Industrial equipment intelligent scheduling system based on fault early warning

Abstract

The embodiment of the invention relates to the technical field of information, in particular to an industrial equipment intelligent scheduling system based on fault early warning. The system comprises a first early warning module which reads parameter data and operation parameter data of an operation unmanned aerial vehicle, and obtains a first fault probability according to a pre-established first fault model; the second early warning module reads the task environment data and obtains a second fault probability according to a pre-established second fault model; the scheduling module is used for generating a scheduling scheme for a plurality of to-be-scheduled operation unmanned aerial vehicles according to the first fault probability, the second fault probability and the task data in each preset scheduling period, and the scheduling scheme comprises the operation unmanned aerial vehicles and task sequences corresponding to the operation unmanned aerial vehicles; and the optimization module is used for obtaining a total fault probability according to the first fault probability and the second fault probability, and optimizing the scheduling scheme by using an optimization algorithm by taking the minimum total fault probability in the scheduling period as a target.

Description

Technical Field

[0001] Multiple embodiments of this specification relate to the field of information technology, and more particularly to an intelligent scheduling system for industrial equipment based on fault warning. Background Art

[0002] The use of unmanned aerial vehicles (UAVs) in various industrial applications is becoming increasingly widespread, such as logistics distribution, agricultural monitoring, infrastructure inspection, etc. However, these application scenarios often face complex environments and operating conditions, increasing the risk of UAV failures. Once a UAV fails during a mission, it may not only lead to mission failure but also cause economic losses and even potential safety hazards. Therefore, it is necessary to study the failure probability of UAVs during operation and perform task scheduling. Summary of the Invention

[0003] Multiple embodiments of this specification describe an intelligent scheduling system for industrial equipment based on fault warning.

[0004] In a first aspect, an embodiment of this specification provides an intelligent scheduling system for industrial equipment based on fault warning, for scheduling mission UAVs, including: A first warning module that reads the parameter data and mission parameter data of the mission UAVs and obtains a first failure probability according to a pre-established first fault model; A second warning module that reads the mission environment data and obtains a second failure probability according to a pre-established second fault model; A scheduling module that generates a scheduling plan for a number of mission UAVs to be scheduled according to the first failure probability, the second failure probability, and mission data in each preset scheduling period, where the scheduling plan includes the mission UAVs and their corresponding mission sequences; An optimization module that obtains the total failure probability according to the first failure probability and the second failure probability, and optimizes the scheduling plan using an optimization algorithm with the goal of minimizing the total failure probability within the scheduling period.

[0005] In a second aspect, an embodiment of this specification provides an intelligent scheduling method for industrial equipment based on fault warning, for scheduling mission UAVs, including the steps of: Reading the parameter data and mission parameter data of the mission UAVs and obtaining a first failure probability according to a pre-established first fault model; Reading the mission environment data and obtaining a second failure probability according to a pre-established second fault model; Generating a scheduling plan for a number of mission UAVs to be scheduled according to the first failure probability, the second failure probability, and mission data in each preset scheduling period, where the scheduling plan includes the mission UAVs and their corresponding mission sequences; Obtain the total failure probability based on the first failure probability and the second failure probability, and use an optimization algorithm to optimize the scheduling scheme with the goal of minimizing the total failure probability within a scheduling period.

[0006] In a third aspect, an embodiment of this specification provides an electronic device, including a processor and a memory; The processor is connected to the memory; The memory is used to store executable program code; The processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute the method described in any of the above aspects.

[0007] In a fourth aspect, an embodiment of this specification provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method described in any of the above aspects is implemented.

[0008] In a fifth aspect, an embodiment of this specification provides a computer program product, including a computer program, and when the computer program is executed by a processor, the method described in any of the above aspects is implemented.

