CN118585773A

CN118585773A - Vibration prediction method and device for material handling trolley

Info

Publication number: CN118585773A
Application number: CN202411053381.XA
Authority: CN
Inventors: 王瑞骥; 丁利强; 刘冉冉; 贾绍锋; 余君山
Original assignee: Huaxin Jiaxing Intelligent Equipment Co ltd
Current assignee: Huaxin Jiaxing Intelligent Equipment Co ltd
Priority date: 2024-08-02
Filing date: 2024-08-02
Publication date: 2024-09-03
Anticipated expiration: 2044-08-02
Also published as: CN118585773B

Abstract

The application provides a vibration prediction method and device of a material handling trolley, wherein the method comprises the following steps: acquiring real-time working state information of a target material handling trolley, and determining a vibration related variable set corresponding to the target material handling trolley based on the real-time working state information of the target material handling trolley, historical task information and using state information of an automatic material transmission system; inputting a vibration related variable set corresponding to the target material handling trolley into a trained vibration prediction model, and outputting a vibration prediction result corresponding to the target material handling trolley; the vibration prediction result comprises a vibration frequency and a vibration amplitude; the vibration prediction model is obtained after training based on vibration related variable sets corresponding to a plurality of material handling trolleys with wafer vibration damage faults and predetermined vibration prediction result labels, and can avoid wafer damage caused by abnormal vibration of the material handling trolleys to the greatest extent.

Description

Vibration prediction method and device for material handling trolley

Technical Field

The application relates to the technical field of vibration prediction, in particular to a vibration prediction method and device of a material handling trolley.

Background

With the continuous development of industrial automation technology, semiconductor processing factories currently use an Automatic material transfer system (Automatic MATERIAL HANDLING SYSTEM, AMHS) to increase the automation degree of the factories. A material handling cart (Overhead Hoist Transport, OHT) is used as the primary material handling tool in an automated material handling system, and vibration during transport can adversely affect the material and in severe cases may even cause wafer damage. Therefore, existing automated material handling systems typically improve the structure of the material handling cart and the transport track in advance to avoid vibration damage to the wafer as much as possible, and simultaneously provide vibration sensors in the material handling cart to monitor real-time vibration.

With the gradual increase of the operation duration of the automatic material conveying system, the abrasion of the material handling trolley and the rail can cause the gradual deterioration of the stability of the material handling trolley, but the deterioration process is generally slower, namely, the data monitored by the vibration sensor in most time are normal data, which are not only meaningless for vibration fault monitoring, but also cause huge data communication and storage pressure, and meanwhile, due to the data communication delay, when the dispatching center receives abnormal data, wafer damage faults often occur. Therefore, the existing automatic material conveying system cannot well solve the problem of wafer damage caused by abnormal vibration of the material handling trolley.

Disclosure of Invention

The application provides a vibration prediction method and device of a material handling trolley, which are used for avoiding the problem of wafer damage caused by abnormal vibration of the material handling trolley to the maximum extent.

The application provides a vibration prediction method of a material handling trolley, which comprises the following steps:

Acquiring real-time working state information of a target material handling trolley, and determining a vibration related variable set corresponding to the target material handling trolley based on the real-time working state information of the target material handling trolley, historical task information and using state information of an automatic material transmission system; the real-time working state information comprises a running route of a task currently being executed, running speed in the running route, a current running track section and a current running speed, and the historical task information comprises a running route of a historical task and the running speed in the running route; the using state information of the automatic material conveying system comprises using frequencies of different track sections; the vibration related variable set comprises: the method comprises the steps of total driving mileage, sub driving mileage corresponding to different types of road sections, average driving speed corresponding to each sub driving mileage, start-stop times, using frequency of a current driving track section and current driving speed;

inputting a vibration related variable set corresponding to the target material handling trolley into a trained vibration prediction model, and outputting a vibration prediction result corresponding to the target material handling trolley; the vibration prediction result comprises a vibration frequency and a vibration amplitude;

The vibration prediction model is obtained after training based on vibration related variable sets corresponding to a plurality of material handling trolleys with wafer vibration damage faults and a predetermined vibration prediction result label.

According to the vibration prediction method of the material handling trolley, the vibration associated variable set corresponding to the target material handling trolley is determined based on the real-time working state information, the historical task information and the use state information of the automatic material transmission system of the target material handling trolley, and the vibration associated variable set specifically comprises the following steps:

determining the current running speed of the target material handling trolley based on the real-time working state information of the target material handling trolley;

Determining the total driving mileage of the target material handling trolley and the sub driving mileage corresponding to different types of road sections based on the driving route of the task currently being executed by the target material handling trolley and the driving route of the historical task;

Determining the average running speed and the start-stop times corresponding to each sub-running mileage of the target material handling trolley based on the running speed in the running route of the task currently being executed by the target material handling trolley and the running speed in the running route of the historical task;

based on the frequency of use of the different track segments, a frequency of use of the current travel track segment of the target material handling trolley is determined.

