# US 10,768,188 B2 · Diagnostic device and method for monitoring operation of a technical system > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,768,188 B2 - Document ID: US10768188B2 - Status: Granted - Kind: B2 - Application number: 15/665,636 - Filed: 2017-08-01 - Published: 2018-02-01 - Granted: 2020-09-08 - Earliest claimed: 2016-08-01 - Assignees: Siemens Aktiengesellschaft - Applicants: Siemens Aktiengesellschaft - Inventors: Thomas Bierweiler; Daniel Labisch - Web page: https://patentgrep.com/patent/US10768188B2 ## CPC - G01N 35/00693: {Calibration} - G01N 35/00584: {Control arrangements for automatic analysers} - G05B 23/0221: {Preprocessing measurements, e.g. data collection rate adjustment; Standardization of measurements; Time series or signal analysis, e.g. frequency analysis or wavelets; Trustworthiness of measurements; Indexes therefor; Measurements using easily measured parameters to estimate parameters difficult to measure; Virtual sensor creation; De-noising; Sensor fusion; Unconventional preprocessing inherently present in specific fault detection methods like PCA-based methods} - G06N 3/088: Non-supervised learning, e.g. competitive learning - G05B 23/024: {Quantitative history assessment, e.g. mathematical relationships between available data; Functions therefor; Principal component analysis [PCA]; Partial least square [PLS]; Statistical classifiers, e.g. Bayesian networks, linear regression or correlation analysis; Neural networks} - G01N: INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES (measuring or testing apparatus or processes other than immunoassay, involving enzymes or microorganisms C12M, C12Q) - G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract A diagnostic device and diagnostic method for monitoring operation of a technical system with an automation system, wherein values of process variables, which were previously automatically determined as relevant to a diagnosis by analyzing a program for a sequential function chart, are determined when each step of the cycle to be checked is executed and evaluated based on at least one predetermined self-organizing map acquired based on fault-free cycles during a system operation with repeatedly run step sequences such that automatic preselection of the process variables is which are relevant to the diagnosis is performed such that misdiagnoses can advantageously and largely be avoided and the reliability of the diagnostic statement can be increased. ## Claims ### Claim 1 A diagnostic device for monitoring operation of a technical system with an automation system, comprising: a data storage unit in which at least one data record having values of process variables and which identifies the operation of the technical system is storable; and an evaluation device via which, based on the at least one data record and at least one predetermined self-organizing map, a diagnostic statement about the operation of the technical system is at least one of (i) determinable and (ii) displayed; wherein the evaluation device is configured to analyze automatically, during operation of the technical system, a program for controlling the sequence via repeatedly run step sequences to determine whether at least one part of the process variables is relevant to the diagnosis, the data record being an n-tuple with a plurality n of coordinates. ### Claim 2 (depends on 1) The diagnostic device as claimed in claim 1, wherein the evaluation device is configured to determine at least one of (i) controlled variables and (ii) measured variables set in steps in a step sequence, which are queried in steps in the step sequence to monitor a transition condition, as process variables which are relevant to the diagnosis. ### Claim 3 (depends on 2) The diagnostic device as claimed in claim 2, wherein the evaluation device is configured to use a data record and the predetermined self-organizing map to at least one of (i) determine and (ii) display the diagnostic statement for steps in the step sequence in each case. ### Claim 4 (depends on 1) The diagnostic device as claimed in claim 1, wherein the evaluation device is configured to use a data record and the predetermined self-organizing map to at least one of (i) determine and (ii) display the diagnostic statement for steps in the step sequence in each case. ### Claim 5 (depends on 4) The diagnostic device as claimed in claim 4, wherein the evaluation device is configured to automatically determine at least one of (i) controlled variables and (ii) measured variables set in a respective step, which are queried in the respective step for monitoring a transition condition, as process variables which are relevant to the diagnosis in the respective step. ### Claim 6 (depends on 1) The diagnostic device as claimed in claim 1, wherein n-tuples which correspond to data records and have predetermined values of process variables for error-free cycles in a step sequence are stored on a node of the at least one predetermined self-organizing map; and wherein the evaluation device is further configured to detect and indicate a variance in the system behavior during the cycle, to be checked, based on the at least one predetermined self-organizing map, in a step sequence from a behavior during error-free cycles. ### Claim 7 (depends on 1) The diagnostic device as claimed in claim 1, wherein the evaluation device is configured to determine a smallest Cartesian distance between the data record of a cycle to be checked and a node of the at least one predetermined self-organizing map to detect a variance in behavior of the technical system. ### Claim 8 (depends on 7) The diagnostic device as claimed in claim 7, wherein the evaluation device is configured to indicate, as a diagnostic statement, a variance from normal behavior in cases of the cycle, to be checked, in a step sequence if the Cartesian distance exceeds a predetermined threshold value. ### Claim 9 (depends on 1) The diagnostic device as claimed in claim 1, wherein the evaluation device is configured to store a plurality of data records identifying an error-free operation of the technical system to predetermine the at least one predetermined self-organizing map prior to a cycle, to be checked, in the data storage unit and configured to calculate n-tuples with values of process variables for error-free cycles for nodes based on said plurality of data records via a learning method and configured to deposit said n-tuples on the nodes of the at least one predetermined self-organizing map. ### Claim 10 (depends on 9) The diagnostic device as claimed in claim 9, wherein the evaluation device is configured to store further data records identifying an error-free operation of the technical system in the data storage unit prior to a cycle to be checked, determine a winner node for the each data record, calculate a respective maximum distances of the data records from winner nodes assigned thereto and to store said calculated respective maximum distance, in each case increased by a margin to avoid misdiagnoses, as predetermined threshold values assigned to the each winner node. ### Claim 11 (depends on 1) The diagnostic device as claimed in claim 1, wherein at least the data storage unit and the evaluation device are implemented via software on a remote service computer for remote diagnosis of the system. ### Claim 12 A diagnostic method for monitoring the operation of a technical system, the method comprising: storing at least one data record which identifies the operation of the technical system and which has values of process variables in a data storage unit; determining a diagnostic statement about the operation of the technical system based on the at least one data record and at least one predetermined self-organizing map, analyzing automatically, during operation of the technical system, a program for controlling a sequence via repeatedly run step sequences to determine whether at least one part of the process variables is relevant to the diagnosis; assigning in each case a coordinate of the data record to the process variables previously determined as relevant to a diagnosis, the data record being an n-tuple with a plurality n of coordinates. ### Claim 13 A non-transitory computer-readable medium encoded with a computer program which, when executed by a computer, causes operation of a technical system with an automation system to be monitored, the computer program comprising: program code for storing at least one data record which identifies the operation of the technical system and which has values of process variables in a data storage unit; program code for determining a diagnostic statement about the operation of the technical system based on the at least one data record and at least one predetermined self-organizing map; program code for analyzing automatically, during operation of the technical system, a program for controlling a sequence via repeatedly run step sequences to determine whether at least one part of the process variables is relevant to the diagnosis; and program code for assigning in each case a coordinate of the data record to the process variables previously determined as relevant to a diagnosis, the data record being an n-tuple with a plurality n of coordinates. ### Claim 14 (depends on 13) The non-transitory computer-readable medium as claimed in claim 13, wherein the non-transitory computer-readable medium comprises a storage medium.