Production Line KPI Generation from Multi-Sensor Data

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The complexity of food processing lines and the variety of sensors used make it challenging and time-consuming to set up a structure for reliably measuring key performance indicators (KPIs), as each line can be configured differently with varying equipment and sensor types, leading to inefficiencies in determining KPIs.

Innovation Solution

A method and system for processing sensor input data using a variables generator and a KPI generator, with shared generation schemes and data centers, to efficiently determine KPIs by standardizing variable and KPI calculations across production lines, ensuring reliability and reducing setup time.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If different sensors and equipment configurations are used in food processing lines to meet diverse production needs, then adaptability and versatility are improved, but device complexity and difficulty of determining KPIs increase

Engineering Contradiction:
ImproveadaptabilityVSAvoidcomplexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent implements a universal KPI determination system that can handle multiple sensor types (magnetic relays, temperature sensors, conductive sensors, flow transmitters) and different production line configurations through a single standardized interface. The system uses standardized data collection methods and unified processing logic that work across diverse sensor configurations, allowing one system to serve multiple functions and adapt to various production needs without requiring separate KPI determination setups for each configuration.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system manages complexity by dynamically adjusting processing parameters based on the specific sensor configuration detected. When different sensor types are identified, the system automatically modifies its data collection frequency, processing algorithms, and aggregation methods accordingly. This allows the system to adapt to various production line setups while maintaining a consistent underlying architecture, resolving the contradiction between handling diverse configurations and maintaining system simplicity.

Inventive Principle:
Principle #35Parameter changes

2Adaptability or versatility

If customized sensor configurations are implemented for different production lines, then adaptability is improved, but time required to set up KPI measurement structures increases

Engineering Contradiction:
ImproveadaptabilityVSAvoidsetup time
Core Design Contradiction:
Adaptability or versatilityVSLoss of time

Solution Approach 1:

The patent employs pre-configured templates and standardized data structures for common sensor types and production line configurations. Before deployment, the system comes with built-in knowledge of how to process data from various sensor types (magnetic relays, temperature sensors, etc.) and pre-established KPI calculation methodologies. When a production line is set up, the system automatically matches the detected sensor configuration to appropriate pre-configured templates, eliminating the need to create KPI measurement structures from scratch and dramatically reducing setup time while maintaining adaptability.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system uses template copying and configuration reuse across different production lines. Once a KPI measurement structure is established for a particular sensor configuration, it can be replicated and adapted for similar production lines. The system stores successful configurations as reusable templates that can be copied and modified for new installations, significantly reducing the time required to set up KPI measurement structures for subsequent production lines while maintaining the ability to handle diverse configurations.

Inventive Principle:
Principle #26Copying

3Productivity

If standardized variable and KPI generation schemes are implemented across production lines, then productivity and reliability are improved, but information security and confidentiality may be compromised

Engineering Contradiction:
ImproveproductivityVSAvoidinformation security
Core Design Contradiction:
ProductivityVSLoss of information

Solution Approach 1:

The patent divides the data architecture into distinct segments: standardized variable generation schemes that are shared across production lines for consistency and productivity, and production-line-specific KPI generation schemes that remain localized and confidential. The system separates universal processing logic (which can be standardized) from proprietary business logic (which should remain confidential). This segmentation allows standardized variables to be generated efficiently while keeping sensitive KPI calculations and business rules confined to individual production lines, thus maintaining both productivity and information security.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system introduces an intermediary layer that acts as a buffer between standardized data collection and proprietary KPI generation. This intermediary layer handles the standardized variable generation and data normalization, then passes processed data to the production-line-specific KPI generation systems. The intermediary ensures that standardized processing benefits are achieved while the actual sensitive KPI calculations and business logic remain isolated and confidential to each production line, preventing unauthorized access while maintaining productivity through standardization.

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentEP3751482B1A method for processing sensor input data captured from sensors placed in a production line, and a system thereof
Publication Date: 2026.02.25 TETRA LAVAL HOLDINGS & FINANCE SA
  • EP3751482B1 patent drawingFigure 1
  • EP3751482B1 patent drawingFigure 2
  • EP3751482B1 patent drawingFigure 3

AI summary

A method (400) for processing sensor input data (118, 120 ,122, 124) captured from sensors (110, 112, 114, 116) placed in a production line (102). The method comprises receiving (402) sensor input data (118, 120, 122, 124) from the sensors (110, 112, 114, 116) placed in the production line by a variables generator (126), wherein the variables generator (126) comprises a first processor (302), a first data communications module (304) and a first memory (306), generating (404) a number of variables (128, 130) based on the sensor input data (118, 120, 122, 124) according to a variable generation scheme (142), transferring (406) the number of variables (128, 130) to a key performance indicator (KPI) generator (146), wherein the KPI generator (146) comprises a second processor (308), a second data communications module (310) and a second memory (312), generating (408) a number of key performance indicators (KPIs) (134, 136) based on the number of variables (128, 130) according to a KPI generation scheme (146), and transferring (410) the number of KPIs () to a user interface (Ul) enabled device (138).