• Email info@ctsols.com
  • Phone 703-289-1560

Asset intelligence is used in monitoring the real-time conditions of the assets in organizations. Assets have to be connected in order to achieve that purpose. We use IoT to equip assets deployed in the field with built-in sensors that provide data regarding the health of the equipment. This data is analyzed by the RedRiver platform which is then able to predict issues ahead of time and take necessary remedial action. This has meant a break from the old-fashioned way of companies spending huge amounts on scheduled maintenance procedures that may or may not be needed. With an IoT solution in place, companies need to perform maintenance only when needed. This increases the longevity of machine parts and optimizes labor time. Eventually, it also results in more satisfied users within the organization.

The boundaries between agency managers and internal users are fast disappearing as real-time analytics and predictive maintenance create totally new working models. Agency managers will be able to monitor the health of all their assets, including those in use and those which are dormant. This means the location of the assets, who are currently using them, standard operating procedures, insurance details, and other relevant aspects. This enables them to deliver outcomes and not just physical assets.

Today the agency manager’s responsibilities are confined to only the uptime and availability of assets. But they should be able to ensure that the assets work. Uptime is therefore of vital importance. This means that the manager should go in for optimum maintenance. How to ensure that? Through predictive rather than reactive maintenance. Predictive analysis helps one get there. By analyzing sensor data based on past performance data, the manager will be able to strike a balance that optimizes maintenance and drives down costs. This is what makes the asset-as-a-service collaborative model attractive to the agency manager.

The asset intelligence thus gathered, provides insights to the agency manager about how to improve the management of a future asset. Also, he gets to learn how the asset can better interact with his business processes to create more value, thereby enabling the agency to move up the value chain.

Transform your business with IoT

 Asset Optimization

Assets are intended to generate revenue. Therefore, an asset tracking plan includes having a clear idea of where the assets are located and their running condition, replenishment needs, etc. The performance of the assets has to be continuously monitored in most cases. Predictive maintenance is part of asset optimization to keep the efficiency of assets high. IoT sensors keep track of asset performance and generate information that helps the organization to take timely decisions to avoid costs and extend the life of assets.

Asset Tracking 

 Monitoring Maintenance

Use RedRiver to monitor your assets, machines, equipment and devices in real-time. When you monitor the health of assets regularly, you will be able to reduce relational operational costs. When temperature, pressure or humidity is outside a permissible range, the IoT sensor can instantly alert Plant Managers triggering a needed response. 


Security is a salient feature of RedRiver. It uses bank-level AES-256 data authentication and data encryption to ensure that the data is kept secure and confidential.

Asset Modeling

 Assets should be created from asset models which are declarative structures that standardize the format of your assets. Data can be processed in assets that represent groups of devices as asset models have consistent information across multiple assets of the same type. Create your industrial assets after defining your asset models. Select an Active asset model to create an asset from and populate asset-specific information such as data stream aliases and attributes. You will also be able to update and delete existing assets and asset models. Every asset based on that asset model will reflect any changes that you make to the underlying model.

AMC Tracking

 The robust IoT platform helps companies extend their smart products to the Internet by defining certain attributes that are associated with them. In the case of digital warranty, product data models, including warranty-related attributes such as the name of the owner, address, contact details, the location of purchase, date of purchase and detailers of seller and product are available in the cloud. These are exported to develop other applications and devices related to warranty management.

RedRiver has the warranty data of the product attached to it. This is available on the cloud and so product users and manufacturers can access it from anywhere. This enables warranty records to be accessed, transferred, altered, and managed from anywhere by different stakeholders.

Asset Grouping

 Navigate from a list of wind farms to individual turbines and view the past and present details for each turbine.

Asset type management

Each asset requires an asset type. Use asset types to categorize your assets. The asset type defines the sensor types or devices that can be associated with the asset. Asset types also define asset actions for assets belonging to the type and the custom attributes for assets under that type. For an asset type with action power on/off, you can directly switch on or switch off your device’s power from the asset page.

Take the scenario of a hospital. The hospital defines asset types for each of its assets and equipment as follows.

Asset Type: HVAC

Device: HVAC Devices like temperature sensor, vibration sensor, alerts for door opening

Attribute: Device serial number

Actions: Power On/Off

Asset Type: Ultrasound Machine

Device: UM Devices like location sensor

Attribute: Device serial number

Asset Type: Bed

Device: Bluetooth/RFID location sensor

Attribute: Bed Number

Hierarchical Asset Associations

Hierarchical asset associations help link connected assets, whereby you can visualize the hierarchy. Create associated assets in one step. View and edit associated asset types from a single interface.

