27 results about "Machine utilization" patented technology

The invention discloses a flexible job shop scheduling method based on deep reinforcement learning, and belongs to the field of intelligent manufacturing and intelligent scheduling, and the method comprises the steps: firstly, taking the minimization of the maximum job completion time and the maximization of the average machine utilization rate as optimization targets, and obtaining a target model; then representing a flexible job shop scheduling problem by using a disjunction graph model to obtain a scheduling state; according to the scheduling state and the target model, an end-to-end learning framework is constructed, and the framework is combined with a multi-attention network for deep feature extraction and a decision network for extensible decision, and a Markov decision process is utilized to obtain a job scheduling model; and finally, the multiple attention network constructs a production adaptability operation-AGV-machine scheme by using the complex relationship among the operation, the AGV and the machine to support the decision of the decision network, and obtains a scheduling schedule by using the job scheduling model to complete flexible job shop scheduling. According to the method, complex modes and relations in data can be better captured, and the performance and generalization ability of the model are improved.

The invention belongs to the technical field of production scheduling of a flexible manufacturing system, and particularly relates to a flexible manufacturing system multi-objective optimization scheduling method based on a Petri network and an improved NSGA-II. The method comprises the following steps: establishing a Petri net model, determining NSGA-II algorithm parameters, encoding and decoding, generating an initialized population, detecting and repairing chromosomes, calculating completion time, total energy consumption and a machine utilization rate and carrying out normalization, rapid non-dominated sorting and crowding degree sorting by visualizing processing procedures of workpieces in the flexible manufacturing system and machine occupation conditions among the workpieces; and carrying out genetic manipulation and outputting a Pareto optimal solution. All chromosomes are adjusted to control feasible chromosomes through a chromosome deadlock detection and repair method, and the chromosomes are decoded into a scheduling sequence. According to the method, the flexible manufacturing system is ensured to carry out optimal scheduling on the production process under the condition of no deadlock, the scheduling sequence meeting the optimization target requirement can be quickly found, the scheduling speed is improved, the machine utilization rate is increased, the energy consumption is reduced, and the production quantity is increased.

The invention relates to the technical field of flexible job shop scheduling in intelligent manufacturing and production scheduling, in particular to a flexible job shop scheduling optimization method for solving and adjusting resource constraints. Comprising the steps of initializing parameters and randomly generating an initial population; sequentially using a crossover operator and a mutation operator to evolve the current population; executing a hybrid decoding strategy on the current population; sorting the individuals in the current population from small to large according to the maximum completion time to form an elite population, and updating the elite population through question specific local search; and judging whether an evolution condition is met or not, if so, executing CP-based mathematical evolution, and outputting a final solution when the running time reaches the total running time. The method has the positive effects of reducing the resource waiting time, improving the machine utilization rate and improving the resource utilization efficiency and the scheduling performance of the whole workshop production.

Systems and methods are disclosed herein for identifying and predicting maintenance events with respect to assets, such as mobile machinery. A computing platform can include control circuit(s) (on-board and / or remote) configured to acquire machine fault data and machine utilization data. A feature set can be generated by transforming the machine fault data (e.g., by fusing the machine fault data with machine utilization data), normalizing the data, generating embeddings, and / or executing imputation algorithms to fill in missing values. A classifier model can be trained using the transformed machine fault data in conjunction with labeled maintenance event data to enable the trained classifier model to learn to recognize utilization-specific fault code patterns. The trained classifier model can generate inferences and predictions regarding machinery maintenance events without the use of maintenance data.

The invention provides a dispatching method and device for a wafer production line, computer equipment and a medium, and the method comprises the steps: obtaining a dispatching request for a to-be-dispatched machine table on the wafer production line, responding to the dispatching request, respectively obtaining dispatching priorities of multiple groups of to-be-processed wafers corresponding to the to-be-dispatched machine table, and sending the dispatching priorities to the to-be-processed machine table; and according to the dispatching priorities of the multiple groups of to-be-processed wafers, dispatching dispatching is carried out on the multiple groups of to-be-processed wafers, so that the multiple groups of to-be-processed wafers are all dispatched to a to-be-dispatched machine table and then corresponding process processing is carried out. Therefore, through dispatching priority calculation, the obtained dispatching priority is combined with the information of the to-be-processed wafer, and subsequent scheduling processing can be carried out in real time based on the condition of the to-be-processed wafer, so that corresponding process processing is carried out after a plurality of groups of to-be-processed wafers are all scheduled to the to-be-dispatched machine; and the productivity and the machine utilization rate of the to-be-dispatched machine are further improved.

