Use data to improve workplace health and safety

Overcome health and safety challenges with advanced analytics

The ability to provide a safe manufacturing workplace and effectively support compliance has never been more vital. Today’s employers have learned the importance of not only managing day-to-day workplace safety but also being prepared to maintain health and safety during major events, such as wars, natural disasters, and pandemics. And while safety has always been critical in any manufacturing environment, it gains even more significance in the context of Manufacturing 4.0.

With the increased integration of digital technologies and automation systems and the implementation of advanced technologies, such as robotics, artificial intelligence, and the Internet of Things, employees will interact ever more closely with automated systems and use interconnected devices, sensors, and automated machinery. Maintaining proper safety standards and protocols for these technologies is crucial to safeguard employees and prevent incidents, such as equipment malfunctions, electrical hazards, and unexpected and unplanned interactions between humans and machines.

Beyond their potential to impact an employee’s quality of life, incidents are expensive. The direct costs, including workers’ compensation and medical and legal services, can be substantial, but the indirect costs of an incident shouldn’t be underestimated; these include retraining, investigations, corrective measures, lost productivity, damage to equipment, reputational risk, and costs associated with lower employee morale, absenteeism, and retention.

To manage health and safety, manufacturers track a host of key metrics, such as

• The total recordable injury frequency rate (the number of injuries occurring in a workplace per 100,000 hours worked)
• The number of incidents per month
• Preventive safety-related incidents or required actions to be taken by employees
• The average time to resolve incidents
• The types of incidents

However, many organizations struggle to get timely notifications of health and safety incidents in their workplaces let alone use their data to model and predictively identify potential risks in their manufacturing environments. But it’s essential that they develop these abilities—and the right data platform can help. By using data and analytics to identify potential hazards and implement preventive measures, companies can mitigate risks, prevent accidents and incidents, and reduce the likelihood of production disruptions, financial losses, and reputational damage.

This use case describes the data analytics architecture required to ingest, store, manage, and gain insight from data to improve health and safety in the manufacturing sector.

How a comprehensive data platform can help you improve workplace safety

The architecture presented here incorporates the most commonly recommended Oracle components used to build an analytics architecture that covers the entire data analytics lifecycle, from discovery through to measurement and action. Manufacturers vary by type and complexity, but in general, the services outlined here will come into play when building data analytic architectures that focus on the wide variety of factors that impact workplace health and safety.

This image shows how Oracle Data Platform for manufacturing can be used to support health and safety. The platform includes the following five pillars:

1. 1. Data Sources, Discovery
2. 2. Ingest, Transform
3. 3. Persist, Curate, Create
4. 4. Analyze, Learn, Predict
5. 5. Measure, Act

The Data Sources, Discovery pillar includes two categories of data.

1. Business record data comprises data from HCM, Environment Health and Safety (EHS) Systems, HR & Training Systems Production Process, Incident reporting systems, Safety Systems.
2. Technical input data includes Images, Email, Videos, Paper Documentation (OCR), Discrete events (emergency stop of production line).

The Ingest, Transform pillar comprises three capabilities.

1. 1. Batch ingestion uses OCI Data Integration, Oracle Data Integrator, and DB tools.
2. 2. Bulk transfer uses OCI FastConnect, OCI Data Transfer, MFT, and OCI CLI.
3. 3. Change data capture uses OCI GoldenGate.

All three capabilities connect unidirectionally into the serving data store and cloud storage within the Persist, Curate, Create pillar.

The Persist, Curate, Create pillar comprises five capabilities.

1. 1. The serving data store uses Oracle Autonomous Data Warehouse and Exadata Cloud Service.
2. 2. Cloud storage uses OCI Object Storage.
3. 3. Governance uses OCI Data Catalog.

These capabilities are connected within the pillar. Cloud storage is unidirectionally connected to the serving data store and managed Hadoop; it is also bidirectionally connected to batch processing.

One capability connects into the Analyze, Learn, Predict pillar. The serving data store connects to both the analytics and visualization capability and also to the data products, APIs capability.

The Analyze, Learn, Predict pillar comprises two capabilities.

1. 1. Analytics and visualization uses Oracle Analytics Cloud, GraphStudio, and ISVs.
2. 2. Data products, APIs uses OCI API Gateway and OCI Functions.

