An intelligent scheduling system for industrial equipment based on fault warning

Abstract

Multiple embodiments of this specification relate to the field of information technology, specifically to an intelligent scheduling system for industrial equipment based on fault warning. The system includes: a first warning module that reads parameter data and operation parameter data of an operating drone and obtains a first fault probability based on a pre-established first fault model; a second warning module that reads task environment data and obtains a second fault probability based on a pre-established second fault model; a scheduling module that generates a scheduling plan for several operating drones to be scheduled within each preset scheduling cycle based on the first and second fault probabilities and task data, the scheduling plan including the operating drones and their corresponding task sequences; and an optimization module that obtains a total fault probability based on the first and second fault probabilities and optimizes the scheduling plan using an optimization algorithm with the goal of minimizing the total fault probability within the scheduling cycle.

Description

Technical Field

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

[0002] Drones are increasingly used in various industrial applications, such as logistics and delivery, agricultural monitoring, and infrastructure inspection. However, these applications often face complex environments and operating conditions, increasing the risk of drone failure. A drone malfunction during a mission can not only lead to mission failure, but also potentially cause economic losses and even safety hazards. Therefore, it is necessary to study the probability of drone failure during operations and effectively schedule missions. Summary of the Invention

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

[0004] In a first aspect, embodiments of this specification provide an intelligent industrial equipment scheduling system based on fault warning, which is used for scheduling operating drones, including:

[0005] The first early warning module reads the parameter data and operation parameter data of the operating UAV and obtains a first failure probability based on a pre-established first failure model;

[0006] The second early warning module reads the task environment data and obtains the second fault probability according to the pre-established second fault model;

[0007] a scheduling module, within each preset scheduling period, generating a scheduling plan for a plurality of operating drones to be scheduled based on the first failure probability, the second failure probability, and the task data, the scheduling plan including the operating drones and their corresponding task sequences;

[0008] The optimization module obtains a total failure probability according to the first failure probability and the second failure probability, and optimizes the scheduling scheme using an optimization algorithm with the goal of minimizing the total failure probability within the scheduling period.

[0009] In a second aspect, the embodiments of this specification provide an intelligent scheduling method for industrial equipment based on fault warning, which is used for scheduling operating drones, including the steps of:

[0010] Reading parameter data and operation parameter data of the operating UAV, and obtaining a first fault probability based on a pre-established first fault model;

[0011] Reading the task environment data, and obtaining the second fault probability according to a pre-established second fault model;

[0012] In each preset scheduling period, generating a scheduling plan for a plurality of operating drones to be scheduled based on the first failure probability, the second failure probability, and the task data, the scheduling plan including the operating drones and their corresponding task sequences;

[0013] A total failure probability is obtained according to the first failure probability and the second failure probability, and the scheduling scheme is optimized using an optimization algorithm with the goal of minimizing the total failure probability within a scheduling period.

[0014] In a third aspect, embodiments of this specification provide an electronic device, including a processor and a memory;

[0015] The processor is connected to the memory;

[0016] The memory is used to store executable program code;

[0017] The processor reads the executable program code stored in the memory to run a program corresponding to the executable program code, so as to execute the method described in any one of the above aspects.

[0018] In a fourth aspect, an embodiment of this specification provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method described in any one of the above aspects is implemented.

[0019] In a fifth aspect, embodiments of this specification provide a computer program product, including a computer program, which implements the method described in any of the above aspects when executed by a processor.

[0020] The beneficial effects of the technical solutions provided by some embodiments of this specification include at least:

[0021] In multiple embodiments of this specification, the provided intelligent scheduling system and method for industrial equipment based on fault warning predicts the probability of failure by establishing a first fault model and a second fault model, so that the operator can identify potential risks in advance and intelligently adjust the task scheduling, thereby ensuring the safety and reliability of the operation process. It is possible to generate the optimal scheduling plan for several operating drones to be scheduled within each preset scheduling cycle, realize the effective allocation of resources, and improve the overall operation efficiency. Through the analysis of historical task environment data, a clustering algorithm is used to determine the optimal time length as the scheduling cycle. The system is allowed to automatically adjust the scheduling cycle according to actual conditions, avoiding the problem of resource waste or untimely scheduling that may be caused by a fixed cycle, and improving the flexibility and response speed of the system.

