Configuration of electrical components

Abstract

The invention relates to a method for configuring a component for an electrical installation, comprising the following steps: acquiring (S1) a data input of a user with respect to a specification of a property of the component by means of at least one human-machine interface; -providing (S2) input data derived from the data input to the artificial intelligence to produce output data, the output data parameterizing the component for a first set of parameters; -transmitting (S3) the output data to a fixedly programmed algorithm to determine a structure of a second set of parameters further parameterizing the component.

Description

Technical Field

[0001] The invention relates to a method for configuring components of an electrotechnical installation. Background Art

[0002] Fixed-programmed product configurators are known which guide the user through a sequence of data queries regarding the properties of a component.

[0003] This results in the problem that the input of the corresponding data via a data query sequence is complex and the data query is not easily understandable to everyone. Summary of the invention

[0004] Therefore, an object of the present invention is to make the configuration of components used in electrical installations more convenient for users.

[0005] Accordingly, it is stipulated that:

[0006] A method for configuring a component for an electrical installation comprises the following steps: obtaining a user's data input with the aid of at least one human-machine interface, the data input being a description of the characteristics of the component; providing input data derived from the data input to an artificial intelligence to generate output data, the output data parameterizing the component for a first set of parameters; transmitting the output data to a fixedly programmed algorithm to determine the structure of a second set of parameters that further parameterizes the component.

[0007] Electrotechnical facilities are systems used to generate, transmit, distribute or use electrical or electromagnetic energy (such as light). Fiber optics is a subfield of electrotechnical engineering.

[0008] Unless otherwise stated, algorithms may include artificial intelligence methods or may be implemented as fixed programmed algorithms.

[0009] Thus, an algorithm may be an artificial intelligence or a fixedly programmed algorithm according to claim 1 or another (fixedly programmed or artificial intelligence) algorithm.

[0010] The structure of the data describes how the information is organized in the data collection. For example, it includes data types such as free text, circuit diagrams, audio, etc., and data formats such as picture data such as JPG or digital data.

[0011] The parameter set includes zero, one, or more parameters of the component. Exemplary parameters include material, number of pins of a plug connector, grid of a plug connector, number of wires of a cable, function of the component, and any other characteristics describing the component.

[0012] User input refers to information, commands, or actions entered by a user into a computer system or software. These inputs can take various forms depending on how the system is designed and what types of interactions it allows. User input is the basic mechanism for communication between a user and a computer.

[0013] Examples of user input include keyboard input, mouse input, touch screen input, voice input, gesture input, form input, file upload, etc.

[0014] A human-machine interface or human-machine interface (HMI for short) allows an operator to operate a machine, an electrical or electronic device, and optionally to observe the machine status and intervene in controllable processes. The provision of information ("feedback") can be carried out by an operator console with signal lights, display areas or keys or by software through a visualization system running, for example, on a terminal. An example of an HMI is a light switch. The control commands are transmitted via a command generator. Exemplary HMIs for computers include a keyboard, a mouse, a dialog box for data selection, a touch pad, a microphone or a camera associated with appropriate software, etc.

[0015] Artificial intelligence is based on a model that is generated with the help of data, so-called training data, and aims at automating and learning intelligent behaviors. Artificial intelligence includes, for example, artificial neural networks, deep learning, machine learning, support vector machines, trees (such as decision trees, random trees, gradient boosting, search trees), etc.

[0016] Training of artificial intelligence (KI) refers to the process of using data and algorithms to adjust an AI model so that it can better perform a specific task. Training is a critical step in enabling AI to recognize patterns in data, make predictions, or complete the tasks for which it was developed.

[0017] The basic idea of ​​the invention is to enable a user to transfer known data, existing data and known information and knowledge in any data format within the scope of configuring components for electrical installations, wherein the transferred data are evaluated in such a way that they do not have to be re-entered.

[0018] According to the invention, it is provided that a first parameter set is determined based on the data input by means of artificial intelligence, wherein the first parameter set at least partially parameterizes the component.

[0019] In order to be able to process data input from which a parameter set for a fully parameterized component cannot be derived, provision is made for the output data to be transmitted to a fixedly programmed algorithm in order to determine the structure of a second parameter set for further parameterizing the component.

[0020] In this case, a combination of a trained artificial intelligence and a permanently programmed algorithm is achieved in such a way that the artificial intelligence makes the application particularly user-friendly, while the permanently programmed algorithm ensures that the training of the artificial intelligence or the generation of training data does not exceed the desired extent.

[0021] Of course, the second parameter set can also be empty, ie if a first parameter set of a fully parameterized component can be derived from the data input.

[0022] Advantageous embodiments and developments emerge from the further dependent claims and from the description with reference to the drawings.

[0023] According to a preferred improvement of the present invention, the first and / or second parameter set has a variable structure.

[0024] Thus, a user-friendly method for configuring components for electrotechnical installations is obtained, since the user can transfer all existing data or input and transfer existing knowledge by a method preferred by the user.

[0025] According to a preferred development of the present invention, the data input is of a variably structured type.

[0026] Thus, it is possible to let the user decide what type of data to transfer and in what form.