The invention provides a dynamic flexible workshop multi-target online rescheduling method based on hierarchical MADDQN driving, aiming at the problem of dynamic multi-target rescheduling in actual production. According to the method, two performance indexes, namely the minimum total tardiness and the maximum machine utilization rate, are optimized. The MADDQN comprises two DDQN agents, and the DDQN of the higher level is a controller for determining the temporary optimization target of the DDQN of the lower level. At each rescheduling point, the high-level DDQN considers a target which needs to emphasize optimization at present, the low-level DDQN considers process machine selection under the current optimization target, and the two intelligent agents cooperate with each other to carry out iterative training. Compared with other rules-based algorithms, the multi-target dynamic scheduling method has certain advantages in each performance index when processing a multi-target dynamic scheduling problem, and still has good performance when solving a large-scale problem.

The utility model provides a grinding pad finishing disc replacing device and a grinding pad finishing disc replacing system.The grinding pad finishing disc replacing device comprises a first bearing table, a first driving part and a first cavity; through cooperation of the first bearing table and the first cavity, automatic replacement of the to-be-replaced grinding pad finishing disc and the to-be-replaced grinding pad finishing disc can be achieved, so that the processing time wasted by manual replacement of the grinding pad finishing disc in the related technology is shortened, and then the machine table utilization rate of the chemical mechanical polishing equipment is increased.

The invention discloses a dynamic flexible workshop scheduling method based on an event-driven DDQN algorithm. The method is used for solving the problem of flexible order workshop dynamic scheduling under the condition that a new order is inserted. The method comprises the following steps: firstly, considering the condition of random insertion of a new order, establishing a dynamic FJSP mathematical model taking minimization of total tardiness as an optimization target, converting the dynamic FJSP mathematical model into a multi-stage decision process based on event driving, and carrying out Markov decision process modeling of a scheduling problem; then seven key state characteristics such as machine utilization rate are designed, five composite scheduling rules are designed to form an action space, and a reward function is designed according to the variable quantity of part of the state characteristics; in addition, a soft epsilon greedy behavior strategy is designed according to the problem scale, and exploration and utilization are reasonably balanced. Through simulation research on a plurality of production scheduling examples, the result shows that the method can effectively cope with a dynamic event of random insertion of a new order, the total delay time is remarkably shortened, and good performance is shown in the aspects of convergence speed and solving efficiency.

The utility model discloses a pull rod type discharging door which comprises a stirring machine and an arc plate, the arc plate is installed on the outer side of the stirring machine, a discharging device used for controlling the stirring machine to conduct discharging is arranged at the position of a discharging opening in the bottom of the arc plate, and a protruding plate is installed on the inner wall of the discharging door. The size and thickness of the convex plate are the same as those of the notch at the discharge port at the bottom of the arc plate. The pull rod type discharge door provides a more uniform material distribution mode for single-machine double-line production of a mixing station, saves the station building cost, improves the single-machine utilization rate of a mixer, has the advantage of simple structure, and is driven by a simple pull rod to realize the synchronism of double discharge doors and the stability of door opening and closing; the use amount of hydraulic or pneumatic execution elements and the use amount of limiting electronic sensors are saved, and the manufacturing cost is saved.

This application relates to a horizontal flying probe inspection device, belonging to the field of flying probe inspection technology. It includes a loading mechanism, a first inspection mechanism, a flipping mechanism, a second inspection mechanism, and an unloading mechanism. The loading mechanism includes a frame, a transport cart, a loading platform, a robotic arm, a suction cup, and a transfer assembly, used to load PCB boards to be inspected and transfer them to the first inspection mechanism. The transfer assembly is mounted on the frame, and the loading platform slides on the transfer assembly to carry the PCB boards to be inspected. The transport cart is used to transport the loading platform to the transfer assembly. The first inspection mechanism is used to inspect the front side of the PCB boards transferred by the storage assembly. This application has the following advantages: it realizes automated PCB board inspection and double-sided inspection of PCB boards, improving inspection efficiency while reducing manual intervention, lowering labor intensity and labor costs, and improving machine utilization efficiency. Furthermore, the horizontal inspection design also enables the inspection of batches of PCB boards.