[0022] Other features and advantages of the various embodiments of this specification will be further disclosed in the following detailed description and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of this specification, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0024] Figure 1 This is a schematic diagram of intelligent scheduling of industrial equipment provided in the embodiments of this specification.

[0025] Figure 2 Schematic diagram of the intelligent scheduling system for industrial equipment provided in the embodiments of this specification.

[0026] Figure 3 This is a data processing diagram of the industrial equipment intelligent scheduling system provided in the embodiments of this specification.

[0027] Figure 4 This is a schematic diagram of the intelligent scheduling method for industrial equipment provided in the embodiments of this specification.

[0028] Figure 5 This is a schematic diagram of an electronic device provided in an embodiment of this specification. DETAILED DESCRIPTION

[0029] The following is an explanation and description of the technical solutions of the embodiments of this specification in conjunction with the drawings of the embodiments of this specification. However, the following embodiments are only preferred embodiments of this specification and are not exhaustive. Based on the embodiments in the implementation mode, other embodiments obtained by those skilled in the art without making any creative work are all within the scope of protection of this specification.

[0030] Throughout this specification, the claims, and the accompanying drawings, the terms "first," "second," "third," and the like are used to distinguish between different items, not to describe a particular order. Furthermore, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or elements is not limited to the listed steps or elements but may optionally include steps or elements not listed, or may include other steps or elements inherent to the process, method, product, or apparatus.

[0031] In the following description, terms such as "inside", "outside", "up", "down", "left", "right", etc. that indicate directions or positional relationships are only used to facilitate the description of the embodiments and simplify the description. They do not indicate or imply that the devices or elements referred to must have a specific direction, be constructed and operate in a specific direction. Therefore, they should not be understood as limitations on this specification.

[0032] The data involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection of relevant data complies with the relevant laws, regulations and standards of relevant countries and regions.

[0033] Before introducing the technical solution in this specification, the application scenarios and related technologies of the technical solution are introduced.

[0034] 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 to work together has become an effective means to solve this problem. It includes small drones 21 and heavy-duty drones 22. The small drone 21 is mainly used to shuttle between fruit trees, quickly collecting freshly picked fruits to small collection points on the mountain. The small drone 21 is light and flexible, and can fly freely between trees, ensuring that the fruits can be delivered to the small collection points in a timely manner. The heavy-duty drone 22 transports the framed fruits at the small collection points to the collection station at the foot of the mountain. The heavy-duty drone 22 needs to transport a large amount of fruits at one time. The collection station at the foot of the mountain uses cars to transport the fruits to the logistics center. The heavy-duty drone 22 has a larger load capacity, but is slightly less flexible, so it is more suitable for transporting framed fruits with a relatively fixed route.

[0035] In addition to transporting fruit, it is also necessary to provide water and work meals, as well as other supplies such as tools, to the people working in the mountains. When transporting more concentrated supplies, such as transporting work meals to the mountains, a heavy-duty drone 22 can be used to transport a large amount of work meals and water at a time. When transporting smaller supplies, such as transporting a single tool or a small amount of water, a small drone 21 is faster and more convenient.

[0036] During these operations, the natural mountain environment and the specific mission conditions—such as fluctuating wind speeds and directions, the weight of the payload, and the duration of continuous operation—are key factors influencing drone failure rates. A drone malfunction can result in the loss of the payload and potentially endanger the safety of personnel and supplies on the ground. Furthermore, if a drone crashes or drops objects, personnel must be deployed to address them. This introduces additional risks if the drone is located in a steep and dangerous area of ​​the mountain. Therefore, minimizing the probability of drone failure is crucial.