The Measure, Act pillar captures how the data analysis may be used: by people and partners and, applications and models.

Peoples and Partners comprises Historical Data, Incident Report Heat Maps, Near-Miss Incidents, Compliance Reporting, Root Cause Analysis, Risk Identification and Assessment.

Applications & Models is standalone and implementation specific.

The three central pillars—Ingest, Transform; Persist, Curate, Create; and Analyze, Learn, Predict—are supported by infrastructure, network, security, and IAM.

Connect, ingest, and transform data

Our solution is composed of three pillars, each supporting specific data platform capabilities. The first pillar provides the capability to connect, ingest, and transform data.

There are three main ways to inject data into an architecture to enable manufacturing organizations to improve workplace health and safety.

• To start our process, if necessary, we’ll enable the bulk transfer of operational transaction data. Bulk transfer services are used in situations where large volumes of data need to be moved to Oracle Cloud Infrastructure (OCI) for the first time—for example, data from existing on-premises analytic repositories or other cloud sources. Generally speaking, datasets related to health and safety aren’t large. Bulk transfer is listed here as a potential component in the rare case that extensive historical data is stored on-premises and needs to be moved to the cloud or if this data is comingled with a larger historical on-premises data warehouse that is being moved to OCI. The specific bulk transfer service we’ll use will depend on the location of the data and the transfer frequency. For example, we may use OCI Data Transfer Service or OCI Data Transfer Appliance to load a large volume of on-premises data from historical planning or data warehouse repositories. When large volumes of data must be moved on an ongoing basis, we recommend using OCI FastConnect, which provides a high-bandwidth, dedicated private network connection between a customer’s data center and OCI.
• Data sources used to measure and report on health and safety typically have an underlying relational data store. OCI GoldenGate can be used to capture data in near real time from incident reporting systems. OCI GoldenGate uses change data capture to detect change events in the underlying structure of the systems that monitor the production environment (for example, temperature, noise or emergency stop of the production line, maintenance operations, and so on) and sends the data in real time to a persistence layer and/or the streaming layer. In this use case, however, data is generally going to be moved through batch ETL processes.
• While streaming and real-time needs are evolving quickly, the most common extract from operations, planning, maintenance, workforce management, HR, training, and safety management systems is some kind of batch ingestion using an ETL process. Batch ingestion is used to import data from systems that can’t support data streaming. This data is generally located in environmental health and safety systems, HR and training systems, and incident reporting systems. These extracts can be ingested frequently, as often as every 10 or 15 minutes, but they are still batch in nature as groups of transactions are extracted and processed rather than individual transactions. OCI offers different services to handle batch ingestion, such as the native OCI Data Integration service and Oracle Data Integrator running on an OCI Compute instance. The choice of service would primarily be based on customer preference rather than technical requirements.

Persist, process, and curate data

Data persistence and processing is built on two (optionally three) components. Some customers will use all of them, others a subset. Depending on the volumes and data types, data could be loaded into object storage or loaded directly into a structured relational database for persistent storage. When we anticipate applying data science capabilities, then data retrieved from data sources in its raw form (as an unprocessed native file or extract) is more typically captured and loaded from transactional systems into cloud storage.

• Cloud storage is the most common data persistence layer for our data platform. It can be used for both structured and unstructured data. OCI Object Storage, OCI Data Flow, and Oracle Autonomous Data Warehouse (ADW) are the basic building blocks. Data retrieved from data sources in its raw format is captured and loaded into OCI Object Storage. OCI Object Storage is the primary data persistence tier.
• We’ll now use a serving data store to persist our curated data in an optimized form for query performance and analytics. We can access our raw data stored in object storage directly from Oracle Autonomous Data Warehouse by creating an external table that maps to the data files stored in OCI Object Storage. An external table provides a virtual view of the data in the object storage location without necessarily requiring that we physically move or load the data into Autonomous Data Warehouse. Data identified as valuable for further analysis can now be loaded into the serving data store, which provides a persistent relational tier used to serve high-quality curated data directly to end users via SQL-based tools. In this solution, Autonomous Data Warehouse is instantiated as the serving data store for the enterprise data warehouse and, if required, more-specialized domain-level data marts.
• ADW can also be the data source for data science projects or the repository required for Oracle Machine Learning. The serving data store may alternatively take one of several forms, including Oracle Database Cloud Service or Oracle Database Exadata Cloud Service.