The present application relates to the technical field of flexible job shop scheduling in intelligent manufacturing and production scheduling, and particularly relates to an optimization method for solving flexible job shop scheduling with adjusted resource constraints. The method comprises the following steps: initializing parameters and randomly generating an initial population; using a crossover operator and a mutation operator in sequence to evolve the current population; executing a hybrid decoding strategy on the current population; sorting the individuals in the current population in ascending order of maximum completion time to form an elite population, and updating the elite population through problem-specific local search; judging whether the evolution condition is met, and if yes, executing mathematical evolution based on CP, and outputting a final solution when the running time reaches the total running time. The present application has the positive effects of reducing resource waiting time, improving machine utilization, and improving the resource utilization efficiency and scheduling performance of the entire workshop production.

The application discloses a large-scale flexible job shop scheduling method and system, acquires job shop related information; creates job agents, machine agents and inventory agents according to the job shop related information based on a multi-agent ant colony algorithm, initializes multi-agent ant colony algorithm parameters and pheromone initial values; constructs a disjunctive graph in the form of a directed graph according to the job shop related information, sequentially traverses the disjunctive graph, and job agents, machine agents and inventory agents generate scheduling solutions according to an agent negotiation protocol and update pheromones; after multiple iterations, it is judged whether a new optimal solution is generated, if the iteration number exceeds the preset number of rounds, the current optimal solution is output, and the final job shop scheduling scheme is obtained. Advantage: the shortest completion time, machine utilization rate and calculation time required by the multi-agent ant colony algorithm have obvious advantages compared with the prior art, and are more suitable for large-scale job scheduling problems.

This invention discloses an automatic CNC blade tip grinding machine that simulates the radius of a gas turbine blade. It is a dedicated grinding machine for machining the outer arc of heavy-duty gas turbine blade tips. This grinding machine is an adaptive arc grinding machine for blades of different radii, comprising a frame, a blade tip grinding assembly, an adaptive radius device, a blade oscillation drive assembly, a rotary table, and an operation box. This invention utilizes a combination of digital control and grinding to process blades made of high-temperature nickel-based alloy materials, improving product quality and enabling the machining of blade tips of different radii on a single machine, thus increasing machine utilization and reducing production costs. This invention simulates the actual operating scenario of a turbine blade, ensuring that the blade tip arc dimension is close to the actual installation, reducing errors. Simultaneously, the simulated radius can be adjusted to achieve different turbine blade tip machining.

The utility model discloses an automobile engine cylinder honing machine which comprises bottom plates, multiple sets of frame bodies are connected between the two sets of bottom plates, worm gear teeth are connected to the multiple sets of frame bodies, sleeve bodies are connected to the multiple sets of frame bodies in a sliding mode, the multiple sets of sleeve bodies movably penetrate through the corresponding worm gear teeth, groove bodies are formed in the multiple sets of sleeve bodies, and the multiple sets of frame bodies are connected with the corresponding worm gear teeth in a sliding mode. In the process that the worms are meshed with the worm gear teeth, the worms complete spiral feeding motion and drive the sleeve bodies to conduct angle rotation motion in the circumferential direction, and therefore the sleeve bodies can conduct angle adjustment work. The tool body can be placed for work according to the actual angle of the cylinder body of the automobile engine, the tool body can conduct honing operation on the cylinder bodies of the automobile engines of different models, machining of the cylinder bodies of the different models can be flexibly switched, the machining utilization rate is guaranteed, and then the production efficiency and economic benefits of enterprises are guaranteed.

The invention relates to the technical field of semiconductor manufacturing, in particular to a machine control method, a machine control device and a machine. The machine control method comprises the following steps: determining a warm-up state of at least one cavity in a machine; determining the number of available loading ports of the machine table; determining a preset loading mode at least based on the warm-up state, the number of the available loading ports and the carrying time of carrying the to-be-processed sheet to the machine table; and according to a preset loading mode, the warming-up sheets and / or the sheets to be processed correspond to the available loading ports so as to be loaded into the corresponding cavities. The proper loading mode is determined by comprehensively considering the warm-up state, the carrying time and the number of the available loading ports, so that it is ensured that the to-be-processed sheets are loaded into the corresponding cavities in time after warm-up, unnecessary repeated warm-up is avoided, the queuing waiting time of the to-be-processed sheets is shortened, the utilization rate and the working efficiency of a machine table are improved, and the production cost is reduced. And the reject ratio of products is reduced.

The invention provides a workshop job scheduling method, device and equipment, and the method comprises the steps: obtaining an initial population corresponding to an initial scheduling scheme of a to-be-processed workpiece in a job shop, and the parameter information of the workshop job; determining a target optimization function of the constraint scheduling scheme according to the parameter information of the workshop operation; screening the initial scheduling schemes in the initial population based on the optimization target value of the target optimization function and the machine utilization rate in each initial scheduling scheme to obtain a first scheduling scheme; meanwhile, real-time state information of the workshop is obtained; and performing optimization processing on the first scheduling scheme according to the workshop real-time state information, the target optimization function and a preset rescheduling strategy to obtain a target scheduling scheme. According to the scheduling method, the initial scheduling scheme is optimized based on the dynamic electric power and workshop real-time state information, the production cost of an enterprise can be reduced, and the flexibility and stability of the scheduling scheme are improved.