[0037] This manual provides an intelligent dispatching system for industrial equipment based on fault warning, which is used for dispatching drones. Figure 2 ,include:

[0038] The first warning module 100 reads parameter data and mission data of the operating UAV and obtains a first failure probability based on a pre-established first failure model;

[0039] The second early warning module 200 reads the task environment data and obtains a second failure probability according to a pre-established second failure model;

[0040] The scheduling module 300 generates a scheduling plan for a plurality of operating drones to be scheduled according to the first failure probability, the second failure probability, and the task data within each preset scheduling period. The scheduling plan includes the operating drones and their corresponding task sequences.

[0041] The optimization module 400 obtains a total failure probability based on 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.

[0042] The small drone 21 and the load-carrying drone 22 are both connected to the server 10 and receive task assignment instructions from the server 10. The system is deployed on the server 10. The operating drone includes a drone and operating equipment, and the parameter data includes drone parameters and operating equipment parameters. The method for establishing the first fault model includes:

[0043] Establishing a simulation model of the operating equipment according to the operating equipment parameters of the operating drone;

[0044] Acquire data boundaries of task data, and generate multiple operation parameter samples according to the data boundaries;

[0045] Inputting the operation parameter sample into the simulation model, and obtaining a fault result according to the simulation of the simulation model;

[0046] The operation parameter sample is associated with the fault result, and the established machine learning model is trained to obtain a first fault model.

[0047] For example, the small drone 21 is equipped with a robotic arm as an operating device for lifting a small amount of bagged fruit or for picking fruit.

[0048] For example, drone parameters include: battery capacity: 20,000 mAh, maximum flight speed: 15 m / s, wind resistance: maximum wind speed of 10 m / s, and weight: 8 kg. Operating equipment parameters, specifically the robotic arm, include: load capacity: maximum 3 kg, operating range: 0.5 m radius, power type: electric, and operating temperature range: -10°C to 40°C.

[0049] First, a simulation model was built based on the operating equipment parameters. Based on the robot arm's parameters, a simulation model was created that simulated the robot arm's behavior and response under different operating conditions. This model was used to simulate the robot arm's performance when picking or lifting fruits of varying weights, such as from 0.5 kg to 3 kg.

[0050] Assume that the task data boundaries are: the weight of the fruit picked ranges from 0.5 kg to 3 kg, the ambient temperature varies from 10°C to 35°C, and the number of pickings ranges from 300 to 10,000. Based on the data boundaries of the task data, generate multiple operation parameter samples. For example, Sample 1: Picked weight = 0.5 kg, ambient temperature = 10°C, and number of pickings 500. Sample 2: Picked weight = 1.5 kg, ambient temperature = 25°C, and number of pickings 5000. Sample 3: Picked weight = 3 kg, ambient temperature = 35°C, and number of pickings 10,000. Data exceeding the task data boundaries can also be generated to simulate situations where the data boundaries are exceeded due to careless operation or underestimation. The operation parameter samples are input into the simulation model, and the simulated operation is repeated several times to obtain failure results.

[0051] Input the above samples into the simulation model and run simulations to observe whether the robot arm will fail under different conditions, such as failure due to overload or motor overheating due to excessive temperature. Record the results of each simulation, for example: Sample 1: No failure, Sample 2: No failure, Sample 3: Motor overheating protection is activated.

[0052] All operational parameter samples are associated with their corresponding failure outcomes to form a training set. For example, a decision tree algorithm is used to train this data to construct a prediction model. This model can predict the probability of a robotic arm failure based on input operational parameters (such as picking weight, ambient temperature, number of pickings, etc.) as the first failure probability.

[0053] On the other hand, the method for establishing the second fault model includes:

[0054] Clustering the drone parameters of the operating drones according to the drone parameters, classifying the operating drones according to the clustering results to obtain a plurality of categories, and obtaining the central drone parameters of the cluster centers corresponding to each category;

[0055] Reading mission environment data, and transforming the mission environment data into a dimension that matches the central UAV parameters;

[0056] Comparing the mission environment data with the central UAV parameters to obtain a comparison compliance vector;

[0057] receiving a fault label, and associating the fault label with the corresponding comparison compliance vector to obtain an environmental data sample;

[0058] Establish and use the environmental data samples to train a machine learning model to obtain a second fault model.