[0009] The beneficial effects brought by the technical solutions provided in some embodiments of this specification at least include: In multiple embodiments of this specification, the intelligent scheduling system and method for industrial equipment based on fault warning establish a first fault model and a second fault model to predict the fault probability, enabling the operator to identify potential risks in advance and intelligently adjust task scheduling, ensuring safety and reliability during the operation process. It can generate an optimal scheduling scheme for several job drones to be scheduled within each preset scheduling period, realize the effective allocation of resources, and improve the overall operation efficiency. By analyzing historical task environment data, a clustering algorithm is used to determine the optimal time length as the scheduling period. The system is allowed to automatically adjust the scheduling period according to the actual situation, avoiding the problems of resource waste or untimely scheduling that may be caused by a fixed period, and improving the flexibility and response speed of the system.

[0010] Other features and advantages of multiple embodiments of this specification will be further revealed in the following specific embodiments and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of this specification, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings in the following description are only some embodiments of this specification. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0012] Figure 1 Schematic diagram of intelligent scheduling of industrial equipment provided by the embodiments of this specification.

[0013] Figure 2 Schematic diagram of an intelligent scheduling system for industrial equipment provided by the embodiments of this specification.

[0014] Figure 3 Schematic diagram of data processing of an intelligent scheduling system for industrial equipment provided by the embodiments of this specification.

[0015] Figure 4 Schematic diagram of an intelligent scheduling method for industrial equipment provided by the embodiments of this specification.

[0016] Figure 5 Schematic diagram of an electronic device provided by the embodiments of this specification. Detailed implementation manners

[0017] The technical solutions of the embodiments of this specification will be explained and described below with reference to the accompanying drawings of the embodiments of this specification. However, the following embodiments are only the preferred embodiments of this specification, not all of them. Based on the embodiments in the implementation manners, other embodiments obtained by those skilled in the art without creative efforts fall within the protection scope of this specification.

[0018] Terms such as "first", "second", "third", etc. in the specification, claims and the above-mentioned drawings of this specification are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products or devices.

[0019] In the following description, terms indicating orientation or positional relationships such as "inside", "outside", "above", "below", "left", "right", etc. are only for convenience of describing the embodiments and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this specification.

[0020] The data involved in this application are all information and data authorized by users or fully authorized by all parties, and the collection of relevant data complies with the relevant laws, regulations and standards of the relevant countries and regions.

[0021] Before introducing the technical solutions described in this specification, the application scenarios of the technical solutions and related technologies will be introduced.

[0022] For example, in an orchard located in a mountainous area, as the seasons change, various fruits such as apples and pears usher in a harvest season. However, due to the complex terrain, traditional ground transportation methods are difficult to meet the needs of efficient picking and transportation. For this purpose, please refer to the attached Figure 1 , the need to use drones of different types and load capacities for collaborative operations has become an effective means to solve this problem. It includes small drones 21 and load-carrying drones 22. Small drones 21 are mainly used to shuttle between fruit trees, quickly collecting fresh fruits that have just been picked to small collection points on the mountain. Small drones 21 are light and flexible, and can fly freely among trees, ensuring that the fruits can be delivered to small collection points in a timely manner. The load-carrying drones 22 transport the framed fruits at the small collection points to the collection station at the foot of the mountain. The load-carrying drones 22 need to transport more fruits at one time. The collection station at the foot of the mountain uses cars to transport the fruits to the logistics center. The load-carrying drones 22 have a larger load capacity, but are slightly less flexible, so they are more suitable for transporting framed fruits with a relatively fixed route.

[0023] In addition to the transportation of fruits, it is also necessary to provide water and working meals, as well as other materials such as tools for people working in the mountains. When the transportation is relatively concentrated, such as transporting working meals to the mountains, a heavy-duty drone 22 can be used to transport more working meals and water at one time. When transporting less materials, such as transporting a tool or a small amount of water, it is faster and more convenient to use a small drone 21 for transportation.

[0024] During the above operations, the natural environment in the mountains and the conditions of related tasks, such as the ever-changing wind speed and direction, the weight of the materials carried, and the duration of continuous work, have become one of the important factors affecting the failure rate of drones. When a drone fails, the materials it carries will be lost, and it may also affect the safety of ground personnel and materials. And if the drone crashes or drops items, personnel need to be organized to deal with it. If the location is in a steep and dangerous place in the mountains, new risks will be introduced. To this end, the probability of drone failure needs to be reduced as much as possible.