According to the vibration prediction method of the material handling trolley, provided by the application, the method further comprises the following steps:

Determining whether the target material handling trolley has a wafer vibration damage risk or not based on a vibration prediction result corresponding to the target material handling trolley;

and under the condition that the target material handling trolley is at risk of wafer vibration damage, carrying out emergency treatment on the target material handling trolley.

According to the vibration prediction method of the material handling trolley provided by the application, based on the vibration prediction result corresponding to the target material handling trolley, whether the target material handling trolley has a wafer vibration damage risk is determined, and the method specifically comprises the following steps:

Judging whether the vibration frequency corresponding to the target material handling trolley exceeds a preset vibration frequency threshold value or not, and judging whether the vibration amplitude corresponding to the target material handling trolley exceeds the preset vibration amplitude threshold value or not;

And judging that the target material handling trolley has a wafer vibration damage risk under the condition that the vibration frequency corresponding to the target material handling trolley exceeds a preset vibration frequency threshold or the vibration amplitude corresponding to the target material handling trolley exceeds a preset vibration amplitude threshold, otherwise, judging that the target material handling trolley does not have the wafer vibration damage risk.

According to the vibration prediction method of the material handling trolley, the emergency treatment is carried out on the target material handling trolley, and the method specifically comprises the following steps:

decelerating the target material handling trolley and judging whether a roaming track exists in a target range;

under the condition that a roaming track exists in a target range, controlling the target material handling trolley to enter the roaming track and stopping running;

And controlling the target material handling trolley to stop running and blocking the current running track section under the condition that no roaming track exists in the target range.

According to the vibration prediction method of the material handling trolley, the preset vibration frequency threshold and the preset vibration amplitude threshold are determined based on a fault knowledge base maintained in advance; the fault knowledge base comprises fault information data of automatic material transmission systems of different semiconductor processing factories, wherein the fault information data comprises fault equipment, fault types and fault associated indexes.

According to the vibration prediction method of the material handling trolley, provided by the application, the steps of determining the vibration frequency threshold and the vibration amplitude threshold based on a fault knowledge base maintained in advance concretely comprise the following steps:

extracting target fault information data of which fault equipment is a material handling trolley and the fault type is wafer vibration damage fault from a fault knowledge base maintained in advance;

determining a vibration frequency critical value and a vibration amplitude critical value when a wafer vibration damage fault occurs based on the fault association index in the target fault information data;

And determining a vibration frequency threshold value and a vibration amplitude threshold value based on the vibration frequency threshold value, the vibration amplitude threshold value and a preset vibration risk margin when the wafer vibration damage fault occurs.

The application also provides a vibration prediction device of a material handling trolley, which comprises:

The vibration related variable set determining module is used for acquiring real-time working state information of the target material handling trolley and determining a vibration related variable set corresponding to the target material handling trolley based on the real-time working state information, the historical task information and the use state information of the automatic material transmission system of the target material handling trolley; the real-time working state information comprises a running route of a task currently being executed, running speed in the running route, a current running track section and a current running speed, and the historical task information comprises a running route of a historical task and the running speed in the running route; the using state information of the automatic material conveying system comprises using frequencies of different track sections; the vibration related variable set comprises: the method comprises the steps of total driving mileage, sub driving mileage corresponding to different types of road sections, average driving speed corresponding to each sub driving mileage, start-stop times, using frequency of a current driving track section and current driving speed;

The vibration prediction module is used for inputting a vibration related variable set corresponding to the target material handling trolley into a trained vibration prediction model and outputting a vibration prediction result corresponding to the target material handling trolley; the vibration prediction result comprises a vibration frequency and a vibration amplitude;

The present application also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of a method of predicting vibration of a materials handling trolley as described in any one of the above.

The present application also provides a computer program product comprising a computer program which, when executed by a processor, implements the steps of a method of predicting vibration of a material handling trolley as described in any one of the above.

