumulative running time average , Cumulative load average , continuous load average and the average number of days since the last maintenance or repair , and further calculate the weight coefficient corresponding to the mean and ;

[0012] Get the real-time continuous running time of each device , Cumulative running time , cumulative load , continuous load and the number of days since the last maintenance or repair , calculate the risk factor of each device and risk thresholds for various devices , when the risk factor of the equipment Exceeds the corresponding risk threshold When a risk occurs, a risk warning for the corresponding equipment is issued;

[0013] Use sensors to periodically collect real-time temperatures of all devices , real-time speed and real-time load , calculate the average temperature of various devices , speed mean And load mean , and further calculate the mean temperature , speed mean And load mean The weight coefficient and ;

[0014] Get the real-time temperature of the device corresponding to the risk threshold , real-time speed and real-time load , calculate the maintenance risk coefficient of risk equipment and maintenance risk threshold , when the risk factor of each risk equipment maintenance Exceeds its corresponding maintenance risk threshold When necessary, a maintenance risk warning will be issued to the corresponding equipment, and the corresponding equipment will be repaired and maintained.

[0015] Furthermore, the continuous running time of each device when it is damaged is obtained , cumulative running time , cumulative load , continuous load and the number of days since the last maintenance or repair After linear normalization, the mean continuous operation time of various equipment damage is calculated. , Cumulative running time average , Cumulative load average , continuous load average and the average number of days since the last maintenance or repair :

[0016] ;

[0017] in, Indicates the type number of the device. Indicates the sequence number between the same type of devices. Indicates the number of damages. a, b, c Is a positive integer.

[0018] Furthermore, the mean continuous operation time of various equipment damage is obtained. , Cumulative running time average , Cumulative load average , continuous load average and the average number of days since the last maintenance or repair , calculate the weight coefficients of each mean in turn and :

[0019] ;

[0020] The corresponding weight coefficients of each mean and The calculation formula is as above.

[0021] Furthermore, obtain the real-time continuous running time of each device , cumulative running time , cumulative load , continuous load and the number of days since the last maintenance or repair , after linear normalization, the risk coefficient of each device is calculated :

[0022] ;

[0023] Corresponding risk factors for each device The calculation formula is as above.

[0024] Further, obtain the risk factor of each device , real-time update calculation to obtain the risk threshold of various devices :

[0025] ;

[0026] When the risk factor of the equipment Exceeds the corresponding risk threshold When a risk occurs, a risk warning for the corresponding equipment is issued.

[0027] Furthermore, sensors are used to periodically collect the real-time temperature of all devices. , real-time speed and real-time load After dimensionless processing, the mean temperature of various devices is calculated , speed mean And load mean :

[0028] ;

[0029] in, Indicates the type number of the device. Indicates the sequence number between the same type of devices. Indicates the number of damages. a, b, m Is a positive integer.

[0030] Furthermore, the average temperature of various devices is obtained , speed mean And load mean , calculate the mean temperature in turn , speed mean And load mean The weight coefficient and :

[0031] ;

[0032] The corresponding temperature mean , speed mean And load mean The weight coefficient and The calculation formula is as above.

[0033] Furthermore, the real-time temperature of the device corresponding to the risk threshold is obtained. , real-time speed and real-time load After linear normalization, the maintenance risk coefficient of risk equipment is calculated. :

[0034] ;

[0035] Corresponding risk equipment maintenance risk factor The calculation formula is as above.

[0036] Further, obtain the risk factor of risk equipment maintenance , real-time update calculation to obtain the maintenance risk threshold of various equipment :

[0037] ;

[0038] When the risk factor of each risk equipment maintenance Exceeds its corresponding maintenance risk threshold When necessary, a maintenance risk warning will be issued to the corresponding equipment, and the corresponding equipment will be repaired and maintained.