[0025] This manual provides an intelligent dispatching system for industrial equipment based on fault warning, which is used for dispatching operating drones. Figure 2 ,include: The first warning module 100 reads parameter data and mission data of the operating UAV and obtains a first fault probability according to a pre-established first fault model; The second early warning module 200 reads the task environment data and obtains a second fault probability according to a pre-established second fault model; The scheduling module 300 generates a scheduling plan for a number of job drones to be scheduled according to the first failure probability, the second failure probability, and task data within each preset scheduling period. The scheduling plan includes the job drones and their corresponding task sequences. The optimization module 400 obtains the total failure probability based on the first failure probability and the second failure probability, and uses an optimization algorithm to optimize the scheduling plan with the goal of minimizing the total failure probability within the scheduling period.

[0026] The small drone 21 and the load-carrying drone 22 are both connected to the server 10 and receive the task assignment instructions from the server 10. This system is deployed on the server 10. The job drones include drones and job equipment. The parameter data includes drone parameters and job equipment parameters. The method for establishing the first failure model includes: Establish a simulation model of the job equipment according to the job equipment parameters of the job drone. Obtain the data boundary of the task data, and generate multiple job parameter samples according to the data boundary. Input the job parameter samples into the simulation model, and obtain the failure results according to the simulation of the simulation model. Associate the job parameter samples with the failure results, and train the established machine learning model to obtain the first failure model.

[0027] Exemplarily, the small drone 21 is equipped with a robotic arm as the job equipment, which is used to lift a small amount of bagged fruits or to pick fruits.

[0028] Exemplarily, the drone parameters include: battery capacity: 20,000 mAh, maximum flight speed: 15 m / s, wind resistance: maximum wind speed 10 m / s, self-weight: 8 kg. The job equipment parameters, that is, the robotic arm parameters include: load-bearing weight: maximum 3 kg, working range: radius 0.5 m, power type: electric, working temperature range: -10°C to 40°C.

[0029] First, establish a simulation model according to the job equipment parameters. Based on the parameters of the robotic arm, create a simulation model that can simulate the behavior and response of the robotic arm under different working conditions. It is used to simulate the performance of the robotic arm when picking or lifting fruits of different weights, such as from 0.5 kg to 3 kg.

[0030] Assume the task data boundaries are as follows: the weight range of the picked fruits is from 0.5 kg to 3 kg, the ambient temperature varies from 10°C to 35°C, and the number of picking times is between 300 and 10,000. According to the data boundaries of the task data, multiple samples of operation parameters are generated. Exemplarily, Sample 1: picking weight = 0.5 kg, ambient temperature = 10°C, number of picking times = 500. Sample 2: picking weight = 1.5 kg, ambient temperature = 25°C, number of picking times = 5,000. Sample 3: picking weight = 3 kg, ambient temperature = 35°C, number of picking times = 10,000. Some data beyond the data boundaries of the task data can also be generated to simulate the situation of exceeding the data boundaries caused by careless operation or insufficient estimation. Input the samples of operation parameters into the simulation model and simulate the number of repeated operations to obtain the failure results.

[0031] Input the above samples into the simulation model for simulation, and observe whether the robotic arm will fail under different conditions, such as the failure of the robotic arm caused by overload or the overheat protection of the motor due to high temperature, etc. Record the results of each simulation. For example: Sample 1: no failure, Sample 2: no failure, Sample 3: overheat protection of the motor starts.

[0032] Associate all the samples of operation parameters with their corresponding failure results as the training set. For example, use the decision tree algorithm to train these data to construct a prediction model. This model can predict the probability of the robotic arm failing according to the input operation parameters (such as picking weight, ambient temperature, number of picking times, etc.), which is used as the first failure probability.

[0033] On the other hand, the method for establishing the second failure model includes: Cluster the drone parameters of the operation drones according to the drone parameters of the operation drones, classify the operation drones according to the clustering results to obtain several categories, and obtain the central drone parameters of the corresponding clustering center for each category; Read the task environment data, transform the dimension of the task environment data so that the dimension is consistent with the central drone parameters; Compare the task environment data with the central drone parameters to obtain a comparison compliance vector; Receive the failure annotation and associate the failure annotation with the corresponding comparison compliance vector to obtain the environmental data sample; Establish and use the environmental data sample to train the machine learning model to obtain the second failure model.