According to the vibration prediction method and device for the material handling trolley, real-time working state information of the target material handling trolley is obtained, and a vibration related variable set corresponding to the target material handling trolley is determined based on the real-time working state information, the historical task information and the using state information of an automatic material transmission system of the target material handling trolley; the real-time working state information comprises a running route of a task currently being executed, running speed in the running route, a current running track section and a current running speed, and the historical task information comprises a running route of a historical task and the running speed in the running route; the using state information of the automatic material conveying system comprises using frequencies of different track sections; the vibration related variable set comprises: the method comprises the steps of total driving mileage, sub driving mileage corresponding to different types of road sections, average driving speed corresponding to each sub driving mileage, start-stop times, using frequency of a current driving track section and current driving speed; inputting a vibration related variable set corresponding to the target material handling trolley into a trained vibration prediction model, and outputting a vibration prediction result corresponding to the target material handling trolley; the vibration prediction result comprises a vibration frequency and a vibration amplitude; the vibration prediction model is obtained after training based on vibration related variable sets corresponding to a plurality of material handling trolleys with wafer vibration damage faults and predetermined vibration prediction result labels, and can accurately predict the vibration condition of the material handling trolleys in combination with the working condition of the material handling trolleys and the service condition of an automatic material transmission system, so that the problem of wafer damage caused by abnormal vibration of the material handling trolleys is avoided to the greatest extent.

Drawings

In order to more clearly illustrate the application or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the application, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.

FIG. 1 is a flow chart of a method for predicting vibration of a material handling cart provided by the present application;

FIG. 2 is a schematic illustration of a determined flow of vibration-related variable sets provided by the present application;

FIG. 3 is a schematic illustration of a determined flow path for a vibration frequency threshold and a vibration amplitude threshold provided by the present application;

FIG. 4 is a schematic flow chart of emergency treatment of a target material handling cart provided by the present application;

FIG. 5 is a schematic diagram of a vibration prediction apparatus for a materials handling cart according to the present application;

fig. 6 is a schematic structural diagram of an electronic device provided by the present application.

Detailed Description

For the purpose of making the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present application, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.

FIG. 1 is a schematic flow chart of a method for predicting vibration of a material handling trolley according to the present application, as shown in FIG. 1, the method includes:

Step 101, acquiring real-time working state information of a target material handling trolley, and determining a vibration related variable set corresponding to the target material handling trolley based on the real-time working state information of the target material handling trolley, historical task information and using state information of an automatic material transmission system; the real-time working state information comprises a running route of a task currently being executed, running speed in the running route, a current running track section and a current running speed, and the historical task information comprises a running route of a historical task and the running speed in the running route; the using state information of the automatic material conveying system comprises using frequencies of different track sections; the vibration related variable set comprises: the method comprises the steps of total driving mileage, sub-driving mileage corresponding to different types of road sections, average driving speed corresponding to each sub-driving mileage, start-stop times, using frequency of a current driving track section and current driving speed.

102, Inputting a vibration related variable set corresponding to the target material handling trolley into a trained vibration prediction model, and outputting a vibration prediction result corresponding to the target material handling trolley; the vibration prediction result comprises a vibration frequency and a vibration amplitude;

Specifically, based on the foregoing, the existing automatic material transfer system generally improves the structure of the material handling trolley and the structure of the transportation track in advance to avoid the damage caused by the vibration of the wafer as much as possible, and meanwhile, the vibration sensor is arranged in the material handling trolley to monitor the real-time vibration. However, the stability degradation process of the material handling trolley is generally slow, that is, the data monitored by the vibration sensor most of the time is normal data, which is not only meaningless for vibration fault monitoring, but also causes huge data communication and storage pressure, and meanwhile, due to data communication delay, when the dispatch center receives abnormal data, wafer damage faults often occur. Therefore, the existing automatic material conveying system cannot well solve the problem of wafer damage caused by abnormal vibration of the material handling trolley. Aiming at the problem, the embodiment of the application provides a vibration prediction method of a material handling trolley, which aims to accurately monitor and timely early warn the vibration condition of the material handling trolley under the condition of not depending on a vibration sensor so as to furthest avoid the problem of wafer damage caused by abnormal vibration of the material handling trolley.

In particular, the application finds that the vibration degree of the material handling trolley is determined by two factors: the first aspect is the state of the material handling trolley itself and the second aspect is the state of the travel track. Along with the gradual increase of the operation duration of the automatic material conveying system, the stability of the operation track can be gradually deteriorated due to factors such as abrasion and aging, and meanwhile, along with the gradual increase of the operation duration of the material handling trolley, the stability of the material handling trolley can be gradually deteriorated due to factors such as abrasion and aging, and the two factors are overlapped, so that the vibration of the material handling trolley is more and more serious, and finally, the vibration damage of the wafer is caused. Based on the vibration, the embodiment of the application obtains a plurality of vibration related variable sets corresponding to the material handling trolley with the wafer vibration damage fault through deep data mining of the fault knowledge base maintained in advance, trains the vibration data with the wafer vibration damage fault as a vibration prediction result label to obtain a vibration prediction model of the material handling trolley, and is used for accurately predicting the real-time vibration condition of the material handling trolley.