[0059] Several drones for fruit harvesting in mountainous areas are used, and the impact of mission environment data such as wind speed and temperature on drone operations is considered.

[0060] For example, the drone parameters for drone A are: maximum flight speed of 12 m / s, wind resistance of 8 m / s, weight of 6 kg, and battery capacity of 18,000 mAh. The drone parameters for drone B are: maximum flight speed of 15 m / s, wind resistance of 10 m / s, weight of 7 kg, and battery capacity of 20,000 mAh. The drone parameters for drone C are: maximum flight speed of 18 m / s, wind resistance of 14 m / s, weight of 9 kg, and battery capacity of 22,000 mAh. The drone parameters for drone D are: maximum flight speed of 10 m / s, wind resistance of 6 m / s, weight of 5 kg, and battery capacity of 16,000 mAh. The drone parameters for drone E are: maximum flight speed of 16 m / s, wind resistance of 12 m / s, weight of 8 kg, and battery capacity of 21,000 mAh.

[0061] Based on the drone parameters, the K-means clustering algorithm is used to classify the drones and calculate the center of each class, i.e., the cluster center. For example, class 1 includes drones A and D, with a maximum flight speed of 11 m / s, wind resistance of 7 m / s, weight of 5.5 kg, and battery capacity of 17,000 mAh. Class 2 includes drones B, C, and E, with a maximum flight speed of 16.3 m / s, wind resistance of 12 m / s, weight of 8.3 kg, and battery capacity of 21,000 mAh.

[0062] Read mission environment data, for example, the wind speed in a certain mission is 11.2 m / s, the temperature is 25°C, and the air pressure is 1009hPa.

[0063] Since temperature and air pressure are not directly involved in the central drone parameters, these two factors can be ignored or converted into factors that affect wind resistance in some way. Here, we only focus on wind speed as the key variable and retain only wind speed information, resulting in the data [11.2].

[0064] On the other hand, in another embodiment, an autoencoder model adjusts the dimensionality of the mission environment data to ensure that it matches the central drone parameters. The input layer receives the mission environment data (e.g., wind speed, temperature, and air pressure). The encoder (left half) compresses the input to 4 dimensions, while the decoder (right half) attempts to restore the original mission environment data. The output layer outputs data of the same dimensionality as the input. This model learns how to transform the mission environment data into a vector with the same dimensionality as the central drone parameters. The adjusted mission environment data is then compared with the central drone parameters for each category to obtain a comparison consistency vector. For example, for mission environment data with a wind speed of 11.2 m / s, the consistency value obtained when compared with the central drone parameters for category 1 is approximately 0.16, indicating that low-performance drones are not suitable for this environment. However, when compared with the central drone parameters for category 2, the consistency value obtained is approximately 0.76, indicating that high-performance drones are more suitable for this environment.

[0065] Receive the fault annotation and associate it with the corresponding comparison consistency vector to obtain an environmental data sample. Assume that under the above conditions, a serious fault has occurred in the drone. Therefore, we associate this fault annotation with the corresponding comparison consistency vector [0.16, 0.76] to form an environmental data sample.

[0066] Using the environmental data samples, including the comparison conformance vectors and corresponding fault labels, a machine learning model is trained to obtain a second fault diagnosis model. Examples include random forests or support vector machines (SVMs). This model can predict the probability of a UAV failure based on the input mission environment data. For example, given new mission environment data (wind speed of 10 m / s), the model can output a failure probability value, namely the second failure probability.

[0067] On the other hand, the method of reading the task environment data and obtaining the second fault probability according to the pre-established second fault model includes:

[0068] Transforming the dimension of the task environment data, and comparing the transformed task environment data with the drone parameters of the working drone performing the corresponding task to obtain a comparison compliance vector;

[0069] A second fault probability is obtained according to a response of the second fault model to the comparison compliance vector.

[0070] This solution can not only classify and evaluate drones according to their own characteristics, but also predict the possibility of drone failure in a specific environment based on actual mission environment conditions, thereby optimizing drone scheduling plans and improving operational efficiency and safety.