[0039] A predictive maintenance system applied to a warehousing logistics system, characterized in that it includes:

[0040] Cumulative standard setting module to obtain the continuous running time of each device when it is damaged , Cumulative running time , cumulative load , continuous load and the number of days since the last maintenance or repair , calculate the mean continuous running time of various equipment damage , Cumulative running time average , Cumulative load average , continuous load average and the average number of days since the last maintenance or repair , and further calculate the weight coefficient corresponding to the mean, and ;

[0041] Risk analysis module, obtains the real-time continuous operation time of each device , Cumulative running time , cumulative load , continuous load and the number of days since the last maintenance or repair , calculate the risk factor of each device and risk thresholds for various devices , when the risk factor of the equipment Exceeds the corresponding risk threshold When a risk occurs, a risk warning for the corresponding equipment is issued;

[0042] Real-time standard setting module, using sensors to periodically collect the real-time temperature of all devices , real-time speed and real-time load , calculate the average temperature of various devices , speed mean And load mean , and further calculate the mean temperature , speed mean And load mean The weight coefficient of and ;

[0043] Maintenance analysis module, obtains the real-time temperature of the equipment corresponding to the risk threshold , real-time speed and real-time load , calculate the maintenance risk coefficient of risk equipment and maintenance risk threshold , when the risk factor of each risk equipment maintenance Exceeds its corresponding maintenance risk threshold When necessary, a maintenance risk warning will be issued to the corresponding equipment, and the corresponding equipment will be repaired and maintained.

[0044] The present invention provides a predictive maintenance method and system applied to a warehousing logistics system, which has the following beneficial effects:

[0045] 1. Obtain the continuous operation time of each device when it is damaged based on the working records of each device in the warehousing logistics system , cumulative running time , cumulative load , continuous load and the number of days since the last maintenance or repair , calculate the mean continuous running time of various equipment damage , Cumulative running time average , Cumulative load average , continuous load average and the average number of days since the last maintenance or repair , and further calculate the weight coefficient corresponding to the mean and , we can better understand the operating characteristics and failure modes of the equipment. These data can help predict the potential failure and life of the equipment, so that measures can be taken in advance for maintenance and replacement to avoid equipment failure during operation.

[0046] 2. Obtain the real-time continuous running time of each device , cumulative running time , cumulative load , continuous load and the number of days since the last maintenance or repair , calculate the risk factor of each device and risk thresholds for various devices , when the risk factor of the equipment Exceeds the corresponding risk threshold When a risk occurs, a risk warning for the corresponding equipment will be issued. According to the risk factor and importance of the equipment, high-risk equipment can be handled first, maintenance personnel and materials can be arranged reasonably, and resource utilization efficiency can be improved.

[0047] 3. Periodically collect the real-time temperature of all devices by using sensors , real-time speed and real-time load , calculate the average temperature of various devices , speed mean And load mean , and further calculate the mean temperature , speed mean And load mean The weight coefficient of and , can promptly discover and deal with equipment failures or performance degradation problems, extend the service life of the equipment, and improve the reliability and stability of the equipment.

[0048] 4. Obtain the real-time temperature of the device corresponding to the risk threshold , real-time speed and real-time load , calculate the maintenance risk coefficient of risk equipment and maintenance risk threshold , when the risk factor of each risk equipment maintenance Exceeds its corresponding maintenance risk threshold When the equipment is in a critical condition, it can issue maintenance risk warnings to the corresponding equipment and carry out maintenance on the corresponding equipment, which can avoid production interruptions caused by equipment failure, help maintain production continuity, and improve warehousing and logistics efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 A schematic diagram of a process of a predictive maintenance method applied to a warehousing logistics system according to the present invention;

[0050] Figure 2 The present invention is a schematic diagram of the structure of a predictive maintenance system applied to a warehousing logistics system. DETAILED DESCRIPTION

[0051] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0052] See also Figure 1 The present invention provides a predictive maintenance method applied to a warehousing logistics system, comprising the following steps:

[0053] Step 1: Obtain the continuous running time of each device when it is damaged , Cumulative running time , cumulative load , continuous load and the number of days since the last maintenance or repair , calculate the mean continuous running time of various equipment damage , Cumulative running time average , Cumulative load average , continuous load average and the average number of days since the last maintenance or repair , and further calculate the weight coefficient corresponding to the mean and ;

[0054] The step 1 includes the following contents:

[0055] Step 101: Obtain the continuous operation time of each device when it is damaged based on the working records of each device in the warehousing logistics system , Cumulative running time , cumulative load , continuous load and the number of days since the last maintenance or repair .