It is noted that, in order to facilitate timely fault monitoring and maintenance of the automatic material conveying system, the manufacturers of the existing automatic material conveying systems collect fault data of the automatic material conveying system that is put into use. The embodiment of the application constructs a fault knowledge base based on massive fault information data of automatic material transmission systems of different semiconductor processing factories, wherein the fault information data comprises fault equipment, fault types and fault associated indexes. Based on the above, the embodiment of the application can save a large amount of data collection work, thereby performing efficient screening and analysis of the target fault information data. The target fault information data refers to fault information data that the fault equipment is a material handling trolley and the fault type is wafer vibration damage fault.

According to the embodiment of the application, through deep excavation and analysis of the target fault information data, the historical running state and the real-time running state of the material handling trolley can have important influence on the stability of the material handling trolley, and based on the fact, the variables which are finally determined by the embodiment of the application and influence the stability of the material handling trolley comprise two parts, namely the historical running state variable and the real-time running state variable. Wherein the historical operating state variables include: the total driving mileage, the sub driving mileage corresponding to different types of road sections, the average driving speed corresponding to each sub driving mileage and the start-stop times, specifically, the types of the road segments include: straight horizontal sections, straight uphill sections, straight downhill sections, and turning sections; the real-time operating state variables include: real-time travel speed and real-time travel track segment. It is understood that the average driving speed corresponding to each sub-driving distance can be obtained by dividing the length of the sub-driving distance by the corresponding driving duration. Correspondingly, the embodiment of the application further discovers that the main influencing factor of the stability of the running track is the use frequency of the track through deep mining and analysis of the target fault information data. It can be understood that due to the production task scheduling and the equipment layout of the semiconductor factory, the use frequencies of different running track sections in the running track of the automatic material conveying system are different, and correspondingly, the stability degradation degree of different track sections is also different. Based on this, the variables that affect the stability of the running track finally determined by the embodiment of the present application include: the frequency of use of the different track segments. The frequency of use may be characterized by the number of times the material handling trolley passes through the track section after production.

In order to ensure the accuracy of the vibration prediction result to the maximum extent, the embodiment of the application comprehensively considers the variable influencing the stability of the material handling trolley and the variable influencing the stability of the running track to finally obtain the vibration related variable set of the material handling trolley, wherein the vibration related variable set comprises: the method comprises the steps of total driving mileage, sub-driving mileage corresponding to different types of road sections, average driving speed corresponding to each sub-driving mileage, start-stop times, using frequency of a current driving track section and current driving speed. In combination with the foregoing, it can be known that the vibration prediction model of the material handling trolley can be trained and obtained based on the vibration related variable sets corresponding to the plurality of material handling trolleys with wafer vibration damage faults and the predetermined vibration prediction result labels. Specifically, a machine learning algorithm suitable for vibration prediction problems, such as decision trees, support vector machines, random forests, neural networks, etc., may be selected. In the training process, a vibration related variable set sample corresponding to the material handling trolley is taken as input, a vibration prediction result label corresponding to the sample is taken as output, and a model is trained to accurately predict the real-time vibration data of the OHT. For model evaluation and optimization, the trained model can be evaluated by using an evaluation data set (i.e. a test set), and indexes such as accuracy, recall, precision and the like of the model are calculated. If the model does not perform well, adjustments and optimizations can be made, such as adjusting model parameters, increasing the number of samples, or using more complex models, etc. The model is continuously evaluated and optimized in the mode until indexes such as accuracy, recall rate and precision rate reach preset standards. It will be appreciated that the preset standard may be determined according to actual needs, and embodiments of the present application are not specifically limited herein.

After the trained vibration prediction model is obtained, the vibration prediction model can be utilized to predict the vibration of the material handling trolley. Specifically, as described in step 101, an embodiment of the present application first needs to determine a vibration-related variable set corresponding to a target material handling cart. It will be appreciated that the target material handling cart may be any material handling cart that is operating in an automated material transfer system. Unlike the model training phase, vibration-associated variable set samples may be determined based on target fault information data in a fault knowledge base. In the actual application stage, related information of the target material handling trolley and the automatic material transmission system is required to be acquired from background data of the automatic material transmission system, and a vibration related variable set is determined based on the related information of the target material handling trolley and the automatic material transmission system. Specifically, the real-time working state information of the target material handling trolley is required to be acquired at first, and then the vibration related variable set corresponding to the target material handling trolley is determined based on the real-time working state information, the historical task information and the using state information of the automatic material transmission system of the target material handling trolley. The real-time working state information comprises a running route of a task currently being executed, a running speed in the running route, a current running track section and a current running speed, and the historical task information comprises a running route of a historical task and a running speed in the running route; the usage status information of the automatic material transfer system includes usage frequencies of different track segments. It can be appreciated that the real-time working state information, the historical task information and the usage state information of the automatic material transfer system of the target material handling trolley are generally stored in a specific area of the database of the automatic material transfer system, so that the embodiment of the application can quickly acquire the information of the target material handling trolley after determining the target material handling trolley, and further determine the vibration related variable set corresponding to the target material handling trolley.