[0071] On the other hand, methods for presetting the scheduling period include:

[0072] Reading historical task environment data, and truncating the historical task environment data into environment data segments according to initial time lengths;

[0073] Clustering the environmental data segments using a clustering algorithm to obtain a plurality of cluster centers;

[0074] Counting the number of free environmental data segments, wherein the free environmental data segments are environmental data segments whose distance from any cluster center is greater than a preset distance threshold;

[0075] The proportion of the number of free environment data fragments is calculated, and the time length is adjusted using an optimization algorithm with the goal of minimizing the proportion of the number, and the scheduling period is set according to the optimized time length.

[0076] Collect historical mission environment data over a period of time. The data fields include: timestamp, wind speed (m / s), temperature (°C), and humidity (%). Truncate the historical mission environment data into environmental data segments based on the initial time length, which is 30 minutes. For example, the environmental data segments used in this embodiment are shown in Table 1.

[0077] Table 1 Environmental data segments used in this embodiment:

[0078] .

[0079] For all data segments, cluster analysis is performed on these feature vectors using a clustering algorithm such as K-means to identify 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]. A "free environment data segment" is a data segment whose distance from any cluster center is greater than a preset distance threshold. For example, the distance threshold is set to a Euclidean distance of 1. The Euclidean distance between each data segment's feature vector and the cluster center is calculated, and the number of data segments with distances exceeding 1 is counted. For example, a data segment with the feature vector [Wind Speed ​​= 9.0, Temperature = 24, Humidity = 42] has a distance of approximately 4.03 from Cluster Center 1 and approximately 2.45 from Cluster Center 2. Since both distances exceed the preset distance threshold of 1, this data segment is considered a free segment. There are 100 data fragments in total, 10 of which are marked as free fragments. The number of free fragments is 10%.

[0080] With the goal of minimizing the proportion of free fragments, the above steps are repeated by adjusting the initially set time length (for example, from 30 minutes to 20 minutes or 40 minutes) until the time length that minimizes the proportion of free fragments is found.

[0081] For example, when we try to shorten the duration to 20 minutes, we may find that the number of free segments has dropped to 5, and the proportion has dropped to 5%. This means that we have found a more optimal duration, 20 minutes. For example, 20 minutes is ultimately used as the final scheduling period setting.

[0082] By dynamically determining the scheduling cycle that best suits the current operating environment, the efficiency and stability of the drone scheduling system can be improved.

[0083] On the other hand, this manual also provides an intelligent scheduling method for industrial equipment based on fault warning, which is used for scheduling of operating drones. Figure 4 , including the steps of:

[0084] Step S1) reading parameter data and mission data of the operating UAV, and obtaining a first fault probability based on a pre-established first fault model;

[0085] Step S2) reading the task environment data and obtaining a second failure probability based on a pre-established second failure model;

[0086] Step S3) within each preset scheduling period, generating a scheduling plan for a plurality of operating drones to be scheduled based on the first failure probability, the second failure probability, and the task data, the scheduling plan including the operating drones and their corresponding task sequences;

[0087] Step S4) Obtain a total failure probability based on the first failure probability and the second failure probability, and optimize the scheduling scheme using an optimization algorithm with the goal of minimizing the total failure probability within the scheduling period.

[0088] See also Figure 5 A schematic structural diagram of an electronic device provided in an embodiment of this specification is shown.

[0089] like 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. The communication bus 1102 may be used to implement communication between the aforementioned components. The user interface 1103 may include buttons, and optionally may also include a standard wired interface or a wireless interface. The network interface 1104 may include, but is not limited to, a Bluetooth module, an NFC module, a Wi-Fi module, etc. The processor 1101 may include one or more processing cores. The processor 1101 utilizes various interfaces and circuits to connect the various components within the entire electronic device 1100. By running or executing instructions, programs, code sets, or instruction sets stored in the memory 1105 and accessing data stored in the memory 1105, it performs various functions of the routing device 1100 and processes data. Optionally, the processor 1101 may be implemented in hardware using at least one of a DSP, an FPGA, and a PLA. The processor 1101 may integrate one or a combination of a CPU, a GPU, and a modem. The CPU primarily processes the operating system, user interface, and applications; the GPU is responsible for rendering and drawing content displayed on the display; and the modem handles wireless communications.