Analyze data, learn, and predict

The ability to analyze, learn, and predict is facilitated by two services enabling three analytics approaches and access to the modeled data.

• Advanced analytics capabilities are increasingly important for maintaining a safe manufacturing environment and optimizing the production process. In this use case, we rely on Oracle Analytics Cloud to deliver analytics and visualizations. This enables you to use descriptive analytics (describes current trends with histograms and charts), predictive analytics (predicts future events, identifies trends, and determines the probability of uncertain outcomes), and prescriptive analytics (proposes suitable actions to support optimal decision-making).

  • Descriptive analytics can help manufacturers identify potential risks and hazards by analyzing historical data, incident reports, and near-miss incidents. By identifying patterns and trends, analytics can highlight areas that require attention and help you prioritize risk mitigation efforts. Additionally, analytics can enable a continuous improvement mindset when it comes to health and safety. By analyzing performance metrics and safety data over time, manufacturers can identify areas for improvement, set benchmarks, and track progress toward safety goals.

    When accidents or incidents occur, descriptive analytics can help investigate the root causes and underlying factors. By analyzing incident reports, witness statements, and other relevant data, patterns and trends can be identified, helping you carry out targeted interventions to prevent similar incidents in the future.

  • Predictive analytics uses safety data to identify patterns, trends, and potential risks to help manufacturers enhance safety measures and prevent accidents and incidents. By analyzing historical safety data, predictive models can identify long-term trends and patterns, such as increasing accident rates, emerging safety risks, or areas where safety measures have been effective, and also assign risk scores to different activities, processes, or conditions. These scores help prioritize resources and interventions to address areas with higher risk levels. Anomalies in safety data, such as unusual patterns or outliers, may indicate potential safety issues or deviations from normal operating conditions, allowing for early detection and prompt corrective actions.
  • Prescriptive analytics supports training and education efforts by identifying areas where additional training is needed. By analyzing safety-related data, such as near-miss incidents or deviations from standard operating procedures, manufacturers can pinpoint gaps in employee knowledge or adherence to safety protocols and implement targeted training interventions.
• Data governance is a critical component. This will be delivered by OCI Data Catalog, a free service providing data governance and metadata management (for both technical and business metadata) for all the data sources in the data platform ecosystem. OCI Data Catalog is also a critical component for queries from Oracle Autonomous Data Warehouse to OCI Object Storage as it provides a way to quickly locate data regardless of its storage method. This allows end users, developers, and data scientists to use a common access language (SQL) across all the persisted data stores in the architecture.
• Our curated, tested, and high-quality data and models can have governance rules and policies applied and can be exposed as a data product (API) by OCI API Gateway within a data mesh architecture for the distribution of safety-related data and analytics across the manufacturing organization.

The benefits of using data to enhance health and safety in the manufacturing industry

Manufacturers have a responsibility to prioritize the health and well-being of their employees. A safe work environment is not only a legal and ethical requirement, but it also impacts employee morale, job satisfaction, and overall well-being. Prioritizing health and safety helps create a positive work culture, enhances employee engagement, and reduces the risk of workplace accidents and injuries. However, ensuring a healthy and safe work environment is particularly challenging in the manufacturing industry—and the challenges are likely to increase over the coming years, driven by Manufacturing 4.0.

In this evolving landscape, manufacturers must not only ensure health and safety measures are in place but also continuously identify opportunities to improve those measures and take preventive actions to avoid accidents, injuries, and occupational illnesses. To do this, they need robust data- and analytics-driven health and safety processes supported by technology, enabling them to

• Capture and manage critical event information and manage all documentation and photos within a single environment
• Collect compliance data to support regulatory reporting
• Manage hazard data—including information about incidents, near misses, and unsafe conditions
• Discover root causes, investigate the incident, and respond immediately
• Track and analyze safety using advanced analytics to monitor progress and detect trends and patterns

Ultimately, these actions help safeguard the physical health and safety of workers, reduce the likelihood of absenteeism and medical expenses, and help maintain productivity and operational continuity.