[0034] Use several drones for mountain fruit harvesting operations and consider the influence of task environment data such as wind speed and temperature on the drone operation.

[0035] Exemplarily, the drone parameters of drone A are: maximum flight speed of 12 m / s, wind resistance of 8 m / s, self-weight of 6 kg, and battery capacity of 18000 mAh. The drone parameters of drone B are: maximum flight speed of 15 m / s, wind resistance of 10 m / s, self-weight of 7 kg, and battery capacity of 20000 mAh. The drone parameters of drone C are: maximum flight speed of 18 m / s, wind resistance of 14 m / s, self-weight of 9 kg, and battery capacity of 22000 mAh. The drone parameters of drone D are: maximum flight speed of 10 m / s, wind resistance of 6 m / s, self-weight of 5 kg, and battery capacity of 16000 mAh. The drone parameters of drone E are: maximum flight speed of 16 m / s, wind resistance of 12 m / s, self-weight of 8 kg, and battery capacity of 21000 mAh.

[0036] According to the drone parameters, use the K-means clustering algorithm to classify the drones and calculate the center point of each class, that is, the clustering center. Exemplarily, class 1 includes drones A and D, and its clustering center is a maximum flight speed of 11 m / s, wind resistance of 7 m / s, self-weight of 5.5 kg, and battery capacity of 17000 mAh; class 2 includes drones B, C, and E, and its clustering center is a maximum flight speed of 16.3 m / s, wind resistance of 12 m / s, self-weight of 8.3 kg, and battery capacity of 21000 mAh.

[0037] Read the task environment data, such as the wind speed of 11.2 m / s, temperature of 25°C, and air pressure of 1009 hPa in a certain task.

[0038] Since the central drone parameters do not directly involve temperature and air pressure, these two factors can be ignored or converted into factors affecting wind resistance in some way. Here, only focus on the wind speed as the key variable and only retain the wind speed information, and the obtained data is [11.2].

[0039] On the other hand, in another embodiment, in order to make the task environment data conform to the central drone parameters, an autoencoder model is used to adjust the dimension. The input layer receives the task environment data (such as wind speed, temperature, air pressure). The encoder part (the left half): compresses the input to 4 dimensions. The decoder part (the right half): attempts to restore the original task environment data. The output layer: outputs data with the same dimension as the input. This model can learn how to transform the task environment data into a vector with the same dimension as the central drone parameters. Compare the adjusted task environment data with the central drone parameters of each category to obtain a comparison compliance vector. For example, for task environment data with a wind speed of 11.2 m / s, when compared with the central drone parameters of category 1, the compliance value is about 0.16, indicating that it is not suitable to use a low-performance drone in this environment; when compared with the central drone parameters of category 2, the compliance value is about 0.76, indicating that it is more suitable to use a high-performance drone in this environment.

[0040] Receive a fault annotation and associate the fault annotation with the corresponding comparison compliance vector to obtain an environmental data sample. Assume that under the above conditions, the drone has a serious fault. Therefore, we associate this fault annotation with the corresponding comparison compliance vector [0.16, 0.76] to form an environmental data sample.

[0041] Use the environmental data sample, including the comparison compliance vector and the corresponding fault annotation, to train a machine learning model to obtain a second fault diagnosis model. Exemplarily, such as a random forest or a support vector machine (SVM). This model can predict the probability of the drone having a fault based on the input task environment data. For example, given a new task environment data (wind speed of 10 m / s), the model can output a fault probability value, that is, the second fault probability.

[0042] On the other hand, the method for reading the task environment data and obtaining the second fault probability according to the pre-established second fault model includes: Transform the task environment data, compare the transformed task environment data with the drone parameters of the working drone performing the corresponding task, and obtain a comparison compliance vector; Obtain the second fault probability according to the response of the second fault model to the comparison compliance vector.