More specifically, fig. 2 is a schematic flow chart of determining a vibration-related variable set provided by the present application, and as shown in fig. 2, the determining, based on real-time working state information, historical task information, and usage state information of an automatic material transfer system, a vibration-related variable set corresponding to a target material transfer cart specifically includes:

Step 1011, determining the current running speed of the target material handling trolley based on the real-time working state information of the target material handling trolley;

Step 1012, determining the total driving range of the target material handling trolley and the sub driving ranges corresponding to different types of road sections based on the driving route of the task currently being executed by the target material handling trolley (i.e. the driving route of the past task) and the driving route of the history task;

step 1013, determining an average running speed and a start-stop number corresponding to each sub-running mileage of the target material handling trolley based on the running speed in the running route of the task currently being executed by the target material handling trolley and the running speed in the running route of the history task;

Step 1014, determining a frequency of use of the current travel track segment of the target material handling trolley based on the frequency of use of the different track segments.

It will be appreciated that since the material handling carts are all performing material handling based on task scheduling instructions, the task scheduling instructions include planned task routes. Therefore, after the task route is determined, the driving mileage of the material handling trolley and the road section type corresponding to the task route can be determined. Meanwhile, the automatic material conveying system monitors the real-time state of the material handling trolley in the task execution process, so that the total driving range of the target material handling trolley and the sub driving ranges corresponding to different types of road sections can be determined based on the driving route of the task currently executed by the target material handling trolley and the driving route of the historical task.

Further, based on the running speed in the running route of the task currently being executed by the target material handling trolley and the running speed in the running route of the historical task, the average running speed and the start-stop times corresponding to each sub-running mileage of the target material handling trolley can be determined. It will be appreciated that the travel speeds of the target materials handling cart in the traveled path of the task currently being performed and the travel speeds of the history task in the travel path refer to the travel speeds corresponding to different positions in the path, and based on this, the average travel speed corresponding to each sub-travel distance of the target materials handling cart can be quickly determined. Meanwhile, the start-stop process is accompanied by obvious acceleration and deceleration processes, so that the start-stop times corresponding to each sub-driving mileage can be rapidly determined based on the driving speed in the driving route of the task currently being executed by the target material handling trolley and the driving speed in the driving route of the historical task. For the method of metering the start-stop times, the start-stop times are preferably increased by one when the start is started or stopped once.

Under the condition that the frequency of use of the current running track section and the different track sections of the target material handling trolley are known, the frequency of use of the current running track section of the target material handling trolley can be rapidly determined based on the frequency of use of the different track sections.

In summary, the embodiments of the present application can quickly determine the vibration-related variable set corresponding to the target material handling cart through the steps 1011-1014.

After the vibration related variable set corresponding to the target material handling trolley is determined, the vibration related variable set corresponding to the target material handling trolley can be input into a trained vibration prediction model, and then a vibration prediction result corresponding to the target material handling trolley is output. It is understood that the vibration prediction result includes a vibration frequency and a vibration amplitude. Based on the method, the real-time vibration condition of the material handling trolley can be quickly and accurately determined under the condition that the vibration sensor is not relied on.

Further, based on the foregoing, it can be seen that, due to the delay of data communication, when the dispatch center receives abnormal data, the wafer damage fault has occurred in the conventional vibration monitoring method of the material handling trolley by using the vibration sensor, so that, in order to avoid the occurrence of the situation to the maximum extent, after the vibration prediction result corresponding to the target material handling trolley is obtained, the vibration prediction method of the material handling trolley according to the embodiment of the present application further includes:

It should be noted that, the existence of the risk of the wafer vibration damage herein does not mean that the wafer vibration damage will occur immediately, but means that the wafer vibration damage will occur after a preset time interval, based on which the wafer damage fault caused by untimely emergency treatment due to delay of data communication can be avoided. The preset time interval may be determined based on a delay value corresponding to the data communication delay, and specifically, according to actual needs, the preset time interval may be several times or even longer than the delay value corresponding to the data communication delay, which is not particularly limited in the embodiment of the present application. More specifically, the determining, based on the vibration prediction result corresponding to the target material handling trolley, whether the target material handling trolley has a risk of wafer vibration damage specifically includes:

According to the method and the device, the wafer vibration damage can be caused by the fact that any one of the vibration frequency and the amplitude of the material handling trolley exceeds the standard, so that the wafer vibration damage risk of the target material handling trolley is judged under the condition that the vibration frequency corresponding to the target material handling trolley exceeds a preset vibration frequency threshold or the vibration amplitude corresponding to the target material handling trolley exceeds a preset vibration amplitude threshold.