The present invention discloses a fast non-dominated sorting genetic algorithm for the dynamic equivalent parallel machine scheduling problem, which is carried out according to the following steps: S1: Generate a population by mixing heuristic rules MODD, ATC, X-RM and a random method; S2: Calculate the objective values of the individuals in the population by a decoding method based on dynamic programming; S3: Determine whether the termination condition is satisfied; if so, end; otherwise, perform fast non-dominated sorting on the individuals in the population; S4: Generate an offspring population through genetic operators; S5: Combine the parent population and the offspring population to form a population of size 2N; S6: Perform fast non-dominated sorting on the individuals in the population, and determine the population by combining crowding degree calculation; S7: Perform neighborhood search on the individuals in the population to generate new solutions to replace the original redundant solutions. The present invention has the characteristics of improving the utilization rate of workshop machines and meeting the customer delivery date.

This disclosure provides a chip manufacturing method, apparatus, equipment, medium, and program product applicable to the cloud computing field. The method includes: responding to a received chip manufacturing request by retrieving a data file for chip manufacturing; analyzing production requirements and machine information to plan the output ratio of each production unit in each production step according to a constructed objective function, obtaining a planning result; the objective function is constructed based on the utilization rate of machines in each production machine group during chip manufacturing; and, if the planning result meets preset conditions, controlling the machines in each production machine group according to the planning result so that the machines can produce chips based on the output ratio, wherein the preset conditions are that the machine utilization rate is minimized when producing chips based on the output ratio, and the difference in utilization rates between multiple production units is minimized.

A networked fitness system provides real time feedback to a user in the proper operation of a stacked weight fitness machine, while aggregating the user data for the benefit of both the user and the fitness facility. The device automatically connects the user's portable electronic device to the stacked weight fitness machine and provides valuable feedback to the user as to proper machine usage in real time. The aggregated fitness data provides fitness suggestions to the user as well as guidance to the fitness facility to minimize user attrition, increase machine utilization, and identify potential equipment issues.

The application discloses a kind of multi-data dimension flow hoisting machinery equipment utilization rate calculation method, comprising the following steps: S1, hoisting machinery equipment, internet of things data collector starts;S2, internet of things platform obtains internet of things data collector data;S3, internet of things platform judges whether the off-car speed of hoisting machinery equipment is greater than set threshold value, if meet, hoisting machinery equipment is in mobile state, and count into effective working time;S4, continue to judge whether the engine speed of hoisting machinery equipment is greater than set threshold value, if not meet, then count into parking waiting time;S5, continue to judge whether the main arm angle and actual weight of hoisting machinery equipment are greater than respective set threshold value, if meet, then count into effective working time;If not meet, then count into parking waiting time;S6, calculate the utilization rate of hoisting machinery equipment.The application creates a kind of flow machine utilization rate algorithm in combination with the actual use scene and each type working condition mode of flow hoisting machinery equipment.

The utility model discloses a ditching and banking machine which comprises a frame, a support device, a power device, a transmission device, a ditching device and a banking device. The frame is provided with an adjusting device, and the adjusting device is provided with an adjusting rod and an adjusting sleeve; the adjusting rod is fixedly connected with the frame, and the adjusting sleeve is fixedly connected with the support device. And the adjusting sleeve is movably connected with the adjusting rod. The utility model aims to provide the ditching banking machine, the ditching banking machine is provided with an innovative adjusting device design, and the width of the working part can be adjusted through the adjusting rod and the adjusting sleeve in the adjusting device, so that the ditching banking machine can adapt to different operation requirements, the utilization rate of the machine is improved, and the cost of purchasing a plurality of machines by a user is reduced.

A product productivity optimization method, module and related equipment, the product productivity optimization method comprising: acquiring information about a product production plan, a product production cycle, a product production process flow, equipment groups, a backup relationship between the equipment groups and a backup relationship between technological processes; according to the product production cycle, the product production process flow and the product production plan, obtaining a predicted load rate of an equipment group in a first unit time; and according to the backup relationship between the equipment groups and the backup relationship between the process flows, carrying out balance optimization processing on the predicted load rates of the equipment groups in the first unit time, and obtaining the balance load rates of the equipment groups with the backup relationship in the first unit time, so that the equipment groups with the backup relationship operate at the balance load rates. According to the technical scheme of the invention, the load rate balance among the equipment groups with the backup relationship can be realized, the overall balance of the production line and the machine utilization rate can be improved, and the full-load capacity maximization can be realized.