[0043] This solution can not only classify and evaluate the drone according to its own characteristics, but also combine the actual task environment conditions to predict the possibility of the drone having a fault in a specific environment, thereby optimizing the drone scheduling scheme and improving the operation efficiency and safety.

[0044] On the other hand, the method for presetting the scheduling period includes: Read the historical task environment data and truncate the historical task environment data into environment data segments according to the initial time length; Use a clustering algorithm to cluster the environment data segments to obtain multiple cluster centers; Count the number of free environment data segments, where the free environment data segments are environment data segments whose distances from any one of the cluster centers are greater than a preset distance threshold; Calculate the proportion of the number of free environment data segments. With the goal of minimizing the proportion, use an optimization algorithm to adjust the time length, and set the scheduling period according to the optimized time length.

[0045] Collect the historical task environment data for a period of time. The data fields include: timestamp, wind speed (m / s), temperature (°C), and humidity (%). Truncate the historical task environment data into environment data segments according to the initial time length, and the initial time length is 30 minutes. Exemplarily, the environment data segments used in this embodiment are shown in Table 1.

[0046] Table 1 Environment data segments used in this embodiment: 。

[0047] For all data segments, use a clustering algorithm such as K-means to perform clustering analysis on these feature vectors to find representative cluster centers. For example, after clustering, two cluster centers are obtained: Cluster center 1: [wind speed = 7.0, temperature = 22.5, humidity = 46] and Cluster center 2: [wind speed = 11.0, temperature = 25, humidity = 40]. Among them, the "free environment data segment" is a data segment whose distance from any one of the cluster centers is greater than the preset distance threshold. Exemplarily, the distance threshold is set to the Euclidean distance equal to 1. Calculate the Euclidean distance between the feature vector of each data segment and the cluster center, and count the number of data segments whose distances all exceed 1. For example, the feature vector of a certain data segment is [wind speed = 9.0, temperature = 24, humidity = 42]. Its distance from cluster center 1 is approximately 4.03, and its distance from cluster center 2 is approximately 2.45. Since both of these distances exceed the set distance threshold of 1, this data segment is regarded as a free segment. There are a total of 100 data segments, and 10 of them are marked as free segments. Then the proportion of the number of free segments is 10%.

[0048] With the goal of minimizing the proportion, by adjusting the initially set time length (such as changing from 30 minutes to 20 minutes or 40 minutes), re-execute the above steps until the time length that minimizes the proportion of the number of free segments is found.

[0049] For example, when we try to shorten the time length to 20 minutes, we may find that the number of free fragments has decreased to 5, and the proportion has dropped to 5%. That is, a more optimal time length, namely 20 minutes, has been found. Exemplarily, 20 minutes is finally set as the final scheduling period.

[0050] By dynamically determining the scheduling period that best suits the current operating environment, the efficiency and stability of the UAV scheduling system are improved.

[0051] On the other hand, this specification also provides an intelligent scheduling method for industrial equipment based on fault warning for the scheduling of operation UAVs. Please refer to the appendix Figure 4 , including the steps: Step S1) Read the parameter data and task data of the operation UAV, and obtain the first fault probability according to the pre-established first fault model; Step S2) Read the task environment data, and obtain the second fault probability according to the pre-established second fault model; Step S3) In each preset scheduling period, generate a scheduling plan for a number of operation UAVs to be scheduled according to the first fault probability, the second fault probability, and the task data. The scheduling plan includes the operation UAVs and their corresponding task sequences; Step S4) Obtain the total fault probability according to the first fault probability and the second fault probability, and use an optimization algorithm to optimize the scheduling plan with the goal of minimizing the total fault probability within the scheduling period.

[0052] Please refer to Figure 5 the schematic structural diagram of an electronic device provided by an embodiment of this specification shown.