Notably, the preset vibration frequency threshold and vibration amplitude threshold are also determined based on a pre-maintained fault knowledge base; based on the foregoing, the fault knowledge base includes fault information data of automatic material conveying systems of different semiconductor processing factories, wherein the fault information data includes fault equipment, fault types and fault associated indexes. FIG. 3 is a schematic flow chart of determining a vibration frequency threshold and a vibration amplitude threshold according to the present application, as shown in FIG. 3, the steps for determining the vibration frequency threshold and the vibration amplitude threshold based on a fault knowledge base maintained in advance specifically include:

step 201, extracting target fault information data of which fault equipment is a material handling trolley and the fault type is wafer vibration damage fault from a fault knowledge base maintained in advance;

Step 202, determining a vibration frequency critical value and a vibration amplitude critical value when a wafer vibration damage fault occurs based on a fault association index in the target fault information data;

Step 203, determining a vibration frequency threshold and a vibration amplitude threshold based on the vibration frequency threshold, the vibration amplitude threshold and a preset vibration risk margin when the wafer vibration damage fault occurs.

Specifically, the vibration frequency and vibration amplitude at which the wafer vibration damage fault occurs are referred to herein as thresholds (i.e., vibration frequency thresholds and vibration amplitude thresholds). Based on the foregoing, the risk of wafer vibration damage refers to the occurrence of wafer vibration damage after a predetermined time interval. Correspondingly, according to the embodiment of the application, through analyzing the vibration frequency and vibration amplitude data of the preset period before the vibration damage fault of the wafer occurs in the material handling trolley in the target fault information data, the vibration frequency and the vibration amplitude before the vibration damage fault occur are found and gradually increased along with time. Accordingly, after the predetermined time interval is determined, the vibration risk margin (i.e., the vibration frequency margin and the vibration amplitude margin) may be determined, and based on this, the vibration frequency threshold (i.e., the difference between the vibration frequency threshold and the vibration frequency margin) and the vibration amplitude threshold (i.e., the difference between the vibration amplitude threshold and the vibration amplitude margin) may be determined. In summary, the vibration frequency threshold and the vibration amplitude threshold determined by the above steps can avoid the occurrence of the wafer vibration damage fault to the maximum extent.

Accordingly, fig. 4 is a schematic flow chart of emergency treatment for a target material handling trolley, as shown in fig. 4, where the emergency treatment for the target material handling trolley specifically includes:

The target range is preferably a range that the target material handling trolley can reach in the preset time interval, and the roaming track in the embodiment of the application is preferably a track section with lower use frequency. Based on the method, under the condition that the roaming track exists in the target range, the target material handling trolley is controlled to enter the roaming track and stop running, so that the influence of subsequent maintenance work on the target material handling trolley on other material handling trolleys can be reduced to the greatest extent. And under the condition that no roaming track exists in the target range, the embodiment of the application controls the target material handling trolley to stop running and blocks the current running track section. That is, in the case where the influence on other materials handling dollies cannot be avoided, the embodiment of the application immediately blocks the current running track section to avoid the collision between the other materials handling dollies and the target materials handling dollies. In summary, the emergency processing method of the embodiment of the application can consider both the transportation efficiency of the automatic material conveying system and the safety of the material handling trolley.

The method provided by the embodiment of the application comprises the steps of obtaining real-time working state information of a target material handling trolley, and determining a vibration related variable set corresponding to the target material handling trolley based on the real-time working state information, historical task information and using state information of an automatic material transmission system of the target material handling trolley; the real-time working state information comprises a running route of a task currently being executed, running speed in the running route, a current running track section and a current running speed, and the historical task information comprises a running route of a historical task and the running speed in the running route; the using state information of the automatic material conveying system comprises using frequencies of different track sections; the vibration related variable set comprises: the method comprises the steps of total driving mileage, sub driving mileage corresponding to different types of road sections, average driving speed corresponding to each sub driving mileage, start-stop times, using frequency of a current driving track section and current driving speed; inputting a vibration related variable set corresponding to the target material handling trolley into a trained vibration prediction model, and outputting a vibration prediction result corresponding to the target material handling trolley; the vibration prediction result comprises a vibration frequency and a vibration amplitude; the vibration prediction model is obtained after training based on vibration related variable sets corresponding to a plurality of material handling trolleys with wafer vibration damage faults and predetermined vibration prediction result labels, and can accurately predict the vibration condition of the material handling trolleys in combination with the working condition of the material handling trolleys and the service condition of an automatic material transmission system, so that the problem of wafer damage caused by abnormal vibration of the material handling trolleys is avoided to the greatest extent.

The vibration prediction device of the material handling trolley provided by the application is described below, and the vibration prediction device of the material handling trolley and the vibration prediction method of the material handling trolley described below can be correspondingly referred to each other.