[0056] Among them, it should be noted that:

[0057] Continuous running time Refers to the running time of the equipment in continuous working state. If the equipment runs continuously for too long, it may cause overheating and increased wear of the equipment, which may lead to failure.

[0058] Cumulative running time It refers to the total time that the equipment has been working from the beginning to the present. It is an important indicator to measure the life and aging of the equipment. By monitoring and analyzing the cumulative operating time, the remaining life of the equipment and possible failures can be predicted.

[0059] Continuous load It refers to the cumulative load that the equipment bears under continuous working conditions. The continuous load is related to the continuous working time and load intensity of the equipment. If the equipment operates in an overload or overload state for a long time, it will cause excessive wear and failure of the equipment.

[0060] Cumulative load It refers to the total load that the equipment has borne from the beginning of its operation to now. The cumulative load is an important parameter to measure the working intensity and wear degree of the equipment, and can predict the wear degree of the equipment and possible failures.

[0061] Days since last maintenance or repair It refers to the number of days that have passed since the equipment was last maintained or repaired. If the equipment is not maintained or repaired for a long time, it may cause equipment failure and performance degradation.

[0062] Step 102: Obtain the continuous running time of each device when it is damaged , Cumulative running time , cumulative load , continuous load and the number of days since the last maintenance or repair After linear normalization, the mean continuous operation time of various equipment damage is calculated. , Cumulative running time average , Cumulative load average , continuous load average and the average number of days since the last maintenance or repair :

[0063]

[0064] in, Indicates the type number of the device. Indicates the sequence number between the same type of devices. Indicates the number of damages. a, b, c Is a positive integer.

[0065] Step 103: Obtain the mean continuous operation time when various devices are damaged , Cumulative running time average , Cumulative load average , continuous load average and the average number of days since the last maintenance or repair , calculate the weight coefficients of each mean in turn and :

[0066] ;

[0067] The corresponding weight coefficients of each mean and The calculation formula is as above.

[0068] When using, combine the contents in steps 101 to 103:

[0069] By obtaining the continuous operation time of each device when it is damaged based on the working records of each device in the warehouse logistics system , Cumulative running time , cumulative load , continuous load and the number of days since the last maintenance or repair , calculate the mean continuous running time of various equipment damage , Cumulative running time average , Cumulative load average , continuous load average and the average number of days since the last maintenance or repair , and further calculate the weight coefficient corresponding to the mean and , we can better understand the operating characteristics and failure modes of the equipment. These data can help predict the potential failure and life of the equipment, so that measures can be taken in advance for maintenance and replacement to avoid equipment failure during operation.

[0070] Step 2: Get the real-time continuous running time of each device , Cumulative running time , cumulative load , continuous load and the number of days since the last maintenance or repair , calculate the risk factor of each device and risk thresholds for various devices , when the risk factor of the equipment Exceeds the corresponding risk threshold When a risk occurs, a risk warning for the corresponding equipment is issued.

[0071] The step 2 includes the following contents:

[0072] Step 201: Obtain the real-time continuous running time of each device , Cumulative running time , cumulative load , continuous load and the number of days since the last maintenance or repair , after linear normalization, the risk coefficient of each device is calculated :

[0073] ;

[0074] Corresponding risk factors for each device The calculation formula is as above.

[0075] Step 202: Obtain the risk factor of each device , real-time update calculation to obtain the risk threshold of various devices :

[0076] ;

[0077] When the risk factor of the equipment Exceeds the corresponding risk threshold When a risk occurs, a risk warning for the corresponding equipment is issued.

[0078] When using, combine the contents in steps 201 and 202:

[0079] By obtaining the real-time continuous running time of each device , Cumulative running time , cumulative load , continuous load and the number of days since the last maintenance or repair , calculate the risk factor of each device and risk thresholds for various devices , when the risk factor of the equipment Exceeds the corresponding risk threshold When a risk occurs, a risk warning for the corresponding equipment will be issued. According to the risk factor and importance of the equipment, high-risk equipment can be handled first, maintenance personnel and materials can be arranged reasonably, and resource utilization efficiency can be improved.