[0053] As Figure 5As shown, the electronic device 1100 may include: at least one processor 1101, at least one network interface 1104, a user interface 1103, a memory 1105, and at least one communication bus 1102. Among them, the communication bus 1102 can be used to realize the connection and communication of the above-mentioned components. Among them, the user interface 1103 may include buttons, and the optional user interface may further include a standard wired interface and a wireless interface. Among them, the network interface 1104 may, but is not limited to, include a Bluetooth module, an NFC module, a Wi-Fi module, etc. Among them, the processor 1101 may include one or more processing cores. The processor 1101 connects various parts within the entire electronic device 1100 through various interfaces and lines, and executes various functions of the routing device 1100 and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 1105, and by calling the data stored in the memory 1105. Optionally, the processor 1101 may be implemented in at least one of the hardware forms of DSP, FPGA, and PLA. The processor 1101 may integrate one or a combination of several of a CPU, a GPU, and a modem, etc. Among them, the CPU mainly processes the operating system, the user interface, application programs, etc.; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communication.

[0054] It can be understood that the above-mentioned modem may not be integrated into the processor 1101 and may be implemented separately by a single chip.

[0055] Among them, the memory 1105 may include RAM and may also include ROM. Optionally, the memory 1105 includes a non-transitory computer-readable medium. The memory 1105 can be used to store instructions, programs, codes, code sets, or instruction sets. The memory 1105 may include a program storage area and a data storage area. Among them, the program storage area may store instructions for implementing the operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned method embodiments, etc.; the data storage area may store the data involved in the above-mentioned method embodiments. Optionally, the memory 1105 may further be at least one storage device located far from the aforementioned processor 1101. The memory 1105, as a computer storage medium, may include an operating system, a network communication module, a user interface module, and application programs. The processor 1101 may be used to call the application programs stored in the memory 1105 and execute the methods in the above-mentioned multiple embodiments.

[0056] The embodiments of this specification also provide a computer-readable storage medium, in which instructions are stored. When the instructions run on a computer or a processor, the computer or the processor is caused to execute multiple steps in the above embodiments. If each component module of the above electronic device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in the computer-readable storage medium.

[0057] The embodiments of this specification also provide a computer program product, including a computer program. When the computer program is executed by a processor, multiple steps in the above embodiments are implemented.

[0058] Without conflict, the technical features in this embodiment and the implementation solutions can be combined arbitrarily.

[0059] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes multiple computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of this specification are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer instructions can be transmitted from a website, a computer, a server 10, or a data center to another website, a computer, a server 10, or a data center in a wired manner (such as coaxial cable, optical fiber, Digital Subscriber Line (DSL)) or a wireless manner (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server 10, a data center, etc. that integrates multiple available media. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a Digital Versatile Disc (DVD)), or a semiconductor medium (for example, a Solid State Disk (SSD)), etc.

[0060] When implemented by hardware or firmware, the foregoing method flow is programmed into a hardware circuit to obtain a corresponding hardware circuit structure and implement corresponding functions. For example, a programmable logic device (PLD) (such as a field programmable gate array (FPGA)) is an integrated circuit whose logic function is determined by a user's programming of the device. A designer can program on his or her own to "integrate" a digital system onto a PLD, without having to ask a chip manufacturer to design and fabricate a dedicated integrated circuit chip. Moreover, nowadays, instead of manually fabricating integrated circuit chips, this programming is mostly implemented using "logic compiler" software, which is similar to the software compiler used in program development and writing. The original code before compilation also has to be written in a specific programming language, which is called a hardware description language (HDL), and there are not only one but many kinds of HDLs. Those skilled in the art should also be clear that as long as the method flow is slightly logically programmed in the above-mentioned several hardware description languages and programmed into an integrated circuit, it is easy to obtain a hardware circuit that implements the logical method flow.

[0061] The embodiments described above are only described in a preferred embodiment manner of this specification, and do not limit the scope of this specification. Without departing from the design spirit of this specification, various deformations and improvements made by those of ordinary skill in the art to the technical solutions of this specification shall fall within the protection scope determined by the claims of this specification.

Claims

1. An intelligent scheduling system for industrial equipment based on fault warning, used for the scheduling of operation drones, characterized in that, Including: A first warning module, which reads the parameter data and task data of the operation UAV, and obtains a first failure probability according to a pre-established first failure model; A second warning module, which reads the task environment data and obtains a second failure probability according to a pre-established second failure model; A scheduling module, within each preset scheduling period, generates a scheduling plan for a number of operation UAVs to be scheduled according to the first failure probability, the second failure probability and the task data, and the scheduling plan includes the operation UAVs and their corresponding task sequences; An optimization module, obtains the total failure probability according to the first failure probability and the second failure probability, and uses an optimization algorithm to optimize the scheduling plan with the lowest total failure probability within the scheduling period as the goal.