Based on any of the above embodiments, fig. 5 is a schematic structural diagram of a vibration prediction apparatus of a material handling trolley according to the present application, as shown in fig. 5, the apparatus includes:

the vibration-related variable set determining module 301 is configured to obtain real-time working state information of a target material handling trolley, and determine a vibration-related variable set corresponding to the target material handling trolley based on the real-time working state information of the target material handling trolley, historical task information and usage state information of an automatic material transfer system; the real-time working state information comprises a running route of a task currently being executed, running speed in the running route, a current running track section and a current running speed, and the historical task information comprises a running route of a historical task and the running speed in the running route; the using state information of the automatic material conveying system comprises using frequencies of different track sections; the vibration related variable set comprises: the method comprises the steps of total driving mileage, sub driving mileage corresponding to different types of road sections, average driving speed corresponding to each sub driving mileage, start-stop times, using frequency of a current driving track section and current driving speed;

The vibration prediction module 302 is configured to input a vibration-related variable set corresponding to the target material handling trolley into a trained vibration prediction model, and output a vibration prediction result corresponding to the target material handling trolley; the vibration prediction result comprises a vibration frequency and a vibration amplitude;

In the device provided by the embodiment of the application, the vibration-related variable set determining module 301 obtains real-time working state information of a target material handling trolley, and determines a vibration-related variable set corresponding to the target material handling trolley based on the real-time working state information of the target material handling trolley, historical task information and use state information of an automatic material transmission system; the real-time working state information comprises a running route of a task currently being executed, running speed in the running route, a current running track section and a current running speed, and the historical task information comprises a running route of a historical task and the running speed in the running route; the using state information of the automatic material conveying system comprises using frequencies of different track sections; the vibration related variable set comprises: the method comprises the steps of total driving mileage, sub driving mileage corresponding to different types of road sections, average driving speed corresponding to each sub driving mileage, start-stop times, using frequency of a current driving track section and current driving speed; the vibration prediction module 302 inputs the vibration related variable set corresponding to the target material handling trolley into a trained vibration prediction model, and outputs a vibration prediction result corresponding to the target material handling trolley; the vibration prediction result comprises a vibration frequency and a vibration amplitude; the vibration prediction model is obtained after training based on vibration related variable sets corresponding to a plurality of material handling trolleys with wafer vibration damage faults and predetermined vibration prediction result labels, and can accurately predict the vibration condition of the material handling trolleys in combination with the working condition of the material handling trolleys and the service condition of an automatic material transmission system, so that the problem of wafer damage caused by abnormal vibration of the material handling trolleys is avoided to the greatest extent.

Based on the above embodiment, the determining, based on the real-time working state information, the historical task information and the usage state information of the automatic material transfer system, the vibration-related variable set corresponding to the target material transfer cart specifically includes:

Based on any of the above embodiments, the apparatus further comprises an emergency processing module for performing the following operations:

Based on any one of the foregoing embodiments, the determining whether the target material handling trolley has a risk of wafer vibration damage based on a vibration prediction result corresponding to the target material handling trolley specifically includes:

Based on any one of the foregoing embodiments, the emergency treatment for the target material handling trolley specifically includes:

Based on any of the above embodiments, the preset vibration frequency threshold and vibration amplitude threshold are determined based on a pre-maintained fault knowledge base; the fault knowledge base comprises fault information data of automatic material transmission systems of different semiconductor processing factories, wherein the fault information data comprises fault equipment, fault types and fault associated indexes.

Based on any of the above embodiments, the step of determining the vibration frequency threshold and the vibration amplitude threshold based on a pre-maintained fault knowledge base specifically includes:

Fig. 6 illustrates a physical schematic diagram of an electronic device, as shown in fig. 6, which may include: processor 401, communication interface (Communications Interface) 402, memory 403 and communication bus 404, wherein processor 401, communication interface 402 and memory 403 complete communication with each other through communication bus 404. Processor 401 may invoke logic instructions in memory 403 to perform the method of predicting vibration of a material handling cart provided by the methods described above, the method comprising: acquiring real-time working state information of a target material handling trolley, and determining a vibration related variable set corresponding to the target material handling trolley based on the real-time working state information of the target material handling trolley, historical task information and using state information of an automatic material transmission system; the real-time working state information comprises a running route of a task currently being executed, running speed in the running route, a current running track section and a current running speed, and the historical task information comprises a running route of a historical task and the running speed in the running route; the using state information of the automatic material conveying system comprises using frequencies of different track sections; the vibration related variable set comprises: the method comprises the steps of total driving mileage, sub driving mileage corresponding to different types of road sections, average driving speed corresponding to each sub driving mileage, start-stop times, using frequency of a current driving track section and current driving speed; inputting a vibration related variable set corresponding to the target material handling trolley into a trained vibration prediction model, and outputting a vibration prediction result corresponding to the target material handling trolley; the vibration prediction result comprises a vibration frequency and a vibration amplitude; the vibration prediction model is obtained after training based on vibration related variable sets corresponding to a plurality of material handling trolleys with wafer vibration damage faults and a predetermined vibration prediction result label.