[0090] It is understandable that the above-mentioned modem may not be integrated into the processor 1101, but may be implemented by a separate chip.

[0091] Memory 1105 may include either RAM or ROM. Optionally, memory 1105 may include non-transitory computer-readable media. Memory 1105 may be used to store instructions, programs, codes, code sets, or instruction sets. Memory 1105 may include a program storage area and a data storage area. The program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, sound playback function, image playback function, etc.), instructions for implementing the aforementioned method embodiments, etc.; the data storage area may store data related to the aforementioned method embodiments, etc. Memory 1105 may also optionally be at least one storage device located remotely from the aforementioned processor 1101. Memory 1105, as a computer storage medium, may include an operating system, a network communication module, a user interface module, and application programs. Processor 1101 may be configured to invoke the application programs stored in memory 1105 and execute the methods described in the aforementioned embodiments.

[0092] The embodiments of this specification also provide a computer-readable storage medium having instructions stored therein that, when executed on a computer or processor, cause the computer or processor to perform the steps of the aforementioned embodiments. If the components of the aforementioned electronic device are implemented as software functional units and sold or used as independent products, they may be stored in the computer-readable storage medium.

[0093] The embodiments of this specification also provide a computer program product, including a computer program, which implements multiple steps in the above embodiments when executed by a processor.

[0094] In the absence of conflict, the technical features in this embodiment and implementation scheme can be combined arbitrarily.

[0095] In the above embodiments, all or part of the embodiments can be implemented using software, hardware, firmware, or any combination thereof. When implemented using software, all or part of the embodiments can be implemented 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, all or part of the processes or functions described in the embodiments of this specification are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted via the computer-readable storage medium. The computer instructions can be transmitted from one website, computer, server 10, or data center to another website, computer, server 10, or data center via wired (e.g., coaxial cable, optical fiber, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible by a computer or a data storage device such as a server 10 or data center that integrates multiple available media. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a digital versatile disc (DVD)), or a semiconductor medium (eg, a solid state drive (SSD)).

[0096] When implemented via hardware or firmware, the aforementioned method flow is programmed into the hardware circuit to obtain the corresponding hardware circuit structure and realize the corresponding function. For example, a programmable logic device (PLD) (such as a field programmable gate array (FPGA)) is such an integrated circuit, whose logical function is determined by the user's device programming. Designers can "integrate" a digital system on a PLD through self-programming, eliminating the need for chip manufacturers to design and manufacture dedicated integrated circuit chips. Moreover, today, instead of manually manufacturing integrated circuit chips, this programming is often performed using "logic compiler" software. This is similar to the software compiler used in program development. Before compilation, the original code must also be written in a specific programming language, called a hardware description language (HDL). There are not just one HDL, but many. Those skilled in the art will also understand that simply by programming the method flow in one of the aforementioned hardware description languages ​​and programming it into the integrated circuit, a hardware circuit that implements the logical method flow can be easily obtained.

[0097] The embodiments described above are merely preferred embodiments of this specification and are not intended to limit the scope of this specification. Without departing from the design spirit of this specification, various modifications and improvements made to the technical solutions of this specification by ordinary technicians in this field should fall within the scope of protection determined by the claims of this specification.

Claims

1. An intelligent industrial equipment scheduling system based on fault warning, used for scheduling operating drones, characterized by: include: The first early warning module reads the parameter data and mission data of the operating UAV and obtains a first failure probability based on a pre-established first failure model; The second early warning module reads the task environment data and obtains the second fault probability according to the pre-established second fault model; a scheduling module, within each preset scheduling period, generating a scheduling plan for a plurality of operating drones to be scheduled based on the first failure probability, the second failure probability, and the task data, the scheduling plan including the operating drones and their corresponding task sequences; an optimization module, which obtains a total failure probability based on 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; Methods for presetting the scheduling period include: Reading historical task environment data, and truncating the historical task environment data into environment data segments according to initial time lengths; Clustering the environmental data segments using a clustering algorithm to obtain a plurality of cluster centers; Counting the number of free environmental data segments, wherein the free environmental data segments are environmental data segments whose distance from any cluster center is greater than a preset distance threshold; The proportion of the number of free environment data fragments is calculated, and the time length is adjusted using an optimization algorithm with the goal of minimizing the proportion of the number, and the scheduling period is set according to the optimized time length.