The utility model discloses a temperature compensation crystal resonator with a double-roller and double-R flat and inverted design, which comprises a base, the surface of the base is fixed with a spring piece through spot welding, a shell is fixedly arranged on the base through a buckle, a wafer is arranged in the shell, the wafer and an electrode coated on the wafer form an oscillator, and the oscillator is connected with the base. The end part of the wafer is connected with the spring piece through a conductive adhesive; a first pin and a second pin are respectively mounted at the bottom of the base; the wafer comprises an R1 roller plane, and the R1 roller plane is arranged on the outer side of the R2 roller plane. According to the temperature compensation crystal resonator with the double-roller double-R flat inverted design, by adopting the unique appearance design of double-roller double-R flat inverted edges, the smoothness and high-temperature overturning points can be effectively improved, the smoothness index is averagely between 0.08 ppm and 0.28 ppm, the high-temperature overturning points are small in scattering difference and good in consistency, the percent of pass is greater than 85%, materials are saved, and the percent of pass and the utilization rate of products on a machine are improved.

The utility model discloses an automatic discharging device which comprises an equipment base, and an automatic discharging monitoring and controlling switch structure is installed on the equipment base. The monitoring and controlling automatic discharging switch structure comprises a discharging conveying belt, a pair of mounting bases, a pair of discharging boxes, a pair of feeding hoppers, a pair of discharging doors, a plurality of mounting blocks, a plurality of rotating hinged supports, two pairs of driving telescopic push rods, two pairs of connecting frames, a controller and a probe monitoring assembly. The utility model relates to the technical field of sintering machines, and has the beneficial effects that the problems that when the existing sintering machine production line is designed and installed, space and cost are saved, the sintering machines share one conveying belt for ore unloading and discharging, the utilization coefficient of the sintering machines almost reaches the maximum and the yield is increased along with the increase of the production cost pressure, and two sintering machines simultaneously unload materials, so that the production efficiency is low are solved. The problems that materials on a conveying belt overflow and even press-stop of the conveying belt are caused, production interruption is caused, the service life of equipment is affected, and meanwhile production efficiency is reduced are solved.

A networked fitness system provides real time feedback to a user in the proper operation of a stacked weight fitness machine, while aggregating the user data for the benefit of both the user and the fitness facility. The device automatically connects the user's portable electronic device to the stacked weight fitness machine and provides valuable feedback to the user as to proper machine usage in real time. The aggregated fitness data provides fitness suggestions to the user as well as guidance to the fitness facility to minimize user attrition, increase machine utilization, and identify potential equipment issues.

This invention discloses a linkage device in the field of COF product packaging, including an inner lead receiving frame and an adhesive dispensing frame. A linkage frame is provided between the inner lead receiving frame and the adhesive dispensing frame. A through hole is provided on the inner lead receiving frame corresponding to the linkage frame, and a through hole is provided on the adhesive dispensing frame corresponding to the linkage frame. The linkage frame includes a base, and two sets of symmetrical support components are provided on the upper surface of the base. A pad is horizontally provided on each of the two support blocks, and two vertical support plates are fixed on the pads. The two support plates are distributed one in front of the other. An L-shaped mounting block is provided on the upper part of the two support plates, and a side guide rail is correspondingly provided on the mounting block. A central support guide rail is provided on the upper part of the central support rail. Two side guide rails are symmetrically distributed on the left and right sides of the central support guide rail, and the central support guide rail and the two side guide rails are parallel to each other. This invention can reduce manpower time, improve machine utilization efficiency, and increase output.

System (200)s and methods are disclosed herein for identifying and predicting maintenance events with respect to assets, such as mobile machinery. A computing platform can include control circuit(s) (on-board and / or remote) configured to acquire machine fault data and machine utilization data. A feature set can be generated by transforming the machine fault data (e.g., by fusing the machine fault data with machine utilization data), normalizing the data, generating embeddings, and / or executing imputation algorithms to fill in missing values. A classifier model (260) can be trained using the transformed machine fault data in conjunction with labeled maintenance event data to enable the trained classifier model (260) to learn to recognize utilization-specific fault code patterns. The trained classifier model (260) can generate inferences and predictions regarding machinery maintenance events without the use of maintenance data.