Further, the logic instructions in the memory 403 may be implemented in the form of software functional units and stored in a computer readable storage medium when sold or used as a stand alone product. Based on this understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.

In another aspect, the present application also provides a computer program product comprising a computer program, the computer program being storable on a non-transitory computer readable storage medium, the computer program, when executed by a processor, being capable of performing the method of predicting vibration of a material handling trolley provided by the methods described above, the method comprising: acquiring real-time working state information of a target material handling trolley, and determining a vibration related variable set corresponding to the target material handling trolley based on the real-time working state information of the target material handling trolley, historical task information and using state information of an automatic material transmission system; the real-time working state information comprises a running route of a task currently being executed, running speed in the running route, a current running track section and a current running speed, and the historical task information comprises a running route of a historical task and the running speed in the running route; the using state information of the automatic material conveying system comprises using frequencies of different track sections; the vibration related variable set comprises: the method comprises the steps of total driving mileage, sub driving mileage corresponding to different types of road sections, average driving speed corresponding to each sub driving mileage, start-stop times, using frequency of a current driving track section and current driving speed; inputting a vibration related variable set corresponding to the target material handling trolley into a trained vibration prediction model, and outputting a vibration prediction result corresponding to the target material handling trolley; the vibration prediction result comprises a vibration frequency and a vibration amplitude; the vibration prediction model is obtained after training based on vibration related variable sets corresponding to a plurality of material handling trolleys with wafer vibration damage faults and a predetermined vibration prediction result label.

In yet another aspect, the present application provides a non-transitory computer readable storage medium having stored thereon a computer program which when executed by a processor is implemented to perform the method of predicting vibration of a material handling trolley provided by the methods described above, the method comprising: acquiring real-time working state information of a target material handling trolley, and determining a vibration related variable set corresponding to the target material handling trolley based on the real-time working state information of the target material handling trolley, historical task information and using state information of an automatic material transmission system; the real-time working state information comprises a running route of a task currently being executed, running speed in the running route, a current running track section and a current running speed, and the historical task information comprises a running route of a historical task and the running speed in the running route; the using state information of the automatic material conveying system comprises using frequencies of different track sections; the vibration related variable set comprises: the method comprises the steps of total driving mileage, sub driving mileage corresponding to different types of road sections, average driving speed corresponding to each sub driving mileage, start-stop times, using frequency of a current driving track section and current driving speed; inputting a vibration related variable set corresponding to the target material handling trolley into a trained vibration prediction model, and outputting a vibration prediction result corresponding to the target material handling trolley; the vibration prediction result comprises a vibration frequency and a vibration amplitude; the vibration prediction model is obtained after training based on vibration related variable sets corresponding to a plurality of material handling trolleys with wafer vibration damage faults and a predetermined vibration prediction result label.

The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.

From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.

Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present application, and are not limiting; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method of predicting vibration of a material handling cart, the method comprising:

2. The method for predicting vibration of a material handling trolley according to claim 1, wherein the determining the vibration-related variable set corresponding to the target material handling trolley based on the real-time working state information, the historical task information and the usage state information of the automatic material transfer system of the target material handling trolley specifically comprises:

3. The method of predicting vibration of a materials handling cart of claim 2, further comprising:

4. The method for predicting vibration of a material handling cart according to claim 3, wherein determining whether the target material handling cart has a risk of wafer vibration damage based on a vibration prediction result corresponding to the target material handling cart specifically comprises:

5. The method for predicting vibration of a materials handling cart as set forth in claim 4, wherein said emergency treatment of said target materials handling cart comprises:

6. The method of claim 5, wherein the predetermined vibration frequency threshold and vibration amplitude threshold are determined based on a pre-maintained fault knowledge base; the fault knowledge base comprises fault information data of automatic material transmission systems of different semiconductor processing factories, wherein the fault information data comprises fault equipment, fault types and fault associated indexes.

7. The method of predicting vibration of a materials handling cart of claim 6, wherein the step of determining the vibration frequency threshold and the vibration amplitude threshold based on a pre-maintained fault knowledge base, comprises:

8. A vibration prediction apparatus for a materials handling cart, said apparatus comprising:

9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor performs the steps of the method of predicting vibration of a materials handling trolley as claimed in any one of claims 1 to 7 when the program is executed.

10. A non-transitory computer readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements the steps of the vibration prediction method of a materials handling trolley according to any one of claims 1 to 7.