[0080] Step 3: Use sensors to periodically collect real-time temperatures of all devices , real-time speed and real-time load After dimensionless processing, the mean temperature of various devices is calculated , speed mean And load mean , and further calculate the mean temperature , speed mean And load mean The weight coefficient of and .

[0081] The step three includes the following contents:

[0082] Step 301: Use sensors to periodically collect real-time temperatures of all devices , real-time speed and real-time load After dimensionless processing, the mean temperature of various devices is calculated , speed mean And load mean :

[0083] ;

[0084] in, Indicates the type number of the device. Indicates the sequence number between the same type of devices. Indicates the number of damages. a, b, m Is a positive integer.

[0085] It should be noted that the real-time temperature is periodically detected by the temperature sensor, the real-time speed is periodically detected by the speed sensor, and the real-time load is periodically detected by the gravity sensor. The periodic detection time can be set Any minute.

[0086] Step 302: Obtain the average temperature of various devices , speed mean And load mean , calculate the mean temperature in turn , speed mean And load mean The weight coefficient and :

[0087] ;

[0088] The corresponding temperature mean , speed mean And load mean The weight coefficient and The calculation formula is as above.

[0089] When used, combine the contents in steps 301 and 302:

[0090] By using sensors to periodically collect the real-time temperature of all devices , real-time speed and real-time load , calculate the average temperature of various devices , speed mean And load mean , and further calculate the mean temperature , speed mean And load mean The weight coefficient and , can promptly discover and deal with equipment failures or performance degradation problems, extend the service life of the equipment, and improve the reliability and stability of the equipment.

[0091] Furthermore, the real-time temperature of the device corresponding to the risk threshold is obtained. , real-time speed and real-time load , calculate the maintenance risk coefficient of risk equipment and maintenance risk threshold , when the risk factor of each risk equipment maintenance Exceeds its corresponding maintenance risk threshold When necessary, a maintenance risk warning will be issued to the corresponding equipment, and the corresponding equipment will be repaired and maintained.

[0092] The step 4 includes the following contents:

[0093] Step 401: Obtain the real-time temperature of the device corresponding to the risk threshold , real-time speed and real-time load After linear normalization, the maintenance risk coefficient of risk equipment is calculated. :

[0094] ;

[0095] Corresponding risk equipment maintenance risk factor The calculation formula is as above

[0096] Step 402: Obtain risk factor for risky equipment maintenance , real-time update calculation to obtain the maintenance risk threshold of various equipment :

[0097] ;

[0098] When the risk factor of each risk equipment maintenance Exceeds its corresponding maintenance risk threshold When necessary, a maintenance risk warning will be issued to the corresponding equipment, and the corresponding equipment will be repaired and maintained.

[0099] When using, combine the contents in steps 401 to 402:

[0100] By obtaining the real-time temperature of the device corresponding to the risk threshold , real-time speed and real-time load , calculate the maintenance risk coefficient of risk equipment and maintenance risk threshold , when the risk factor of each risk equipment maintenance Exceeds its corresponding maintenance risk threshold When the equipment is in a critical condition, it can issue maintenance risk warnings to the corresponding equipment and carry out maintenance on the corresponding equipment, which can avoid production interruptions caused by equipment failure, help maintain production continuity, and improve warehousing and logistics efficiency.

[0101] See also Figure 2 , a predictive maintenance system applied to a warehousing logistics system, comprising:

[0102] Cumulative standard setting module to obtain the continuous running time of each device when it is damaged , Cumulative running time , cumulative load , continuous load and the number of days since the last maintenance or repair , calculate the mean continuous running time of various equipment damage , Cumulative running time average , Cumulative load average , continuous load average and the average number of days since the last maintenance or repair , and further calculate the weight coefficient corresponding to the mean, and ;

[0103] Risk analysis module, obtains the real-time continuous operation time of each device , Cumulative running time , cumulative load , continuous load and the number of days since the last maintenance or repair , calculate the risk factor of each device and risk thresholds for various devices , when the risk factor of the equipment Exceeds the corresponding risk threshold When a risk occurs, a risk warning for the corresponding equipment is issued;

[0104] Real-time standard setting module, using sensors to periodically collect the real-time temperature of all devices , real-time speed and real-time load , calculate the average temperature of various devices , speed mean And load mean , and further calculate the mean temperature , speed mean And load mean The weight coefficient of and ;

[0105] Maintenance analysis module, obtains the real-time temperature of the equipment corresponding to the risk threshold , real-time speed and real-time load , calculate the maintenance risk coefficient of risk equipment and maintenance risk threshold , when the risk factor of each risk equipment maintenance Exceeds its corresponding maintenance risk threshold When necessary, a maintenance risk warning will be issued to the corresponding equipment, and the corresponding equipment will be repaired and maintained.