For example, a truck asset may include associated assets like wheels, engine, and fuel tank. When creating the truck asset type, you can choose to define these associated assets along with their custom and sensor attributes.

The asset types may look like the following:


Attributes: Model, Color


Attributes: Size

Sensor Attributes: Pressure


Attributes: Make, Model

Sensor Attributes: RPM

Fuel Tank

Attributes: Capacity

Sensor Attributes: Fuel Level

Alert Attributes: Low Fuel Alert

Creation of a truck asset automatically creates its required subsets. You will be able to specify the mandatory and optional attributes for creating a truck asset. For sensor attributes, you must associate the attributes to their respective device attributes added in RedRiver.

Whatever your business is, we can create a digital twin of it namely, an organization that enclosed all the IoT-enabled assets as part of your operations. An organization can be treated as a digital placeholder for the various entities in your business. It also holds information about their location, and the users associated with them. The privileged of the users are set in the organization.

Your healthcare or manufacturing or renewables business application contains, more often than not, several organizations. These are classifications done based on technology or geography or verticals. Accordingly, the assets will be slotted in the respective organizations.

The next level of division is the group. Your hierarchical organization can be subdivided into groups. This happens for companies with a range of products. Each product will fall under a group of the organization. Again, a group is an assortment of similar assets. If there are two distinct groups for two products, each will have its own set of assets. Assets can be grouped with a single user or multiple users controlling the asset group. For instance, if you are running an automobile factory, we can group all the wheels under one group. Or the classification could be different, based on all assets on the shop floor, etc.

Hierarchical groups in an organization involves groups and subgroups based on parent-child relationships. A factory can divide assets and create groups based on countries of location. And again, within each country, there can be subgroups based on the factory’s products such as cars, trucks, minivans, etc. The assets contained in a group can be static or dynamic meaning you can add assets manually or use filters to select the assets dynamically. Use a filter group for assets of the same type.

Predictive Maintenance

 Track changes in input and output parameters to improve ROI through effective wind farm monitoring. The data visualized by RedRiver gives you a quick grasp of the complex operating environment.

High-quality data is used in the Machine Learning-based approach to building effective models that provide higher accuracy in predictions. The following factors are to be considered while developing a solution.

  Predictive Maintenance services

Predictive Maintenance services are driven by predictive analytics which is intended to detect and monitor faults and failures in equipment. This helps prevent the possibility of critical failure and downtime. This enables deploying restrained resources and increasing device and equipment lifecycles. In the process, the quality of the supply chain process is advanced.

  Error History

Past maintenance record is key to Predictive maintenance. The algorithm should be fitted data on normal operational and failure patterns when training a model. Therefore, the training dataset should include sufficient training examples on normal and error samples. Records of replacement of parts in the past is a source to collect the necessary error events. The maintenance history contains information including on the repairs that were done and the parts that were replaced. This information helps to get you correct model results. The failure history is also represented by special error codes and parts order dates, helping us know failure patterns. 

 Machine operating conditions

Streaming data of the sensor-based equipment in operation is a source of valuable dataset samples. Predictive Maintenance assumes that the condition of a machine gets worse over time as it performs its daily operations. The data will have features that capture this aging pattern along with the anomalies that lead to degradation. 

 Static feature data

Predictive maintenance also uses static feature data or technical information of the equipment such as the date on which it was built, the model, the start date of service, and the location of the system. RedRiver is a far better alternative to the traditional approach.  The IoT solution is better because mechanism failures are linked to random reasons for 80% of the time and to its age 20% of the time.    With IoT, you can store terabytes of data and run the Machine Learning algorithms on several computers at a time.

 The data captured on the sensors undergo many transitions, eventually going on to create a Predictive Maintenance application that will alert users to potential device and equipment failures. The transitions are the following.

 The key values of the equipment, like temperature and pressure, to be monitored, are identified. A field gateway filters and processes the data before it goes to the Cloud.  A Cloud Gateway receives information from the Field Gateway and allows secure transmission and connectivity with different protocols of field gateways. 

 Data Lake

The data gathered by sensors arrives raw with often irrelevant or inaccurate items. The sets of sensor readings are measured at certain times. When there is a need to have insights from the data stored here, it moves to the Big Data Warehouse. 

 Data Warehouse

Data Warehouse is where the data is cleaned and structured. The data contains the parameters taken by the sensors along with time and information on types, locations, and dates on which the parameters were taken. It is now ready to be fitted into the Machine Learning model. 

 Machine Learning model

In the ML stage, you can reveal the hidden dataset correlations, detect abnormal data patterns, and predict future failures. You will also receive notifications and monitor alerts on potential needs in maintenance through an application.

Get Free Consultation