[0027] It is also advantageous here if the data input comprises image data, manually produced image data, photographs, circuit diagrams, audio data, free text and / or the like.

[0028] Accordingly, data input may be communicated using a variety of human interfaces, such as a keyboard, microphone, touch pad, camera, and / or file selection.

[0029] According to a preferred embodiment of the invention, a permanently programmed algorithm generates a request for a user input in order to determine the second parameter set.

[0030] Thus, it is conceivable that the user may interrogate parameters that are not extracted from the data input according to a pre-formulated query catalog.

[0031] Alternatively or additionally, it is also conceivable that the algorithm determines suitable data inputs based on the structure of the second parameter set in order to at least partially determine the second parameter set and proposes the determined data inputs to the user.

[0032] Accordingly, it is conceivable that the algorithm determines that some information about the component is missing, which information will be determined from the circuit diagram. In this case, it is advantageous to suggest to the user that the circuit diagram be transmitted.

[0033] Alternatively, it is also conceivable that the algorithm asks the user specific questions, which the user can answer using a keyboard or by voice input.

[0034] According to a preferred development of the invention, the method analyzes whether there are components parameterized by the first parameter set or by the first and second parameter sets, wherein provision is made for the components to be designed and / or mass-produced by means of artificial intelligence and / or fixedly programmed algorithms.

[0035] It is therefore conceivable that the check for the presence of the corresponding component can be implemented by artificial intelligence and / or a fixedly programmed algorithm.

[0036] It is of course also conceivable that the design or series production of components can be realized by artificial intelligence and / or fixedly programmed algorithms.

[0037] Here, it is also advantageous if the designed components are authorized by means of a permanently programmed algorithm.

[0038] Authorization can be understood as the creation of a part in the catalog, the ability of a user to order a part, or the release of a designed or mass-produced part for further process steps in the corporate structure.

[0039] It is advantageous here to carry out the authorization using a fixedly programmed algorithm in order to avoid the need for complex training of the artificial intelligence for this purpose.

[0040] According to a preferred improvement of the present invention, the artificial intelligence includes an artificial neural network, a SVM, a decision tree and / or a random tree.

[0041] When the computer program product is run on a computer, the computer program product of the method according to an embodiment of the present invention performs the steps of the method described above. When the program involved is used on a computer, the computer program product produces an effect, namely, software-assisted configuration of electrical facilities based on human technical knowledge. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The present invention will be further described below with reference to the exemplary embodiments illustrated in the schematic drawings of the accompanying drawings.

[0043] Figure 1 A schematic block diagram of an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0044] The accompanying drawings promote a further understanding of the embodiments of the present invention. The accompanying drawings illustrate the embodiments and are used in conjunction with the description to explain the principles and schemes of the present invention. Other embodiments and many of the advantages mentioned can be found in the accompanying drawings. The elements of the accompanying drawings are not necessarily shown to scale with each other.

[0045] In the figures of the drawings, identical elements, features and components having the same function and acting in the same manner are provided with the same reference symbols in each case, unless otherwise indicated.

[0046] Figure 1 A schematic block diagram of a method for configuring a component of an electrical installation is shown, which method has steps S1 to S3 . In step S1 , a user's data input regarding specifications of a property of a component is acquired by means of at least one human-machine interface.

[0047] In step S2 , input data are provided to the artificial intelligence, which are derived from the data input, in order to generate output data which parameterize the component for a first set of parameters.

[0048] In step S3 , the output data are passed to a fixedly programmed algorithm in order to determine the structure of a second parameter set for further parameterizing the component.

[0049] Description of Reference Numerals

[0050] S1-S3 Method Steps

Claims

1. A method for configuring a component for an electrical installation, comprising the following steps: - obtaining (S1) user input of data about characteristics of the component by means of at least one human-machine interface; - providing (S2) input data derived from the data input to the artificial intelligence to generate output data, the output data parameterizing the component for a first set of parameters; - transmitting (S3) said output data to a fixedly programmed algorithm to determine the structure of a second set of parameters further parameterizing said component.

2. The method according to claim 1, wherein: The first parameter set and / or the second parameter set are of variable structure.

3. A method according to any one of the preceding claims, wherein: The data input is of variable structure.

4. A method according to any one of the preceding claims, wherein: The data input may include image data, hand-crafted image data, photographs, circuit diagrams, audio data, free text and / or the like.

5. A method according to any one of the preceding claims, wherein: The fixedly programmed algorithm generates a query for user input to determine the second set of parameters.

6. A method according to any one of the preceding claims, wherein: An algorithm determines a suitable data input based on the structure of the second set of parameters to at least partially determine the second set of parameters and suggests the determined data input to the user.

7. A method according to any one of the preceding claims, wherein: With the aid of the method it is analyzed whether a component exists which is parameterized by the first parameter set or by the first and second parameter sets, wherein the component is designed and / or mass-produced with the aid of the algorithm.

8. The method according to claim 7, wherein: The designed and / or mass-produced components are authorized with the aid of the permanently programmed algorithm.

9. A method according to any one of the preceding claims, wherein: The artificial intelligence includes artificial neural networks, support vector machines, decision trees and / or random trees.

Images