# US 11,309,906 B2 · Method, field device and cloud infrastructure for data acquisition

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 11,309,906 B2
- Document ID: US11309906B2
- Status: Granted
- Kind: B2
- Application number: 16/629,354
- Filed: 2017-07-17
- Published: 2021-05-06
- Granted: 2022-04-19
- Earliest claimed: 2017-07-17
- Assignees: Siemens Aktiengesellschaft
- Applicants: Siemens Aktiengesellschaft
- Inventors: Steffen Lamparter; Ingo Thon
- Web page: https://patentgrep.com/patent/US11309906B2

## CPC

- H03M 7/3059: {Digital compression and data reduction techniques where the original information is represented by a subset or similar information, e.g. lossy compression}
- H03M 7/6064: {Selection of Compressor}
- H04L 67/1097: for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
- H03M: CODING; DECODING; CODE CONVERSION IN GENERAL (using fluidic means F15C4/00; optical analogue/digital converters G02F7/00; coding, decoding or code conversion, specially adapted for particular applications, see the relevant subclasses, e.g. G01D, G01R, G06F, G06T, G09G, G10L, G11B, G11C, H04B, H04L, H04M, H04N; ciphering or deciphering for cryptography or other purposes involving the need for secrecy G09C)
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

A sensor data are compressed on field devices using a representation is provided. The field device immediately decompresses the compressed data in order to detect a deviation. If there is a deviation, then a cloud storage receives the sensor data as raw uncompressed data. A cloud component receives a trigger signal from the field device, indicating that the representation used by the field device for compression does not sufficiently describe the sensor data. The cloud component then learns a new representation by retrieving and analyzing all data stored in the cloud storage. The method and field device provide robust, compression-based data acquisition. They improve quality and precision of the data captured by the field devices. As the representation in the field device can be updated, it becomes possible to accommodate changes in the device setup. The cloud infrastructure provides automatic learning of the representation in the cloud.

## Claims

### Claim 1

A method for data acquisition,
with the following steps:
acquiring, by a sensor of a field device, sensor data,
compressing, by a data compressor of the field device using a representation, the sensor data to generate compressed data,
decompressing, by a data decompressor of the field device using the representation, the compressed data to generate decompressed data, and
comparing, by a comparison unit of the field device, the sensor data with the decompressed data, and detecting a deviation if a difference between the sensor data and the decompressed data exceeds a threshold.

### Claim 2 (depends on 1)

The method according to claim 1, with the additional steps of
sending the compressed data to a first cloud component, and
decompressing, by the first cloud component using the representation, the compressed data, and storing the decompressed data in a cloud storage.

### Claim 3 (depends on 1)

The method according to claim 1, with the additional step of
sending the sensor data as raw uncompressed data to a cloud storage, if the comparison unit detects a deviation.

### Claim 4 (depends on 2)

The method according to claim 2, with the additional step of
sending the sensor data as raw uncompressed data to the cloud storage, and
replacing decompressed data that was stored by the first cloud component with the raw uncompressed data in the cloud storage,
if the comparison unit detects a deviation.

### Claim 5 (depends on 3)

The method according to claim 3, with the additional steps of
learning, by a second cloud component, a new representation, by retrieving and analyzing all data stored in the cloud storage, and
replacing the representation used by the data compressor and the data decompressor with the new representation, if the comparison unit detects a deviation.

### Claim 6 (depends on 4)

The method according to claim 4, with the additional steps of
learning, by a second cloud component, a new representation, by retrieving and analyzing all data stored in the cloud storage, and
replacing the representation used by the data compressor, the data decompressor and the first cloud component, with the new representation, if the comparison unit detects a deviation.

### Claim 7 (depends on 1)

The method according to claim 1, with the additional step of
triggering an alarm on the field device, if the comparison unit detects a deviation.

### Claim 8 (depends on 2)

The method according to claim 2,
with many field devices sending data to the cloud storage.

### Claim 9 (depends on 8)

The method according to claim 8,
wherein the second cloud component creates multiple new representations if the data in the cloud storage are heterogeneous, and
wherein the second cloud component deploys one of the multiple representations to each of the field devices.

### Claim 10 (depends on 1)

The method according to claim 1, with the data compressor and data decompressor being parts of a neural autoencoder.

### Claim 11 (depends on 5)

The method according to claim 5,
wherein the learning of the new representation comprises using a back-propagation algorithm or a Limited-memory Broyden-Fletcher-Goldfarb-Shannon algorithm.

### Claim 12 (depends on 10)

The method according to claim 10,
wherein the learning of the new representation comprises using weight decaying or a sparsity autoencoder.

### Claim 13

A field device,
configured for acquiring sensor data from at least one sensor,
with a data compressor, configured for compressing, using a representation, the sensor data generate compressed data,
with a data decompressor, configured for decompressing, using the representation, the compressed data to generate decompressed data, and
with a comparison unit, configured for comparing the sensor data with the decompressed data, and detecting a deviation if a difference between the sensor data and the decompressed data exceeds a threshold.

### Claim 14 (depends on 13)

The field device according to claim 13,
with a network interface and configured for sending the compressed data to a cloud, in a first cloud component.

### Claim 15 (depends on 13)

The field device according to claim 13,
with a network interface and configured for sending the sensor data as raw uncompressed data to a cloud storage, if the comparison unit detects a deviation.

### Claim 16 (depends on 13)

The field device according to claim 13,
configured for generating an alarm if the comparison unit detects a deviation.

### Claim 17

A cloud infrastructure,
with a cloud storage, configured for receiving sensor data as raw uncompressed data from at least one field device,
with a second cloud component, configured for
receiving a trigger signal from a field device, the trigger signal indicating that a representation used by the field device for compression of sensor data does not sufficiently describe the sensor data, and
learning a new representation by retrieving and analyzing all data stored in the cloud storage.

### Claim 18 (depends on 17)

The cloud infrastructure according to claim 17,
with a first cloud component configured for
receiving compressed data from the field device,
decompressing the compressed data using a representation stored in the cloud, and
storing decompressed data in the cloud storage;
wherein the cloud storage is configured for overwriting decompressed data with corresponding raw uncompressed data in case raw uncompressed data are received.

### Claim 19 (depends on 17)

The cloud infrastructure according to claim 17,
connected to several field devices, and
wherein the second cloud component is configured for
creating multiple new representations the data in the cloud storage are heterogeneous, and
deploying one of the multiple new representations to each of the field devices.

### Claim 20 (depends on 17)

A network for data acquisition,
with a cloud infrastructure according to claim 17 and
with several field devices.

### Claim 21 (depends on 1)

A computer-readable storage media having stored thereon:
instructions executable by one or more processors of a computer system, wherein execution of the instructions causes the computer system to perform the method according to claim 1.

### Claim 22 (depends on 1)

A computer program,
which is being executed by one or more processors of a computer system and performs the method according to claim 1.