Provided is an intelligent manufacturing system. The intelligent manufacturing system includes a demonstration line site layer, a network transmission and cloud service layer and a display terminal layer. The demonstration line site layer includes a production line and an information collection subsystem. The production line is configured to produce a product, and the information collection subsystem is configured to collect production information of the production line. The network transmission and cloud service layer is configured to acquire and transmit the production information collected by the information collection subsystem. The display terminal layer is configured to receive and display the production information.

A process improvement support device according to an aspect of the present disclosure includes: at least one memory configured to store instructions; and at least one processor configured to execute the instructions to: accumulate cycle times of a plurality of processes in a production line over a predetermined period; calculate a cycle time distribution that is a distribution of the cycle times of each of the processes in the predetermined period; and generate information for evaluating a correlation between the cycle time distribution of a first process and the cycle time distribution of a second process.

A material processing path selection method includes calculating a plurality of candidate material processing paths, determining a bottleneck process tank, and for each of the plurality of candidate material processing paths, calculating a bottleneck process tank utilization rate to select a candidate material processing path with a highest bottleneck process tank utilization rate in the plurality of candidate material processing paths as a target material processing path. The bottleneck process tank is a process tank having a highest use frequency among all process tanks, A use frequency of the process tank is equal to a total process time length of all materials that need to be transferred to the process tank divided by a number of all the materials that need to be transferred to the process tank.

The embodiments of the present invention provide a dynamic production scheduling method, apparatus and electronic device based on deep reinforcement learning, which relate to the technical field of Industrial Internet of Things, and can reduce the overall processing time of jobs on the basis of not exceeding the processing capacity of production device. The embodiments of the present invention includes: acquiring static characteristics, dynamic characteristics of each of jobs and system dynamic characteristics, inputting the static characteristics, dynamic characteristics of each of jobs to be scheduled and system dynamic characteristics into a scheduling model to obtain a job execution sequence or batch execution sequence of the jobs in each production stage, wherein, the static characteristics of the job include an amount of tasks and time required for completion, the dynamic characteristics of the job include reception moment, and the system dynamic characteristics include a remaining amount of tasks that can be performed by the device in each production stage. The scheduling model is a model obtained after training a first actor network based on static characteristics and dynamic characteristics of a sample job, system dynamic characteristics, and a first critic network.

A display system according to one or more embodiments includes: a control unit; a display unit; and a storage unit. The storage unit is configured to store a causal relationship model representing a relationship between two or more components of the plurality of components and an abnormality that may occur in the production facility, and the control unit is configured to: display, on the display unit, a model diagram that has nodes and one or more edges connecting the nodes to each other, based on the causal relationship model; and in response to a mode selection, such as a request from a user, display the model diagram in either a first mode in which all the nodes are displayed, or a second mode in which the nodes are allocated among a predetermined number of groups based on a predetermined criterion and the groups are displayed as nodes.

The present disclosure provides a warehousing control system and a computer device. The warehousing control system includes: a communication module configured to transmit and receive information; and a warehousing server configured to: plan, upon receiving a container warehousing task via the communication module, a target warehousing area and a target warehousing space corresponding to each container in the container warehousing task, and assign a warehouse hoisting apparatus to hoist a target container carried by a transportation vehicle to a corresponding target warehousing space; and/or assign, upon receiving a container distribution task via the communication module, a warehouse hoisting apparatus to load a target container in the container distribution task onto an assigned transportation vehicle. In this way, intelligent unmanned warehousing can be achieved, such that the operation efficiency of warehousing can be improved and the cost of warehousing management can be reduced.

Disclosed herein is technology for performing a simulation based optimization to identify a schedule for a manufacturing tool. An example method may include determining, by a processing device, resources of a manufacturing tool, wherein the resources comprise a first chamber and a second chamber; accessing task data indicating a first manufacturing task and a second manufacturing task; determining a duration to perform the first manufacturing task using the first chamber and a duration to perform the second manufacturing task using the second chamber; updating a machine learning model based on the duration to perform the first manufacturing task and the duration to perform the second manufacturing task; performing a set of computer simulations that uses the machine learning model and the task data to produce a set of simulation results; storing, by the processing device, a simulation result of the set of simulation results in a data store.

A production plan creation device includes a processor configured to receive, in a case of receiving a modification request to add a new task to an existing plan including plural tasks performed to produce a product using resources, a retention condition for retaining the plan for a task included in the existing plan, and modify the existing plan into a plan in which the plural tasks and the new task are performed using the resources while accounting for the retention condition and content of the new task.

The present application provides laser machine automatic operating method and system, which method comprises: basing on feature information to judge whether a wafer has completed operation on a laser machine, if yes, skipping over the laser machine to perform the next procedure, if not, executing step; processing the wafer on the laser machine, wherein the laser machine generates record information, and the record information is related to operation information of the wafer on the laser machine; and acquiring the record information, and basing on the record information to generate feature information, the feature information serving as judging criteria in step.

Systems and methods for generating device profiles of production devices in a production environment are disclosed. The methods include receiving operational data comprising a plurality of data streams generated by the plurality of production devices, training one or more models based on the operational data that are configured to create a device profile for each of the plurality of production devices for use by a job planner and generating the device profile for each of the plurality of production devices. The device profile includes information relating to one or more operational characteristics of that production device.