2. The intelligent scheduling system for industrial equipment based on failure warning according to claim 1, wherein The operation UAV includes a UAV and an operation device, and the parameter data includes UAV parameters and operation device parameters. The method for establishing the first failure model includes: According to the operation device parameters of the operation UAV, establish a simulation model of the operation device; Obtain the data boundary of the task data, and generate a plurality of operation parameter samples according to the data boundary; Input the operation parameter samples into the simulation model, and obtain a failure result according to the simulation of the simulation model; Associate the operation parameter samples with the failure result, and train the established machine learning model to obtain the first failure model.

3. The intelligent scheduling system for industrial equipment based on failure warning according to claim 2, wherein The method for establishing the second failure model includes: According to the UAV parameters of the operation UAV, cluster the UAV parameters, classify the operation UAVs according to the clustering result, obtain a number of categories, and obtain the central UAV parameters of the corresponding clustering center for each category; Read the task environment data, and transform the dimension of the task environment data to match the dimension of the central UAV parameters; Compare the task environment data with the central UAV parameters to obtain a comparison compliance vector; Receive a failure annotation, and associate the failure annotation with the corresponding comparison compliance vector to obtain an environmental data sample; Establish and use the environmental data sample to train a machine learning model to obtain the second failure model.

4. The intelligent scheduling system for industrial equipment based on failure warning according to claim 3, wherein The method for transforming the dimension of the task environment data to match the dimension of the central UAV parameters includes: Establish an autoencoder model, and the output dimension of the left half of the autoencoder model matches the dimension of the central UAV parameters; Use the task environment data to train the autoencoder model until the accuracy of the autoencoder model reaches a preset accuracy threshold; Obtain a dimension transformation model according to the left half of the autoencoder model, and transform the dimension of the task environment data according to the dimension transformation model.

5. The intelligent scheduling system for industrial equipment based on failure warning according to claim 3 or 4, wherein A method for reading task environment data and obtaining a second failure probability according to a pre-established second failure model includes: Dimensionality reduction is performed on the task environment data, and the dimensionality-reduced task environment data is compared with the drone parameters of the job drone performing the corresponding task to obtain a comparison compliance vector; According to the response of the second failure model to the comparison compliance vector, a second failure probability is obtained.

6. An intelligent scheduling system for industrial equipment based on fault warning according to any one of claims 1 to 4, characterized in that The method for presetting a scheduling period includes: Read historical task environment data, and truncate the historical task environment data into environment data segments according to an initial time length; Use a clustering algorithm to cluster the environment data segments to obtain multiple cluster centers; Count the number of free environment data segments, where the free environment data segments are environment data segments whose distances from any one of the cluster centers are greater than a preset distance threshold; Calculate the proportion of the number of free environment data segments, aiming at the lowest proportion of the number, use an optimization algorithm to adjust the time length, and set the scheduling period according to the optimized time length.

7. An intelligent scheduling method for industrial equipment based on fault warning, which is used for the scheduling of operation drones, is characterized in that, Including the steps: Read the parameter data and task data of the job drone, and obtain a first failure probability according to a pre-established first failure model; Read task environment data, and obtain a second failure probability according to a pre-established second failure model; Within each preset scheduling period, according to the first failure probability, the second failure probability, and the task data, generate a scheduling plan for a plurality of job drones to be scheduled, where the scheduling plan includes the job drones and their corresponding task sequences; Obtain the total failure probability according to the first failure probability and the second failure probability, and use an optimization algorithm to optimize the scheduling plan with the lowest total failure probability within the scheduling period as the goal.

8. An electronic device, characterized in that, Including a processor and a memory; The processor is connected to the memory; The memory is used to store executable program code; The processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute the method according to claim 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the method according to claim 7 is implemented.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, the method according to claim 7 is implemented.

Images