2. The intelligent industrial equipment scheduling system based on fault warning according to claim 1 is characterized in that: The operating drone includes a drone and operating equipment, and the parameter data includes drone parameters and operating equipment parameters. The method of establishing the first fault model includes: Establishing a simulation model of the operating equipment according to the operating equipment parameters of the operating drone; Acquire data boundaries of task data, and generate multiple operation parameter samples according to the data boundaries; Inputting the operation parameter sample into the simulation model, and obtaining a fault result according to the simulation of the simulation model; The operation parameter sample is associated with the fault result, and the established machine learning model is trained to obtain a first fault model.

3. The intelligent industrial equipment scheduling system based on fault warning according to claim 2 is characterized in that: The method of establishing the second fault model includes: Clustering the drone parameters of the operating drones according to the drone parameters, classifying the operating drones according to the clustering results to obtain a plurality of categories, and obtaining the central drone parameters of the cluster centers corresponding to each category; Reading mission environment data, and transforming the mission environment data into a dimension that matches the central UAV parameters; Comparing the mission environment data with the central UAV parameters to obtain a comparison compliance vector; receiving a fault label, and associating the fault label with the corresponding comparison compliance vector to obtain an environmental data sample; Establish and use the environmental data samples to train a machine learning model to obtain a second fault model.

4. The intelligent industrial equipment scheduling system based on fault warning according to claim 3 is characterized in that: The method of transforming the dimension of the mission environment data so that the dimension matches the central UAV parameter includes: Establishing an autoencoder model, wherein the output dimension of the left half of the autoencoder model matches the dimension of the central drone parameter; Training the autoencoder model using the task environment data until the accuracy of the autoencoder model reaches a preset accuracy threshold; A variable dimension model is obtained according to the left half of the autoencoding model, and the task environment data is variable dimensioned according to the variable dimension model.

5. The intelligent industrial equipment scheduling system based on fault warning according to claim 3 or 4, characterized in that: The method of reading the task environment data and obtaining the second fault probability according to the pre-established second fault model includes: Transforming the dimension of the task environment data, and comparing the transformed task environment data with the drone parameters of the working drone performing the corresponding task to obtain a comparison compliance vector; A second fault probability is obtained according to a response of the second fault model to the comparison compliance vector.

6. An intelligent scheduling method for industrial equipment based on fault warning, used for scheduling of operating drones, characterized in that: Including steps: Read parameter data and mission data of the operating UAV, and obtain a first fault probability based on a pre-established first fault model; Reading the task environment data, and obtaining the second fault probability according to a pre-established second fault model; In each preset scheduling period, generating a scheduling plan for a plurality of operating drones to be scheduled based on the first failure probability, the second failure probability, and the task data, the scheduling plan including the operating drones and their corresponding task sequences; Obtaining a total failure probability based on the first failure probability and the second failure probability, and optimizing the scheduling plan using an optimization algorithm with the goal of minimizing the total failure probability within the scheduling period; Methods for presetting the scheduling period include: Reading historical task environment data, and truncating the historical task environment data into environment data segments according to initial time lengths; Clustering the environmental data segments using a clustering algorithm to obtain a plurality of cluster centers; Counting the number of free environmental data segments, wherein the free environmental data segments are environmental data segments whose distance from any cluster center is greater than a preset distance threshold; The proportion of the number of free environment data fragments is calculated, and the time length is adjusted using an optimization algorithm with the goal of minimizing the proportion of the number, and the scheduling period is set according to the optimized time length.

7. 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 reads the executable program code stored in the memory to run a program corresponding to the executable program code, so as to execute the method according to claim 6.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to claim 6 is implemented.

9. Computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to claim 6 is implemented.

Images