[0106] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A predictive maintenance system applied to a warehousing logistics system, characterized in that: including: Cumulative standard setting module to obtain the continuous running time of each device when it is damaged , cumulative running time , cumulative load , continuous load and the number of days since the last maintenance or repair , calculate the mean continuous running time of various equipment damage , Cumulative running time average , Cumulative load average , continuous load average and the average number of days since the last maintenance or repair , and further calculate the weight coefficient corresponding to the mean and ; Risk analysis module, obtains the real-time continuous operation time of each device , cumulative running time , cumulative load , continuous load and the number of days since the last maintenance or repair , calculate the risk factor of each device and risk thresholds for various devices , when the risk factor of the equipment Exceeds the corresponding risk threshold When a risk occurs, a risk warning for the corresponding equipment is issued; Real-time standard setting module, using sensors to periodically collect the real-time temperature of all devices , real-time speed and real-time load , calculate the average temperature of various devices , speed mean And load mean , and further calculate the mean temperature , speed mean And load mean The weight coefficient of and ; Maintenance analysis module, obtains the real-time temperature of the equipment corresponding to the risk threshold , real-time speed and real-time load , calculate the maintenance risk coefficient of risk equipment and maintenance risk threshold , when the risk factor of each risk equipment maintenance Exceeds its corresponding maintenance risk threshold When necessary, issue maintenance risk warnings to the corresponding equipment and perform maintenance on the corresponding equipment; Get the continuous running time of each device when it is damaged , cumulative running time , cumulative load , continuous load and the number of days since the last maintenance or repair After linear normalization, the mean continuous operation time of various equipment damage is calculated. , Cumulative running time average , Cumulative load average , continuous load average and the average number of days since the last maintenance or repair : ； in, Indicates the type number of the device. Indicates the sequence number between the same type of devices. Indicates the number of damages. a、b、c is a positive integer; Get the average continuous running time of various equipment failures , Cumulative running time average , Cumulative load average , continuous load average and the average number of days since the last maintenance or repair , calculate the weight coefficients of each mean in turn and : ； The corresponding weight coefficients of each mean and The calculation formula is as above; Get the real-time continuous running time of each device , Cumulative running time , cumulative load , continuous load and the number of days since the last maintenance or repair , after linear normalization, the risk coefficient of each device is calculated : ； Corresponding risk factors for each device The calculation formula is as above; Get the risk factor of each device , real-time update calculation to obtain the risk threshold of various devices : ； When the risk factor of the equipment Exceeds the corresponding risk threshold When a risk occurs, a risk warning for the corresponding equipment is issued; Use sensors to periodically collect real-time temperatures of all devices , real-time speed and real-time load After dimensionless processing, the mean temperature of various devices is calculated , speed mean And load mean : ； in, Indicates the type number of the device. Indicates the sequence number between the same type of devices. Indicates the number of damages. a, b, m is a positive integer; Get the average temperature of various devices , speed mean And load mean , calculate the mean temperature in turn , speed mean And load mean The weight coefficient and : ； The corresponding temperature mean , speed mean And load mean The weight coefficient and The calculation formula is as above; Get the real-time temperature of the device corresponding to the risk threshold , real-time speed and real-time load After linear normalization, the maintenance risk coefficient of risk equipment is calculated. : ； Corresponding risk equipment maintenance risk factor The calculation formula is as above; Obtain the risk factor of risk equipment maintenance , real-time update calculation to obtain the maintenance risk threshold of various equipment : ； When the risk factor of each risk equipment maintenance Exceeds its corresponding maintenance risk threshold When necessary, a maintenance risk warning will be issued to the corresponding equipment, and the corresponding equipment will be repaired and maintained.

Images